fix(mcp): validate remote URLs up-front with a clear error

Port from anomalyco/opencode#25019 ("fix: handle invalid mcp urls").

Previously: a typo in `config.yaml` (missing scheme, wrong scheme,
empty string, non-string value) slipped past `_is_http()` and hit
`httpx.URL(url)` or `streamablehttp_client(url, ...)` deep in the
transport layer. That raised a generic exception which went through
the reconnect-backoff loop, so a bad URL caused _MAX_INITIAL_CONNECT_RETRIES
attempts with doubling backoff — about a minute of pointless retries
plus an opaque error — before the server was marked failed.

Now: we validate the URL once, at the top of `run()`, before
entering the retry loop. A malformed URL raises `InvalidMcpUrlError`
(a `ValueError` subclass) with a message that names the offending
server and explains exactly what was wrong. `_ready` is set and
`_error` is populated, so `start()` re-raises and the server shows
up as failed in `hermes mcp list` without any backoff burn.

Validation rules:
- Must be a string (rejects None, dict, int)
- Must be non-empty (rejects '' and whitespace-only)
- Scheme must be http or https (rejects file://, ws://, stdio://)
- Must have a non-empty host (rejects http:///, http://:8080)

Tests (21 new cases in tests/tools/test_mcp_invalid_url.py):
- TestValidUrlsAccepted: http, https, IPv6, ports, paths, query strings
- TestInvalidUrlsRejected: every rejection path above + clear error text
- TestErrorIsValueError: downstream code catching ValueError still works

E2E verified: a misconfigured server with `url: not-a-valid-url`
now fails in <0.001s with the clear error, instead of minutes of retries.

Doesn't touch stdio servers (they use `command`, not `url`) — the
validator only fires when `_is_http()` returns True.

.dockerignore

@@ -9,12 +9,6 @@ node_modules
 .venv
 **/.venv
 
-# Built artifacts that are regenerated inside the image.  Excluded so local
-# rebuilds on the developer's machine don't invalidate the npm-install layer
-# that now depends on the full ui-tui/packages/hermes-ink/ tree being present.
-ui-tui/dist/
-ui-tui/packages/hermes-ink/dist/
-
 # CI/CD
 .github
 

.github/workflows/deploy-site.yml

@@ -76,16 +76,6 @@ jobs:
         run: |
           mkdir -p _site/docs
           cp -r website/build/* _site/docs/
-          # llms.txt / llms-full.txt are also published at the site root
-          # (https://hermes-agent.nousresearch.com/llms.txt) because some
-          # agents and IDE plugins probe the classic root-level path rather
-          # than /docs/llms.txt. Same file, two URLs, one source of truth.
-          if [ -f website/build/llms.txt ]; then
-            cp website/build/llms.txt _site/llms.txt
-          fi
-          if [ -f website/build/llms-full.txt ]; then
-            cp website/build/llms-full.txt _site/llms-full.txt
-          fi
 
       - name: Upload artifact
         uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa  # v3

Dockerfile

@@ -28,26 +28,10 @@ WORKDIR /opt/hermes
 # ---------- Layer-cached dependency install ----------
 # Copy only package manifests first so npm install + Playwright are cached
 # unless the lockfiles themselves change.
-#
-# ui-tui/packages/hermes-ink/ is copied IN FULL (not just its manifests)
-# because it is referenced as a `file:` workspace dependency from
-# ui-tui/package.json.  Copying the tree up front lets npm resolve the
-# workspace to real content instead of stopping at a bare package.json.
 COPY package.json package-lock.json ./
 COPY web/package.json web/package-lock.json web/
 COPY ui-tui/package.json ui-tui/package-lock.json ui-tui/
-COPY ui-tui/packages/hermes-ink/ ui-tui/packages/hermes-ink/
-
-# `npm_config_install_links=false` forces npm to install `file:` deps as
-# symlinks (the npm 10+ default) even on Debian's older bundled npm 9.x,
-# which defaults to `install-links=true` and installs file deps as *copies*.
-# The host-side package-lock.json is generated with a newer npm that uses
-# symlinks, so an install-as-copy produces a hidden node_modules/.package-lock.json
-# that permanently disagrees with the root lock on the @hermes/ink entry.
-# That disagreement trips the TUI launcher's `_tui_need_npm_install()`
-# check on every startup and triggers a runtime `npm install` that then
-# fails with EACCES (node_modules/ is root-owned from build time).
-ENV npm_config_install_links=false
+COPY ui-tui/packages/hermes-ink/package.json ui-tui/packages/hermes-ink/package-lock.json ui-tui/packages/hermes-ink/
 
 RUN npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
@@ -61,7 +45,13 @@ COPY --chown=hermes:hermes . .
 
 # Build browser dashboard and terminal UI assets.
 RUN cd web && npm run build && \
-    cd ../ui-tui && npm run build
+    cd ../ui-tui && npm run build && \
+    rm -rf node_modules/@hermes/ink && \
+    rm -rf packages/hermes-ink/node_modules && \
+    cp -R packages/hermes-ink node_modules/@hermes/ink && \
+    npm install --omit=dev --prefer-offline --no-audit --prefix node_modules/@hermes/ink && \
+    rm -rf node_modules/@hermes/ink/node_modules/react && \
+    node --input-type=module -e "await import('@hermes/ink')"
 
 # ---------- Permissions ----------
 # Make install dir world-readable so any HERMES_UID can read it at runtime.

acp_adapter/server.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import asyncio
 import contextvars
-import json
 import logging
 import os
 from collections import defaultdict, deque
@@ -48,7 +47,6 @@ from acp.schema import (
     TextContentBlock,
     UnstructuredCommandInput,
     Usage,
-    UsageUpdate,
     UserMessageChunk,
 )
 
@@ -67,7 +65,6 @@ from acp_adapter.events import (
 )
 from acp_adapter.permissions import make_approval_callback
 from acp_adapter.session import SessionManager, SessionState, _expand_acp_enabled_toolsets
-from acp_adapter.tools import build_tool_complete, build_tool_start
 
 logger = logging.getLogger(__name__)
 
@@ -167,8 +164,6 @@ class HermesACPAgent(acp.Agent):
         "context": "Show conversation context info",
         "reset": "Clear conversation history",
         "compact": "Compress conversation context",
-        "steer": "Inject guidance into the currently running agent turn",
-        "queue": "Queue a prompt to run after the current turn finishes",
         "version": "Show Hermes version",
     }
 
@@ -198,16 +193,6 @@ class HermesACPAgent(acp.Agent):
             "name": "compact",
             "description": "Compress conversation context",
         },
-        {
-            "name": "steer",
-            "description": "Inject guidance into the currently running agent turn",
-            "input_hint": "guidance for the active turn",
-        },
-        {
-            "name": "queue",
-            "description": "Queue a prompt to run after the current turn finishes",
-            "input_hint": "prompt to run next",
-        },
         {
             "name": "version",
             "description": "Show Hermes version",
@@ -318,66 +303,6 @@ class HermesACPAgent(acp.Agent):
 
         return target_provider, new_model
 
-    @staticmethod
-    def _build_usage_update(state: SessionState) -> UsageUpdate | None:
-        """Build ACP native context-usage data for clients like Zed.
-
-        Zed's circular context indicator is driven by ACP ``usage_update``
-        session updates: ``size`` is the model context window and ``used`` is
-        the current request pressure.  Hermes estimates ``used`` from the same
-        buckets it sends to providers: system prompt, conversation history, and
-        tool schemas.
-        """
-        agent = state.agent
-        compressor = getattr(agent, "context_compressor", None)
-        size = int(getattr(compressor, "context_length", 0) or 0)
-        if size <= 0:
-            return None
-
-        try:
-            from agent.model_metadata import estimate_request_tokens_rough
-
-            used = estimate_request_tokens_rough(
-                state.history,
-                system_prompt=getattr(agent, "_cached_system_prompt", "") or "",
-                tools=getattr(agent, "tools", None) or None,
-            )
-        except Exception:
-            logger.debug("Could not estimate ACP native context usage", exc_info=True)
-            used = int(getattr(compressor, "last_prompt_tokens", 0) or 0)
-
-        return UsageUpdate(
-            session_update="usage_update",
-            size=max(size, 0),
-            used=max(used, 0),
-        )
-
-    async def _send_usage_update(self, state: SessionState) -> None:
-        """Send ACP native context usage to the connected client."""
-        if not self._conn:
-            return
-        update = self._build_usage_update(state)
-        if update is None:
-            return
-        try:
-            await self._conn.session_update(
-                session_id=state.session_id,
-                update=update,
-            )
-        except Exception:
-            logger.warning(
-                "Failed to send ACP usage update for session %s",
-                state.session_id,
-                exc_info=True,
-            )
-
-    def _schedule_usage_update(self, state: SessionState) -> None:
-        """Schedule native context indicator refresh after ACP responses."""
-        if not self._conn:
-            return
-        loop = asyncio.get_running_loop()
-        loop.call_soon(asyncio.create_task, self._send_usage_update(state))
-
     async def _register_session_mcp_servers(
         self,
         state: SessionState,
@@ -548,99 +473,37 @@ class HermesACPAgent(acp.Agent):
             )
         return None
 
-    @staticmethod
-    def _history_tool_call_name_args(tool_call: dict[str, Any]) -> tuple[str, dict[str, Any]]:
-        """Extract function name/arguments from an OpenAI-style tool_call."""
-        function = tool_call.get("function") if isinstance(tool_call.get("function"), dict) else {}
-        name = str(function.get("name") or tool_call.get("name") or "unknown_tool")
-        raw_args = function.get("arguments") or tool_call.get("arguments") or tool_call.get("args") or {}
-        if isinstance(raw_args, str):
-            try:
-                parsed = json.loads(raw_args)
-            except Exception:
-                parsed = {"raw": raw_args}
-            raw_args = parsed
-        if not isinstance(raw_args, dict):
-            raw_args = {}
-        return name, raw_args
-
-    @staticmethod
-    def _history_tool_call_id(tool_call: dict[str, Any]) -> str:
-        """Return the stable provider tool call id for ACP history replay."""
-        return str(
-            tool_call.get("id")
-            or tool_call.get("call_id")
-            or tool_call.get("tool_call_id")
-            or ""
-        ).strip()
-
     async def _replay_session_history(self, state: SessionState) -> None:
         """Send persisted user/assistant history to clients during session/load.
 
         Zed's ACP history UI calls ``session/load`` after the user picks an item
         from the Agents sidebar. The agent must then replay the full conversation
-        as user/assistant chunks plus reconstructed tool-call start/completion
-        notifications; merely restoring server-side state makes Hermes remember
-        context, but leaves the editor looking like a clean thread.
+        as ``user_message_chunk`` / ``agent_message_chunk`` notifications; merely
+        restoring server-side state makes Hermes remember context, but leaves the
+        editor looking like a clean thread.
         """
         if not self._conn or not state.history:
             return
 
-        active_tool_calls: dict[str, tuple[str, dict[str, Any]]] = {}
-
-        async def _send(update: Any) -> bool:
+        for message in state.history:
+            role = str(message.get("role") or "")
+            if role not in {"user", "assistant"}:
+                continue
+            text = self._history_message_text(message)
+            if not text:
+                continue
+            update = self._history_message_update(role=role, text=text)
+            if update is None:
+                continue
             try:
                 await self._conn.session_update(session_id=state.session_id, update=update)
-                return True
             except Exception:
                 logger.warning(
                     "Failed to replay ACP history for session %s",
                     state.session_id,
                     exc_info=True,
                 )
-                return False
-
-        for message in state.history:
-            role = str(message.get("role") or "")
-
-            if role in {"user", "assistant"}:
-                text = self._history_message_text(message)
-                if text:
-                    update = self._history_message_update(role=role, text=text)
-                    if update is not None and not await _send(update):
-                        return
-
-            if role == "assistant" and isinstance(message.get("tool_calls"), list):
-                for tool_call in message["tool_calls"]:
-                    if not isinstance(tool_call, dict):
-                        continue
-                    tool_call_id = self._history_tool_call_id(tool_call)
-                    if not tool_call_id:
-                        continue
-                    tool_name, args = self._history_tool_call_name_args(tool_call)
-                    active_tool_calls[tool_call_id] = (tool_name, args)
-                    if not await _send(build_tool_start(tool_call_id, tool_name, args)):
-                        return
-                continue
-
-            if role == "tool":
-                tool_call_id = str(message.get("tool_call_id") or "").strip()
-                tool_name = str(message.get("tool_name") or "").strip()
-                function_args: dict[str, Any] | None = None
-                if tool_call_id in active_tool_calls:
-                    tool_name, function_args = active_tool_calls.pop(tool_call_id)
-                if not tool_call_id or not tool_name:
-                    continue
-                result = message.get("content")
-                if not await _send(
-                    build_tool_complete(
-                        tool_call_id,
-                        tool_name,
-                        result=result if isinstance(result, str) else None,
-                        function_args=function_args,
-                    )
-                ):
-                    return
+                return
 
     async def new_session(
         self,
@@ -652,24 +515,11 @@ class HermesACPAgent(acp.Agent):
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("New session %s (cwd=%s)", state.session_id, cwd)
         self._schedule_available_commands_update(state.session_id)
-        self._schedule_usage_update(state)
         return NewSessionResponse(
             session_id=state.session_id,
             models=self._build_model_state(state),
         )
 
-    def _schedule_history_replay(self, state: SessionState) -> None:
-        """Replay persisted history after session/load or session/resume returns.
-
-        Zed only attaches streamed transcript/tool updates once the load/resume
-        response has completed. Sending replay notifications while the request is
-        still in-flight can make the server look correct in logs while the editor
-        drops or fails to attach the tool-call history.
-        """
-        loop = asyncio.get_running_loop()
-        replay_coro = self._replay_session_history(state)
-        loop.call_soon(asyncio.create_task, replay_coro)
-
     async def load_session(
         self,
         cwd: str,
@@ -683,9 +533,8 @@ class HermesACPAgent(acp.Agent):
             return None
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Loaded session %s", session_id)
-        self._schedule_history_replay(state)
+        await self._replay_session_history(state)
         self._schedule_available_commands_update(session_id)
-        self._schedule_usage_update(state)
         return LoadSessionResponse(models=self._build_model_state(state))
 
     async def resume_session(
@@ -701,17 +550,13 @@ class HermesACPAgent(acp.Agent):
             state = self.session_manager.create_session(cwd=cwd)
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Resumed session %s", state.session_id)
-        self._schedule_history_replay(state)
+        await self._replay_session_history(state)
         self._schedule_available_commands_update(state.session_id)
-        self._schedule_usage_update(state)
         return ResumeSessionResponse(models=self._build_model_state(state))
 
     async def cancel(self, session_id: str, **kwargs: Any) -> None:
         state = self.session_manager.get_session(session_id)
         if state and state.cancel_event:
-            with state.runtime_lock:
-                if state.is_running and state.current_prompt_text:
-                    state.interrupted_prompt_text = state.current_prompt_text
             state.cancel_event.set()
             try:
                 if getattr(state, "agent", None) and hasattr(state.agent, "interrupt"):
@@ -809,39 +654,6 @@ class HermesACPAgent(acp.Agent):
         if not has_content:
             return PromptResponse(stop_reason="end_turn")
 
-        # /steer on an idle session has no in-flight tool call to inject into.
-        # Rewrite it so the payload runs as a normal user prompt, matching the
-        # gateway's behavior (gateway/run.py ~L4898). Two sub-cases:
-        #   1. Zed-interrupt salvage — a prior prompt was cancelled by the
-        #      client right before /steer arrived; replay it with the steer
-        #      text attached as explicit correction/guidance so the user's
-        #      in-flight work isn't lost.
-        #   2. Plain idle — no prior work to salvage; just run the steer
-        #      payload as a regular prompt. Without this, _cmd_steer would
-        #      silently append to state.queued_prompts and respond with
-        #      "No active turn — queued for the next turn", which looks like
-        #      /queue even though the user never typed /queue.
-        if isinstance(user_content, str) and user_text.startswith("/steer"):
-            steer_text = user_text.split(maxsplit=1)[1].strip() if len(user_text.split(maxsplit=1)) > 1 else ""
-            interrupted_prompt = ""
-            rewrite_idle = False
-            with state.runtime_lock:
-                if not state.is_running and steer_text:
-                    if state.interrupted_prompt_text:
-                        interrupted_prompt = state.interrupted_prompt_text
-                        state.interrupted_prompt_text = ""
-                    else:
-                        rewrite_idle = True
-            if interrupted_prompt:
-                user_text = (
-                    f"{interrupted_prompt}\n\n"
-                    f"User correction/guidance after interrupt: {steer_text}"
-                )
-                user_content = user_text
-            elif rewrite_idle:
-                user_text = steer_text
-                user_content = steer_text
-
         # Intercept slash commands — handle locally without calling the LLM.
         # Slash commands are text-only; if the client included images/resources,
         # send the whole multimodal prompt to the agent instead of treating it as
@@ -852,27 +664,8 @@ class HermesACPAgent(acp.Agent):
                 if self._conn:
                     update = acp.update_agent_message_text(response_text)
                     await self._conn.session_update(session_id, update)
-                    await self._send_usage_update(state)
                 return PromptResponse(stop_reason="end_turn")
 
-        # If Zed sends another regular prompt while the same ACP session is
-        # still running, queue it instead of racing two AIAgent loops against
-        # the same state.history. /steer and /queue are handled above and can
-        # land immediately.
-        with state.runtime_lock:
-            if state.is_running:
-                queued_text = user_text or "[Image attachment]"
-                state.queued_prompts.append(queued_text)
-                depth = len(state.queued_prompts)
-                if self._conn:
-                    update = acp.update_agent_message_text(
-                        f"Queued for the next turn. ({depth} queued)"
-                    )
-                    await self._conn.session_update(session_id, update)
-                return PromptResponse(stop_reason="end_turn")
-            state.is_running = True
-            state.current_prompt_text = user_text or "[Image attachment]"
-
         logger.info("Prompt on session %s: %s", session_id, user_text[:100])
 
         conn = self._conn
@@ -885,37 +678,24 @@ class HermesACPAgent(acp.Agent):
         tool_call_meta: dict[str, dict[str, Any]] = {}
         previous_approval_cb = None
 
-        streamed_message = False
-
         if conn:
             tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
-            reasoning_cb = make_thinking_cb(conn, session_id, loop)
+            thinking_cb = make_thinking_cb(conn, session_id, loop)
             step_cb = make_step_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
             message_cb = make_message_cb(conn, session_id, loop)
-
-            def stream_delta_cb(text: str) -> None:
-                nonlocal streamed_message
-                if text:
-                    streamed_message = True
-                message_cb(text)
-
             approval_cb = make_approval_callback(conn.request_permission, loop, session_id)
         else:
             tool_progress_cb = None
-            reasoning_cb = None
+            thinking_cb = None
             step_cb = None
-            stream_delta_cb = None
+            message_cb = None
             approval_cb = None
 
         agent = state.agent
         agent.tool_progress_callback = tool_progress_cb
-        # ACP thought panes should not receive Hermes' local kawaii waiting/status
-        # updates. Route provider/model reasoning deltas instead; if the provider
-        # emits no reasoning, Zed should not get a fake "thinking" accordion.
-        agent.thinking_callback = None
-        agent.reasoning_callback = reasoning_cb
+        agent.thinking_callback = thinking_cb
         agent.step_callback = step_cb
-        agent.stream_delta_callback = stream_delta_cb
+        agent.message_callback = message_cb
 
         # Approval callback is per-thread (thread-local, GHSA-qg5c-hvr5-hjgr).
         # Set it INSIDE _run_agent so the TLS write happens in the executor
@@ -997,9 +777,6 @@ class HermesACPAgent(acp.Agent):
             result = await loop.run_in_executor(_executor, ctx.run, _run_agent)
         except Exception:
             logger.exception("Executor error for session %s", session_id)
-            with state.runtime_lock:
-                state.is_running = False
-                state.current_prompt_text = ""
             return PromptResponse(stop_reason="end_turn")
 
         if result.get("messages"):
@@ -1021,32 +798,10 @@ class HermesACPAgent(acp.Agent):
                 )
             except Exception:
                 logger.debug("Failed to auto-title ACP session %s", session_id, exc_info=True)
-        if final_response and conn and not streamed_message:
+        if final_response and conn:
             update = acp.update_agent_message_text(final_response)
             await conn.session_update(session_id, update)
 
-        # Mark this turn idle before draining queued work so recursive prompt()
-        # calls can acquire the session. Queued turns are intentionally run as
-        # normal follow-up user prompts, preserving role alternation and history.
-        with state.runtime_lock:
-            state.is_running = False
-            state.current_prompt_text = ""
-
-        while True:
-            with state.runtime_lock:
-                if not state.queued_prompts:
-                    break
-                next_prompt = state.queued_prompts.pop(0)
-            if conn:
-                await conn.session_update(
-                    session_id,
-                    acp.update_user_message_text(next_prompt),
-                )
-            await self.prompt(
-                prompt=[TextContentBlock(type="text", text=next_prompt)],
-                session_id=session_id,
-            )
-
         usage = None
         if any(result.get(key) is not None for key in ("prompt_tokens", "completion_tokens", "total_tokens")):
             usage = Usage(
@@ -1057,8 +812,6 @@ class HermesACPAgent(acp.Agent):
                 cached_read_tokens=result.get("cache_read_tokens"),
             )
 
-        await self._send_usage_update(state)
-
         stop_reason = "cancelled" if state.cancel_event and state.cancel_event.is_set() else "end_turn"
         return PromptResponse(stop_reason=stop_reason, usage=usage)
 
@@ -1126,8 +879,6 @@ class HermesACPAgent(acp.Agent):
             "context": self._cmd_context,
             "reset": self._cmd_reset,
             "compact": self._cmd_compact,
-            "steer": self._cmd_steer,
-            "queue": self._cmd_queue,
             "version": self._cmd_version,
         }.get(cmd)
 
@@ -1191,84 +942,22 @@ class HermesACPAgent(acp.Agent):
             return f"Could not list tools: {e}"
 
     def _cmd_context(self, args: str, state: SessionState) -> str:
-        """Show ACP session context pressure and compression guidance."""
         n_messages = len(state.history)
-
-        # Count by role.
+        if n_messages == 0:
+            return "Conversation is empty (no messages yet)."
+        # Count by role
         roles: dict[str, int] = {}
         for msg in state.history:
             role = msg.get("role", "unknown")
             roles[role] = roles.get(role, 0) + 1
-
-        agent = state.agent
-        model = state.model or getattr(agent, "model", "")
-        provider = getattr(agent, "provider", None) or "auto"
-        compressor = getattr(agent, "context_compressor", None)
-        context_length = int(getattr(compressor, "context_length", 0) or 0)
-        threshold_tokens = int(getattr(compressor, "threshold_tokens", 0) or 0)
-
-        try:
-            from agent.model_metadata import estimate_request_tokens_rough
-
-            system_prompt = getattr(agent, "_cached_system_prompt", "") or ""
-            tools = getattr(agent, "tools", None) or None
-            approx_tokens = estimate_request_tokens_rough(
-                state.history,
-                system_prompt=system_prompt,
-                tools=tools,
-            )
-        except Exception:
-            logger.debug("Could not estimate ACP context usage", exc_info=True)
-            approx_tokens = 0
-
-        if threshold_tokens <= 0 and context_length > 0:
-            threshold_tokens = int(context_length * 0.80)
-
         lines = [
-            f"Conversation: {n_messages} messages"
-            if n_messages
-            else "Conversation is empty (no messages yet).",
+            f"Conversation: {n_messages} messages",
             f"  user: {roles.get('user', 0)}, assistant: {roles.get('assistant', 0)}, "
             f"tool: {roles.get('tool', 0)}, system: {roles.get('system', 0)}",
         ]
+        model = state.model or getattr(state.agent, "model", "")
         if model:
             lines.append(f"Model: {model}")
-        lines.append(f"Provider: {provider}")
-
-        if approx_tokens > 0:
-            if context_length > 0:
-                usage_pct = (approx_tokens / context_length) * 100
-                lines.append(
-                    f"Context usage: ~{approx_tokens:,} / {context_length:,} tokens ({usage_pct:.1f}%)"
-                )
-            else:
-                lines.append(f"Context usage: ~{approx_tokens:,} tokens")
-
-        if threshold_tokens > 0:
-            if approx_tokens > 0:
-                threshold_pct = (threshold_tokens / context_length) * 100 if context_length > 0 else 0
-                remaining = max(threshold_tokens - approx_tokens, 0)
-                if approx_tokens >= threshold_tokens:
-                    lines.append(
-                        f"Compression: due now (threshold ~{threshold_tokens:,}"
-                        + (f", {threshold_pct:.0f}%" if threshold_pct else "")
-                        + "). Run /compact."
-                    )
-                else:
-                    lines.append(
-                        f"Compression: ~{remaining:,} tokens until threshold "
-                        f"(~{threshold_tokens:,}"
-                        + (f", {threshold_pct:.0f}%" if threshold_pct else "")
-                        + ")."
-                    )
-            else:
-                lines.append(f"Compression threshold: ~{threshold_tokens:,} tokens")
-
-        if getattr(agent, "compression_enabled", True) is False:
-            lines.append("Compression is disabled for this agent.")
-        else:
-            lines.append("Tip: run /compact to compress manually before the threshold.")
-
         return "\n".join(lines)
 
     def _cmd_reset(self, args: str, state: SessionState) -> str:
@@ -1286,16 +975,10 @@ class HermesACPAgent(acp.Agent):
             if not hasattr(agent, "_compress_context"):
                 return "Context compression not available for this agent."
 
-            from agent.model_metadata import estimate_request_tokens_rough
+            from agent.model_metadata import estimate_messages_tokens_rough
 
             original_count = len(state.history)
-            # Include system prompt + tool schemas so the figure reflects real
-            # request pressure, not a transcript-only underestimate (#6217).
-            _sys_prompt = getattr(agent, "_cached_system_prompt", "") or ""
-            _tools = getattr(agent, "tools", None) or None
-            approx_tokens = estimate_request_tokens_rough(
-                state.history, system_prompt=_sys_prompt, tools=_tools
-            )
+            approx_tokens = estimate_messages_tokens_rough(state.history)
             original_session_db = getattr(agent, "_session_db", None)
 
             try:
@@ -1315,13 +998,7 @@ class HermesACPAgent(acp.Agent):
             self.session_manager.save_session(state.session_id)
 
             new_count = len(state.history)
-            _sys_prompt_after = getattr(agent, "_cached_system_prompt", "") or _sys_prompt
-            _tools_after = getattr(agent, "tools", None) or _tools
-            new_tokens = estimate_request_tokens_rough(
-                state.history,
-                system_prompt=_sys_prompt_after,
-                tools=_tools_after,
-            )
+            new_tokens = estimate_messages_tokens_rough(state.history)
             return (
                 f"Context compressed: {original_count} -> {new_count} messages\n"
                 f"~{approx_tokens:,} -> ~{new_tokens:,} tokens"
@@ -1329,34 +1006,6 @@ class HermesACPAgent(acp.Agent):
         except Exception as e:
             return f"Compression failed: {e}"
 
-    def _cmd_steer(self, args: str, state: SessionState) -> str:
-        steer_text = args.strip()
-        if not steer_text:
-            return "Usage: /steer <guidance>"
-
-        if state.is_running and hasattr(state.agent, "steer"):
-            try:
-                if state.agent.steer(steer_text):
-                    preview = steer_text[:80] + ("..." if len(steer_text) > 80 else "")
-                    return f"⏩ Steer queued for the active turn: {preview}"
-            except Exception as exc:
-                logger.warning("ACP steer failed for session %s: %s", state.session_id, exc)
-                return f"⚠️ Steer failed: {exc}"
-
-        with state.runtime_lock:
-            state.queued_prompts.append(steer_text)
-            depth = len(state.queued_prompts)
-        return f"No active turn — queued for the next turn. ({depth} queued)"
-
-    def _cmd_queue(self, args: str, state: SessionState) -> str:
-        queued_text = args.strip()
-        if not queued_text:
-            return "Usage: /queue <prompt>"
-        with state.runtime_lock:
-            state.queued_prompts.append(queued_text)
-            depth = len(state.queued_prompts)
-        return f"Queued for the next turn. ({depth} queued)"
-
     def _cmd_version(self, args: str, state: SessionState) -> str:
         return f"Hermes Agent v{HERMES_VERSION}"
 

acp_adapter/session.py

@@ -26,33 +26,6 @@ from typing import Any, Dict, List, Optional
 logger = logging.getLogger(__name__)
 
 
-def _win_path_to_wsl(path: str) -> str | None:
-    """Convert a Windows drive path to its WSL /mnt/<drive>/... equivalent."""
-    match = re.match(r"^([A-Za-z]):[\\/](.*)$", path)
-    if not match:
-        return None
-    drive = match.group(1).lower()
-    tail = match.group(2).replace("\\", "/")
-    return f"/mnt/{drive}/{tail}"
-
-
-def _translate_acp_cwd(cwd: str) -> str:
-    """Translate Windows ACP cwd values when Hermes itself is running in WSL.
-
-    Windows ACP clients can launch ``hermes acp`` inside WSL while still sending
-    editor workspaces as Windows drive paths such as ``E:\\Projects``. Store
-    and execute against the WSL mount path so agents, tools, and persisted ACP
-    sessions all agree on the usable workspace. Native Linux/macOS keeps the
-    original cwd unchanged.
-    """
-    from hermes_constants import is_wsl
-
-    if not is_wsl():
-        return cwd
-    translated = _win_path_to_wsl(str(cwd))
-    return translated if translated is not None else cwd
-
-
 def _normalize_cwd_for_compare(cwd: str | None) -> str:
     raw = str(cwd or ".").strip()
     if not raw:
@@ -61,9 +34,11 @@ def _normalize_cwd_for_compare(cwd: str | None) -> str:
 
     # Normalize Windows drive paths into the equivalent WSL mount form so
     # ACP history filters match the same workspace across Windows and WSL.
-    translated = _win_path_to_wsl(expanded)
-    if translated is not None:
-        expanded = translated
+    match = re.match(r"^([A-Za-z]):[\\/](.*)$", expanded)
+    if match:
+        drive = match.group(1).lower()
+        tail = match.group(2).replace("\\", "/")
+        expanded = f"/mnt/{drive}/{tail}"
     elif re.match(r"^/mnt/[A-Za-z]/", expanded):
         expanded = f"/mnt/{expanded[5].lower()}/{expanded[7:]}"
 
@@ -121,18 +96,12 @@ def _acp_stderr_print(*args, **kwargs) -> None:
 
 
 def _register_task_cwd(task_id: str, cwd: str) -> None:
-    """Bind a task/session id to the editor's working directory for tools.
-
-    Zed can launch Hermes from a Windows workspace while the ACP process runs
-    inside WSL. In that case ACP sends cwd as e.g. ``E:\\Projects\\POTI``;
-    local tools need the WSL mount equivalent or subprocess creation fails
-    before the command can run.
-    """
+    """Bind a task/session id to the editor's working directory for tools."""
     if not task_id:
         return
     try:
         from tools.terminal_tool import register_task_env_overrides
-        register_task_env_overrides(task_id, {"cwd": _translate_acp_cwd(cwd)})
+        register_task_env_overrides(task_id, {"cwd": cwd})
     except Exception:
         logger.debug("Failed to register ACP task cwd override", exc_info=True)
 
@@ -176,11 +145,6 @@ class SessionState:
     model: str = ""
     history: List[Dict[str, Any]] = field(default_factory=list)
     cancel_event: Any = None  # threading.Event
-    is_running: bool = False
-    queued_prompts: List[str] = field(default_factory=list)
-    runtime_lock: Any = field(default_factory=Lock)
-    current_prompt_text: str = ""
-    interrupted_prompt_text: str = ""
 
 
 class SessionManager:
@@ -211,7 +175,6 @@ class SessionManager:
         """Create a new session with a unique ID and a fresh AIAgent."""
         import threading
 
-        cwd = _translate_acp_cwd(cwd)
         session_id = str(uuid.uuid4())
         agent = self._make_agent(session_id=session_id, cwd=cwd)
         state = SessionState(
@@ -254,7 +217,6 @@ class SessionManager:
         """Deep-copy a session's history into a new session."""
         import threading
 
-        cwd = _translate_acp_cwd(cwd)
         original = self.get_session(session_id)  # checks DB too
         if original is None:
             return None
@@ -356,7 +318,6 @@ class SessionManager:
 
     def update_cwd(self, session_id: str, cwd: str) -> Optional[SessionState]:
         """Update the working directory for a session and its tool overrides."""
-        cwd = _translate_acp_cwd(cwd)
         state = self.get_session(session_id)  # checks DB too
         if state is None:
             return None

acp_adapter/tools.py

@@ -28,11 +28,6 @@ TOOL_KIND_MAP: Dict[str, ToolKind] = {
     "terminal": "execute",
     "process": "execute",
     "execute_code": "execute",
-    # Session/meta tools
-    "todo": "other",
-    "skill_view": "read",
-    "skills_list": "read",
-    "skill_manage": "edit",
     # Web / fetch
     "web_search": "fetch",
     "web_extract": "fetch",
@@ -56,28 +51,6 @@ TOOL_KIND_MAP: Dict[str, ToolKind] = {
 }
 
 
-_POLISHED_TOOLS = {
-    # Core operator loop
-    "todo", "memory", "session_search", "delegate_task",
-    # Files / execution
-    "read_file", "write_file", "patch", "search_files", "terminal", "process", "execute_code",
-    # Skills / web / browser / media
-    "skill_view", "skills_list", "skill_manage", "web_search", "web_extract",
-    "browser_navigate", "browser_click", "browser_type", "browser_press", "browser_scroll",
-    "browser_back", "browser_snapshot", "browser_console", "browser_get_images", "browser_vision",
-    "vision_analyze", "image_generate", "text_to_speech",
-    # Schedulers / platform integrations
-    "cronjob", "send_message", "clarify", "discord", "discord_admin",
-    "ha_list_entities", "ha_get_state", "ha_list_services", "ha_call_service",
-    "feishu_doc_read", "feishu_drive_list_comments", "feishu_drive_list_comment_replies",
-    "feishu_drive_reply_comment", "feishu_drive_add_comment",
-    "kanban_create", "kanban_show", "kanban_comment", "kanban_complete",
-    "kanban_block", "kanban_link", "kanban_heartbeat",
-    "yb_query_group_info", "yb_query_group_members", "yb_search_sticker",
-    "yb_send_dm", "yb_send_sticker", "mixture_of_agents",
-}
-
-
 def get_tool_kind(tool_name: str) -> ToolKind:
     """Return the ACP ToolKind for a hermes tool, defaulting to 'other'."""
     return TOOL_KIND_MAP.get(tool_name, "other")
@@ -112,645 +85,18 @@ def build_tool_title(tool_name: str, args: Dict[str, Any]) -> str:
         if urls:
             return f"extract: {urls[0]}" + (f" (+{len(urls)-1})" if len(urls) > 1 else "")
         return "web extract"
-    if tool_name == "process":
-        action = str(args.get("action") or "").strip() or "manage"
-        sid = str(args.get("session_id") or "").strip()
-        return f"process {action}: {sid}" if sid else f"process {action}"
     if tool_name == "delegate_task":
-        tasks = args.get("tasks")
-        if isinstance(tasks, list) and tasks:
-            return f"delegate batch ({len(tasks)} tasks)"
         goal = args.get("goal", "")
         if goal and len(goal) > 60:
             goal = goal[:57] + "..."
         return f"delegate: {goal}" if goal else "delegate task"
-    if tool_name == "session_search":
-        query = str(args.get("query") or "").strip()
-        return f"session search: {query}" if query else "recent sessions"
-    if tool_name == "memory":
-        action = str(args.get("action") or "manage").strip() or "manage"
-        target = str(args.get("target") or "memory").strip() or "memory"
-        return f"memory {action}: {target}"
     if tool_name == "execute_code":
-        code = str(args.get("code") or "").strip()
-        first_line = next((line.strip() for line in code.splitlines() if line.strip()), "")
-        if first_line:
-            if len(first_line) > 70:
-                first_line = first_line[:67] + "..."
-            return f"python: {first_line}"
-        return "python code"
-    if tool_name == "todo":
-        items = args.get("todos")
-        if isinstance(items, list):
-            return f"todo ({len(items)} item{'s' if len(items) != 1 else ''})"
-        return "todo"
-    if tool_name == "skill_view":
-        name = str(args.get("name") or "?").strip() or "?"
-        file_path = str(args.get("file_path") or "").strip()
-        suffix = f"/{file_path}" if file_path else ""
-        return f"skill view ({name}{suffix})"
-    if tool_name == "skills_list":
-        category = str(args.get("category") or "").strip()
-        return f"skills list ({category})" if category else "skills list"
-    if tool_name == "skill_manage":
-        action = str(args.get("action") or "manage").strip() or "manage"
-        name = str(args.get("name") or "?").strip() or "?"
-        file_path = str(args.get("file_path") or "").strip()
-        target = f"{name}/{file_path}" if file_path else name
-        if len(target) > 64:
-            target = target[:61] + "..."
-        return f"skill {action}: {target}"
-    if tool_name == "browser_navigate":
-        return f"navigate: {args.get('url', '?')}"
-    if tool_name == "browser_snapshot":
-        return "browser snapshot"
-    if tool_name == "browser_vision":
-        return f"browser vision: {str(args.get('question', '?'))[:50]}"
-    if tool_name == "browser_get_images":
-        return "browser images"
+        return "execute code"
     if tool_name == "vision_analyze":
-        return f"analyze image: {str(args.get('question', '?'))[:50]}"
-    if tool_name == "image_generate":
-        prompt = str(args.get("prompt") or args.get("description") or "").strip()
-        return f"generate image: {prompt[:50]}" if prompt else "generate image"
-    if tool_name == "cronjob":
-        action = str(args.get("action") or "manage").strip() or "manage"
-        job_id = str(args.get("job_id") or args.get("id") or "").strip()
-        return f"cron {action}: {job_id}" if job_id else f"cron {action}"
+        return f"analyze image: {args.get('question', '?')[:50]}"
     return tool_name
 
 
-def _text(content: str) -> Any:
-    return acp.tool_content(acp.text_block(content))
-
-
-def _json_loads_maybe(value: Optional[str]) -> Any:
-    if not isinstance(value, str):
-        return value
-    try:
-        return json.loads(value)
-    except Exception:
-        pass
-
-    # Some Hermes tools append a human hint after a JSON payload, e.g.
-    # ``{...}\n\n[Hint: Results truncated...]``. Keep the structured rendering path
-    # by decoding the first JSON value instead of falling back to raw text.
-    try:
-        decoded, _ = json.JSONDecoder().raw_decode(value.lstrip())
-        return decoded
-    except Exception:
-        return None
-
-
-def _truncate_text(text: str, limit: int = 5000) -> str:
-    if len(text) <= limit:
-        return text
-    return text[: max(0, limit - 100)] + f"\n... ({len(text)} chars total, truncated)"
-
-
-def _fenced_text(text: str, language: str = "") -> str:
-    """Return a Markdown fence that cannot be broken by backticks in text."""
-    longest = max((len(run) for run in text.split("`")[1::2]), default=0)
-    fence = "`" * max(3, longest + 1)
-    return f"{fence}{language}\n{text}\n{fence}"
-
-
-def _format_todo_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict) or not isinstance(data.get("todos"), list):
-        return None
-    summary = data.get("summary") if isinstance(data.get("summary"), dict) else {}
-    icon = {
-        "completed": "✅",
-        "in_progress": "🔄",
-        "pending": "⏳",
-        "cancelled": "✗",
-    }
-    lines = ["**Todo list**", ""]
-    for item in data["todos"]:
-        if not isinstance(item, dict):
-            continue
-        status = str(item.get("status") or "pending")
-        content = str(item.get("content") or item.get("id") or "").strip()
-        if content:
-            lines.append(f"- {icon.get(status, '•')} {content}")
-    if summary:
-        cancelled = summary.get("cancelled", 0)
-        lines.extend([
-            "",
-            "**Progress:** "
-            f"{summary.get('completed', 0)} completed, "
-            f"{summary.get('in_progress', 0)} in progress, "
-            f"{summary.get('pending', 0)} pending"
-            + (f", {cancelled} cancelled" if cancelled else ""),
-        ])
-    return "\n".join(lines)
-
-
-def _format_read_file_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    if data.get("error") and not data.get("content"):
-        return f"Read failed: {data.get('error')}"
-    content = data.get("content")
-    if not isinstance(content, str):
-        return None
-    path = str((args or {}).get("path") or data.get("path") or "file").strip()
-    offset = (args or {}).get("offset")
-    limit = (args or {}).get("limit")
-    range_bits = []
-    if offset:
-        range_bits.append(f"from line {offset}")
-    if limit:
-        range_bits.append(f"limit {limit}")
-    suffix = f" ({', '.join(range_bits)})" if range_bits else ""
-    header = f"Read {path}{suffix}"
-    if data.get("total_lines") is not None:
-        header += f" — {data.get('total_lines')} total lines"
-    # Hermes read_file output is line-numbered with `|`. If we send it as raw
-    # Markdown, Zed can interpret pipes as tables and collapse the layout.
-    # Fence the payload so file lines stay readable and literal.
-    return _truncate_text(f"{header}\n\n{_fenced_text(content)}")
-
-
-def _format_search_files_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    matches = data.get("matches")
-    if not isinstance(matches, list):
-        return None
-
-    total = data.get("total_count", len(matches))
-    shown = min(len(matches), 12)
-    truncated = bool(data.get("truncated")) or len(matches) > shown
-    lines = [
-        "Search results",
-        f"Found {total} match{'es' if total != 1 else ''}; showing {shown}.",
-        "",
-    ]
-
-    for match in matches[:shown]:
-        if not isinstance(match, dict):
-            lines.append(f"- {match}")
-            continue
-
-        path = str(match.get("path") or match.get("file") or match.get("filename") or "?")
-        line = match.get("line") or match.get("line_number")
-        content = str(match.get("content") or match.get("text") or "").strip()
-        loc = f"{path}:{line}" if line else path
-        lines.append(f"- {loc}")
-        if content:
-            snippet = _truncate_text(" ".join(content.split()), 300)
-            lines.append(f"  {snippet}")
-
-    if truncated:
-        lines.extend([
-            "",
-            "Results truncated. Narrow the search, add file_glob, or use offset to page.",
-        ])
-    return _truncate_text("\n".join(lines), limit=7000)
-
-
-def _format_execute_code_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return result if isinstance(result, str) and result.strip() else None
-    output = str(data.get("output") or "")
-    error = str(data.get("error") or "")
-    exit_code = data.get("exit_code")
-    parts = [f"Exit code: {exit_code}" if exit_code is not None else "Execution complete"]
-    if output:
-        parts.extend(["", "Output:", output])
-    if error:
-        parts.extend(["", "Error:", error])
-    return _truncate_text("\n".join(parts))
-
-
-def _extract_markdown_headings(content: str, limit: int = 8) -> list[str]:
-    headings: list[str] = []
-    for line in content.splitlines():
-        stripped = line.strip()
-        if stripped.startswith("#"):
-            heading = stripped.lstrip("#").strip()
-            if heading:
-                headings.append(heading)
-        if len(headings) >= limit:
-            break
-    return headings
-
-
-def _format_skill_view_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    if data.get("success") is False:
-        return f"Skill view failed: {data.get('error', 'unknown error')}"
-    name = str(data.get("name") or "skill")
-    file_path = str(data.get("file") or data.get("path") or "SKILL.md")
-    description = str(data.get("description") or "").strip()
-    content = str(data.get("content") or "")
-    linked = data.get("linked_files") if isinstance(data.get("linked_files"), dict) else None
-
-    lines = ["**Skill loaded**", "", f"- **Name:** `{name}`", f"- **File:** `{file_path}`"]
-    if description:
-        lines.append(f"- **Description:** {description}")
-    if content:
-        lines.append(f"- **Content:** {len(content):,} chars loaded into agent context")
-    if linked:
-        linked_count = sum(len(v) for v in linked.values() if isinstance(v, list))
-        lines.append(f"- **Linked files:** {linked_count}")
-
-    headings = _extract_markdown_headings(content)
-    if headings:
-        lines.extend(["", "**Sections**"])
-        lines.extend(f"- {heading}" for heading in headings)
-
-    lines.extend([
-        "",
-        "_Full skill content is available to the agent but hidden here to keep ACP readable._",
-    ])
-    return "\n".join(lines)
-
-
-def _format_skill_manage_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-
-    action = str((args or {}).get("action") or "manage").strip() or "manage"
-    name = str((args or {}).get("name") or data.get("name") or "skill").strip() or "skill"
-    file_path = str((args or {}).get("file_path") or data.get("file_path") or "SKILL.md").strip() or "SKILL.md"
-    success = data.get("success")
-    status = "✅ Skill updated" if success is not False else "✗ Skill update failed"
-
-    lines = [f"**{status}**", "", f"- **Action:** `{action}`", f"- **Skill:** `{name}`"]
-    if action not in {"delete"}:
-        lines.append(f"- **File:** `{file_path}`")
-
-    message = str(data.get("message") or data.get("error") or "").strip()
-    if message:
-        lines.append(f"- **Result:** {message}")
-
-    replacements = data.get("replacements") or data.get("replacement_count")
-    if replacements is not None:
-        lines.append(f"- **Replacements:** {replacements}")
-
-    path = str(data.get("path") or "").strip()
-    if path:
-        lines.append(f"- **Path:** `{path}`")
-
-    return "\n".join(lines)
-
-
-def _format_web_search_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    web = data.get("data", {}).get("web") if isinstance(data.get("data"), dict) else data.get("web")
-    if not isinstance(web, list):
-        return None
-    lines = [f"Web results: {len(web)}"]
-    for item in web[:10]:
-        if not isinstance(item, dict):
-            continue
-        title = str(item.get("title") or item.get("url") or "result").strip()
-        url = str(item.get("url") or "").strip()
-        desc = str(item.get("description") or "").strip()
-        lines.append(f"• {title}" + (f" — {url}" if url else ""))
-        if desc:
-            lines.append(f"  {desc}")
-    return _truncate_text("\n".join(lines))
-
-
-def _format_web_extract_result(result: Optional[str]) -> Optional[str]:
-    """Return only web_extract errors for ACP; success stays compact via title."""
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    if data.get("success") is False and data.get("error"):
-        return f"Web extract failed: {data.get('error')}"
-    results = data.get("results")
-    if not isinstance(results, list):
-        return None
-
-    failures: list[str] = []
-    for item in results[:10]:
-        if not isinstance(item, dict):
-            continue
-        error = str(item.get("error") or "").strip()
-        if not error or error in {"None", "null"}:
-            continue
-        url = str(item.get("url") or "").strip()
-        title = str(item.get("title") or url or "Untitled").strip()
-        failures.append(
-            f"- {title}" + (f" — {url}" if url and url != title else "") + f"\n  Error: {_truncate_text(error, limit=500)}"
-        )
-
-    if not failures:
-        return None
-    lines = [f"Web extract failed for {len(failures)} URL{'s' if len(failures) != 1 else ''}"]
-    lines.extend(failures)
-    return "\n".join(lines)
-
-
-def _format_process_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return result if isinstance(result, str) and result.strip() else None
-    if data.get("success") is False and data.get("error"):
-        return f"Process error: {data.get('error')}"
-    action = str((args or {}).get("action") or "process").strip() or "process"
-    if isinstance(data.get("processes"), list):
-        processes = data["processes"]
-        lines = [f"Processes: {len(processes)}"]
-        for proc in processes[:20]:
-            if not isinstance(proc, dict):
-                lines.append(f"- {proc}")
-                continue
-            sid = str(proc.get("session_id") or proc.get("id") or "?")
-            status = str(proc.get("status") or ("exited" if proc.get("exited") else "running"))
-            cmd = str(proc.get("command") or "").strip()
-            pid = proc.get("pid")
-            code = proc.get("exit_code")
-            bits = [status]
-            if pid is not None:
-                bits.append(f"pid {pid}")
-            if code is not None:
-                bits.append(f"exit {code}")
-            lines.append(f"- `{sid}` — {', '.join(bits)}" + (f" — {cmd[:120]}" if cmd else ""))
-        if len(processes) > 20:
-            lines.append(f"... {len(processes) - 20} more process(es)")
-        return "\n".join(lines)
-
-    status = str(data.get("status") or data.get("state") or action).strip()
-    sid = str(data.get("session_id") or (args or {}).get("session_id") or "").strip()
-    lines = [f"Process {action}: {status}" + (f" (`{sid}`)" if sid else "")]
-    for key, label in (("command", "Command"), ("pid", "PID"), ("exit_code", "Exit code"), ("returncode", "Exit code"), ("lines", "Lines")):
-        if data.get(key) is not None:
-            lines.append(f"- **{label}:** {data.get(key)}")
-    output = data.get("output") or data.get("new_output") or data.get("log") or data.get("stdout")
-    error = data.get("error") or data.get("stderr")
-    if output:
-        lines.extend(["", "Output:", _truncate_text(str(output), limit=5000)])
-    if error:
-        lines.extend(["", "Error:", _truncate_text(str(error), limit=2000)])
-    msg = data.get("message")
-    if msg and not output and not error:
-        lines.append(str(msg))
-    return _truncate_text("\n".join(lines), limit=7000)
-
-
-def _format_delegate_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    if data.get("error") and not isinstance(data.get("results"), list):
-        return f"Delegation failed: {data.get('error')}"
-    results = data.get("results")
-    if not isinstance(results, list):
-        return None
-    total = data.get("total_duration_seconds")
-    lines = [f"Delegation results: {len(results)} task{'s' if len(results) != 1 else ''}" + (f" in {total}s" if total is not None else "")]
-    icon = {"completed": "✅", "failed": "✗", "error": "✗", "timeout": "⏱", "interrupted": "⚠"}
-    for item in results:
-        if not isinstance(item, dict):
-            lines.append(f"- {item}")
-            continue
-        idx = item.get("task_index")
-        status = str(item.get("status") or "unknown")
-        model = item.get("model")
-        dur = item.get("duration_seconds")
-        role = item.get("_child_role")
-        header = f"{icon.get(status, '•')} Task {idx + 1 if isinstance(idx, int) else '?'}: {status}"
-        bits = []
-        if model:
-            bits.append(str(model))
-        if role:
-            bits.append(f"role={role}")
-        if dur is not None:
-            bits.append(f"{dur}s")
-        if bits:
-            header += " (" + ", ".join(bits) + ")"
-        lines.extend(["", header])
-        summary = str(item.get("summary") or "").strip()
-        error = str(item.get("error") or "").strip()
-        if summary:
-            lines.append(_truncate_text(summary, limit=1200))
-        if error:
-            lines.append("Error: " + _truncate_text(error, limit=800))
-        trace = item.get("tool_trace")
-        if isinstance(trace, list) and trace:
-            names = [str(t.get("tool") or "?") for t in trace if isinstance(t, dict)]
-            if names:
-                lines.append("Tools: " + ", ".join(names[:12]) + (f" (+{len(names)-12})" if len(names) > 12 else ""))
-    return _truncate_text("\n".join(lines), limit=8000)
-
-
-def _format_session_search_result(result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    if data.get("success") is False:
-        return f"Session search failed: {data.get('error', 'unknown error')}"
-    results = data.get("results")
-    if not isinstance(results, list):
-        return None
-    mode = data.get("mode") or "search"
-    query = data.get("query")
-    lines = ["Recent sessions" if mode == "recent" else f"Session search results" + (f" for `{query}`" if query else "")]
-    if not results:
-        lines.append(str(data.get("message") or "No matching sessions found."))
-        return "\n".join(lines)
-    for item in results:
-        if not isinstance(item, dict):
-            continue
-        sid = str(item.get("session_id") or "?")
-        title = str(item.get("title") or item.get("when") or "Untitled session").strip()
-        when = str(item.get("last_active") or item.get("started_at") or item.get("when") or "").strip()
-        count = item.get("message_count")
-        source = str(item.get("source") or "").strip()
-        meta = ", ".join(str(x) for x in [when, source, f"{count} msgs" if count is not None else ""] if x)
-        lines.append(f"- **{title}** (`{sid}`)" + (f" — {meta}" if meta else ""))
-        summary = str(item.get("summary") or item.get("preview") or "").strip()
-        if summary:
-            lines.append("  " + _truncate_text(" ".join(summary.split()), limit=500))
-    return _truncate_text("\n".join(lines), limit=7000)
-
-
-def _format_memory_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return None
-    action = str((args or {}).get("action") or "memory").strip() or "memory"
-    target = str(data.get("target") or (args or {}).get("target") or "memory")
-    if data.get("success") is False:
-        lines = [f"✗ Memory {action} failed ({target})", str(data.get("error") or "unknown error")]
-        matches = data.get("matches")
-        if isinstance(matches, list) and matches:
-            lines.append("Matches:")
-            lines.extend(f"- {_truncate_text(str(m), 160)}" for m in matches[:5])
-        return "\n".join(lines)
-    lines = [f"✅ Memory {action} saved ({target})"]
-    if data.get("message"):
-        lines.append(str(data.get("message")))
-    if data.get("entry_count") is not None:
-        lines.append(f"Entries: {data.get('entry_count')}")
-    if data.get("usage"):
-        lines.append(f"Usage: {data.get('usage')}")
-    # Avoid dumping all memory entries into ACP UI; show only the explicit new value preview.
-    preview = str((args or {}).get("content") or (args or {}).get("old_text") or "").strip()
-    if preview:
-        lines.append("Preview: " + _truncate_text(preview, limit=300))
-    return "\n".join(lines)
-
-
-def _format_edit_result(tool_name: str, result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    path = str((args or {}).get("path") or "file").strip()
-    if isinstance(data, dict):
-        if data.get("success") is False or data.get("error"):
-            return f"{tool_name} failed for {path}: {data.get('error', 'unknown error')}"
-        message = str(data.get("message") or "").strip()
-        replacements = data.get("replacements") or data.get("replacement_count")
-        lines = [f"✅ {tool_name} completed" + (f" for `{path}`" if path else "")]
-        if message:
-            lines.append(message)
-        if replacements is not None:
-            lines.append(f"Replacements: {replacements}")
-        if data.get("files_modified"):
-            files = data.get("files_modified")
-            if isinstance(files, list):
-                lines.append("Files: " + ", ".join(f"`{f}`" for f in files[:8]))
-        return "\n".join(lines)
-    if isinstance(result, str) and result.strip():
-        return _truncate_text(result, limit=3000)
-    return f"✅ {tool_name} completed" + (f" for `{path}`" if path else "")
-
-
-def _format_browser_result(tool_name: str, result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return result if isinstance(result, str) and result.strip() else None
-    if data.get("success") is False or data.get("error"):
-        return f"{tool_name} failed: {data.get('error', 'unknown error')}"
-    if tool_name == "browser_get_images":
-        images = data.get("images") or data.get("data")
-        if isinstance(images, list):
-            lines = [f"Images found: {len(images)}"]
-            for img in images[:12]:
-                if isinstance(img, dict):
-                    alt = str(img.get("alt") or "").strip()
-                    url = str(img.get("url") or img.get("src") or "").strip()
-                    lines.append(f"- {alt or 'image'}" + (f" — {url}" if url else ""))
-            return _truncate_text("\n".join(lines), limit=5000)
-    title = str(data.get("title") or data.get("url") or data.get("status") or tool_name)
-    text = str(data.get("text") or data.get("content") or data.get("snapshot") or data.get("analysis") or data.get("message") or "").strip()
-    lines = [title]
-    if data.get("url") and data.get("url") != title:
-        lines.append(str(data.get("url")))
-    if text:
-        lines.extend(["", _truncate_text(text, limit=5000)])
-    return _truncate_text("\n".join(lines), limit=7000)
-
-
-def _format_media_or_cron_result(tool_name: str, result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, dict):
-        return result if isinstance(result, str) and result.strip() else None
-    if data.get("success") is False or data.get("error"):
-        return f"{tool_name} failed: {data.get('error', 'unknown error')}"
-    lines = [f"✅ {tool_name} completed"]
-    for key in ("file_path", "path", "url", "image_url", "job_id", "id", "status", "message", "next_run"):
-        if data.get(key):
-            lines.append(f"- **{key}:** {data.get(key)}")
-    return "\n".join(lines)
-
-
-def _format_generic_structured_result(tool_name: str, result: Optional[str]) -> Optional[str]:
-    data = _json_loads_maybe(result)
-    if not isinstance(data, (dict, list)):
-        return result if isinstance(result, str) and result.strip() else None
-    if isinstance(data, list):
-        lines = [f"{tool_name}: {len(data)} item{'s' if len(data) != 1 else ''}"]
-        for item in data[:12]:
-            lines.append(f"- {_truncate_text(str(item), limit=240)}")
-        return _truncate_text("\n".join(lines), limit=5000)
-
-    if data.get("success") is False or data.get("error"):
-        return f"{tool_name} failed: {data.get('error', 'unknown error')}"
-
-    lines = [f"✅ {tool_name} completed" if data.get("success") is True else f"{tool_name} result"]
-    priority_keys = (
-        "message", "status", "id", "task_id", "issue_id", "title", "name", "entity_id",
-        "state", "service", "url", "path", "file_path", "count", "total", "next_run",
-    )
-    seen = set()
-    for key in priority_keys:
-        value = data.get(key)
-        if value in (None, "", [], {}):
-            continue
-        seen.add(key)
-        lines.append(f"- **{key}:** {_truncate_text(str(value), limit=500)}")
-
-    for key, value in data.items():
-        if key in seen or key in {"success", "raw", "content", "entries"}:
-            continue
-        if value in (None, "", [], {}):
-            continue
-        if isinstance(value, (dict, list)):
-            preview = json.dumps(value, ensure_ascii=False, default=str)
-        else:
-            preview = str(value)
-        lines.append(f"- **{key}:** {_truncate_text(preview, limit=500)}")
-        if len(lines) >= 14:
-            break
-
-    content = data.get("content")
-    if isinstance(content, str) and content.strip():
-        lines.extend(["", _truncate_text(content.strip(), limit=1500)])
-    return _truncate_text("\n".join(lines), limit=7000)
-
-
-def _build_polished_completion_content(
-    tool_name: str,
-    result: Optional[str],
-    function_args: Optional[Dict[str, Any]],
-) -> Optional[List[Any]]:
-    formatter = {
-        "todo": lambda: _format_todo_result(result),
-        "read_file": lambda: _format_read_file_result(result, function_args),
-        "write_file": lambda: _format_edit_result(tool_name, result, function_args),
-        "patch": lambda: _format_edit_result(tool_name, result, function_args),
-        "search_files": lambda: _format_search_files_result(result),
-        "execute_code": lambda: _format_execute_code_result(result),
-        "process": lambda: _format_process_result(result, function_args),
-        "delegate_task": lambda: _format_delegate_result(result),
-        "session_search": lambda: _format_session_search_result(result),
-        "memory": lambda: _format_memory_result(result, function_args),
-        "skill_view": lambda: _format_skill_view_result(result),
-        "skill_manage": lambda: _format_skill_manage_result(result, function_args),
-        "web_search": lambda: _format_web_search_result(result),
-        "web_extract": lambda: _format_web_extract_result(result),
-        "browser_navigate": lambda: _format_browser_result(tool_name, result, function_args),
-        "browser_snapshot": lambda: _format_browser_result(tool_name, result, function_args),
-        "browser_vision": lambda: _format_browser_result(tool_name, result, function_args),
-        "browser_get_images": lambda: _format_browser_result(tool_name, result, function_args),
-        "vision_analyze": lambda: _format_media_or_cron_result(tool_name, result),
-        "image_generate": lambda: _format_media_or_cron_result(tool_name, result),
-        "cronjob": lambda: _format_media_or_cron_result(tool_name, result),
-    }.get(tool_name)
-    if formatter is None and tool_name in _POLISHED_TOOLS:
-        formatter = lambda: _format_generic_structured_result(tool_name, result)
-    if formatter is None:
-        return None
-    text = formatter()
-    if not text:
-        return None
-    return [_text(text)]
-
-
 def _build_patch_mode_content(patch_text: str) -> List[Any]:
     """Parse V4A patch mode input into ACP diff blocks when possible."""
     if not patch_text:
@@ -912,11 +258,7 @@ def _build_tool_complete_content(
         except Exception:
             pass
 
-    polished_content = _build_polished_completion_content(tool_name, result, function_args)
-    if polished_content:
-        return polished_content
-
-    return [_text(display_result)]
+    return [acp.tool_content(acp.text_block(display_result))]
 
 
 # ---------------------------------------------------------------------------
@@ -946,6 +288,7 @@ def build_tool_start(
             content = _build_patch_mode_content(patch_text)
         return acp.start_tool_call(
             tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
         )
 
     if tool_name == "write_file":
@@ -954,172 +297,32 @@ def build_tool_start(
         content = [acp.tool_diff_content(path=path, new_text=file_content)]
         return acp.start_tool_call(
             tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
         )
 
     if tool_name == "terminal":
         command = arguments.get("command", "")
-        content = [_text(f"$ {command}")]
+        content = [acp.tool_content(acp.text_block(f"$ {command}"))]
         return acp.start_tool_call(
             tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
         )
 
     if tool_name == "read_file":
-        # The title and location already identify the file. Sending a synthetic
-        # "Reading ..." content block makes Zed render an unhelpful Output
-        # section before the real file contents arrive on completion.
+        path = arguments.get("path", "")
+        content = [acp.tool_content(acp.text_block(f"Reading {path}"))]
         return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=None, locations=locations,
+            tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
         )
 
     if tool_name == "search_files":
         pattern = arguments.get("pattern", "")
         target = arguments.get("target", "content")
-        search_path = arguments.get("path")
-        where = f" in {search_path}" if search_path else ""
-        content = [_text(f"Searching for '{pattern}' ({target}){where}")]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "todo":
-        items = arguments.get("todos")
-        if isinstance(items, list):
-            preview_lines = ["Updating todo list", ""]
-            for item in items[:8]:
-                if isinstance(item, dict):
-                    preview_lines.append(f"- {item.get('status', 'pending')}: {item.get('content', item.get('id', ''))}")
-            if len(items) > 8:
-                preview_lines.append(f"... {len(items) - 8} more")
-            content = [_text("\n".join(preview_lines))]
-        else:
-            content = [_text("Reading todo list")]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "skill_view":
-        name = str(arguments.get("name") or "?").strip() or "?"
-        file_path = str(arguments.get("file_path") or "SKILL.md").strip() or "SKILL.md"
-        content = [_text(f"Loading skill '{name}' ({file_path})")]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "skill_manage":
-        action = str(arguments.get("action") or "manage").strip() or "manage"
-        name = str(arguments.get("name") or "?").strip() or "?"
-        file_path = str(arguments.get("file_path") or "SKILL.md").strip() or "SKILL.md"
-        path = f"skills/{name}/{file_path}" if file_path else f"skills/{name}"
-
-        if action == "patch":
-            old = str(arguments.get("old_string") or "")
-            new = str(arguments.get("new_string") or "")
-            content = [acp.tool_diff_content(path=path, old_text=old or None, new_text=new)]
-        elif action in {"edit", "create"}:
-            content = [
-                acp.tool_diff_content(
-                    path=path,
-                    new_text=str(arguments.get("content") or ""),
-                )
-            ]
-        elif action == "write_file":
-            target = str(arguments.get("file_path") or "file")
-            content = [
-                acp.tool_diff_content(
-                    path=f"skills/{name}/{target}",
-                    new_text=str(arguments.get("file_content") or ""),
-                )
-            ]
-        elif action in {"delete", "remove_file"}:
-            target = str(arguments.get("file_path") or file_path or name)
-            content = [_text(f"Removing {target} from skill '{name}'")]
-        else:
-            content = [_text(f"Running skill_manage action '{action}' on skill '{name}' ({file_path})")]
-
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "execute_code":
-        code = str(arguments.get("code") or "").strip()
-        preview = code[:1200] + (f"\n... ({len(code)} chars total, truncated)" if len(code) > 1200 else "")
-        content = [_text(f"Running Python helper script:\n\n```python\n{preview}\n```" if preview else "Running Python helper script")]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "web_search":
-        query = str(arguments.get("query") or "").strip()
-        content = [_text(f"Searching the web for: {query}" if query else "Searching the web")]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "web_extract":
-        # The title identifies the URL(s). Avoid a duplicate content block so
-        # Zed renders this like read_file: compact start, concise completion.
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=None, locations=locations,
-        )
-
-    if tool_name == "process":
-        action = str(arguments.get("action") or "").strip() or "manage"
-        sid = str(arguments.get("session_id") or "").strip()
-        data_preview = str(arguments.get("data") or "").strip()
-        text = f"Process action: {action}" + (f"\nSession: {sid}" if sid else "")
-        if data_preview:
-            text += "\nInput: " + _truncate_text(data_preview, limit=500)
-        content = [_text(text)]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "delegate_task":
-        tasks = arguments.get("tasks")
-        if isinstance(tasks, list) and tasks:
-            lines = [f"Delegating {len(tasks)} tasks", ""]
-            for i, task in enumerate(tasks[:8], 1):
-                if isinstance(task, dict):
-                    goal = str(task.get("goal") or "").strip()
-                    role = str(task.get("role") or "").strip()
-                    lines.append(f"{i}. " + _truncate_text(goal, limit=160) + (f" ({role})" if role else ""))
-            if len(tasks) > 8:
-                lines.append(f"... {len(tasks) - 8} more")
-            content = [_text("\n".join(lines))]
-        else:
-            goal = str(arguments.get("goal") or "").strip()
-            content = [_text("Delegating task" + (f":\n{_truncate_text(goal, limit=800)}" if goal else ""))]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "session_search":
-        query = str(arguments.get("query") or "").strip()
-        content = [_text(f"Searching past sessions for: {query}" if query else "Loading recent sessions")]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name == "memory":
-        action = str(arguments.get("action") or "manage").strip() or "manage"
-        target = str(arguments.get("target") or "memory").strip() or "memory"
-        preview = str(arguments.get("content") or arguments.get("old_text") or "").strip()
-        text = f"Memory {action} ({target})"
-        if preview:
-            text += "\nPreview: " + _truncate_text(preview, limit=500)
-        content = [_text(text)]
-        return acp.start_tool_call(
-            tool_call_id, title, kind=kind, content=content, locations=locations,
-        )
-
-    if tool_name in _POLISHED_TOOLS:
-        try:
-            args_text = json.dumps(arguments, indent=2, default=str)
-        except (TypeError, ValueError):
-            args_text = str(arguments)
-        content = [_text(_truncate_text(args_text, limit=1200))]
+        content = [acp.tool_content(acp.text_block(f"Searching for '{pattern}' ({target})"))]
         return acp.start_tool_call(
             tool_call_id, title, kind=kind, content=content, locations=locations,
+            raw_input=arguments,
         )
 
     # Generic fallback
@@ -1131,7 +334,7 @@ def build_tool_start(
     content = [acp.tool_content(acp.text_block(args_text))]
     return acp.start_tool_call(
         tool_call_id, title, kind=kind, content=content, locations=locations,
-        raw_input=None if tool_name in _POLISHED_TOOLS else arguments,
+        raw_input=arguments,
     )
 
 
@@ -1144,22 +347,18 @@ def build_tool_complete(
 ) -> ToolCallProgress:
     """Create a ToolCallUpdate (progress) event for a completed tool call."""
     kind = get_tool_kind(tool_name)
-    if tool_name == "web_extract":
-        error_text = _format_web_extract_result(result)
-        content = [_text(error_text)] if error_text else None
-    else:
-        content = _build_tool_complete_content(
-            tool_name,
-            result,
-            function_args=function_args,
-            snapshot=snapshot,
-        )
+    content = _build_tool_complete_content(
+        tool_name,
+        result,
+        function_args=function_args,
+        snapshot=snapshot,
+    )
     return acp.update_tool_call(
         tool_call_id,
         kind=kind,
         status="completed",
         content=content,
-        raw_output=None if tool_name in _POLISHED_TOOLS else result,
+        raw_output=result,
     )
 
 

agent/anthropic_adapter.py

@@ -1241,24 +1241,10 @@ def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
     if not tools:
         return []
     result = []
-    seen_names: set = set()
     for t in tools:
         fn = t.get("function", {})
-        name = fn.get("name", "")
-        # Defensive dedup: Anthropic rejects requests with duplicate tool
-        # names.  Upstream injection paths already dedup, but this guard
-        # converts a hard API failure into a warning.  See: #18478
-        if name and name in seen_names:
-            logger.warning(
-                "convert_tools_to_anthropic: duplicate tool name '%s' "
-                "— dropping second occurrence",
-                name,
-            )
-            continue
-        if name:
-            seen_names.add(name)
         result.append({
-            "name": name,
+            "name": fn.get("name", ""),
             "description": fn.get("description", ""),
             "input_schema": _normalize_tool_input_schema(
                 fn.get("parameters", {"type": "object", "properties": {}})

agent/auxiliary_client.py

@@ -259,68 +259,13 @@ _PROVIDERS_WITHOUT_VISION: frozenset = frozenset({
     "kimi-coding-cn",
 })
 
-# OpenRouter app attribution headers (base — always sent)
-_OR_HEADERS_BASE = {
+# OpenRouter app attribution headers
+_OR_HEADERS = {
     "HTTP-Referer": "https://hermes-agent.nousresearch.com",
     "X-OpenRouter-Title": "Hermes Agent",
     "X-OpenRouter-Categories": "productivity,cli-agent",
 }
 
-# Truthy values for boolean env-var parsing.
-_TRUTHY_ENV_VALUES = frozenset({"1", "true", "yes", "on"})
-
-
-def build_or_headers(or_config: dict | None = None) -> dict:
-    """Build OpenRouter headers, optionally including response-cache headers.
-
-    Precedence for response cache: env var > config.yaml > default (enabled).
-
-    Environment variables:
-        ``HERMES_OPENROUTER_CACHE`` — truthy (``1``/``true``/``yes``/``on``)
-            enables caching; ``0``/``false``/``no``/``off`` disables.
-            Overrides ``openrouter.response_cache`` in config.yaml.
-        ``HERMES_OPENROUTER_CACHE_TTL`` — integer seconds (1-86400).
-            Overrides ``openrouter.response_cache_ttl`` in config.yaml.
-
-    *or_config* is the ``openrouter`` section from config.yaml.  When *None*,
-    falls back to reading config from disk via ``load_config()``.
-    """
-    headers = dict(_OR_HEADERS_BASE)
-
-    # Resolve config from disk if not provided.
-    if or_config is None:
-        try:
-            from hermes_cli.config import load_config
-            or_config = load_config().get("openrouter", {})
-        except Exception:
-            or_config = {}
-
-    # Determine cache enabled: env var overrides config.
-    env_cache = os.environ.get("HERMES_OPENROUTER_CACHE", "").strip().lower()
-    if env_cache:
-        cache_enabled = env_cache in _TRUTHY_ENV_VALUES
-    else:
-        cache_enabled = or_config.get("response_cache", False)
-
-    if not cache_enabled:
-        return headers
-
-    headers["X-OpenRouter-Cache"] = "true"
-
-    # Determine TTL: env var overrides config.
-    env_ttl = os.environ.get("HERMES_OPENROUTER_CACHE_TTL", "").strip()
-    if env_ttl:
-        if env_ttl.isdigit():
-            ttl = int(env_ttl)
-            if 1 <= ttl <= 86400:
-                headers["X-OpenRouter-Cache-TTL"] = str(ttl)
-    else:
-        ttl = or_config.get("response_cache_ttl", 300)
-        if isinstance(ttl, (int, float)) and 1 <= ttl <= 86400:
-            headers["X-OpenRouter-Cache-TTL"] = str(int(ttl))
-
-    return headers
-
 # Vercel AI Gateway app attribution headers. HTTP-Referer maps to
 # referrerUrl and X-Title maps to appName in the gateway's analytics.
 from hermes_cli import __version__ as _HERMES_VERSION
@@ -1204,23 +1149,23 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
 
 
 
-def _try_openrouter(explicit_api_key: str = None) -> Tuple[Optional[OpenAI], Optional[str]]:
+def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
     pool_present, entry = _select_pool_entry("openrouter")
     if pool_present:
-        or_key = explicit_api_key or _pool_runtime_api_key(entry)
+        or_key = _pool_runtime_api_key(entry)
         if not or_key:
             return None, None
         base_url = _pool_runtime_base_url(entry, OPENROUTER_BASE_URL) or OPENROUTER_BASE_URL
         logger.debug("Auxiliary client: OpenRouter via pool")
         return OpenAI(api_key=or_key, base_url=base_url,
-                       default_headers=build_or_headers()), _OPENROUTER_MODEL
+                       default_headers=_OR_HEADERS), _OPENROUTER_MODEL
 
-    or_key = explicit_api_key or os.getenv("OPENROUTER_API_KEY")
+    or_key = os.getenv("OPENROUTER_API_KEY")
     if not or_key:
         return None, None
     logger.debug("Auxiliary client: OpenRouter")
     return OpenAI(api_key=or_key, base_url=OPENROUTER_BASE_URL,
-                   default_headers=build_or_headers()), _OPENROUTER_MODEL
+                   default_headers=_OR_HEADERS), _OPENROUTER_MODEL
 
 
 def _describe_openrouter_unavailable() -> str:
@@ -1966,7 +1911,7 @@ def _to_async_client(sync_client, model: str, is_vision: bool = False):
     }
     sync_base_url = str(sync_client.base_url)
     if base_url_host_matches(sync_base_url, "openrouter.ai"):
-        async_kwargs["default_headers"] = build_or_headers()
+        async_kwargs["default_headers"] = dict(_OR_HEADERS)
     elif base_url_host_matches(sync_base_url, "api.githubcopilot.com"):
         from hermes_cli.copilot_auth import copilot_request_headers
 
@@ -2032,12 +1977,6 @@ def resolve_provider_client(
         (client, resolved_model) or (None, None) if auth is unavailable.
     """
     _validate_proxy_env_urls()
-    # Preserve the original provider name before alias normalization so a
-    # user-declared ``custom_providers`` entry whose name coincidentally
-    # matches a built-in alias (e.g. user names their custom provider "kimi"
-    # which aliases to "kimi-coding") is still reachable via the named-custom
-    # branch below.
-    original_provider = (provider or "").strip().lower()
     # Normalise aliases
     provider = _normalize_aux_provider(provider)
 
@@ -2108,9 +2047,9 @@ def resolve_provider_client(
         return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
                 else (client, final_model))
 
-    # ── OpenRouter ───────────────────────────────────────────
+    # ── OpenRouter ───────────────────────────────────────────────────
     if provider == "openrouter":
-        client, default = _try_openrouter(explicit_api_key=explicit_api_key)
+        client, default = _try_openrouter()
         if client is None:
             logger.warning(
                 "resolve_provider_client: openrouter requested but %s",
@@ -2224,18 +2163,7 @@ def resolve_provider_client(
     # ── Named custom providers (config.yaml providers dict / custom_providers list) ───
     try:
         from hermes_cli.runtime_provider import _get_named_custom_provider
-        # When the raw requested name is an alias (``kimi`` → ``kimi-coding``)
-        # and the user defined a ``custom_providers`` entry under that alias
-        # name, the custom entry is the intended target — the built-in alias
-        # rewriting would otherwise hijack the request.  Only preferred when
-        # the raw name is an alias (not a canonical provider name) so custom
-        # entries that coincidentally match a canonical provider (e.g. ``nous``)
-        # still defer to the built-in per `_get_named_custom_provider`'s guard.
-        custom_entry = None
-        if original_provider and original_provider != provider:
-            custom_entry = _get_named_custom_provider(original_provider)
-        if custom_entry is None:
-            custom_entry = _get_named_custom_provider(provider)
+        custom_entry = _get_named_custom_provider(provider)
         if custom_entry:
             custom_base = custom_entry.get("base_url", "").strip()
             custom_key = custom_entry.get("api_key", "").strip()
@@ -2345,12 +2273,6 @@ def resolve_provider_client(
 
         creds = resolve_api_key_provider_credentials(provider)
         api_key = str(creds.get("api_key", "")).strip()
-        # Honour an explicit api_key override (e.g. from a fallback_model entry
-        # or a custom_providers entry) so callers that pass an explicit
-        # credential can authenticate against endpoints where no built-in
-        # credential is registered for this provider alias.
-        if explicit_api_key:
-            api_key = explicit_api_key.strip() or api_key
         if not api_key:
             tried_sources = list(pconfig.api_key_env_vars)
             if provider == "copilot":
@@ -2362,11 +2284,6 @@ def resolve_provider_client(
 
         raw_base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
         base_url = _to_openai_base_url(raw_base_url)
-        # Honour an explicit base_url override from the caller — used when a
-        # fallback_model entry (or custom_providers lookup) routes through a
-        # built-in provider name but targets a user-specified endpoint.
-        if explicit_base_url:
-            base_url = _to_openai_base_url(explicit_base_url.strip().rstrip("/"))
 
         default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
         final_model = _normalize_resolved_model(model or default_model, provider)
@@ -3292,26 +3209,7 @@ def _build_call_kwargs(
             kwargs["max_tokens"] = max_tokens
 
     if tools:
-        # Defensive dedup: providers like Google Vertex, Azure, and Bedrock
-        # reject requests with duplicate tool names (HTTP 400).  The upstream
-        # injection paths (run_agent.py) already dedup, but this guard
-        # converts a hard API failure into a warning if an upstream regression
-        # reintroduces duplicates.  See: #18478
-        _seen: set = set()
-        _deduped: list = []
-        for _t in tools:
-            _tname = (_t.get("function") or {}).get("name", "")
-            if _tname and _tname in _seen:
-                logger.warning(
-                    "_build_call_kwargs: duplicate tool name '%s' removed "
-                    "(provider=%s model=%s)",
-                    _tname, provider, model,
-                )
-                continue
-            if _tname:
-                _seen.add(_tname)
-            _deduped.append(_t)
-        kwargs["tools"] = _deduped
+        kwargs["tools"] = tools
 
     # Provider-specific extra_body
     merged_extra = dict(extra_body or {})

agent/context_compressor.py

@@ -538,7 +538,7 @@ class ContextCompressor(ContextEngine):
             # Token-budget approach: walk backward accumulating tokens
             accumulated = 0
             boundary = len(result)
-            min_protect = min(protect_tail_count, len(result))
+            min_protect = min(protect_tail_count, len(result) - 1)
             for i in range(len(result) - 1, -1, -1):
                 msg = result[i]
                 raw_content = msg.get("content") or ""
@@ -992,8 +992,8 @@ The user has requested that this compaction PRIORITISE preserving all informatio
     def _get_tool_call_id(tc) -> str:
         """Extract the call ID from a tool_call entry (dict or SimpleNamespace)."""
         if isinstance(tc, dict):
-            return tc.get("call_id", "") or tc.get("id", "") or ""
-        return getattr(tc, "call_id", "") or getattr(tc, "id", "") or ""
+            return tc.get("id", "")
+        return getattr(tc, "id", "") or ""
 
     def _sanitize_tool_pairs(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """Fix orphaned tool_call / tool_result pairs after compression.

agent/credential_pool.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import logging
-import os
 import random
 import threading
 import time
@@ -14,7 +13,7 @@ from datetime import datetime
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 from hermes_constants import OPENROUTER_BASE_URL
-from hermes_cli.config import get_env_value, load_env
+from hermes_cli.config import get_env_value
 import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
     CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
@@ -1381,16 +1380,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
 def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool, Set[str]]:
     changed = False
     active_sources: Set[str] = set()
-
-    # Prefer ~/.hermes/.env over os.environ — the user's config file is the
-    # authoritative source for Hermes credentials. Stale env vars from parent
-    # processes (Codex CLI, test scripts, etc.) should not override deliberate
-    # changes to the .env file.
-    def _get_env_prefer_dotenv(key: str) -> str:
-        env_file = load_env()
-        val = env_file.get(key) or os.environ.get(key) or ""
-        return val.strip()
-
     # Honour user suppression — `hermes auth remove <provider> <N>` for an
     # env-seeded credential marks the env:<VAR> source as suppressed so it
     # won't be re-seeded from the user's shell environment or ~/.hermes/.env.
@@ -1402,8 +1391,8 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         def _is_source_suppressed(_p, _s):  # type: ignore[misc]
             return False
     if provider == "openrouter":
-        # Prefer ~/.hermes/.env over os.environ
-        token = _get_env_prefer_dotenv("OPENROUTER_API_KEY")
+        # Check both os.environ and ~/.hermes/.env file
+        token = (get_env_value("OPENROUTER_API_KEY") or "").strip()
         if token:
             source = "env:OPENROUTER_API_KEY"
             if _is_source_suppressed(provider, source):
@@ -1429,7 +1418,7 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
 
     env_url = ""
     if pconfig.base_url_env_var:
-        env_url = _get_env_prefer_dotenv(pconfig.base_url_env_var).rstrip("/")
+        env_url = (get_env_value(pconfig.base_url_env_var) or "").strip().rstrip("/")
 
     env_vars = list(pconfig.api_key_env_vars)
     if provider == "anthropic":
@@ -1440,8 +1429,8 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         ]
 
     for env_var in env_vars:
-        # Prefer ~/.hermes/.env over os.environ
-        token = _get_env_prefer_dotenv(env_var)
+        # Check both os.environ and ~/.hermes/.env file
+        token = (get_env_value(env_var) or "").strip()
         if not token:
             continue
         source = f"env:{env_var}"

agent/curator.py

@@ -55,7 +55,6 @@ def _default_state() -> Dict[str, Any]:
         "last_run_at": None,
         "last_run_duration_seconds": None,
         "last_run_summary": None,
-        "last_report_path": None,
         "paused": False,
         "run_count": 0,
     }
@@ -184,16 +183,7 @@ def should_run_now(now: Optional[datetime] = None) -> bool:
     Gates:
       - curator.enabled == True
       - not paused
-      - last_run_at present AND older than interval_hours
-
-    First-run behavior: when there is no ``last_run_at`` (fresh install, or
-    install that predates the curator), we DO NOT run immediately. The
-    curator is designed to run after at least ``interval_hours`` (7 days by
-    default) of skill activity, not on the first background tick after
-    ``hermes update``. On first observation we seed ``last_run_at`` to "now"
-    and defer the first real pass by one full interval. Users who want to
-    run it sooner can always invoke ``hermes curator run`` (with or without
-    ``--dry-run``) explicitly — that path bypasses this gate.
+      - last_run_at missing, OR older than interval_hours
 
     The idle check (min_idle_hours) is applied at the call site where we know
     whether an agent is actively running — here we only enforce the static
@@ -207,21 +197,7 @@ def should_run_now(now: Optional[datetime] = None) -> bool:
     state = load_state()
     last = _parse_iso(state.get("last_run_at"))
     if last is None:
-        # Never run before. Seed state so we wait a full interval before the
-        # first real pass. Report-only; do not auto-mutate the library the
-        # very first time a gateway ticks after an update.
-        if now is None:
-            now = datetime.now(timezone.utc)
-        try:
-            state["last_run_at"] = now.isoformat()
-            state["last_run_summary"] = (
-                "deferred first run — curator seeded, will run after one "
-                "interval; use `hermes curator run --dry-run` to preview now"
-            )
-            save_state(state)
-        except Exception as e:  # pragma: no cover — best-effort persistence
-            logger.debug("Failed to seed curator last_run_at: %s", e)
-        return False
+        return True
 
     if now is None:
         now = datetime.now(timezone.utc)
@@ -282,33 +258,6 @@ def apply_automatic_transitions(now: Optional[datetime] = None) -> Dict[str, int
 # Review prompt for the forked agent
 # ---------------------------------------------------------------------------
 
-CURATOR_DRY_RUN_BANNER = (
-    "═══════════════════════════════════════════════════════════════\n"
-    "DRY-RUN — REPORT ONLY. DO NOT MUTATE THE SKILL LIBRARY.\n"
-    "═══════════════════════════════════════════════════════════════\n"
-    "\n"
-    "This is a PREVIEW pass. Follow every instruction below EXCEPT:\n"
-    "\n"
-    "  • DO NOT call skill_manage with action=patch, create, delete, "
-    "write_file, or remove_file.\n"
-    "  • DO NOT call terminal to mv skill directories into .archive/.\n"
-    "  • DO NOT call terminal to mv, cp, rm, or rewrite any file under "
-    "~/.hermes/skills/.\n"
-    "  • skills_list and skill_view are FINE — read as much as you need.\n"
-    "\n"
-    "Your output IS the deliverable. Produce the exact same "
-    "human-readable summary and structured YAML block you would "
-    "produce on a live run — but describe the actions you WOULD take, "
-    "not actions you took. A downstream reviewer will read the report "
-    "and decide whether to approve a live run with "
-    "`hermes curator run` (no flag).\n"
-    "\n"
-    "If you accidentally take a mutating action, say so explicitly in "
-    "the summary so the reviewer can revert it.\n"
-    "═══════════════════════════════════════════════════════════════"
-)
-
-
 CURATOR_REVIEW_PROMPT = (
     "You are running as Hermes' background skill CURATOR. This is an "
     "UMBRELLA-BUILDING consolidation pass, not a passive audit and not a "
@@ -387,11 +336,6 @@ CURATOR_REVIEW_PROMPT = (
     "  - skill_manage action=write_file — add a references/, templates/, "
     "or scripts/ file under an existing skill (the skill must already "
     "exist)\n"
-    "  - skill_manage action=delete     — archive a skill. MUST pass "
-    "`absorbed_into=<umbrella>` when you've merged its content into another "
-    "skill, or `absorbed_into=\"\"` when you're truly pruning with no "
-    "forwarding target. This drives cron-job skill-reference migration — "
-    "guessing from your YAML summary after the fact is fragile.\n"
     "  - terminal                       — mv a sibling into the archive "
     "OR move its content into a support subfile\n\n"
     "'keep' is a legitimate decision ONLY when the skill is already a "
@@ -642,76 +586,15 @@ def _parse_structured_summary(
     return out
 
 
-def _extract_absorbed_into_declarations(
-    tool_calls: List[Dict[str, Any]],
-) -> Dict[str, Dict[str, Any]]:
-    """Walk this run's tool calls and extract model-declared absorption targets.
-
-    The curator prompt requires every ``skill_manage(action='delete')`` call
-    to pass ``absorbed_into=<umbrella>`` when consolidating, or
-    ``absorbed_into=""`` when truly pruning. This is the single authoritative
-    signal for classification — the model's own declaration at the moment of
-    deletion, which beats both post-hoc YAML summary parsing and substring
-    heuristics on other tool calls.
-
-    Returns ``{skill_name: {"into": "<umbrella>" | "", "declared": True}}``.
-    Entries with ``into == ""`` are explicit prunings.
-    Skills without a ``skill_manage(delete)`` call, or with one that omitted
-    ``absorbed_into``, are not in the returned dict — caller falls back to
-    the existing heuristic/YAML logic for those (backward compat with older
-    curator runs and any callers that don't populate the arg).
-    """
-    out: Dict[str, Dict[str, Any]] = {}
-    for tc in tool_calls or []:
-        if not isinstance(tc, dict):
-            continue
-        if tc.get("name") != "skill_manage":
-            continue
-        raw = tc.get("arguments") or ""
-        args: Dict[str, Any] = {}
-        if isinstance(raw, dict):
-            args = raw
-        elif isinstance(raw, str):
-            try:
-                args = json.loads(raw)
-            except Exception:
-                continue
-        if not isinstance(args, dict):
-            continue
-        if args.get("action") != "delete":
-            continue
-        name = args.get("name")
-        if not isinstance(name, str) or not name.strip():
-            continue
-        # absorbed_into must be present (even empty string is meaningful);
-        # missing key means the model didn't declare intent.
-        if "absorbed_into" not in args:
-            continue
-        target = args.get("absorbed_into")
-        if target is None:
-            continue
-        if not isinstance(target, str):
-            continue
-        out[name.strip()] = {"into": target.strip(), "declared": True}
-    return out
-
-
 def _reconcile_classification(
     removed: List[str],
     heuristic: Dict[str, List[Dict[str, Any]]],
     model_block: Dict[str, List[Dict[str, str]]],
     destinations: Set[str],
-    absorbed_declarations: Optional[Dict[str, Dict[str, Any]]] = None,
 ) -> Dict[str, List[Dict[str, Any]]]:
     """Merge heuristic (tool-call evidence) with the model's structured block.
 
-    Rules (evaluated in order; first match wins):
-    - **Model-declared `absorbed_into` at delete time is authoritative.** Any
-      entry in ``absorbed_declarations`` beats every other signal. This is
-      the model telling us directly, at the moment of deletion, what it did.
-      ``into != ""`` and target exists → consolidated. ``into == ""`` →
-      pruned. ``into != ""`` but target doesn't exist → hallucination; fall
-      through to the usual signals.
+    Rules:
     - Model-declared consolidation wins when its ``into`` target exists
       in ``destinations`` (survived or newly-created). This gives the
       model authority over intent + rationale.
@@ -732,8 +615,6 @@ def _reconcile_classification(
     model_cons = {e["from"]: e for e in model_block.get("consolidations", [])}
     model_pruned = {e["name"]: e for e in model_block.get("prunings", [])}
 
-    declared = absorbed_declarations or {}
-
     consolidated: List[Dict[str, Any]] = []
     pruned: List[Dict[str, Any]] = []
 
@@ -741,36 +622,6 @@ def _reconcile_classification(
         mc = model_cons.get(name)
         mp = model_pruned.get(name)
         hc = heur_cons.get(name)
-        dec = declared.get(name)
-
-        # Authoritative: model declared `absorbed_into` at the delete call.
-        if dec is not None:
-            into_claim = dec.get("into", "")
-            if into_claim and into_claim in destinations:
-                entry: Dict[str, Any] = {
-                    "name": name,
-                    "into": into_claim,
-                    "source": "absorbed_into (model-declared at delete)",
-                    "reason": (mc.get("reason") or "") if mc else "",
-                }
-                if hc and hc.get("evidence"):
-                    entry["evidence"] = hc["evidence"]
-                consolidated.append(entry)
-                continue
-            if into_claim == "":
-                # Explicit prune declaration
-                pruned.append({
-                    "name": name,
-                    "source": "absorbed_into=\"\" (model-declared prune)",
-                    "reason": (mp.get("reason") or "") if mp else "",
-                })
-                continue
-            # into_claim is non-empty but target doesn't exist: the model
-            # named a nonexistent umbrella at delete time. The tool already
-            # rejects this at the skill_manage layer, so we shouldn't see it
-            # in practice — but if it slips through (e.g. the umbrella was
-            # deleted LATER in the same run), fall through to the usual
-            # signals rather than trusting a broken reference.
 
         # Model says consolidated — trust it if the destination is real.
         if mc and mc.get("into") in destinations:
@@ -906,57 +757,15 @@ def _write_run_report(
     )
     model_block = _parse_structured_summary(llm_meta.get("final", "") or "")
     destinations = set(after_names) | set(added or [])
-    # Authoritative signal: extract per-delete `absorbed_into` declarations
-    # from this run's tool calls. These beat both the YAML summary block and
-    # the substring heuristic — the model is telling us directly, at the
-    # moment of deletion, whether each archived skill was consolidated
-    # (into=<umbrella>) or pruned (into="").
-    absorbed_declarations = _extract_absorbed_into_declarations(
-        llm_meta.get("tool_calls", []) or []
-    )
     classification = _reconcile_classification(
         removed=removed,
         heuristic=heuristic,
         model_block=model_block,
         destinations=destinations,
-        absorbed_declarations=absorbed_declarations,
     )
     consolidated = classification["consolidated"]
     pruned = classification["pruned"]
 
-    # Rewrite cron job skill references. When the curator consolidates
-    # skill X into umbrella Y, any cron job that lists X fails to load
-    # it at run time — the scheduler skips it and the job runs without
-    # the instructions it was scheduled to follow. Rewriting the
-    # references in-place keeps scheduled jobs working across
-    # consolidation passes. Best-effort: never let a cron-module issue
-    # break the curator.
-    cron_rewrites: Dict[str, Any] = {"rewrites": [], "jobs_updated": 0, "jobs_scanned": 0}
-    try:
-        consolidated_map = {
-            e["name"]: e["into"]
-            for e in consolidated
-            if isinstance(e, dict) and e.get("name") and e.get("into")
-        }
-        pruned_names = [
-            e["name"] for e in pruned
-            if isinstance(e, dict) and e.get("name")
-        ]
-        if consolidated_map or pruned_names:
-            from cron.jobs import rewrite_skill_refs as _rewrite_cron_refs
-            cron_rewrites = _rewrite_cron_refs(
-                consolidated=consolidated_map,
-                pruned=pruned_names,
-            )
-    except Exception as e:
-        logger.debug("Curator cron skill rewrite failed: %s", e, exc_info=True)
-        cron_rewrites = {
-            "rewrites": [],
-            "jobs_updated": 0,
-            "jobs_scanned": 0,
-            "error": str(e),
-        }
-
     payload = {
         "started_at": started_at.isoformat(),
         "duration_seconds": round(elapsed_seconds, 2),
@@ -972,7 +781,6 @@ def _write_run_report(
             "consolidated_this_run": len(consolidated),
             "pruned_this_run": len(pruned),
             "state_transitions": len(transitions),
-            "cron_jobs_rewritten": int(cron_rewrites.get("jobs_updated", 0)),
             "tool_calls_total": sum(tc_counts.values()),
         },
         "tool_call_counts": tc_counts,
@@ -982,7 +790,6 @@ def _write_run_report(
         "pruned_names": [p["name"] for p in pruned],
         "added": added,
         "state_transitions": transitions,
-        "cron_rewrites": cron_rewrites,
         "llm_final": llm_meta.get("final", ""),
         "llm_summary": llm_meta.get("summary", ""),
         "llm_error": llm_meta.get("error"),
@@ -1005,17 +812,6 @@ def _write_run_report(
     except Exception as e:
         logger.debug("Curator REPORT.md write failed: %s", e)
 
-    # cron_rewrites.json — only when at least one job was touched, to
-    # keep run dirs uncluttered for the common no-op case.
-    try:
-        if int(cron_rewrites.get("jobs_updated", 0)) > 0:
-            (run_dir / "cron_rewrites.json").write_text(
-                json.dumps(cron_rewrites, indent=2, ensure_ascii=False) + "\n",
-                encoding="utf-8",
-            )
-    except Exception as e:
-        logger.debug("Curator cron_rewrites.json write failed: %s", e)
-
     return run_dir
 
 
@@ -1146,39 +942,6 @@ def _render_report_markdown(p: Dict[str, Any]) -> str:
             lines.append(f"- `{t.get('name')}`: {t.get('from')} → {t.get('to')}")
         lines.append("")
 
-    # Cron job rewrites — show which scheduled jobs had their skill
-    # references updated so users can audit that the auto-rewrite did
-    # the right thing. Only present when at least one job changed.
-    cron_rw = p.get("cron_rewrites") or {}
-    cron_rewrites_list = cron_rw.get("rewrites") or []
-    if cron_rewrites_list:
-        lines.append(f"### Cron job skill references rewritten ({len(cron_rewrites_list)})\n")
-        lines.append(
-            "_Cron jobs that referenced a consolidated or pruned skill were "
-            "updated in-place so they keep loading the right instructions "
-            "on their next run. See `cron_rewrites.json` for the full record._\n"
-        )
-        SHOW = 25
-        for entry in cron_rewrites_list[:SHOW]:
-            job_name = entry.get("job_name") or entry.get("job_id") or "?"
-            before = entry.get("before") or []
-            after = entry.get("after") or []
-            mapped = entry.get("mapped") or {}
-            dropped = entry.get("dropped") or []
-            lines.append(
-                f"- `{job_name}`: `{', '.join(before)}` → `{', '.join(after) or '(none)'}`"
-            )
-            for old, new in mapped.items():
-                lines.append(f"    - `{old}` → `{new}` (consolidated)")
-            for name in dropped:
-                lines.append(f"    - `{name}` dropped (pruned)")
-        if len(cron_rewrites_list) > SHOW:
-            lines.append(
-                f"- … and {len(cron_rewrites_list) - SHOW} more "
-                "(see `cron_rewrites.json`)"
-            )
-        lines.append("")
-
     # Full LLM final response
     final = (p.get("llm_final") or "").strip()
     if final:
@@ -1229,7 +992,6 @@ def _render_candidate_list() -> str:
 def run_curator_review(
     on_summary: Optional[Callable[[str], None]] = None,
     synchronous: bool = False,
-    dry_run: bool = False,
 ) -> Dict[str, Any]:
     """Execute a single curator review pass.
 
@@ -1242,43 +1004,9 @@ def run_curator_review(
 
     If *synchronous* is True, the LLM review runs in the calling thread; the
     default is to spawn a daemon thread so the caller returns immediately.
-
-    If *dry_run* is True, the automatic stale/archive transitions are SKIPPED
-    and the LLM review pass is instructed to produce a report only — no
-    skill_manage mutations, no terminal archive moves. The REPORT.md still
-    gets written and ``state.last_report_path`` still records it so users
-    can read what the curator WOULD have done.
     """
     start = datetime.now(timezone.utc)
-    if dry_run:
-        # Count candidates without mutating state.
-        try:
-            report = skill_usage.agent_created_report()
-            counts = {
-                "checked": len(report),
-                "marked_stale": 0,
-                "archived": 0,
-                "reactivated": 0,
-            }
-        except Exception:
-            counts = {"checked": 0, "marked_stale": 0, "archived": 0, "reactivated": 0}
-    else:
-        # Pre-mutation snapshot — best-effort, never blocks the run. A
-        # failed snapshot logs at debug and continues (the alternative is
-        # that a transient disk issue silently disables curator forever,
-        # which is worse). Users who want to require snapshots can disable
-        # curator entirely until they can fix disk space.
-        try:
-            from agent import curator_backup
-            snap = curator_backup.snapshot_skills(reason="pre-curator-run")
-            if snap is not None and on_summary:
-                try:
-                    on_summary(f"curator: snapshot created ({snap.name})")
-                except Exception:
-                    pass
-        except Exception as e:
-            logger.debug("Curator pre-run snapshot failed: %s", e, exc_info=True)
-        counts = apply_automatic_transitions(now=start)
+    counts = apply_automatic_transitions(now=start)
 
     auto_summary_parts = []
     if counts["marked_stale"]:
@@ -1290,16 +1018,11 @@ def run_curator_review(
     auto_summary = ", ".join(auto_summary_parts) if auto_summary_parts else "no changes"
 
     # Persist state before the LLM pass so a crash mid-review still records
-    # the run and doesn't immediately re-trigger. In dry-run we do NOT bump
-    # last_run_at or run_count — a preview shouldn't push the next scheduled
-    # real pass out. We still record a summary so `hermes curator status`
-    # shows that a preview ran.
+    # the run and doesn't immediately re-trigger.
     state = load_state()
-    if not dry_run:
-        state["last_run_at"] = start.isoformat()
-        state["run_count"] = int(state.get("run_count", 0)) + 1
-    prefix = "dry-run auto: " if dry_run else "auto: "
-    state["last_run_summary"] = f"{prefix}{auto_summary}"
+    state["last_run_at"] = start.isoformat()
+    state["run_count"] = int(state.get("run_count", 0)) + 1
+    state["last_run_summary"] = f"auto: {auto_summary}"
     save_state(state)
 
     def _llm_pass():
@@ -1315,7 +1038,7 @@ def run_curator_review(
         try:
             candidate_list = _render_candidate_list()
             if "No agent-created skills" in candidate_list:
-                final_summary = f"{prefix}{auto_summary}; llm: skipped (no candidates)"
+                final_summary = f"auto: {auto_summary}; llm: skipped (no candidates)"
                 llm_meta = {
                     "final": "",
                     "summary": "skipped (no candidates)",
@@ -1325,21 +1048,14 @@ def run_curator_review(
                     "error": None,
                 }
             else:
-                if dry_run:
-                    prompt = (
-                        f"{CURATOR_DRY_RUN_BANNER}\n\n"
-                        f"{CURATOR_REVIEW_PROMPT}\n\n"
-                        f"{candidate_list}"
-                    )
-                else:
-                    prompt = f"{CURATOR_REVIEW_PROMPT}\n\n{candidate_list}"
+                prompt = f"{CURATOR_REVIEW_PROMPT}\n\n{candidate_list}"
                 llm_meta = _run_llm_review(prompt)
                 final_summary = (
-                    f"{prefix}{auto_summary}; llm: {llm_meta.get('summary', 'no change')}"
+                    f"auto: {auto_summary}; llm: {llm_meta.get('summary', 'no change')}"
                 )
         except Exception as e:
             logger.debug("Curator LLM pass failed: %s", e, exc_info=True)
-            final_summary = f"{prefix}{auto_summary}; llm: error ({e})"
+            final_summary = f"auto: {auto_summary}; llm: error ({e})"
             llm_meta = {
                 "final": "",
                 "summary": f"error ({e})",

agent/curator_backup.py

@@ -1,693 +0,0 @@
-"""Curator snapshot + rollback.
-
-A pre-run snapshot of ``~/.hermes/skills/`` (excluding ``.curator_backups/``
-itself) is taken before any mutating curator pass. Snapshots are tar.gz
-files under ``~/.hermes/skills/.curator_backups/<utc-iso>/`` with a
-companion ``manifest.json`` describing the snapshot (reason, time, size,
-counted skill files). Rollback picks a snapshot, moves the current
-``skills/`` tree aside into another snapshot so even the rollback itself
-is undoable, then extracts the chosen snapshot into place.
-
-The snapshot does NOT include:
-  - ``.curator_backups/`` (would recurse)
-  - ``.hub/`` (hub-installed skills — managed by the hub, not us)
-
-It DOES include:
-  - all SKILL.md files + their directories (``scripts/``, ``references/``,
-    ``templates/``, ``assets/``)
-  - ``.usage.json`` (usage telemetry — needed to rehydrate state cleanly)
-  - ``.archive/`` (so rollback restores previously-archived skills too)
-  - ``.curator_state`` (so rolling back also restores the last-run-at
-    pointer — otherwise the curator would immediately re-fire on the next
-    tick)
-  - ``.bundled_manifest`` (so protection markers stay consistent)
-
-Alongside the skills tarball, each snapshot also captures a copy of
-``~/.hermes/cron/jobs.json`` as ``cron-jobs.json`` when it exists. Cron
-jobs reference skills by name in their ``skills``/``skill`` fields; the
-curator's consolidation pass rewrites those in place via
-``cron.jobs.rewrite_skill_refs()``. Without capturing the pre-run state,
-rolling back the skills tree would leave cron jobs pointing at the
-umbrella skills even though the narrow skills they were originally
-configured with have been restored. We store the whole jobs.json for
-fidelity but rollback only touches the ``skills``/``skill`` fields — the
-rest (schedule, next_run_at, enabled, prompt, etc.) is live state and
-we leave it alone.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import re
-import shutil
-import tarfile
-import tempfile
-import time
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-from hermes_constants import get_hermes_home
-
-logger = logging.getLogger(__name__)
-
-
-DEFAULT_KEEP = 5
-
-# Entries under skills/ that should NEVER be rolled up into a snapshot.
-# .hub/ is managed by the skills hub; rolling it back would break lockfile
-# invariants. .curator_backups is the backup dir itself — recursion bomb.
-_EXCLUDE_TOP_LEVEL = {".curator_backups", ".hub"}
-
-# Snapshot id regex: UTC ISO with colons replaced by dashes so the filename
-# is portable (Windows-safe). An optional ``-NN`` suffix handles two
-# snapshots landing in the same wallclock second.
-_ID_RE = re.compile(r"^\d{4}-\d{2}-\d{2}T\d{2}-\d{2}-\d{2}Z(-\d{2})?$")
-
-
-def _backups_dir() -> Path:
-    return get_hermes_home() / "skills" / ".curator_backups"
-
-
-def _skills_dir() -> Path:
-    return get_hermes_home() / "skills"
-
-
-def _cron_jobs_file() -> Path:
-    """Source path for the live cron jobs store (``~/.hermes/cron/jobs.json``)."""
-    return get_hermes_home() / "cron" / "jobs.json"
-
-
-CRON_JOBS_FILENAME = "cron-jobs.json"
-
-
-def _backup_cron_jobs_into(dest: Path) -> Dict[str, Any]:
-    """Copy the live cron jobs.json into ``dest`` as ``cron-jobs.json``.
-
-    Returns a small dict describing what was captured so the caller can
-    fold it into the manifest. Never raises — if the cron file is missing
-    or unreadable, the return dict has ``backed_up=False`` and the reason,
-    and the snapshot proceeds without cron data (the snapshot is still
-    useful for rolling back skills).
-    """
-    src = _cron_jobs_file()
-    info: Dict[str, Any] = {"backed_up": False, "jobs_count": 0}
-    if not src.exists():
-        info["reason"] = "no cron/jobs.json present"
-        return info
-    try:
-        raw = src.read_text(encoding="utf-8")
-    except OSError as e:
-        logger.debug("Failed to read cron/jobs.json for backup: %s", e)
-        info["reason"] = f"read error: {e}"
-        return info
-    # Count jobs as a nice diagnostic — but don't fail the snapshot if the
-    # file is unparseable; just store the raw text and let rollback deal
-    # with it (or not, if it's corrupted). jobs.json wraps the list as
-    # `{"jobs": [...], "updated_at": ...}` — we count via that shape, and
-    # fall back to bare-list shape just in case the format ever changes.
-    try:
-        parsed = json.loads(raw)
-        if isinstance(parsed, dict):
-            inner = parsed.get("jobs")
-            if isinstance(inner, list):
-                info["jobs_count"] = len(inner)
-        elif isinstance(parsed, list):
-            info["jobs_count"] = len(parsed)
-    except (json.JSONDecodeError, TypeError):
-        info["jobs_count"] = 0
-        info["parse_warning"] = "jobs.json was not valid JSON at snapshot time"
-    try:
-        (dest / CRON_JOBS_FILENAME).write_text(raw, encoding="utf-8")
-    except OSError as e:
-        logger.debug("Failed to write cron backup file: %s", e)
-        info["reason"] = f"write error: {e}"
-        return info
-    info["backed_up"] = True
-    return info
-
-
-def _utc_id(now: Optional[datetime] = None) -> str:
-    """UTC ISO-ish filesystem-safe timestamp: ``2026-05-01T13-05-42Z``."""
-    if now is None:
-        now = datetime.now(timezone.utc)
-    # isoformat → "2026-05-01T13:05:42.123456+00:00"; strip subseconds and tz.
-    s = now.replace(microsecond=0).isoformat()
-    if s.endswith("+00:00"):
-        s = s[:-6]
-    return s.replace(":", "-") + "Z"
-
-
-def _load_config() -> Dict[str, Any]:
-    try:
-        from hermes_cli.config import load_config
-        cfg = load_config()
-    except Exception as e:
-        logger.debug("Failed to load config for curator backup: %s", e)
-        return {}
-    if not isinstance(cfg, dict):
-        return {}
-    cur = cfg.get("curator") or {}
-    if not isinstance(cur, dict):
-        return {}
-    bk = cur.get("backup") or {}
-    return bk if isinstance(bk, dict) else {}
-
-
-def is_enabled() -> bool:
-    """Default ON — the whole point of the backup is safety by default."""
-    return bool(_load_config().get("enabled", True))
-
-
-def get_keep() -> int:
-    cfg = _load_config()
-    try:
-        n = int(cfg.get("keep", DEFAULT_KEEP))
-    except (TypeError, ValueError):
-        n = DEFAULT_KEEP
-    return max(1, n)
-
-
-# ---------------------------------------------------------------------------
-# Snapshot
-# ---------------------------------------------------------------------------
-
-def _count_skill_files(base: Path) -> int:
-    try:
-        return sum(1 for _ in base.rglob("SKILL.md"))
-    except OSError:
-        return 0
-
-
-def _write_manifest(dest: Path, reason: str, archive_path: Path,
-                    skills_counted: int,
-                    cron_info: Optional[Dict[str, Any]] = None) -> None:
-    manifest = {
-        "id": dest.name,
-        "reason": reason,
-        "created_at": datetime.now(timezone.utc).isoformat(),
-        "archive": archive_path.name,
-        "archive_bytes": archive_path.stat().st_size,
-        "skill_files": skills_counted,
-    }
-    if cron_info is not None:
-        manifest["cron_jobs"] = {
-            "backed_up": bool(cron_info.get("backed_up", False)),
-            "jobs_count": int(cron_info.get("jobs_count", 0)),
-        }
-        if not cron_info.get("backed_up"):
-            manifest["cron_jobs"]["reason"] = cron_info.get("reason", "not captured")
-        if cron_info.get("parse_warning"):
-            manifest["cron_jobs"]["parse_warning"] = cron_info["parse_warning"]
-    (dest / "manifest.json").write_text(
-        json.dumps(manifest, indent=2, sort_keys=True), encoding="utf-8"
-    )
-
-
-def snapshot_skills(reason: str = "manual") -> Optional[Path]:
-    """Create a tar.gz snapshot of ``~/.hermes/skills/`` and prune old ones.
-
-    Returns the snapshot directory path, or ``None`` if the snapshot was
-    skipped (backup disabled, skills dir missing, or an IO error occurred —
-    in which case we log at debug and return None so the curator never
-    aborts a pass because of a backup failure).
-    """
-    if not is_enabled():
-        logger.debug("Curator backup disabled by config; skipping snapshot")
-        return None
-
-    skills = _skills_dir()
-    if not skills.exists():
-        logger.debug("No ~/.hermes/skills/ directory — nothing to back up")
-        return None
-
-    backups = _backups_dir()
-    try:
-        backups.mkdir(parents=True, exist_ok=True)
-    except OSError as e:
-        logger.debug("Failed to create backups dir %s: %s", backups, e)
-        return None
-
-    # Uniquify: if a snapshot with the same second already exists (can
-    # happen if two curator runs fire in the same second), append a short
-    # counter. Avoids clobbering and avoids timestamp collisions.
-    base_id = _utc_id()
-    snap_id = base_id
-    counter = 1
-    while (backups / snap_id).exists():
-        snap_id = f"{base_id}-{counter:02d}"
-        counter += 1
-
-    dest = backups / snap_id
-    try:
-        dest.mkdir(parents=True, exist_ok=False)
-    except OSError as e:
-        logger.debug("Failed to create snapshot dir %s: %s", dest, e)
-        return None
-
-    archive = dest / "skills.tar.gz"
-    try:
-        # Stream into the tarball — no tempdir copy needed.
-        with tarfile.open(archive, "w:gz", compresslevel=6) as tf:
-            for entry in sorted(skills.iterdir()):
-                if entry.name in _EXCLUDE_TOP_LEVEL:
-                    continue
-                # arcname: store paths relative to skills/ so extraction
-                # drops cleanly back into the skills dir.
-                tf.add(str(entry), arcname=entry.name, recursive=True)
-        # Capture cron/jobs.json alongside the tarball. Never fails the
-        # snapshot — the skills side is the core guarantee; cron is
-        # additive. We still record in the manifest whether it was
-        # captured so rollback can surface "no cron data in this snapshot".
-        cron_info = _backup_cron_jobs_into(dest)
-        _write_manifest(dest, reason, archive,
-                        _count_skill_files(skills),
-                        cron_info=cron_info)
-    except (OSError, tarfile.TarError) as e:
-        logger.debug("Curator snapshot failed: %s", e, exc_info=True)
-        # Clean up partial snapshot
-        try:
-            shutil.rmtree(dest, ignore_errors=True)
-        except OSError:
-            pass
-        return None
-
-    _prune_old(keep=get_keep())
-    logger.info("Curator snapshot created: %s (%s)", snap_id, reason)
-    return dest
-
-
-def _prune_old(keep: int) -> List[str]:
-    """Delete regular snapshots beyond the newest *keep*. Returns deleted
-    ids. Staging dirs (``.rollback-staging-*``) are implementation detail
-    and pruned independently on every call."""
-    backups = _backups_dir()
-    if not backups.exists():
-        return []
-    entries: List[Tuple[str, Path]] = []
-    stale_staging: List[Path] = []
-    for child in backups.iterdir():
-        if not child.is_dir():
-            continue
-        if child.name.startswith(".rollback-staging-"):
-            # Staging dirs are only supposed to exist briefly during a
-            # rollback. If we find one here (e.g. from a crashed rollback),
-            # clean it up opportunistically.
-            stale_staging.append(child)
-            continue
-        if _ID_RE.match(child.name):
-            entries.append((child.name, child))
-    # Newest first (lexicographic works because the id is UTC ISO).
-    entries.sort(key=lambda t: t[0], reverse=True)
-    deleted: List[str] = []
-    for _, path in entries[keep:]:
-        try:
-            shutil.rmtree(path)
-            deleted.append(path.name)
-        except OSError as e:
-            logger.debug("Failed to prune %s: %s", path, e)
-    for path in stale_staging:
-        try:
-            shutil.rmtree(path)
-        except OSError as e:
-            logger.debug("Failed to clean stale staging dir %s: %s", path, e)
-    return deleted
-
-
-# ---------------------------------------------------------------------------
-# List + rollback
-# ---------------------------------------------------------------------------
-
-def _read_manifest(snap_dir: Path) -> Dict[str, Any]:
-    mf = snap_dir / "manifest.json"
-    if not mf.exists():
-        return {}
-    try:
-        return json.loads(mf.read_text(encoding="utf-8"))
-    except (OSError, json.JSONDecodeError):
-        return {}
-
-
-def list_backups() -> List[Dict[str, Any]]:
-    """Return all restorable snapshots, newest first. Only entries with a
-    real ``skills.tar.gz`` tarball are listed — transient
-    ``.rollback-staging-*`` directories created mid-rollback are
-    implementation detail and not shown."""
-    backups = _backups_dir()
-    if not backups.exists():
-        return []
-    out: List[Dict[str, Any]] = []
-    for child in sorted(backups.iterdir(), reverse=True):
-        if not child.is_dir():
-            continue
-        if not _ID_RE.match(child.name):
-            continue
-        if not (child / "skills.tar.gz").exists():
-            continue
-        mf = _read_manifest(child)
-        mf.setdefault("id", child.name)
-        mf.setdefault("path", str(child))
-        if "archive_bytes" not in mf:
-            arc = child / "skills.tar.gz"
-            try:
-                mf["archive_bytes"] = arc.stat().st_size
-            except OSError:
-                mf["archive_bytes"] = 0
-        out.append(mf)
-    return out
-
-
-def _resolve_backup(backup_id: Optional[str]) -> Optional[Path]:
-    """Return the path of the requested backup, or the newest one if
-    *backup_id* is None. Returns None if no match."""
-    backups = _backups_dir()
-    if not backups.exists():
-        return None
-    if backup_id:
-        target = backups / backup_id
-        if (
-            target.is_dir()
-            and _ID_RE.match(backup_id)
-            and (target / "skills.tar.gz").exists()
-        ):
-            return target
-        return None
-    candidates = [
-        c for c in sorted(backups.iterdir(), reverse=True)
-        if c.is_dir() and _ID_RE.match(c.name) and (c / "skills.tar.gz").exists()
-    ]
-    return candidates[0] if candidates else None
-
-
-def _restore_cron_skill_links(snapshot_dir: Path) -> Dict[str, Any]:
-    """Reconcile backed-up cron skill links into the live ``cron/jobs.json``.
-
-    We do NOT overwrite the whole cron file. Only the ``skills`` and
-    ``skill`` fields are restored, and only on jobs that still exist in the
-    current file (matched by ``id``). Everything else about the job —
-    schedule, next_run_at, last_run_at, enabled, prompt, workdir, hooks —
-    is live state that the user/scheduler has modified since the snapshot;
-    overwriting it would regress unrelated cron activity.
-
-    Rules:
-    - Jobs present in backup AND live, with differing skills → skills restored.
-    - Jobs present in backup AND live, with matching skills → no-op.
-    - Jobs present in backup but gone from live (user deleted the job
-      after the snapshot) → skipped, noted in the return report.
-    - Jobs present in live but not in backup (user created a new cron
-      job after the snapshot) → left untouched.
-
-    Never raises; failures are captured in the return dict. Writes through
-    ``cron.jobs`` to pick up the same lock + atomic-write path that tick()
-    uses, so we don't race the scheduler.
-    """
-    report: Dict[str, Any] = {
-        "attempted": False,
-        "restored": [],
-        "skipped_missing": [],
-        "unchanged": 0,
-        "error": None,
-    }
-    backup_file = snapshot_dir / CRON_JOBS_FILENAME
-    if not backup_file.exists():
-        report["error"] = f"snapshot has no {CRON_JOBS_FILENAME}"
-        return report
-
-    try:
-        backup_text = backup_file.read_text(encoding="utf-8")
-        backup_parsed = json.loads(backup_text)
-    except (OSError, json.JSONDecodeError) as e:
-        report["error"] = f"failed to load backed-up jobs: {e}"
-        return report
-    # jobs.json on disk is `{"jobs": [...], "updated_at": ...}`; accept both
-    # that shape and a bare list for forward compat.
-    if isinstance(backup_parsed, dict):
-        backup_jobs = backup_parsed.get("jobs")
-    elif isinstance(backup_parsed, list):
-        backup_jobs = backup_parsed
-    else:
-        backup_jobs = None
-    if not isinstance(backup_jobs, list):
-        report["error"] = "backed-up cron-jobs.json has no jobs list"
-        return report
-
-    # Build a lookup of the backed-up skill state keyed by job id.
-    # We only need the two skill-ish fields (legacy single and modern list).
-    backup_by_id: Dict[str, Dict[str, Any]] = {}
-    for job in backup_jobs:
-        if not isinstance(job, dict):
-            continue
-        jid = job.get("id")
-        if not isinstance(jid, str) or not jid:
-            continue
-        backup_by_id[jid] = {
-            "skills": job.get("skills"),
-            "skill": job.get("skill"),
-            "name": job.get("name") or jid,
-        }
-
-    if not backup_by_id:
-        report["attempted"] = True  # we tried but there was nothing to do
-        return report
-
-    # Load and rewrite the live jobs under the scheduler's lock.
-    try:
-        from cron.jobs import load_jobs, save_jobs, _jobs_file_lock
-    except ImportError as e:
-        report["error"] = f"cron module unavailable: {e}"
-        return report
-
-    report["attempted"] = True
-    try:
-        with _jobs_file_lock:
-            live_jobs = load_jobs()
-            changed = False
-
-            live_ids = set()
-            for live in live_jobs:
-                if not isinstance(live, dict):
-                    continue
-                jid = live.get("id")
-                if not isinstance(jid, str) or not jid:
-                    continue
-                live_ids.add(jid)
-
-                backup = backup_by_id.get(jid)
-                if backup is None:
-                    continue  # live job didn't exist at snapshot time
-
-                cur_skills = live.get("skills")
-                cur_skill = live.get("skill")
-                bkp_skills = backup.get("skills")
-                bkp_skill = backup.get("skill")
-
-                if cur_skills == bkp_skills and cur_skill == bkp_skill:
-                    report["unchanged"] += 1
-                    continue
-
-                # Restore. Preserve absence (don't force the key to appear
-                # if the backup didn't have it either).
-                if bkp_skills is None:
-                    live.pop("skills", None)
-                else:
-                    live["skills"] = bkp_skills
-                if bkp_skill is None:
-                    live.pop("skill", None)
-                else:
-                    live["skill"] = bkp_skill
-
-                report["restored"].append({
-                    "job_id": jid,
-                    "job_name": backup.get("name") or jid,
-                    "from": {"skills": cur_skills, "skill": cur_skill},
-                    "to": {"skills": bkp_skills, "skill": bkp_skill},
-                })
-                changed = True
-
-            # Jobs in backup but not in live = user deleted them after snapshot
-            for jid, backup in backup_by_id.items():
-                if jid not in live_ids:
-                    report["skipped_missing"].append({
-                        "job_id": jid,
-                        "job_name": backup.get("name") or jid,
-                    })
-
-            if changed:
-                save_jobs(live_jobs)
-    except Exception as e:  # noqa: BLE001 — rollback must not die mid-restore
-        logger.debug("Cron skill-link restore failed: %s", e, exc_info=True)
-        report["error"] = f"restore failed mid-flight: {e}"
-
-    return report
-
-
-
-def rollback(backup_id: Optional[str] = None) -> Tuple[bool, str, Optional[Path]]:
-    """Restore ``~/.hermes/skills/`` from a snapshot.
-
-    Strategy:
-      1. Resolve the target snapshot (explicit id or newest regular).
-      2. Take a safety snapshot of the CURRENT skills tree under
-         ``.curator_backups/pre-rollback-<ts>/`` so the rollback itself is
-         undoable.
-      3. Move all current top-level entries (except ``.curator_backups``
-         and ``.hub``) into a tempdir.
-      4. Extract the chosen snapshot into ``~/.hermes/skills/``.
-      5. On failure during 4, move the tempdir contents back (best-effort)
-         and return failure.
-
-    Returns ``(ok, message, snapshot_path)``.
-    """
-    target = _resolve_backup(backup_id)
-    if target is None:
-        return (
-            False,
-            f"no matching backup found"
-            + (f" for id '{backup_id}'" if backup_id else "")
-            + " (use `hermes curator rollback --list` to see available snapshots)",
-            None,
-        )
-    archive = target / "skills.tar.gz"
-    if not archive.exists():
-        return (False, f"snapshot {target.name} has no skills.tar.gz — corrupted?", None)
-
-    skills = _skills_dir()
-    skills.mkdir(parents=True, exist_ok=True)
-    backups = _backups_dir()
-    backups.mkdir(parents=True, exist_ok=True)
-
-    # Step 2: safety snapshot of current state FIRST. If this fails we bail
-    # out before touching anything — otherwise a failed extract could leave
-    # the user with no skills.
-    try:
-        snapshot_skills(reason=f"pre-rollback to {target.name}")
-    except Exception as e:
-        return (False, f"pre-rollback safety snapshot failed: {e}", None)
-
-    # Additionally move current entries into an internal staging dir so
-    # the extract happens into an empty skills tree (predictable result).
-    # This dir is implementation detail — not listed as a restorable
-    # backup. The safety snapshot above is the user-facing undo handle.
-    staged = backups / f".rollback-staging-{_utc_id()}"
-    try:
-        staged.mkdir(parents=True, exist_ok=False)
-    except OSError as e:
-        return (False, f"failed to create staging dir: {e}", None)
-
-    moved: List[Tuple[Path, Path]] = []
-    try:
-        for entry in list(skills.iterdir()):
-            if entry.name in _EXCLUDE_TOP_LEVEL:
-                continue
-            dest = staged / entry.name
-            shutil.move(str(entry), str(dest))
-            moved.append((entry, dest))
-    except OSError as e:
-        # Best-effort rollback of the move
-        for orig, dest in moved:
-            try:
-                shutil.move(str(dest), str(orig))
-            except OSError:
-                pass
-        try:
-            shutil.rmtree(staged, ignore_errors=True)
-        except OSError:
-            pass
-        return (False, f"failed to stage current skills: {e}", None)
-
-    # Step 4: extract the snapshot into skills/
-    try:
-        with tarfile.open(archive, "r:gz") as tf:
-            # Python 3.12+ supports filter='data' for safer extraction.
-            # Fall back to the unfiltered call for older interpreters but
-            # still reject absolute paths and .. components defensively.
-            for member in tf.getmembers():
-                name = member.name
-                if name.startswith("/") or ".." in Path(name).parts:
-                    raise tarfile.TarError(
-                        f"refusing to extract unsafe path: {name!r}"
-                    )
-            try:
-                tf.extractall(str(skills), filter="data")  # type: ignore[call-arg]
-            except TypeError:
-                # Python < 3.12 — no filter kwarg
-                tf.extractall(str(skills))
-    except (OSError, tarfile.TarError) as e:
-        # Best-effort recover: move staged contents back
-        for orig, dest in moved:
-            try:
-                shutil.move(str(dest), str(orig))
-            except OSError:
-                pass
-        try:
-            shutil.rmtree(staged, ignore_errors=True)
-        except OSError:
-            pass
-        return (False, f"snapshot extract failed (state restored): {e}", None)
-
-    # Extract succeeded — the staging dir has served its purpose. The
-    # user's undo handle is the safety snapshot tarball we took earlier.
-    try:
-        shutil.rmtree(staged, ignore_errors=True)
-    except OSError:
-        pass
-
-    # Reconcile cron skill-links. Surgical: only the skills/skill fields
-    # on jobs matched by id. Everything else in jobs.json is live state
-    # (schedule, next_run_at, enabled, prompt, etc.) and we leave it
-    # alone. Failures here don't fail the overall rollback — the skills
-    # tree is already restored, which is the main guarantee.
-    cron_report = _restore_cron_skill_links(target)
-
-    summary_bits = [f"restored from snapshot {target.name}"]
-    if cron_report.get("attempted"):
-        restored_n = len(cron_report.get("restored") or [])
-        skipped_n = len(cron_report.get("skipped_missing") or [])
-        if cron_report.get("error"):
-            summary_bits.append(f"cron links: error — {cron_report['error']}")
-        elif restored_n == 0 and skipped_n == 0 and cron_report.get("unchanged", 0) == 0:
-            # Attempted but nothing matched — empty snapshot or no overlapping ids.
-            pass
-        else:
-            parts = []
-            if restored_n:
-                parts.append(f"{restored_n} job(s) had skill links restored")
-            if skipped_n:
-                parts.append(f"{skipped_n} backed-up job(s) no longer exist (skipped)")
-            if cron_report.get("unchanged"):
-                parts.append(f"{cron_report['unchanged']} already matched")
-            summary_bits.append("cron links: " + ", ".join(parts))
-
-    logger.info("Curator rollback: restored from %s (cron_report=%s)",
-                target.name, cron_report)
-    return (True, "; ".join(summary_bits), target)
-
-
-# ---------------------------------------------------------------------------
-# Human-readable summary for CLI
-# ---------------------------------------------------------------------------
-
-def format_size(n: int) -> str:
-    for unit in ("B", "KB", "MB", "GB"):
-        if n < 1024 or unit == "GB":
-            return f"{n:.1f} {unit}" if unit != "B" else f"{n} B"
-        n /= 1024
-    return f"{n:.1f} GB"
-
-
-def summarize_backups() -> str:
-    rows = list_backups()
-    if not rows:
-        return "No curator snapshots yet."
-    lines = [f"{'id':<24}  {'reason':<40}  {'skills':>6}  {'size':>8}"]
-    lines.append("─" * len(lines[0]))
-    for r in rows:
-        lines.append(
-            f"{r.get('id','?'):<24}  "
-            f"{(r.get('reason','?') or '?')[:40]:<40}  "
-            f"{r.get('skill_files', 0):>6}  "
-            f"{format_size(int(r.get('archive_bytes', 0))):>8}"
-        )
-    return "\n".join(lines)

agent/manual_compression_feedback.py

@@ -20,25 +20,25 @@ def summarize_manual_compression(
         headline = f"No changes from compression: {before_count} messages"
         if after_tokens == before_tokens:
             token_line = (
-                f"Approx request size: ~{before_tokens:,} tokens (unchanged)"
+                f"Rough transcript estimate: ~{before_tokens:,} tokens (unchanged)"
             )
         else:
             token_line = (
-                f"Approx request size: ~{before_tokens:,} → "
+                f"Rough transcript estimate: ~{before_tokens:,} → "
                 f"~{after_tokens:,} tokens"
             )
     else:
         headline = f"Compressed: {before_count} → {after_count} messages"
         token_line = (
-            f"Approx request size: ~{before_tokens:,} → "
+            f"Rough transcript estimate: ~{before_tokens:,} → "
             f"~{after_tokens:,} tokens"
         )
 
     note = None
     if not noop and after_count < before_count and after_tokens > before_tokens:
         note = (
-            "Note: fewer messages can still raise this estimate when "
-            "compression rewrites the transcript into denser summaries."
+            "Note: fewer messages can still raise this rough transcript estimate "
+            "when compression rewrites the transcript into denser summaries."
         )
 
     return {

agent/moonshot_schema.py

@@ -81,56 +81,15 @@ def _repair_schema(node: Any, is_schema: bool = True) -> Any:
         return repaired
 
     # Rule 2: when anyOf is present, type belongs only on the children.
-    # Additionally, Moonshot rejects null-type branches inside anyOf
-    # (enum value (<nil>) does not match any type in [string]).
-    # Collapse the anyOf to the first non-null branch and infer its type.
     if "anyOf" in repaired and isinstance(repaired["anyOf"], list):
         repaired.pop("type", None)
-        non_null = [b for b in repaired["anyOf"]
-                    if isinstance(b, dict) and b.get("type") != "null"]
-        if non_null and len(non_null) < len(repaired["anyOf"]):
-            # Drop the anyOf wrapper — keep only the non-null branch.
-            # If there's a single non-null branch, promote it and fall
-            # through to Rules 1/3 so nullable/enum cleanup still applies
-            # to the merged node.
-            if len(non_null) == 1:
-                merge = {k: v for k, v in repaired.items() if k != "anyOf"}
-                merge.update(non_null[0])
-                repaired = merge
-            else:
-                repaired["anyOf"] = non_null
-                return repaired
-        else:
-            # Nothing to collapse — parent type stripped, children already
-            # repaired by the recursive walk above.
-            return repaired
-
-    # Moonshot also rejects non-standard keywords like ``nullable`` on
-    # parameter schemas — strip it.
-    repaired.pop("nullable", None)
+        return repaired
 
     # Rule 1: property schemas without type need one.  $ref nodes are exempt
     # — their type comes from the referenced definition.
-    # Fill missing type BEFORE Rule 3 so enum cleanup can check the type.
-    if "$ref" not in repaired:
-        repaired = _fill_missing_type(repaired)
-
-    # Rule 3: Moonshot rejects null/empty-string values inside enum arrays
-    # when the parent type is a scalar (string, integer, etc.).  The error:
-    #   "enum value (<nil>) does not match any type in [string]"
-    # Strip null and empty-string from enum values, and if the enum becomes
-    # empty, drop it entirely.
-    if "enum" in repaired and isinstance(repaired["enum"], list):
-        node_type = repaired.get("type")
-        if node_type in ("string", "integer", "number", "boolean"):
-            cleaned = [v for v in repaired["enum"]
-                       if v is not None and v != ""]
-            if cleaned:
-                repaired["enum"] = cleaned
-            else:
-                repaired.pop("enum")
-
-    return repaired
+    if "$ref" in repaired:
+        return repaired
+    return _fill_missing_type(repaired)
 
 
 def _fill_missing_type(node: Dict[str, Any]) -> Dict[str, Any]:

agent/skill_commands.py

@@ -6,7 +6,6 @@ can invoke skills via /skill-name commands.
 
 import json
 import logging
-import os
 import re
 from pathlib import Path
 from typing import Any, Dict, Optional
@@ -21,35 +20,10 @@ from agent.skill_preprocessing import (
 logger = logging.getLogger(__name__)
 
 _skill_commands: Dict[str, Dict[str, Any]] = {}
-_skill_commands_platform: Optional[str] = None
 # Patterns for sanitizing skill names into clean hyphen-separated slugs.
 _SKILL_INVALID_CHARS = re.compile(r"[^a-z0-9-]")
 _SKILL_MULTI_HYPHEN = re.compile(r"-{2,}")
 
-
-def _resolve_skill_commands_platform() -> Optional[str]:
-    """Return the current platform scope used for disabled-skill filtering.
-
-    Used to detect when the active platform has shifted so
-    :func:`get_skill_commands` can drop a stale cache that was populated
-    for a different platform's ``skills.platform_disabled`` view (#14536).
-
-    Resolves from (in order) ``HERMES_PLATFORM`` env var and
-    ``HERMES_SESSION_PLATFORM`` from the gateway session context. Returns
-    ``None`` when no platform scope is active (e.g. classic CLI, RL
-    rollouts, standalone scripts).
-    """
-    try:
-        from gateway.session_context import get_session_env
-
-        resolved_platform = (
-            os.getenv("HERMES_PLATFORM")
-            or get_session_env("HERMES_SESSION_PLATFORM")
-        )
-    except Exception:
-        resolved_platform = os.getenv("HERMES_PLATFORM")
-    return resolved_platform or None
-
 def _load_skill_payload(skill_identifier: str, task_id: str | None = None) -> tuple[dict[str, Any], Path | None, str] | None:
     """Load a skill by name/path and return (loaded_payload, skill_dir, display_name)."""
     raw_identifier = (skill_identifier or "").strip()
@@ -244,8 +218,7 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
     Returns:
         Dict mapping "/skill-name" to {name, description, skill_md_path, skill_dir}.
     """
-    global _skill_commands, _skill_commands_platform
-    _skill_commands_platform = _resolve_skill_commands_platform()
+    global _skill_commands
     _skill_commands = {}
     try:
         from tools.skills_tool import SKILLS_DIR, _parse_frontmatter, skill_matches_platform, _get_disabled_skill_names
@@ -305,16 +278,8 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
 
 
 def get_skill_commands() -> Dict[str, Dict[str, Any]]:
-    """Return the current skill commands mapping (scan first if empty).
-
-    Rescans when the active platform scope changes (e.g. a gateway
-    process serving Telegram and Discord concurrently) so each platform
-    sees its own ``skills.platform_disabled`` view (#14536).
-    """
-    if (
-        not _skill_commands
-        or _skill_commands_platform != _resolve_skill_commands_platform()
-    ):
+    """Return the current skill commands mapping (scan first if empty)."""
+    if not _skill_commands:
         scan_skill_commands()
     return _skill_commands
 

agent/tool_guardrails.py

@@ -1,455 +0,0 @@
-"""Pure tool-call loop guardrail primitives.
-
-The controller in this module is intentionally side-effect free: it tracks
-per-turn tool-call observations and returns decisions. Runtime code owns whether
-those decisions become warning guidance, synthetic tool results, or controlled
-turn halts.
-"""
-
-from __future__ import annotations
-
-import hashlib
-import json
-from dataclasses import dataclass, field
-from typing import Any, Mapping
-
-from utils import safe_json_loads
-
-
-IDEMPOTENT_TOOL_NAMES = frozenset(
-    {
-        "read_file",
-        "search_files",
-        "web_search",
-        "web_extract",
-        "session_search",
-        "browser_snapshot",
-        "browser_console",
-        "browser_get_images",
-        "mcp_filesystem_read_file",
-        "mcp_filesystem_read_text_file",
-        "mcp_filesystem_read_multiple_files",
-        "mcp_filesystem_list_directory",
-        "mcp_filesystem_list_directory_with_sizes",
-        "mcp_filesystem_directory_tree",
-        "mcp_filesystem_get_file_info",
-        "mcp_filesystem_search_files",
-    }
-)
-
-MUTATING_TOOL_NAMES = frozenset(
-    {
-        "terminal",
-        "execute_code",
-        "write_file",
-        "patch",
-        "todo",
-        "memory",
-        "skill_manage",
-        "browser_click",
-        "browser_type",
-        "browser_press",
-        "browser_scroll",
-        "browser_navigate",
-        "send_message",
-        "cronjob",
-        "delegate_task",
-        "process",
-    }
-)
-
-
-@dataclass(frozen=True)
-class ToolCallGuardrailConfig:
-    """Thresholds for per-turn tool-call loop detection.
-
-    Warnings are enabled by default and never prevent tool execution. Hard stops
-    are explicit opt-in so interactive CLI/TUI sessions get a gentle nudge unless
-    the user enables circuit-breaker behavior in config.yaml.
-    """
-
-    warnings_enabled: bool = True
-    hard_stop_enabled: bool = False
-    exact_failure_warn_after: int = 2
-    exact_failure_block_after: int = 5
-    same_tool_failure_warn_after: int = 3
-    same_tool_failure_halt_after: int = 8
-    no_progress_warn_after: int = 2
-    no_progress_block_after: int = 5
-    idempotent_tools: frozenset[str] = field(default_factory=lambda: IDEMPOTENT_TOOL_NAMES)
-    mutating_tools: frozenset[str] = field(default_factory=lambda: MUTATING_TOOL_NAMES)
-
-    @classmethod
-    def from_mapping(cls, data: Mapping[str, Any] | None) -> "ToolCallGuardrailConfig":
-        """Build config from the `tool_loop_guardrails` config.yaml section."""
-        if not isinstance(data, Mapping):
-            return cls()
-
-        warn_after = data.get("warn_after")
-        if not isinstance(warn_after, Mapping):
-            warn_after = {}
-        hard_stop_after = data.get("hard_stop_after")
-        if not isinstance(hard_stop_after, Mapping):
-            hard_stop_after = {}
-
-        defaults = cls()
-        return cls(
-            warnings_enabled=_as_bool(data.get("warnings_enabled"), defaults.warnings_enabled),
-            hard_stop_enabled=_as_bool(data.get("hard_stop_enabled"), defaults.hard_stop_enabled),
-            exact_failure_warn_after=_positive_int(
-                warn_after.get("exact_failure", data.get("exact_failure_warn_after")),
-                defaults.exact_failure_warn_after,
-            ),
-            same_tool_failure_warn_after=_positive_int(
-                warn_after.get("same_tool_failure", data.get("same_tool_failure_warn_after")),
-                defaults.same_tool_failure_warn_after,
-            ),
-            no_progress_warn_after=_positive_int(
-                warn_after.get("idempotent_no_progress", data.get("no_progress_warn_after")),
-                defaults.no_progress_warn_after,
-            ),
-            exact_failure_block_after=_positive_int(
-                hard_stop_after.get("exact_failure", data.get("exact_failure_block_after")),
-                defaults.exact_failure_block_after,
-            ),
-            same_tool_failure_halt_after=_positive_int(
-                hard_stop_after.get("same_tool_failure", data.get("same_tool_failure_halt_after")),
-                defaults.same_tool_failure_halt_after,
-            ),
-            no_progress_block_after=_positive_int(
-                hard_stop_after.get("idempotent_no_progress", data.get("no_progress_block_after")),
-                defaults.no_progress_block_after,
-            ),
-        )
-
-
-@dataclass(frozen=True)
-class ToolCallSignature:
-    """Stable, non-reversible identity for a tool name plus canonical args."""
-
-    tool_name: str
-    args_hash: str
-
-    @classmethod
-    def from_call(cls, tool_name: str, args: Mapping[str, Any] | None) -> "ToolCallSignature":
-        canonical = canonical_tool_args(args or {})
-        return cls(tool_name=tool_name, args_hash=_sha256(canonical))
-
-    def to_metadata(self) -> dict[str, str]:
-        """Return public metadata without raw argument values."""
-        return {"tool_name": self.tool_name, "args_hash": self.args_hash}
-
-
-@dataclass(frozen=True)
-class ToolGuardrailDecision:
-    """Decision returned by the tool-call guardrail controller."""
-
-    action: str = "allow"  # allow | warn | block | halt
-    code: str = "allow"
-    message: str = ""
-    tool_name: str = ""
-    count: int = 0
-    signature: ToolCallSignature | None = None
-
-    @property
-    def allows_execution(self) -> bool:
-        return self.action in {"allow", "warn"}
-
-    @property
-    def should_halt(self) -> bool:
-        return self.action in {"block", "halt"}
-
-    def to_metadata(self) -> dict[str, Any]:
-        data: dict[str, Any] = {
-            "action": self.action,
-            "code": self.code,
-            "message": self.message,
-            "tool_name": self.tool_name,
-            "count": self.count,
-        }
-        if self.signature is not None:
-            data["signature"] = self.signature.to_metadata()
-        return data
-
-
-def canonical_tool_args(args: Mapping[str, Any]) -> str:
-    """Return sorted compact JSON for parsed tool arguments."""
-    if not isinstance(args, Mapping):
-        raise TypeError(f"tool args must be a mapping, got {type(args).__name__}")
-    return json.dumps(
-        args,
-        ensure_ascii=False,
-        sort_keys=True,
-        separators=(",", ":"),
-        default=str,
-    )
-
-
-def classify_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]:
-    """Safety-fallback classifier used only when callers don't pass ``failed``.
-
-    Mirrors ``agent.display._detect_tool_failure`` exactly so the guardrail
-    never disagrees with the CLI's user-visible ``[error]`` tag. Production
-    callers in ``run_agent.py`` always pass an explicit ``failed=`` derived
-    from ``_detect_tool_failure``; this function exists so standalone callers
-    (tests, tooling) still get consistent behavior.
-    """
-    if result is None:
-        return False, ""
-
-    if tool_name == "terminal":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
-            exit_code = data.get("exit_code")
-            if exit_code is not None and exit_code != 0:
-                return True, f" [exit {exit_code}]"
-        return False, ""
-
-    if tool_name == "memory":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
-            if data.get("success") is False and "exceed the limit" in data.get("error", ""):
-                return True, " [full]"
-
-    lower = result[:500].lower()
-    if '"error"' in lower or '"failed"' in lower or result.startswith("Error"):
-        return True, " [error]"
-
-    return False, ""
-
-
-class ToolCallGuardrailController:
-    """Per-turn controller for repeated failed/non-progressing tool calls."""
-
-    def __init__(self, config: ToolCallGuardrailConfig | None = None):
-        self.config = config or ToolCallGuardrailConfig()
-        self.reset_for_turn()
-
-    def reset_for_turn(self) -> None:
-        self._exact_failure_counts: dict[ToolCallSignature, int] = {}
-        self._same_tool_failure_counts: dict[str, int] = {}
-        self._no_progress: dict[ToolCallSignature, tuple[str, int]] = {}
-        self._halt_decision: ToolGuardrailDecision | None = None
-
-    @property
-    def halt_decision(self) -> ToolGuardrailDecision | None:
-        return self._halt_decision
-
-    def before_call(self, tool_name: str, args: Mapping[str, Any] | None) -> ToolGuardrailDecision:
-        signature = ToolCallSignature.from_call(tool_name, _coerce_args(args))
-        if not self.config.hard_stop_enabled:
-            return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
-
-        exact_count = self._exact_failure_counts.get(signature, 0)
-        if exact_count >= self.config.exact_failure_block_after:
-            decision = ToolGuardrailDecision(
-                action="block",
-                code="repeated_exact_failure_block",
-                message=(
-                    f"Blocked {tool_name}: the same tool call failed {exact_count} "
-                    "times with identical arguments. Stop retrying it unchanged; "
-                    "change strategy or explain the blocker."
-                ),
-                tool_name=tool_name,
-                count=exact_count,
-                signature=signature,
-            )
-            self._halt_decision = decision
-            return decision
-
-        if self._is_idempotent(tool_name):
-            record = self._no_progress.get(signature)
-            if record is not None:
-                _result_hash, repeat_count = record
-                if repeat_count >= self.config.no_progress_block_after:
-                    decision = ToolGuardrailDecision(
-                        action="block",
-                        code="idempotent_no_progress_block",
-                        message=(
-                            f"Blocked {tool_name}: this read-only call returned the same "
-                            f"result {repeat_count} times. Stop repeating it unchanged; "
-                            "use the result already provided or try a different query."
-                        ),
-                        tool_name=tool_name,
-                        count=repeat_count,
-                        signature=signature,
-                    )
-                    self._halt_decision = decision
-                    return decision
-
-        return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
-
-    def after_call(
-        self,
-        tool_name: str,
-        args: Mapping[str, Any] | None,
-        result: str | None,
-        *,
-        failed: bool | None = None,
-    ) -> ToolGuardrailDecision:
-        args = _coerce_args(args)
-        signature = ToolCallSignature.from_call(tool_name, args)
-        if failed is None:
-            failed, _ = classify_tool_failure(tool_name, result)
-
-        if failed:
-            exact_count = self._exact_failure_counts.get(signature, 0) + 1
-            self._exact_failure_counts[signature] = exact_count
-            self._no_progress.pop(signature, None)
-
-            same_count = self._same_tool_failure_counts.get(tool_name, 0) + 1
-            self._same_tool_failure_counts[tool_name] = same_count
-
-            if self.config.hard_stop_enabled and same_count >= self.config.same_tool_failure_halt_after:
-                decision = ToolGuardrailDecision(
-                    action="halt",
-                    code="same_tool_failure_halt",
-                    message=(
-                        f"Stopped {tool_name}: it failed {same_count} times this turn. "
-                        "Stop retrying the same failing tool path and choose a different approach."
-                    ),
-                    tool_name=tool_name,
-                    count=same_count,
-                    signature=signature,
-                )
-                self._halt_decision = decision
-                return decision
-
-            if self.config.warnings_enabled and exact_count >= self.config.exact_failure_warn_after:
-                return ToolGuardrailDecision(
-                    action="warn",
-                    code="repeated_exact_failure_warning",
-                    message=(
-                        f"{tool_name} has failed {exact_count} times with identical arguments. "
-                        "This looks like a loop; inspect the error and change strategy "
-                        "instead of retrying it unchanged."
-                    ),
-                    tool_name=tool_name,
-                    count=exact_count,
-                    signature=signature,
-                )
-
-            if self.config.warnings_enabled and same_count >= self.config.same_tool_failure_warn_after:
-                return ToolGuardrailDecision(
-                    action="warn",
-                    code="same_tool_failure_warning",
-                    message=(
-                        f"{tool_name} has failed {same_count} times this turn. "
-                        "This looks like a loop; change approach before retrying."
-                    ),
-                    tool_name=tool_name,
-                    count=same_count,
-                    signature=signature,
-                )
-
-            return ToolGuardrailDecision(tool_name=tool_name, count=exact_count, signature=signature)
-
-        self._exact_failure_counts.pop(signature, None)
-        self._same_tool_failure_counts.pop(tool_name, None)
-
-        if not self._is_idempotent(tool_name):
-            self._no_progress.pop(signature, None)
-            return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
-
-        result_hash = _result_hash(result)
-        previous = self._no_progress.get(signature)
-        repeat_count = 1
-        if previous is not None and previous[0] == result_hash:
-            repeat_count = previous[1] + 1
-        self._no_progress[signature] = (result_hash, repeat_count)
-
-        if self.config.warnings_enabled and repeat_count >= self.config.no_progress_warn_after:
-            return ToolGuardrailDecision(
-                action="warn",
-                code="idempotent_no_progress_warning",
-                message=(
-                    f"{tool_name} returned the same result {repeat_count} times. "
-                    "Use the result already provided or change the query instead of "
-                    "repeating it unchanged."
-                ),
-                tool_name=tool_name,
-                count=repeat_count,
-                signature=signature,
-            )
-
-        return ToolGuardrailDecision(tool_name=tool_name, count=repeat_count, signature=signature)
-
-    def _is_idempotent(self, tool_name: str) -> bool:
-        if tool_name in self.config.mutating_tools:
-            return False
-        return tool_name in self.config.idempotent_tools
-
-
-def toolguard_synthetic_result(decision: ToolGuardrailDecision) -> str:
-    """Build a synthetic role=tool content string for a blocked tool call."""
-    return json.dumps(
-        {
-            "error": decision.message,
-            "guardrail": decision.to_metadata(),
-        },
-        ensure_ascii=False,
-    )
-
-
-def append_toolguard_guidance(result: str, decision: ToolGuardrailDecision) -> str:
-    """Append runtime guidance to the current tool result content."""
-    if decision.action not in {"warn", "halt"} or not decision.message:
-        return result
-    label = "Tool loop hard stop" if decision.action == "halt" else "Tool loop warning"
-    suffix = (
-        f"\n\n[{label}: "
-        f"{decision.code}; count={decision.count}; {decision.message}]"
-    )
-    return (result or "") + suffix
-
-
-def _coerce_args(args: Mapping[str, Any] | None) -> Mapping[str, Any]:
-    return args if isinstance(args, Mapping) else {}
-
-
-def _result_hash(result: str | None) -> str:
-    parsed = safe_json_loads(result or "")
-    if parsed is not None:
-        try:
-            canonical = json.dumps(
-                parsed,
-                ensure_ascii=False,
-                sort_keys=True,
-                separators=(",", ":"),
-                default=str,
-            )
-        except TypeError:
-            canonical = str(parsed)
-    else:
-        canonical = result or ""
-    return _sha256(canonical)
-
-
-def _as_bool(value: Any, default: bool) -> bool:
-    if value is None:
-        return default
-    if isinstance(value, bool):
-        return value
-    if isinstance(value, (int, float)):
-        return bool(value)
-    if isinstance(value, str):
-        lowered = value.strip().lower()
-        if lowered in {"1", "true", "yes", "on", "enabled"}:
-            return True
-        if lowered in {"0", "false", "no", "off", "disabled"}:
-            return False
-    return default
-
-
-def _positive_int(value: Any, default: int) -> int:
-    if value is None:
-        return default
-    try:
-        parsed = int(value)
-    except (TypeError, ValueError):
-        return default
-    return parsed if parsed >= 1 else default
-
-
-def _sha256(value: str) -> str:
-    return hashlib.sha256(value.encode("utf-8")).hexdigest()

cli-config.yaml.example

@@ -121,18 +121,6 @@ model:
 #   # Data policy: "allow" (default) or "deny" to exclude providers that may store data
 #   # data_collection: "deny"
 
-# =============================================================================
-# OpenRouter Response Caching (only applies when using OpenRouter)
-# =============================================================================
-# Cache identical API responses at the OpenRouter edge for free instant replays.
-# When enabled, identical requests (same model, messages, parameters) return
-# cached responses with zero billing. Separate from Anthropic prompt caching.
-# See: https://openrouter.ai/docs/guides/features/response-caching
-#
-# openrouter:
-#   response_cache: true         # Enable response caching (default: true)
-#   response_cache_ttl: 300      # Cache TTL in seconds, 1-86400 (default: 300)
-
 # =============================================================================
 # Git Worktree Isolation
 # =============================================================================
@@ -301,25 +289,6 @@ browser:
   # after this period of no activity between agent loops (default: 120 = 2 minutes)
   inactivity_timeout: 120
 
-# =============================================================================
-# Tool Loop Guardrails
-# =============================================================================
-# Soft warnings are enabled by default. They append guidance to repeated failed
-# or non-progressing tool results but still let the tool execute. Hard stops are
-# opt-in circuit breakers for autonomous/cron sessions where stopping a loop is
-# preferable to spending the full iteration budget.
-tool_loop_guardrails:
-  warnings_enabled: true
-  hard_stop_enabled: false
-  warn_after:
-    exact_failure: 2
-    same_tool_failure: 3
-    idempotent_no_progress: 2
-  hard_stop_after:
-    exact_failure: 5
-    same_tool_failure: 8
-    idempotent_no_progress: 5
-
 # =============================================================================
 # Context Compression (Auto-shrinks long conversations)
 # =============================================================================

cli.py

@@ -15,6 +15,7 @@ Usage:
 
 import logging
 import os
+import re
 import shutil
 import sys
 import json
@@ -85,7 +86,7 @@ from hermes_cli.browser_connect import (
     try_launch_chrome_debug,
 )
 from hermes_cli.env_loader import load_hermes_dotenv
-from utils import base_url_host_matches, is_truthy_value
+from utils import base_url_host_matches
 
 _hermes_home = get_hermes_home()
 _project_env = Path(__file__).parent / '.env'
@@ -599,7 +600,6 @@ def load_cli_config() -> Dict[str, Any]:
 # Load configuration at module startup
 CLI_CONFIG = load_cli_config()
 
-
 # Initialize centralized logging early — agent.log + errors.log in ~/.hermes/logs/.
 # This ensures CLI sessions produce a log trail even before AIAgent is instantiated.
 try:
@@ -934,20 +934,6 @@ def _run_state_db_auto_maintenance(session_db) -> None:
     try:
         from hermes_cli.config import load_config as _load_full_config
         from hermes_constants import get_hermes_home as _get_hermes_home
-        _hermes_home_maint = _get_hermes_home()
-
-        # One-time prune of empty TUI ghost sessions.
-        try:
-            if not session_db.get_meta("ghost_session_prune_v1"):
-                pruned = session_db.prune_empty_ghost_sessions(
-                    sessions_dir=_hermes_home_maint / "sessions"
-                )
-                session_db.set_meta("ghost_session_prune_v1", "1")
-                if pruned:
-                    logger.info("Pruned %d empty TUI ghost sessions", pruned)
-        except Exception as _prune_exc:
-            logger.debug("Ghost session prune skipped: %s", _prune_exc)
-
         cfg = (_load_full_config().get("sessions") or {})
         if not cfg.get("auto_prune", False):
             return
@@ -955,7 +941,7 @@ def _run_state_db_auto_maintenance(session_db) -> None:
             retention_days=int(cfg.get("retention_days", 90)),
             min_interval_hours=int(cfg.get("min_interval_hours", 24)),
             vacuum=bool(cfg.get("vacuum_after_prune", True)),
-            sessions_dir=_hermes_home_maint / "sessions",
+            sessions_dir=_get_hermes_home() / "sessions",
         )
     except Exception as exc:
         logger.debug("state.db auto-maintenance skipped: %s", exc)
@@ -2132,8 +2118,6 @@ class HermesCLI:
         
         # Parse and validate toolsets
         self.enabled_toolsets = toolsets
-        self.disabled_toolsets = CLI_CONFIG["agent"].get("disabled_toolsets") or []
-
         if toolsets and "all" not in toolsets and "*" not in toolsets:
             # Validate each toolset — MCP server names are resolved via
             # live registry aliases (registered during discover_mcp_tools),
@@ -2928,14 +2912,7 @@ class HermesCLI:
 
         def _expand_ref(match):
             path = Path(match.group(1))
-            # Use try/except instead of path.exists() to avoid TOCTOU race:
-            # the paste file may be deleted between check and read, causing
-            # the input to be silently dropped (#17666).
-            try:
-                return path.read_text(encoding="utf-8")
-            except (OSError, IOError):
-                logger.warning("Paste file gone or unreadable, returning placeholder: %s", path)
-                return match.group(0)
+            return path.read_text(encoding="utf-8") if path.exists() else match.group(0)
 
         return paste_ref_re.sub(_expand_ref, text)
 
@@ -3591,7 +3568,6 @@ class HermesCLI:
                 credential_pool=runtime.get("credential_pool"),
                 max_iterations=self.max_turns,
                 enabled_toolsets=self.enabled_toolsets,
-                disabled_toolsets=self.disabled_toolsets,
                 verbose_logging=self.verbose,
                 quiet_mode=not self.verbose,
                 ephemeral_system_prompt=self.system_prompt if self.system_prompt else None,
@@ -3639,18 +3615,14 @@ class HermesCLI:
                 tuple(runtime.get("args") or ()),
             )
 
-            # Force-create DB row on /title intent, then apply title.
-            if self._pending_title and self._session_db and self.agent:
+            if self._pending_title and self._session_db:
                 try:
-                    self.agent._ensure_db_session()
-                    if self.agent._session_db_created:
-                        self._session_db.set_session_title(self.session_id, self._pending_title)
-                        _cprint(f"  Session title applied: {self._pending_title}")
-                        self._pending_title = None
-                    # else: row creation failed transiently — keep _pending_title for retry
+                    self._session_db.set_session_title(self.session_id, self._pending_title)
+                    _cprint(f"  Session title applied: {self._pending_title}")
+                    self._pending_title = None
                 except (ValueError, Exception) as e:
                     _cprint(f"  Could not apply pending title: {e}")
-                    # Keep _pending_title so it can be retried after row creation succeeds
+                    self._pending_title = None
             return True
         except Exception as e:
             ChatConsole().print(f"[bold red]Failed to initialize agent: {e}[/]")
@@ -4978,7 +4950,6 @@ class HermesCLI:
 
             if self._session_db:
                 try:
-                    self.agent._session_db_created = False
                     self._session_db.create_session(
                         session_id=self.session_id,
                         source=os.environ.get("HERMES_SESSION_SOURCE", "cli"),
@@ -4988,7 +4959,6 @@ class HermesCLI:
                             "reasoning_config": self.reasoning_config,
                         },
                     )
-                    self.agent._session_db_created = True
                 except Exception:
                     pass
             # Notify memory providers that session_id rotated to a fresh
@@ -6567,8 +6537,6 @@ class HermesCLI:
                 # No active run — treat as a normal next-turn message.
                 self._pending_input.put(payload)
                 _cprint(f"  No agent running; queued as next turn: {payload[:80]}{'...' if len(payload) > 80 else ''}")
-        elif canonical == "goal":
-            self._handle_goal_command(cmd_original)
         elif canonical == "skin":
             self._handle_skin_command(cmd_original)
         elif canonical == "voice":
@@ -6614,17 +6582,12 @@ class HermesCLI:
                     self._console_print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
             # Check for plugin-registered slash commands
             elif base_cmd.lstrip("/") in _get_plugin_cmd_handler_names():
-                from hermes_cli.plugins import (
-                    get_plugin_command_handler,
-                    resolve_plugin_command_result,
-                )
+                from hermes_cli.plugins import get_plugin_command_handler
                 plugin_handler = get_plugin_command_handler(base_cmd.lstrip("/"))
                 if plugin_handler:
                     user_args = cmd_original[len(base_cmd):].strip()
                     try:
-                        result = resolve_plugin_command_result(
-                            plugin_handler(user_args)
-                        )
+                        result = plugin_handler(user_args)
                         if result:
                             _cprint(str(result))
                     except Exception as e:
@@ -7049,166 +7012,6 @@ class HermesCLI:
             print("   status       Show current browser mode")
             print()
 
-    # ────────────────────────────────────────────────────────────────
-    # /goal — persistent cross-turn goals (Ralph-style loop)
-    # ────────────────────────────────────────────────────────────────
-    def _get_goal_manager(self):
-        """Return the GoalManager bound to the current session_id.
-
-        Cached on ``self._goal_manager`` and rebound lazily when
-        ``session_id`` changes (e.g. after /new or a compression-driven
-        session split).
-        """
-        try:
-            from hermes_cli.goals import GoalManager
-            from hermes_cli.config import load_config
-        except Exception as exc:
-            logging.debug("goal manager unavailable: %s", exc)
-            return None
-
-        sid = getattr(self, "session_id", None) or ""
-        if not sid:
-            return None
-
-        existing = getattr(self, "_goal_manager", None)
-        if existing is not None and getattr(existing, "session_id", None) == sid:
-            return existing
-
-        try:
-            cfg = load_config() or {}
-            goals_cfg = cfg.get("goals") or {}
-            max_turns = int(goals_cfg.get("max_turns", 20) or 20)
-        except Exception:
-            max_turns = 20
-
-        mgr = GoalManager(session_id=sid, default_max_turns=max_turns)
-        self._goal_manager = mgr
-        return mgr
-
-    def _handle_goal_command(self, cmd: str) -> None:
-        """Dispatch /goal subcommands: set / status / pause / resume / clear."""
-        parts = (cmd or "").strip().split(None, 1)
-        arg = parts[1].strip() if len(parts) > 1 else ""
-
-        mgr = self._get_goal_manager()
-        if mgr is None:
-            _cprint(f"  {_DIM}Goals unavailable (no active session).{_RST}")
-            return
-
-        lower = arg.lower()
-
-        # Bare /goal or /goal status → show current state
-        if not arg or lower == "status":
-            _cprint(f"  {mgr.status_line()}")
-            return
-
-        if lower == "pause":
-            state = mgr.pause(reason="user-paused")
-            if state is None:
-                _cprint(f"  {_DIM}No goal set.{_RST}")
-            else:
-                _cprint(f"  ⏸ Goal paused: {state.goal}")
-            return
-
-        if lower == "resume":
-            state = mgr.resume()
-            if state is None:
-                _cprint(f"  {_DIM}No goal to resume.{_RST}")
-            else:
-                _cprint(f"  ▶ Goal resumed: {state.goal}")
-                _cprint(
-                    f"  {_DIM}Send any message (or press Enter on an empty prompt "
-                    f"is a no-op; type 'continue' to kick it off).{_RST}"
-                )
-            return
-
-        if lower in ("clear", "stop", "done"):
-            had = mgr.has_goal()
-            mgr.clear()
-            if had:
-                _cprint("  ✓ Goal cleared.")
-            else:
-                _cprint(f"  {_DIM}No active goal.{_RST}")
-            return
-
-        # Otherwise treat the arg as the goal text.
-        try:
-            state = mgr.set(arg)
-        except ValueError as exc:
-            _cprint(f"  Invalid goal: {exc}")
-            return
-
-        _cprint(f"  ⊙ Goal set ({state.max_turns}-turn budget): {state.goal}")
-        _cprint(
-            f"  {_DIM}After each turn, a judge model will check if the goal is done. "
-            f"Hermes keeps working until it is, you pause/clear it, or the budget is "
-            f"exhausted. Use /goal status, /goal pause, /goal resume, /goal clear.{_RST}"
-        )
-        # Kick the loop off immediately so the user doesn't have to send a
-        # separate message after setting the goal.
-        try:
-            self._pending_input.put(state.goal)
-        except Exception:
-            pass
-
-    def _maybe_continue_goal_after_turn(self) -> None:
-        """Hook run after every CLI turn. Judges + maybe re-queues.
-
-        Safe to call when no goal is set — returns quickly.
-
-        Preemption is automatic: if a real user message is already in
-        ``_pending_input`` we skip judging (the user's new input takes
-        priority and we'll re-judge after that turn). If judge says done,
-        mark it done and tell the user. If judge says continue and we're
-        under budget, push the continuation prompt onto the queue.
-        """
-        mgr = self._get_goal_manager()
-        if mgr is None or not mgr.is_active():
-            return
-
-        # If a real user message is already queued, don't inject a
-        # continuation prompt on top — let the user's turn go first.
-        try:
-            if getattr(self, "_pending_input", None) is not None \
-                    and not self._pending_input.empty():
-                return
-        except Exception:
-            pass
-
-        # Extract the agent's final response for this turn.
-        last_response = ""
-        try:
-            hist = self.conversation_history or []
-            for msg in reversed(hist):
-                if msg.get("role") == "assistant":
-                    content = msg.get("content", "")
-                    if isinstance(content, list):
-                        # Multimodal content — flatten text parts.
-                        parts = [
-                            p.get("text", "")
-                            for p in content
-                            if isinstance(p, dict) and p.get("type") in ("text", "output_text")
-                        ]
-                        last_response = "\n".join(t for t in parts if t)
-                    else:
-                        last_response = str(content or "")
-                    break
-        except Exception:
-            last_response = ""
-
-        decision = mgr.evaluate_after_turn(last_response, user_initiated=True)
-        msg = decision.get("message") or ""
-        if msg:
-            _cprint(f"  {msg}")
-
-        if decision.get("should_continue"):
-            prompt = decision.get("continuation_prompt")
-            if prompt:
-                try:
-                    self._pending_input.put(prompt)
-                except Exception as exc:
-                    logging.debug("goal continuation enqueue failed: %s", exc)
-
     def _handle_skin_command(self, cmd: str):
         """Handle /skin [name] — show or change the display skin."""
         try:
@@ -7335,7 +7138,7 @@ class HermesCLI:
         import os
         from hermes_cli.colors import Colors as _Colors
 
-        current = is_truthy_value(os.environ.get("HERMES_YOLO_MODE"))
+        current = bool(os.environ.get("HERMES_YOLO_MODE"))
         if current:
             os.environ.pop("HERMES_YOLO_MODE", None)
             _cprint(
@@ -7532,20 +7335,10 @@ class HermesCLI:
         original_count = len(self.conversation_history)
         with self._busy_command("Compressing context..."):
             try:
-                from agent.model_metadata import estimate_request_tokens_rough
+                from agent.model_metadata import estimate_messages_tokens_rough
                 from agent.manual_compression_feedback import summarize_manual_compression
                 original_history = list(self.conversation_history)
-                # Include system prompt + tool schemas in the estimate —
-                # a transcript-only number understates real request pressure
-                # and can even appear to grow after compression because a
-                # dense handoff summary replaces many short turns (#6217).
-                _sys_prompt = getattr(self.agent, "_cached_system_prompt", "") or ""
-                _tools = getattr(self.agent, "tools", None) or None
-                approx_tokens = estimate_request_tokens_rough(
-                    original_history,
-                    system_prompt=_sys_prompt,
-                    tools=_tools,
-                )
+                approx_tokens = estimate_messages_tokens_rough(original_history)
                 if focus_topic:
                     print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens), "
                           f"focus: \"{focus_topic}\"...")
@@ -7577,11 +7370,7 @@ class HermesCLI:
                 ):
                     self.session_id = self.agent.session_id
                     self._pending_title = None
-                new_tokens = estimate_request_tokens_rough(
-                    self.conversation_history,
-                    system_prompt=_sys_prompt,
-                    tools=_tools,
-                )
+                new_tokens = estimate_messages_tokens_rough(self.conversation_history)
                 summary = summarize_manual_compression(
                     original_history,
                     self.conversation_history,
@@ -11547,17 +11336,6 @@ class HermesCLI:
 
                         app.invalidate()  # Refresh status line
 
-                        # Goal continuation: if a standing goal is active, ask
-                        # the judge whether the turn satisfied it. If not, and
-                        # there's no real user message already queued, push the
-                        # continuation prompt back into _pending_input so the
-                        # next loop iteration picks it up naturally (and any
-                        # user input that arrives in between still preempts).
-                        try:
-                            self._maybe_continue_goal_after_turn()
-                        except Exception as _goal_exc:
-                            logging.debug("goal continuation hook failed: %s", _goal_exc)
-
                         # Continuous voice: auto-restart recording after agent responds.
                         # Dispatch to a daemon thread so play_beep (sd.wait) and
                         # AudioRecorder.start (lock acquire) never block process_loop —
@@ -11591,7 +11369,7 @@ class HermesCLI:
                             pass  # Non-fatal — don't break the main loop
 
                 except Exception as e:
-                    logger.warning("process_loop unhandled error (msg may be lost): %s", e)
+                    print(f"Error: {e}")
         
         # Start processing thread
         process_thread = threading.Thread(target=process_loop, daemon=True)

cron/jobs.py

@@ -882,121 +882,3 @@ def save_job_output(job_id: str, output: str):
         raise
     
     return output_file
-
-
-# =============================================================================
-# Skill reference rewriting (curator integration)
-# =============================================================================
-
-def rewrite_skill_refs(
-    consolidated: Optional[Dict[str, str]] = None,
-    pruned: Optional[List[str]] = None,
-) -> Dict[str, Any]:
-    """Rewrite cron job skill references after a curator consolidation pass.
-
-    When the curator consolidates a skill X into umbrella Y (or archives X
-    as pruned), any cron job that lists ``X`` in its ``skills`` field will
-    fail to load ``X`` at run time — the scheduler logs a warning and
-    skips the skill, so the job runs without the instructions it was
-    scheduled to follow. See cron/scheduler.py where ``skill_view`` is
-    called per skill name.
-
-    This function repairs cron jobs in-place:
-
-    - A skill listed in ``consolidated`` is replaced with its umbrella
-      target (the ``into`` value). If the umbrella is already in the
-      job's skill list, the stale name is dropped without duplication.
-    - A skill listed in ``pruned`` is dropped outright — there is no
-      forwarding target.
-    - Ordering and other skills in the list are preserved.
-    - The legacy ``skill`` field is realigned via ``_apply_skill_fields``.
-
-    Args:
-        consolidated: mapping of ``old_skill_name -> umbrella_skill_name``.
-        pruned: list of skill names that were archived with no forwarding
-            target.
-
-    Returns a report dict::
-
-        {
-            "rewrites": [
-                {
-                    "job_id": ...,
-                    "job_name": ...,
-                    "before": [...],
-                    "after": [...],
-                    "mapped": {"old": "new", ...},
-                    "dropped": ["old", ...],
-                },
-                ...
-            ],
-            "jobs_updated": N,
-            "jobs_scanned": M,
-        }
-
-    Best-effort: exceptions from loading/saving propagate to the caller so
-    tests can assert behaviour; the curator invocation site wraps this
-    call in a try/except so a failure here never breaks the curator.
-    """
-    consolidated = dict(consolidated or {})
-    pruned_set = set(pruned or [])
-    # A skill listed in both wins as "consolidated" — it has a target,
-    # which is the more useful of the two outcomes.
-    pruned_set -= set(consolidated.keys())
-
-    if not consolidated and not pruned_set:
-        return {"rewrites": [], "jobs_updated": 0, "jobs_scanned": 0}
-
-    with _jobs_file_lock:
-        jobs = load_jobs()
-        rewrites: List[Dict[str, Any]] = []
-        changed = False
-
-        for job in jobs:
-            skills_before = _normalize_skill_list(job.get("skill"), job.get("skills"))
-            if not skills_before:
-                continue
-
-            mapped: Dict[str, str] = {}
-            dropped: List[str] = []
-            new_skills: List[str] = []
-
-            for name in skills_before:
-                if name in consolidated:
-                    target = consolidated[name]
-                    mapped[name] = target
-                    if target and target not in new_skills:
-                        new_skills.append(target)
-                elif name in pruned_set:
-                    dropped.append(name)
-                else:
-                    if name not in new_skills:
-                        new_skills.append(name)
-
-            if not mapped and not dropped:
-                continue
-
-            job["skills"] = new_skills
-            job["skill"] = new_skills[0] if new_skills else None
-            changed = True
-
-            rewrites.append({
-                "job_id": job.get("id"),
-                "job_name": job.get("name") or job.get("id"),
-                "before": list(skills_before),
-                "after": list(new_skills),
-                "mapped": mapped,
-                "dropped": dropped,
-            })
-
-        if changed:
-            save_jobs(jobs)
-            logger.info(
-                "Curator rewrote skill references in %d cron job(s)", len(rewrites)
-            )
-
-        return {
-            "rewrites": rewrites,
-            "jobs_updated": len(rewrites),
-            "jobs_scanned": len(jobs),
-        }

docker-compose.yml

@@ -40,7 +40,7 @@ services:
       # - TEAMS_CLIENT_SECRET=${TEAMS_CLIENT_SECRET}
       # - TEAMS_TENANT_ID=${TEAMS_TENANT_ID}
       # - TEAMS_ALLOWED_USERS=${TEAMS_ALLOWED_USERS}
-      # - TEAMS_PORT=${TEAMS_PORT:-3978}
+      # - TEAMS_PORT=3978
     command: ["gateway", "run"]
 
   dashboard:

gateway/config.py

@@ -36,26 +36,6 @@ def _coerce_bool(value: Any, default: bool = True) -> bool:
     return is_truthy_value(value, default=default)
 
 
-def _coerce_float(value: Any, default: float) -> float:
-    """Coerce numeric config values, falling back on malformed input."""
-    if value is None:
-        return default
-    try:
-        return float(value)
-    except (TypeError, ValueError):
-        return default
-
-
-def _coerce_int(value: Any, default: int) -> int:
-    """Coerce integer config values, falling back on malformed input."""
-    if value is None:
-        return default
-    try:
-        return int(value)
-    except (TypeError, ValueError):
-        return default
-
-
 def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:
     """Normalize unauthorized DM behavior to a supported value."""
     if isinstance(value, str):
@@ -65,15 +45,6 @@ def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> st
     return default
 
 
-def _normalize_notice_delivery(value: Any, default: str = "public") -> str:
-    """Normalize notice delivery mode to a supported value."""
-    if isinstance(value, str):
-        normalized = value.strip().lower()
-        if normalized in {"public", "private"}:
-            return normalized
-    return default
-
-
 # Module-level cache for bundled platform plugin names (lives outside the
 # enum so it doesn't become an accidental enum member).
 _Platform__bundled_plugin_names: Optional[set] = None
@@ -330,13 +301,13 @@ class StreamingConfig:
         if not data:
             return cls()
         return cls(
-            enabled=_coerce_bool(data.get("enabled"), False),
+            enabled=data.get("enabled", False),
             transport=data.get("transport", "edit"),
-            edit_interval=_coerce_float(data.get("edit_interval"), 1.0),
-            buffer_threshold=_coerce_int(data.get("buffer_threshold"), 40),
+            edit_interval=float(data.get("edit_interval", 1.0)),
+            buffer_threshold=int(data.get("buffer_threshold", 40)),
             cursor=data.get("cursor", " ▉"),
-            fresh_final_after_seconds=_coerce_float(
-                data.get("fresh_final_after_seconds"), 60.0
+            fresh_final_after_seconds=float(
+                data.get("fresh_final_after_seconds", 60.0)
             ),
         )
 
@@ -601,17 +572,6 @@ class GatewayConfig:
                 )
         return self.unauthorized_dm_behavior
 
-    def get_notice_delivery(self, platform: Optional[Platform] = None) -> str:
-        """Return the effective notice-delivery mode for a platform."""
-        if platform:
-            platform_cfg = self.platforms.get(platform)
-            if platform_cfg and "notice_delivery" in platform_cfg.extra:
-                return _normalize_notice_delivery(
-                    platform_cfg.extra.get("notice_delivery"),
-                    "public",
-                )
-        return "public"
-
 
 def load_gateway_config() -> GatewayConfig:
     """
@@ -727,11 +687,6 @@ def load_gateway_config() -> GatewayConfig:
                         platform_cfg.get("unauthorized_dm_behavior"),
                         gw_data.get("unauthorized_dm_behavior", "pair"),
                     )
-                if "notice_delivery" in platform_cfg:
-                    bridged["notice_delivery"] = _normalize_notice_delivery(
-                        platform_cfg.get("notice_delivery"),
-                        "public",
-                    )
                 if "reply_prefix" in platform_cfg:
                     bridged["reply_prefix"] = platform_cfg["reply_prefix"]
                 if "reply_in_thread" in platform_cfg:
@@ -945,12 +900,6 @@ def load_gateway_config() -> GatewayConfig:
                 if "dm_mention_threads" in matrix_cfg and not os.getenv("MATRIX_DM_MENTION_THREADS"):
                     os.environ["MATRIX_DM_MENTION_THREADS"] = str(matrix_cfg["dm_mention_threads"]).lower()
 
-            # Feishu settings → env vars (env vars take precedence)
-            feishu_cfg = yaml_cfg.get("feishu", {})
-            if isinstance(feishu_cfg, dict):
-                if "allow_bots" in feishu_cfg and not os.getenv("FEISHU_ALLOW_BOTS"):
-                    os.environ["FEISHU_ALLOW_BOTS"] = str(feishu_cfg["allow_bots"]).lower()
-
     except Exception as e:
         logger.warning(
             "Failed to process config.yaml — falling back to .env / gateway.json values. "
@@ -1102,14 +1051,7 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         if Platform.WHATSAPP not in config.platforms:
             config.platforms[Platform.WHATSAPP] = PlatformConfig()
         config.platforms[Platform.WHATSAPP].enabled = True
-    whatsapp_home = os.getenv("WHATSAPP_HOME_CHANNEL")
-    if whatsapp_home and Platform.WHATSAPP in config.platforms:
-        config.platforms[Platform.WHATSAPP].home_channel = HomeChannel(
-            platform=Platform.WHATSAPP,
-            chat_id=whatsapp_home,
-            name=os.getenv("WHATSAPP_HOME_CHANNEL_NAME", "Home"),
-        )
-
+    
     # Slack
     slack_token = os.getenv("SLACK_BOT_TOKEN")
     if slack_token:

gateway/delivery.py

@@ -53,10 +53,9 @@ class DeliveryTarget:
         - "telegram" → Telegram home channel
         - "telegram:123456" → specific Telegram chat
         """
-        target_stripped = target.strip()
-        target_lower = target_stripped.lower()
+        target = target.strip().lower()
         
-        if target_lower == "origin":
+        if target == "origin":
             if origin:
                 return cls(
                     platform=origin.platform,
@@ -68,14 +67,13 @@ class DeliveryTarget:
                 # Fallback to local if no origin
                 return cls(platform=Platform.LOCAL, is_origin=True)
         
-        if target_lower == "local":
+        if target == "local":
             return cls(platform=Platform.LOCAL)
         
         # Check for platform:chat_id or platform:chat_id:thread_id format
-        # Use the original case for chat_id/thread_id to preserve case-sensitive IDs
-        if ":" in target_stripped:
-            parts = target_stripped.split(":", 2)
-            platform_str = parts[0].lower()  # Platform names are case-insensitive
+        if ":" in target:
+            parts = target.split(":", 2)
+            platform_str = parts[0]
             chat_id = parts[1] if len(parts) > 1 else None
             thread_id = parts[2] if len(parts) > 2 else None
             try:
@@ -87,7 +85,7 @@ class DeliveryTarget:
         
         # Just a platform name (use home channel)
         try:
-            platform = Platform(target_lower)
+            platform = Platform(target)
             return cls(platform=platform)
         except ValueError:
             # Unknown platform, treat as local

gateway/platforms/_http_client_limits.py

@@ -1,84 +0,0 @@
-"""Shared HTTP client factory for long-lived platform adapters.
-
-Gateway messaging platforms (QQ Bot, Feishu, WeCom, DingTalk, Signal,
-BlueBubbles, WeCom-callback) keep a persistent ``httpx.AsyncClient``
-alive for the adapter's lifetime.  That amortises TLS/connection setup
-across many API calls, but it also means the process's file-descriptor
-pressure is sensitive to how aggressively the pool recycles idle keep-
-alive connections.
-
-httpx's default ``keepalive_expiry`` is 5 seconds.  On macOS behind
-Cloudflare Warp (and other transparent proxies), peer-initiated FIN can
-sit in ``CLOSE_WAIT`` longer than that before the local socket actually
-drains — which, multiplied across 7 long-lived adapters plus the LLM
-client and MCP clients, walks straight into the default 256 fd limit.
-See #18451.
-
-``platform_httpx_limits()`` returns a tighter ``httpx.Limits`` the
-adapter factories use instead of the httpx default.  The values chosen:
-
-* ``max_keepalive_connections=10`` — plenty for any single adapter;
-  platform APIs rarely parallelise beyond this.
-* ``keepalive_expiry=2.0`` — close idle sockets aggressively so a
-  proxy's lingering CLOSE_WAIT window can't starve the process.
-
-Override via ``HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY`` /
-``HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE`` env vars when tuning under load.
-"""
-
-from __future__ import annotations
-
-import os
-
-try:
-    import httpx
-except ImportError:  # pragma: no cover — optional dep
-    httpx = None  # type: ignore[assignment]
-
-
-_DEFAULT_KEEPALIVE_EXPIRY_S = 2.0
-_DEFAULT_MAX_KEEPALIVE = 10
-
-
-def platform_httpx_limits() -> "httpx.Limits | None":
-    """Return ``httpx.Limits`` tuned for persistent platform-adapter clients.
-
-    Returns ``None`` when httpx isn't importable, so callers can fall
-    back to httpx's built-in default without a hard dependency on this
-    helper being reachable.
-    """
-    if httpx is None:
-        return None
-
-    def _env_float(name: str, default: float) -> float:
-        raw = os.environ.get(name, "").strip()
-        if not raw:
-            return default
-        try:
-            val = float(raw)
-        except (TypeError, ValueError):
-            return default
-        return val if val > 0 else default
-
-    def _env_int(name: str, default: int) -> int:
-        raw = os.environ.get(name, "").strip()
-        if not raw:
-            return default
-        try:
-            val = int(raw)
-        except (TypeError, ValueError):
-            return default
-        return val if val > 0 else default
-
-    keepalive_expiry = _env_float(
-        "HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY", _DEFAULT_KEEPALIVE_EXPIRY_S
-    )
-    max_keepalive = _env_int(
-        "HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE", _DEFAULT_MAX_KEEPALIVE
-    )
-
-    return httpx.Limits(
-        max_keepalive_connections=max_keepalive,
-        # Leave max_connections at httpx default (100) — plenty of headroom.
-        keepalive_expiry=keepalive_expiry,
-    )

gateway/platforms/api_server.py

@@ -2351,11 +2351,10 @@ class APIServerAdapter(BasePlatformAdapter):
             )
             if agent_ref is not None:
                 agent_ref[0] = agent
-            effective_task_id = session_id or str(uuid.uuid4())
             result = agent.run_conversation(
                 user_message=user_message,
                 conversation_history=conversation_history,
-                task_id=effective_task_id,
+                task_id="default",
             )
             usage = {
                 "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -2552,11 +2551,10 @@ class APIServerAdapter(BasePlatformAdapter):
                 )
                 self._active_run_agents[run_id] = agent
                 def _run_sync():
-                    effective_task_id = session_id or run_id
                     r = agent.run_conversation(
                         user_message=user_message,
                         conversation_history=conversation_history,
-                        task_id=effective_task_id,
+                        task_id="default",
                     )
                     u = {
                         "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,

gateway/platforms/base.py

@@ -416,7 +416,7 @@ def is_host_excluded_by_no_proxy(hostname: str, no_proxy_value: str | None = Non
 from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
-from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple, Union
+from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple
 from enum import Enum
 
 from pathlib import Path as _Path
@@ -981,7 +981,7 @@ def coerce_plaintext_gateway_command(event: "MessageEvent") -> None:
         return
 
 
-@dataclass
+@dataclass 
 class SendResult:
     """Result of sending a message."""
     success: bool
@@ -991,45 +991,6 @@ class SendResult:
     retryable: bool = False  # True for transient connection errors — base will retry automatically
 
 
-class EphemeralReply(str):
-    """System-notice reply that auto-deletes after a TTL.
-
-    Slash-command handlers in ``gateway/run.py`` can return this wrapper
-    instead of a plain string to request that the reply message be deleted
-    after ``ttl_seconds`` on platforms that support ``delete_message``.
-
-    Subclassing ``str`` keeps the wrapper transparent to anything that
-    treats handler return values as text (existing tests use ``in`` /
-    ``startswith`` / equality; the ``_process_message_background`` pipeline
-    extracts attachments from the string content).  ``isinstance(r,
-    EphemeralReply)`` still distinguishes ephemeral replies from plain
-    strings so the send path can schedule deletion.
-
-    Platforms that don't override :meth:`BasePlatformAdapter.delete_message`
-    silently ignore the TTL — the message is sent normally and left in
-    place.  When ``ttl_seconds`` is ``None``, the pipeline uses the
-    configured ``display.ephemeral_system_ttl`` default.  A default of ``0``
-    disables auto-deletion globally, preserving prior behavior.
-    """
-
-    ttl_seconds: Optional[int]
-
-    def __new__(cls, text: str, ttl_seconds: Optional[int] = None):
-        instance = super().__new__(cls, text)
-        instance.ttl_seconds = ttl_seconds
-        return instance
-
-    @property
-    def text(self) -> str:
-        """Return the underlying text.
-
-        Provided for call sites that want an explicit string conversion,
-        though ``str(reply)`` and using ``reply`` directly where a string
-        is expected both work identically.
-        """
-        return str.__str__(self)
-
-
 def merge_pending_message_event(
     pending_messages: Dict[str, MessageEvent],
     session_key: str,
@@ -1073,11 +1034,6 @@ def merge_pending_message_event(
                     existing.text = event.text
             if existing_is_photo or incoming_is_photo:
                 existing.message_type = MessageType.PHOTO
-            elif (
-                getattr(existing, "message_type", None) == MessageType.TEXT
-                and event.message_type != MessageType.TEXT
-            ):
-                existing.message_type = event.message_type
             return
 
         if (
@@ -1112,10 +1068,8 @@ _RETRYABLE_ERROR_PATTERNS = (
 )
 
 
-# Type for message handlers.  Handlers may return a plain string (normal
-# reply), an ``EphemeralReply`` to opt the reply into auto-deletion, or
-# ``None`` when the response was already delivered (e.g. via streaming).
-MessageHandler = Callable[[MessageEvent], Awaitable[Optional[Union[str, "EphemeralReply"]]]]
+# Type for message handlers
+MessageHandler = Callable[[MessageEvent], Awaitable[Optional[str]]]
 
 
 def resolve_channel_prompt(
@@ -1500,64 +1454,6 @@ class BasePlatformAdapter(ABC):
         """
         return False
 
-    def _get_ephemeral_system_ttl_default(self) -> int:
-        """Read ``display.ephemeral_system_ttl`` from config.
-
-        Returns the TTL in seconds to use when an :class:`EphemeralReply`
-        does not specify one explicitly.  ``0`` (the default) disables
-        auto-deletion.  Non-fatal if config is unreadable.
-        """
-        try:
-            from hermes_cli.config import load_config as _load_config
-        except Exception:
-            return 0
-        try:
-            cfg = _load_config()
-        except Exception:
-            return 0
-        display = cfg.get("display", {}) if isinstance(cfg, dict) else {}
-        if not isinstance(display, dict):
-            return 0
-        raw = display.get("ephemeral_system_ttl", 0)
-        try:
-            return int(raw)
-        except (TypeError, ValueError):
-            return 0
-
-    def _schedule_ephemeral_delete(
-        self,
-        chat_id: str,
-        message_id: str,
-        ttl_seconds: int,
-    ) -> None:
-        """Spawn a detached task that deletes ``message_id`` after ``ttl_seconds``.
-
-        Best-effort — failures (gateway restart, permission denied, message
-        too old for Telegram's 48h window) are swallowed at debug level.
-        Does not block the caller.
-        """
-
-        async def _run_delete() -> None:
-            try:
-                await asyncio.sleep(max(1, int(ttl_seconds)))
-                await self.delete_message(chat_id=chat_id, message_id=message_id)
-            except asyncio.CancelledError:
-                raise
-            except Exception as e:
-                logger.debug(
-                    "[%s] Ephemeral delete failed for %s/%s: %s",
-                    self.name, chat_id, message_id, e,
-                )
-
-        coro = _run_delete()
-        try:
-            asyncio.create_task(coro)
-        except RuntimeError:
-            # No running loop (e.g. unit tests that never reach the async
-            # path).  Close the coroutine cleanly so Python doesn't warn
-            # about it never being awaited, then drop silently.
-            coro.close()
-
     async def send_slash_confirm(
         self,
         chat_id: str,
@@ -1593,26 +1489,6 @@ class BasePlatformAdapter(ABC):
         """
         return SendResult(success=False, error="Not supported")
 
-    async def send_private_notice(
-        self,
-        chat_id: str,
-        user_id: Optional[str],
-        content: str,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        """Send a notice privately when the platform supports it.
-
-        The default implementation falls back to a normal send so callers can
-        use one code path across platforms.
-        """
-        return await self.send(
-            chat_id=chat_id,
-            content=content,
-            reply_to=reply_to,
-            metadata=metadata,
-        )
-
     async def send_typing(self, chat_id: str, metadata=None) -> None:
         """
         Send a typing indicator.
@@ -2167,28 +2043,6 @@ class BasePlatformAdapter(ABC):
         lowered = error.lower()
         return "timed out" in lowered or "readtimeout" in lowered or "writetimeout" in lowered
 
-    def _unwrap_ephemeral(self, response: Any) -> Tuple[Optional[str], int]:
-        """Unwrap a handler response into (text, ttl_seconds).
-
-        Accepts a plain string, ``None``, or an :class:`EphemeralReply`.
-        Returns ``(text, ttl)`` where ``ttl > 0`` means the caller should
-        schedule a deletion via :meth:`_schedule_ephemeral_delete` after
-        the send succeeds.  ``ttl`` is forced to 0 when the adapter
-        doesn't override :meth:`delete_message` so non-supporting
-        platforms silently degrade to normal sends.
-        """
-        if isinstance(response, EphemeralReply):
-            ttl = response.ttl_seconds
-            if ttl is None:
-                try:
-                    ttl = int(self._get_ephemeral_system_ttl_default())
-                except Exception:
-                    ttl = 0
-            if ttl and ttl > 0 and type(self).delete_message is BasePlatformAdapter.delete_message:
-                ttl = 0
-            return response.text, int(ttl or 0)
-        return response, 0
-
     async def _send_with_retry(
         self,
         chat_id: str,
@@ -2496,20 +2350,13 @@ class BasePlatformAdapter(ABC):
                 release_guard=False,
                 discard_pending=False,
             )
-            _text, _eph_ttl = self._unwrap_ephemeral(response)
-            if _text:
-                _r = await self._send_with_retry(
+            if response:
+                await self._send_with_retry(
                     chat_id=event.source.chat_id,
-                    content=_text,
+                    content=response,
                     reply_to=event.message_id,
                     metadata=thread_meta,
                 )
-                if _eph_ttl > 0 and _r.success and _r.message_id:
-                    self._schedule_ephemeral_delete(
-                        chat_id=event.source.chat_id,
-                        message_id=_r.message_id,
-                        ttl_seconds=_eph_ttl,
-                    )
         except Exception:
             # On failure, restore the original guard if one still exists so
             # we don't leave the session in a half-reset state.
@@ -2589,20 +2436,13 @@ class BasePlatformAdapter(ABC):
                 try:
                     _thread_meta = {"thread_id": event.source.thread_id} if event.source.thread_id else None
                     response = await self._message_handler(event)
-                    _text, _eph_ttl = self._unwrap_ephemeral(response)
-                    if _text:
-                        _r = await self._send_with_retry(
+                    if response:
+                        await self._send_with_retry(
                             chat_id=event.source.chat_id,
-                            content=_text,
+                            content=response,
                             reply_to=event.message_id,
                             metadata=_thread_meta,
                         )
-                        if _eph_ttl > 0 and _r.success and _r.message_id:
-                            self._schedule_ephemeral_delete(
-                                chat_id=event.source.chat_id,
-                                message_id=_r.message_id,
-                                ttl_seconds=_eph_ttl,
-                            )
                 except Exception as e:
                     logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
                 return
@@ -2676,6 +2516,7 @@ class BasePlatformAdapter(ABC):
         # Fall back to a new Event only if the entry was removed externally.
         interrupt_event = self._active_sessions.get(session_key) or asyncio.Event()
         self._active_sessions[session_key] = interrupt_event
+        callback_generation = getattr(interrupt_event, "_hermes_run_generation", None)
         
         # Start continuous typing indicator (refreshes every 2 seconds)
         _thread_metadata = {"thread_id": event.source.thread_id} if event.source.thread_id else None
@@ -2708,16 +2549,7 @@ class BasePlatformAdapter(ABC):
 
             # Call the handler (this can take a while with tool calls)
             response = await self._message_handler(event)
-
-            # Slash-command handlers may return an EphemeralReply sentinel to
-            # request that their reply message auto-delete after a TTL (used
-            # for system notices like "✨ New session started!" that the user
-            # doesn't need to keep in the thread).  Unwrap here so all the
-            # downstream extract_media / text-processing logic sees a plain
-            # string, and remember the TTL + platform capability so the
-            # post-send block can schedule the deletion.
-            response, _ephemeral_ttl = self._unwrap_ephemeral(response)
-
+            
             # Send response if any.  A None/empty response is normal when
             # streaming already delivered the text (already_sent=True) or
             # when the message was queued behind an active agent.  Log at
@@ -2806,21 +2638,6 @@ class BasePlatformAdapter(ABC):
                     )
                     _record_delivery(result)
 
-                    # Schedule auto-deletion of system-notice replies.
-                    # Detached so the handler returns immediately; errors
-                    # (permission denied, message too old) are swallowed.
-                    if (
-                        _ephemeral_ttl
-                        and _ephemeral_ttl > 0
-                        and result.success
-                        and result.message_id
-                    ):
-                        self._schedule_ephemeral_delete(
-                            chat_id=event.source.chat_id,
-                            message_id=result.message_id,
-                            ttl_seconds=_ephemeral_ttl,
-                        )
-
                 # Human-like pacing delay between text and media
                 human_delay = self._get_human_delay()
 
@@ -2998,20 +2815,7 @@ class BasePlatformAdapter(ABC):
         finally:
             # Fire any one-shot post-delivery callback registered for this
             # session (e.g. deferred background-review notifications).
-            #
-            # Snapshot the callback generation HERE (after the agent has run),
-            # not at the top of this task.  _hermes_run_generation is set on
-            # the interrupt event by GatewayRunner._bind_adapter_run_generation
-            # during _handle_message_with_agent — which happens DURING the
-            # self._message_handler(event) await above.  Snapshotting earlier
-            # always captured None, which bypassed the generation-ownership
-            # check in pop_post_delivery_callback and let stale runs fire a
-            # fresher run's callbacks.
-            _callback_generation = getattr(
-                interrupt_event,
-                "_hermes_run_generation",
-                None,
-            )
+            _callback_generation = callback_generation
             if hasattr(self, "pop_post_delivery_callback"):
                 _post_cb = self.pop_post_delivery_callback(
                     session_key,

gateway/platforms/bluebubbles.py

@@ -162,9 +162,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             return False
         from aiohttp import web
 
-        # Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
-        from gateway.platforms._http_client_limits import platform_httpx_limits
-        self.client = httpx.AsyncClient(timeout=30.0, limits=platform_httpx_limits())
+        self.client = httpx.AsyncClient(timeout=30.0)
         try:
             await self._api_get("/api/v1/ping")
             info = await self._api_get("/api/v1/server/info")

gateway/platforms/dingtalk.py

@@ -228,11 +228,7 @@ class DingTalkAdapter(BasePlatformAdapter):
             return False
 
         try:
-            # Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
-            from gateway.platforms._http_client_limits import platform_httpx_limits
-            self._http_client = httpx.AsyncClient(
-                timeout=30.0, limits=platform_httpx_limits(),
-            )
+            self._http_client = httpx.AsyncClient(timeout=30.0)
 
             credential = dingtalk_stream.Credential(
                 self._client_id, self._client_secret

gateway/platforms/discord.py

@@ -613,21 +613,6 @@ class DiscordAdapter(BasePlatformAdapter):
             # so LLM output or echoed user content can't ping the whole
             # server; override per DISCORD_ALLOW_MENTION_* env vars or the
             # discord.allow_mentions.* block in config.yaml.
-
-            # Close any existing client to prevent zombie websocket connections
-            # on reconnect (see #18187). Without this, the old client remains
-            # connected to Discord gateway and both fire on_message, causing
-            # double responses.
-            if self._client is not None:
-                try:
-                    if not self._client.is_closed():
-                        await self._client.close()
-                except Exception:
-                    logger.debug("[%s] Failed to close previous Discord client", self.name)
-                finally:
-                    self._client = None
-                    self._ready_event.clear()
-
             self._client = commands.Bot(
                 command_prefix="!",  # Not really used, we handle raw messages
                 intents=intents,
@@ -2599,32 +2584,40 @@ class DiscordAdapter(BasePlatformAdapter):
         hidden skills. The slash picker also becomes more discoverable —
         Discord live-filters by the user's typed prefix against both the
         skill name and its description.
-
-        The entries list and lookup dict are stored on ``self`` rather
-        than captured in closure variables so :meth:`refresh_skill_group`
-        can repopulate them when the user runs ``/reload-skills`` without
-        needing to touch the Discord slash-command tree or trigger a
-        ``tree.sync()`` call.
         """
         try:
+            from hermes_cli.commands import discord_skill_commands_by_category
+
             existing_names = set()
             try:
                 existing_names = {cmd.name for cmd in tree.get_commands()}
             except Exception:
                 pass
 
-            # Populate the instance-level entries/lookup so the
-            # autocomplete + handler callbacks below always read the
-            # freshest state. refresh_skill_group() re-runs the same
-            # collector and mutates these two attributes in place.
-            self._skill_entries: list[tuple[str, str, str]] = []
-            self._skill_lookup: dict[str, tuple[str, str]] = {}
-            self._skill_group_reserved_names: set[str] = set(existing_names)
-            self._refresh_skill_catalog_state()
+            # Reuse the existing collector for consistent filtering
+            # (per-platform disabled, hub-excluded, name clamping), then
+            # flatten — the category grouping was only useful for the
+            # nested layout.
+            categories, uncategorized, hidden = discord_skill_commands_by_category(
+                reserved_names=existing_names,
+            )
+            entries: list[tuple[str, str, str]] = list(uncategorized)
+            for cat_skills in categories.values():
+                entries.extend(cat_skills)
 
-            if not self._skill_entries:
+            if not entries:
                 return
 
+            # Stable alphabetical order so the autocomplete suggestion
+            # list is predictable across restarts.
+            entries.sort(key=lambda t: t[0])
+
+            # name -> (description, cmd_key) — used by both the autocomplete
+            # callback and the handler for O(1) dispatch.
+            skill_lookup: dict[str, tuple[str, str]] = {
+                n: (d, k) for n, d, k in entries
+            }
+
             async def _autocomplete_name(
                 interaction: "discord.Interaction", current: str,
             ) -> list:
@@ -2634,13 +2627,10 @@ class DiscordAdapter(BasePlatformAdapter):
                 "/skill pdf" surfaces skills whose description mentions
                 PDFs even if the name doesn't. Discord caps this list at
                 25 entries per query.
-
-                Reads ``self._skill_entries`` so a ``/reload-skills`` run
-                since process start shows up on the very next keystroke.
                 """
                 q = (current or "").strip().lower()
                 choices: list = []
-                for name, desc, _key in self._skill_entries:
+                for name, desc, _key in entries:
                     if not q or q in name.lower() or (desc and q in desc.lower()):
                         if desc:
                             label = f"{name} — {desc}"
@@ -2664,7 +2654,7 @@ class DiscordAdapter(BasePlatformAdapter):
             async def _skill_handler(
                 interaction: "discord.Interaction", name: str, args: str = "",
             ):
-                entry = self._skill_lookup.get(name)
+                entry = skill_lookup.get(name)
                 if not entry:
                     await interaction.response.send_message(
                         f"Unknown skill: `{name}`. Start typing for "
@@ -2686,74 +2676,16 @@ class DiscordAdapter(BasePlatformAdapter):
 
             logger.info(
                 "[%s] Registered /skill command with %d skill(s) via autocomplete",
-                self.name, len(self._skill_entries),
+                self.name, len(entries),
             )
-            if self._skill_group_hidden_count:
+            if hidden:
                 logger.info(
                     "[%s] %d skill(s) filtered out of /skill (name clamp / reserved)",
-                    self.name, self._skill_group_hidden_count,
+                    self.name, hidden,
                 )
         except Exception as exc:
             logger.warning("[%s] Failed to register /skill command: %s", self.name, exc)
 
-    def _refresh_skill_catalog_state(self) -> None:
-        """Re-scan disk for skills and repopulate ``self._skill_entries``.
-
-        Called once from :meth:`_register_skill_group` at startup and
-        again from :meth:`refresh_skill_group` whenever the user runs
-        ``/reload-skills``. No Discord API calls are made — autocomplete
-        and the handler both read from these instance attributes
-        directly, so an in-place mutation is sufficient.
-        """
-        from hermes_cli.commands import discord_skill_commands_by_category
-
-        reserved = getattr(self, "_skill_group_reserved_names", set())
-        categories, uncategorized, hidden = discord_skill_commands_by_category(
-            reserved_names=set(reserved),
-        )
-        entries: list[tuple[str, str, str]] = list(uncategorized)
-        for cat_skills in categories.values():
-            entries.extend(cat_skills)
-        # Stable alphabetical order so the autocomplete suggestion
-        # list is predictable across restarts.
-        entries.sort(key=lambda t: t[0])
-
-        self._skill_entries = entries
-        self._skill_lookup = {n: (d, k) for n, d, k in entries}
-        self._skill_group_hidden_count = hidden
-
-    def refresh_skill_group(self) -> tuple[int, int]:
-        """Rescan skills and update the live ``/skill`` autocomplete state.
-
-        Invoked by :meth:`gateway.run.GatewayOrchestrator._handle_reload_skills_command`
-        after :func:`agent.skill_commands.reload_skills` has refreshed
-        the in-process skill-command registry. Without this call, the
-        ``/skill`` autocomplete dropdown keeps showing the list captured
-        at process start — new skills stay invisible and deleted skills
-        return an "Unknown skill" error when clicked.
-
-        Because autocomplete options are fetched dynamically by Discord,
-        we only need to mutate the entries/lookup attributes read by the
-        callbacks — no ``tree.sync()`` is required.
-
-        Returns ``(new_count, hidden_count)``.
-        """
-        try:
-            self._refresh_skill_catalog_state()
-        except Exception as exc:
-            logger.warning(
-                "[%s] Failed to refresh /skill autocomplete after reload: %s",
-                self.name, exc,
-            )
-            return (len(getattr(self, "_skill_entries", [])), 0)
-        logger.info(
-            "[%s] Refreshed /skill autocomplete: %d skill(s) available (%d filtered)",
-            self.name,
-            len(self._skill_entries),
-            self._skill_group_hidden_count,
-        )
-        return (len(self._skill_entries), self._skill_group_hidden_count)
-
     def _build_slash_event(self, interaction: discord.Interaction, text: str) -> MessageEvent:
         """Build a MessageEvent from a Discord slash command interaction."""
         is_dm = isinstance(interaction.channel, discord.DMChannel)
@@ -2919,15 +2851,8 @@ class DiscordAdapter(BasePlatformAdapter):
             raw = os.getenv("DISCORD_FREE_RESPONSE_CHANNELS", "")
         if isinstance(raw, list):
             return {str(part).strip() for part in raw if str(part).strip()}
-        # Coerce non-list scalars (str/int/float) to str before splitting.
-        # YAML parses a bare numeric value such as
-        # `free_response_channels: 1491973769726791812` as int, which was
-        # previously falling through the isinstance(str) branch and silently
-        # returning an empty set.  str() here accepts whatever scalar the YAML
-        # loader hands us without changing existing string/CSV semantics.
-        s = str(raw).strip() if raw is not None else ""
-        if s:
-            return {part.strip() for part in s.split(",") if part.strip()}
+        if isinstance(raw, str) and raw.strip():
+            return {part.strip() for part in raw.split(",") if part.strip()}
         return set()
 
     def _thread_parent_channel(self, channel: Any) -> Any:
@@ -3153,7 +3078,6 @@ class DiscordAdapter(BasePlatformAdapter):
     async def send_update_prompt(
         self, chat_id: str, prompt: str, default: str = "",
         session_key: str = "",
-        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send an interactive button-based update prompt (Yes / No).
 
@@ -3163,10 +3087,9 @@ class DiscordAdapter(BasePlatformAdapter):
         if not self._client or not DISCORD_AVAILABLE:
             return SendResult(success=False, error="Not connected")
         try:
-            target_id = metadata.get("thread_id") if metadata and metadata.get("thread_id") else chat_id
-            channel = self._client.get_channel(int(target_id))
+            channel = self._client.get_channel(int(chat_id))
             if not channel:
-                channel = await self._client.fetch_channel(int(target_id))
+                channel = await self._client.fetch_channel(int(chat_id))
 
             default_hint = f" (default: {default})" if default else ""
             embed = discord.Embed(

gateway/platforms/feishu.py

@@ -64,7 +64,7 @@ from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 from types import SimpleNamespace
-from typing import Any, Dict, List, Literal, Optional, Sequence
+from typing import Any, Dict, List, Optional, Sequence
 from urllib.error import HTTPError, URLError
 from urllib.parse import urlencode
 from urllib.request import Request, urlopen
@@ -141,7 +141,6 @@ from gateway.platforms.base import (
 )
 from gateway.status import acquire_scoped_lock, release_scoped_lock
 from hermes_constants import get_hermes_home
-from utils import atomic_json_write
 
 logger = logging.getLogger(__name__)
 
@@ -388,8 +387,6 @@ class FeishuAdapterSettings:
     admins: frozenset[str] = frozenset()
     default_group_policy: str = ""
     group_rules: Dict[str, FeishuGroupRule] = field(default_factory=dict)
-    allow_bots: str = "none"  # "none" | "mentions" | "all"
-    require_mention: bool = True
 
 
 @dataclass
@@ -399,7 +396,6 @@ class FeishuGroupRule:
     policy: str  # "open" | "allowlist" | "blacklist" | "admin_only" | "disabled"
     allowlist: set[str] = field(default_factory=set)
     blacklist: set[str] = field(default_factory=set)
-    require_mention: Optional[bool] = None  # None = inherit global
 
 
 @dataclass
@@ -409,40 +405,6 @@ class FeishuBatchState:
     counts: Dict[str, int] = field(default_factory=dict)
 
 
-# ---------------------------------------------------------------------------
-# Admission: policy types
-# ---------------------------------------------------------------------------
-
-
-RejectReason = Literal[
-    "self_echo",
-    "self_ids_unknown",
-    "bots_disabled",
-    "bot_not_mentioned",
-    "group_policy_rejected",
-]
-
-
-def _is_bot_sender(sender: Any) -> bool:
-    # receive_v1 docs say {user, bot}; accept "app" defensively.
-    return getattr(sender, "sender_type", "") in ("bot", "app")
-
-
-def _sender_identity(sender: Any) -> frozenset:
-    # Take any non-empty id variant — tenant sender_id_type decides which are populated.
-    sid = getattr(sender, "sender_id", None)
-    if sid is None:
-        return frozenset()
-    return frozenset(
-        v for v in (
-            getattr(sid, "open_id", None),
-            getattr(sid, "user_id", None),
-            getattr(sid, "union_id", None),
-        )
-        if v
-    )
-
-
 # ---------------------------------------------------------------------------
 # Markdown rendering helpers
 # ---------------------------------------------------------------------------
@@ -1415,16 +1377,10 @@ class FeishuAdapter(BasePlatformAdapter):
             for chat_id, rule_cfg in raw_group_rules.items():
                 if not isinstance(rule_cfg, dict):
                     continue
-                # Only override when the key is explicitly set — missing vs false
-                # must not collapse.
-                per_chat_require_mention: Optional[bool] = None
-                if "require_mention" in rule_cfg:
-                    per_chat_require_mention = _to_boolean(rule_cfg.get("require_mention"))
                 group_rules[str(chat_id)] = FeishuGroupRule(
                     policy=str(rule_cfg.get("policy", "open")).strip().lower(),
                     allowlist=set(str(u).strip() for u in rule_cfg.get("allowlist", []) if str(u).strip()),
                     blacklist=set(str(u).strip() for u in rule_cfg.get("blacklist", []) if str(u).strip()),
-                    require_mention=per_chat_require_mention,
                 )
 
         # Bot-level admins
@@ -1434,16 +1390,6 @@ class FeishuAdapter(BasePlatformAdapter):
         # Default group policy (for groups not in group_rules)
         default_group_policy = str(extra.get("default_group_policy", "")).strip().lower()
 
-        # Env-only so adapter and gateway auth bypass share one source; yaml
-        # feishu.allow_bots is bridged to this env var at config load.
-        allow_bots = os.getenv("FEISHU_ALLOW_BOTS", "none").strip().lower()
-        if allow_bots not in ("none", "mentions", "all"):
-            logger.warning(
-                "[Feishu] Unknown allow_bots=%r, falling back to 'none'. Valid: none, mentions, all.",
-                allow_bots,
-            )
-            allow_bots = "none"
-
         return FeishuAdapterSettings(
             app_id=str(extra.get("app_id") or os.getenv("FEISHU_APP_ID", "")).strip(),
             app_secret=str(extra.get("app_secret") or os.getenv("FEISHU_APP_SECRET", "")).strip(),
@@ -1500,10 +1446,6 @@ class FeishuAdapter(BasePlatformAdapter):
             admins=admins,
             default_group_policy=default_group_policy,
             group_rules=group_rules,
-            allow_bots=allow_bots,
-            require_mention=_to_boolean(
-                extra.get("require_mention", os.getenv("FEISHU_REQUIRE_MENTION", "true"))
-            ),
         )
 
     def _apply_settings(self, settings: FeishuAdapterSettings) -> None:
@@ -1534,8 +1476,6 @@ class FeishuAdapter(BasePlatformAdapter):
         self._ws_reconnect_interval = settings.ws_reconnect_interval
         self._ws_ping_interval = settings.ws_ping_interval
         self._ws_ping_timeout = settings.ws_ping_timeout
-        self._allow_bots = settings.allow_bots
-        self._require_mention = settings.require_mention
 
     def _build_event_handler(self) -> Any:
         if EventDispatcherHandler is None:
@@ -2249,28 +2189,30 @@ class FeishuAdapter(BasePlatformAdapter):
         event = getattr(data, "event", None)
         message = getattr(event, "message", None)
         sender = getattr(event, "sender", None)
-        if not message or not sender or not getattr(sender, "sender_id", None):
-            logger.debug("[Feishu] Dropping malformed inbound event: missing message/sender")
+        sender_id = getattr(sender, "sender_id", None)
+        if not message or not sender_id:
+            logger.debug("[Feishu] Dropping malformed inbound event: missing message or sender_id")
             return
 
         message_id = getattr(message, "message_id", None)
         if not message_id or self._is_duplicate(message_id):
             logger.debug("[Feishu] Dropping duplicate/missing message_id: %s", message_id)
             return
-
-        reason = self._admit(sender, message)
-        if reason is not None:
-            logger.debug("[Feishu] dropping inbound event: %s", reason)
+        if self._is_self_sent_bot_message(event):
+            logger.debug("[Feishu] Dropping self-sent bot event: %s", message_id)
             return
 
         chat_type = getattr(message, "chat_type", "p2p")
+        chat_id = getattr(message, "chat_id", "") or ""
+        if chat_type != "p2p" and not self._should_accept_group_message(message, sender_id, chat_id):
+            logger.debug("[Feishu] Dropping group message that failed mention/policy gate: %s", message_id)
+            return
         await self._process_inbound_message(
             data=data,
             message=message,
-            sender_id=getattr(sender, "sender_id", None),
+            sender_id=sender_id,
             chat_type=chat_type,
             message_id=message_id,
-            is_bot=_is_bot_sender(sender),
         )
 
     def _on_message_read_event(self, data: P2ImMessageMessageReadV1) -> None:
@@ -2447,11 +2389,10 @@ class FeishuAdapter(BasePlatformAdapter):
             msg = items[0] if items else None
             if not msg:
                 return
-            # GET im/v1/messages returns sender.id=app_id for bot messages —
-            # peer bots and us share sender_type="app" but differ on app_id.
             sender = getattr(msg, "sender", None)
-            if str(getattr(sender, "id", "") or "") != self._app_id:
-                return  # only route reactions on this bot's own messages
+            sender_type = str(getattr(sender, "sender_type", "") or "").lower()
+            if sender_type != "app":
+                return  # only route reactions on our own bot messages
             chat_id = str(getattr(msg, "chat_id", "") or "")
             chat_type_raw = str(getattr(msg, "chat_type", "p2p") or "p2p")
             if not chat_id:
@@ -2738,7 +2679,6 @@ class FeishuAdapter(BasePlatformAdapter):
         sender_id: Any,
         chat_type: str,
         message_id: str,
-        is_bot: bool = False,
     ) -> None:
         text, inbound_type, media_urls, media_types, mentions = await self._extract_message_content(message)
 
@@ -2764,27 +2704,19 @@ class FeishuAdapter(BasePlatformAdapter):
         )
         reply_to_text = await self._fetch_message_text(reply_to_message_id) if reply_to_message_id else None
 
-        sender_primary = (
-            getattr(sender_id, "open_id", None)
-            or getattr(sender_id, "user_id", None)
-            or getattr(sender_id, "union_id", None)
-            or "<unknown>"
-        )
         logger.info(
-            "[Feishu] Inbound %s message received: id=%s type=%s chat_id=%s sender=%s:%s text=%r media=%d",
+            "[Feishu] Inbound %s message received: id=%s type=%s chat_id=%s text=%r media=%d",
             "dm" if chat_type == "p2p" else "group",
             message_id,
             inbound_type.value,
             getattr(message, "chat_id", "") or "",
-            "bot" if is_bot else "user",
-            sender_primary,
             text[:120],
             len(media_urls),
         )
 
         chat_id = getattr(message, "chat_id", "") or ""
         chat_info = await self.get_chat_info(chat_id)
-        sender_profile = await self._resolve_sender_profile(sender_id, is_bot=is_bot)
+        sender_profile = await self._resolve_sender_profile(sender_id)
         source = self.build_source(
             chat_id=chat_id,
             chat_name=chat_info.get("name") or chat_id or "Feishu Chat",
@@ -2793,7 +2725,6 @@ class FeishuAdapter(BasePlatformAdapter):
             user_name=sender_profile["user_name"],
             thread_id=getattr(message, "thread_id", None) or None,
             user_id_alt=sender_profile["user_id_alt"],
-            is_bot=is_bot,
         )
         normalized = MessageEvent(
             text=text,
@@ -2922,18 +2853,13 @@ class FeishuAdapter(BasePlatformAdapter):
                 },
             )
             response.raise_for_status()
-            # Snapshot Content-Type and body while the client context is
-            # still active so pooled connections fully release on exit.
-            # See #18451.
-            content_type_hdr = str(response.headers.get("Content-Type", ""))
-            body = response.content
         filename = self._derive_remote_filename(
             file_url,
-            content_type=content_type_hdr,
+            content_type=str(response.headers.get("Content-Type", "")),
             default_name=preferred_name,
             default_ext=default_ext,
         )
-        cached_path = cache_document_from_bytes(body, filename)
+        cached_path = cache_document_from_bytes(response.content, filename)
         return cached_path, filename
 
     @staticmethod
@@ -3521,12 +3447,7 @@ class FeishuAdapter(BasePlatformAdapter):
             return "dm"
         return "group"
 
-    async def _resolve_sender_profile(
-        self,
-        sender_id: Any,
-        *,
-        is_bot: bool = False,
-    ) -> Dict[str, Optional[str]]:
+    async def _resolve_sender_profile(self, sender_id: Any) -> Dict[str, Optional[str]]:
         """Map Feishu's three-tier user IDs onto Hermes' SessionSource fields.
 
         Preference order for the primary ``user_id`` field:
@@ -3543,11 +3464,7 @@ class FeishuAdapter(BasePlatformAdapter):
         union_id = getattr(sender_id, "union_id", None) or None
         # Prefer tenant-scoped user_id; fall back to app-scoped open_id.
         primary_id = user_id or open_id
-        # bot/v3/bots/basic_batch only accepts open_id.
-        name_lookup_id = open_id if is_bot else (primary_id or union_id)
-        display_name = await self._resolve_sender_name_from_api(
-            name_lookup_id, is_bot=is_bot,
-        )
+        display_name = await self._resolve_sender_name_from_api(primary_id or union_id)
         return {
             "user_id": primary_id,
             "user_name": display_name,
@@ -3567,14 +3484,11 @@ class FeishuAdapter(BasePlatformAdapter):
         self._sender_name_cache.pop(sender_id, None)
         return None
 
-    async def _resolve_sender_name_from_api(
-        self,
-        sender_id: Optional[str],
-        *,
-        is_bot: bool = False,
-    ) -> Optional[str]:
-        """Bots divert to bot/basic_batch — contact API doesn't return bot names.
-        Failures are silent so the pipeline never blocks on name resolution.
+    async def _resolve_sender_name_from_api(self, sender_id: Optional[str]) -> Optional[str]:
+        """Fetch the sender's display name from the Feishu contact API with a 10-minute cache.
+
+        ID-type detection mirrors openclaw: ou_ → open_id, on_ → union_id, else user_id.
+        Failures are silently suppressed; the message pipeline must not block on name resolution.
         """
         if not sender_id or not self._client:
             return None
@@ -3584,16 +3498,7 @@ class FeishuAdapter(BasePlatformAdapter):
         now = time.time()
         cached_name = self._get_cached_sender_name(trimmed)
         if cached_name is not None:
-            return cached_name or None  # "" cached means "known nameless"
-        if is_bot:
-            names = await self._fetch_bot_names([trimmed])
-            if names is None:
-                return None
-            expire_at = now + _FEISHU_SENDER_NAME_TTL_SECONDS
-            for oid, name in names.items():
-                self._sender_name_cache[oid] = (name, expire_at)
-            hit = self._sender_name_cache.get(trimmed)
-            return (hit[0] or None) if hit else None
+            return cached_name
         try:
             from lark_oapi.api.contact.v3 import GetUserRequest  # lazy import
             if trimmed.startswith("ou_"):
@@ -3622,35 +3527,6 @@ class FeishuAdapter(BasePlatformAdapter):
             logger.debug("[Feishu] Failed to resolve sender name for %s", sender_id, exc_info=True)
         return None
 
-    async def _fetch_bot_names(self, bot_ids: List[str]) -> Optional[Dict[str, str]]:
-        if not self._client or not bot_ids:
-            return None
-        try:
-            req = (
-                BaseRequest.builder()
-                .http_method(HttpMethod.GET)
-                .uri("/open-apis/bot/v3/bots/basic_batch")
-                .queries([("bot_ids", oid) for oid in bot_ids])
-                .token_types({AccessTokenType.TENANT})
-                .build()
-            )
-            resp = await asyncio.to_thread(self._client.request, req)
-            content = getattr(getattr(resp, "raw", None), "content", None)
-            if not content:
-                return None
-            payload = json.loads(content)
-            if payload.get("code") != 0:
-                return None
-            bots = (payload.get("data") or {}).get("bots") or {}
-            return {
-                oid: str(info.get("name") or "").strip()
-                for oid, info in bots.items()
-                if oid
-            }
-        except Exception:
-            logger.debug("[Feishu] Failed to fetch bot names for %s", bot_ids, exc_info=True)
-            return None
-
     async def _fetch_message_text(self, message_id: str) -> Optional[str]:
         if not self._client or not message_id:
             return None
@@ -3714,60 +3590,10 @@ class FeishuAdapter(BasePlatformAdapter):
             logger.exception("[Feishu] Background inbound processing failed")
 
     # =========================================================================
-    # Inbound admission
+    # Group policy and mention gating
     # =========================================================================
 
-    def _admit(self, sender: Any, message: Any) -> Optional[RejectReason]:
-        sender_ids = _sender_identity(sender)
-        self_ids = frozenset(v for v in (self._bot_open_id, self._bot_user_id) if v)
-        is_bot = _is_bot_sender(sender)
-        is_group = getattr(message, "chat_type", "p2p") != "p2p"
-        chat_id = getattr(message, "chat_id", "") or ""
-        require_mention = is_group and self._require_mention_for(chat_id)
-
-        # Defensive only — Feishu doesn't echo our outbound back as inbound,
-        # and open_id is always populated on both sides.
-        if self_ids and sender_ids & self_ids:
-            return "self_echo"
-
-        if is_bot:
-            mode = self._allow_bots
-            if mode != "mentions" and mode != "all":
-                return "bots_disabled"
-            # Defensive: pre-hydration or malformed payloads.
-            if not self_ids or not sender_ids:
-                return "self_ids_unknown"
-            # Step 4 covers mention enforcement for groups when require_mention
-            # is on; check here only on paths step 4 won't reach.
-            if mode == "mentions" and not require_mention and not self._mentions_self(message):
-                return "bot_not_mentioned"
-
-        if not is_group:
-            return None
-
-        if not self._allow_group_message(
-            getattr(sender, "sender_id", None), chat_id, is_bot=is_bot,
-        ):
-            return "group_policy_rejected"
-        if require_mention and not self._mentions_self(message):
-            return "group_policy_rejected"
-        return None
-
-    def _require_mention_for(self, chat_id: str) -> bool:
-        rule = self._group_rules.get(chat_id) if chat_id else None
-        if rule and rule.require_mention is not None:
-            return rule.require_mention
-        return self._require_mention
-
-    # --- Group policy ---------------------------------------------------------
-
-    def _allow_group_message(
-        self,
-        sender_id: Any,
-        chat_id: str = "",
-        *,
-        is_bot: bool = False,
-    ) -> bool:
+    def _allow_group_message(self, sender_id: Any, chat_id: str = "") -> bool:
         """Per-group policy gate for non-DM traffic."""
         sender_open_id = getattr(sender_id, "open_id", None)
         sender_user_id = getattr(sender_id, "user_id", None)
@@ -3786,17 +3612,12 @@ class FeishuAdapter(BasePlatformAdapter):
             allowlist = self._allowed_group_users
             blacklist = set()
 
-        # Channel locks apply to everyone; allowlist/blacklist only gate humans
-        # (bots were already cleared upstream by FEISHU_ALLOW_BOTS).
         if policy == "disabled":
             return False
         if policy == "open":
             return True
         if policy == "admin_only":
             return False
-        if is_bot:
-            return True
-
         if policy == "allowlist":
             return bool(sender_ids and (sender_ids & allowlist))
         if policy == "blacklist":
@@ -3804,16 +3625,17 @@ class FeishuAdapter(BasePlatformAdapter):
 
         return bool(sender_ids and (sender_ids & self._allowed_group_users))
 
-    # --- Mention detection ----------------------------------------------------
-
-    def _mentions_self(self, message: Any) -> bool:
-        # @_all is Feishu's @everyone placeholder.
+    def _should_accept_group_message(self, message: Any, sender_id: Any, chat_id: str = "") -> bool:
+        """Require an explicit @mention before group messages enter the agent."""
+        if not self._allow_group_message(sender_id, chat_id):
+            return False
+        # @_all is Feishu's @everyone placeholder — always route to the bot.
         raw_content = getattr(message, "content", "") or ""
         if "@_all" in raw_content:
             return True
         mentions = getattr(message, "mentions", None) or []
-        if mentions and self._message_mentions_bot(mentions):
-            return True
+        if mentions:
+            return self._message_mentions_bot(mentions)
         normalized = normalize_feishu_message(
             message_type=getattr(message, "message_type", "") or "",
             raw_content=raw_content,
@@ -3822,6 +3644,23 @@ class FeishuAdapter(BasePlatformAdapter):
         )
         return self._post_mentions_bot(normalized.mentions)
 
+    def _is_self_sent_bot_message(self, event: Any) -> bool:
+        """Return True only for Feishu events emitted by this Hermes bot."""
+        sender = getattr(event, "sender", None)
+        sender_type = str(getattr(sender, "sender_type", "") or "").strip().lower()
+        if sender_type not in {"bot", "app"}:
+            return False
+
+        sender_id = getattr(sender, "sender_id", None)
+        sender_open_id = str(getattr(sender_id, "open_id", "") or "").strip()
+        sender_user_id = str(getattr(sender_id, "user_id", "") or "").strip()
+
+        if self._bot_open_id and sender_open_id == self._bot_open_id:
+            return True
+        if self._bot_user_id and sender_user_id == self._bot_user_id:
+            return True
+        return False
+
     def _message_mentions_bot(self, mentions: List[Any]) -> bool:
         # IDs trump names: when both sides have open_id (or both user_id),
         # match requires equal IDs. Name fallback only when either side
@@ -3965,7 +3804,7 @@ class FeishuAdapter(BasePlatformAdapter):
             recent = self._seen_message_order[-self._dedup_cache_size:]
             # Save as {msg_id: timestamp} so TTL filtering works across restarts.
             payload = {"message_ids": {k: self._seen_message_ids[k] for k in recent if k in self._seen_message_ids}}
-            atomic_json_write(self._dedup_state_path, payload, indent=None)
+            self._dedup_state_path.write_text(json.dumps(payload, ensure_ascii=False), encoding="utf-8")
         except OSError:
             logger.warning("[Feishu] Failed to persist dedup state to %s", self._dedup_state_path, exc_info=True)
 

gateway/platforms/helpers.py

@@ -13,8 +13,6 @@ import time
 from pathlib import Path
 from typing import TYPE_CHECKING, Dict
 
-from utils import atomic_json_write
-
 if TYPE_CHECKING:
     from gateway.platforms.base import MessageEvent
 
@@ -239,11 +237,12 @@ class ThreadParticipationTracker:
 
     def _save(self) -> None:
         path = self._state_path()
+        path.parent.mkdir(parents=True, exist_ok=True)
         thread_list = list(self._threads)
         if len(thread_list) > self._max_tracked:
             thread_list = thread_list[-self._max_tracked:]
             self._threads = set(thread_list)
-        atomic_json_write(path, thread_list, indent=None)
+        path.write_text(json.dumps(thread_list), encoding="utf-8")
 
     def mark(self, thread_id: str) -> None:
         """Mark *thread_id* as participated and persist."""

gateway/platforms/qqbot/adapter.py

@@ -243,14 +243,10 @@ class QQAdapter(BasePlatformAdapter):
             return False
 
         try:
-            # Tighter keepalive pool so idle CLOSE_WAIT sockets drain
-            # faster behind proxies like Cloudflare Warp (#18451).
-            from gateway.platforms._http_client_limits import platform_httpx_limits
             self._http_client = httpx.AsyncClient(
                 timeout=30.0,
                 follow_redirects=True,
                 event_hooks={"response": [_ssrf_redirect_guard]},
-                limits=platform_httpx_limits(),
             )
 
             # 1. Get access token

gateway/platforms/signal.py

@@ -248,9 +248,7 @@ class SignalAdapter(BasePlatformAdapter):
         except Exception as e:
             logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
 
-        # Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
-        from gateway.platforms._http_client_limits import platform_httpx_limits
-        self.client = httpx.AsyncClient(timeout=30.0, limits=platform_httpx_limits())
+        self.client = httpx.AsyncClient(timeout=30.0)
         try:
             # Health check — verify signal-cli daemon is reachable
             try:
@@ -536,18 +534,6 @@ class SignalAdapter(BasePlatformAdapter):
                 except Exception:
                     logger.exception("Signal: failed to fetch attachment %s", att_id)
 
-        # Skip envelopes with no meaningful content (no text, no attachments).
-        # Catches profile key updates, empty messages, and other metadata-only
-        # envelopes that still carry a dataMessage wrapper but have nothing
-        # worth processing. See issue: signal-cli logs "Profile key update" +
-        # Hermes receives msg='' triggering a full agent turn for nothing.
-        if (not text or not text.strip()) and not media_urls:
-            logger.debug(
-                "Signal: skipping contentless envelope from %s (%d attachments)",
-                redact_phone(sender), len(media_urls) if media_urls else 0,
-            )
-            return
-
         # Build session source
         source = self.build_source(
             chat_id=chat_id,

gateway/platforms/slack.py

@@ -9,7 +9,6 @@ Uses slack-bolt (Python) with Socket Mode for:
 """
 
 import asyncio
-import contextvars
 import json
 import logging
 import os
@@ -22,7 +21,6 @@ try:
     from slack_bolt.async_app import AsyncApp
     from slack_bolt.adapter.socket_mode.async_handler import AsyncSocketModeHandler
     from slack_sdk.web.async_client import AsyncWebClient
-    import aiohttp
     SLACK_AVAILABLE = True
 except ImportError:
     SLACK_AVAILABLE = False
@@ -52,16 +50,6 @@ from gateway.platforms.base import (
 
 logger = logging.getLogger(__name__)
 
-# ContextVar carrying the user_id of the slash-command invoker.
-# Set in _handle_slash_command, read in send() to match the correct
-# stashed response_url when multiple users issue commands on the same
-# channel concurrently.  ContextVars propagate to child asyncio.Tasks
-# (Python 3.7+), so the value set in _handle_slash_command's task is
-# visible in _process_message_background's child task.
-_slash_user_id: contextvars.ContextVar[Optional[str]] = contextvars.ContextVar(
-    "_slash_user_id", default=None,
-)
-
 
 @dataclass
 class _ThreadContextCache:
@@ -322,11 +310,6 @@ class SlackAdapter(BasePlatformAdapter):
         # Track active assistant thread status indicators so stop_typing can
         # clear them (chat_id → thread_ts).
         self._active_status_threads: Dict[str, str] = {}
-        # Slash-command contexts: stash response_url + user_id so send()
-        # can route the first reply ephemerally.  Keyed by
-        # (channel_id, user_id) to avoid cross-user collisions.
-        # Each value: {"response_url": str, "ts": float}
-        self._slash_command_contexts: Dict[Tuple[str, str], Dict[str, Any]] = {}
 
     def _describe_slack_api_error(self, response: Any, *, file_obj: Optional[Dict[str, Any]] = None) -> Optional[str]:
         """Convert Slack API auth/permission failures into actionable user-facing text."""
@@ -385,103 +368,6 @@ class SlackAdapter(BasePlatformAdapter):
             )
         return None
 
-    # ------------------------------------------------------------------
-    # Slash-command ephemeral helpers
-    # ------------------------------------------------------------------
-
-    _SLASH_CTX_TTL = 120.0  # seconds — response_url is valid for 30 min;
-    # we use a much shorter TTL to avoid routing unrelated messages
-    # as ephemeral if the command handler was slow or dropped.
-
-    def _pop_slash_context(
-        self, chat_id: str,
-    ) -> Optional[Dict[str, Any]]:
-        """Return and remove the slash-command context for *chat_id*, if fresh.
-
-        Contexts older than ``_SLASH_CTX_TTL`` seconds are silently discarded.
-
-        Uses the ``_slash_user_id`` ContextVar (set in ``_handle_slash_command``)
-        to match the exact ``(channel_id, user_id)`` key.  This prevents a
-        concurrent slash command from a different user on the same channel from
-        stealing another user's ephemeral context.  Falls back to a
-        channel-only scan when the ContextVar is unset (e.g. send() called
-        from a non-slash code path — should not match anything).
-        """
-        now = time.monotonic()
-        # Clean up stale entries on every lookup — dict is small.
-        stale_keys = [
-            k for k, v in self._slash_command_contexts.items()
-            if now - v["ts"] > self._SLASH_CTX_TTL
-        ]
-        for k in stale_keys:
-            self._slash_command_contexts.pop(k, None)
-
-        # Precise match: (channel_id, user_id) from ContextVar.
-        uid = _slash_user_id.get()
-        if uid:
-            return self._slash_command_contexts.pop((chat_id, uid), None)
-
-        # Fallback: channel-only scan (only reachable when ContextVar is
-        # unset, i.e. send() called outside a slash-command async context).
-        match_key = None
-        for key in list(self._slash_command_contexts):
-            if key[0] == chat_id:
-                match_key = key
-                break
-        if match_key is None:
-            return None
-        return self._slash_command_contexts.pop(match_key)
-
-    async def _send_slash_ephemeral(
-        self,
-        ctx: Dict[str, Any],
-        content: str,
-    ) -> "SendResult":
-        """Replace the initial ephemeral ack via ``response_url``.
-
-        Slack's ``response_url`` accepts a POST with ``replace_original``
-        for up to 30 minutes after the slash command was invoked.  This
-        lets us swap the "Running /cmd…" placeholder with the real reply,
-        and the message stays ephemeral ("Only visible to you").
-
-        Falls back to a simple ``True`` SendResult if the POST fails —
-        the user already saw the initial ack, so a delivery failure here
-        is non-critical.
-        """
-        formatted = self.format_message(content)
-        # Slack's response_url has the same ~40k char limit as chat_postMessage.
-        # Truncate to MAX_MESSAGE_LENGTH and use only the first chunk — the
-        # response_url replaces a single ephemeral ack, so multi-chunk isn't
-        # possible.  Long responses are rare for command replies.
-        chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
-        text = chunks[0] if chunks else formatted
-        payload = {
-            "response_type": "ephemeral",
-            "replace_original": True,
-            "text": text,
-        }
-        try:
-            async with aiohttp.ClientSession() as session:
-                async with session.post(
-                    ctx["response_url"],
-                    json=payload,
-                    timeout=aiohttp.ClientTimeout(total=10),
-                ) as resp:
-                    if resp.status == 200:
-                        return SendResult(success=True, message_id=None)
-                    body = await resp.text()
-                    logger.warning(
-                        "[Slack] response_url POST returned %s: %s",
-                        resp.status,
-                        body[:200],
-                    )
-        except Exception as e:
-            logger.warning(
-                "[Slack] response_url POST failed: %s", e,
-            )
-        # Non-fatal — the user saw the initial ack already.
-        return SendResult(success=True, message_id=None)
-
     async def connect(self) -> bool:
         """Connect to Slack via Socket Mode."""
         if not SLACK_AVAILABLE:
@@ -560,16 +446,12 @@ class SlackAdapter(BasePlatformAdapter):
             async def handle_message_event(event, say):
                 await self._handle_slack_message(event)
 
-            # Handle app_mention explicitly. In some Slack app configurations,
-            # channel mentions arrive only as app_mention events rather than the
-            # generic message event. Forward them into the normal message
-            # pipeline so @mentions reliably produce replies.
-            # NOTE: when Slack fires BOTH message and app_mention for the same
-            # @mention, they share the same event ts — the dedup in
-            # _handle_slack_message (MessageDeduplicator) suppresses the second.
+            # Acknowledge app_mention events to prevent Bolt 404 errors.
+            # The "message" handler above already processes @mentions in
+            # channels, so this is intentionally a no-op to avoid duplicates.
             @self._app.event("app_mention")
             async def handle_app_mention(event, say):
-                await self._handle_slack_message(event)
+                pass
 
             # File lifecycle events can arrive around snippet uploads even when
             # the actual user message is what we care about. Ack them so Slack
@@ -620,11 +502,7 @@ class SlackAdapter(BasePlatformAdapter):
 
             @self._app.command(_slash_pattern)
             async def handle_hermes_command(ack, command):
-                slash = (command.get("command") or "").lstrip("/")
-                await ack(
-                    response_type="ephemeral",
-                    text=f"Running `/{slash}`…",
-                )
+                await ack()
                 await self._handle_slash_command(command)
 
             # Register Block Kit action handlers for approval buttons
@@ -696,17 +574,6 @@ class SlackAdapter(BasePlatformAdapter):
             return SendResult(success=False, error="Not connected")
 
         try:
-            # Check for a pending slash-command context.  When the user ran a
-            # native slash command (e.g. /q, /stop, /model), the initial ack
-            # already showed an ephemeral "Running /cmd…" message.  If we have
-            # a stashed response_url for this channel, replace that ack with
-            # the actual command reply ephemerally instead of posting publicly.
-            slash_ctx = self._pop_slash_context(chat_id)
-            if slash_ctx:
-                return await self._send_slash_ephemeral(
-                    slash_ctx, content,
-                )
-
             # Convert standard markdown → Slack mrkdwn
             formatted = self.format_message(content)
 
@@ -734,10 +601,6 @@ class SlackAdapter(BasePlatformAdapter):
 
                 last_result = await self._get_client(chat_id).chat_postMessage(**kwargs)
 
-            # Clear Slack Assistant status as soon as the final message is posted.
-            if thread_ts:
-                await self.stop_typing(chat_id)
-
             # Track the sent message ts so we can auto-respond to thread
             # replies without requiring @mention.
             sent_ts = last_result.get("ts") if last_result else None
@@ -761,42 +624,6 @@ class SlackAdapter(BasePlatformAdapter):
             logger.error("[Slack] Send error: %s", e, exc_info=True)
             return SendResult(success=False, error=str(e))
 
-    async def send_private_notice(
-        self,
-        chat_id: str,
-        user_id: str,
-        content: str,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        """Send a Slack ephemeral message visible only to one user."""
-        if not self._app:
-            return SendResult(success=False, error="Not connected")
-        if not chat_id or not user_id:
-            return SendResult(success=False, error="chat_id and user_id are required")
-
-        try:
-            formatted = self.format_message(content)
-            thread_ts = self._resolve_thread_ts(reply_to, metadata)
-            kwargs = {
-                "channel": chat_id,
-                "user": user_id,
-                "text": formatted,
-                "mrkdwn": True,
-            }
-            if thread_ts:
-                kwargs["thread_ts"] = thread_ts
-
-            result = await self._get_client(chat_id).chat_postEphemeral(**kwargs)
-            return SendResult(
-                success=True,
-                message_id=result.get("message_ts") or result.get("ts"),
-                raw_response=result,
-            )
-        except Exception as e:  # pragma: no cover - defensive logging
-            logger.error("[Slack] Ephemeral send error: %s", e, exc_info=True)
-            return SendResult(success=False, error=str(e))
-
     async def edit_message(
         self,
         chat_id: str,
@@ -815,8 +642,6 @@ class SlackAdapter(BasePlatformAdapter):
                 ts=message_id,
                 text=formatted,
             )
-            if finalize:
-                await self.stop_typing(chat_id)
             return SendResult(success=True, message_id=message_id)
         except Exception as e:  # pragma: no cover - defensive logging
             logger.error(
@@ -857,7 +682,7 @@ class SlackAdapter(BasePlatformAdapter):
             # in an assistant-enabled context. Falls back to reactions.
             logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
 
-    async def stop_typing(self, chat_id: str, metadata=None) -> None:
+    async def stop_typing(self, chat_id: str) -> None:
         """Clear the assistant thread status indicator."""
         if not self._app:
             return
@@ -1144,7 +969,7 @@ class SlackAdapter(BasePlatformAdapter):
             return _ph(f'<{url}|{label}>')
 
         text = re.sub(
-            r'(?<!!)\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
+            r'\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
             _convert_markdown_link,
             text,
         )
@@ -1191,11 +1016,9 @@ class SlackAdapter(BasePlatformAdapter):
         )
 
         # 10) Convert italic: _text_ stays as _text_ (already Slack italic)
-        #     Single *text* → _text_ (Slack italic), but only when the
-        #     emphasized text touches non-whitespace on both sides so literal
-        #     delimiters like "a * b * c" are preserved.
+        #     Single *text* → _text_ (Slack italic)
         text = re.sub(
-            r'(?<!\*)\*(\S(?:[^*\n]*?\S)?)\*(?!\*)',
+            r'(?<!\*)\*([^*\n]+)\*(?!\*)',
             lambda m: _ph(f'_{m.group(1)}_'),
             text,
         )
@@ -2701,14 +2524,9 @@ class SlackAdapter(BasePlatformAdapter):
             # gateway command dispatcher by prepending the slash.
             text = f"/{slash_name} {text}".strip()
 
-        # Slack slash commands can originate from DMs or shared channels.
-        # Preserve DM semantics only for DM channel IDs; shared channels must
-        # keep group semantics so different users do not collide into one
-        # session key.
-        is_dm = str(channel_id).startswith("D")
         source = self.build_source(
             chat_id=channel_id,
-            chat_type="dm" if is_dm else "group",
+            chat_type="dm",  # Slash commands are always in DM-like context
             user_id=user_id,
         )
 
@@ -2719,26 +2537,7 @@ class SlackAdapter(BasePlatformAdapter):
             raw_message=command,
         )
 
-        # Stash the Slack response_url so the first reply for this
-        # channel+user can be routed ephemerally (replaces the initial
-        # "Running /cmd…" ack shown by handle_hermes_command).
-        # Only stash for COMMAND events (text starts with "/") — free-form
-        # questions via "/hermes <question>" must produce public replies so
-        # the whole channel can see the agent's answer.
-        response_url = command.get("response_url", "")
-        if response_url and user_id and channel_id and text.startswith("/"):
-            self._slash_command_contexts[(channel_id, user_id)] = {
-                "response_url": response_url,
-                "ts": time.monotonic(),
-            }
-
-        # Set the ContextVar so send() can match the correct stashed
-        # response_url even when multiple users slash concurrently.
-        _slash_user_id_token = _slash_user_id.set(user_id or None)
-        try:
-            await self.handle_message(event)
-        finally:
-            _slash_user_id.reset(_slash_user_id_token)
+        await self.handle_message(event)
 
     def _has_active_session_for_thread(
         self,
@@ -2899,13 +2698,6 @@ class SlackAdapter(BasePlatformAdapter):
             raw = os.getenv("SLACK_FREE_RESPONSE_CHANNELS", "")
         if isinstance(raw, list):
             return {str(part).strip() for part in raw if str(part).strip()}
-        # Coerce non-list scalars (str/int/float) to str before splitting.
-        # A bare numeric YAML value (`free_response_channels: 1234567890`) is
-        # loaded as int and was previously falling through the isinstance(str)
-        # branch to return an empty set.  str() here accepts whatever scalar
-        # the YAML loader hands us without changing existing string/CSV
-        # semantics.
-        s = str(raw).strip() if raw is not None else ""
-        if s:
-            return {part.strip() for part in s.split(",") if part.strip()}
+        if isinstance(raw, str) and raw.strip():
+            return {part.strip() for part in raw.split(",") if part.strip()}
         return set()

gateway/platforms/telegram.py

@@ -290,53 +290,14 @@ class TelegramAdapter(BasePlatformAdapter):
         # and any other slash-confirm prompts; see GatewayRunner._request_slash_confirm).
         self._slash_confirm_state: Dict[str, str] = {}
 
-    def _is_callback_user_authorized(
-        self,
-        user_id: str,
-        *,
-        chat_id: Optional[str] = None,
-        chat_type: Optional[str] = None,
-        thread_id: Optional[str] = None,
-        user_name: Optional[str] = None,
-    ) -> bool:
+    @staticmethod
+    def _is_callback_user_authorized(user_id: str) -> bool:
         """Return whether a Telegram inline-button caller may perform gated actions."""
-        normalized_user_id = str(user_id or "").strip()
-        if not normalized_user_id:
-            return False
-
-        runner = getattr(getattr(self, "_message_handler", None), "__self__", None)
-        auth_fn = getattr(runner, "_is_user_authorized", None)
-        if callable(auth_fn):
-            try:
-                from gateway.session import SessionSource
-
-                normalized_chat_type = str(chat_type or "dm").strip().lower() or "dm"
-                if normalized_chat_type == "private":
-                    normalized_chat_type = "dm"
-                elif normalized_chat_type == "supergroup":
-                    normalized_chat_type = "forum" if thread_id is not None else "group"
-
-                source = SessionSource(
-                    platform=Platform.TELEGRAM,
-                    chat_id=str(chat_id or normalized_user_id),
-                    chat_type=normalized_chat_type,
-                    user_id=normalized_user_id,
-                    user_name=str(user_name).strip() if user_name else None,
-                    thread_id=str(thread_id) if thread_id is not None else None,
-                )
-                return bool(auth_fn(source))
-            except Exception:
-                logger.debug(
-                    "[Telegram] Falling back to env-only callback auth for user %s",
-                    normalized_user_id,
-                    exc_info=True,
-                )
-
         allowed_csv = os.getenv("TELEGRAM_ALLOWED_USERS", "").strip()
         if not allowed_csv:
             return True
         allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
-        return "*" in allowed_ids or normalized_user_id in allowed_ids
+        return "*" in allowed_ids or user_id in allowed_ids
 
     @classmethod
     def _metadata_thread_id(cls, metadata: Optional[Dict[str, Any]]) -> Optional[str]:
@@ -512,17 +473,6 @@ class TelegramAdapter(BasePlatformAdapter):
                 self.name, attempt,
             )
             self._polling_network_error_count = 0
-            # start_polling() returning is necessary but not sufficient:
-            # PTB's Updater can be left in a state where `running` is True
-            # but the underlying long-poll task is wedged on a stale httpx
-            # connection and never makes progress. No error_callback fires
-            # in that state, so the reconnect ladder won't advance on its
-            # own. Schedule a deferred probe to detect the wedge and
-            # re-enter the ladder if needed.
-            if not self.has_fatal_error:
-                probe = asyncio.ensure_future(self._verify_polling_after_reconnect())
-                self._background_tasks.add(probe)
-                probe.add_done_callback(self._background_tasks.discard)
         except Exception as retry_err:
             logger.warning("[%s] Telegram polling reconnect failed: %s", self.name, retry_err)
             # start_polling failed — polling is dead and no further error
@@ -534,50 +484,6 @@ class TelegramAdapter(BasePlatformAdapter):
                 self._background_tasks.add(task)
                 task.add_done_callback(self._background_tasks.discard)
 
-    async def _verify_polling_after_reconnect(self) -> None:
-        """Heartbeat probe scheduled after a successful reconnect.
-
-        PTB's Updater can survive a botched stop()+start_polling() cycle
-        with `running=True` but a wedged consumer task. No error callback
-        fires, so the reconnect ladder doesn't advance on its own. This
-        probe detects the wedge by:
-
-        1. Sleeping HEARTBEAT_PROBE_DELAY so a healthy long-poll has time
-           to complete at least one cycle.
-        2. Verifying `Updater.running` is still True.
-        3. Probing the bot endpoint with a tight asyncio timeout. A
-           wedged httpx pool fails this probe; a healthy one returns
-           well under the timeout.
-
-        On any failure, re-enter the reconnect ladder so the existing
-        MAX_NETWORK_RETRIES path can ultimately escalate to fatal-error.
-        """
-        HEARTBEAT_PROBE_DELAY = 60
-        PROBE_TIMEOUT = 10
-
-        await asyncio.sleep(HEARTBEAT_PROBE_DELAY)
-
-        if self.has_fatal_error:
-            return
-        if not (self._app and self._app.updater and self._app.updater.running):
-            logger.warning(
-                "[%s] Updater not running %ds after reconnect — treating as wedged",
-                self.name, HEARTBEAT_PROBE_DELAY,
-            )
-            await self._handle_polling_network_error(
-                RuntimeError("Updater not running after reconnect heartbeat")
-            )
-            return
-
-        try:
-            await asyncio.wait_for(self._app.bot.get_me(), PROBE_TIMEOUT)
-        except Exception as probe_err:
-            logger.warning(
-                "[%s] Polling heartbeat probe failed %ds after reconnect: %s",
-                self.name, HEARTBEAT_PROBE_DELAY, probe_err,
-            )
-            await self._handle_polling_network_error(probe_err)
-
     async def _handle_polling_conflict(self, error: Exception) -> None:
         if self.has_fatal_error and self.fatal_error_code == "telegram_polling_conflict":
             return
@@ -816,20 +722,6 @@ class TelegramAdapter(BasePlatformAdapter):
                     # Persist thread_id to config so we don't recreate on next restart
                     self._persist_dm_topic_thread_id(int(chat_id), topic_name, thread_id)
 
-                    # Send a seed message so the topic is visible in Telegram's client.
-                    # Empty topics are hidden by the client UI until they contain a message.
-                    try:
-                        await self._bot.send_message(
-                            chat_id=int(chat_id),
-                            message_thread_id=thread_id,
-                            text=f"\U0001f4cc {topic_name}",
-                        )
-                    except Exception as seed_err:
-                        logger.debug(
-                            "[%s] Could not send seed message to topic '%s': %s",
-                            self.name, topic_name, seed_err,
-                        )
-
     async def connect(self) -> bool:
         """Connect to Telegram via polling or webhook.
 
@@ -1429,7 +1321,6 @@ class TelegramAdapter(BasePlatformAdapter):
     async def send_update_prompt(
         self, chat_id: str, prompt: str, default: str = "",
         session_key: str = "",
-        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         """Send an inline-keyboard update prompt (Yes / No buttons).
 
@@ -1447,14 +1338,11 @@ class TelegramAdapter(BasePlatformAdapter):
                     InlineKeyboardButton("✗ No", callback_data="update_prompt:n"),
                 ]
             ])
-            thread_id = self._metadata_thread_id(metadata)
-            message_thread_id = self._message_thread_id_for_send(thread_id)
             msg = await self._bot.send_message(
                 chat_id=int(chat_id),
                 text=text,
                 parse_mode=ParseMode.MARKDOWN,
                 reply_markup=keyboard,
-                message_thread_id=message_thread_id,
                 **self._link_preview_kwargs(),
             )
             return SendResult(success=True, message_id=str(msg.message_id))
@@ -1872,12 +1760,6 @@ class TelegramAdapter(BasePlatformAdapter):
         if not query or not query.data:
             return
         data = query.data
-        query_message = getattr(query, "message", None)
-        query_chat_id = getattr(query_message, "chat_id", None)
-        query_chat = getattr(query_message, "chat", None)
-        query_chat_type = getattr(query_chat, "type", None)
-        query_thread_id = getattr(query_message, "message_thread_id", None)
-        query_user_name = getattr(query.from_user, "first_name", None)
 
         # --- Model picker callbacks ---
         if data.startswith(("mp:", "mm:", "mb", "mx", "mg:")):
@@ -1899,13 +1781,7 @@ class TelegramAdapter(BasePlatformAdapter):
 
                 # Only authorized users may click approval buttons.
                 caller_id = str(getattr(query.from_user, "id", ""))
-                if not self._is_callback_user_authorized(
-                    caller_id,
-                    chat_id=query_chat_id,
-                    chat_type=str(query_chat_type) if query_chat_type is not None else None,
-                    thread_id=str(query_thread_id) if query_thread_id is not None else None,
-                    user_name=query_user_name,
-                ):
+                if not self._is_callback_user_authorized(caller_id):
                     await query.answer(text="⛔ You are not authorized to approve commands.")
                     return
 
@@ -1955,14 +1831,8 @@ class TelegramAdapter(BasePlatformAdapter):
                 choice = parts[1]  # once, always, cancel
                 confirm_id = parts[2]
 
-                caller_id = str(getattr(query.from_user, "id", ""))
-                if not self._is_callback_user_authorized(
-                    caller_id,
-                    chat_id=query_chat_id,
-                    chat_type=str(query_chat_type) if query_chat_type is not None else None,
-                    thread_id=str(query_thread_id) if query_thread_id is not None else None,
-                    user_name=query_user_name,
-                ):
+                caller_id = str(getattr(query.from_user, "id", "")) 
+                if not self._is_callback_user_authorized(caller_id):
                     await query.answer(text="⛔ You are not authorized to answer this prompt.")
                     return
 
@@ -2021,13 +1891,7 @@ class TelegramAdapter(BasePlatformAdapter):
             return
         answer = data.split(":", 1)[1]  # "y" or "n"
         caller_id = str(getattr(query.from_user, "id", ""))
-        if not self._is_callback_user_authorized(
-            caller_id,
-            chat_id=query_chat_id,
-            chat_type=str(query_chat_type) if query_chat_type is not None else None,
-            thread_id=str(query_thread_id) if query_thread_id is not None else None,
-            user_name=query_user_name,
-        ):
+        if not self._is_callback_user_authorized(caller_id):
             await query.answer(text="⛔ You are not authorized to answer update prompts.")
             return
         await query.answer(text=f"Sent '{answer}' to the update process.")

gateway/platforms/wecom.py

@@ -206,11 +206,7 @@ class WeComAdapter(BasePlatformAdapter):
             return False
 
         try:
-            # Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
-            from gateway.platforms._http_client_limits import platform_httpx_limits
-            self._http_client = httpx.AsyncClient(
-                timeout=30.0, follow_redirects=True, limits=platform_httpx_limits(),
-            )
+            self._http_client = httpx.AsyncClient(timeout=30.0, follow_redirects=True)
             await self._open_connection()
             self._mark_connected()
             self._listen_task = asyncio.create_task(self._listen_loop())

gateway/platforms/wecom_callback.py

@@ -119,9 +119,7 @@ class WecomCallbackAdapter(BasePlatformAdapter):
             pass
 
         try:
-            # Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
-            from gateway.platforms._http_client_limits import platform_httpx_limits
-            self._http_client = httpx.AsyncClient(timeout=20.0, limits=platform_httpx_limits())
+            self._http_client = httpx.AsyncClient(timeout=20.0)
             self._app = web.Application()
             self._app.router.add_get("/health", self._handle_health)
             self._app.router.add_get(self._path, self._handle_verify)

gateway/platforms/weixin.py

@@ -2030,9 +2030,7 @@ async def send_weixin_direct(
 
     live_adapter = _LIVE_ADAPTERS.get(resolved_token)
     send_session = getattr(live_adapter, '_send_session', None)
-    if (live_adapter is not None and send_session is not None
-            and not send_session.closed
-            and send_session._loop is asyncio.get_running_loop()):
+    if live_adapter is not None and send_session is not None and not send_session.closed:
         last_result: Optional[SendResult] = None
         cleaned = live_adapter.format_message(message)
         if cleaned:

gateway/platforms/whatsapp.py

@@ -185,13 +185,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
         self._bridge_log: Optional[Path] = None
         self._poll_task: Optional[asyncio.Task] = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
-        # Set to True by disconnect() before we SIGTERM our child bridge so
-        # _check_managed_bridge_exit() can distinguish an intentional
-        # shutdown-time exit (returncode -15 / -2 / 0) from a real crash.
-        # Without this, every graceful gateway shutdown/restart would log
-        # "Fatal whatsapp adapter error" plus dispatch a fatal-error
-        # notification before the normal "✓ whatsapp disconnected" fires.
-        self._shutting_down: bool = False
 
     def _whatsapp_require_mention(self) -> bool:
         configured = self.config.extra.get("require_mention")
@@ -562,21 +555,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
         if returncode is None:
             return None
 
-        # Planned shutdown: disconnect() sets _shutting_down before it sends
-        # SIGTERM to the bridge, so a returncode of -15 (SIGTERM), -2 (SIGINT),
-        # or 0 (clean exit) at that point is expected, not a crash. Treat it
-        # as informational and skip the fatal-error path.
-        # getattr-with-default keeps tests that construct the adapter via
-        # ``WhatsAppAdapter.__new__`` (bypassing __init__) working without
-        # every _make_adapter() helper having to seed the attribute.
-        if getattr(self, "_shutting_down", False) and returncode in (0, -2, -15):
-            logger.info(
-                "[%s] Bridge exited during shutdown (code %d).",
-                self.name,
-                returncode,
-            )
-            return None
-
         message = f"WhatsApp bridge process exited unexpectedly (code {returncode})."
         if not self.has_fatal_error:
             logger.error("[%s] %s", self.name, message)
@@ -587,10 +565,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
 
     async def disconnect(self) -> None:
         """Stop the WhatsApp bridge and clean up any orphaned processes."""
-        # Flip the shutdown flag BEFORE signalling the child so the exit-check
-        # path (which runs from other tasks like send() and the poll loop)
-        # doesn't race us and report the intentional termination as fatal.
-        self._shutting_down = True
         if self._bridge_process:
             try:
                 try:
@@ -902,15 +876,11 @@ class WhatsAppAdapter(BasePlatformAdapter):
         try:
             import aiohttp
 
-            # Must wrap in `async with` — a bare `await session.post(...)`
-            # leaves the response object alive until GC, holding its TCP
-            # socket in CLOSE_WAIT. See #18451.
-            async with self._http_session.post(
+            await self._http_session.post(
                 f"http://127.0.0.1:{self._bridge_port}/typing",
                 json={"chatId": chat_id},
                 timeout=aiohttp.ClientTimeout(total=5)
-            ):
-                pass
+            )
         except Exception:
             pass  # Ignore typing indicator failures
     

gateway/platforms/yuanbao.py

@@ -1896,12 +1896,10 @@ class OwnerCommandMiddleware(InboundMiddleware):
         if cmd not in cls.ALLOWLIST:
             return None, None, False
 
-        # Sender identity check: bot owner <-> push.from_account == push.bot_owner_id.
-        # The allowlisted commands (/approve, /deny, /stop, /reset, ...) are
-        # privileged — leaking them to non-owners lets any group member approve
-        # a dangerous tool call, kill the owner's task, or wipe session state.
-        owner_id = str((push or {}).get("bot_owner_id") or "").strip()
-        is_owner = bool(owner_id) and owner_id == from_account
+        # Sender identity check: bot owner <-> push.from_account == push.bot_owner_id
+        # owner_id = (push or {}).get("bot_owner_id") or ""
+        # is_owner = bool(owner_id) and owner_id == from_account
+        is_owner = True
         return cmd, cmd_line, is_owner
 
     async def handle(self, ctx: InboundContext, next_fn) -> None:

gateway/session.py

@@ -458,15 +458,6 @@ class SessionEntry:
     was_auto_reset: bool = False
     auto_reset_reason: Optional[str] = None  # "idle" or "daily"
     reset_had_activity: bool = False  # whether the expired session had any messages
-
-    # Set by reset_session() when the user explicitly sends /new or /reset.
-    # Consumed once by _handle_message_with_agent to trigger topic/channel
-    # skill re-injection on the first message of the new session.  We can't
-    # reuse was_auto_reset for this because that flag fires the "session
-    # expired due to inactivity" user-facing notice and a misleading
-    # context-note prepend — both wrong for an explicit manual reset.
-    # See issue #6508.
-    is_fresh_reset: bool = False
     
     # Set by the background expiry watcher after it finalizes an expired
     # session (invoking on_session_finalize hooks and evicting the cached
@@ -517,7 +508,6 @@ class SessionEntry:
                 if self.last_resume_marked_at
                 else None
             ),
-            "is_fresh_reset": self.is_fresh_reset,
         }
         if self.origin:
             result["origin"] = self.origin.to_dict()
@@ -566,7 +556,6 @@ class SessionEntry:
             resume_pending=data.get("resume_pending", False),
             resume_reason=data.get("resume_reason"),
             last_resume_marked_at=last_resume_marked_at,
-            is_fresh_reset=data.get("is_fresh_reset", False),
         )
 
 
@@ -1143,7 +1132,6 @@ class SessionStore:
                 display_name=old_entry.display_name,
                 platform=old_entry.platform,
                 chat_type=old_entry.chat_type,
-                is_fresh_reset=True,
             )
 
             self._entries[session_key] = new_entry

gateway/status.py

@@ -21,7 +21,6 @@ from datetime import datetime, timezone
 from pathlib import Path
 from hermes_constants import get_hermes_home
 from typing import Any, Optional
-from utils import atomic_json_write
 
 if sys.platform == "win32":
     import msvcrt
@@ -35,10 +34,6 @@ _IS_WINDOWS = sys.platform == "win32"
 _UNSET = object()
 _GATEWAY_LOCK_FILENAME = "gateway.lock"
 _gateway_lock_handle = None
-# Windows byte-range locks are mandatory for other readers. Lock a byte well
-# past the JSON payload so runtime status / PID readers can still read the file
-# while another process holds the mutual-exclusion lock.
-_WINDOWS_LOCK_OFFSET = 1024 * 1024
 
 
 def _get_pid_path() -> Path:
@@ -210,7 +205,8 @@ def _read_json_file(path: Path) -> Optional[dict[str, Any]]:
 
 
 def _write_json_file(path: Path, payload: dict[str, Any]) -> None:
-    atomic_json_write(path, payload, indent=None, separators=(",", ":"))
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps(payload))
 
 
 def _read_pid_record(pid_path: Optional[Path] = None) -> Optional[dict]:
@@ -290,7 +286,7 @@ def _try_acquire_file_lock(handle) -> bool:
             if handle.tell() == 0:
                 handle.write("\n")
                 handle.flush()
-            handle.seek(_WINDOWS_LOCK_OFFSET)
+            handle.seek(0)
             msvcrt.locking(handle.fileno(), msvcrt.LK_NBLCK, 1)
         else:
             fcntl.flock(handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
@@ -302,7 +298,7 @@ def _try_acquire_file_lock(handle) -> bool:
 def _release_file_lock(handle) -> None:
     try:
         if _IS_WINDOWS:
-            handle.seek(_WINDOWS_LOCK_OFFSET)
+            handle.seek(0)
             msvcrt.locking(handle.fileno(), msvcrt.LK_UNLCK, 1)
         else:
             fcntl.flock(handle.fileno(), fcntl.LOCK_UN)

hermes_cli/auth.py

@@ -43,7 +43,7 @@ import yaml
 
 from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
 from hermes_constants import OPENROUTER_BASE_URL
-from utils import atomic_replace, atomic_yaml_write, is_truthy_value
+from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -2480,8 +2480,8 @@ def _resolve_verify(
     tls_state = tls_state if isinstance(tls_state, dict) else {}
 
     effective_insecure = (
-        is_truthy_value(insecure, default=False) if insecure is not None
-        else is_truthy_value(tls_state.get("insecure", False), default=False)
+        bool(insecure) if insecure is not None
+        else bool(tls_state.get("insecure", False))
     )
     effective_ca = (
         ca_bundle
@@ -3653,7 +3653,7 @@ def _update_config_for_provider(
 
     config["model"] = model_cfg
 
-    atomic_yaml_write(config_path, config, sort_keys=False)
+    config_path.write_text(yaml.safe_dump(config, sort_keys=False))
     return config_path
 
 
@@ -3712,7 +3712,7 @@ def _reset_config_provider() -> Path:
         model["provider"] = "auto"
         if "base_url" in model:
             model["base_url"] = OPENROUTER_BASE_URL
-    atomic_yaml_write(config_path, config, sort_keys=False)
+    config_path.write_text(yaml.safe_dump(config, sort_keys=False))
     return config_path
 
 

hermes_cli/commands.py

@@ -10,7 +10,6 @@ To add an alias: set ``aliases=("short",)`` on the existing ``CommandDef``.
 
 from __future__ import annotations
 
-import logging
 import os
 import re
 import shutil
@@ -20,10 +19,6 @@ from collections.abc import Callable, Mapping
 from dataclasses import dataclass
 from typing import Any
 
-from utils import is_truthy_value
-
-logger = logging.getLogger(__name__)
-
 # prompt_toolkit is an optional CLI dependency — only needed for
 # SlashCommandCompleter and SlashCommandAutoSuggest.  Gateway and test
 # environments that lack it must still be able to import this module
@@ -98,8 +93,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
                aliases=("q",), args_hint="<prompt>"),
     CommandDef("steer", "Inject a message after the next tool call without interrupting", "Session",
                args_hint="<prompt>"),
-    CommandDef("goal", "Set a standing goal Hermes works on across turns until achieved", "Session",
-               args_hint="[text | pause | resume | clear | status]"),
     CommandDef("status", "Show session info", "Session"),
     CommandDef("profile", "Show active profile name and home directory", "Info"),
     CommandDef("sethome", "Set this chat as the home channel", "Session",
@@ -378,7 +371,7 @@ def _resolve_config_gates() -> set[str]:
             else:
                 val = None
                 break
-        if is_truthy_value(val, default=False):
+        if val:
             result.add(cmd.name)
     return result
 
@@ -614,26 +607,13 @@ def _collect_gateway_skill_entries(
     try:
         from agent.skill_commands import get_skill_commands
         from tools.skills_tool import SKILLS_DIR
-        from agent.skill_utils import get_external_skills_dirs
         _skills_dir = str(SKILLS_DIR.resolve())
-        _hub_dir = str((SKILLS_DIR / ".hub").resolve()).rstrip("/") + "/"
-        # Build set of allowed directory prefixes: local skills dir + any
-        # user-configured ``skills.external_dirs``. Ensure each prefix ends
-        # with ``/`` so ``/my-skills`` does not also match ``/my-skills-extra``.
-        # Without this widening, external skills are visible in
-        # ``hermes skills list`` and the agent's ``/skill-name`` dispatch but
-        # silently excluded from gateway slash menus (#8110).
-        _allowed_prefixes = [_skills_dir.rstrip("/") + "/"]
-        _allowed_prefixes.extend(
-            str(d).rstrip("/") + "/" for d in get_external_skills_dirs()
-        )
+        _hub_dir = str((SKILLS_DIR / ".hub").resolve())
         skill_cmds = get_skill_commands()
         for cmd_key in sorted(skill_cmds):
             info = skill_cmds[cmd_key]
             skill_path = info.get("skill_md_path", "")
-            if not skill_path:
-                continue
-            if not any(skill_path.startswith(prefix) for prefix in _allowed_prefixes):
+            if not skill_path.startswith(_skills_dir):
                 continue
             if skill_path.startswith(_hub_dir):
                 continue
@@ -737,40 +717,24 @@ def discord_skill_commands(
 def discord_skill_commands_by_category(
     reserved_names: set[str],
 ) -> tuple[dict[str, list[tuple[str, str, str]]], list[tuple[str, str, str]], int]:
-    """Return skill entries organized by category for Discord ``/skill`` autocomplete.
+    """Return skill entries organized by category for Discord ``/skill`` subcommand groups.
 
-    Skills whose directory is nested at least 2 levels under a scan root
+    Skills whose directory is nested at least 2 levels under ``SKILLS_DIR``
     (e.g. ``creative/ascii-art/SKILL.md``) are grouped by their top-level
     category.  Root-level skills (e.g. ``dogfood/SKILL.md``) are returned as
-    *uncategorized*.
+    *uncategorized* — the caller should register them as direct subcommands
+    of the ``/skill`` group.
 
-    Scan roots include the local ``SKILLS_DIR`` **and** any configured
-    ``skills.external_dirs`` — matching the widened filter applied to the
-    flat ``discord_skill_commands()`` collector in #18741. Without this
-    parity, external-dir skills are visible via ``hermes skills list`` and
-    the agent's ``/skill-name`` dispatch but silently absent from Discord's
-    ``/skill`` autocomplete.
-
-    Filtering mirrors :func:`discord_skill_commands`: hub skills excluded,
-    per-platform disabled excluded, names clamped to 32 chars, descriptions
-    clamped to 100 chars.
-
-    The legacy 25-group × 25-subcommand caps (from the old nested
-    ``/skill <cat> <name>`` layout) are **not** applied — the live caller
-    (``_register_skill_group`` in ``gateway/platforms/discord.py``, refactored
-    in PR #11580) flattens these results and feeds them into a single
-    autocomplete callback, which scales to thousands of entries without any
-    per-command payload concerns. ``hidden_count`` is retained in the return
-    tuple for backward compatibility and still reports skills dropped for
-    other reasons (32-char clamp collision vs a reserved name).
+    The same filtering as :func:`discord_skill_commands` is applied: hub
+    skills excluded, per-platform disabled excluded, names clamped.
 
     Returns:
         ``(categories, uncategorized, hidden_count)``
 
         - *categories*: ``{category_name: [(name, description, cmd_key), ...]}``
         - *uncategorized*: ``[(name, description, cmd_key), ...]``
-        - *hidden_count*: skills dropped due to name clamp collisions
-          against already-registered command names.
+        - *hidden_count*: skills dropped due to Discord group limits
+          (25 subcommand groups, 25 subcommands per group)
     """
     from pathlib import Path as _P
 
@@ -784,33 +748,14 @@ def discord_skill_commands_by_category(
     # Collect raw skill data --------------------------------------------------
     categories: dict[str, list[tuple[str, str, str]]] = {}
     uncategorized: list[tuple[str, str, str]] = []
-    # Map clamped-32-char-name → what it came from, so we can emit an
-    # actionable warning on collision. Reserved (gateway-builtin) command
-    # names are marked with a sentinel so the warning distinguishes
-    # "skill collided with a reserved command" from "two skills collided
-    # on the 32-char clamp" — the latter is the rename-worthy case.
-    _names_used: dict[str, str] = {n: "<reserved>" for n in reserved_names}
+    _names_used: set[str] = set(reserved_names)
     hidden = 0
 
     try:
         from agent.skill_commands import get_skill_commands
-        from agent.skill_utils import get_external_skills_dirs
         from tools.skills_tool import SKILLS_DIR
-
         _skills_dir = SKILLS_DIR.resolve()
         _hub_dir = (SKILLS_DIR / ".hub").resolve()
-        # Build list of (resolved_root, is_local) tuples. Each external dir
-        # becomes its own scan root for category derivation — a skill at
-        # ``<external>/mlops/foo/SKILL.md`` is still categorized as "mlops".
-        _scan_roots: list[_P] = [_skills_dir]
-        try:
-            for ext in get_external_skills_dirs():
-                try:
-                    _scan_roots.append(_P(ext).resolve())
-                except Exception:
-                    continue
-        except Exception:
-            pass
         skill_cmds = get_skill_commands()
 
         for cmd_key in sorted(skill_cmds):
@@ -819,21 +764,10 @@ def discord_skill_commands_by_category(
             if not skill_path:
                 continue
             sp = _P(skill_path).resolve()
-            # Hub skills are loaded via the skill hub, not surfaced as
-            # slash commands.
-            if str(sp).startswith(str(_hub_dir)):
+            # Skip skills outside SKILLS_DIR or from the hub
+            if not str(sp).startswith(str(_skills_dir)):
                 continue
-            # Accept skill if it lives under any scan root; record the
-            # matching root so we can derive the category correctly.
-            matched_root: _P | None = None
-            for root in _scan_roots:
-                try:
-                    sp.relative_to(root)
-                except ValueError:
-                    continue
-                matched_root = root
-                break
-            if matched_root is None:
+            if str(sp).startswith(str(_hub_dir)):
                 continue
 
             skill_name = info.get("name", "")
@@ -841,50 +775,22 @@ def discord_skill_commands_by_category(
                 continue
 
             raw_name = cmd_key.lstrip("/")
-            # Clamp to 32 chars (Discord per-command name limit)
+            # Clamp to 32 chars (Discord limit)
             discord_name = raw_name[:32]
             if discord_name in _names_used:
-                # Two skills whose first 32 chars are identical. One wins
-                # (the first one seen, which is alphabetical because the
-                # caller iterates ``sorted(skill_cmds)``); the other is
-                # dropped from Discord's /skill autocomplete.
-                #
-                # Silently counting this as ``hidden`` (the old behavior)
-                # meant skill authors had no way to discover the drop —
-                # their skill just didn't appear in the picker. Emit a
-                # WARNING naming both sides so the author can rename the
-                # losing skill's frontmatter name to something with a
-                # distinct 32-char prefix.
-                prior = _names_used[discord_name]
-                if prior == "<reserved>":
-                    logger.warning(
-                        "Discord /skill: %r (from %r) collides on its 32-char "
-                        "clamp with a reserved gateway command name %r — the "
-                        "skill will not appear in the /skill autocomplete. "
-                        "Rename the skill's frontmatter ``name:`` to differ "
-                        "in its first 32 chars.",
-                        discord_name, cmd_key, discord_name,
-                    )
-                else:
-                    logger.warning(
-                        "Discord /skill: %r and %r both clamp to %r on "
-                        "Discord's 32-char command-name limit — only %r "
-                        "will appear in the /skill autocomplete. Rename "
-                        "one skill's frontmatter ``name:`` to differ in "
-                        "its first 32 chars.",
-                        prior, cmd_key, discord_name, prior,
-                    )
-                hidden += 1
                 continue
-            _names_used[discord_name] = cmd_key
+            _names_used.add(discord_name)
 
             desc = info.get("description", "")
             if len(desc) > 100:
                 desc = desc[:97] + "..."
 
-            # Determine category from the relative path within the matched
-            # scan root. e.g. creative/ascii-art/SKILL.md → ("creative", ...)
-            rel = sp.parent.relative_to(matched_root)
+            # Determine category from the relative path within SKILLS_DIR.
+            # e.g. creative/ascii-art/SKILL.md → parts = ("creative", "ascii-art")
+            try:
+                rel = sp.parent.relative_to(_skills_dir)
+            except ValueError:
+                continue
             parts = rel.parts
             if len(parts) >= 2:
                 cat = parts[0]
@@ -894,7 +800,28 @@ def discord_skill_commands_by_category(
     except Exception:
         pass
 
-    return categories, uncategorized, hidden
+    # Enforce Discord limits: 25 subcommand groups, 25 subcommands each ------
+    _MAX_GROUPS = 25
+    _MAX_PER_GROUP = 25
+
+    trimmed_categories: dict[str, list[tuple[str, str, str]]] = {}
+    group_count = 0
+    for cat in sorted(categories):
+        if group_count >= _MAX_GROUPS:
+            hidden += len(categories[cat])
+            continue
+        entries = categories[cat][:_MAX_PER_GROUP]
+        hidden += max(0, len(categories[cat]) - _MAX_PER_GROUP)
+        trimmed_categories[cat] = entries
+        group_count += 1
+
+    # Uncategorized skills also count against the 25 top-level limit
+    remaining_slots = _MAX_GROUPS - group_count
+    if len(uncategorized) > remaining_slots:
+        hidden += len(uncategorized) - remaining_slots
+        uncategorized = uncategorized[:remaining_slots]
+
+    return trimmed_categories, uncategorized, hidden
 
 
 # ---------------------------------------------------------------------------
@@ -907,13 +834,6 @@ def discord_skill_commands_by_category(
 _SLACK_MAX_SLASH_COMMANDS = 50
 _SLACK_NAME_LIMIT = 32
 _SLACK_INVALID_CHARS = re.compile(r"[^a-z0-9_\-]")
-_SLACK_RESERVED_COMMANDS = frozenset({
-    # Built-in Slack slash commands that cannot be registered by apps.
-    # https://slack.com/help/articles/201259356-Use-built-in-slash-commands
-    "me", "status", "away", "dnd", "shrug", "remind", "msg", "feed",
-    "who", "collapse", "expand", "leave", "join", "open", "search",
-    "topic", "mute", "pro", "shortcuts",
-})
 
 
 def _sanitize_slack_name(raw: str) -> str:
@@ -940,10 +860,6 @@ def slack_native_slashes() -> list[tuple[str, str, str]]:
     documented form (e.g. ``/background``, ``/bg``, and ``/btw`` all work).
     Plugin-registered slash commands are included too.
 
-    Commands whose sanitized name collides with a Slack built-in
-    (e.g. ``/status``, ``/me``, ``/join``) are silently skipped.  Users
-    can still reach them via ``/hermes <command>``.
-
     Results are clamped to Slack's 50-command limit with duplicate-name
     avoidance. ``/hermes`` is always reserved as the first entry so the
     legacy ``/hermes <subcommand>`` form keeps working for anything that
@@ -961,8 +877,6 @@ def slack_native_slashes() -> list[tuple[str, str, str]]:
         slack_name = _sanitize_slack_name(name)
         if not slack_name or slack_name in seen:
             return
-        if slack_name in _SLACK_RESERVED_COMMANDS:
-            return
         if len(entries) >= _SLACK_MAX_SLASH_COMMANDS:
             return
         # Slack description cap is 2000 chars; keep it short.

hermes_cli/config.py

@@ -400,12 +400,7 @@ DEFAULT_CONFIG = {
         # The gateway stops accepting new work, waits for running agents
         # to finish, then interrupts any remaining runs after the timeout.
         # 0 = no drain, interrupt immediately.
-        #
-        # 180s is calibrated for realistic in-flight agent turns: a typical
-        # coding conversation mid-reasoning runs 60–150s per call, so a 60s
-        # budget routinely interrupted legitimate work on /restart. Raise
-        # further in config.yaml if you run very-long-reasoning models.
-        "restart_drain_timeout": 180,
+        "restart_drain_timeout": 60,
         # Max app-level retry attempts for API errors (connection drops,
         # provider timeouts, 5xx, etc.) before the agent surfaces the
         # failure.  The OpenAI SDK already does its own low-level retries
@@ -462,7 +457,6 @@ DEFAULT_CONFIG = {
         # remains available as a tool regardless of this setting — the routing
         # only controls how inbound user images are presented.
         "image_input_mode": "auto",
-        "disabled_toolsets": [],
     },
     
     "terminal": {
@@ -612,24 +606,6 @@ DEFAULT_CONFIG = {
         "max_line_length": 2000,
     },
 
-    # Tool loop guardrails nudge models when they repeat failed or
-    # non-progressing tool calls. Soft warnings are always-on by default;
-    # hard stops are opt-in so interactive CLI/TUI sessions keep flowing.
-    "tool_loop_guardrails": {
-        "warnings_enabled": True,
-        "hard_stop_enabled": False,
-        "warn_after": {
-            "exact_failure": 2,
-            "same_tool_failure": 3,
-            "idempotent_no_progress": 2,
-        },
-        "hard_stop_after": {
-            "exact_failure": 5,
-            "same_tool_failure": 8,
-            "idempotent_no_progress": 5,
-        },
-    },
-
     "compression": {
         "enabled": True,
         "threshold": 0.50,            # compress when context usage exceeds this ratio
@@ -644,18 +620,6 @@ DEFAULT_CONFIG = {
         "cache_ttl": "5m",
     },
 
-    # OpenRouter-specific settings.
-    # response_cache: enable OpenRouter response caching (X-OpenRouter-Cache header).
-    #   When enabled, identical requests return cached responses for free (zero billing).
-    #   This is separate from Anthropic prompt caching and works alongside it.
-    #   See: https://openrouter.ai/docs/guides/features/response-caching
-    # response_cache_ttl: how long cached responses remain valid, in seconds (1-86400).
-    #   Default 300 (5 minutes). Only used when response_cache is enabled.
-    "openrouter": {
-        "response_cache": True,
-        "response_cache_ttl": 300,
-    },
-
     # AWS Bedrock provider configuration.
     # Only used when model.provider is "bedrock".
     "bedrock": {
@@ -792,14 +756,6 @@ DEFAULT_CONFIG = {
         "tool_progress_command": False,  # Enable /verbose command in messaging gateway
         "tool_progress_overrides": {},  # DEPRECATED — use display.platforms instead
         "tool_preview_length": 0,  # Max chars for tool call previews (0 = no limit, show full paths/commands)
-        # Auto-delete system-notice replies (e.g. "✨ New session started!",
-        # "♻ Restarting gateway…", "⚡ Stopped…") after N seconds on platforms
-        # that support message deletion (currently Telegram; other platforms
-        # ignore and leave the message in place).  Only affects slash-command
-        # replies wrapped with gateway.platforms.base.EphemeralReply — agent
-        # responses and content messages are never touched.  Default 0
-        # (disabled) preserves prior behavior.
-        "ephemeral_system_ttl": 0,
         "platforms": {},  # Per-platform display overrides: {"telegram": {"tool_progress": "all"}, "slack": {"tool_progress": "off"}}
         # Gateway runtime-metadata footer appended to the FINAL message of a turn
         # (disabled by default to keep replies minimal). When enabled, renders
@@ -842,7 +798,7 @@ DEFAULT_CONFIG = {
             # Voices: alloy, echo, fable, onyx, nova, shimmer
         },
         "xai": {
-            "voice_id": "eve",  # or custom voice ID — see https://docs.x.ai/developers/model-capabilities/audio/custom-voices
+            "voice_id": "eve",
             "language": "en",
             "sample_rate": 24000,
             "bit_rate": 128000,
@@ -969,23 +925,7 @@ DEFAULT_CONFIG = {
     # injected at the start of every API call for few-shot priming.
     # Never saved to sessions, logs, or trajectories.
     "prefill_messages_file": "",
-
-    # Goals — persistent cross-turn goals (Ralph-style loop).
-    # After every turn, a lightweight judge call asks the auxiliary model
-    # whether the active /goal is satisfied by the assistant's last
-    # response. If not, Hermes feeds a continuation prompt back into the
-    # same session and keeps working until the goal is done, the turn
-    # budget is exhausted, or the user pauses/clears it. Judge failures
-    # fail OPEN (continue) so a flaky judge never wedges progress — the
-    # turn budget is the real backstop.
-    "goals": {
-        # Max continuation turns before Hermes auto-pauses the goal and
-        # asks the user to /goal resume. Protects against judge false
-        # negatives (goal actually done but judge says continue) and
-        # unbounded model spend on fuzzy / unachievable goals.
-        "max_turns": 20,
-    },
-
+    
     # Skills — external skill directories for sharing skills across tools/agents.
     # Each path is expanded (~, ${VAR}) and resolved.  Read-only — skill creation
     # always goes to ~/.hermes/skills/.
@@ -1039,14 +979,6 @@ DEFAULT_CONFIG = {
         # Archive a skill (move to skills/.archive/) after this many days
         # without use. Archived skills are recoverable — no auto-deletion.
         "archive_after_days": 90,
-        # Pre-run backup: before every real curator pass (dry-run is
-        # skipped), snapshot ~/.hermes/skills/ into
-        # ~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz so the
-        # user can roll back with `hermes curator rollback`.
-        "backup": {
-            "enabled": True,
-            "keep": 5,  # retain last N regular snapshots
-        },
     },
 
     # Honcho AI-native memory -- reads ~/.honcho/config.json as single source of truth.
@@ -1818,29 +1750,6 @@ OPTIONAL_ENV_VARS = {
         "password": False,
         "category": "tool",
     },
-    "TINYFISH_API_KEY": {
-        "description": "TinyFish API key for cloud browser, search, fetch, and agent",
-        "prompt": "TinyFish API key",
-        "url": "https://agent.tinyfish.ai/api-keys",
-        "tools": ["browser_navigate", "browser_click"],
-        "password": True,
-        "category": "tool",
-    },
-    "TINYFISH_API_URL": {
-        "description": "TinyFish browser API URL override (optional, for staging/dev)",
-        "prompt": "TinyFish API URL (leave empty for default)",
-        "url": None,
-        "tools": ["browser_navigate", "browser_click"],
-        "password": False,
-        "category": "tool",
-    },
-    "TINYFISH_BROWSER_TIMEOUT": {
-        "description": "TinyFish browser session inactivity timeout in seconds (optional, default 300)",
-        "prompt": "Browser session timeout (seconds)",
-        "tools": ["browser_navigate", "browser_click"],
-        "password": False,
-        "category": "tool",
-    },
     "CAMOFOX_URL": {
         "description": "Camofox browser server URL for local anti-detection browsing (e.g. http://localhost:9377)",
         "prompt": "Camofox server URL",
@@ -2509,17 +2418,7 @@ def get_missing_skill_config_vars() -> List[Dict[str, Any]]:
     except Exception:
         return []
 
-    try:
-        all_vars = discover_all_skill_config_vars()
-    except Exception as e:
-        # A malformed SKILL.md, unreadable external skill dir, or similar
-        # should never break `hermes update`.  Skill-config prompting is a
-        # post-migration nicety, not a blocker.
-        import logging
-        logging.getLogger(__name__).debug(
-            "discover_all_skill_config_vars failed: %s", e
-        )
-        return []
+    all_vars = discover_all_skill_config_vars()
     if not all_vars:
         return []
 
@@ -4456,7 +4355,6 @@ def show_config():
         ("TAVILY_API_KEY", "Tavily"),
         ("BROWSERBASE_API_KEY", "Browserbase"),
         ("BROWSER_USE_API_KEY", "Browser Use"),
-        ("TINYFISH_API_KEY", "TinyFish"),
         ("FAL_KEY", "FAL"),
     ]
     
@@ -4641,7 +4539,6 @@ def set_config_value(key: str, value: str):
         'FIRECRAWL_GATEWAY_URL', 'TOOL_GATEWAY_DOMAIN', 'TOOL_GATEWAY_SCHEME',
         'TOOL_GATEWAY_USER_TOKEN', 'TAVILY_API_KEY',
         'BROWSERBASE_API_KEY', 'BROWSERBASE_PROJECT_ID', 'BROWSER_USE_API_KEY',
-        'TINYFISH_API_KEY', 'TINYFISH_API_URL', 'TINYFISH_BROWSER_TIMEOUT',
         'FAL_KEY', 'TELEGRAM_BOT_TOKEN', 'DISCORD_BOT_TOKEN',
         'TERMINAL_SSH_HOST', 'TERMINAL_SSH_USER', 'TERMINAL_SSH_KEY',
         'SUDO_PASSWORD', 'SLACK_BOT_TOKEN', 'SLACK_APP_TOKEN',

hermes_cli/curator.py

@@ -160,11 +160,7 @@ def _cmd_run(args) -> int:
         print("curator: disabled via config; enable with `curator.enabled: true`")
         return 1
 
-    dry = bool(getattr(args, "dry_run", False))
-    if dry:
-        print("curator: running DRY-RUN (report only, no mutations)...")
-    else:
-        print("curator: running review pass...")
+    print("curator: running review pass...")
 
     def _on_summary(msg: str) -> None:
         print(msg)
@@ -172,29 +168,17 @@ def _cmd_run(args) -> int:
     result = curator.run_curator_review(
         on_summary=_on_summary,
         synchronous=bool(args.synchronous),
-        dry_run=dry,
     )
     auto = result.get("auto_transitions", {})
     if auto:
-        if dry:
-            print(
-                f"auto (preview): {auto.get('checked', 0)} candidate skill(s) "
-                "— no transitions applied in dry-run"
-            )
-        else:
-            print(
-                f"auto: checked={auto.get('checked', 0)} "
-                f"stale={auto.get('marked_stale', 0)} "
-                f"archived={auto.get('archived', 0)} "
-                f"reactivated={auto.get('reactivated', 0)}"
-            )
+        print(
+            f"auto: checked={auto.get('checked', 0)} "
+            f"stale={auto.get('marked_stale', 0)} "
+            f"archived={auto.get('archived', 0)} "
+            f"reactivated={auto.get('reactivated', 0)}"
+        )
     if not args.synchronous:
         print("llm pass running in background — check `hermes curator status` later")
-    if dry:
-        print(
-            "dry-run: no changes applied. When the report lands, read it with "
-            "`hermes curator status` and run `hermes curator run` (no flag) to apply."
-        )
     return 0
 
 
@@ -245,98 +229,6 @@ def _cmd_restore(args) -> int:
     return 0 if ok else 1
 
 
-def _cmd_backup(args) -> int:
-    """Take a manual snapshot of the skills tree. Same mechanism as the
-    automatic pre-run snapshot, just user-initiated."""
-    from agent import curator_backup
-    if not curator_backup.is_enabled():
-        print(
-            "curator: backups are disabled via config "
-            "(`curator.backup.enabled: false`); re-enable to snapshot"
-        )
-        return 1
-    reason = getattr(args, "reason", None) or "manual"
-    snap = curator_backup.snapshot_skills(reason=reason)
-    if snap is None:
-        print("curator: snapshot failed — check logs (backup disabled or IO error)")
-        return 1
-    print(f"curator: snapshot created at ~/.hermes/skills/.curator_backups/{snap.name}")
-    return 0
-
-
-def _cmd_rollback(args) -> int:
-    """Restore the skills tree from a snapshot. Defaults to newest.
-
-    ``--list`` prints available snapshots and exits. ``--id <stamp>`` picks
-    a specific one. Without ``-y``, prompts for confirmation. A safety
-    snapshot of the current tree is always taken first, so rollbacks are
-    themselves undoable.
-    """
-    from agent import curator_backup
-
-    if getattr(args, "list", False):
-        print(curator_backup.summarize_backups())
-        return 0
-
-    backup_id = getattr(args, "backup_id", None)
-    target_path = curator_backup._resolve_backup(backup_id)
-    if target_path is None:
-        rows = curator_backup.list_backups()
-        if not rows:
-            print(
-                "curator: no snapshots exist yet. Take one with "
-                "`hermes curator backup` or wait for the next curator run."
-            )
-        else:
-            print(
-                f"curator: no snapshot matching "
-                f"{'id ' + repr(backup_id) if backup_id else 'your query'}."
-            )
-            print("Available:")
-            print(curator_backup.summarize_backups())
-        return 1
-
-    manifest = curator_backup._read_manifest(target_path)
-    print(f"Rollback target: {target_path.name}")
-    if manifest:
-        print(f"  reason:      {manifest.get('reason', '?')}")
-        print(f"  created_at:  {manifest.get('created_at', '?')}")
-        print(f"  skill files: {manifest.get('skill_files', '?')}")
-        cron = manifest.get("cron_jobs") or {}
-        if isinstance(cron, dict):
-            if cron.get("backed_up"):
-                print(
-                    f"  cron jobs:   {cron.get('jobs_count', 0)} "
-                    f"(will be restored for skill-link fields only)"
-                )
-            else:
-                reason = cron.get("reason", "not captured")
-                print(f"  cron jobs:   not in snapshot ({reason})")
-    print(
-        "\nThis will replace the current ~/.hermes/skills/ tree (a safety "
-        "snapshot of the current state is taken first so this is undoable). "
-        "Cron jobs that still exist will have their skills/skill fields "
-        "restored from the snapshot; all other cron fields are left alone."
-    )
-
-    if not getattr(args, "yes", False):
-        try:
-            ans = input("Proceed? [y/N] ").strip().lower()
-        except (EOFError, KeyboardInterrupt):
-            print("\ncancelled")
-            return 1
-        if ans not in ("y", "yes"):
-            print("cancelled")
-            return 1
-
-    ok, msg, _ = curator_backup.rollback(backup_id=target_path.name)
-    if ok:
-        print(f"curator: {msg}")
-        return 0
-    print(f"curator: rollback failed — {msg}")
-    return 1
-
-
 # ---------------------------------------------------------------------------
 # argparse wiring (called from hermes_cli.main)
 # ---------------------------------------------------------------------------
@@ -358,11 +250,6 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
         "--sync", "--synchronous", dest="synchronous", action="store_true",
         help="Wait for the LLM review pass to finish (default: background thread)",
     )
-    p_run.add_argument(
-        "--dry-run", dest="dry_run", action="store_true",
-        help="Report only — no state changes, no archives, no consolidation "
-             "(use this to preview what curator would do)",
-    )
     p_run.set_defaults(func=_cmd_run)
 
     p_pause = subs.add_parser("pause", help="Pause the curator until resumed")
@@ -383,36 +270,6 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
     p_restore.add_argument("skill", help="Skill name")
     p_restore.set_defaults(func=_cmd_restore)
 
-    p_backup = subs.add_parser(
-        "backup",
-        help="Take a manual tar.gz snapshot of ~/.hermes/skills/ "
-             "(curator also does this automatically before every real run)",
-    )
-    p_backup.add_argument(
-        "--reason", default=None,
-        help="Free-text label stored in manifest.json (default: 'manual')",
-    )
-    p_backup.set_defaults(func=_cmd_backup)
-
-    p_rollback = subs.add_parser(
-        "rollback",
-        help="Restore ~/.hermes/skills/ from a curator snapshot "
-             "(defaults to the newest)",
-    )
-    p_rollback.add_argument(
-        "--list", action="store_true",
-        help="List available snapshots and exit without restoring",
-    )
-    p_rollback.add_argument(
-        "--id", dest="backup_id", default=None,
-        help="Snapshot id to restore (see `--list`); default: newest",
-    )
-    p_rollback.add_argument(
-        "-y", "--yes", action="store_true",
-        help="Skip confirmation prompt",
-    )
-    p_rollback.set_defaults(func=_cmd_rollback)
-
 
 def cli_main(argv=None) -> int:
     """Standalone entry (also usable by hermes_cli.main fallthrough)."""

hermes_cli/doctor.py

@@ -263,11 +263,8 @@ def run_doctor(args):
     if env_path.exists():
         check_ok(f"{_DHH}/.env file exists")
         
-        # Check for common issues. Pin encoding to UTF-8 because .env files are
-        # written as UTF-8 everywhere in the codebase, while Path.read_text()
-        # defaults to the system locale — which crashes on non-UTF-8 Windows
-        # locales (e.g. GBK) as soon as the file contains any non-ASCII byte.
-        content = env_path.read_text(encoding="utf-8")
+        # Check for common issues
+        content = env_path.read_text()
         if _has_provider_env_config(content):
             check_ok("API key or custom endpoint configured")
         else:

hermes_cli/gateway.py

@@ -10,7 +10,6 @@ import shutil
 import signal
 import subprocess
 import sys
-import textwrap
 from dataclasses import dataclass
 from pathlib import Path
 
@@ -60,13 +59,6 @@ class GatewayRuntimeSnapshot:
     def has_process_service_mismatch(self) -> bool:
         return self.service_installed and self.running and not self.service_running
 
-
-@dataclass(frozen=True)
-class ProfileGatewayProcess:
-    profile: str
-    path: Path
-    pid: int
-
 def _get_service_pids() -> set:
     """Return PIDs currently managed by systemd or launchd gateway services.
 
@@ -188,7 +180,7 @@ def _graceful_restart_via_sigusr1(pid: int, drain_timeout: float) -> bool:
 
     SIGUSR1 is wired in gateway/run.py to ``request_restart(via_service=True)``
     which drains in-flight agent runs (up to ``agent.restart_drain_timeout``
-    seconds), then exits with code 75.  Both systemd (``Restart=always``
+    seconds), then exits with code 75.  Both systemd (``Restart=on-failure``
     + ``RestartForceExitStatus=75``) and launchd (``KeepAlive.SuccessfulExit
     = false``) relaunch the process after the graceful exit.
 
@@ -379,83 +371,6 @@ def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = Fals
     return pids
 
 
-def find_profile_gateway_processes(
-    exclude_pids: set | None = None,
-) -> list[ProfileGatewayProcess]:
-    """Return running gateway PIDs mapped to Hermes profiles via PID files."""
-    _exclude = set(exclude_pids or set())
-    processes: list[ProfileGatewayProcess] = []
-    try:
-        from gateway.status import get_running_pid
-        from hermes_cli.profiles import list_profiles
-    except Exception:
-        return processes
-
-    seen: set[int] = set()
-    for profile in list_profiles():
-        try:
-            pid = get_running_pid(profile.path / "gateway.pid", cleanup_stale=False)
-        except Exception:
-            continue
-        if pid is None or pid <= 0 or pid in _exclude or pid in seen:
-            continue
-        seen.add(pid)
-        processes.append(ProfileGatewayProcess(profile=profile.name, path=profile.path, pid=pid))
-    return processes
-
-
-def _gateway_run_args_for_profile(profile: str) -> list[str]:
-    args = [get_python_path(), "-m", "hermes_cli.main"]
-    if profile != "default":
-        args.extend(["--profile", profile])
-    args.extend(["gateway", "run", "--replace"])
-    return args
-
-
-def launch_detached_profile_gateway_restart(profile: str, old_pid: int) -> bool:
-    """Relaunch a manually-run profile gateway after its current PID exits."""
-    if old_pid <= 0:
-        return False
-
-    watcher = textwrap.dedent(
-        """
-        import os
-        import subprocess
-        import sys
-        import time
-
-        pid = int(sys.argv[1])
-        cmd = sys.argv[2:]
-        deadline = time.monotonic() + 120
-        while time.monotonic() < deadline:
-            try:
-                os.kill(pid, 0)
-            except ProcessLookupError:
-                break
-            except PermissionError:
-                pass
-            time.sleep(0.2)
-        subprocess.Popen(
-            cmd,
-            stdout=subprocess.DEVNULL,
-            stderr=subprocess.DEVNULL,
-            start_new_session=True,
-        )
-        """
-    ).strip()
-
-    try:
-        subprocess.Popen(
-            [sys.executable, "-c", watcher, str(old_pid), *_gateway_run_args_for_profile(profile)],
-            stdout=subprocess.DEVNULL,
-            stderr=subprocess.DEVNULL,
-            start_new_session=True,
-        )
-    except OSError:
-        return False
-    return True
-
-
 def _probe_systemd_service_running(system: bool = False) -> tuple[bool, bool]:
     selected_system = _select_systemd_scope(system)
     unit_exists = get_systemd_unit_path(system=selected_system).exists()
@@ -1655,7 +1570,8 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
 Description={SERVICE_DESCRIPTION}
 After=network-online.target
 Wants=network-online.target
-StartLimitIntervalSec=0
+StartLimitIntervalSec=600
+StartLimitBurst=5
 
 [Service]
 Type=simple
@@ -1669,10 +1585,8 @@ Environment="LOGNAME={username}"
 Environment="PATH={sane_path}"
 Environment="VIRTUAL_ENV={venv_dir}"
 Environment="HERMES_HOME={hermes_home}"
-Restart=always
-RestartSec=60
-RestartMaxDelaySec=300
-RestartSteps=5
+Restart=on-failure
+RestartSec=30
 RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
 KillMode=mixed
 KillSignal=SIGTERM
@@ -1692,9 +1606,9 @@ WantedBy=multi-user.target
     sane_path = ":".join(path_entries)
     return f"""[Unit]
 Description={SERVICE_DESCRIPTION}
-After=network-online.target
-Wants=network-online.target
-StartLimitIntervalSec=0
+After=network.target
+StartLimitIntervalSec=600
+StartLimitBurst=5
 
 [Service]
 Type=simple
@@ -1703,10 +1617,8 @@ WorkingDirectory={working_dir}
 Environment="PATH={sane_path}"
 Environment="VIRTUAL_ENV={venv_dir}"
 Environment="HERMES_HOME={hermes_home}"
-Restart=always
-RestartSec=60
-RestartMaxDelaySec=300
-RestartSteps=5
+Restart=on-failure
+RestartSec=30
 RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
 KillMode=mixed
 KillSignal=SIGTERM
@@ -2454,7 +2366,7 @@ def run_gateway(verbose: int = 0, quiet: bool = False, replace: bool = False):
     print()
     
     # Exit with code 1 if gateway fails to connect any platform,
-    # so systemd Restart=always will retry on transient errors
+    # so systemd Restart=on-failure will retry on transient errors
     verbosity = None if quiet else verbose
     try:
         success = asyncio.run(start_gateway(replace=replace, verbosity=verbosity))
@@ -4465,4 +4377,4 @@ def _gateway_command_inner(args):
         if not supports_systemd_services() and not is_macos():
             print("Legacy unit migration only applies to systemd-based Linux hosts.")
             return
-        remove_legacy_hermes_units(interactive=not yes, dry_run=dry_run)
+        remove_legacy_hermes_units(interactive=not yes, dry_run=dry_run)

hermes_cli/goals.py

@@ -1,535 +0,0 @@
-"""Persistent session goals — the Ralph loop for Hermes.
-
-A goal is a free-form user objective that stays active across turns. After
-each turn completes, a small judge call asks an auxiliary model "is this
-goal satisfied by the assistant's last response?". If not, Hermes feeds a
-continuation prompt back into the same session and keeps working until the
-goal is done, turn budget is exhausted, the user pauses/clears it, or the
-user sends a new message (which takes priority and pauses the goal loop).
-
-State is persisted in SessionDB's ``state_meta`` table keyed by
-``goal:<session_id>`` so ``/resume`` picks it up.
-
-Design notes / invariants:
-
-- The continuation prompt is just a normal user message appended to the
-  session via ``run_conversation``. No system-prompt mutation, no toolset
-  swap — prompt caching stays intact.
-- Judge failures are fail-OPEN: ``continue``. A broken judge must not wedge
-  progress; the turn budget is the backstop.
-- When a real user message arrives mid-loop it preempts the continuation
-  prompt and also pauses the goal loop for that turn (we still re-judge
-  after, so if the user's message happens to complete the goal the judge
-  will say ``done``).
-- This module has zero hard dependency on ``cli.HermesCLI`` or the gateway
-  runner — both wire the same ``GoalManager`` in.
-
-Nothing in this module touches the agent's system prompt or toolset.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import re
-import time
-from dataclasses import dataclass, asdict
-from typing import Any, Dict, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-
-# ──────────────────────────────────────────────────────────────────────
-# Constants & defaults
-# ──────────────────────────────────────────────────────────────────────
-
-DEFAULT_MAX_TURNS = 20
-DEFAULT_JUDGE_TIMEOUT = 30.0
-# Cap how much of the last response + recent messages we send to the judge.
-_JUDGE_RESPONSE_SNIPPET_CHARS = 4000
-
-
-CONTINUATION_PROMPT_TEMPLATE = (
-    "[Continuing toward your standing goal]\n"
-    "Goal: {goal}\n\n"
-    "Continue working toward this goal. Take the next concrete step. "
-    "If you believe the goal is complete, state so explicitly and stop. "
-    "If you are blocked and need input from the user, say so clearly and stop."
-)
-
-
-JUDGE_SYSTEM_PROMPT = (
-    "You are a strict judge evaluating whether an autonomous agent has "
-    "achieved a user's stated goal. You receive the goal text and the "
-    "agent's most recent response. Your only job is to decide whether "
-    "the goal is fully satisfied based on that response.\n\n"
-    "A goal is DONE only when:\n"
-    "- The response explicitly confirms the goal was completed, OR\n"
-    "- The response clearly shows the final deliverable was produced, OR\n"
-    "- The response explains the goal is unachievable / blocked / needs "
-    "user input (treat this as DONE with reason describing the block).\n\n"
-    "Otherwise the goal is NOT done — CONTINUE.\n\n"
-    "Reply ONLY with a single JSON object on one line:\n"
-    '{\"done\": <true|false>, \"reason\": \"<one-sentence rationale>\"}'
-)
-
-
-JUDGE_USER_PROMPT_TEMPLATE = (
-    "Goal:\n{goal}\n\n"
-    "Agent's most recent response:\n{response}\n\n"
-    "Is the goal satisfied?"
-)
-
-
-# ──────────────────────────────────────────────────────────────────────
-# Dataclass
-# ──────────────────────────────────────────────────────────────────────
-
-
-@dataclass
-class GoalState:
-    """Serializable goal state stored per session."""
-
-    goal: str
-    status: str = "active"          # active | paused | done | cleared
-    turns_used: int = 0
-    max_turns: int = DEFAULT_MAX_TURNS
-    created_at: float = 0.0
-    last_turn_at: float = 0.0
-    last_verdict: Optional[str] = None        # "done" | "continue" | "skipped"
-    last_reason: Optional[str] = None
-    paused_reason: Optional[str] = None       # why we auto-paused (budget, etc.)
-
-    def to_json(self) -> str:
-        return json.dumps(asdict(self), ensure_ascii=False)
-
-    @classmethod
-    def from_json(cls, raw: str) -> "GoalState":
-        data = json.loads(raw)
-        return cls(
-            goal=data.get("goal", ""),
-            status=data.get("status", "active"),
-            turns_used=int(data.get("turns_used", 0) or 0),
-            max_turns=int(data.get("max_turns", DEFAULT_MAX_TURNS) or DEFAULT_MAX_TURNS),
-            created_at=float(data.get("created_at", 0.0) or 0.0),
-            last_turn_at=float(data.get("last_turn_at", 0.0) or 0.0),
-            last_verdict=data.get("last_verdict"),
-            last_reason=data.get("last_reason"),
-            paused_reason=data.get("paused_reason"),
-        )
-
-
-# ──────────────────────────────────────────────────────────────────────
-# Persistence (SessionDB state_meta)
-# ──────────────────────────────────────────────────────────────────────
-
-
-def _meta_key(session_id: str) -> str:
-    return f"goal:{session_id}"
-
-
-_DB_CACHE: Dict[str, Any] = {}
-
-
-def _get_session_db() -> Optional[Any]:
-    """Return a SessionDB instance for the current HERMES_HOME.
-
-    SessionDB has no built-in singleton, but opening a new connection per
-    /goal call would thrash the file. We cache one instance per
-    ``hermes_home`` path so profile switches still pick up the right DB.
-    Defensive against import/instantiation failures so tests and
-    non-standard launchers can still use the GoalManager.
-    """
-    try:
-        from hermes_constants import get_hermes_home
-        from hermes_state import SessionDB
-
-        home = str(get_hermes_home())
-    except Exception as exc:  # pragma: no cover
-        logger.debug("GoalManager: SessionDB bootstrap failed (%s)", exc)
-        return None
-
-    cached = _DB_CACHE.get(home)
-    if cached is not None:
-        return cached
-    try:
-        db = SessionDB()
-    except Exception as exc:  # pragma: no cover
-        logger.debug("GoalManager: SessionDB() raised (%s)", exc)
-        return None
-    _DB_CACHE[home] = db
-    return db
-
-
-def load_goal(session_id: str) -> Optional[GoalState]:
-    """Load the goal for a session, or None if none exists."""
-    if not session_id:
-        return None
-    db = _get_session_db()
-    if db is None:
-        return None
-    try:
-        raw = db.get_meta(_meta_key(session_id))
-    except Exception as exc:
-        logger.debug("GoalManager: get_meta failed: %s", exc)
-        return None
-    if not raw:
-        return None
-    try:
-        return GoalState.from_json(raw)
-    except Exception as exc:
-        logger.warning("GoalManager: could not parse stored goal for %s: %s", session_id, exc)
-        return None
-
-
-def save_goal(session_id: str, state: GoalState) -> None:
-    """Persist a goal to SessionDB. No-op if DB unavailable."""
-    if not session_id:
-        return
-    db = _get_session_db()
-    if db is None:
-        return
-    try:
-        db.set_meta(_meta_key(session_id), state.to_json())
-    except Exception as exc:
-        logger.debug("GoalManager: set_meta failed: %s", exc)
-
-
-def clear_goal(session_id: str) -> None:
-    """Mark a goal cleared in the DB (preserved for audit, status=cleared)."""
-    state = load_goal(session_id)
-    if state is None:
-        return
-    state.status = "cleared"
-    save_goal(session_id, state)
-
-
-# ──────────────────────────────────────────────────────────────────────
-# Judge
-# ──────────────────────────────────────────────────────────────────────
-
-
-def _truncate(text: str, limit: int) -> str:
-    if not text:
-        return ""
-    if len(text) <= limit:
-        return text
-    return text[:limit] + "… [truncated]"
-
-
-_JSON_OBJECT_RE = re.compile(r"\{.*?\}", re.DOTALL)
-
-
-def _parse_judge_response(raw: str) -> Tuple[bool, str]:
-    """Parse the judge's reply. Fail-open to ``(False, "<reason>")``.
-
-    Returns ``(done, reason)``.
-    """
-    if not raw:
-        return False, "judge returned empty response"
-
-    text = raw.strip()
-
-    # Strip markdown code fences the model may wrap JSON in.
-    if text.startswith("```"):
-        text = text.strip("`")
-        # Peel off leading json/JSON/etc tag
-        nl = text.find("\n")
-        if nl != -1:
-            text = text[nl + 1:]
-
-    # First try: parse the whole blob.
-    data: Optional[Dict[str, Any]] = None
-    try:
-        data = json.loads(text)
-    except Exception:
-        # Second try: pull the first JSON object out.
-        match = _JSON_OBJECT_RE.search(text)
-        if match:
-            try:
-                data = json.loads(match.group(0))
-            except Exception:
-                data = None
-
-    if not isinstance(data, dict):
-        return False, f"judge reply was not JSON: {_truncate(raw, 200)!r}"
-
-    done_val = data.get("done")
-    if isinstance(done_val, str):
-        done = done_val.strip().lower() in ("true", "yes", "1", "done")
-    else:
-        done = bool(done_val)
-    reason = str(data.get("reason") or "").strip()
-    if not reason:
-        reason = "no reason provided"
-    return done, reason
-
-
-def judge_goal(
-    goal: str,
-    last_response: str,
-    *,
-    timeout: float = DEFAULT_JUDGE_TIMEOUT,
-) -> Tuple[str, str]:
-    """Ask the auxiliary model whether the goal is satisfied.
-
-    Returns ``(verdict, reason)`` where verdict is ``"done"``, ``"continue"``,
-    or ``"skipped"`` (when the judge couldn't be reached).
-
-    This is deliberately fail-open: any error returns ``("continue", "...")``
-    so a broken judge doesn't wedge progress — the turn budget is the
-    backstop.
-    """
-    if not goal.strip():
-        return "skipped", "empty goal"
-    if not last_response.strip():
-        # No substantive reply this turn — almost certainly not done yet.
-        return "continue", "empty response (nothing to evaluate)"
-
-    try:
-        from agent.auxiliary_client import get_text_auxiliary_client
-    except Exception as exc:
-        logger.debug("goal judge: auxiliary client import failed: %s", exc)
-        return "continue", "auxiliary client unavailable"
-
-    try:
-        client, model = get_text_auxiliary_client("goal_judge")
-    except Exception as exc:
-        logger.debug("goal judge: get_text_auxiliary_client failed: %s", exc)
-        return "continue", "auxiliary client unavailable"
-
-    if client is None or not model:
-        return "continue", "no auxiliary client configured"
-
-    prompt = JUDGE_USER_PROMPT_TEMPLATE.format(
-        goal=_truncate(goal, 2000),
-        response=_truncate(last_response, _JUDGE_RESPONSE_SNIPPET_CHARS),
-    )
-
-    try:
-        resp = client.chat.completions.create(
-            model=model,
-            messages=[
-                {"role": "system", "content": JUDGE_SYSTEM_PROMPT},
-                {"role": "user", "content": prompt},
-            ],
-            temperature=0,
-            max_tokens=200,
-            timeout=timeout,
-        )
-    except Exception as exc:
-        logger.info("goal judge: API call failed (%s) — falling through to continue", exc)
-        return "continue", f"judge error: {type(exc).__name__}"
-
-    try:
-        raw = resp.choices[0].message.content or ""
-    except Exception:
-        raw = ""
-
-    done, reason = _parse_judge_response(raw)
-    verdict = "done" if done else "continue"
-    logger.info("goal judge: verdict=%s reason=%s", verdict, _truncate(reason, 120))
-    return verdict, reason
-
-
-# ──────────────────────────────────────────────────────────────────────
-# GoalManager — the orchestration surface CLI + gateway talk to
-# ──────────────────────────────────────────────────────────────────────
-
-
-class GoalManager:
-    """Per-session goal state + continuation decisions.
-
-    The CLI and gateway each hold one ``GoalManager`` per live session.
-
-    Methods:
-
-    - ``set(goal)`` — start a new standing goal.
-    - ``clear()`` — remove the active goal.
-    - ``pause()`` / ``resume()`` — explicit user controls.
-    - ``status()`` — printable one-liner.
-    - ``evaluate_after_turn(last_response)`` — call the judge, update state,
-      and return a decision dict the caller uses to drive the next turn.
-    - ``next_continuation_prompt()`` — the canonical user-role message to
-      feed back into ``run_conversation``.
-    """
-
-    def __init__(self, session_id: str, *, default_max_turns: int = DEFAULT_MAX_TURNS):
-        self.session_id = session_id
-        self.default_max_turns = int(default_max_turns or DEFAULT_MAX_TURNS)
-        self._state: Optional[GoalState] = load_goal(session_id)
-
-    # --- introspection ------------------------------------------------
-
-    @property
-    def state(self) -> Optional[GoalState]:
-        return self._state
-
-    def is_active(self) -> bool:
-        return self._state is not None and self._state.status == "active"
-
-    def has_goal(self) -> bool:
-        return self._state is not None and self._state.status in ("active", "paused")
-
-    def status_line(self) -> str:
-        s = self._state
-        if s is None or s.status in ("cleared",):
-            return "No active goal. Set one with /goal <text>."
-        turns = f"{s.turns_used}/{s.max_turns} turns"
-        if s.status == "active":
-            return f"⊙ Goal (active, {turns}): {s.goal}"
-        if s.status == "paused":
-            extra = f" — {s.paused_reason}" if s.paused_reason else ""
-            return f"⏸ Goal (paused, {turns}{extra}): {s.goal}"
-        if s.status == "done":
-            return f"✓ Goal done ({turns}): {s.goal}"
-        return f"Goal ({s.status}, {turns}): {s.goal}"
-
-    # --- mutation -----------------------------------------------------
-
-    def set(self, goal: str, *, max_turns: Optional[int] = None) -> GoalState:
-        goal = (goal or "").strip()
-        if not goal:
-            raise ValueError("goal text is empty")
-        state = GoalState(
-            goal=goal,
-            status="active",
-            turns_used=0,
-            max_turns=int(max_turns) if max_turns else self.default_max_turns,
-            created_at=time.time(),
-            last_turn_at=0.0,
-        )
-        self._state = state
-        save_goal(self.session_id, state)
-        return state
-
-    def pause(self, reason: str = "user-paused") -> Optional[GoalState]:
-        if not self._state:
-            return None
-        self._state.status = "paused"
-        self._state.paused_reason = reason
-        save_goal(self.session_id, self._state)
-        return self._state
-
-    def resume(self, *, reset_budget: bool = True) -> Optional[GoalState]:
-        if not self._state:
-            return None
-        self._state.status = "active"
-        self._state.paused_reason = None
-        if reset_budget:
-            self._state.turns_used = 0
-        save_goal(self.session_id, self._state)
-        return self._state
-
-    def clear(self) -> None:
-        if self._state is None:
-            return
-        self._state.status = "cleared"
-        save_goal(self.session_id, self._state)
-        self._state = None
-
-    def mark_done(self, reason: str) -> None:
-        if not self._state:
-            return
-        self._state.status = "done"
-        self._state.last_verdict = "done"
-        self._state.last_reason = reason
-        save_goal(self.session_id, self._state)
-
-    # --- the main entry point called after every turn -----------------
-
-    def evaluate_after_turn(
-        self,
-        last_response: str,
-        *,
-        user_initiated: bool = True,
-    ) -> Dict[str, Any]:
-        """Run the judge and update state. Return a decision dict.
-
-        ``user_initiated`` distinguishes a real user prompt (True) from a
-        continuation prompt we fed ourselves (False). Both increment
-        ``turns_used`` because both consume model budget.
-
-        Decision keys:
-          - ``status``: current goal status after update
-          - ``should_continue``: bool — caller should fire another turn
-          - ``continuation_prompt``: str or None
-          - ``verdict``: "done" | "continue" | "skipped" | "inactive"
-          - ``reason``: str
-          - ``message``: user-visible one-liner to print/send
-        """
-        state = self._state
-        if state is None or state.status != "active":
-            return {
-                "status": state.status if state else None,
-                "should_continue": False,
-                "continuation_prompt": None,
-                "verdict": "inactive",
-                "reason": "no active goal",
-                "message": "",
-            }
-
-        # Count the turn that just finished.
-        state.turns_used += 1
-        state.last_turn_at = time.time()
-
-        verdict, reason = judge_goal(state.goal, last_response)
-        state.last_verdict = verdict
-        state.last_reason = reason
-
-        if verdict == "done":
-            state.status = "done"
-            save_goal(self.session_id, state)
-            return {
-                "status": "done",
-                "should_continue": False,
-                "continuation_prompt": None,
-                "verdict": "done",
-                "reason": reason,
-                "message": f"✓ Goal achieved: {reason}",
-            }
-
-        if state.turns_used >= state.max_turns:
-            state.status = "paused"
-            state.paused_reason = f"turn budget exhausted ({state.turns_used}/{state.max_turns})"
-            save_goal(self.session_id, state)
-            return {
-                "status": "paused",
-                "should_continue": False,
-                "continuation_prompt": None,
-                "verdict": "continue",
-                "reason": reason,
-                "message": (
-                    f"⏸ Goal paused — {state.turns_used}/{state.max_turns} turns used. "
-                    "Use /goal resume to keep going, or /goal clear to stop."
-                ),
-            }
-
-        save_goal(self.session_id, state)
-        return {
-            "status": "active",
-            "should_continue": True,
-            "continuation_prompt": self.next_continuation_prompt(),
-            "verdict": "continue",
-            "reason": reason,
-            "message": (
-                f"↻ Continuing toward goal ({state.turns_used}/{state.max_turns}): {reason}"
-            ),
-        }
-
-    def next_continuation_prompt(self) -> Optional[str]:
-        if not self._state or self._state.status != "active":
-            return None
-        return CONTINUATION_PROMPT_TEMPLATE.format(goal=self._state.goal)
-
-
-__all__ = [
-    "GoalState",
-    "GoalManager",
-    "CONTINUATION_PROMPT_TEMPLATE",
-    "DEFAULT_MAX_TURNS",
-    "load_goal",
-    "save_goal",
-    "clear_goal",
-    "judge_goal",
-]

hermes_cli/main.py

@@ -289,7 +289,7 @@ def _has_any_provider_configured() -> bool:
     env_file = get_env_path()
     if env_file.exists():
         try:
-            for line in env_file.read_text(encoding="utf-8").splitlines():
+            for line in env_file.read_text().splitlines():
                 line = line.strip()
                 if line.startswith("#") or "=" not in line:
                     continue
@@ -800,8 +800,6 @@ def _print_tui_exit_summary(session_id: Optional[str], active_session_file: Opti
 
         title = db.get_session_title(target)
         message_count = int(session.get("message_count") or 0)
-        if message_count == 0:
-            return  # No real conversation — don't show resume info
         input_tokens = int(session.get("input_tokens") or 0)
         output_tokens = int(session.get("output_tokens") or 0)
         cache_read_tokens = int(session.get("cache_read_tokens") or 0)
@@ -5433,45 +5431,6 @@ def _find_stale_dashboard_pids() -> list[int]:
     return dashboard_pids
 
 
-def _print_curator_first_run_notice() -> None:
-    """Print a short heads-up about the skill curator after `hermes update`.
-
-    Only fires when the curator is enabled AND has no recorded run yet, which
-    is exactly the window where the gateway ticker used to fire Curator
-    against a fresh skill library immediately after an update. We defer the
-    first real pass by one ``interval_hours``; this notice tells the user how
-    to preview or disable before then. Silent on steady state.
-    """
-    try:
-        from agent import curator
-    except Exception:
-        return
-    try:
-        if not curator.is_enabled():
-            return
-        state = curator.load_state()
-    except Exception:
-        return
-    if state.get("last_run_at"):
-        # Curator has run before (real or already seeded) — no notice needed.
-        return
-    try:
-        hours = curator.get_interval_hours()
-    except Exception:
-        hours = 24 * 7
-    days = max(1, hours // 24)
-    print()
-    print("ℹ Skill curator")
-    print(
-        f"  Background skill maintenance is enabled. First pass is deferred "
-        f"~{days}d after installation; only agent-created skills are in "
-        f"scope and nothing is ever auto-deleted (archive is recoverable)."
-    )
-    print("  Preview now:  hermes curator run --dry-run")
-    print("  Pause it:     hermes curator pause")
-    print("  Docs:         https://hermes-agent.nousresearch.com/docs/user-guide/features/curator")
-
-
 def _kill_stale_dashboard_processes(
     reason: str = "the running backend no longer matches the updated frontend",
 ) -> None:
@@ -5709,10 +5668,6 @@ def _update_via_zip(args):
 
     print()
     print("✓ Update complete!")
-    try:
-        _print_curator_first_run_notice()
-    except Exception as e:
-        logger.debug("Curator first-run notice failed: %s", e)
     _kill_stale_dashboard_processes()
 
 
@@ -6718,7 +6673,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
         if gateway_mode
         else None
     )
-    assume_yes = bool(getattr(args, "yes", False))
 
     print("⚕ Updating Hermes Agent...")
     print()
@@ -6838,10 +6792,8 @@ def _cmd_update_impl(args, gateway_mode: bool):
         else:
             auto_stash_ref = _stash_local_changes_if_needed(git_cmd, PROJECT_ROOT)
 
-        prompt_for_restore = (
-            auto_stash_ref is not None
-            and not assume_yes
-            and (gateway_mode or (sys.stdin.isatty() and sys.stdout.isatty()))
+        prompt_for_restore = auto_stash_ref is not None and (
+            gateway_mode or (sys.stdin.isatty() and sys.stdout.isatty())
         )
 
         # Check if there are updates
@@ -7102,10 +7054,7 @@ def _cmd_update_impl(args, gateway_mode: bool):
                 print(f"  ℹ️  {len(missing_config)} new config option(s) available")
 
             print()
-            if assume_yes:
-                print("  ℹ --yes: auto-applying config migration (skipping API-key prompts).")
-                response = "y"
-            elif gateway_mode:
+            if gateway_mode:
                 response = (
                     _gateway_prompt(
                         "Would you like to configure new options now? [Y/n]", "n"
@@ -7131,17 +7080,14 @@ def _cmd_update_impl(args, gateway_mode: bool):
 
             if response in ("", "y", "yes"):
                 print()
-                # In gateway mode OR under --yes, run auto-migrations only (no
-                # input() prompts for API keys which would hang the detached
-                # process / defeat the point of --yes).
-                results = migrate_config(
-                    interactive=not (gateway_mode or assume_yes), quiet=False
-                )
+                # In gateway mode, run auto-migrations only (no input() prompts
+                # for API keys which would hang the detached process).
+                results = migrate_config(interactive=not gateway_mode, quiet=False)
 
                 if results["env_added"] or results["config_added"]:
                     print()
                     print("✓ Configuration updated!")
-                if (gateway_mode or assume_yes) and missing_env:
+                if gateway_mode and missing_env:
                     print("  ℹ API keys require manual entry: hermes config migrate")
             else:
                 print()
@@ -7152,15 +7098,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
         print()
         print("✓ Update complete!")
 
-        # Curator first-run heads-up. Only prints when curator is enabled AND
-        # has never run — i.e. the window where the ticker would otherwise
-        # have fired against a fresh skill library. Kept silent on steady
-        # state so we don't nag.
-        try:
-            _print_curator_first_run_notice()
-        except Exception as e:
-            logger.debug("Curator first-run notice failed: %s", e)
-
         # Repair RHEL-family root installs where /usr/local/bin isn't on PATH
         # for non-login interactive shells.  No-op on every other platform.
         try:
@@ -7200,8 +7137,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
                 supports_systemd_services,
                 _ensure_user_systemd_env,
                 find_gateway_pids,
-                find_profile_gateway_processes,
-                launch_detached_profile_gateway_restart,
                 _get_service_pids,
                 _graceful_restart_via_sigusr1,
             )
@@ -7305,7 +7240,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
 
             restarted_services = []
             killed_pids = set()
-            relaunched_profiles = []
 
             # --- Systemd services (Linux) ---
             # Discover all hermes-gateway* units (default + profiles)
@@ -7495,33 +7429,7 @@ def _cmd_update_impl(args, gateway_mode: bool):
             manual_pids = find_gateway_pids(
                 exclude_pids=service_pids, all_profiles=True
             )
-            profile_processes = {
-                proc.pid: proc
-                for proc in find_profile_gateway_processes(exclude_pids=service_pids)
-                if proc.pid in manual_pids
-            }
-            for pid, proc in profile_processes.items():
-                if not launch_detached_profile_gateway_restart(proc.profile, pid):
-                    continue
-                # Prefer a graceful SIGUSR1 drain so in-flight agent runs
-                # finish before the watcher respawns the gateway.  If the
-                # gateway doesn't support SIGUSR1 or doesn't exit within
-                # the drain budget, fall back to SIGTERM — the watcher
-                # still sees the exit and relaunches either way.
-                drained = _graceful_restart_via_sigusr1(
-                    pid, drain_timeout=_drain_budget,
-                )
-                if not drained:
-                    try:
-                        os.kill(pid, _signal.SIGTERM)
-                    except (ProcessLookupError, PermissionError):
-                        pass
-                killed_pids.add(pid)
-                relaunched_profiles.append(proc.profile)
-
             for pid in manual_pids:
-                if pid in profile_processes:
-                    continue
                 try:
                     os.kill(pid, _signal.SIGTERM)
                     killed_pids.add(pid)
@@ -7532,14 +7440,11 @@ def _cmd_update_impl(args, gateway_mode: bool):
                 print()
                 for svc in restarted_services:
                     print(f"  ✓ Restarted {svc}")
-                if relaunched_profiles:
-                    names = ", ".join(relaunched_profiles)
-                    print(f"  ✓ Restarting manual gateway profile(s): {names}")
-                unmapped_count = len(killed_pids) - len(relaunched_profiles)
-                if unmapped_count:
-                    print(f"  → Stopped {unmapped_count} manual gateway process(es)")
+                if killed_pids:
+                    print(f"  → Stopped {len(killed_pids)} manual gateway process(es)")
                     print("    Restart manually: hermes gateway run")
-                    if unmapped_count > 1:
+                    # Also restart for each profile if needed
+                    if len(killed_pids) > 1:
                         print(
                             "    (or: hermes -p <profile> gateway run  for each profile)"
                         )
@@ -7548,42 +7453,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
                 # No gateways were running — nothing to do
                 pass
 
-            # --- Post-restart survivor sweep -----------------------------
-            # Issue #17648: some gateways ignore SIGTERM (stuck drain,
-            # blocked I/O, PID dead but zombie).  The detached profile
-            # watchers wait 120s for the old PID to exit — if it never
-            # does, no respawn happens and the user keeps hitting
-            # ImportError against a stale sys.modules.  Give the
-            # graceful paths a brief window to complete, then SIGKILL
-            # any remaining pre-update PIDs so the watcher / service
-            # manager can relaunch with fresh code.
-            try:
-                _time.sleep(3.0)
-                _service_pids_after = _get_service_pids()
-                _surviving = find_gateway_pids(
-                    exclude_pids=_service_pids_after, all_profiles=True,
-                )
-                # Scope to PIDs we already tried to kill during this
-                # update (killed_pids).  Anything new is a gateway that
-                # started AFTER our restart attempt — respecting user
-                # intent, we don't kill those.
-                _stuck = [pid for pid in _surviving if pid in killed_pids]
-                if _stuck:
-                    print()
-                    print(
-                        f"  ⚠ {len(_stuck)} gateway process(es) ignored SIGTERM — force-killing"
-                    )
-                    for pid in _stuck:
-                        try:
-                            os.kill(pid, _signal.SIGKILL)
-                        except (ProcessLookupError, PermissionError):
-                            pass
-                    # Give the OS a beat to reap the processes so the
-                    # watchers see them exit and respawn.
-                    _time.sleep(1.5)
-            except Exception as _sweep_exc:
-                logger.debug("Post-restart survivor sweep failed: %s", _sweep_exc)
-
         except Exception as e:
             logger.debug("Gateway restart during update failed: %s", e)
 
@@ -9992,13 +9861,6 @@ Examples:
         default=False,
         help="Force a pre-update backup for this run (off by default; overrides updates.pre_update_backup)",
     )
-    update_parser.add_argument(
-        "--yes",
-        "-y",
-        action="store_true",
-        default=False,
-        help="Assume yes for interactive prompts (config migration, stash restore). API-key entry is skipped; run 'hermes config migrate' separately for those.",
-    )
     update_parser.set_defaults(func=cmd_update)
 
     # =========================================================================

hermes_cli/memory_setup.py

@@ -361,7 +361,7 @@ def _write_env_vars(env_path: Path, env_writes: dict) -> None:
 
     existing_lines = []
     if env_path.exists():
-        existing_lines = env_path.read_text(encoding="utf-8").splitlines()
+        existing_lines = env_path.read_text().splitlines()
 
     updated_keys = set()
     new_lines = []

hermes_cli/model_switch.py

@@ -891,19 +891,14 @@ def switch_model(
     if not validation.get("accepted"):
         override = False
         if user_providers:
-            # user_providers is a dict: {provider_slug: config_dict}
-            for slug, cfg in user_providers.items():
-                if slug == target_provider:
-                    cfg_models = cfg.get("models", {})
-                    # Direct membership works for dict (keys) and list (strings)
-                    if new_model in cfg_models:
+            for up in user_providers:
+                if isinstance(up, dict) and up.get("provider") == target_provider:
+                    cfg_models = up.get("models", [])
+                    if new_model in cfg_models or any(
+                        m.get("name") == new_model for m in cfg_models if isinstance(m, dict)
+                    ):
                         override = True
                         break
-                    # Also accept if models is a list of dicts with 'name' field
-                    if isinstance(cfg_models, list):
-                        if any(m.get("name") == new_model for m in cfg_models if isinstance(m, dict)):
-                            override = True
-                            break
         if override:
             validation = {"accepted": True, "persist": True, "recognized": False, "message": validation.get("message", "")}
         else:
@@ -1057,45 +1052,6 @@ def list_authenticated_providers(
         if normed:
             _builtin_endpoints.add(normed)
 
-    def _has_fast_aws_sdk_signal() -> bool:
-        """Return True when explicit AWS auth config is present.
-
-        This intentionally avoids botocore's full credential chain. Provider
-        picker/model-switch discovery can run for non-Bedrock providers, and
-        botocore may otherwise probe EC2 IMDS (169.254.169.254) on local
-        machines before returning no credentials.
-        """
-        if os.environ.get("AWS_BEARER_TOKEN_BEDROCK", "").strip():
-            return True
-        if (
-            os.environ.get("AWS_ACCESS_KEY_ID", "").strip()
-            and os.environ.get("AWS_SECRET_ACCESS_KEY", "").strip()
-        ):
-            return True
-        return any(
-            os.environ.get(name, "").strip()
-            for name in (
-                "AWS_PROFILE",
-                "AWS_CONTAINER_CREDENTIALS_RELATIVE_URI",
-                "AWS_CONTAINER_CREDENTIALS_FULL_URI",
-                "AWS_WEB_IDENTITY_TOKEN_FILE",
-            )
-        )
-
-    def _has_aws_sdk_creds_for_listing(slug: str) -> bool:
-        """Credential check for AWS SDK providers in non-runtime discovery."""
-        slug_norm = str(slug or "").strip().lower()
-        current_norm = str(current_provider or "").strip().lower()
-        if _has_fast_aws_sdk_signal():
-            return True
-        if slug_norm != current_norm:
-            return False
-        try:
-            from agent.bedrock_adapter import has_aws_credentials
-            return bool(has_aws_credentials())
-        except Exception:
-            return False
-
     data = fetch_models_dev()
 
     # Build curated model lists keyed by hermes provider ID
@@ -1223,9 +1179,7 @@ def list_authenticated_providers(
 
         # Check if credentials exist
         has_creds = False
-        if overlay.auth_type == "aws_sdk":
-            has_creds = _has_aws_sdk_creds_for_listing(hermes_slug)
-        elif overlay.extra_env_vars:
+        if overlay.extra_env_vars:
             has_creds = any(os.environ.get(ev) for ev in overlay.extra_env_vars)
         # Also check api_key_env_vars from PROVIDER_REGISTRY for api_key auth_type
         if not has_creds and overlay.auth_type == "api_key":
@@ -1365,7 +1319,11 @@ def list_authenticated_providers(
         # credentials come from the boto3 credential chain (env vars,
         # ~/.aws/credentials, instance roles, etc.)
         if not _cp_has_creds and _cp_config and getattr(_cp_config, "auth_type", "") == "aws_sdk":
-            _cp_has_creds = _has_aws_sdk_creds_for_listing(_cp.slug)
+            try:
+                from agent.bedrock_adapter import has_aws_credentials
+                _cp_has_creds = has_aws_credentials()
+            except Exception:
+                pass
 
         if not _cp_has_creds:
             continue
@@ -1454,17 +1412,14 @@ def list_authenticated_providers(
                         models_list = list(fb)
 
             # Prefer the endpoint's live /models list when credentials are
-            # available, unless the provider explicitly opts out via
-            # discover_models: false (e.g. dedicated endpoints that expose
-            # the entire aggregator catalog via /models).
+            # available. This keeps OpenAI-compatible relays (for example CRS)
+            # in sync when the server catalog changes without requiring the
+            # user to mirror every model into config.yaml.
             api_key = str(ep_cfg.get("api_key", "") or "").strip()
             if not api_key:
                 key_env = str(ep_cfg.get("key_env", "") or "").strip()
                 api_key = os.environ.get(key_env, "").strip() if key_env else ""
-            discover = ep_cfg.get("discover_models", True)
-            if isinstance(discover, str):
-                discover = discover.lower() not in ("false", "no", "0")
-            if api_url and api_key and discover:
+            if api_url and api_key:
                 try:
                     from hermes_cli.models import fetch_api_models
                     live_models = fetch_api_models(api_key, api_url)

hermes_cli/models.py

@@ -774,6 +774,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("nous",           "Nous Portal",              "Nous Portal (Nous Research subscription)"),
     ProviderEntry("openrouter",     "OpenRouter",               "OpenRouter (100+ models, pay-per-use)"),
     ProviderEntry("lmstudio",       "LM Studio",                "LM Studio (local desktop app with built-in model server)"),
+    ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway (200+ models, $5 free credit, no markup)"),
     ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
     ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
     ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2.5 and V2 models — pro, omni, flash)"),
@@ -803,7 +804,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("opencode-go",    "OpenCode Go",              "OpenCode Go (open models, $10/month subscription)"),
     ProviderEntry("bedrock",        "AWS Bedrock",              "AWS Bedrock (Claude, Nova, Llama, DeepSeek — IAM or API key)"),
     ProviderEntry("azure-foundry",  "Azure Foundry",            "Azure Foundry (OpenAI-style or Anthropic-style endpoint — your Azure AI deployment)"),
-    ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway"),
 ]
 
 # Derived dicts — used throughout the codebase

hermes_cli/nous_subscription.py

@@ -141,7 +141,6 @@ def _browser_label(current_provider: str) -> str:
         "browserbase": "Browserbase",
         "browser-use": "Browser Use",
         "firecrawl": "Firecrawl",
-        "tinyfish": "TinyFish",
         "camofox": "Camofox",
         "local": "Local browser",
     }
@@ -170,7 +169,6 @@ def _resolve_browser_feature_state(
     direct_browserbase: bool,
     direct_browser_use: bool,
     direct_firecrawl: bool,
-    direct_tinyfish: bool,
     managed_browser_available: bool,
 ) -> tuple[str, bool, bool, bool]:
     """Resolve browser availability using the same precedence as runtime."""
@@ -198,10 +196,6 @@ def _resolve_browser_feature_state(
             available = bool(browser_local_available and direct_firecrawl)
             active = bool(browser_tool_enabled and available)
             return current_provider, available, active, False
-        if current_provider == "tinyfish":
-            available = bool(browser_local_available and direct_tinyfish)
-            active = bool(browser_tool_enabled and available)
-            return current_provider, available, active, False
         if current_provider == "camofox":
             return current_provider, False, False, False
 
@@ -292,7 +286,6 @@ def get_nous_subscription_features(
     direct_camofox = bool(get_env_value("CAMOFOX_URL"))
     direct_browserbase = bool(get_env_value("BROWSERBASE_API_KEY") and get_env_value("BROWSERBASE_PROJECT_ID"))
     direct_browser_use = bool(get_env_value("BROWSER_USE_API_KEY"))
-    direct_tinyfish = bool(get_env_value("TINYFISH_API_KEY"))
     direct_modal = has_direct_modal_credentials()
 
     # When use_gateway is set, suppress direct credentials for managed detection
@@ -370,7 +363,6 @@ def get_nous_subscription_features(
         direct_browserbase=direct_browserbase,
         direct_browser_use=direct_browser_use,
         direct_firecrawl=direct_firecrawl,
-        direct_tinyfish=direct_tinyfish,
         managed_browser_available=managed_browser_available,
     )
 

hermes_cli/plugins.py

@@ -33,15 +33,12 @@ so plugin-defined tools appear alongside the built-in tools.
 
 from __future__ import annotations
 
-import asyncio
 import importlib
 import importlib.metadata
 import importlib.util
-import inspect
 import logging
 import os
 import sys
-import threading
 import types
 from dataclasses import dataclass, field
 from pathlib import Path
@@ -1229,55 +1226,6 @@ def get_plugin_command_handler(name: str) -> Optional[Callable]:
     return entry["handler"] if entry else None
 
 
-_PLUGIN_COMMAND_AWAIT_TIMEOUT_SECS = 30.0
-
-
-def resolve_plugin_command_result(result: Any) -> Any:
-    """Resolve a plugin command return value, awaiting async handlers when needed.
-
-    Sync CLI/TUI dispatch sites call plugin handlers from plain functions.
-    If a handler is async, await it directly when no loop is running; if
-    we're already inside an active loop, run it in a helper thread with its
-    own loop so the caller still gets a concrete result synchronously. The
-    threaded path is bounded by a 30s timeout so a hung async handler cannot
-    wedge the terminal indefinitely.
-    """
-    if not inspect.isawaitable(result):
-        return result
-
-    try:
-        asyncio.get_running_loop()
-    except RuntimeError:
-        return asyncio.run(result)
-
-    outcome: Dict[str, Any] = {}
-    failure: Dict[str, BaseException] = {}
-    done = threading.Event()
-
-    def _runner() -> None:
-        try:
-            outcome["value"] = asyncio.run(result)
-        except BaseException as exc:  # pragma: no cover - re-raised below
-            failure["exc"] = exc
-        finally:
-            done.set()
-
-    thread = threading.Thread(
-        target=_runner,
-        name="hermes-plugin-command-await",
-        daemon=True,
-    )
-    thread.start()
-    if not done.wait(timeout=_PLUGIN_COMMAND_AWAIT_TIMEOUT_SECS):
-        raise TimeoutError(
-            "Plugin command async handler did not complete within "
-            f"{_PLUGIN_COMMAND_AWAIT_TIMEOUT_SECS:.0f}s"
-        )
-    if "exc" in failure:
-        raise failure["exc"]
-    return outcome.get("value")
-
-
 def get_plugin_commands() -> Dict[str, dict]:
     """Return the full plugin commands dict (name → {handler, description, plugin}).
 

hermes_cli/plugins_cmd.py

@@ -15,18 +15,13 @@ import shutil
 import subprocess
 import sys
 from pathlib import Path
-from typing import Any, Optional
+from typing import Optional
 
 from hermes_constants import get_hermes_home
 from hermes_cli.config import cfg_get
 
 logger = logging.getLogger(__name__)
 
-
-class PluginOperationError(Exception):
-    """Recoverable plugin install/update failure (CLI exits; HTTP maps to 4xx)."""
-
-
 # Minimum manifest version this installer understands.
 # Plugins may declare ``manifest_version: 1`` in plugin.yaml;
 # future breaking changes to the manifest schema bump this.
@@ -155,24 +150,6 @@ def _copy_example_files(plugin_dir: Path, console) -> None:
                 )
 
 
-def _missing_requires_env_names(manifest: dict) -> list[str]:
-    """Return declared ``requires_env`` names that are unset in ``~/.hermes/.env``."""
-    requires_env = manifest.get("requires_env") or []
-    if not requires_env:
-        return []
-
-    from hermes_cli.config import get_env_value
-
-    env_specs: list[dict] = []
-    for entry in requires_env:
-        if isinstance(entry, str):
-            env_specs.append({"name": entry})
-        elif isinstance(entry, dict) and entry.get("name"):
-            env_specs.append(entry)
-
-    return [s["name"] for s in env_specs if s.get("name") and not get_env_value(s["name"])]
-
-
 def _prompt_plugin_env_vars(manifest: dict, console) -> None:
     """Prompt for required environment variables declared in plugin.yaml.
 
@@ -306,95 +283,6 @@ def _require_installed_plugin(name: str, plugins_dir: Path, console) -> Path:
 # ---------------------------------------------------------------------------
 
 
-def _install_plugin_core(identifier: str, *, force: bool) -> tuple[Path, dict, str]:
-    """Clone Git plugin into ``~/.hermes/plugins``.
-
-    Returns ``(target_dir, installed_manifest, canonical_name)``.
-    Raises ``PluginOperationError`` on failure.
-    """
-    import tempfile
-
-    try:
-        git_url = _resolve_git_url(identifier)
-    except ValueError as e:
-        raise PluginOperationError(str(e)) from e
-
-    plugins_dir = _plugins_dir()
-
-    with tempfile.TemporaryDirectory() as tmp:
-        tmp_target = Path(tmp) / "plugin"
-
-        try:
-            result = subprocess.run(
-                ["git", "clone", "--depth", "1", git_url, str(tmp_target)],
-                capture_output=True,
-                text=True,
-                timeout=60,
-            )
-        except FileNotFoundError as e:
-            raise PluginOperationError(
-                "git is not installed or not in PATH.",
-            ) from e
-        except subprocess.TimeoutExpired as e:
-            raise PluginOperationError(
-                "Git clone timed out after 60 seconds.",
-            ) from e
-
-        if result.returncode != 0:
-            err = (result.stderr or result.stdout or "").strip()
-            raise PluginOperationError(f"Git clone failed:\n{err}")
-
-        manifest = _read_manifest(tmp_target)
-        plugin_name = manifest.get("name") or _repo_name_from_url(git_url)
-
-        try:
-            target = _sanitize_plugin_name(plugin_name, plugins_dir)
-        except ValueError as e:
-            raise PluginOperationError(str(e)) from e
-
-        mv = manifest.get("manifest_version")
-        if mv is not None:
-            try:
-                mv_int = int(mv)
-            except (ValueError, TypeError):
-                raise PluginOperationError(
-                    f"Plugin '{plugin_name}' has invalid manifest_version "
-                    f"'{mv}' (expected an integer).",
-                ) from None
-            if mv_int > _SUPPORTED_MANIFEST_VERSION:
-                from hermes_cli.config import recommended_update_command
-
-                raise PluginOperationError(
-                    f"Plugin '{plugin_name}' requires manifest_version {mv}, "
-                    f"but this installer only supports up to {_SUPPORTED_MANIFEST_VERSION}. "
-                    f"Run {recommended_update_command()} to update Hermes.",
-                ) from None
-
-        if target.exists():
-            if not force:
-                raise PluginOperationError(
-                    f"Plugin '{plugin_name}' already exists. Use force reinstall "
-                    f"or run `hermes plugins update {plugin_name}`.",
-                )
-            shutil.rmtree(target)
-
-        shutil.move(str(tmp_target), str(target))
-
-    has_yaml = (target / "plugin.yaml").exists() or (target / "plugin.yml").exists()
-    if not has_yaml and not (target / "__init__.py").exists():
-        logger.warning(
-            "%s has no plugin.yaml / __init__.py; may not be a valid plugin",
-            plugin_name,
-        )
-
-    from rich.console import Console
-
-    _copy_example_files(target, Console())
-    installed_manifest = _read_manifest(target)
-    installed_name = installed_manifest.get("name") or target.name
-    return target, installed_manifest, installed_name
-
-
 def cmd_install(
     identifier: str,
     force: bool = False,
@@ -405,6 +293,7 @@ def cmd_install(
     After install, prompt "Enable now? [y/N]" unless *enable* is provided
     (True = auto-enable without prompting, False = install disabled).
     """
+    import tempfile
     from rich.console import Console
 
     console = Console()
@@ -415,41 +304,114 @@ def cmd_install(
         console.print(f"[red]Error:[/red] {e}")
         sys.exit(1)
 
+    # Warn about insecure / local URL schemes
     if git_url.startswith(("http://", "file://")):
         console.print(
             "[yellow]Warning:[/yellow] Using insecure/local URL scheme. "
-            "Consider using https:// or git@ for production installs.",
+            "Consider using https:// or git@ for production installs."
         )
 
-    console.print(f"[dim]Cloning {git_url}...[/dim]")
+    plugins_dir = _plugins_dir()
 
-    try:
-        target, installed_manifest, installed_name = _install_plugin_core(
-            identifier,
-            force=force,
-        )
-    except PluginOperationError as e:
-        console.print(f"[red]Error:[/red] {e}")
-        sys.exit(1)
+    # Clone into a temp directory first so we can read plugin.yaml for the name
+    with tempfile.TemporaryDirectory() as tmp:
+        tmp_target = Path(tmp) / "plugin"
+        console.print(f"[dim]Cloning {git_url}...[/dim]")
 
-    if not (target / "plugin.yaml").exists() and not (target / "plugin.yml").exists() and not (
-        target / "__init__.py"
-    ).exists():
+        try:
+            result = subprocess.run(
+                ["git", "clone", "--depth", "1", git_url, str(tmp_target)],
+                capture_output=True,
+                text=True,
+                timeout=60,
+            )
+        except FileNotFoundError:
+            console.print("[red]Error:[/red] git is not installed or not in PATH.")
+            sys.exit(1)
+        except subprocess.TimeoutExpired:
+            console.print("[red]Error:[/red] Git clone timed out after 60 seconds.")
+            sys.exit(1)
+
+        if result.returncode != 0:
+            console.print(
+                f"[red]Error:[/red] Git clone failed:\n{result.stderr.strip()}"
+            )
+            sys.exit(1)
+
+        # Read manifest
+        manifest = _read_manifest(tmp_target)
+        plugin_name = manifest.get("name") or _repo_name_from_url(git_url)
+
+        # Sanitize plugin name against path traversal
+        try:
+            target = _sanitize_plugin_name(plugin_name, plugins_dir)
+        except ValueError as e:
+            console.print(f"[red]Error:[/red] {e}")
+            sys.exit(1)
+
+        # Check manifest_version compatibility
+        mv = manifest.get("manifest_version")
+        if mv is not None:
+            try:
+                mv_int = int(mv)
+            except (ValueError, TypeError):
+                console.print(
+                    f"[red]Error:[/red] Plugin '{plugin_name}' has invalid "
+                    f"manifest_version '{mv}' (expected an integer)."
+                )
+                sys.exit(1)
+            if mv_int > _SUPPORTED_MANIFEST_VERSION:
+                from hermes_cli.config import recommended_update_command
+                console.print(
+                    f"[red]Error:[/red] Plugin '{plugin_name}' requires manifest_version "
+                    f"{mv}, but this installer only supports up to {_SUPPORTED_MANIFEST_VERSION}.\n"
+                    f"Run [bold]{recommended_update_command()}[/bold] to get a newer installer."
+                )
+                sys.exit(1)
+
+        if target.exists():
+            if not force:
+                console.print(
+                    f"[red]Error:[/red] Plugin '{plugin_name}' already exists at {target}.\n"
+                    f"Use [bold]--force[/bold] to remove and reinstall, or "
+                    f"[bold]hermes plugins update {plugin_name}[/bold] to pull latest."
+                )
+                sys.exit(1)
+            console.print(f"[dim]  Removing existing {plugin_name}...[/dim]")
+            shutil.rmtree(target)
+
+        # Move from temp to final location
+        shutil.move(str(tmp_target), str(target))
+
+    # Validate it looks like a plugin
+    if not (target / "plugin.yaml").exists() and not (target / "__init__.py").exists():
         console.print(
-            f"[yellow]Warning:[/yellow] {installed_name} doesn't contain plugin.yaml "
-            f"or __init__.py. It may not be a valid Hermes plugin.",
+            f"[yellow]Warning:[/yellow] {plugin_name} doesn't contain plugin.yaml "
+            f"or __init__.py. It may not be a valid Hermes plugin."
         )
 
+    # Copy .example files to their real names (e.g. config.yaml.example → config.yaml)
+    _copy_example_files(target, console)
+
+    # Re-read manifest from installed location (for env var prompting)
+    installed_manifest = _read_manifest(target)
+
+    # Prompt for required environment variables before showing after-install docs
     _prompt_plugin_env_vars(installed_manifest, console)
 
     _display_after_install(target, identifier)
 
+    # Determine the canonical plugin name for enable-list bookkeeping.
+    installed_name = installed_manifest.get("name") or target.name
+
+    # Decide whether to enable: explicit flag > interactive prompt > default off
     should_enable = enable
     if should_enable is None:
+        # Interactive prompt unless stdin isn't a TTY (scripted install).
         if sys.stdin.isatty() and sys.stdout.isatty():
             try:
                 answer = input(
-                    f"  Enable '{installed_name}' now? [y/N]: ",
+                    f"  Enable '{installed_name}' now? [y/N]: "
                 ).strip().lower()
                 should_enable = answer in ("y", "yes")
             except (EOFError, KeyboardInterrupt):
@@ -465,12 +427,12 @@ def cmd_install(
         _save_enabled_set(enabled)
         _save_disabled_set(disabled)
         console.print(
-            f"[green]✓[/green] Plugin [bold]{installed_name}[/bold] enabled.",
+            f"[green]✓[/green] Plugin [bold]{installed_name}[/bold] enabled."
         )
     else:
         console.print(
             f"[dim]Plugin installed but not enabled. "
-            f"Run `hermes plugins enable {installed_name}` to activate.[/dim]",
+            f"Run `hermes plugins enable {installed_name}` to activate.[/dim]"
         )
 
     console.print("[dim]Restart the gateway for the plugin to take effect:[/dim]")
@@ -500,22 +462,36 @@ def cmd_update(name: str) -> None:
 
     console.print(f"[dim]Updating {name}...[/dim]")
 
-    ok, output = _git_pull_plugin_dir(target)
-    if not ok:
-        console.print(f"[red]Error:[/red] {output}")
+    try:
+        result = subprocess.run(
+            ["git", "pull", "--ff-only"],
+            capture_output=True,
+            text=True,
+            timeout=60,
+            cwd=str(target),
+        )
+    except FileNotFoundError:
+        console.print("[red]Error:[/red] git is not installed or not in PATH.")
+        sys.exit(1)
+    except subprocess.TimeoutExpired:
+        console.print("[red]Error:[/red] Git pull timed out after 60 seconds.")
+        sys.exit(1)
+
+    if result.returncode != 0:
+        console.print(f"[red]Error:[/red] Git pull failed:\n{result.stderr.strip()}")
         sys.exit(1)
 
     # Copy any new .example files
     _copy_example_files(target, console)
 
-    out = output.strip()
-    if "Already up to date" in out:
+    output = result.stdout.strip()
+    if "Already up to date" in output:
         console.print(
             f"[green]✓[/green] Plugin [bold]{name}[/bold] is already up to date."
         )
     else:
         console.print(f"[green]✓[/green] Plugin [bold]{name}[/bold] updated.")
-        console.print(f"[dim]{out}[/dim]")
+        console.print(f"[dim]{output}[/dim]")
 
 
 def cmd_remove(name: str) -> None:
@@ -1268,247 +1244,6 @@ def _run_composite_fallback(plugin_names, plugin_labels, plugin_selected,
     print()
 
 
-def dashboard_install_plugin(
-    identifier: str,
-    *,
-    force: bool,
-    enable: bool,
-) -> dict[str, Any]:
-    """Non-interactive install for the web dashboard. Returns a JSON-serializable dict."""
-    warnings: list[str] = []
-    try:
-        git_url = _resolve_git_url(identifier)
-        if git_url.startswith(("http://", "file://")):
-            warnings.append(
-                "Insecure URL scheme; prefer https:// or git@ for production installs.",
-            )
-    except ValueError:
-        pass
-
-    try:
-        target, installed_manifest, installed_name = _install_plugin_core(
-            identifier,
-            force=force,
-        )
-    except PluginOperationError as exc:
-        return {"ok": False, "error": str(exc)}
-
-    missing_env = _missing_requires_env_names(installed_manifest)
-    if enable:
-        en = _get_enabled_set()
-        dis = _get_disabled_set()
-        en.add(installed_name)
-        dis.discard(installed_name)
-        _save_enabled_set(en)
-        _save_disabled_set(dis)
-
-    hint: str | None = None
-    ap = target / "after-install.md"
-    if ap.exists():
-        hint = str(ap)
-
-    return {
-        "ok": True,
-        "plugin_name": installed_name,
-        "warnings": warnings,
-        "missing_env": missing_env,
-        "after_install_path": hint,
-        "enabled": enable,
-    }
-
-
-def _get_plugin_toolset_key(name: str) -> Optional[str]:
-    """Return the toolset key a plugin registers its tools under, or None.
-
-    Queries the live tool registry — the plugin must already be loaded.
-    Falls back to reading ``provides_tools`` from plugin.yaml and looking
-    up the toolset from the registry for the first tool name found.
-    """
-    try:
-        from tools.registry import registry
-    except Exception:
-        return None
-
-    # Check the plugin manager for tools this plugin registered
-    try:
-        from hermes_cli.plugins import discover_plugins, get_plugin_manager
-        discover_plugins()  # idempotent — ensures plugins are loaded
-        manager = get_plugin_manager()
-        for _key, loaded in manager._plugins.items():
-            if loaded.manifest.name == name or _key == name:
-                for tool_name in loaded.tools_registered:
-                    entry = registry.get_entry(tool_name)
-                    if entry and entry.toolset:
-                        return entry.toolset
-                break
-    except Exception:
-        pass
-
-    # Fallback: read provides_tools from manifest on disk and query registry
-    try:
-        from hermes_cli.plugins import get_bundled_plugins_dir
-        for base in (get_bundled_plugins_dir(), _plugins_dir()):
-            if not base.is_dir():
-                continue
-            candidate = base / name
-            if candidate.is_dir():
-                manifest = _read_manifest(candidate)
-                for tool_name in manifest.get("provides_tools") or []:
-                    entry = registry.get_entry(tool_name)
-                    if entry and entry.toolset:
-                        return entry.toolset
-    except Exception:
-        pass
-
-    return None
-
-
-def _toggle_plugin_toolset(name: str, *, enable: bool) -> None:
-    """Add or remove a plugin's toolset from platform_toolsets for all platforms.
-
-    Only acts if the plugin actually provides tools (has a toolset key).
-    """
-    toolset_key = _get_plugin_toolset_key(name)
-    if not toolset_key:
-        return
-
-    from hermes_cli.config import load_config, save_config
-
-    config = load_config()
-    platform_toolsets = config.get("platform_toolsets")
-    if not isinstance(platform_toolsets, dict):
-        platform_toolsets = {}
-        config["platform_toolsets"] = platform_toolsets
-
-    changed = False
-    for platform, ts_list in platform_toolsets.items():
-        if not isinstance(ts_list, list):
-            continue
-        if enable:
-            if toolset_key not in ts_list:
-                ts_list.append(toolset_key)
-                changed = True
-        else:
-            if toolset_key in ts_list:
-                ts_list.remove(toolset_key)
-                changed = True
-
-    # If enabling and no platforms have toolset lists yet, add to "cli" at minimum
-    if enable and not changed and not platform_toolsets:
-        platform_toolsets["cli"] = [toolset_key]
-        changed = True
-
-    if changed:
-        save_config(config)
-
-
-def dashboard_set_agent_plugin_enabled(name: str, *, enabled: bool) -> dict[str, Any]:
-    """Enable or disable a plugin in ``config.yaml`` (runtime allow/deny lists).
-
-    For plugins that provide tools (toolsets), also toggles the toolset in
-    ``platform_toolsets`` so the agent actually sees the tools in sessions.
-    """
-    if not _plugin_exists(name):
-        return {"ok": False, "error": f"Plugin '{name}' is not installed or bundled."}
-
-    en = _get_enabled_set()
-    dis = _get_disabled_set()
-
-    if enabled:
-        if name in en and name not in dis:
-            return {"ok": True, "name": name, "unchanged": True}
-        en.add(name)
-        dis.discard(name)
-        _save_enabled_set(en)
-        _save_disabled_set(dis)
-        _toggle_plugin_toolset(name, enable=True)
-        return {"ok": True, "name": name, "unchanged": False}
-
-    if name not in en and name in dis:
-        return {"ok": True, "name": name, "unchanged": True}
-
-    en.discard(name)
-    dis.add(name)
-    _save_enabled_set(en)
-    _save_disabled_set(dis)
-    _toggle_plugin_toolset(name, enable=False)
-    return {"ok": True, "name": name, "unchanged": False}
-
-
-def _user_installed_plugin_dir(name: str) -> Optional[Path]:
-    """Resolved path under ``~/.hermes/plugins/<name>`` if it exists."""
-    plugins_dir = _plugins_dir()
-    try:
-        target = _sanitize_plugin_name(name, plugins_dir)
-    except ValueError:
-        return None
-    return target if target.is_dir() else None
-
-
-def dashboard_update_user_plugin(name: str) -> dict[str, Any]:
-    """``git pull`` inside ``~/.hermes/plugins/<name>``."""
-    target = _user_installed_plugin_dir(name)
-    if target is None:
-        return {
-            "ok": False,
-            "error": f"Plugin '{name}' was not found under {_plugins_dir()}.",
-        }
-
-    if not (target / ".git").exists():
-        return {
-            "ok": False,
-            "error": f"Plugin '{name}' is not a git checkout; cannot pull updates.",
-        }
-
-    ok, msg = _git_pull_plugin_dir(target)
-    if not ok:
-        return {"ok": False, "error": msg}
-
-    from rich.console import Console
-
-    _copy_example_files(target, Console())
-    unchanged = "Already up to date" in msg
-    return {"ok": True, "name": name, "output": msg, "unchanged": unchanged}
-
-
-def _git_pull_plugin_dir(target: Path) -> tuple[bool, str]:
-    try:
-        result = subprocess.run(
-            ["git", "pull", "--ff-only"],
-            capture_output=True,
-            text=True,
-            timeout=60,
-            cwd=str(target),
-        )
-    except FileNotFoundError:
-        return False, "git is not installed or not in PATH."
-    except subprocess.TimeoutExpired:
-        return False, "Git pull timed out after 60 seconds."
-
-    if result.returncode != 0:
-        err = (result.stderr or "").strip() or result.stdout.strip()
-        return False, err or "git pull failed."
-    return True, result.stdout.strip()
-
-
-def dashboard_remove_user_plugin(name: str) -> dict[str, Any]:
-    """Delete a plugin tree under ``~/.hermes/plugins/`` only."""
-    plugins_dir = _plugins_dir()
-    for n, _ver, _d, src, _path in _discover_all_plugins():
-        if n == name and src == "bundled":
-            return {"ok": False, "error": "Bundled plugins cannot be removed from the dashboard."}
-
-    target = _user_installed_plugin_dir(name)
-    if target is None:
-        return {
-            "ok": False,
-            "error": f"Plugin '{name}' was not found under {plugins_dir}.",
-        }
-
-    shutil.rmtree(target)
-    return {"ok": True, "name": name}
-
-
 def plugins_command(args) -> None:
     """Dispatch hermes plugins subcommands."""
     action = getattr(args, "plugins_action", None)

hermes_cli/runtime_provider.py

@@ -358,20 +358,11 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
         return None
     if not requested_norm.startswith("custom:"):
         try:
-            canonical = auth_mod.resolve_provider(requested_norm)
+            auth_mod.resolve_provider(requested_norm)
         except AuthError:
             pass
         else:
-            # A user-declared ``custom_providers`` entry whose name matches
-            # only an *alias* (``kimi`` → built-in ``kimi-coding``) is the
-            # user's intended target — alias rewriting would otherwise hijack
-            # the request.  We only defer to the built-in when the raw name is
-            # the canonical provider itself (``nous``, ``openrouter``, …) so
-            # accidentally shadowing a canonical provider still resolves to
-            # the built-in. See tests/hermes_cli/test_runtime_provider_resolution.py
-            # ``test_named_custom_provider_does_not_shadow_builtin_provider``.
-            if (canonical or "").strip().lower() == requested_norm:
-                return None
+            return None
 
     config = load_config()
     

hermes_cli/setup.py

@@ -384,7 +384,7 @@ def _print_setup_summary(config: dict, hermes_home):
     else:
         tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY/FIRECRAWL_API_URL, or TAVILY_API_KEY"))
 
-    # Browser tools (local Chromium, Camofox, Browserbase, Browser Use, Firecrawl, or TinyFish)
+    # Browser tools (local Chromium, Camofox, Browserbase, Browser Use, or Firecrawl)
     browser_provider = subscription_features.browser.current_provider
     if subscription_features.browser.managed_by_nous:
         tool_status.append(("Browser Automation (Nous Browser Use)", True, None))
@@ -406,10 +406,6 @@ def _print_setup_summary(config: dict, hermes_home):
             )
         elif browser_provider == "Camofox":
             missing_browser_hint = "CAMOFOX_URL"
-        elif browser_provider == "TinyFish":
-            missing_browser_hint = (
-                "npm install -g agent-browser and set TINYFISH_API_KEY"
-            )
         elif browser_provider == "Local browser":
             missing_browser_hint = "npm install -g agent-browser"
         tool_status.append(
@@ -1194,13 +1190,6 @@ def _setup_tts_provider(config: dict):
                     "Falling back to Edge TTS."
                 )
                 selected = "edge"
-        if selected == "xai":
-            print()
-            voice_id = prompt("xAI voice_id (Enter for 'eve', or paste a custom voice ID)")
-            if voice_id and voice_id.strip():
-                config.setdefault("tts", {}).setdefault("xai", {})["voice_id"] = voice_id.strip()
-                print_success(f"xAI voice_id set to: {voice_id.strip()}")
-
 
     elif selected == "minimax":
         existing = get_env_value("MINIMAX_API_KEY")
@@ -1654,11 +1643,7 @@ def setup_terminal_backend(config: dict):
 def _apply_default_agent_settings(config: dict):
     """Apply recommended defaults for all agent settings without prompting."""
     config.setdefault("agent", {})["max_turns"] = 90
-    # config.yaml is the authoritative source for max_turns; the gateway
-    # bridges it into HERMES_MAX_ITERATIONS at startup. We no longer write
-    # to .env to avoid the dual-source inconsistency that caused the
-    # 60-vs-500 bug (stale .env entry silently shadowing config.yaml).
-    remove_env_value("HERMES_MAX_ITERATIONS")
+    save_env_value("HERMES_MAX_ITERATIONS", "90")
 
     config.setdefault("display", {})["tool_progress"] = "all"
 
@@ -1688,10 +1673,9 @@ def setup_agent_settings(config: dict):
     print()
 
     # ── Max Iterations ──
-    # config.yaml is authoritative; read from there. If a legacy .env
-    # entry is still around (from pre-PR#18413 setups), prefer the
-    # config value so we don't surface a stale number to the user.
-    current_max = str(cfg_get(config, "agent", "max_turns", default=90))
+    current_max = get_env_value("HERMES_MAX_ITERATIONS") or str(
+        cfg_get(config, "agent", "max_turns", default=90)
+    )
     print_info("Maximum tool-calling iterations per conversation.")
     print_info("Higher = more complex tasks, but costs more tokens.")
     print_info(
@@ -1702,13 +1686,9 @@ def setup_agent_settings(config: dict):
     try:
         max_iter = int(max_iter_str)
         if max_iter > 0:
-            # Write to config.yaml (authoritative) only. Also clean up any
-            # stale .env entry from earlier setup runs — the gateway's
-            # bridge in gateway/run.py now unconditionally derives
-            # HERMES_MAX_ITERATIONS from agent.max_turns at startup.
+            save_env_value("HERMES_MAX_ITERATIONS", str(max_iter))
             config.setdefault("agent", {})["max_turns"] = max_iter
             config.pop("max_turns", None)
-            remove_env_value("HERMES_MAX_ITERATIONS")
             print_success(f"Max iterations set to {max_iter}")
     except ValueError:
         print_warning("Invalid number, keeping current value")

hermes_cli/slack_cli.py

@@ -18,7 +18,6 @@ for reinstall when scopes/commands change.
 from __future__ import annotations
 
 import json
-import os
 import sys
 from pathlib import Path
 
@@ -129,7 +128,7 @@ def slack_manifest_command(args) -> int:
 
                 target = Path(get_hermes_home()) / "slack-manifest.json"
             except Exception:
-                target = Path(os.environ.get("HERMES_HOME") or str(Path.home() / ".hermes")) / "slack-manifest.json"
+                target = Path.home() / ".hermes" / "slack-manifest.json"
         else:
             target = Path(write_target).expanduser()
         target.parent.mkdir(parents=True, exist_ok=True)

hermes_cli/status.py

@@ -125,7 +125,6 @@ def show_status(args):
     keys = {
         "OpenRouter": "OPENROUTER_API_KEY",
         "OpenAI": "OPENAI_API_KEY",
-        "NVIDIA": "NVIDIA_API_KEY",
         "Z.AI/GLM": "GLM_API_KEY",
         "Kimi": "KIMI_API_KEY",
         "StepFun Step Plan": "STEPFUN_API_KEY",

hermes_cli/tools_config.py

@@ -379,15 +379,6 @@ TOOL_CATEGORIES = {
                 "browser_provider": "firecrawl",
                 "post_setup": "agent_browser",
             },
-            {
-                "name": "TinyFish",
-                "tag": "Low latency browser with stealth & proxies",
-                "env_vars": [
-                    {"key": "TINYFISH_API_KEY", "prompt": "TinyFish API key", "url": "https://agent.tinyfish.ai/api-keys"},
-                ],
-                "browser_provider": "tinyfish",
-                "post_setup": "agent_browser",
-            },
             {
                 "name": "Camofox",
                 "badge": "free · local",
@@ -1831,7 +1822,7 @@ def _reconfigure_tool(config: dict):
         cat = TOOL_CATEGORIES.get(ts_key)
         reqs = TOOLSET_ENV_REQUIREMENTS.get(ts_key)
         if cat or reqs:
-            if _toolset_has_keys(ts_key, config) or _toolset_enabled_for_reconfigure(ts_key, config):
+            if _toolset_has_keys(ts_key, config):
                 configurable.append((ts_key, ts_label))
 
     if not configurable:
@@ -1857,28 +1848,6 @@ def _reconfigure_tool(config: dict):
     save_config(config)
 
 
-def _toolset_enabled_for_reconfigure(ts_key: str, config: dict) -> bool:
-    """Return True if a configurable toolset is enabled anywhere.
-
-    Reconfigure must include enabled-but-unconfigured categories so users can
-    finish provider/API-key setup without disabling and re-enabling the toolset.
-    """
-    for platform in PLATFORMS:
-        if not _toolset_allowed_for_platform(ts_key, platform):
-            continue
-        try:
-            enabled = _get_platform_tools(
-                config,
-                platform,
-                include_default_mcp_servers=False,
-            )
-        except Exception:
-            continue
-        if ts_key in enabled:
-            return True
-    return False
-
-
 def _configure_tool_category_for_reconfig(ts_key: str, cat: dict, config: dict):
     """Reconfigure a tool category - provider selection + API key update."""
     icon = cat.get("icon", "")

hermes_cli/web_server.py

@@ -345,7 +345,6 @@ _CATEGORY_MERGE: Dict[str, str] = {
     "dashboard": "display",
     "code_execution": "agent",
     "prompt_caching": "agent",
-    "goals": "agent",
     # Only `telegram.reactions` currently lives under telegram — fold it in
     # with the other messaging-platform config (discord) so it isn't an
     # orphan tab of one field.
@@ -2882,25 +2881,6 @@ _VALID_CHANNEL_RE = re.compile(r"^[A-Za-z0-9._-]{1,128}$")
 # loopback so tests don't need to rewrite request scope.
 _LOOPBACK_HOSTS = frozenset({"127.0.0.1", "::1", "localhost", "testclient"})
 
-
-def _is_public_bind() -> bool:
-    """True when bound to all-interfaces (operator used --insecure)."""
-    return getattr(app.state, "bound_host", "") in ("0.0.0.0", "::")
-
-
-def _ws_client_is_allowed(ws: "WebSocket") -> bool:
-    """Check if the WebSocket client IP is acceptable.
-
-    Allows loopback always; allows any IP when bound to all-interfaces
-    (--insecure mode, guarded by session token auth).
-    """
-    if _is_public_bind():
-        return True
-    client_host = ws.client.host if ws.client else ""
-    if not client_host:
-        return True
-    return client_host in _LOOPBACK_HOSTS
-
 # Per-channel subscriber registry used by /api/pub (PTY-side gateway → dashboard)
 # and /api/events (dashboard → browser sidebar).  Keyed by an opaque channel id
 # the chat tab generates on mount; entries auto-evict when the last subscriber
@@ -2991,7 +2971,8 @@ async def pty_ws(ws: WebSocket) -> None:
         await ws.close(code=4401)
         return
 
-    if not _ws_client_is_allowed(ws):
+    client_host = ws.client.host if ws.client else ""
+    if client_host and client_host not in _LOOPBACK_HOSTS:
         await ws.close(code=4403)
         return
 
@@ -3098,7 +3079,8 @@ async def gateway_ws(ws: WebSocket) -> None:
         await ws.close(code=4401)
         return
 
-    if not _ws_client_is_allowed(ws):
+    client_host = ws.client.host if ws.client else ""
+    if client_host and client_host not in _LOOPBACK_HOSTS:
         await ws.close(code=4403)
         return
 
@@ -3130,7 +3112,8 @@ async def pub_ws(ws: WebSocket) -> None:
         await ws.close(code=4401)
         return
 
-    if not _ws_client_is_allowed(ws):
+    client_host = ws.client.host if ws.client else ""
+    if client_host and client_host not in _LOOPBACK_HOSTS:
         await ws.close(code=4403)
         return
 
@@ -3159,7 +3142,8 @@ async def events_ws(ws: WebSocket) -> None:
         await ws.close(code=4401)
         return
 
-    if not _ws_client_is_allowed(ws):
+    client_host = ws.client.host if ws.client else ""
+    if client_host and client_host not in _LOOPBACK_HOSTS:
         await ws.close(code=4403)
         return
 
@@ -3633,16 +3617,12 @@ def _get_dashboard_plugins(force_rescan: bool = False) -> list:
 
 @app.get("/api/dashboard/plugins")
 async def get_dashboard_plugins():
-    """Return discovered dashboard plugins (excludes user-hidden ones)."""
+    """Return discovered dashboard plugins."""
     plugins = _get_dashboard_plugins()
-    # Read user's hidden plugins list from config.
-    config = load_config()
-    hidden: list = cfg_get(config, "dashboard", "hidden_plugins", default=[]) or []
-    # Strip internal fields before sending to frontend and filter out hidden.
+    # Strip internal fields before sending to frontend.
     return [
         {k: v for k, v in p.items() if not k.startswith("_")}
         for p in plugins
-        if p["name"] not in hidden
     ]
 
 
@@ -3653,268 +3633,6 @@ async def rescan_dashboard_plugins():
     return {"ok": True, "count": len(plugins)}
 
 
-class _AgentPluginInstallBody(BaseModel):
-    identifier: str
-    force: bool = False
-    enable: bool = True
-
-
-def _strip_dashboard_manifest(p: Dict[str, Any]) -> Dict[str, Any]:
-    return {k: v for k, v in p.items() if not k.startswith("_")}
-
-
-def _merged_plugins_hub() -> Dict[str, Any]:
-    """Agent discovery + dashboard manifests + optional provider picker metadata."""
-    from hermes_cli.plugins_cmd import (
-        _discover_all_plugins,
-        _get_current_context_engine,
-        _get_current_memory_provider,
-        _discover_context_engines,
-        _discover_memory_providers,
-        _get_disabled_set,
-        _get_enabled_set,
-        _read_manifest as _read_plugin_manifest_at,
-    )
-
-    dashboard_list = _get_dashboard_plugins()
-    dash_by_name = {str(p["name"]): p for p in dashboard_list}
-
-    disabled_set = _get_disabled_set()
-    enabled_set = _get_enabled_set()
-
-    # Read user-hidden plugins from config for the user_hidden field.
-    config = load_config()
-    hidden_plugins: list = cfg_get(config, "dashboard", "hidden_plugins", default=[]) or []
-
-    plugins_root_resolved = (get_hermes_home() / "plugins").resolve()
-    rows: List[Dict[str, Any]] = []
-
-    for name, version, description, source, dir_str in _discover_all_plugins():
-        if name in disabled_set:
-            runtime_status = "disabled"
-        elif name in enabled_set:
-            runtime_status = "enabled"
-        else:
-            runtime_status = "inactive"
-
-        dir_path = Path(dir_str)
-        dm = dash_by_name.get(name)
-        has_dash_manifest = dm is not None or (dir_path / "dashboard" / "manifest.json").exists()
-
-        under_user_tree = False
-        try:
-            dir_path.resolve().relative_to(plugins_root_resolved)
-            under_user_tree = True
-        except ValueError:
-            pass
-
-        can_remove_update = (
-            source in ("user", "git") and under_user_tree and Path(dir_str).is_dir()
-        )
-
-        # Check if this plugin provides tools that require auth
-        auth_required = False
-        auth_command = ""
-        manifest_data = _read_plugin_manifest_at(dir_path)
-        provides_tools = manifest_data.get("provides_tools") or []
-        if provides_tools:
-            try:
-                from tools.registry import registry
-                for tname in provides_tools:
-                    entry = registry.get_entry(tname)
-                    if entry and entry.check_fn and not entry.check_fn():
-                        auth_required = True
-                        auth_command = f"hermes auth {name}"
-                        break
-            except Exception:
-                pass
-
-        rows.append({
-            "name": name,
-            "version": version or "",
-            "description": description or "",
-            "source": source,
-            "runtime_status": runtime_status,
-            "has_dashboard_manifest": has_dash_manifest,
-            "dashboard_manifest": _strip_dashboard_manifest(dm) if dm else None,
-            "path": dir_str,
-            "can_remove": can_remove_update,
-            "can_update_git": can_remove_update and (Path(dir_str) / ".git").exists(),
-            "auth_required": auth_required,
-            "auth_command": auth_command,
-            "user_hidden": name in hidden_plugins,
-        })
-
-    agent_names = {r["name"] for r in rows}
-    orphan_dashboard = [
-        _strip_dashboard_manifest(p)
-        for p in dashboard_list
-        if str(p["name"]) not in agent_names
-    ]
-
-    memory_providers: List[Dict[str, str]] = []
-    try:
-        for n, desc in _discover_memory_providers():
-            memory_providers.append({"name": n, "description": desc})
-    except Exception:
-        memory_providers = []
-
-    context_engines: List[Dict[str, str]] = []
-    try:
-        for n, desc in _discover_context_engines():
-            context_engines.append({"name": n, "description": desc})
-    except Exception:
-        context_engines = []
-
-    return {
-        "plugins": rows,
-        "orphan_dashboard_plugins": orphan_dashboard,
-        "providers": {
-            "memory_provider": _get_current_memory_provider() or "",
-            "memory_options": memory_providers,
-            "context_engine": _get_current_context_engine(),
-            "context_options": context_engines,
-        },
-    }
-
-
-@app.get("/api/dashboard/plugins/hub")
-async def get_plugins_hub(request: Request):
-    """Unified agent plugins + dashboard extension metadata (session protected)."""
-    _require_token(request)
-    try:
-        return _merged_plugins_hub()
-    except Exception as exc:
-        _log.warning("plugins/hub failed: %s", exc)
-        raise HTTPException(status_code=500, detail="Failed to build plugins hub.") from exc
-
-
-@app.post("/api/dashboard/agent-plugins/install")
-async def post_agent_plugin_install(request: Request, body: _AgentPluginInstallBody):
-    _require_token(request)
-    from hermes_cli.plugins_cmd import dashboard_install_plugin
-
-    result = dashboard_install_plugin(
-        body.identifier.strip(),
-        force=body.force,
-        enable=body.enable,
-    )
-    if not result.get("ok"):
-        raise HTTPException(
-            status_code=400,
-            detail=result.get("error") or "Install failed.",
-        )
-    _get_dashboard_plugins(force_rescan=True)
-    # Strip internal paths from the response
-    result.pop("after_install_path", None)
-    return result
-
-
-def _validate_plugin_name(name: str) -> str:
-    """Reject path-traversal attempts in plugin name URL parameters."""
-    if not name or "/" in name or "\\" in name or ".." in name:
-        raise HTTPException(status_code=400, detail="Invalid plugin name.")
-    return name
-
-
-@app.post("/api/dashboard/agent-plugins/{name}/enable")
-async def post_agent_plugin_enable(request: Request, name: str):
-    _require_token(request)
-    name = _validate_plugin_name(name)
-    from hermes_cli.plugins_cmd import dashboard_set_agent_plugin_enabled
-
-    result = dashboard_set_agent_plugin_enabled(name, enabled=True)
-    if not result.get("ok"):
-        raise HTTPException(status_code=400, detail=result.get("error") or "Enable failed.")
-    return result
-
-
-@app.post("/api/dashboard/agent-plugins/{name}/disable")
-async def post_agent_plugin_disable(request: Request, name: str):
-    _require_token(request)
-    name = _validate_plugin_name(name)
-    from hermes_cli.plugins_cmd import dashboard_set_agent_plugin_enabled
-
-    result = dashboard_set_agent_plugin_enabled(name, enabled=False)
-    if not result.get("ok"):
-        raise HTTPException(status_code=400, detail=result.get("error") or "Disable failed.")
-    return result
-
-
-@app.post("/api/dashboard/agent-plugins/{name}/update")
-async def post_agent_plugin_update(request: Request, name: str):
-    _require_token(request)
-    name = _validate_plugin_name(name)
-    from hermes_cli.plugins_cmd import dashboard_update_user_plugin
-
-    result = dashboard_update_user_plugin(name)
-    if not result.get("ok"):
-        raise HTTPException(status_code=400, detail=result.get("error") or "Update failed.")
-    _get_dashboard_plugins(force_rescan=True)
-    return result
-
-
-@app.delete("/api/dashboard/agent-plugins/{name}")
-async def delete_agent_plugin(request: Request, name: str):
-    _require_token(request)
-    name = _validate_plugin_name(name)
-    from hermes_cli.plugins_cmd import dashboard_remove_user_plugin
-
-    result = dashboard_remove_user_plugin(name)
-    if not result.get("ok"):
-        raise HTTPException(status_code=400, detail=result.get("error") or "Remove failed.")
-    _get_dashboard_plugins(force_rescan=True)
-    return result
-
-
-class _PluginProvidersPutBody(BaseModel):
-    memory_provider: Optional[str] = None
-    context_engine: Optional[str] = None
-
-
-@app.put("/api/dashboard/plugin-providers")
-async def put_plugin_providers(request: Request, body: _PluginProvidersPutBody):
-    """Persist memory provider / context engine selection (writes config.yaml)."""
-    _require_token(request)
-    from hermes_cli.plugins_cmd import (
-        _save_context_engine,
-        _save_memory_provider,
-    )
-
-    if body.memory_provider is not None:
-        _save_memory_provider(body.memory_provider)
-    if body.context_engine is not None:
-        _save_context_engine(body.context_engine)
-    return {"ok": True}
-
-
-class _PluginVisibilityBody(BaseModel):
-    hidden: bool
-
-
-@app.post("/api/dashboard/plugins/{name}/visibility")
-async def post_plugin_visibility(request: Request, name: str, body: _PluginVisibilityBody):
-    """Toggle a plugin's sidebar visibility (persists to config.yaml dashboard.hidden_plugins)."""
-    _require_token(request)
-    name = _validate_plugin_name(name)
-
-    config = load_config()
-    if "dashboard" not in config or not isinstance(config.get("dashboard"), dict):
-        config["dashboard"] = {}
-    hidden_list: list = config["dashboard"].get("hidden_plugins") or []
-    if not isinstance(hidden_list, list):
-        hidden_list = []
-
-    if body.hidden and name not in hidden_list:
-        hidden_list.append(name)
-    elif not body.hidden and name in hidden_list:
-        hidden_list.remove(name)
-
-    config["dashboard"]["hidden_plugins"] = hidden_list
-    save_config(config)
-    return {"ok": True, "name": name, "hidden": body.hidden}
-
-
 @app.get("/dashboard-plugins/{plugin_name}/{file_path:path}")
 async def serve_plugin_asset(plugin_name: str, file_path: str):
     """Serve static assets from a dashboard plugin directory.

hermes_constants.py

@@ -8,64 +8,14 @@ import os
 from pathlib import Path
 
 
-_profile_fallback_warned: bool = False
-
-
 def get_hermes_home() -> Path:
     """Return the Hermes home directory (default: ~/.hermes).
 
     Reads HERMES_HOME env var, falls back to ~/.hermes.
     This is the single source of truth — all other copies should import this.
-
-    When ``HERMES_HOME`` is unset but an ``active_profile`` file indicates
-    a non-default profile is active, logs a loud one-shot warning to
-    ``errors.log`` so cross-profile data corruption is diagnosable instead
-    of silent.  Behavior is unchanged otherwise — we still return
-    ``~/.hermes`` — because raising here would brick 30+ module-level
-    callers that import this at load time.  Subprocess spawners are
-    expected to propagate ``HERMES_HOME`` explicitly (see the systemd
-    template in ``hermes_cli/gateway.py`` and the kanban dispatcher in
-    ``hermes_cli/kanban_db.py``).  See https://github.com/NousResearch/hermes-agent/issues/18594.
     """
     val = os.environ.get("HERMES_HOME", "").strip()
-    if val:
-        return Path(val)
-
-    # Guard: if a non-default profile is sticky-active, warn once that
-    # the fallback to the default profile is almost certainly wrong.
-    global _profile_fallback_warned
-    if not _profile_fallback_warned:
-        try:
-            # Inline the default-root resolution from get_default_hermes_root()
-            # to stay import-safe (this function is called from module scope
-            # in 30+ files; we cannot afford to trigger logging setup here).
-            active_path = (Path.home() / ".hermes" / "active_profile")
-            active = active_path.read_text().strip() if active_path.exists() else ""
-        except (UnicodeDecodeError, OSError):
-            active = ""
-        if active and active != "default":
-            _profile_fallback_warned = True
-            # Write directly to stderr.  We intentionally do NOT route this
-            # through ``logging`` because (a) this function is called at
-            # module-import time from 30+ sites, often before logging is
-            # configured, and (b) root-logger propagation would double-emit
-            # on consoles where a StreamHandler is already attached.
-            import sys
-            msg = (
-                f"[HERMES_HOME fallback] HERMES_HOME is unset but active "
-                f"profile is {active!r}. Falling back to ~/.hermes, which "
-                f"is the DEFAULT profile — not {active!r}. Any data this "
-                f"process writes will land in the wrong profile. The "
-                f"subprocess spawner should pass HERMES_HOME explicitly "
-                f"(see issue #18594)."
-            )
-            try:
-                sys.stderr.write(msg + "\n")
-                sys.stderr.flush()
-            except Exception:
-                pass
-
-    return Path.home() / ".hermes"
+    return Path(val) if val else Path.home() / ".hermes"
 
 
 def get_default_hermes_root() -> Path:

hermes_state.py

@@ -514,7 +514,7 @@ class SessionDB:
     # Session lifecycle
     # =========================================================================
 
-    def _insert_session_row(
+    def create_session(
         self,
         session_id: str,
         source: str,
@@ -523,8 +523,8 @@ class SessionDB:
         system_prompt: str = None,
         user_id: str = None,
         parent_session_id: str = None,
-    ) -> None:
-        """Shared INSERT OR IGNORE for session rows."""
+    ) -> str:
+        """Create a new session record. Returns the session_id."""
         def _do(conn):
             conn.execute(
                 """INSERT OR IGNORE INTO sessions (id, source, user_id, model, model_config,
@@ -542,11 +542,8 @@ class SessionDB:
                 ),
             )
         self._execute_write(_do)
-
-    def create_session(self, session_id: str, source: str, **kwargs) -> str:
-        """Create a new session record. Returns the session_id."""
-        self._insert_session_row(session_id, source, **kwargs)
         return session_id
+
     def end_session(self, session_id: str, end_reason: str) -> None:
         """Mark a session as ended.
 
@@ -682,41 +679,21 @@ class SessionDB:
         session_id: str,
         source: str = "unknown",
         model: str = None,
-        **kwargs,
-    ) -> str:
-        """Ensure a session row exists (INSERT OR IGNORE). Accepts optional kwargs."""
-        self._insert_session_row(session_id, source, model=model, **kwargs)
-        return session_id
-
-    def prune_empty_ghost_sessions(self, sessions_dir: "Optional[Path]" = None) -> int:
-        """Remove empty TUI ghost sessions (no messages, no title, >24hr old)."""
-        cutoff = time.time() - 86400  # Only sessions older than 24 hours
+    ) -> None:
+        """Ensure a session row exists, creating it with minimal metadata if absent.
 
+        Used by _flush_messages_to_session_db to recover from a failed
+        create_session() call (e.g. transient SQLite lock at agent startup).
+        INSERT OR IGNORE is safe to call even when the row already exists.
+        """
         def _do(conn):
-            rows = conn.execute("""
-                SELECT id FROM sessions
-                WHERE source = 'tui'
-                  AND title IS NULL
-                  AND ended_at IS NOT NULL
-                  AND started_at < ?
-                  AND NOT EXISTS (
-                      SELECT 1 FROM messages WHERE messages.session_id = sessions.id
-                  )
-            """, (cutoff,)).fetchall()
-            ids = [r[0] if isinstance(r, (tuple, list)) else r["id"] for r in rows]
-            if ids:
-                placeholders = ",".join("?" * len(ids))
-                conn.execute(
-                    f"DELETE FROM sessions WHERE id IN ({placeholders})", ids
-                )
-            return ids
-
-        removed_ids = self._execute_write(_do) or []
-        # Clean up any on-disk session files (belt-and-suspenders)
-        if sessions_dir and removed_ids:
-            for sid in removed_ids:
-                self._remove_session_files(sessions_dir, sid)
-        return len(removed_ids)
+            conn.execute(
+                """INSERT OR IGNORE INTO sessions
+                   (id, source, model, started_at)
+                   VALUES (?, ?, ?, ?)""",
+                (session_id, source, model, time.time()),
+            )
+        self._execute_write(_do)
 
     def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
         """Get a session by ID."""
@@ -956,7 +933,6 @@ class SessionDB:
         offset: int = 0,
         include_children: bool = False,
         project_compression_tips: bool = True,
-        order_by_last_active: bool = False,
     ) -> List[Dict[str, Any]]:
         """List sessions with preview (first user message) and last active timestamp.
 
@@ -976,14 +952,6 @@ class SessionDB:
         compressed continuations from being invisible to users while keeping
         delegate subagents and branches hidden. Pass ``False`` to return the
         raw root rows (useful for admin/debug UIs).
-
-        Pass ``order_by_last_active=True`` to sort by most-recent activity
-        instead of original conversation start time. For compression chains,
-        the "most-recent activity" is taken from the live tip (not the root),
-        so an old conversation that was compressed and continued recently
-        surfaces in the correct slot. Ordering is computed at SQL level via
-        a recursive CTE that walks compression-continuation edges, so LIMIT
-        and OFFSET still apply efficiently.
         """
         where_clauses = []
         params = []
@@ -1011,80 +979,25 @@ class SessionDB:
             params.extend(exclude_sources)
 
         where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
-        if order_by_last_active:
-            # Compute effective_last_active by walking each surfaced session's
-            # compression-continuation chain forward in SQL and taking the MAX
-            # timestamp across the chain. This lets us ORDER BY + LIMIT at SQL
-            # level instead of fetching every row and sorting in Python, while
-            # still surfacing old compression roots whose live tip is fresh.
-            #
-            # The CTE seeds from rows the outer WHERE admits (roots + branch
-            # children), then recursively joins forward through
-            # compression-continuation edges using the same criteria as
-            # get_compression_tip (parent.end_reason='compression' AND
-            # child.started_at >= parent.ended_at).
-            query = f"""
-                WITH RECURSIVE chain(root_id, cur_id) AS (
-                    SELECT s.id, s.id FROM sessions s {where_sql}
-                    UNION ALL
-                    SELECT c.root_id, child.id
-                    FROM chain c
-                    JOIN sessions parent ON parent.id = c.cur_id
-                    JOIN sessions child ON child.parent_session_id = c.cur_id
-                    WHERE parent.end_reason = 'compression'
-                      AND child.started_at >= parent.ended_at
-                ),
-                chain_max AS (
-                    SELECT
-                        root_id,
-                        MAX(COALESCE(
-                            (SELECT MAX(m.timestamp) FROM messages m WHERE m.session_id = cur_id),
-                            (SELECT started_at FROM sessions ss WHERE ss.id = cur_id)
-                        )) AS effective_last_active
-                    FROM chain
-                    GROUP BY root_id
-                )
-                SELECT s.*,
-                    COALESCE(
-                        (SELECT SUBSTR(REPLACE(REPLACE(m.content, X'0A', ' '), X'0D', ' '), 1, 63)
-                         FROM messages m
-                         WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
-                         ORDER BY m.timestamp, m.id LIMIT 1),
-                        ''
-                    ) AS _preview_raw,
-                    COALESCE(
-                        (SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
-                        s.started_at
-                    ) AS last_active,
-                    COALESCE(cm.effective_last_active, s.started_at) AS _effective_last_active
-                FROM sessions s
-                LEFT JOIN chain_max cm ON cm.root_id = s.id
-                {where_sql}
-                ORDER BY _effective_last_active DESC, s.started_at DESC, s.id DESC
-                LIMIT ? OFFSET ?
-            """
-            # WHERE params apply twice (CTE seed + outer select).
-            params = params + params + [limit, offset]
-        else:
-            query = f"""
-                SELECT s.*,
-                    COALESCE(
-                        (SELECT SUBSTR(REPLACE(REPLACE(m.content, X'0A', ' '), X'0D', ' '), 1, 63)
-                         FROM messages m
-                         WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
-                         ORDER BY m.timestamp, m.id LIMIT 1),
-                        ''
-                    ) AS _preview_raw,
-                    COALESCE(
-                        (SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
-                        s.started_at
-                    ) AS last_active
-                FROM sessions s
-                {where_sql}
-                ORDER BY s.started_at DESC
-                LIMIT ? OFFSET ?
-            """
-            params.extend([limit, offset])
+        query = f"""
+            SELECT s.*,
+                COALESCE(
+                    (SELECT SUBSTR(REPLACE(REPLACE(m.content, X'0A', ' '), X'0D', ' '), 1, 63)
+                     FROM messages m
+                     WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
+                     ORDER BY m.timestamp, m.id LIMIT 1),
+                    ''
+                ) AS _preview_raw,
+                COALESCE(
+                    (SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
+                    s.started_at
+                ) AS last_active
+            FROM sessions s
+            {where_sql}
+            ORDER BY s.started_at DESC
+            LIMIT ? OFFSET ?
+        """
+        params.extend([limit, offset])
         with self._lock:
             cursor = self._conn.execute(query, params)
             rows = cursor.fetchall()
@@ -1098,8 +1011,6 @@ class SessionDB:
                 s["preview"] = text + ("..." if len(raw) > 60 else "")
             else:
                 s["preview"] = ""
-            # Drop the internal ordering column so callers see a clean dict.
-            s.pop("_effective_last_active", None)
             sessions.append(s)
 
         # Project compression roots forward to their tips. Each row whose
@@ -1177,48 +1088,6 @@ class SessionDB:
     # Message storage
     # =========================================================================
 
-    # Sentinel prefix used to distinguish JSON-encoded structured content
-    # (multimodal messages: lists of parts like text + image_url) from plain
-    # string content. The NUL byte is not legal in normal text, so this
-    # cannot collide with real user content.
-    _CONTENT_JSON_PREFIX = "\x00json:"
-
-    @classmethod
-    def _encode_content(cls, content: Any) -> Any:
-        """Serialize structured (list/dict) message content for sqlite.
-
-        sqlite3 can only bind ``str``, ``bytes``, ``int``, ``float``, and ``None``
-        to query parameters. Multimodal messages have ``content`` as a list of
-        parts (``[{"type": "text", ...}, {"type": "image_url", ...}]``), which
-        raises ``ProgrammingError: Error binding parameter N: type 'list' is
-        not supported`` when bound directly.
-
-        Returns the value unchanged when it's already a safe scalar, or a
-        sentinel-prefixed JSON string for lists/dicts. Paired with
-        :meth:`_decode_content` on read.
-        """
-        if content is None or isinstance(content, (str, bytes, int, float)):
-            return content
-        try:
-            return cls._CONTENT_JSON_PREFIX + json.dumps(content)
-        except (TypeError, ValueError):
-            # Last-resort fallback: stringify so persistence never fails.
-            return str(content)
-
-    @classmethod
-    def _decode_content(cls, content: Any) -> Any:
-        """Reverse :meth:`_encode_content`; returns scalars unchanged."""
-        if isinstance(content, str) and content.startswith(cls._CONTENT_JSON_PREFIX):
-            try:
-                return json.loads(content[len(cls._CONTENT_JSON_PREFIX):])
-            except (json.JSONDecodeError, TypeError):
-                logger.warning(
-                    "Failed to decode JSON-encoded message content; "
-                    "returning raw string"
-                )
-                return content
-        return content
-
     def append_message(
         self,
         session_id: str,
@@ -1255,9 +1124,6 @@ class SessionDB:
             if codex_message_items else None
         )
         tool_calls_json = json.dumps(tool_calls) if tool_calls else None
-        # Multimodal content (list of parts) must be JSON-encoded: sqlite3
-        # cannot bind list/dict parameters directly.
-        stored_content = self._encode_content(content)
 
         # Pre-compute tool call count
         num_tool_calls = 0
@@ -1274,7 +1140,7 @@ class SessionDB:
                 (
                     session_id,
                     role,
-                    stored_content,
+                    content,
                     tool_call_id,
                     tool_calls_json,
                     tool_name,
@@ -1357,7 +1223,7 @@ class SessionDB:
                     (
                         session_id,
                         role,
-                        self._encode_content(msg.get("content")),
+                        msg.get("content"),
                         msg.get("tool_call_id"),
                         tool_calls_json,
                         msg.get("tool_name"),
@@ -1396,8 +1262,6 @@ class SessionDB:
         result = []
         for row in rows:
             msg = dict(row)
-            if "content" in msg:
-                msg["content"] = self._decode_content(msg["content"])
             if msg.get("tool_calls"):
                 try:
                     msg["tool_calls"] = json.loads(msg["tool_calls"])
@@ -1487,15 +1351,15 @@ class SessionDB:
             placeholders = ",".join("?" for _ in session_ids)
             rows = self._conn.execute(
                 "SELECT role, content, tool_call_id, tool_calls, tool_name, "
-                "finish_reason, reasoning, reasoning_content, reasoning_details, "
-                "codex_reasoning_items, codex_message_items "
+                "reasoning, reasoning_content, reasoning_details, codex_reasoning_items, "
+                "codex_message_items "
                 f"FROM messages WHERE session_id IN ({placeholders}) ORDER BY timestamp, id",
                 tuple(session_ids),
             ).fetchall()
 
         messages = []
         for row in rows:
-            content = self._decode_content(row["content"])
+            content = row["content"]
             if row["role"] in {"user", "assistant"} and isinstance(content, str):
                 content = sanitize_context(content).strip()
             msg = {"role": row["role"], "content": content}
@@ -1513,8 +1377,6 @@ class SessionDB:
             # that replay reasoning (OpenRouter, OpenAI, Nous) receive
             # coherent multi-turn reasoning context.
             if row["role"] == "assistant":
-                if row["finish_reason"]:
-                    msg["finish_reason"] = row["finish_reason"]
                 if row["reasoning"]:
                     msg["reasoning"] = row["reasoning"]
                 if row["reasoning_content"] is not None:
@@ -1882,26 +1744,10 @@ class SessionDB:
                            )""",
                         (match["id"], match["id"]),
                     )
-                    context_msgs = []
-                    for r in ctx_cursor.fetchall():
-                        raw = r["content"]
-                        decoded = self._decode_content(raw)
-                        # Multimodal context: render a compact text-only
-                        # summary for search previews.
-                        if isinstance(decoded, list):
-                            text_parts = [
-                                p.get("text", "") for p in decoded
-                                if isinstance(p, dict) and p.get("type") == "text"
-                            ]
-                            text = " ".join(t for t in text_parts if t).strip()
-                            preview = text or "[multimodal content]"
-                        elif isinstance(decoded, str):
-                            preview = decoded
-                        else:
-                            preview = ""
-                        context_msgs.append(
-                            {"role": r["role"], "content": preview[:200]}
-                        )
+                    context_msgs = [
+                        {"role": r["role"], "content": (r["content"] or "")[:200]}
+                        for r in ctx_cursor.fetchall()
+                    ]
                 match["context"] = context_msgs
             except Exception:
                 match["context"] = []

model_tools.py

@@ -356,17 +356,12 @@ def _compute_tool_definitions(
             else:
                 if not quiet_mode:
                     print(f"⚠️  Unknown toolset: {toolset_name}")
-    else:
-        # Default: start with everything
+
+    elif disabled_toolsets:
         from toolsets import get_all_toolsets
         for ts_name in get_all_toolsets():
             tools_to_include.update(resolve_toolset(ts_name))
 
-    # Always apply disabled toolsets as a subtraction step at the end.
-    # This ensures that even if a composite toolset (like hermes-cli)
-    # is enabled, any tools belonging to a disabled toolset are strictly
-    # stripped out. See issue #17309.
-    if disabled_toolsets:
         for toolset_name in disabled_toolsets:
             if validate_toolset(toolset_name):
                 resolved = resolve_toolset(toolset_name)
@@ -381,6 +376,10 @@ def _compute_tool_definitions(
             else:
                 if not quiet_mode:
                     print(f"⚠️  Unknown toolset: {toolset_name}")
+    else:
+        from toolsets import get_all_toolsets
+        for ts_name in get_all_toolsets():
+            tools_to_include.update(resolve_toolset(ts_name))
 
     # Plugin-registered tools are now resolved through the normal toolset
     # path — validate_toolset() / resolve_toolset() / get_all_toolsets()

nix/tui.nix

@@ -4,7 +4,7 @@ let
   src = ../ui-tui;
   npmDeps = pkgs.fetchNpmDeps {
     inherit src;
-    hash = "sha256-a/HGI9OgVcTnZrMXA7xFMGnFoVxyHe95fulVz+WNYB0=";
+    hash = "sha256-Chz+NW9NXqboXHOa6PKwf5bhAkkcFtKNhvKWwg2XSPc=";
   };
 
   npm = hermesNpmLib.mkNpmPassthru { folder = "ui-tui"; attr = "tui"; pname = "hermes-tui"; };

optional-skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py

@@ -2960,7 +2960,7 @@ class Migrator:
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Migrate OpenClaw user state into Hermes Agent.")
     parser.add_argument("--source", default=str(Path.home() / ".openclaw"), help="OpenClaw home directory")
-    parser.add_argument("--target", default=os.environ.get("HERMES_HOME") or str(Path.home() / ".hermes"), help="Hermes home directory")
+    parser.add_argument("--target", default=str(Path.home() / ".hermes"), help="Hermes home directory")
     parser.add_argument(
         "--workspace-target",
         help="Optional workspace root where the workspace instructions file should be copied",

optional-skills/productivity/here-now/SKILL.md

@@ -1,217 +0,0 @@
----
-name: here.now
-description: Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.
-version: 1.15.3
-author: here.now
-license: MIT
-prerequisites:
-  commands: [curl, file, jq]
-platforms: [macos, linux]
-metadata:
-  hermes:
-    tags: [here.now, herenow, publish, deploy, hosting, static-site, web, share, URL, drive, storage]
-    homepage: https://here.now
-    requires_toolsets: [terminal]
----
-
-# here.now
-
-here.now lets agents publish websites and store private files in cloud Drives.
-
-Use here.now for two jobs:
-
-- **Sites**: publish websites and files at `{slug}.here.now`.
-- **Drives**: store private agent files in cloud folders.
-
-## Current docs
-
-**Before answering questions about here.now capabilities, features, or workflows, read the current docs:**
-
-→ **https://here.now/docs**
-
-Read the docs:
-
-- at the first here.now-related interaction in a conversation
-- any time the user asks how to do something
-- any time the user asks what is possible, supported, or recommended
-- before telling the user a feature is unsupported
-
-Topics that require current docs (do not rely on local skill text alone):
-
-- Drives and Drive sharing
-- custom domains
-- payments and payment gating
-- forking
-- proxy routes and service variables
-- handles and links
-- limits and quotas
-- SPA routing
-- error handling and remediation
-- feature availability
-
-**If docs and live API behavior disagree, trust the live API behavior.**
-
-If the docs fetch fails or times out, continue with the local skill and live API/script output. Prefer live API behavior for active operations.
-
-## Requirements
-
-- Required binaries: `curl`, `file`, `jq`
-- Optional environment variable: `$HERENOW_API_KEY`
-- Optional Drive token variable: `$HERENOW_DRIVE_TOKEN`
-- Optional credentials file: `~/.herenow/credentials`
-- Skill helper paths:
-  - `${HERMES_SKILL_DIR}/scripts/publish.sh` for publishing sites
-  - `${HERMES_SKILL_DIR}/scripts/drive.sh` for private Drive storage
-
-## Create a site
-
-```bash
-PUBLISH="${HERMES_SKILL_DIR}/scripts/publish.sh"
-bash "$PUBLISH" {file-or-dir} --client hermes
-```
-
-Outputs the live URL (e.g. `https://bright-canvas-a7k2.here.now/`).
-
-Under the hood this is a three-step flow: create/update -> upload files -> finalize. A site is not live until finalize succeeds.
-
-Without an API key this creates an **anonymous site** that expires in 24 hours.
-With a saved API key, the site is permanent.
-
-**File structure:** For HTML sites, place `index.html` at the root of the directory you publish, not inside a subdirectory. The directory's contents become the site root. For example, publish `my-site/` where `my-site/index.html` exists — don't publish a parent folder that contains `my-site/`.
-
-You can also publish raw files without any HTML. Single files get a rich auto-viewer (images, PDF, video, audio). Multiple files get an auto-generated directory listing with folder navigation and an image gallery.
-
-## Update an existing site
-
-```bash
-PUBLISH="${HERMES_SKILL_DIR}/scripts/publish.sh"
-bash "$PUBLISH" {file-or-dir} --slug {slug} --client hermes
-```
-
-The script auto-loads the `claimToken` from `.herenow/state.json` when updating anonymous sites. Pass `--claim-token {token}` to override.
-
-Authenticated updates require a saved API key.
-
-## Use a Drive
-
-Use a Drive when the user wants private cloud storage for agent files: documents, context, memory, plans, assets, media, research, code, and anything else that should persist without being published as a website.
-
-Every signed-in account has a default Drive named `My Drive`.
-
-```bash
-DRIVE="${HERMES_SKILL_DIR}/scripts/drive.sh"
-bash "$DRIVE" default
-bash "$DRIVE" ls "My Drive"
-bash "$DRIVE" put "My Drive" notes/today.md --from ./notes/today.md
-bash "$DRIVE" cat "My Drive" notes/today.md
-bash "$DRIVE" share "My Drive" --perms write --prefix notes/ --ttl 7d
-```
-
-Use scoped Drive tokens for agent-to-agent handoff. If you receive a `herenow_drive` share block, use its `token` as `Authorization: Bearer <token>` against `api_base`, respect `pathPrefix` when present, and preserve ETags on writes. A `pathPrefix` of `null` means full-Drive access. If the skill is available, prefer `drive.sh`; otherwise call the listed API operations directly.
-
-## API key storage
-
-The publish script reads the API key from these sources (first match wins):
-
-1. `--api-key {key}` flag (CI/scripting only — avoid in interactive use)
-2. `$HERENOW_API_KEY` environment variable
-3. `~/.herenow/credentials` file (recommended for agents)
-
-To store a key, write it to the credentials file:
-
-```bash
-mkdir -p ~/.herenow && echo "{API_KEY}" > ~/.herenow/credentials && chmod 600 ~/.herenow/credentials
-```
-
-**IMPORTANT**: After receiving an API key, save it immediately — run the command above yourself. Do not ask the user to run it manually. Avoid passing the key via CLI flags (e.g. `--api-key`) in interactive sessions; the credentials file is the preferred storage method.
-
-Never commit credentials or local state files (`~/.herenow/credentials`, `.herenow/state.json`) to source control.
-
-## Getting an API key
-
-To upgrade from anonymous (24h) to permanent sites:
-
-1. Ask the user for their email address.
-2. Request a one-time sign-in code:
-
-```bash
-curl -sS https://here.now/api/auth/agent/request-code \
-  -H "content-type: application/json" \
-  -d '{"email": "user@example.com"}'
-```
-
-3. Tell the user: "Check your inbox for a sign-in code from here.now and paste it here."
-4. Verify the code and get the API key:
-
-```bash
-curl -sS https://here.now/api/auth/agent/verify-code \
-  -H "content-type: application/json" \
-  -d '{"email":"user@example.com","code":"ABCD-2345"}'
-```
-
-5. Save the returned `apiKey` yourself (do not ask the user to do this):
-
-```bash
-mkdir -p ~/.herenow && echo "{API_KEY}" > ~/.herenow/credentials && chmod 600 ~/.herenow/credentials
-```
-
-## State file
-
-After every site create/update, the script writes to `.herenow/state.json` in the working directory:
-
-```json
-{
-  "publishes": {
-    "bright-canvas-a7k2": {
-      "siteUrl": "https://bright-canvas-a7k2.here.now/",
-      "claimToken": "abc123",
-      "claimUrl": "https://here.now/claim?slug=bright-canvas-a7k2&token=abc123",
-      "expiresAt": "2026-02-18T01:00:00.000Z"
-    }
-  }
-}
-```
-
-Before creating or updating sites, you may check this file to find prior slugs.
-Treat `.herenow/state.json` as internal cache only.
-Never present this local file path as a URL, and never use it as source of truth for auth mode, expiry, or claim URL.
-
-## What to tell the user
-
-For published sites:
-
-- Always share the `siteUrl` from the current script run.
-- Read and follow `publish_result.*` lines from script stderr to determine auth mode.
-- When `publish_result.auth_mode=authenticated`: tell the user the site is **permanent** and saved to their account. No claim URL is needed.
-- When `publish_result.auth_mode=anonymous`: tell the user the site **expires in 24 hours**. Share the claim URL (if `publish_result.claim_url` is non-empty and starts with `https://`) so they can keep it permanently. Warn that claim tokens are only returned once and cannot be recovered.
-- Never tell the user to inspect `.herenow/state.json` for claim URLs or auth status.
-
-For Drives:
-
-- Do not describe Drive files as public URLs.
-- Tell the user Drive contents are private unless shared with a scoped token.
-- When sharing access with another agent, prefer a scoped token with a narrow `pathPrefix` and short TTL.
-
-## publish.sh options
-
-| Flag                   | Description                                  |
-| ---------------------- | -------------------------------------------- |
-| `--slug {slug}`        | Update an existing site instead of creating |
-| `--claim-token {token}`| Override claim token for anonymous updates    |
-| `--title {text}`       | Viewer title (non-HTML sites)             |
-| `--description {text}` | Viewer description                            |
-| `--ttl {seconds}`      | Set expiry (authenticated only)               |
-| `--client {name}`      | Agent name for attribution (e.g. `hermes`)    |
-| `--base-url {url}`     | API base URL (default: `https://here.now`)    |
-| `--allow-nonherenow-base-url` | Allow sending auth to non-default `--base-url` |
-| `--api-key {key}`      | API key override (prefer credentials file)    |
-| `--spa`                | Enable SPA routing (serve index.html for unknown paths) |
-| `--forkable`           | Allow others to fork this site                           |
-
-## Beyond publish.sh
-
-For Drive operations, use `drive.sh` or the Drive API. For broader account and site management — delete, metadata, passwords, payments, domains, handles, links, variables, proxy routes, forking, duplication, and more — see the current docs:
-
-→ **https://here.now/docs**
-
-Full docs: https://here.now/docs

optional-skills/productivity/here-now/scripts/drive.sh

@@ -1,406 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-BASE_URL="https://here.now"
-CREDENTIALS_FILE="$HOME/.herenow/credentials"
-API_KEY="${HERENOW_API_KEY:-}"
-DRIVE_TOKEN="${HERENOW_DRIVE_TOKEN:-}"
-ALLOW_NON_HERENOW_BASE_URL=0
-MAX_FILE_BYTES=$((500 * 1024 * 1024))
-
-usage() {
-  cat <<'USAGE'
-Usage: drive.sh [global options] <command> [args]
-
-Global options:
-  --api-key <key>        Account API key (or $HERENOW_API_KEY / ~/.herenow/credentials)
-  --token <drv_live_...> Drive token (or $HERENOW_DRIVE_TOKEN)
-  --base-url <url>       API base (default: https://here.now)
-  --allow-nonherenow-base-url
-
-Commands:
-  create [name] [--default]
-  default
-  ls
-  ls <drive> [prefix]
-  cat <drive> <path>
-  put <drive> <path> --from <local-file>
-  import <drive> <prefix> --from <local-folder> [--dry-run]
-  export <drive> <prefix> --to <local-folder> [--dry-run]
-  rm <drive> <path> [--recursive --confirm <path>]
-  share <drive> --perms read|write [--prefix notes/] [--ttl 30d] [--label text] [--manage-tokens]
-  tokens <drive>
-  revoke <drive> <tokenId>
-  delete <drive> --confirm "<drive name>"
-USAGE
-  exit 1
-}
-
-die() { echo "error: $1" >&2; exit 1; }
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-SKILL_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
-BUNDLED_JQ="${SKILL_DIR}/bin/jq"
-
-if [[ -x "$BUNDLED_JQ" ]]; then
-  JQ_BIN="$BUNDLED_JQ"
-elif command -v jq >/dev/null 2>&1; then
-  JQ_BIN="$(command -v jq)"
-else
-  die "requires jq"
-fi
-
-for cmd in curl file; do
-  command -v "$cmd" >/dev/null 2>&1 || die "requires $cmd"
-done
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --api-key) API_KEY="$2"; shift 2 ;;
-    --token) DRIVE_TOKEN="$2"; shift 2 ;;
-    --base-url) BASE_URL="$2"; shift 2 ;;
-    --allow-nonherenow-base-url) ALLOW_NON_HERENOW_BASE_URL=1; shift ;;
-    --help|-h) usage ;;
-    --*) die "unknown global option: $1" ;;
-    *) break ;;
-  esac
-done
-
-CMD="${1:-}"
-[[ -n "$CMD" ]] || usage
-shift || true
-
-if [[ -z "$API_KEY" && -z "$DRIVE_TOKEN" && -f "$CREDENTIALS_FILE" ]]; then
-  API_KEY=$(tr -d '[:space:]' < "$CREDENTIALS_FILE")
-fi
-
-BASE_URL="${BASE_URL%/}"
-if [[ "$BASE_URL" != "https://here.now" && "$ALLOW_NON_HERENOW_BASE_URL" -ne 1 ]]; then
-  if [[ -n "$API_KEY" || -n "$DRIVE_TOKEN" ]]; then
-    die "refusing to send credentials to non-default base URL; pass --allow-nonherenow-base-url to override"
-  fi
-fi
-
-auth_header=()
-if [[ -n "$DRIVE_TOKEN" ]]; then
-  auth_header=(-H "authorization: Bearer $DRIVE_TOKEN")
-elif [[ -n "$API_KEY" ]]; then
-  auth_header=(-H "authorization: Bearer $API_KEY")
-else
-  die "missing credentials; set HERENOW_API_KEY, HERENOW_DRIVE_TOKEN, or ~/.herenow/credentials"
-fi
-
-compute_sha256() {
-  local f="$1"
-  if command -v sha256sum >/dev/null 2>&1; then
-    sha256sum "$f" | cut -d' ' -f1
-  else
-    shasum -a 256 "$f" | cut -d' ' -f1
-  fi
-}
-
-guess_content_type() {
-  local f="$1"
-  case "${f##*.}" in
-    html|htm) echo "text/html; charset=utf-8" ;;
-    css) echo "text/css; charset=utf-8" ;;
-    js|mjs) echo "text/javascript; charset=utf-8" ;;
-    json) echo "application/json; charset=utf-8" ;;
-    md|txt) echo "text/plain; charset=utf-8" ;;
-    svg) echo "image/svg+xml" ;;
-    png) echo "image/png" ;;
-    jpg|jpeg) echo "image/jpeg" ;;
-    gif) echo "image/gif" ;;
-    webp) echo "image/webp" ;;
-    pdf) echo "application/pdf" ;;
-    *) file --brief --mime-type "$f" 2>/dev/null || echo "application/octet-stream" ;;
-  esac
-}
-
-api_json() {
-  local method="$1"; shift
-  local url="$1"; shift
-  local body="${1:-}"
-  local tmp
-  tmp=$(mktemp)
-  local code
-  if [[ -n "$body" ]]; then
-    code=$(curl -sS -o "$tmp" -w "%{http_code}" -X "$method" "$url" "${auth_header[@]}" -H "content-type: application/json" -d "$body")
-  else
-    code=$(curl -sS -o "$tmp" -w "%{http_code}" -X "$method" "$url" "${auth_header[@]}")
-  fi
-  if [[ "$code" -lt 200 || "$code" -ge 300 ]]; then
-    local err
-    err=$("$JQ_BIN" -r '.error // empty' "$tmp" 2>/dev/null || true)
-    [[ -n "$err" ]] || err="$(cat "$tmp")"
-    rm -f "$tmp"
-    die "HTTP $code: $err"
-  fi
-  cat "$tmp"
-  rm -f "$tmp"
-}
-
-urlenc() {
-  "$JQ_BIN" -nr --arg v "$1" '$v|@uri'
-}
-
-urlenc_path() {
-  local path="$1"
-  local out=""
-  local part
-  IFS='/' read -r -a parts <<< "$path"
-  for part in "${parts[@]}"; do
-    [[ -n "$out" ]] && out="$out/"
-    out="$out$(urlenc "$part")"
-  done
-  echo "$out"
-}
-
-resolve_drive() {
-  local name="$1"
-  if [[ "$name" == drv_* ]]; then
-    echo "$name"
-    return
-  fi
-  if [[ -n "$DRIVE_TOKEN" ]]; then
-    die "drive tokens must reference drives by drv_ id; use account credentials to resolve drive names"
-  fi
-  if [[ "$name" == "default" || "$name" == "my-drive" || "$name" == "My Drive" ]]; then
-    api_json GET "$BASE_URL/api/v1/drives/default" | "$JQ_BIN" -r '.drive.id'
-    return
-  fi
-  local rows count
-  rows=$(api_json GET "$BASE_URL/api/v1/drives" | "$JQ_BIN" --arg n "$name" '[.drives[] | select(.name == $n)]')
-  count=$(echo "$rows" | "$JQ_BIN" 'length')
-  [[ "$count" -eq 1 ]] || die "drive name '$name' matched $count drives; use a drv_ id"
-  echo "$rows" | "$JQ_BIN" -r '.[0].id'
-}
-
-drive_head() {
-  local id="$1"
-  api_json GET "$BASE_URL/api/v1/drives/$id" | "$JQ_BIN" -r '.drive.headVersionId // .headVersionId // empty'
-}
-
-file_meta() {
-  local id="$1"
-  local path="$2"
-  local prefix
-  prefix=$(urlenc "$path")
-  api_json GET "$BASE_URL/api/v1/drives/$id/files?prefix=$prefix&limit=200" | "$JQ_BIN" -c --arg p "$path" '.files[]? | select(.path == $p)' | head -n 1
-}
-
-put_file() {
-  local drive="$1"; shift
-  local path="$1"; shift
-  local local_file=""
-  while [[ $# -gt 0 ]]; do
-    case "$1" in
-      --from) local_file="$2"; shift 2 ;;
-      *) die "unexpected put argument: $1" ;;
-    esac
-  done
-  [[ -f "$local_file" ]] || die "--from must be a file"
-  local id sz ct sha meta body upload upload_url upload_id http_code
-  id=$(resolve_drive "$drive")
-  sz=$(wc -c < "$local_file" | tr -d ' ')
-  [[ "$sz" -le "$MAX_FILE_BYTES" ]] || die "$path exceeds the $MAX_FILE_BYTES byte Drive file limit"
-  ct=$(guess_content_type "$local_file")
-  sha=$(compute_sha256 "$local_file")
-  meta=$(file_meta "$id" "$path" || true)
-  body=$("$JQ_BIN" -n --arg p "$path" --argjson s "$sz" --arg c "$ct" --arg sha "$sha" \
-    '{path:$p,size:$s,contentType:$c,sha256:$sha}')
-  if [[ -n "$meta" ]]; then
-    etag=$(echo "$meta" | "$JQ_BIN" -r '.etag')
-    body=$(echo "$body" | "$JQ_BIN" --arg e "$etag" '.ifMatch = $e')
-  else
-    body=$(echo "$body" | "$JQ_BIN" '.ifNoneMatch = "*"')
-  fi
-  upload=$(api_json POST "$BASE_URL/api/v1/drives/$id/files/uploads" "$body")
-  upload_url=$(echo "$upload" | "$JQ_BIN" -r '.uploadUrl')
-  upload_id=$(echo "$upload" | "$JQ_BIN" -r '.uploadId')
-  http_code=$(curl -sS -o /dev/null -w "%{http_code}" -X PUT "$upload_url" -H "Content-Type: $ct" --data-binary "@$local_file")
-  [[ "$http_code" -ge 200 && "$http_code" -lt 300 ]] || die "upload failed for $path (HTTP $http_code)"
-  api_json POST "$BASE_URL/api/v1/drives/$id/files/finalize" "$("$JQ_BIN" -n --arg u "$upload_id" '{uploadId:$u}')" | "$JQ_BIN" .
-}
-
-case "$CMD" in
-  create)
-    name=""
-    is_default="false"
-    while [[ $# -gt 0 ]]; do
-      case "$1" in
-        --default) is_default="true"; shift ;;
-        *) [[ -z "$name" ]] && name="$1" || die "unexpected argument: $1"; shift ;;
-      esac
-    done
-    body=$("$JQ_BIN" -n --arg n "$name" --argjson d "$is_default" '{isDefault:$d} + (if $n == "" then {} else {name:$n} end)')
-    api_json POST "$BASE_URL/api/v1/drives" "$body" | "$JQ_BIN" .
-    ;;
-  default)
-    api_json GET "$BASE_URL/api/v1/drives/default" | "$JQ_BIN" .
-    ;;
-  ls)
-    if [[ $# -eq 0 ]]; then
-      [[ -z "$DRIVE_TOKEN" ]] || die "drive tokens cannot list drives; pass a drv_ id"
-      api_json GET "$BASE_URL/api/v1/drives" | "$JQ_BIN" .
-    else
-      id=$(resolve_drive "$1")
-      prefix="${2:-}"
-      api_json GET "$BASE_URL/api/v1/drives/$id/files?prefix=$(urlenc "$prefix")" | "$JQ_BIN" .
-    fi
-    ;;
-  cat)
-    [[ $# -eq 2 ]] || die "usage: drive.sh cat <drive> <path>"
-    id=$(resolve_drive "$1")
-    curl -fsS "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$2")" "${auth_header[@]}"
-    ;;
-  put)
-    [[ $# -ge 2 ]] || die "usage: drive.sh put <drive> <path> --from <local-file>"
-    put_file "$@"
-    ;;
-  import)
-    [[ $# -ge 2 ]] || die "usage: drive.sh import <drive> <prefix> --from <local-folder> [--dry-run]"
-    drive="$1"; prefix="${2%/}"; shift 2
-    from=""; dry=0
-    while [[ $# -gt 0 ]]; do
-      case "$1" in
-        --from) from="$2"; shift 2 ;;
-        --dry-run) dry=1; shift ;;
-        *) die "unexpected import argument: $1" ;;
-      esac
-    done
-    [[ -d "$from" ]] || die "--from must be a folder"
-    uploaded=0
-    skipped=0
-    failed=0
-    planned=0
-    while IFS= read -r -d '' f; do
-      rel="${f#$from/}"
-      [[ "$rel" == .git/* || "$rel" == node_modules/* || "$rel" == ".DS_Store" || "$rel" == */.DS_Store ]] && continue
-      planned=$((planned + 1))
-      sz=$(wc -c < "$f" | tr -d ' ')
-      if [[ "$sz" -gt "$MAX_FILE_BYTES" ]]; then
-        echo "skip oversized $f ($sz bytes > $MAX_FILE_BYTES)" >&2
-        skipped=$((skipped + 1))
-        continue
-      fi
-      dest="$rel"
-      [[ -n "$prefix" ]] && dest="$prefix/$rel"
-      if [[ "$dry" -eq 1 ]]; then
-        echo "upload $f -> $dest"
-        skipped=$((skipped + 1))
-      else
-        if (put_file "$drive" "$dest" --from "$f" >/dev/null); then
-          uploaded=$((uploaded + 1))
-        else
-          failed=$((failed + 1))
-        fi
-      fi
-    done < <(find "$from" -type f -print0 | sort -z)
-    echo "planned=$planned uploaded=$uploaded skipped=$skipped failed=$failed"
-    [[ "$failed" -eq 0 ]] || exit 1
-    ;;
-  export)
-    [[ $# -ge 2 ]] || die "usage: drive.sh export <drive> <prefix> --to <local-folder> [--dry-run]"
-    id=$(resolve_drive "$1"); prefix="${2%/}"; shift 2
-    to=""; dry=0
-    while [[ $# -gt 0 ]]; do
-      case "$1" in
-        --to) to="$2"; shift 2 ;;
-        --dry-run) dry=1; shift ;;
-        *) die "unexpected export argument: $1" ;;
-      esac
-    done
-    [[ -n "$to" ]] || die "--to is required"
-    cursor=""
-    total=0
-    while true; do
-      url="$BASE_URL/api/v1/drives/$id/files?prefix=$(urlenc "$prefix")&limit=200"
-      [[ -n "$cursor" ]] && url="$url&cursor=$(urlenc "$cursor")"
-      files=$(api_json GET "$url")
-      while IFS= read -r p; do
-        [[ -n "$p" ]] || continue
-        rel="$p"
-        [[ -n "$prefix" ]] && rel="${p#$prefix/}"
-        out="$to/$rel"
-        if [[ "$dry" -eq 1 ]]; then
-          echo "download $p -> $out"
-        else
-          mkdir -p "$(dirname "$out")"
-          curl -fsS "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$p")" "${auth_header[@]}" -o "$out"
-        fi
-        total=$((total + 1))
-      done < <(echo "$files" | "$JQ_BIN" -r '.files[].path')
-      cursor=$(echo "$files" | "$JQ_BIN" -r '.nextCursor // empty')
-      [[ -n "$cursor" ]] || break
-    done
-    echo "files=$total"
-    ;;
-  rm)
-    [[ $# -ge 2 ]] || die "usage: drive.sh rm <drive> <path> [--recursive --confirm <path>]"
-    id=$(resolve_drive "$1"); path="$2"; shift 2
-    recursive=0; confirm=""
-    while [[ $# -gt 0 ]]; do
-      case "$1" in
-        --recursive) recursive=1; shift ;;
-        --confirm) confirm="$2"; shift 2 ;;
-        *) die "unexpected rm argument: $1" ;;
-      esac
-    done
-    if [[ "$recursive" -eq 1 ]]; then
-      [[ "$confirm" == "$path" ]] || die "recursive delete requires --confirm '$path'"
-      head=$(drive_head "$id")
-      api_json DELETE "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$path")?recursive=true&baseVersionId=$(urlenc "$head")" | "$JQ_BIN" .
-    else
-      meta=$(file_meta "$id" "$path")
-      etag=$(echo "$meta" | "$JQ_BIN" -r '.etag')
-      curl -fsS -X DELETE "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$path")" "${auth_header[@]}" -H "If-Match: $etag" | "$JQ_BIN" .
-    fi
-    ;;
-  share)
-    [[ $# -ge 1 ]] || die "usage: drive.sh share <drive> --perms read|write [--prefix notes/] [--ttl 30d] [--label text] [--manage-tokens]"
-    id=$(resolve_drive "$1"); shift
-    perms="write"; prefix=""; ttl=""; label=""; manage_tokens="false"
-    while [[ $# -gt 0 ]]; do
-      case "$1" in
-        --perms) perms="$2"; shift 2 ;;
-        --prefix) prefix="$2"; shift 2 ;;
-        --ttl) ttl="$2"; shift 2 ;;
-        --label) label="$2"; shift 2 ;;
-        --manage-tokens) manage_tokens="true"; shift ;;
-        *) die "unexpected share argument: $1" ;;
-      esac
-    done
-    body=$("$JQ_BIN" -n --arg p "$perms" --arg pp "$prefix" --arg ttl "$ttl" --arg label "$label" --argjson mt "$manage_tokens" \
-      '{perms:$p} + (if $mt then {manageTokens:true} else {} end) + (if $ttl == "" then {} else {ttl:$ttl} end) + (if $pp == "" then {} else {pathPrefix:$pp} end) + (if $label == "" then {} else {label:$label} end)')
-    api_json POST "$BASE_URL/api/v1/drives/$id/tokens" "$body" | "$JQ_BIN" -r '.shareBlock'
-    ;;
-  tokens)
-    [[ $# -eq 1 ]] || die "usage: drive.sh tokens <drive>"
-    id=$(resolve_drive "$1")
-    api_json GET "$BASE_URL/api/v1/drives/$id/tokens" | "$JQ_BIN" .
-    ;;
-  revoke)
-    [[ $# -eq 2 ]] || die "usage: drive.sh revoke <drive> <tokenId>"
-    id=$(resolve_drive "$1")
-    api_json DELETE "$BASE_URL/api/v1/drives/$id/tokens/$2" | "$JQ_BIN" .
-    ;;
-  delete)
-    [[ $# -ge 1 ]] || die "usage: drive.sh delete <drive> --confirm <drive name>"
-    id=$(resolve_drive "$1"); shift
-    confirm=""
-    while [[ $# -gt 0 ]]; do
-      case "$1" in
-        --confirm) confirm="$2"; shift 2 ;;
-        *) die "unexpected delete argument: $1" ;;
-      esac
-    done
-    drive=$(api_json GET "$BASE_URL/api/v1/drives/$id")
-    name=$(echo "$drive" | "$JQ_BIN" -r '.drive.name')
-    [[ "$confirm" == "$name" ]] || die "delete requires --confirm '$name'"
-    api_json DELETE "$BASE_URL/api/v1/drives/$id" | "$JQ_BIN" .
-    ;;
-  *)
-    die "unknown command: $CMD"
-    ;;
-esac

optional-skills/productivity/here-now/scripts/publish.sh

@@ -1,445 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-BASE_URL="https://here.now"
-CREDENTIALS_FILE="$HOME/.herenow/credentials"
-API_KEY="${HERENOW_API_KEY:-}"
-API_KEY_SOURCE="none"
-if [[ -n "${HERENOW_API_KEY:-}" ]]; then
-  API_KEY_SOURCE="env"
-fi
-ALLOW_NON_HERENOW_BASE_URL=0
-SLUG=""
-CLAIM_TOKEN=""
-TITLE=""
-DESCRIPTION=""
-TTL=""
-CLIENT=""
-TARGET=""
-FORKABLE=""
-SPA_MODE=""
-FROM_DRIVE=""
-DRIVE_VERSION=""
-
-usage() {
-  cat <<'USAGE'
-Usage: publish.sh <file-or-dir> [options]
-
-Options:
-  --api-key <key>         API key (or set $HERENOW_API_KEY)
-  --slug <slug>           Update existing publish
-  --claim-token <token>   Claim token for anonymous updates
-  --title <text>          Viewer title
-  --description <text>    Viewer description
-  --ttl <seconds>         Expiry (authenticated only)
-  --client <name>         Agent name for attribution (e.g. cursor, claude-code)
-  --forkable              Allow others to fork this site
-  --spa                   Enable SPA routing
-  --from-drive <drv_...>  Publish a Drive snapshot instead of local files
-  --version <dv_...>      Drive version for --from-drive (default: current head)
-  --base-url <url>        API base (default: https://here.now)
-  --allow-nonherenow-base-url
-                         Allow auth requests to non-default API base URL
-USAGE
-  exit 1
-}
-
-die() { echo "error: $1" >&2; exit 1; }
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-SKILL_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
-BUNDLED_JQ="${SKILL_DIR}/bin/jq"
-
-if [[ -x "$BUNDLED_JQ" ]]; then
-  JQ_BIN="$BUNDLED_JQ"
-elif command -v jq >/dev/null 2>&1; then
-  JQ_BIN="$(command -v jq)"
-else
-  die "requires jq"
-fi
-
-for cmd in curl file; do
-  command -v "$cmd" >/dev/null 2>&1 || die "requires $cmd"
-done
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --api-key)      API_KEY="$2"; API_KEY_SOURCE="flag"; shift 2 ;;
-    --slug)         SLUG="$2"; shift 2 ;;
-    --claim-token)  CLAIM_TOKEN="$2"; shift 2 ;;
-    --title)        TITLE="$2"; shift 2 ;;
-    --description)  DESCRIPTION="$2"; shift 2 ;;
-    --ttl)          TTL="$2"; shift 2 ;;
-    --client)       CLIENT="$2"; shift 2 ;;
-    --base-url)     BASE_URL="$2"; shift 2 ;;
-    --allow-nonherenow-base-url) ALLOW_NON_HERENOW_BASE_URL=1; shift ;;
-    --forkable)     FORKABLE="true"; shift ;;
-    --spa)          SPA_MODE="true"; shift ;;
-    --from-drive)   FROM_DRIVE="$2"; shift 2 ;;
-    --version)      DRIVE_VERSION="$2"; shift 2 ;;
-    --help|-h)      usage ;;
-    -*)             die "unknown option: $1" ;;
-    *)              [[ -z "$TARGET" ]] && TARGET="$1" || die "unexpected argument: $1"; shift ;;
-  esac
-done
-
-if [[ -n "$FROM_DRIVE" ]]; then
-  [[ -z "$TARGET" ]] || die "--from-drive does not accept a local file-or-dir argument"
-else
-  [[ -n "$TARGET" ]] || usage
-  [[ -e "$TARGET" ]] || die "path does not exist: $TARGET"
-fi
-
-# Load API key from credentials file if not provided via flag or env
-if [[ -z "$API_KEY" && -f "$CREDENTIALS_FILE" ]]; then
-  API_KEY=$(cat "$CREDENTIALS_FILE" | tr -d '[:space:]')
-  [[ -n "$API_KEY" ]] && API_KEY_SOURCE="credentials"
-fi
-
-BASE_URL="${BASE_URL%/}"
-STATE_DIR=".herenow"
-STATE_FILE="$STATE_DIR/state.json"
-
-# Safety guard: avoid accidentally sending bearer auth to arbitrary endpoints.
-if [[ -n "$API_KEY" && "$BASE_URL" != "https://here.now" && "$ALLOW_NON_HERENOW_BASE_URL" -ne 1 ]]; then
-  die "refusing to send API key to non-default base URL; pass --allow-nonherenow-base-url to override"
-fi
-
-# Auto-load claim token from state file for anonymous updates
-if [[ -n "$SLUG" && -z "$CLAIM_TOKEN" && -z "$API_KEY" && -f "$STATE_FILE" ]]; then
-  CLAIM_TOKEN=$("$JQ_BIN" -r --arg s "$SLUG" '.publishes[$s].claimToken // empty' "$STATE_FILE" 2>/dev/null || true)
-fi
-
-if [[ -n "$FROM_DRIVE" ]]; then
-  [[ -n "$API_KEY" ]] || die "--from-drive requires an account API key"
-  BODY=$("$JQ_BIN" -n --arg d "$FROM_DRIVE" '{driveId:$d}')
-  [[ -n "$DRIVE_VERSION" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" --arg v "$DRIVE_VERSION" '.versionId = $v')
-  [[ -n "$SLUG" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" --arg s "$SLUG" '.slug = $s')
-  if [[ -n "$TITLE" || -n "$DESCRIPTION" ]]; then
-    viewer="{}"
-    [[ -n "$TITLE" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg t "$TITLE" '.title = $t')
-    [[ -n "$DESCRIPTION" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg d "$DESCRIPTION" '.description = $d')
-    BODY=$(echo "$BODY" | "$JQ_BIN" --argjson v "$viewer" '.viewer = $v')
-  fi
-  [[ "$FORKABLE" == "true" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" '.forkable = true')
-  [[ "$SPA_MODE" == "true" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" '.spaMode = true')
-  CLIENT_HEADER_VALUE="here-now-publish-sh"
-  if [[ -n "$CLIENT" ]]; then
-    normalized_client=$(echo "$CLIENT" | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9._-' '-')
-    normalized_client="${normalized_client#-}"
-    normalized_client="${normalized_client%-}"
-    if [[ -n "$normalized_client" ]]; then
-      CLIENT_HEADER_VALUE="${normalized_client}/publish-sh"
-    fi
-  fi
-
-  echo "publishing from Drive..." >&2
-  RESPONSE=$(curl -sS -X POST "$BASE_URL/api/v1/publish/from-drive" \
-    -H "authorization: Bearer $API_KEY" \
-    -H "x-herenow-client: $CLIENT_HEADER_VALUE" \
-    -H "content-type: application/json" \
-    -d "$BODY")
-  if echo "$RESPONSE" | "$JQ_BIN" -e '.error' >/dev/null 2>&1; then
-    err=$(echo "$RESPONSE" | "$JQ_BIN" -r '.error')
-    die "$err"
-  fi
-  SITE_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.siteUrl')
-  OUT_SLUG=$(echo "$RESPONSE" | "$JQ_BIN" -r '.slug')
-  CURRENT_VERSION=$(echo "$RESPONSE" | "$JQ_BIN" -r '.currentVersionId')
-  DRIVE_VERSION_OUT=$(echo "$RESPONSE" | "$JQ_BIN" -r '.driveVersionId')
-  echo "$SITE_URL"
-  echo "" >&2
-  echo "publish_result.site_url=$SITE_URL" >&2
-  echo "publish_result.slug=$OUT_SLUG" >&2
-  echo "publish_result.action=from_drive" >&2
-  echo "publish_result.auth_mode=authenticated" >&2
-  echo "publish_result.api_key_source=$API_KEY_SOURCE" >&2
-  echo "publish_result.persistence=permanent" >&2
-  echo "publish_result.drive_id=$FROM_DRIVE" >&2
-  echo "publish_result.drive_version_id=$DRIVE_VERSION_OUT" >&2
-  echo "publish_result.current_version_id=$CURRENT_VERSION" >&2
-  exit 0
-fi
-
-compute_sha256() {
-  local f="$1"
-  if command -v sha256sum >/dev/null 2>&1; then
-    sha256sum "$f" | cut -d' ' -f1
-  else
-    shasum -a 256 "$f" | cut -d' ' -f1
-  fi
-}
-
-guess_content_type() {
-  local f="$1"
-  case "${f##*.}" in
-    html|htm) echo "text/html; charset=utf-8" ;;
-    css)      echo "text/css; charset=utf-8" ;;
-    js|mjs)   echo "text/javascript; charset=utf-8" ;;
-    json)     echo "application/json; charset=utf-8" ;;
-    md|txt)   echo "text/plain; charset=utf-8" ;;
-    svg)      echo "image/svg+xml" ;;
-    png)      echo "image/png" ;;
-    jpg|jpeg) echo "image/jpeg" ;;
-    gif)      echo "image/gif" ;;
-    webp)     echo "image/webp" ;;
-    pdf)      echo "application/pdf" ;;
-    mp4)      echo "video/mp4" ;;
-    mov)      echo "video/quicktime" ;;
-    mp3)      echo "audio/mpeg" ;;
-    wav)      echo "audio/wav" ;;
-    xml)      echo "application/xml" ;;
-    woff2)    echo "font/woff2" ;;
-    woff)     echo "font/woff" ;;
-    ttf)      echo "font/ttf" ;;
-    ico)      echo "image/x-icon" ;;
-    *)
-      local detected
-      detected=$(file --brief --mime-type "$f" 2>/dev/null || echo "application/octet-stream")
-      echo "$detected"
-      ;;
-  esac
-}
-
-# Build file manifest as JSON array
-FILES_JSON="[]"
-
-if [[ -f "$TARGET" ]]; then
-  sz=$(wc -c < "$TARGET" | tr -d ' ')
-  ct=$(guess_content_type "$TARGET")
-  bn=$(basename "$TARGET")
-  h=$(compute_sha256 "$TARGET")
-  FILES_JSON=$("$JQ_BIN" -n --arg p "$bn" --argjson s "$sz" --arg c "$ct" --arg h "$h" \
-    '[{"path":$p,"size":$s,"contentType":$c,"hash":$h}]')
-  FILE_MAP=$("$JQ_BIN" -n --arg p "$bn" --arg a "$(cd "$(dirname "$TARGET")" && pwd)/$(basename "$TARGET")" \
-    '{($p):$a}')
-elif [[ -d "$TARGET" ]]; then
-  FILE_MAP="{}"
-  while IFS= read -r -d '' f; do
-    rel="${f#$TARGET/}"
-    [[ "$rel" == ".DS_Store" ]] && continue
-    [[ "$(basename "$rel")" == ".DS_Store" ]] && continue
-    [[ "$rel" == ".herenow/fork-meta.json" ]] && continue
-    sz=$(wc -c < "$f" | tr -d ' ')
-    ct=$(guess_content_type "$f")
-    h=$(compute_sha256 "$f")
-    abs=$(cd "$(dirname "$f")" && pwd)/$(basename "$f")
-    FILES_JSON=$(echo "$FILES_JSON" | "$JQ_BIN" --arg p "$rel" --argjson s "$sz" --arg c "$ct" --arg h "$h" \
-      '. + [{"path":$p,"size":$s,"contentType":$c,"hash":$h}]')
-    FILE_MAP=$(echo "$FILE_MAP" | "$JQ_BIN" --arg p "$rel" --arg a "$abs" '. + {($p):$a}')
-  done < <(find "$TARGET" -type f -print0 | sort -z)
-else
-  die "not a file or directory: $TARGET"
-fi
-
-file_count=$(echo "$FILES_JSON" | "$JQ_BIN" 'length')
-[[ "$file_count" -gt 0 ]] || die "no files found"
-
-# Read fork-meta.json defaults if present and no explicit flags given
-FORK_META=""
-if [[ -d "$TARGET" ]]; then
-  FORK_META_PATH="$TARGET/.herenow/fork-meta.json"
-  if [[ -f "$FORK_META_PATH" ]]; then
-    FORK_META=$(cat "$FORK_META_PATH")
-    if [[ -z "$FORKABLE" ]]; then
-      FORKABLE=$("$JQ_BIN" -r '.forkable // empty' <<< "$FORK_META" 2>/dev/null || true)
-    fi
-  fi
-fi
-
-# Build request body
-BODY=$(echo "$FILES_JSON" | "$JQ_BIN" '{files: .}')
-
-if [[ -n "$TTL" ]]; then
-  BODY=$(echo "$BODY" | "$JQ_BIN" --argjson t "$TTL" '.ttlSeconds = $t')
-fi
-
-if [[ -n "$TITLE" || -n "$DESCRIPTION" ]]; then
-  viewer="{}"
-  [[ -n "$TITLE" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg t "$TITLE" '.title = $t')
-  [[ -n "$DESCRIPTION" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg d "$DESCRIPTION" '.description = $d')
-  BODY=$(echo "$BODY" | "$JQ_BIN" --argjson v "$viewer" '.viewer = $v')
-fi
-
-if [[ -n "$CLAIM_TOKEN" && -n "$SLUG" && -z "$API_KEY" ]]; then
-  BODY=$(echo "$BODY" | "$JQ_BIN" --arg ct "$CLAIM_TOKEN" '.claimToken = $ct')
-fi
-
-if [[ "$FORKABLE" == "true" ]]; then
-  BODY=$(echo "$BODY" | "$JQ_BIN" '.forkable = true')
-fi
-
-if [[ "$SPA_MODE" == "true" ]]; then
-  BODY=$(echo "$BODY" | "$JQ_BIN" '.spaMode = true')
-fi
-
-# Determine endpoint and method
-if [[ -n "$SLUG" ]]; then
-  URL="$BASE_URL/api/v1/publish/$SLUG"
-  METHOD="PUT"
-else
-  URL="$BASE_URL/api/v1/publish"
-  METHOD="POST"
-fi
-
-# Build auth header
-AUTH_ARGS=()
-if [[ -n "$API_KEY" ]]; then
-  AUTH_ARGS=(-H "authorization: Bearer $API_KEY")
-fi
-
-AUTH_MODE="anonymous"
-if [[ -n "$API_KEY" ]]; then
-  AUTH_MODE="authenticated"
-fi
-
-CLIENT_HEADER_VALUE="here-now-publish-sh"
-if [[ -n "$CLIENT" ]]; then
-  normalized_client=$(echo "$CLIENT" | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9._-' '-')
-  normalized_client="${normalized_client#-}"
-  normalized_client="${normalized_client%-}"
-  if [[ -n "$normalized_client" ]]; then
-    CLIENT_HEADER_VALUE="${normalized_client}/publish-sh"
-  fi
-fi
-CLIENT_ARGS=(-H "x-herenow-client: $CLIENT_HEADER_VALUE")
-
-# Step 1: Create/update publish
-echo "creating publish ($file_count files)..." >&2
-RESPONSE=$(curl -sS -X "$METHOD" "$URL" \
-  "${AUTH_ARGS[@]+"${AUTH_ARGS[@]}"}" \
-  "${CLIENT_ARGS[@]+"${CLIENT_ARGS[@]}"}" \
-  -H "content-type: application/json" \
-  -d "$BODY")
-
-# Check for errors
-if echo "$RESPONSE" | "$JQ_BIN" -e '.error' >/dev/null 2>&1; then
-  err=$(echo "$RESPONSE" | "$JQ_BIN" -r '.error')
-  details=$(echo "$RESPONSE" | "$JQ_BIN" -r '.details // empty')
-  die "$err${details:+ ($details)}"
-fi
-
-OUT_SLUG=$(echo "$RESPONSE" | "$JQ_BIN" -r '.slug')
-VERSION_ID=$(echo "$RESPONSE" | "$JQ_BIN" -r '.upload.versionId')
-FINALIZE_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.upload.finalizeUrl')
-SITE_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.siteUrl')
-UPLOAD_COUNT=$(echo "$RESPONSE" | "$JQ_BIN" '.upload.uploads | length')
-SKIPPED_COUNT=$(echo "$RESPONSE" | "$JQ_BIN" '.upload.skipped // [] | length')
-
-[[ "$OUT_SLUG" != "null" ]] || die "unexpected response: $RESPONSE"
-
-# Step 2: Upload files (skipped files are unchanged from previous version)
-if [[ "$SKIPPED_COUNT" -gt 0 ]]; then
-  echo "uploading $UPLOAD_COUNT files ($SKIPPED_COUNT unchanged, skipped)..." >&2
-else
-  echo "uploading $UPLOAD_COUNT files..." >&2
-fi
-upload_errors=0
-
-for i in $(seq 0 $((UPLOAD_COUNT - 1))); do
-  upload_path=$(echo "$RESPONSE" | "$JQ_BIN" -r ".upload.uploads[$i].path")
-  upload_url=$(echo "$RESPONSE" | "$JQ_BIN" -r ".upload.uploads[$i].url")
-  upload_ct=$(echo "$RESPONSE" | "$JQ_BIN" -r ".upload.uploads[$i].headers[\"Content-Type\"] // empty")
-
-  if [[ -f "$TARGET" && ! -d "$TARGET" ]]; then
-    local_file="$TARGET"
-  else
-    local_file=$(echo "$FILE_MAP" | "$JQ_BIN" -r --arg p "$upload_path" '.[$p]')
-  fi
-
-  if [[ ! -f "$local_file" ]]; then
-    echo "warning: missing local file for $upload_path" >&2
-    upload_errors=$((upload_errors + 1))
-    continue
-  fi
-
-  ct_args=()
-  [[ -n "$upload_ct" ]] && ct_args=(-H "Content-Type: $upload_ct")
-
-  http_code=$(curl -sS -o /dev/null -w "%{http_code}" -X PUT "$upload_url" \
-    "${ct_args[@]+"${ct_args[@]}"}" \
-    --data-binary "@$local_file")
-
-  if [[ "$http_code" -lt 200 || "$http_code" -ge 300 ]]; then
-    echo "warning: upload failed for $upload_path (HTTP $http_code)" >&2
-    upload_errors=$((upload_errors + 1))
-  fi
-done
-
-[[ "$upload_errors" -eq 0 ]] || die "$upload_errors file(s) failed to upload"
-
-# Step 3: Finalize
-echo "finalizing..." >&2
-FIN_RESPONSE=$(curl -sS -X POST "$FINALIZE_URL" \
-  "${AUTH_ARGS[@]+"${AUTH_ARGS[@]}"}" \
-  "${CLIENT_ARGS[@]+"${CLIENT_ARGS[@]}"}" \
-  -H "content-type: application/json" \
-  -d "{\"versionId\":\"$VERSION_ID\"}")
-
-if echo "$FIN_RESPONSE" | "$JQ_BIN" -e '.error' >/dev/null 2>&1; then
-  err=$(echo "$FIN_RESPONSE" | "$JQ_BIN" -r '.error')
-  die "finalize failed: $err"
-fi
-
-# Save state
-mkdir -p "$STATE_DIR"
-if [[ -f "$STATE_FILE" ]]; then
-  STATE=$(cat "$STATE_FILE")
-else
-  STATE='{"publishes":{}}'
-fi
-
-entry=$("$JQ_BIN" -n --arg s "$SITE_URL" '{siteUrl: $s}')
-
-RESPONSE_CLAIM_TOKEN=$(echo "$RESPONSE" | "$JQ_BIN" -r '.claimToken // empty')
-RESPONSE_CLAIM_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.claimUrl // empty')
-RESPONSE_EXPIRES=$(echo "$RESPONSE" | "$JQ_BIN" -r '.expiresAt // empty')
-
-[[ -n "$RESPONSE_CLAIM_TOKEN" ]] && entry=$(echo "$entry" | "$JQ_BIN" --arg v "$RESPONSE_CLAIM_TOKEN" '.claimToken = $v')
-[[ -n "$RESPONSE_CLAIM_URL" ]] && entry=$(echo "$entry" | "$JQ_BIN" --arg v "$RESPONSE_CLAIM_URL" '.claimUrl = $v')
-[[ -n "$RESPONSE_EXPIRES" ]] && entry=$(echo "$entry" | "$JQ_BIN" --arg v "$RESPONSE_EXPIRES" '.expiresAt = $v')
-
-STATE=$(echo "$STATE" | "$JQ_BIN" --arg slug "$OUT_SLUG" --argjson e "$entry" '.publishes[$slug] = $e')
-echo "$STATE" | "$JQ_BIN" '.' > "$STATE_FILE"
-
-# Output
-echo "$SITE_URL"
-
-PERSISTENCE="permanent"
-if [[ "$AUTH_MODE" == "anonymous" ]]; then
-  PERSISTENCE="expires_24h"
-elif [[ -n "$RESPONSE_EXPIRES" ]]; then
-  PERSISTENCE="expires_at"
-fi
-
-SAFE_CLAIM_URL=""
-if [[ -n "$RESPONSE_CLAIM_URL" && "$RESPONSE_CLAIM_URL" == https://* ]]; then
-  SAFE_CLAIM_URL="$RESPONSE_CLAIM_URL"
-fi
-
-ACTION="create"
-if [[ -n "$SLUG" ]]; then
-  ACTION="update"
-fi
-
-echo "" >&2
-echo "publish_result.site_url=$SITE_URL" >&2
-echo "publish_result.slug=$OUT_SLUG" >&2
-echo "publish_result.action=$ACTION" >&2
-echo "publish_result.auth_mode=$AUTH_MODE" >&2
-echo "publish_result.api_key_source=$API_KEY_SOURCE" >&2
-echo "publish_result.persistence=$PERSISTENCE" >&2
-echo "publish_result.expires_at=$RESPONSE_EXPIRES" >&2
-echo "publish_result.claim_url=$SAFE_CLAIM_URL" >&2
-
-if [[ "$AUTH_MODE" == "authenticated" ]]; then
-  echo "authenticated publish (permanent, saved to your account)" >&2
-else
-  echo "anonymous publish (expires in 24h)" >&2
-  if [[ -n "$SAFE_CLAIM_URL" ]]; then
-    echo "claim URL: $SAFE_CLAIM_URL" >&2
-  fi
-  if [[ -n "$RESPONSE_CLAIM_TOKEN" ]]; then
-    echo "claim token saved to $STATE_FILE" >&2
-  fi
-fi

plugins/hermes-achievements/dashboard/plugin_api.py

@@ -12,14 +12,6 @@ import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Set
 
-try:
-    from hermes_constants import get_hermes_home
-except ImportError:
-    import os as _os
-    def get_hermes_home() -> Path:  # type: ignore[misc]
-        val = (_os.environ.get("HERMES_HOME") or "").strip()
-        return Path(val) if val else Path.home() / ".hermes"
-
 try:
     from fastapi import APIRouter
 except Exception:  # Allows local unit tests without dashboard dependencies.
@@ -143,15 +135,15 @@ ACHIEVEMENTS: List[Dict[str, Any]] = [
 
 
 def state_path() -> Path:
-    return get_hermes_home() / "plugins" / "hermes-achievements" / "state.json"
+    return Path.home() / ".hermes" / "plugins" / "hermes-achievements" / "state.json"
 
 
 def snapshot_path() -> Path:
-    return get_hermes_home() / "plugins" / "hermes-achievements" / "scan_snapshot.json"
+    return Path.home() / ".hermes" / "plugins" / "hermes-achievements" / "scan_snapshot.json"
 
 
 def checkpoint_path() -> Path:
-    return get_hermes_home() / "plugins" / "hermes-achievements" / "scan_checkpoint.json"
+    return Path.home() / ".hermes" / "plugins" / "hermes-achievements" / "scan_checkpoint.json"
 
 
 def load_state() -> Dict[str, Any]:

plugins/kanban/dashboard/dist/index.js

@@ -231,7 +231,7 @@
               String(this.state.error && this.state.error.message || this.state.error)),
             h(Button, {
               onClick: () => this.setState({ error: null }),
-              size: "sm",
+              className: "h-7 px-3 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
             }, "Reload view"),
           ),
         );
@@ -599,11 +599,11 @@
       h("div", { className: "flex-1" }),
       h(Button, {
         onClick: props.onNudgeDispatch,
-        size: "sm",
+        className: "h-8 px-3 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
       }, "Nudge dispatcher"),
       h(Button, {
         onClick: props.onRefresh,
-        size: "sm",
+        className: "h-8 px-3 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
       }, "Refresh"),
     );
   }
@@ -619,21 +619,21 @@
         `${props.count} selected`),
       h(Button, {
         onClick: function () { props.onApply({ status: "ready" }); },
-        size: "sm",
+        className: "hermes-kanban-bulk-btn",
       }, "→ ready"),
       h(Button, {
         onClick: function () {
           props.onApply({ status: "done" },
             `Mark ${props.count} task(s) as done?`);
         },
-        size: "sm",
+        className: "hermes-kanban-bulk-btn",
       }, "Complete"),
       h(Button, {
         onClick: function () {
           props.onApply({ archive: true },
             `Archive ${props.count} task(s)?`);
         },
-        size: "sm",
+        className: "hermes-kanban-bulk-btn",
       }, "Archive"),
       h("div", { className: "hermes-kanban-bulk-reassign" },
         h(Select, {
@@ -654,13 +654,14 @@
             setAssignee("");
           },
           disabled: !assignee,
-          size: "sm",
+          className: cn("hermes-kanban-bulk-btn",
+            !assignee ? "opacity-40 cursor-not-allowed" : ""),
         }, "Apply"),
       ),
       h("div", { className: "flex-1" }),
       h(Button, {
         onClick: props.onClear,
-        size: "sm",
+        className: "hermes-kanban-bulk-btn",
       }, "Clear"),
     );
   }
@@ -992,11 +993,11 @@
       h("div", { className: "flex gap-2" },
         h(Button, {
           onClick: submit,
-          size: "sm",
+          className: "h-7 px-2 text-xs border border-border hover:bg-foreground/10 cursor-pointer flex-1",
         }, "Create"),
         h(Button, {
           onClick: props.onCancel,
-          size: "sm",
+          className: "h-7 px-2 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
         }, "Cancel"),
       ),
     );
@@ -1124,7 +1125,7 @@
           }),
           h(Button, {
             onClick: handleComment,
-            size: "sm",
+            className: "h-8 px-3 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
           }, "Comment"),
         ) : null,
       ),
@@ -1354,10 +1355,10 @@
         className: "h-8 text-sm flex-1",
       }),
       h(Button, { onClick: save,
-        size: "sm",
+        className: "h-7 px-2 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
       }, "Save"),
       h(Button, { onClick: props.onCancel,
-        size: "sm",
+        className: "h-7 px-2 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
       }, "Cancel"),
     );
   }
@@ -1438,10 +1439,10 @@
         editing
           ? h("div", { className: "flex gap-1" },
               h(Button, { onClick: save,
-                size: "sm",
+                className: "h-6 px-2 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
               }, "Save"),
               h(Button, { onClick: function () { setEditing(false); setV(props.task.body || ""); },
-                size: "sm",
+                className: "h-6 px-2 text-xs border border-border hover:bg-foreground/10 cursor-pointer",
               }, "Cancel"),
             )
           : h("button", {
@@ -1515,7 +1516,8 @@
             props.onAddParent(newParent).then(function () { setNewParent(""); });
           },
           disabled: !newParent,
-          size: "sm",
+          className: cn("h-7 px-2 text-xs border border-border cursor-pointer",
+            !newParent ? "opacity-40 cursor-not-allowed" : "hover:bg-foreground/10"),
         }, "+ parent"),
       ),
       h("div", { className: "hermes-kanban-deps-row" },
@@ -1554,7 +1556,8 @@
             props.onAddChild(newChild).then(function () { setNewChild(""); });
           },
           disabled: !newChild,
-          size: "sm",
+          className: cn("h-7 px-2 text-xs border border-border cursor-pointer",
+            !newChild ? "opacity-40 cursor-not-allowed" : "hover:bg-foreground/10"),
         }, "+ child"),
       ),
     );
@@ -1566,7 +1569,10 @@
       return h(Button, {
         onClick: function () { if (enabled !== false) props.onPatch(patch, { confirm: confirmMsg }); },
         disabled: enabled === false,
-        size: "sm",
+        className: cn(
+          "h-7 px-2 text-xs border border-border cursor-pointer",
+          enabled === false ? "opacity-40 cursor-not-allowed" : "hover:bg-foreground/10",
+        ),
       }, label);
     };
     return h("div", { className: "hermes-kanban-actions" },

plugins/kanban/dashboard/dist/style.css

@@ -251,11 +251,6 @@
   border-radius: var(--radius-sm, 0.25rem);
 }
 
-.hermes-kanban-inline-create > .flex.gap-2:last-child > button:first-of-type {
-  flex: 1;
-  min-width: 0;
-}
-
 /* ---- Drawer (task detail side panel) --------------------------------- */
 
 .hermes-kanban-drawer-shade {
@@ -465,17 +460,14 @@
   font-size: 0.75rem;
   padding-right: 0.25rem;
 }
-
-.hermes-kanban-bulk > button,
-.hermes-kanban-bulk-reassign > button {
+.hermes-kanban-bulk-btn {
   height: 1.7rem !important;
   padding: 0 0.5rem !important;
   font-size: 0.7rem !important;
   border: 1px solid var(--color-border);
   cursor: pointer;
 }
-.hermes-kanban-bulk > button:hover:not(:disabled),
-.hermes-kanban-bulk-reassign > button:hover:not(:disabled) {
+.hermes-kanban-bulk-btn:hover {
   background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
 }
 .hermes-kanban-bulk-reassign {

plugins/memory/honcho/client.py

@@ -110,17 +110,6 @@ def _parse_context_tokens(host_val, root_val) -> int | None:
     return None
 
 
-def _parse_int_config(host_val, root_val, default: int) -> int:
-    """Parse an integer config: host wins, then root, then default."""
-    for val in (host_val, root_val):
-        if val is not None:
-            try:
-                return int(val)
-            except (ValueError, TypeError):
-                pass
-    return default
-
-
 def _parse_dialectic_depth(host_val, root_val) -> int:
     """Parse dialecticDepth: host wins, then root, then 1. Clamped to 1-3."""
     for val in (host_val, root_val):
@@ -474,10 +463,10 @@ class HonchoClientConfig:
                 raw.get("dialecticDynamic"),
                 default=True,
             ),
-            dialectic_max_chars=_parse_int_config(
-                host_block.get("dialecticMaxChars"),
-                raw.get("dialecticMaxChars"),
-                default=600,
+            dialectic_max_chars=int(
+                host_block.get("dialecticMaxChars")
+                or raw.get("dialecticMaxChars")
+                or 600
             ),
             dialectic_depth=_parse_dialectic_depth(
                 host_block.get("dialecticDepth"),
@@ -498,15 +487,15 @@ class HonchoClientConfig:
                 or raw.get("reasoningLevelCap")
                 or "high"
             ),
-            message_max_chars=_parse_int_config(
-                host_block.get("messageMaxChars"),
-                raw.get("messageMaxChars"),
-                default=25000,
+            message_max_chars=int(
+                host_block.get("messageMaxChars")
+                or raw.get("messageMaxChars")
+                or 25000
             ),
-            dialectic_max_input_chars=_parse_int_config(
-                host_block.get("dialecticMaxInputChars"),
-                raw.get("dialecticMaxInputChars"),
-                default=10000,
+            dialectic_max_input_chars=int(
+                host_block.get("dialecticMaxInputChars")
+                or raw.get("dialecticMaxInputChars")
+                or 10000
             ),
             recall_mode=_normalize_recall_mode(
                 host_block.get("recallMode")

plugins/memory/honcho/session.py

@@ -160,13 +160,11 @@ class HonchoSessionManager:
         Peers are lazy -- no API call until first use.
         Observation settings are controlled per-session via SessionPeerConfig.
         """
-        with self._cache_lock:
-            if peer_id in self._peers_cache:
-                return self._peers_cache[peer_id]
+        if peer_id in self._peers_cache:
+            return self._peers_cache[peer_id]
 
         peer = self.honcho.peer(peer_id)
-        with self._cache_lock:
-            self._peers_cache[peer_id] = peer
+        self._peers_cache[peer_id] = peer
         return peer
 
     def _get_or_create_honcho_session(
@@ -178,10 +176,9 @@ class HonchoSessionManager:
         Returns:
             Tuple of (honcho_session, existing_messages).
         """
-        with self._cache_lock:
-            if session_id in self._sessions_cache:
-                logger.debug("Honcho session '%s' retrieved from cache", session_id)
-                return self._sessions_cache[session_id], []
+        if session_id in self._sessions_cache:
+            logger.debug("Honcho session '%s' retrieved from cache", session_id)
+            return self._sessions_cache[session_id], []
 
         session = self.honcho.session(session_id)
 

plugins/platforms/teams/adapter.py

@@ -38,7 +38,6 @@ except ImportError:
 
 try:
     from microsoft_teams.apps import App, ActivityContext
-    from microsoft_teams.common.http.client import ClientOptions
     from microsoft_teams.api import MessageActivity, ConversationReference
     from microsoft_teams.api.activities.typing import TypingActivityInput
     from microsoft_teams.api.activities.invoke.adaptive_card import AdaptiveCardInvokeActivity
@@ -58,7 +57,6 @@ try:
     TEAMS_SDK_AVAILABLE = True
 except ImportError:
     TEAMS_SDK_AVAILABLE = False
-    ClientOptions = None  # type: ignore[assignment,misc]
     App = None  # type: ignore[assignment,misc]
     ActivityContext = None  # type: ignore[assignment,misc]
     MessageActivity = None  # type: ignore[assignment,misc]
@@ -210,7 +208,6 @@ class TeamsAdapter(BasePlatformAdapter):
                 client_secret=self._client_secret,
                 tenant_id=self._tenant_id,
                 http_server_adapter=_AiohttpBridgeAdapter(aiohttp_app),
-                client=ClientOptions(headers={"User-Agent": "Hermes"}),
             )
 
             # Register message handler before initialize()

run_agent.py

@@ -162,13 +162,6 @@ from agent.display import (
     _detect_tool_failure,
     get_tool_emoji as _get_tool_emoji,
 )
-from agent.tool_guardrails import (
-    ToolCallGuardrailConfig,
-    ToolCallGuardrailController,
-    ToolGuardrailDecision,
-    append_toolguard_guidance,
-    toolguard_synthetic_result,
-)
 from agent.trajectory import (
     convert_scratchpad_to_think, has_incomplete_scratchpad,
     save_trajectory as _save_trajectory_to_file,
@@ -1157,8 +1150,6 @@ class AIAgent:
         # Tool execution state — allows _vprint during tool execution
         # even when stream consumers are registered (no tokens streaming then)
         self._executing_tools = False
-        self._tool_guardrails = ToolCallGuardrailController()
-        self._tool_guardrail_halt_decision: ToolGuardrailDecision | None = None
 
         # Interrupt mechanism for breaking out of tool loops
         self._interrupt_requested = False
@@ -1258,10 +1249,6 @@ class AIAgent:
         # after each API call.  Accessed by /usage slash command.
         self._rate_limit_state: Optional["RateLimitState"] = None
 
-        # OpenRouter response cache hit counter — incremented when
-        # X-OpenRouter-Cache-Status: HIT is seen in streaming response headers.
-        self._or_cache_hits: int = 0
-
         # Centralized logging — agent.log (INFO+) and errors.log (WARNING+)
         # both live under ~/.hermes/logs/.  Idempotent, so gateway mode
         # (which creates a new AIAgent per message) won't duplicate handlers.
@@ -1425,8 +1412,11 @@ class AIAgent:
                     client_kwargs["args"] = self.acp_args
                 effective_base = base_url
                 if base_url_host_matches(effective_base, "openrouter.ai"):
-                    from agent.auxiliary_client import build_or_headers
-                    client_kwargs["default_headers"] = build_or_headers()
+                    client_kwargs["default_headers"] = {
+                        "HTTP-Referer": "https://hermes-agent.nousresearch.com",
+                        "X-OpenRouter-Title": "Hermes Agent",
+                        "X-OpenRouter-Categories": "productivity,cli-agent",
+                    }
                 elif base_url_host_matches(effective_base, "api.routermint.com"):
                     client_kwargs["default_headers"] = _routermint_headers()
                 elif base_url_host_matches(effective_base, "api.githubcopilot.com"):
@@ -1474,49 +1464,17 @@ class AIAgent:
                                 _env_hint = _pcfg.api_key_env_vars[0]
                         except Exception:
                             pass
-                        # --- Init-time fallback (#17929) ---
-                        _fb_entries = []
-                        if isinstance(fallback_model, list):
-                            _fb_entries = [
-                                f for f in fallback_model
-                                if isinstance(f, dict) and f.get("provider") and f.get("model")
-                            ]
-                        elif isinstance(fallback_model, dict) and fallback_model.get("provider") and fallback_model.get("model"):
-                            _fb_entries = [fallback_model]
-                        _fb_resolved = False
-                        for _fb in _fb_entries:
-                            _fb_client, _fb_model = resolve_provider_client(
-                                _fb["provider"], model=_fb["model"], raw_codex=True,
-                                explicit_base_url=_fb.get("base_url"),
-                                explicit_api_key=_fb.get("api_key"),
-                            )
-                            if _fb_client is not None:
-                                self.provider = _fb["provider"]
-                                self.model = _fb_model or _fb["model"]
-                                self._fallback_activated = True
-                                client_kwargs = {
-                                    "api_key": _fb_client.api_key,
-                                    "base_url": str(_fb_client.base_url),
-                                }
-                                if _provider_timeout is not None:
-                                    client_kwargs["timeout"] = _provider_timeout
-                                if hasattr(_fb_client, "_default_headers") and _fb_client._default_headers:
-                                    client_kwargs["default_headers"] = dict(_fb_client._default_headers)
-                                _fb_resolved = True
-                                break
-                        if not _fb_resolved:
-                            raise RuntimeError(
-                                f"Provider '{_explicit}' is set in config.yaml but no API key "
-                                f"was found. Set the {_env_hint} environment "
-                                f"variable, or switch to a different provider with `hermes model`."
-                            )
-                    if not getattr(self, "_fallback_activated", False):
-                        # No provider configured — reject with a clear message.
                         raise RuntimeError(
-                            "No LLM provider configured. Run `hermes model` to "
-                            "select a provider, or run `hermes setup` for first-time "
-                            "configuration."
+                            f"Provider '{_explicit}' is set in config.yaml but no API key "
+                            f"was found. Set the {_env_hint} environment "
+                            f"variable, or switch to a different provider with `hermes model`."
                         )
+                    # No provider configured — reject with a clear message.
+                    raise RuntimeError(
+                        "No LLM provider configured. Run `hermes model` to "
+                        "select a provider, or run `hermes setup` for first-time "
+                        "configuration."
+                    )
             
             self._client_kwargs = client_kwargs  # stored for rebuilding after interrupt
 
@@ -1569,7 +1527,7 @@ class AIAgent:
         else:
             self._fallback_chain = []
         self._fallback_index = 0
-        self._fallback_activated = getattr(self, "_fallback_activated", False)
+        self._fallback_activated = False
         # Legacy attribute kept for backward compat (tests, external callers)
         self._fallback_model = self._fallback_chain[0] if self._fallback_chain else None
         if self._fallback_chain and not self.quiet_mode:
@@ -1665,12 +1623,30 @@ class AIAgent:
         self._session_db = session_db
         self._parent_session_id = parent_session_id
         self._last_flushed_db_idx = 0  # tracks DB-write cursor to prevent duplicate writes
-        self._session_db_created = False  # DB row deferred to run_conversation()
-        self._session_init_model_config = {
-            "max_iterations": self.max_iterations,
-            "reasoning_config": reasoning_config,
-            "max_tokens": max_tokens,
-        }
+        if self._session_db:
+            try:
+                self._session_db.create_session(
+                    session_id=self.session_id,
+                    source=self.platform or os.environ.get("HERMES_SESSION_SOURCE", "cli"),
+                    model=self.model,
+                    model_config={
+                        "max_iterations": self.max_iterations,
+                        "reasoning_config": reasoning_config,
+                        "max_tokens": max_tokens,
+                    },
+                    user_id=None,
+                    parent_session_id=self._parent_session_id,
+                )
+            except Exception as e:
+                # Transient SQLite lock contention (e.g. CLI and gateway writing
+                # concurrently) must NOT permanently disable session_search for
+                # this agent.  Keep _session_db alive — subsequent message
+                # flushes and session_search calls will still work once the
+                # lock clears.  The session row may be missing from the index
+                # for this run, but that is recoverable (flushes upsert rows).
+                logger.warning(
+                    "Session DB create_session failed (session_search still available): %s", e
+                )
         
         # In-memory todo list for task planning (one per agent/session)
         from tools.todo_tool import TodoStore
@@ -1682,14 +1658,6 @@ class AIAgent:
             _agent_cfg = _load_agent_config()
         except Exception:
             _agent_cfg = {}
-        try:
-            self._tool_guardrails = ToolCallGuardrailController(
-                ToolCallGuardrailConfig.from_mapping(
-                    _agent_cfg.get("tool_loop_guardrails", {})
-                )
-            )
-        except Exception as _tlg_err:
-            logger.warning("Tool loop guardrail config ignored: %s", _tlg_err)
         # Cache only the derived auxiliary compression context override that is
         # needed later by the startup feasibility check.  Avoid exposing a
         # broad pseudo-public config object on the agent instance.
@@ -2185,28 +2153,6 @@ class AIAgent:
                 "is_anthropic_oauth": self._is_anthropic_oauth,
             })
 
-    def _ensure_db_session(self) -> None:
-        """Create session DB row on first use. Disables _session_db on failure."""
-        if self._session_db_created or not self._session_db:
-            return
-        try:
-            self._session_db.create_session(
-                session_id=self.session_id,
-                source=self.platform or os.environ.get("HERMES_SESSION_SOURCE", "cli"),
-                model=self.model,
-                model_config=self._session_init_model_config,
-                system_prompt=self._cached_system_prompt,
-                user_id=None,
-                parent_session_id=self._parent_session_id,
-            )
-            self._session_db_created = True
-        except Exception as e:
-            # Transient failure (e.g. SQLite lock). Keep _session_db alive —
-            # _session_db_created stays False so next run_conversation() retries.
-            logger.warning(
-                "Session DB creation failed (will retry next turn): %s", e
-            )
-
     def reset_session_state(self):
         """Reset all session-scoped token counters to 0 for a fresh session.
         
@@ -3756,9 +3702,14 @@ class AIAgent:
             return
         self._apply_persist_user_message_override(messages)
         try:
-            # Retry row creation if the earlier attempt failed transiently.
-            if not self._session_db_created:
-                self._ensure_db_session()
+            # If create_session() failed at startup (e.g. transient lock), the
+            # session row may not exist yet.  ensure_session() uses INSERT OR
+            # IGNORE so it is a no-op when the row is already there.
+            self._session_db.ensure_session(
+                self.session_id,
+                source=self.platform or "cli",
+                model=self.model,
+            )
             start_idx = len(conversation_history) if conversation_history else 0
             flush_from = max(start_idx, self._last_flushed_db_idx)
             for msg in messages[flush_from:]:
@@ -4581,28 +4532,6 @@ class AIAgent:
         """Return the last captured RateLimitState, or None."""
         return self._rate_limit_state
 
-    def _check_openrouter_cache_status(self, http_response: Any) -> None:
-        """Read X-OpenRouter-Cache-Status from response headers and log it.
-
-        Increments ``_or_cache_hits`` on HIT so callers can report savings.
-        """
-        if http_response is None:
-            return
-        headers = getattr(http_response, "headers", None)
-        if not headers:
-            return
-        try:
-            status = headers.get("x-openrouter-cache-status")
-            if not status:
-                return
-            if status.upper() == "HIT":
-                self._or_cache_hits += 1
-                logger.info("OpenRouter response cache HIT (total: %d)", self._or_cache_hits)
-            else:
-                logger.debug("OpenRouter response cache %s", status.upper())
-        except Exception:
-            pass  # Never let header parsing break the agent loop
-
     def get_activity_summary(self) -> dict:
         """Return a snapshot of the agent's current activity for diagnostics.
 
@@ -5053,8 +4982,8 @@ class AIAgent:
     def _get_tool_call_id_static(tc) -> str:
         """Extract call ID from a tool_call entry (dict or object)."""
         if isinstance(tc, dict):
-            return tc.get("call_id", "") or tc.get("id", "") or ""
-        return getattr(tc, "call_id", "") or getattr(tc, "id", "") or ""
+            return tc.get("id", "") or ""
+        return getattr(tc, "id", "") or ""
 
     _VALID_API_ROLES = frozenset({"system", "user", "assistant", "tool", "function", "developer"})
 
@@ -6180,10 +6109,10 @@ class AIAgent:
         return True
 
     def _apply_client_headers_for_base_url(self, base_url: str) -> None:
-        from agent.auxiliary_client import _AI_GATEWAY_HEADERS, build_or_headers
+        from agent.auxiliary_client import _AI_GATEWAY_HEADERS, _OR_HEADERS
 
         if base_url_host_matches(base_url, "openrouter.ai"):
-            self._client_kwargs["default_headers"] = build_or_headers()
+            self._client_kwargs["default_headers"] = dict(_OR_HEADERS)
         elif base_url_host_matches(base_url, "ai-gateway.vercel.sh"):
             self._client_kwargs["default_headers"] = dict(_AI_GATEWAY_HEADERS)
         elif base_url_host_matches(base_url, "api.routermint.com"):
@@ -6803,9 +6732,6 @@ class AIAgent:
             # response via .response before any chunks are consumed.
             self._capture_rate_limits(getattr(stream, "response", None))
 
-            # Log OpenRouter response cache status when present.
-            self._check_openrouter_cache_status(getattr(stream, "response", None))
-
             content_parts: list = []
             tool_calls_acc: dict = {}
             tool_gen_notified: set = set()
@@ -8660,13 +8586,9 @@ class AIAgent:
             # message. Without it, replaying the persisted message causes
             # HTTP 400 ("The reasoning_content in the thinking mode must
             # be passed back to the API"). Include streamed reasoning
-            # text when captured; otherwise pad with a single space —
-            # DeepSeek V4 Pro tightened validation and rejects empty
-            # string ("The reasoning content in the thinking mode must
-            # be passed back to the API"). A space satisfies non-empty
-            # checks everywhere without leaking fabricated reasoning.
-            # Refs #15250, #17400, #17341.
-            msg["reasoning_content"] = reasoning_text or " "
+            # text when captured; otherwise pad with empty string.
+            # Refs #15250, #17400.
+            msg["reasoning_content"] = reasoning_text or ""
 
         # Additive fallback (refs #16844, #16884). Streaming-only providers
         # (glm, MiniMax, gpt-5.x via aigw, Anthropic via openai-compat shims)
@@ -8821,20 +8743,11 @@ class AIAgent:
             return
 
         # 1. Explicit reasoning_content already set — preserve it verbatim
-        # (includes DeepSeek/Kimi's own space-placeholder written at creation
-        # time, and any valid reasoning content from the same provider).
-        #
-        # Exception: sessions persisted BEFORE #17341 have empty-string
-        # placeholders pinned at creation time. DeepSeek V4 Pro rejects
-        # those with HTTP 400. When the active provider enforces the
-        # thinking-mode echo, upgrade "" → " " on replay so stale history
-        # doesn't 400 the user on the next turn.
+        # (includes DeepSeek/Kimi's own empty-string placeholder written at
+        # creation time, and any valid reasoning content from the same provider).
         existing = source_msg.get("reasoning_content")
         if isinstance(existing, str):
-            if existing == "" and self._needs_thinking_reasoning_pad():
-                api_msg["reasoning_content"] = " "
-            else:
-                api_msg["reasoning_content"] = existing
+            api_msg["reasoning_content"] = existing
             return
 
         needs_thinking_pad = self._needs_thinking_reasoning_pad()
@@ -8846,10 +8759,8 @@ class AIAgent:
         # pins reasoning_content at creation time for tool-call turns, so the
         # shape (reasoning set, reasoning_content absent, tool_calls present)
         # is unreachable from same-provider DeepSeek history after this fix.
-        # Inject a single space to satisfy the API without leaking another
-        # provider's chain of thought to DeepSeek/Kimi. Space (not "")
-        # because DeepSeek V4 Pro rejects empty-string reasoning_content
-        # in thinking mode (refs #17341).
+        # Inject "" to satisfy the API without leaking another provider's
+        # chain of thought to DeepSeek/Kimi.
         normalized_reasoning = source_msg.get("reasoning")
         if (
             needs_thinking_pad
@@ -8857,7 +8768,7 @@ class AIAgent:
             and isinstance(normalized_reasoning, str)
             and normalized_reasoning
         ):
-            api_msg["reasoning_content"] = " "
+            api_msg["reasoning_content"] = ""
             return
 
         # 3. Healthy session: promote 'reasoning' field to 'reasoning_content'
@@ -8870,15 +8781,12 @@ class AIAgent:
             return
 
         # 4. DeepSeek / Kimi thinking mode: all assistant messages need
-        # reasoning_content. Inject a single space to satisfy the provider's
-        # requirement when no explicit reasoning content is present. Covers
-        # both tool-call turns (already-poisoned history with no reasoning
-        # at all) and plain text turns. Space (not "") because DeepSeek V4
-        # Pro tightened validation and rejects empty string with HTTP 400
-        # ("The reasoning content in the thinking mode must be passed back
-        # to the API"). Refs #17341.
+        # reasoning_content. Inject "" to satisfy the provider's requirement
+        # when no explicit reasoning content is present. Covers both
+        # tool-call turns (already-poisoned history with no reasoning at all)
+        # and plain text turns.
         if needs_thinking_pad:
-            api_msg["reasoning_content"] = " "
+            api_msg["reasoning_content"] = ""
             return
 
         # 5. reasoning_content was present but not a string (e.g. None after
@@ -9113,15 +9021,12 @@ class AIAgent:
                 self.session_id = f"{datetime.now().strftime('%Y%m%d_%H%M%S')}_{uuid.uuid4().hex[:6]}"
                 # Update session_log_file to point to the new session's JSON file
                 self.session_log_file = self.logs_dir / f"session_{self.session_id}.json"
-                self._session_db_created = False
                 self._session_db.create_session(
                     session_id=self.session_id,
                     source=self.platform or os.environ.get("HERMES_SESSION_SOURCE", "cli"),
                     model=self.model,
-                    model_config=self._session_init_model_config,
                     parent_session_id=old_session_id,
                 )
-                self._session_db_created = True
                 # Auto-number the title for the continuation session
                 if old_title:
                     try:
@@ -9179,14 +9084,9 @@ class AIAgent:
 
         # Update token estimate after compaction so pressure calculations
         # use the post-compression count, not the stale pre-compression one.
-        # Use estimate_request_tokens_rough() so tool schemas are included —
-        # with 50+ tools enabled, schemas alone can add 20-30K tokens, and
-        # omitting them delays the next compression cycle far past the
-        # configured threshold (issue #14695).
-        _compressed_est = estimate_request_tokens_rough(
-            compressed,
-            system_prompt=new_system_prompt or "",
-            tools=self.tools or None,
+        _compressed_est = (
+            estimate_tokens_rough(new_system_prompt)
+            + estimate_messages_tokens_rough(compressed)
         )
         self.context_compressor.last_prompt_tokens = _compressed_est
         self.context_compressor.last_completion_tokens = 0
@@ -9207,44 +9107,6 @@ class AIAgent:
         )
         return compressed, new_system_prompt
 
-    def _set_tool_guardrail_halt(self, decision: ToolGuardrailDecision) -> None:
-        """Record the first guardrail decision that should stop this turn."""
-        if decision.should_halt and self._tool_guardrail_halt_decision is None:
-            self._tool_guardrail_halt_decision = decision
-
-    def _toolguard_controlled_halt_response(self, decision: ToolGuardrailDecision) -> str:
-        tool = decision.tool_name or "a tool"
-        return (
-            f"I stopped retrying {tool} because it hit the tool-call guardrail "
-            f"({decision.code}) after {decision.count} repeated non-progressing "
-            "attempts. The last tool result explains the blocker; the next step is "
-            "to change strategy instead of repeating the same call."
-        )
-
-    def _append_guardrail_observation(
-        self,
-        tool_name: str,
-        function_args: dict,
-        function_result: str,
-        *,
-        failed: bool,
-    ) -> str:
-        decision = self._tool_guardrails.after_call(
-            tool_name,
-            function_args,
-            function_result,
-            failed=failed,
-        )
-        if decision.action in {"warn", "halt"}:
-            function_result = append_toolguard_guidance(function_result, decision)
-        if decision.should_halt:
-            self._set_tool_guardrail_halt(decision)
-        return function_result
-
-    def _guardrail_block_result(self, decision: ToolGuardrailDecision) -> str:
-        self._set_tool_guardrail_halt(decision)
-        return toolguard_synthetic_result(decision)
-
     def _execute_tool_calls(self, assistant_message, messages: list, effective_task_id: str, api_call_count: int = 0) -> None:
         """Execute tool calls from the assistant message and append results to messages.
 
@@ -9288,8 +9150,7 @@ class AIAgent:
         )
 
     def _invoke_tool(self, function_name: str, function_args: dict, effective_task_id: str,
-                     tool_call_id: Optional[str] = None, messages: list = None,
-                     pre_tool_block_checked: bool = False) -> str:
+                     tool_call_id: Optional[str] = None, messages: list = None) -> str:
         """Invoke a single tool and return the result string. No display logic.
 
         Handles both agent-level tools (todo, memory, etc.) and registry-dispatched
@@ -9298,14 +9159,13 @@ class AIAgent:
         """
         # Check plugin hooks for a block directive before executing anything.
         block_message: Optional[str] = None
-        if not pre_tool_block_checked:
-            try:
-                from hermes_cli.plugins import get_pre_tool_call_block_message
-                block_message = get_pre_tool_call_block_message(
-                    function_name, function_args, task_id=effective_task_id or "",
-                )
-            except Exception:
-                pass
+        try:
+            from hermes_cli.plugins import get_pre_tool_call_block_message
+            block_message = get_pre_tool_call_block_message(
+                function_name, function_args, task_id=effective_task_id or "",
+            )
+        except Exception:
+            pass
         if block_message is not None:
             return json.dumps({"error": block_message}, ensure_ascii=False)
 
@@ -9457,31 +9317,13 @@ class AIAgent:
                 except Exception:
                     pass
 
-            block_result = None
-            blocked_by_guardrail = False
-            try:
-                from hermes_cli.plugins import get_pre_tool_call_block_message
-                block_message = get_pre_tool_call_block_message(
-                    function_name, function_args, task_id=effective_task_id or "",
-                )
-            except Exception:
-                block_message = None
-
-            if block_message is not None:
-                block_result = json.dumps({"error": block_message}, ensure_ascii=False)
-            else:
-                guardrail_decision = self._tool_guardrails.before_call(function_name, function_args)
-                if not guardrail_decision.allows_execution:
-                    block_result = self._guardrail_block_result(guardrail_decision)
-                    blocked_by_guardrail = True
-
-            parsed_calls.append((tool_call, function_name, function_args, block_result, blocked_by_guardrail))
+            parsed_calls.append((tool_call, function_name, function_args))
 
         # ── Logging / callbacks ──────────────────────────────────────────
-        tool_names_str = ", ".join(name for _, name, _, _, _ in parsed_calls)
+        tool_names_str = ", ".join(name for _, name, _ in parsed_calls)
         if not self.quiet_mode:
             print(f"  ⚡ Concurrent: {num_tools} tool calls — {tool_names_str}")
-            for i, (tc, name, args, block_result, blocked_by_guardrail) in enumerate(parsed_calls, 1):
+            for i, (tc, name, args) in enumerate(parsed_calls, 1):
                 args_str = json.dumps(args, ensure_ascii=False)
                 if self.verbose_logging:
                     print(f"  📞 Tool {i}: {name}({list(args.keys())})")
@@ -9490,9 +9332,7 @@ class AIAgent:
                     args_preview = args_str[:self.log_prefix_chars] + "..." if len(args_str) > self.log_prefix_chars else args_str
                     print(f"  📞 Tool {i}: {name}({list(args.keys())}) - {args_preview}")
 
-        for tc, name, args, block_result, blocked_by_guardrail in parsed_calls:
-            if block_result is not None:
-                continue
+        for tc, name, args in parsed_calls:
             if self.tool_progress_callback:
                 try:
                     preview = _build_tool_preview(name, args)
@@ -9500,9 +9340,7 @@ class AIAgent:
                 except Exception as cb_err:
                     logging.debug(f"Tool progress callback error: {cb_err}")
 
-        for tc, name, args, block_result, blocked_by_guardrail in parsed_calls:
-            if block_result is not None:
-                continue
+        for tc, name, args in parsed_calls:
             if self.tool_start_callback:
                 try:
                     self.tool_start_callback(tc.id, name, args)
@@ -9510,11 +9348,8 @@ class AIAgent:
                     logging.debug(f"Tool start callback error: {cb_err}")
 
         # ── Concurrent execution ─────────────────────────────────────────
-        # Each slot holds (function_name, function_args, function_result, duration, error_flag, blocked_flag)
+        # Each slot holds (function_name, function_args, function_result, duration, error_flag)
         results = [None] * num_tools
-        for i, (tc, name, args, block_result, blocked_by_guardrail) in enumerate(parsed_calls):
-            if block_result is not None:
-                results[i] = (name, args, block_result, 0.0, True, True)
 
         # Touch activity before launching workers so the gateway knows
         # we're executing tools (not stuck).
@@ -9569,14 +9404,7 @@ class AIAgent:
                     pass
             start = time.time()
             try:
-                result = self._invoke_tool(
-                    function_name,
-                    function_args,
-                    effective_task_id,
-                    tool_call.id,
-                    messages=messages,
-                    pre_tool_block_checked=True,
-                )
+                result = self._invoke_tool(function_name, function_args, effective_task_id, tool_call.id, messages=messages)
             except Exception as tool_error:
                 result = f"Error executing tool '{function_name}': {tool_error}"
                 logger.error("_invoke_tool raised for %s: %s", function_name, tool_error, exc_info=True)
@@ -9586,7 +9414,7 @@ class AIAgent:
                 logger.info("tool %s failed (%.2fs): %s", function_name, duration, result[:200])
             else:
                 logger.info("tool %s completed (%.2fs, %d chars)", function_name, duration, len(result))
-            results[index] = (function_name, function_args, result, duration, is_error, False)
+            results[index] = (function_name, function_args, result, duration, is_error)
             # Tear down worker-tid tracking.  Clear any interrupt bit we may
             # have set so the next task scheduled onto this recycled tid
             # starts with a clean slate.
@@ -9612,67 +9440,61 @@ class AIAgent:
             spinner.start()
 
         try:
-            runnable_calls = [
-                (i, tc, name, args)
-                for i, (tc, name, args, block_result, blocked_by_guardrail) in enumerate(parsed_calls)
-                if block_result is None
-            ]
-            futures = []
-            if runnable_calls:
-                max_workers = min(len(runnable_calls), _MAX_TOOL_WORKERS)
-                with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
-                    for i, tc, name, args in runnable_calls:
-                        # Propagate ContextVars (e.g. _approval_session_key); mirrors asyncio.to_thread.
-                        ctx = contextvars.copy_context()
-                        f = executor.submit(ctx.run, _run_tool, i, tc, name, args)
-                        futures.append(f)
+            max_workers = min(num_tools, _MAX_TOOL_WORKERS)
+            with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
+                futures = []
+                for i, (tc, name, args) in enumerate(parsed_calls):
+                    # Propagate ContextVars (e.g. _approval_session_key); mirrors asyncio.to_thread.
+                    ctx = contextvars.copy_context()
+                    f = executor.submit(ctx.run, _run_tool, i, tc, name, args)
+                    futures.append(f)
 
-                    # Wait for all to complete with periodic heartbeats so the
-                    # gateway's inactivity monitor doesn't kill us during long
-                    # concurrent tool batches. Also check for user interrupts
-                    # so we don't block indefinitely when the user sends /stop
-                    # or a new message during concurrent tool execution.
-                    _conc_start = time.time()
-                    _interrupt_logged = False
-                    while True:
-                        done, not_done = concurrent.futures.wait(
-                            futures, timeout=5.0,
-                        )
-                        if not not_done:
-                            break
+                # Wait for all to complete with periodic heartbeats so the
+                # gateway's inactivity monitor doesn't kill us during long
+                # concurrent tool batches.  Also check for user interrupts
+                # so we don't block indefinitely when the user sends /stop
+                # or a new message during concurrent tool execution.
+                _conc_start = time.time()
+                _interrupt_logged = False
+                while True:
+                    done, not_done = concurrent.futures.wait(
+                        futures, timeout=5.0,
+                    )
+                    if not not_done:
+                        break
 
-                        # Check for interrupt — the per-thread interrupt signal
-                        # already causes individual tools (terminal, execute_code)
-                        # to abort, but tools without interrupt checks (web_search,
-                        # read_file) will run to completion. Cancel any futures
-                        # that haven't started yet so we don't block on them.
-                        if self._interrupt_requested:
-                            if not _interrupt_logged:
-                                _interrupt_logged = True
-                                self._vprint(
-                                    f"{self.log_prefix}⚡ Interrupt: cancelling "
-                                    f"{len(not_done)} pending concurrent tool(s)",
-                                    force=True,
-                                )
-                            for f in not_done:
-                                f.cancel()
-                            # Give already-running tools a moment to notice the
-                            # per-thread interrupt signal and exit gracefully.
-                            concurrent.futures.wait(not_done, timeout=3.0)
-                            break
-
-                        _conc_elapsed = int(time.time() - _conc_start)
-                        # Heartbeat every ~30s (6 × 5s poll intervals)
-                        if _conc_elapsed > 0 and _conc_elapsed % 30 < 6:
-                            _still_running = [
-                                parsed_calls[futures.index(f)][1]
-                                for f in not_done
-                                if f in futures
-                            ]
-                            self._touch_activity(
-                                f"concurrent tools running ({_conc_elapsed}s, "
-                                f"{len(not_done)} remaining: {', '.join(_still_running[:3])})"
+                    # Check for interrupt — the per-thread interrupt signal
+                    # already causes individual tools (terminal, execute_code)
+                    # to abort, but tools without interrupt checks (web_search,
+                    # read_file) will run to completion.  Cancel any futures
+                    # that haven't started yet so we don't block on them.
+                    if self._interrupt_requested:
+                        if not _interrupt_logged:
+                            _interrupt_logged = True
+                            self._vprint(
+                                f"{self.log_prefix}⚡ Interrupt: cancelling "
+                                f"{len(not_done)} pending concurrent tool(s)",
+                                force=True,
                             )
+                        for f in not_done:
+                            f.cancel()
+                        # Give already-running tools a moment to notice the
+                        # per-thread interrupt signal and exit gracefully.
+                        concurrent.futures.wait(not_done, timeout=3.0)
+                        break
+
+                    _conc_elapsed = int(time.time() - _conc_start)
+                    # Heartbeat every ~30s (6 × 5s poll intervals)
+                    if _conc_elapsed > 0 and _conc_elapsed % 30 < 6:
+                        _still_running = [
+                            parsed_calls[futures.index(f)][1]
+                            for f in not_done
+                            if f in futures
+                        ]
+                        self._touch_activity(
+                            f"concurrent tools running ({_conc_elapsed}s, "
+                            f"{len(not_done)} remaining: {', '.join(_still_running[:3])})"
+                        )
         finally:
             if spinner:
                 # Build a summary message for the spinner stop
@@ -9681,9 +9503,8 @@ class AIAgent:
                 spinner.stop(f"⚡ {completed}/{num_tools} tools completed in {total_dur:.1f}s total")
 
         # ── Post-execution: display per-tool results ─────────────────────
-        for i, (tc, name, args, block_result, blocked_by_guardrail) in enumerate(parsed_calls):
+        for i, (tc, name, args) in enumerate(parsed_calls):
             r = results[i]
-            blocked = False
             if r is None:
                 # Tool was cancelled (interrupt) or thread didn't return
                 if self._interrupt_requested:
@@ -9692,21 +9513,13 @@ class AIAgent:
                     function_result = f"Error executing tool '{name}': thread did not return a result"
                 tool_duration = 0.0
             else:
-                function_name, function_args, function_result, tool_duration, is_error, blocked = r
-
-                if not blocked:
-                    function_result = self._append_guardrail_observation(
-                        function_name,
-                        function_args,
-                        function_result,
-                        failed=is_error,
-                    )
+                function_name, function_args, function_result, tool_duration, is_error = r
 
                 if is_error:
                     result_preview = function_result[:200] if len(function_result) > 200 else function_result
                     logger.warning("Tool %s returned error (%.2fs): %s", function_name, tool_duration, result_preview)
 
-                if not blocked and self.tool_progress_callback:
+                if self.tool_progress_callback:
                     try:
                         self.tool_progress_callback(
                             "tool.completed", function_name, None, None,
@@ -9734,7 +9547,7 @@ class AIAgent:
             self._current_tool = None
             self._touch_activity(f"tool completed: {name} ({tool_duration:.1f}s)")
 
-            if not blocked and self.tool_complete_callback:
+            if self.tool_complete_callback:
                 try:
                     self.tool_complete_callback(tc.id, name, args, function_result)
                 except Exception as cb_err:
@@ -9816,17 +9629,9 @@ class AIAgent:
             except Exception:
                 pass
 
-            _guardrail_block_decision: ToolGuardrailDecision | None = None
-            if _block_msg is None:
-                guardrail_decision = self._tool_guardrails.before_call(function_name, function_args)
-                if not guardrail_decision.allows_execution:
-                    _guardrail_block_decision = guardrail_decision
-
-            _execution_blocked = _block_msg is not None or _guardrail_block_decision is not None
-
-            if _execution_blocked:
-                # Tool blocked by plugin or guardrail policy — skip counters,
-                # callbacks, checkpointing, activity mutation, and real execution.
+            if _block_msg is not None:
+                # Tool blocked by plugin policy — skip counter resets.
+                # Execution is handled below in the tool dispatch chain.
                 pass
             else:
                 # Reset nudge counters when the relevant tool is actually used
@@ -9844,35 +9649,35 @@ class AIAgent:
                     args_preview = args_str[:self.log_prefix_chars] + "..." if len(args_str) > self.log_prefix_chars else args_str
                     print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())}) - {args_preview}")
 
-            if not _execution_blocked:
+            if _block_msg is None:
                 self._current_tool = function_name
                 self._touch_activity(f"executing tool: {function_name}")
 
             # Set activity callback for long-running tool execution (terminal
             # commands, etc.) so the gateway's inactivity monitor doesn't kill
             # the agent while a command is running.
-            if not _execution_blocked:
+            if _block_msg is None:
                 try:
                     from tools.environments.base import set_activity_callback
                     set_activity_callback(self._touch_activity)
                 except Exception:
                     pass
 
-            if not _execution_blocked and self.tool_progress_callback:
+            if _block_msg is None and self.tool_progress_callback:
                 try:
                     preview = _build_tool_preview(function_name, function_args)
                     self.tool_progress_callback("tool.started", function_name, preview, function_args)
                 except Exception as cb_err:
                     logging.debug(f"Tool progress callback error: {cb_err}")
 
-            if not _execution_blocked and self.tool_start_callback:
+            if _block_msg is None and self.tool_start_callback:
                 try:
                     self.tool_start_callback(tool_call.id, function_name, function_args)
                 except Exception as cb_err:
                     logging.debug(f"Tool start callback error: {cb_err}")
 
             # Checkpoint: snapshot working dir before file-mutating tools
-            if not _execution_blocked and function_name in ("write_file", "patch") and self._checkpoint_mgr.enabled:
+            if _block_msg is None and function_name in ("write_file", "patch") and self._checkpoint_mgr.enabled:
                 try:
                     file_path = function_args.get("path", "")
                     if file_path:
@@ -9884,7 +9689,7 @@ class AIAgent:
                     pass  # never block tool execution
 
             # Checkpoint before destructive terminal commands
-            if not _execution_blocked and function_name == "terminal" and self._checkpoint_mgr.enabled:
+            if _block_msg is None and function_name == "terminal" and self._checkpoint_mgr.enabled:
                 try:
                     cmd = function_args.get("command", "")
                     if _is_destructive_command(cmd):
@@ -9901,11 +9706,6 @@ class AIAgent:
                 # Tool blocked by plugin policy — return error without executing.
                 function_result = json.dumps({"error": _block_msg}, ensure_ascii=False)
                 tool_duration = 0.0
-            elif _guardrail_block_decision is not None:
-                # Tool blocked by tool-loop guardrail — synthesize exactly one
-                # tool result for the original tool_call_id without executing.
-                function_result = self._guardrail_block_result(_guardrail_block_decision)
-                tool_duration = 0.0
             elif function_name == "todo":
                 from tools.todo_tool import todo_tool as _todo_tool
                 function_result = _todo_tool(
@@ -10089,22 +9889,12 @@ class AIAgent:
             # Log tool errors to the persistent error log so [error] tags
             # in the UI always have a corresponding detailed entry on disk.
             _is_error_result, _ = _detect_tool_failure(function_name, function_result)
-            if not _execution_blocked:
-                function_result = self._append_guardrail_observation(
-                    function_name,
-                    function_args,
-                    function_result,
-                    failed=_is_error_result,
-                )
-                result_preview = function_result if self.verbose_logging else (
-                    function_result[:200] if len(function_result) > 200 else function_result
-                )
             if _is_error_result:
                 logger.warning("Tool %s returned error (%.2fs): %s", function_name, tool_duration, result_preview)
             else:
                 logger.info("tool %s completed (%.2fs, %d chars)", function_name, tool_duration, len(function_result))
 
-            if not _execution_blocked and self.tool_progress_callback:
+            if self.tool_progress_callback:
                 try:
                     self.tool_progress_callback(
                         "tool.completed", function_name, None, None,
@@ -10120,7 +9910,7 @@ class AIAgent:
                 logging.debug(f"Tool {function_name} completed in {tool_duration:.2f}s")
                 logging.debug(f"Tool result ({len(function_result)} chars): {function_result}")
 
-            if not _execution_blocked and self.tool_complete_callback:
+            if self.tool_complete_callback:
                 try:
                     self.tool_complete_callback(tool_call.id, function_name, function_args, function_result)
                 except Exception as cb_err:
@@ -10223,13 +10013,6 @@ class AIAgent:
                 for idx, pfm in enumerate(self.prefill_messages):
                     api_messages.insert(sys_offset + idx, pfm.copy())
 
-            # Same safety net as the main loop: repair tool-call/result
-            # pairing before asking for a final summary.  Compression and
-            # session resume can leave a tool result whose parent assistant
-            # tool_call was summarized away; Responses API rejects that as
-            # "No tool call found for function call output".
-            api_messages = self._sanitize_api_messages(api_messages)
-
             # Same safety net as the main loop: drop thinking-only assistant
             # turns so Anthropic-family providers don't 400 the summary call.
             api_messages = self._drop_thinking_only_and_merge_users(api_messages)
@@ -10411,8 +10194,6 @@ class AIAgent:
         # Installed once, transparent when streams are healthy, prevents crash on write.
         _install_safe_stdio()
 
-        self._ensure_db_session()
-
         # Tag all log records on this thread with the session ID so
         # ``hermes logs --session <id>`` can filter a single conversation.
         from hermes_logging import set_session_context
@@ -10456,8 +10237,6 @@ class AIAgent:
         self._last_content_tools_all_housekeeping = False
         self._mute_post_response = False
         self._unicode_sanitization_passes = 0
-        self._tool_guardrails.reset_for_turn()
-        self._tool_guardrail_halt_decision = None
 
         # Pre-turn connection health check: detect and clean up dead TCP
         # connections left over from provider outages or dropped streams.
@@ -13255,16 +13034,6 @@ class AIAgent:
 
                     self._execute_tool_calls(assistant_message, messages, effective_task_id, api_call_count)
 
-                    if self._tool_guardrail_halt_decision is not None:
-                        decision = self._tool_guardrail_halt_decision
-                        _turn_exit_reason = "guardrail_halt"
-                        final_response = self._toolguard_controlled_halt_response(decision)
-                        self._emit_status(
-                            f"⚠️ Tool guardrail halted {decision.tool_name}: {decision.code}"
-                        )
-                        messages.append({"role": "assistant", "content": final_response})
-                        break
-
                     # Reset per-turn retry counters after successful tool
                     # execution so a single truncation doesn't poison the
                     # entire conversation.
@@ -13308,13 +13077,7 @@ class AIAgent:
                         # causing premature compression.  (#12026)
                         _real_tokens = _compressor.last_prompt_tokens
                     else:
-                        # Include tool schemas — with 50+ tools enabled
-                        # these add 20-30K tokens the messages-only
-                        # estimate misses, which can skip compression
-                        # past the configured threshold (#14695).
-                        _real_tokens = estimate_request_tokens_rough(
-                            messages, tools=self.tools or None
-                        )
+                        _real_tokens = estimate_messages_tokens_rough(messages)
 
                     if self.compression_enabled and _compressor.should_compress(_real_tokens):
                         self._safe_print("  ⟳ compacting context…")
@@ -13797,7 +13560,6 @@ class AIAgent:
             "messages": messages,
             "api_calls": api_call_count,
             "completed": completed,
-            "turn_exit_reason": _turn_exit_reason,
             "partial": False,  # True only when stopped due to invalid tool calls
             "interrupted": interrupted,
             "response_previewed": getattr(self, "_response_was_previewed", False),
@@ -13817,8 +13579,6 @@ class AIAgent:
             "cost_status": self.session_cost_status,
             "cost_source": self.session_cost_source,
         }
-        if self._tool_guardrail_halt_decision is not None:
-            result["guardrail"] = self._tool_guardrail_halt_decision.to_metadata()
         # If a /steer landed after the final assistant turn (no more tool
         # batches to drain into), hand it back to the caller so it can be
         # delivered as the next user turn instead of being silently lost.

scripts/profile-tui.py

@@ -35,18 +35,10 @@ import time
 from pathlib import Path
 from typing import Any
 
-_PROJECT_ROOT = Path(__file__).resolve().parent.parent
-sys.path.insert(0, str(_PROJECT_ROOT))
-try:
-    from hermes_constants import get_hermes_home
-except ImportError:
-    def get_hermes_home() -> Path:  # type: ignore[misc]
-        val = (os.environ.get("HERMES_HOME") or "").strip()
-        return Path(val) if val else Path.home() / ".hermes"
 
 DEFAULT_TUI_DIR = Path(os.environ.get("HERMES_TUI_DIR", "/home/bb/hermes-agent/ui-tui"))
-DEFAULT_LOG = Path(os.environ.get("HERMES_PERF_LOG", str(get_hermes_home() / "perf.log")))
-DEFAULT_STATE_DB = get_hermes_home() / "state.db"
+DEFAULT_LOG = Path(os.environ.get("HERMES_PERF_LOG", str(Path.home() / ".hermes" / "perf.log")))
+DEFAULT_STATE_DB = Path.home() / ".hermes" / "state.db"
 
 # Keystroke escape sequences.  Matches what xterm/VT220 send when the
 # terminal has bracketed-paste disabled and the key-repeat handler fires.

scripts/release.py

@@ -41,18 +41,13 @@ PYPROJECT_FILE = REPO_ROOT / "pyproject.toml"
 AUTHOR_MAP = {
     # teknium (multiple emails)
     "teknium1@gmail.com": "teknium1",
-    "m@mobrienv.dev": "mikeyobrien",
     "qiyin.zuo@pcitc.com": "qiyin-code",
     "leone.parise@gmail.com": "leoneparise",
     "teknium@nousresearch.com": "teknium1",
     "127238744+teknium1@users.noreply.github.com": "teknium1",
-    "159539633+MottledShadow@users.noreply.github.com": "MottledShadow",
-    "aludwin+gh@gmail.com": "adamludwin",
     "2093036+exiao@users.noreply.github.com": "exiao",
     "rylen.anil@gmail.com": "rylena",
-    "godnanijatin@gmail.com": "jatingodnani",
     "14046872+tmimmanuel@users.noreply.github.com": "tmimmanuel",
-    "657290301@qq.com": "IMHaoyan",
     "revar@users.noreply.github.com": "revaraver",
     # Matrix parity salvage batch (April 2026)
     "sr@samirusani": "samrusani",
@@ -81,13 +76,6 @@ AUTHOR_MAP = {
     "thomasjhon6666@gmail.com": "ThomassJonax",
     "focusflow.app.help@gmail.com": "yes999zc",
     "rob@atlas.lan": "rmoen",
-    # Slack ephemeral slash-ack salvage (May 2026)
-    "probepark@users.noreply.github.com": "probepark",
-    # Slack batch salvage (May 2026)
-    "280484231+prive-fe-bot@users.noreply.github.com": "priveperfumes",
-    "amr@ghanem.sa": "amroessam",
-    "paperlantern.agent@gmail.com": "Hinotoi-agent",
-    "valda@underscore.jp": "valda",
     "162235745+0z1-ghb@users.noreply.github.com": "0z1-ghb",
     "yes999zc@163.com": "yes999zc",
     "343873859@qq.com": "DrStrangerUJN",
@@ -104,8 +92,6 @@ AUTHOR_MAP = {
     "130918800+devorun@users.noreply.github.com": "devorun",
     "surat.s@itm.kmutnb.ac.th": "beesrsj2500",
     "beesr@bee.localdomain": "beesrsj2500",
-    "mind-dragon@nous.research": "Mind-Dragon",
-    "juntingpublic@gmail.com": "JustinUssuri",
     "mtf201013@gmail.com": "ma-pony",
     "sonoyuncudmr@gmail.com": "Sonoyunchu",
     "43525405+yatesjalex@users.noreply.github.com": "yatesjalex",
@@ -114,8 +100,6 @@ AUTHOR_MAP = {
     "web3blind@users.noreply.github.com": "web3blind",
     "julia@alexland.us": "alexg0bot",
     "christian@scheid.tech": "scheidti",
-    # Moonshot schema anyOf+enum salvage (May 2026)
-    "git@local.invalid": "hendrixfreire",
     "1060770+benjaminsehl@users.noreply.github.com": "benjaminsehl",
     "nerijusn76@gmail.com": "Nerijusas",
     "itonov@proton.me": "Ito-69",
@@ -128,7 +112,6 @@ AUTHOR_MAP = {
     "foxion37@gmail.com": "foxion37",
     "bloodcarter@gmail.com": "bloodcarter",
     "scott@scotttrinh.com": "scotttrinh",
-    "quocanh261997@gmail.com": "quocanh261997",
     # contributors (from noreply pattern)
     "david.vv@icloud.com": "davidvv",
     "wangqiang@wangqiangdeMac-mini.local": "xiaoqiang243",
@@ -184,7 +167,6 @@ AUTHOR_MAP = {
     "sir_even@icloud.com": "sirEven",
     "36056348+sirEven@users.noreply.github.com": "sirEven",
     "70424851+insecurejezza@users.noreply.github.com": "insecurejezza",
-    "jezzahehn@gmail.com": "JezzaHehn",
     "254021826+dodo-reach@users.noreply.github.com": "dodo-reach",
     "259807879+Bartok9@users.noreply.github.com": "Bartok9",
     "270082434+crayfish-ai@users.noreply.github.com": "crayfish-ai",
@@ -310,7 +292,6 @@ AUTHOR_MAP = {
     "154585401+LeonSGP43@users.noreply.github.com": "LeonSGP43",
     "12250313+Kailigithub@users.noreply.github.com": "Kailigithub",
     "mgparkprint@gmail.com": "vlwkaos",
-    "1317078257maroon@gmail.com": "Oxidane-bot",
     "tranquil_flow@protonmail.com": "Tranquil-Flow",
     "LyleLengyel@gmail.com": "mcndjxlefnd",
     "wangshengyang2004@163.com": "Wangshengyang2004",
@@ -349,7 +330,6 @@ AUTHOR_MAP = {
     "stefan@dimagents.ai": "dimitrovi",
     "hermes@noushq.ai": "benbarclay",
     "chinmingcock@gmail.com": "ChimingLiu",
-    "allard.quek@singtel.com": "AllardQuek",
     "openclaw@sparklab.ai": "openclaw",
     "semihcvlk53@gmail.com": "Himess",
     "erenkar950@gmail.com": "erenkarakus",
@@ -371,10 +351,6 @@ AUTHOR_MAP = {
     "xowiekk@gmail.com": "Xowiek",
     "1243352777@qq.com": "zons-zhaozhy",
     "e.silacandmr@gmail.com": "Es1la",
-    "h3057183414@gmail.com": "CoreyNoDream",
-    "franksong2702@gmail.com": "franksong2702",
-    "673088860@qq.com": "ambition0802",
-    "beibei1988@proton.me": "beibi9966",
     # ── bulk addition: 75 emails resolved via API, PR salvage bodies, noreply
     #    crossref, and GH contributor list matching (April 2026 audit) ──
     "1115117931@qq.com": "aaronagent",
@@ -446,8 +422,6 @@ AUTHOR_MAP = {
     "ogzerber@users.noreply.github.com": "ogzerber",
     "cola-runner@users.noreply.github.com": "cola-runner",
     "ygd58@users.noreply.github.com": "ygd58",
-    "45554392+warabe1122@users.noreply.github.com": "warabe1122",
-    "187001140+willy-scr@users.noreply.github.com": "willy-scr",
     "vominh1919@users.noreply.github.com": "vominh1919",
     "iamagenius00@users.noreply.github.com": "iamagenius00",
     "9219265+cresslank@users.noreply.github.com": "cresslank",
@@ -472,7 +446,6 @@ AUTHOR_MAP = {
     "taosiyuan163@153.com": "taosiyuan163",
     "tesseracttars@gmail.com": "tesseracttars-creator",
     "tianliangjay@gmail.com": "xingkongliang",
-    "1317078257maroon@gmail.com": "Oxidane-bot",
     "tranquil_flow@protonmail.com": "Tranquil-Flow",
     "LyleLengyel@gmail.com": "mcndjxlefnd",
     "unayung@gmail.com": "Unayung",
@@ -518,11 +491,9 @@ AUTHOR_MAP = {
     "hubin_ll@qq.com": "LLQWQ",
     "memosr_email@gmail.com": "memosr",
     "jperlow@gmail.com": "perlowja",
-    "jasonpette1783@gmail.com": "web-dev0521",
     "tangyuanjc@JCdeAIfenshendeMac-mini.local": "tangyuanjc",
     "harryplusplus@gmail.com": "harryplusplus",
     "anthhub@163.com": "anthhub",
-    "allard.quek@singtel.com": "AllardQuek",
     "shenuu@gmail.com": "shenuu",
     "xiayh17@gmail.com": "xiayh0107",
     "zhujianxyz@gmail.com": "opriz",
@@ -673,7 +644,6 @@ AUTHOR_MAP = {
     "web3blind@gmail.com": "web3blind",
     "ztzheng@163.com": "chengoak",  # PR #17467
     "24110240104@m.fudan.edu.cn": "YuShu",  # co-author only
-    "simantak@mac.local": "simantak-dabhade",  # PR #6329
 }
 
 

tests/acp/test_mcp_e2e.py

@@ -178,10 +178,9 @@ class TestMcpRegistrationE2E:
         complete_event = completions[0]
         assert isinstance(complete_event, ToolCallProgress)
         assert complete_event.status == "completed"
-        # Completion should contain human-readable output rather than forcing raw JSON panes.
-        assert complete_event.content
-        assert "hello" in complete_event.content[0].content.text
-        assert complete_event.raw_output is None
+        # rawOutput should contain the tool result string
+        assert complete_event.raw_output is not None
+        assert "hello" in str(complete_event.raw_output)
 
     def test_patch_mode_tool_start_emits_diff_blocks_for_v4a_patch(self):
         update = build_tool_start(

tests/acp/test_server.py

@@ -27,10 +27,7 @@ from acp.schema import (
     SetSessionModeResponse,
     SessionInfo,
     TextContentBlock,
-    ToolCallProgress,
-    ToolCallStart,
     Usage,
-    UsageUpdate,
     UserMessageChunk,
 )
 from acp_adapter.server import HermesACPAgent, HERMES_VERSION
@@ -203,8 +200,6 @@ class TestSessionOps:
             "context",
             "reset",
             "compact",
-            "steer",
-            "queue",
             "version",
         ]
         model_cmd = next(
@@ -213,46 +208,6 @@ class TestSessionOps:
         assert model_cmd.input is not None
         assert model_cmd.input.root.hint == "model name to switch to"
 
-    def test_build_usage_update_for_zed_context_indicator(self, agent, mock_manager):
-        state = mock_manager.create_session(cwd="/tmp")
-        state.history = [{"role": "user", "content": "hello"}]
-        state.agent.context_compressor = MagicMock(context_length=100_000)
-        state.agent._cached_system_prompt = "system"
-        state.agent.tools = [{"type": "function", "function": {"name": "demo"}}]
-
-        with patch(
-            "agent.model_metadata.estimate_request_tokens_rough",
-            return_value=25_000,
-        ):
-            update = agent._build_usage_update(state)
-
-        assert isinstance(update, UsageUpdate)
-        assert update.session_update == "usage_update"
-        assert update.size == 100_000
-        assert update.used == 25_000
-
-    @pytest.mark.asyncio
-    async def test_send_usage_update_to_client(self, agent, mock_manager):
-        state = mock_manager.create_session(cwd="/tmp")
-        state.agent.context_compressor = MagicMock(context_length=100_000)
-        mock_conn = MagicMock(spec=acp.Client)
-        mock_conn.session_update = AsyncMock()
-        agent._conn = mock_conn
-
-        with patch(
-            "agent.model_metadata.estimate_request_tokens_rough",
-            return_value=25_000,
-        ):
-            await agent._send_usage_update(state)
-
-        mock_conn.session_update.assert_awaited_once()
-        call = mock_conn.session_update.await_args
-        assert call.kwargs["session_id"] == state.session_id
-        update = call.kwargs["update"]
-        assert isinstance(update, UsageUpdate)
-        assert update.size == 100_000
-        assert update.used == 25_000
-
     @pytest.mark.asyncio
     async def test_cancel_sets_event(self, agent):
         resp = await agent.new_session(cwd=".")
@@ -283,31 +238,11 @@ class TestSessionOps:
             {"role": "system", "content": "hidden system"},
             {"role": "user", "content": "what controls the / slash commands?"},
             {"role": "assistant", "content": "HermesACPAgent._ADVERTISED_COMMANDS controls them."},
-            {
-                "role": "assistant",
-                "content": "",
-                "tool_calls": [
-                    {
-                        "id": "call_search_1",
-                        "type": "function",
-                        "function": {
-                            "name": "search_files",
-                            "arguments": '{"pattern":"slash commands","path":"."}',
-                        },
-                    }
-                ],
-            },
-            {
-                "role": "tool",
-                "tool_call_id": "call_search_1",
-                "content": '{"total_count":1,"matches":[{"path":"cli.py","line":42,"content":"slash commands"}]}',
-            },
+            {"role": "tool", "content": "tool output should not replay"},
         ]
 
         mock_conn.session_update.reset_mock()
         resp = await agent.load_session(cwd="/tmp", session_id=new_resp.session_id)
-        await asyncio.sleep(0)
-        await asyncio.sleep(0)
 
         assert isinstance(resp, LoadSessionResponse)
         calls = mock_conn.session_update.await_args_list
@@ -322,21 +257,6 @@ class TestSessionOps:
         assert isinstance(replay_calls[1].kwargs["update"], AgentMessageChunk)
         assert replay_calls[1].kwargs["update"].content.text.startswith("HermesACPAgent")
 
-        tool_updates = [
-            call.kwargs["update"]
-            for call in calls
-            if getattr(call.kwargs.get("update"), "session_update", None)
-            in {"tool_call", "tool_call_update"}
-        ]
-        assert len(tool_updates) == 2
-        assert isinstance(tool_updates[0], ToolCallStart)
-        assert tool_updates[0].tool_call_id == "call_search_1"
-        assert tool_updates[0].title == "search: slash commands"
-        assert isinstance(tool_updates[1], ToolCallProgress)
-        assert tool_updates[1].tool_call_id == "call_search_1"
-        assert "Search results" in tool_updates[1].content[0].content.text
-        assert "cli.py:42" in tool_updates[1].content[0].content.text
-
     @pytest.mark.asyncio
     async def test_resume_session_replays_persisted_history_to_client(self, agent):
         mock_conn = MagicMock(spec=acp.Client)
@@ -349,8 +269,6 @@ class TestSessionOps:
 
         mock_conn.session_update.reset_mock()
         resp = await agent.resume_session(cwd="/tmp", session_id=new_resp.session_id)
-        await asyncio.sleep(0)
-        await asyncio.sleep(0)
 
         assert isinstance(resp, ResumeSessionResponse)
         updates = [call.kwargs["update"] for call in mock_conn.session_update.await_args_list]
@@ -360,27 +278,6 @@ class TestSessionOps:
             for update in updates
         )
 
-    @pytest.mark.asyncio
-    async def test_load_session_schedules_history_replay_after_response(self, agent):
-        """Zed only attaches replayed updates after session/load has completed."""
-        new_resp = await agent.new_session(cwd="/tmp")
-        state = agent.session_manager.get_session(new_resp.session_id)
-        state.history = [{"role": "user", "content": "hello from history"}]
-        events = []
-
-        async def replay_after_response(_state):
-            events.append("replay")
-
-        with patch.object(agent, "_replay_session_history", side_effect=replay_after_response):
-            resp = await agent.load_session(cwd="/tmp", session_id=new_resp.session_id)
-            events.append("returned")
-
-        assert isinstance(resp, LoadSessionResponse)
-        assert events == ["returned"]
-        await asyncio.sleep(0)
-        await asyncio.sleep(0)
-        assert events == ["returned", "replay"]
-
     @pytest.mark.asyncio
     async def test_resume_session_creates_new_if_missing(self, agent):
         resume_resp = await agent.resume_session(cwd="/tmp", session_id="nonexistent")
@@ -625,11 +522,6 @@ class TestPrompt:
         assert isinstance(resp, PromptResponse)
         assert resp.stop_reason == "end_turn"
         state.agent.run_conversation.assert_called_once()
-        assert state.agent.tool_progress_callback is not None
-        assert state.agent.step_callback is not None
-        assert state.agent.stream_delta_callback is not None
-        assert state.agent.reasoning_callback is not None
-        assert state.agent.thinking_callback is None
 
     @pytest.mark.asyncio
     async def test_prompt_updates_history(self, agent):
@@ -673,40 +565,12 @@ class TestPrompt:
         prompt = [TextContentBlock(type="text", text="help me")]
         await agent.prompt(prompt=prompt, session_id=new_resp.session_id)
 
-        # session_update should include the final message (usage_update may follow it)
+        # session_update should have been called with the final message
         mock_conn.session_update.assert_called()
-        updates = [
-            call.kwargs.get("update") or call.args[1]
-            for call in mock_conn.session_update.call_args_list
-        ]
-        assert any(update.session_update == "agent_message_chunk" for update in updates)
-
-    @pytest.mark.asyncio
-    async def test_prompt_does_not_duplicate_streamed_final_message(self, agent):
-        """If ACP already streamed response chunks, final_response should not be sent again."""
-        new_resp = await agent.new_session(cwd=".")
-        state = agent.session_manager.get_session(new_resp.session_id)
-
-        def mock_run(*args, **kwargs):
-            state.agent.stream_delta_callback("streamed answer")
-            return {"final_response": "streamed answer", "messages": []}
-
-        state.agent.run_conversation = mock_run
-
-        mock_conn = MagicMock(spec=acp.Client)
-        mock_conn.session_update = AsyncMock()
-        agent._conn = mock_conn
-
-        prompt = [TextContentBlock(type="text", text="hello")]
-        await agent.prompt(prompt=prompt, session_id=new_resp.session_id)
-
-        updates = [
-            call.kwargs.get("update") or call.args[1]
-            for call in mock_conn.session_update.call_args_list
-        ]
-        agent_chunks = [update for update in updates if update.session_update == "agent_message_chunk"]
-        assert len(agent_chunks) == 1
-        assert agent_chunks[0].content.text == "streamed answer"
+        # Get the last call's update argument
+        last_call = mock_conn.session_update.call_args_list[-1]
+        update = last_call[1].get("update") or last_call[0][1]
+        assert update.session_update == "agent_message_chunk"
 
     @pytest.mark.asyncio
     async def test_prompt_auto_titles_session(self, agent):
@@ -844,43 +708,6 @@ class TestSlashCommands:
         assert "2 messages" in result
         assert "user: 1" in result
 
-    def test_context_shows_usage_and_compression_threshold(self, agent, mock_manager):
-        state = self._make_state(mock_manager)
-        state.history = [{"role": "user", "content": "hello"}]
-        state.agent.context_compressor = MagicMock(
-            context_length=100_000,
-            threshold_tokens=80_000,
-        )
-        state.agent._cached_system_prompt = "system"
-        state.agent.tools = [{"type": "function", "function": {"name": "demo"}}]
-
-        with patch(
-            "agent.model_metadata.estimate_request_tokens_rough",
-            return_value=25_000,
-        ):
-            result = agent._handle_slash_command("/context", state)
-
-        assert "Context usage: ~25,000 / 100,000 tokens (25.0%)" in result
-        assert "Compression: ~55,000 tokens until threshold (~80,000, 80%)" in result
-        assert "Tip: run /compact" in result
-
-    def test_context_says_compression_due_when_past_threshold(self, agent, mock_manager):
-        state = self._make_state(mock_manager)
-        state.history = [{"role": "user", "content": "hello"}]
-        state.agent.context_compressor = MagicMock(
-            context_length=100_000,
-            threshold_tokens=80_000,
-        )
-
-        with patch(
-            "agent.model_metadata.estimate_request_tokens_rough",
-            return_value=82_000,
-        ):
-            result = agent._handle_slash_command("/context", state)
-
-        assert "Context usage: ~82,000 / 100,000 tokens (82.0%)" in result
-        assert "Compression: due now (threshold ~80,000, 80%). Run /compact." in result
-
     def test_reset_clears_history(self, agent, mock_manager):
         state = self._make_state(mock_manager)
         state.history = [{"role": "user", "content": "hello"}]
@@ -903,7 +730,6 @@ class TestSlashCommands:
         ]
         state.agent.compression_enabled = True
         state.agent._cached_system_prompt = "system"
-        state.agent.tools = None
         original_session_db = object()
         state.agent._session_db = original_session_db
 
@@ -920,7 +746,7 @@ class TestSlashCommands:
         with (
             patch.object(agent.session_manager, "save_session") as mock_save,
             patch(
-                "agent.model_metadata.estimate_request_tokens_rough",
+                "agent.model_metadata.estimate_messages_tokens_rough",
                 side_effect=[40, 12],
             ),
         ):
@@ -960,12 +786,7 @@ class TestSlashCommands:
         resp = await agent.prompt(prompt=prompt, session_id=new_resp.session_id)
 
         assert resp.stop_reason == "end_turn"
-        updates = [
-            call.kwargs.get("update") or call.args[1]
-            for call in mock_conn.session_update.call_args_list
-        ]
-        assert any(update.session_update == "agent_message_chunk" for update in updates)
-        assert any(update.session_update == "usage_update" for update in updates)
+        mock_conn.session_update.assert_called_once()
 
     @pytest.mark.asyncio
     async def test_unknown_slash_falls_through_to_llm(self, agent, mock_manager):

tests/acp/test_session.py

@@ -8,7 +8,6 @@ from types import SimpleNamespace
 import pytest
 from unittest.mock import MagicMock, patch
 
-from acp_adapter import session as acp_session
 from acp_adapter.session import SessionManager, SessionState
 from hermes_state import SessionDB
 
@@ -43,27 +42,6 @@ class TestCreateSession:
         state = manager.create_session(cwd="/tmp/work")
         assert calls == [(state.session_id, "/tmp/work")]
 
-
-    def test_register_task_cwd_translates_windows_drive_for_wsl_tools(self, monkeypatch):
-        captured = {}
-
-        def fake_register_task_env_overrides(task_id, overrides):
-            captured["task_id"] = task_id
-            captured["overrides"] = overrides
-
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-        monkeypatch.setattr(
-            "tools.terminal_tool.register_task_env_overrides",
-            fake_register_task_env_overrides,
-        )
-
-        acp_session._register_task_cwd("session-1", r"E:\Projects\AI\paperclip")
-
-        assert captured == {
-            "task_id": "session-1",
-            "overrides": {"cwd": "/mnt/e/Projects/AI/paperclip"},
-        }
-
     def test_session_ids_are_unique(self, manager):
         s1 = manager.create_session()
         s2 = manager.create_session()
@@ -78,59 +56,6 @@ class TestCreateSession:
         assert manager.get_session("does-not-exist") is None
 
 
-
-
-# ---------------------------------------------------------------------------
-# WSL cwd translation
-# ---------------------------------------------------------------------------
-
-
-class TestWslCwdTranslation:
-    def test_translate_acp_cwd_converts_windows_drive_path_when_wsl(self, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-
-        assert acp_session._translate_acp_cwd(r"E:\Projects\AI\paperclip") == "/mnt/e/Projects/AI/paperclip"
-
-    def test_translate_acp_cwd_handles_forward_slashes_when_wsl(self, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-
-        assert acp_session._translate_acp_cwd("D:/work/project") == "/mnt/d/work/project"
-
-    def test_translate_acp_cwd_leaves_windows_drive_path_unchanged_off_wsl(self, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", False)
-
-        assert acp_session._translate_acp_cwd(r"E:\Projects\AI\paperclip") == r"E:\Projects\AI\paperclip"
-
-    def test_translate_acp_cwd_leaves_posix_path_unchanged_on_wsl(self, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-
-        assert acp_session._translate_acp_cwd("/mnt/e/Projects/AI/paperclip") == "/mnt/e/Projects/AI/paperclip"
-
-    def test_create_session_stores_translated_cwd_on_wsl(self, manager, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-
-        state = manager.create_session(cwd=r"E:\Projects\AI\paperclip")
-
-        assert state.cwd == "/mnt/e/Projects/AI/paperclip"
-
-    def test_fork_session_stores_translated_cwd_on_wsl(self, manager, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-        original = manager.create_session(cwd="/tmp/base")
-
-        forked = manager.fork_session(original.session_id, cwd=r"D:\work\project")
-
-        assert forked is not None
-        assert forked.cwd == "/mnt/d/work/project"
-
-    def test_update_cwd_stores_translated_cwd_on_wsl(self, manager, monkeypatch):
-        monkeypatch.setattr("hermes_constants._wsl_detected", True)
-        state = manager.create_session(cwd="/tmp/old")
-
-        updated = manager.update_cwd(state.session_id, cwd=r"C:\Users\foo\project")
-
-        assert updated is not None
-        assert updated.cwd == "/mnt/c/Users/foo/project"
-
 # ---------------------------------------------------------------------------
 # fork
 # ---------------------------------------------------------------------------

tests/acp/test_tools.py

@@ -52,12 +52,6 @@ class TestToolKindMap:
     def test_tool_kind_execute_code(self):
         assert get_tool_kind("execute_code") == "execute"
 
-    def test_tool_kind_todo(self):
-        assert get_tool_kind("todo") == "other"
-
-    def test_tool_kind_skill_view(self):
-        assert get_tool_kind("skill_view") == "read"
-
     def test_tool_kind_browser_navigate(self):
         assert get_tool_kind("browser_navigate") == "fetch"
 
@@ -116,25 +110,6 @@ class TestBuildToolTitle:
         title = build_tool_title("web_search", {"query": "python asyncio"})
         assert "python asyncio" in title
 
-    def test_skill_view_title_includes_skill_name(self):
-        title = build_tool_title("skill_view", {"name": "github-pitfalls"})
-        assert title == "skill view (github-pitfalls)"
-
-    def test_skill_view_title_includes_linked_file(self):
-        title = build_tool_title("skill_view", {"name": "github-pitfalls", "file_path": "references/api.md"})
-        assert title == "skill view (github-pitfalls/references/api.md)"
-
-    def test_execute_code_title_includes_first_code_line(self):
-        title = build_tool_title("execute_code", {"code": "\nfrom hermes_tools import terminal\nprint('done')"})
-        assert title == "python: from hermes_tools import terminal"
-
-    def test_skill_manage_title_includes_action_and_target(self):
-        title = build_tool_title(
-            "skill_manage",
-            {"action": "patch", "name": "hermes-agent-operations", "file_path": "references/acp.md"},
-        )
-        assert title == "skill patch: hermes-agent-operations/references/acp.md"
-
     def test_unknown_tool_uses_name(self):
         title = build_tool_title("some_new_tool", {"foo": "bar"})
         assert title == "some_new_tool"
@@ -189,23 +164,15 @@ class TestBuildToolStart:
         assert "ls -la /tmp" in text
 
     def test_build_tool_start_for_read_file(self):
-        """read_file start should stay compact; completion carries file contents."""
+        """read_file should include the path in content."""
         args = {"path": "/etc/hosts", "offset": 1, "limit": 50}
         result = build_tool_start("tc-3", "read_file", args)
         assert isinstance(result, ToolCallStart)
         assert result.kind == "read"
-        assert result.content is None
-        assert result.raw_input is None
-
-    def test_build_tool_start_for_web_extract_is_compact(self):
-        """web_extract start should stay compact; title identifies URLs."""
-        args = {"urls": ["https://example.com/docs"]}
-        result = build_tool_start("tc-web-start", "web_extract", args)
-        assert isinstance(result, ToolCallStart)
-        assert result.title == "extract: https://example.com/docs"
-        assert result.kind == "fetch"
-        assert result.content is None
-        assert result.raw_input is None
+        assert len(result.content) >= 1
+        content_item = result.content[0]
+        assert isinstance(content_item, ContentToolCallContent)
+        assert "/etc/hosts" in content_item.content.text
 
     def test_build_tool_start_for_search(self):
         """search_files should include pattern in content."""
@@ -214,48 +181,6 @@ class TestBuildToolStart:
         assert isinstance(result, ToolCallStart)
         assert result.kind == "search"
         assert "TODO" in result.content[0].content.text
-        assert result.raw_input is None
-
-    def test_build_tool_start_for_todo_is_human_readable(self):
-        args = {"todos": [{"id": "one", "content": "Fix ACP rendering", "status": "in_progress"}]}
-        result = build_tool_start("tc-todo", "todo", args)
-        assert result.title == "todo (1 item)"
-        assert "Fix ACP rendering" in result.content[0].content.text
-        assert result.raw_input is None
-
-    def test_build_tool_start_for_skill_view_is_human_readable(self):
-        result = build_tool_start("tc-skill", "skill_view", {"name": "github-pitfalls"})
-        assert result.title == "skill view (github-pitfalls)"
-        assert "github-pitfalls" in result.content[0].content.text
-        assert result.raw_input is None
-
-    def test_build_tool_start_for_execute_code_shows_code_preview(self):
-        result = build_tool_start("tc-code", "execute_code", {"code": "print('hello')"})
-        assert result.kind == "execute"
-        assert result.title == "python: print('hello')"
-        assert "```python" in result.content[0].content.text
-        assert "print('hello')" in result.content[0].content.text
-        assert result.raw_input is None
-
-    def test_build_tool_start_for_skill_manage_patch_shows_diff(self):
-        result = build_tool_start(
-            "tc-skill-manage",
-            "skill_manage",
-            {
-                "action": "patch",
-                "name": "hermes-agent-operations",
-                "file_path": "references/acp.md",
-                "old_string": "old advice",
-                "new_string": "new advice",
-            },
-        )
-        assert result.kind == "edit"
-        assert result.title == "skill patch: hermes-agent-operations/references/acp.md"
-        assert isinstance(result.content[0], FileEditToolCallContent)
-        assert result.content[0].path == "skills/hermes-agent-operations/references/acp.md"
-        assert result.content[0].old_text == "old advice"
-        assert result.content[0].new_text == "new advice"
-        assert result.raw_input is None
 
     def test_build_tool_start_generic_fallback(self):
         """Unknown tools should get a generic text representation."""
@@ -280,158 +205,6 @@ class TestBuildToolComplete:
         content_item = result.content[0]
         assert isinstance(content_item, ContentToolCallContent)
         assert "total 42" in content_item.content.text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_todo_is_checklist(self):
-        result = build_tool_complete(
-            "tc-todo",
-            "todo",
-            '{"todos":[{"id":"a","content":"Inspect ACP","status":"completed"},{"id":"b","content":"Patch renderers","status":"in_progress"}],"summary":{"total":2,"pending":0,"in_progress":1,"completed":1,"cancelled":0}}',
-        )
-        text = result.content[0].content.text
-        assert "✅ Inspect ACP" in text
-        assert "- 🔄 Patch renderers" in text
-        assert "**Progress:** 1 completed, 1 in progress, 0 pending" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_skill_view_summarizes_content_without_raw_json(self):
-        result = build_tool_complete(
-            "tc-skill",
-            "skill_view",
-            '{"success":true,"name":"github-pitfalls","description":"GitHub gotchas","content":"# GitHub Pitfalls\\nUse gh carefully.","path":"github/github-pitfalls/SKILL.md"}',
-        )
-        text = result.content[0].content.text
-        assert "**Skill loaded**" in text
-        assert "`github-pitfalls`" in text
-        assert "GitHub gotchas" in text
-        assert "GitHub Pitfalls" in text
-        assert "Use gh carefully" not in text
-        assert "Full skill content is available to the agent" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_execute_code_formats_output(self):
-        result = build_tool_complete("tc-code", "execute_code", '{"output":"hello\\n","exit_code":0}')
-        text = result.content[0].content.text
-        assert "Exit code: 0" in text
-        assert "hello" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_skill_manage_summarizes_without_raw_json(self):
-        result = build_tool_complete(
-            "tc-skill-manage",
-            "skill_manage",
-            '{"success":true,"message":"Patched references/hermes-acp-zed-rendering.md in skill \'hermes-agent-operations\' (1 replacement)."}',
-            function_args={
-                "action": "patch",
-                "name": "hermes-agent-operations",
-                "file_path": "references/hermes-acp-zed-rendering.md",
-            },
-        )
-        text = result.content[0].content.text
-        assert "**✅ Skill updated**" in text
-        assert "`patch`" in text
-        assert "`hermes-agent-operations`" in text
-        assert "references/hermes-acp-zed-rendering.md" in text
-        assert "{\"success\"" not in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_read_file_formats_content(self):
-        result = build_tool_complete(
-            "tc-read",
-            "read_file",
-            '{"content":"1|hello\\n2|world","total_lines":2}',
-            function_args={"path":"README.md","offset":1,"limit":20},
-        )
-        text = result.content[0].content.text
-        assert "Read README.md" in text
-        assert "```\n1|hello\n2|world\n```" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_search_files_formats_matches(self):
-        result = build_tool_complete(
-            "tc-search",
-            "search_files",
-            '{"total_count":2,"matches":[{"path":"README.md","line":3,"content":"TODO: fix this"},{"path":"src/app.py","line":9,"content":"needle"}],"truncated":true}\n\n[Hint: Results truncated. Use offset=12 to see more.]',
-        )
-        text = result.content[0].content.text
-        assert "Search results" in text
-        assert "Found 2 matches" in text
-        assert "README.md:3" in text
-        assert "TODO: fix this" in text
-        assert "Results truncated" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_process_list_formats_table(self):
-        result = build_tool_complete(
-            "tc-process",
-            "process",
-            '{"processes":[{"session_id":"p1","status":"running","pid":123,"command":"npm run dev"}]}',
-            function_args={"action":"list"},
-        )
-        text = result.content[0].content.text
-        assert "Processes: 1" in text
-        assert "`p1`" in text
-        assert "npm run dev" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_delegate_task_summarizes_children(self):
-        result = build_tool_complete(
-            "tc-delegate",
-            "delegate_task",
-            '{"results":[{"task_index":0,"status":"completed","summary":"Reviewed ACP rendering.","model":"gpt-5.5","duration_seconds":3.2,"tool_trace":[{"tool":"read_file"}]}],"total_duration_seconds":3.4}',
-        )
-        text = result.content[0].content.text
-        assert "Delegation results: 1 task" in text
-        assert "Reviewed ACP rendering" in text
-        assert "gpt-5.5" in text
-        assert "Tools: read_file" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_session_search_recent(self):
-        result = build_tool_complete(
-            "tc-session",
-            "session_search",
-            '{"success":true,"mode":"recent","results":[{"session_id":"s1","title":"ACP work","last_active":"2026-05-02","message_count":12,"preview":"Polished tool rendering."}],"count":1}',
-        )
-        text = result.content[0].content.text
-        assert "Recent sessions" in text
-        assert "ACP work" in text
-        assert "Polished tool rendering" in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_memory_avoids_dumping_entries(self):
-        result = build_tool_complete(
-            "tc-memory",
-            "memory",
-            '{"success":true,"target":"user","entries":["private long memory"],"usage":"1% — 19/2000 chars","entry_count":1,"message":"Entry added."}',
-            function_args={"action":"add","target":"user","content":"User likes concise ACP rendering."},
-        )
-        text = result.content[0].content.text
-        assert "Memory add saved" in text
-        assert "User likes concise ACP rendering" in text
-        assert "private long memory" not in text
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_web_extract_success_stays_compact(self):
-        result = build_tool_complete(
-            "tc-web-extract",
-            "web_extract",
-            '{"results":[{"url":"https://example.com","title":"Example","content":"# Intro\\nThis is extracted content."}]}',
-        )
-        assert result.content is None
-        assert result.raw_output is None
-
-    def test_build_tool_complete_for_web_extract_error_shows_error(self):
-        result = build_tool_complete(
-            "tc-web-extract-error",
-            "web_extract",
-            '{"results":[{"url":"https://example.com","title":"Example","error":"timeout"}]}',
-        )
-        text = result.content[0].content.text
-        assert "Web extract failed" in text
-        assert "https://example.com" in text
-        assert "timeout" in text
-        assert result.raw_output is None
 
     def test_build_tool_complete_truncates_large_output(self):
         """Very large outputs should be truncated."""

tests/acp_adapter/test_acp_commands.py

@@ -1,150 +0,0 @@
-from types import SimpleNamespace
-
-import pytest
-from acp.schema import TextContentBlock
-
-from acp_adapter.server import HermesACPAgent
-from acp_adapter.session import SessionManager
-
-
-class FakeAgent:
-    def __init__(self):
-        self.model = "fake-model"
-        self.provider = "fake-provider"
-        self.enabled_toolsets = ["hermes-acp"]
-        self.disabled_toolsets = []
-        self.tools = []
-        self.valid_tool_names = set()
-        self.steers = []
-        self.runs = []
-
-    def steer(self, text):
-        self.steers.append(text)
-        return True
-
-    def run_conversation(self, *, user_message, conversation_history, task_id, **kwargs):
-        self.runs.append(user_message)
-        messages = list(conversation_history or [])
-        messages.append({"role": "user", "content": user_message})
-        final = f"ran: {user_message}"
-        messages.append({"role": "assistant", "content": final})
-        return {"final_response": final, "messages": messages}
-
-
-class CaptureConn:
-    def __init__(self):
-        self.updates = []
-
-    async def session_update(self, *args, **kwargs):
-        if kwargs:
-            self.updates.append((kwargs.get("session_id"), kwargs.get("update")))
-        else:
-            self.updates.append((args[0], args[1]))
-
-    async def request_permission(self, *args, **kwargs):
-        return SimpleNamespace(outcome="allow")
-
-
-class NoopDb:
-    def get_session(self, *_args, **_kwargs):
-        return None
-
-    def create_session(self, *_args, **_kwargs):
-        return None
-
-    def update_session(self, *_args, **_kwargs):
-        return None
-
-
-def make_agent_and_state():
-    fake = FakeAgent()
-    manager = SessionManager(agent_factory=lambda **kwargs: fake, db=NoopDb())
-    acp_agent = HermesACPAgent(session_manager=manager)
-    state = manager.create_session(cwd=".")
-    conn = CaptureConn()
-    acp_agent.on_connect(conn)
-    return acp_agent, state, fake, conn
-
-
-@pytest.mark.asyncio
-async def test_acp_steer_slash_command_injects_into_running_agent():
-    acp_agent, state, fake, _conn = make_agent_and_state()
-    state.is_running = True
-
-    response = await acp_agent.prompt(
-        session_id=state.session_id,
-        prompt=[TextContentBlock(type="text", text="/steer prefer the simpler fix")],
-    )
-
-    assert response.stop_reason == "end_turn"
-    assert fake.steers == ["prefer the simpler fix"]
-    assert fake.runs == []
-
-
-@pytest.mark.asyncio
-async def test_acp_steer_after_zed_interrupt_replays_interrupted_prompt_with_guidance():
-    acp_agent, state, fake, _conn = make_agent_and_state()
-    state.interrupted_prompt_text = "write hi to a text file"
-
-    response = await acp_agent.prompt(
-        session_id=state.session_id,
-        prompt=[TextContentBlock(type="text", text="/steer write HELLO instead")],
-    )
-
-    assert response.stop_reason == "end_turn"
-    assert fake.steers == []
-    assert fake.runs == [
-        "write hi to a text file\n\nUser correction/guidance after interrupt: write HELLO instead"
-    ]
-    assert state.interrupted_prompt_text == ""
-
-
-@pytest.mark.asyncio
-async def test_acp_steer_on_idle_session_runs_as_regular_prompt():
-    # /steer on an idle session (no running turn, nothing to salvage) should
-    # run the steer payload as a normal user prompt — NOT silently append it
-    # to state.queued_prompts. Without this, users on Zed / other ACP clients
-    # see their /steer turn into "queued for the next turn" when they never
-    # typed /queue. Matches gateway/run.py ~L4898 idle-/steer behavior.
-    acp_agent, state, fake, _conn = make_agent_and_state()
-
-    response = await acp_agent.prompt(
-        session_id=state.session_id,
-        prompt=[TextContentBlock(type="text", text="/steer summarize the README")],
-    )
-
-    assert response.stop_reason == "end_turn"
-    assert fake.steers == []
-    assert fake.runs == ["summarize the README"]
-    assert state.queued_prompts == []
-
-
-@pytest.mark.asyncio
-async def test_acp_queue_slash_command_adds_next_turn_without_running_now():
-    acp_agent, state, fake, _conn = make_agent_and_state()
-
-    response = await acp_agent.prompt(
-        session_id=state.session_id,
-        prompt=[TextContentBlock(type="text", text="/queue run the tests after this")],
-    )
-
-    assert response.stop_reason == "end_turn"
-    assert state.queued_prompts == ["run the tests after this"]
-    assert fake.runs == []
-
-
-@pytest.mark.asyncio
-async def test_acp_prompt_drains_queued_turns_after_current_run():
-    acp_agent, state, fake, conn = make_agent_and_state()
-    state.queued_prompts.append("then run tests")
-
-    response = await acp_agent.prompt(
-        session_id=state.session_id,
-        prompt=[TextContentBlock(type="text", text="make the change")],
-    )
-
-    assert response.stop_reason == "end_turn"
-    assert fake.runs == ["make the change", "then run tests"]
-    assert state.queued_prompts == []
-    agent_messages = [u for _sid, u in conn.updates if getattr(u, "session_update", None) == "agent_message_chunk"]
-    assert len(agent_messages) >= 2

tests/agent/test_anthropic_adapter.py

@@ -1836,55 +1836,3 @@ class TestResolveMessagesMaxTokens:
         result = _resolve_anthropic_messages_max_tokens(0.5, "claude-opus-4-6")
         assert result > 0
         assert result != 0
-
-
-# ---------------------------------------------------------------------------
-# convert_tools_to_anthropic — tool dedup at API boundary
-# ---------------------------------------------------------------------------
-
-class TestConvertToolsToAnthropicDedup:
-    """convert_tools_to_anthropic must deduplicate tool names.
-
-    Anthropic rejects requests with duplicate tool names.  This guard converts
-    a hard failure into a warning log.  See:
-    https://github.com/NousResearch/hermes-agent/issues/18478
-    """
-
-    def _make_openai_tool(self, name: str) -> dict:
-        return {
-            "type": "function",
-            "function": {
-                "name": name,
-                "description": f"Tool {name}",
-                "parameters": {"type": "object", "properties": {}},
-            },
-        }
-
-    def test_unique_tools_pass_through(self):
-        tools = [self._make_openai_tool("alpha"), self._make_openai_tool("beta")]
-        result = convert_tools_to_anthropic(tools)
-        assert len(result) == 2
-        names = [t["name"] for t in result]
-        assert names == ["alpha", "beta"]
-
-    def test_duplicate_tool_names_are_deduplicated(self):
-        """RED test — must fail until dedup guard is added."""
-        tools = [
-            self._make_openai_tool("lcm_grep"),
-            self._make_openai_tool("lcm_describe"),
-            self._make_openai_tool("lcm_grep"),  # duplicate
-            self._make_openai_tool("lcm_expand"),
-            self._make_openai_tool("lcm_describe"),  # duplicate
-        ]
-        result = convert_tools_to_anthropic(tools)
-        names = [t["name"] for t in result]
-        assert len(names) == len(set(names)), (
-            f"Duplicate tool names found: {names}"
-        )
-        assert len(result) == 3  # lcm_grep, lcm_describe, lcm_expand
-
-    def test_empty_tools_returns_empty(self):
-        assert convert_tools_to_anthropic([]) == []
-
-    def test_none_tools_returns_empty(self):
-        assert convert_tools_to_anthropic(None) == []

tests/agent/test_auxiliary_client.py

@@ -16,7 +16,6 @@ from agent.auxiliary_client import (
     auxiliary_max_tokens_param,
     call_llm,
     async_call_llm,
-    _build_call_kwargs,
     _read_codex_access_token,
     _get_provider_chain,
     _is_payment_error,
@@ -1753,143 +1752,3 @@ class TestVisionAutoSkipsKimiCoding:
             "kimi-coding",
             "kimi-coding-cn",
         })
-
-
-# ---------------------------------------------------------------------------
-# _build_call_kwargs — tool dedup at API boundary
-# ---------------------------------------------------------------------------
-
-class TestBuildCallKwargsToolDedup:
-    """_build_call_kwargs must deduplicate tool names before passing to API.
-
-    Providers like Google Vertex, Azure, and Bedrock reject requests with
-    duplicate tool names (HTTP 400).  This guard converts a hard failure into
-    a warning log so agent turns succeed even if an upstream injection path
-    regresses.  See: https://github.com/NousResearch/hermes-agent/issues/18478
-    """
-
-    def _make_tool(self, name: str) -> dict:
-        return {
-            "type": "function",
-            "function": {
-                "name": name,
-                "description": f"Tool {name}",
-                "parameters": {"type": "object", "properties": {}},
-            },
-        }
-
-    def test_unique_tools_pass_through_unchanged(self):
-        tools = [self._make_tool("alpha"), self._make_tool("beta")]
-        kwargs = _build_call_kwargs(
-            provider="openai", model="gpt-4o", messages=[], tools=tools,
-        )
-        assert len(kwargs["tools"]) == 2
-        names = [t["function"]["name"] for t in kwargs["tools"]]
-        assert names == ["alpha", "beta"]
-
-    def test_duplicate_tool_names_are_deduplicated(self):
-        """RED test — must fail until dedup guard is added."""
-        tools = [
-            self._make_tool("lcm_grep"),
-            self._make_tool("lcm_describe"),
-            self._make_tool("lcm_grep"),  # duplicate
-            self._make_tool("lcm_expand"),
-            self._make_tool("lcm_describe"),  # duplicate
-        ]
-        kwargs = _build_call_kwargs(
-            provider="google", model="gemini-2.5-pro", messages=[], tools=tools,
-        )
-        result_tools = kwargs["tools"]
-        names = [t["function"]["name"] for t in result_tools]
-        # Must be deduplicated — no repeated names
-        assert len(names) == len(set(names)), (
-            f"Duplicate tool names found: {names}"
-        )
-        assert len(result_tools) == 3  # lcm_grep, lcm_describe, lcm_expand
-
-    def test_empty_tools_unchanged(self):
-        kwargs = _build_call_kwargs(
-            provider="openai", model="gpt-4o", messages=[], tools=[],
-        )
-        assert kwargs.get("tools") == [] or "tools" not in kwargs
-
-    def test_none_tools_unchanged(self):
-        kwargs = _build_call_kwargs(
-            provider="openai", model="gpt-4o", messages=[], tools=None,
-        )
-        assert "tools" not in kwargs
-
-
-@pytest.fixture(autouse=True)
-def _clean_env(monkeypatch):
-    """Strip provider env vars so each test starts clean."""
-    for key in (
-        "OPENROUTER_API_KEY", "OPENAI_BASE_URL", "OPENAI_API_KEY",
-    ):
-        monkeypatch.delenv(key, raising=False)
-
-
-class TestOpenRouterExplicitApiKey:
-    """Test that explicit_api_key is correctly propagated to _try_openrouter()."""
-
-    def test_resolve_provider_client_passes_explicit_api_key_to_openrouter(
-        self, monkeypatch
-    ):
-        """
-        When resolve_provider_client() is called with explicit_api_key for OpenRouter,
-        the explicit key should be passed to the OpenAI client instead of falling back
-        to OPENROUTER_API_KEY env var.
-        """
-        # Set up env var as fallback (should NOT be used when explicit_api_key is provided)
-        monkeypatch.setenv("OPENROUTER_API_KEY", "env-fallback-key")
-
-        # Mock OpenAI to capture the api_key used
-        mock_openai = MagicMock()
-        mock_openai.return_value = MagicMock(name="openrouter-client")
-
-        with patch("agent.auxiliary_client.OpenAI", mock_openai):
-            client, model = resolve_provider_client(
-                provider="openrouter",
-                explicit_api_key="explicit-pool-key",
-            )
-
-            # Verify a client was created
-            assert client is not None
-            # Verify the explicit key was used, not the env var fallback
-            mock_openai.assert_called_once()
-            call_kwargs = mock_openai.call_args[1]
-            assert call_kwargs["api_key"] == "explicit-pool-key", (
-                f"Expected explicit_api_key to be passed, got: {call_kwargs['api_key']}"
-            )
-            assert call_kwargs["api_key"] != "env-fallback-key", (
-                "Should NOT fall back to OPENROUTER_API_KEY when explicit_api_key is provided"
-            )
-
-    def test_resolve_provider_client_without_explicit_api_key_falls_back_to_env(
-        self, monkeypatch
-    ):
-        """
-        When resolve_provider_client() is called WITHOUT explicit_api_key for OpenRouter,
-        it should fall back to OPENROUTER_API_KEY env var.
-        """
-        # Set up env var as fallback (should be used when explicit_api_key is NOT provided)
-        monkeypatch.setenv("OPENROUTER_API_KEY", "env-fallback-key")
-
-        # Mock OpenAI to capture the api_key used
-        mock_openai = MagicMock()
-        mock_openai.return_value = MagicMock(name="openrouter-client")
-
-        with patch("agent.auxiliary_client.OpenAI", mock_openai):
-            client, model = resolve_provider_client(
-                provider="openrouter",
-                explicit_api_key=None,
-            )
-
-            # Verify a client was created
-            assert client is not None
-            # Verify the env var fallback was used
-            mock_openai.assert_called_once()
-            call_kwargs = mock_openai.call_args[1]
-            assert call_kwargs["api_key"] == "env-fallback-key", (
-                f"Expected env fallback key to be used when explicit_api_key is None, got: {call_kwargs['api_key']}"
-            )

tests/agent/test_auxiliary_named_custom_providers.py

@@ -427,68 +427,3 @@ class TestProvidersDictApiModeAnthropicMessages:
         assert isinstance(sync_client, OpenAI)
         async_client, _ = resolve_provider_client("localchat", async_mode=True)
         assert isinstance(async_client, AsyncOpenAI)
-
-
-class TestCustomProviderAliasCollision:
-    """A user-declared custom_providers entry whose name matches a built-in
-    *alias* (not a canonical provider) must win over the built-in.
-
-    Regression guard for #15743: users who defined fallback_model pointing at
-    a custom_providers entry named ``kimi`` were having requests routed to
-    the built-in kimi-coding endpoint because ``_normalize_aux_provider``
-    rewrote ``kimi`` → ``kimi-coding`` before the named-custom lookup.
-    """
-
-    def test_custom_named_kimi_wins_over_builtin_alias(self, tmp_path):
-        _write_config(tmp_path, {
-            "model": {"provider": "openrouter", "default": "anthropic/claude-sonnet-4.6"},
-            "custom_providers": [
-                {
-                    "name": "kimi",
-                    "base_url": "https://my-custom-kimi.example.com/v1",
-                    "api_key": "my-kimi-key",
-                    "models": {"my-kimi-model": {"context_length": 200000}},
-                },
-            ],
-        })
-        from agent.auxiliary_client import resolve_provider_client
-        from openai import OpenAI
-        client, model = resolve_provider_client("kimi", model="my-kimi-model", raw_codex=True)
-        assert isinstance(client, OpenAI)
-        assert "my-custom-kimi.example.com" in str(client.base_url)
-        assert client.api_key == "my-kimi-key"
-        assert model == "my-kimi-model"
-
-    def test_bare_kimi_without_custom_still_routes_to_builtin(self, tmp_path, monkeypatch):
-        """Regression guard: bare 'kimi' with no custom entry must still
-        reach the built-in kimi-coding provider."""
-        _write_config(tmp_path, {
-            "model": {"provider": "openrouter", "default": "anthropic/claude-sonnet-4.6"},
-        })
-        monkeypatch.setenv("KIMI_API_KEY", "builtin-kimi-key")
-        from agent.auxiliary_client import resolve_provider_client
-        client, _ = resolve_provider_client("kimi", model="kimi-k2-0905-preview", raw_codex=True)
-        assert client is not None
-        base_url = str(client.base_url)
-        # Built-in kimi-coding points at api.moonshot.ai
-        assert "moonshot" in base_url or "kimi" in base_url, f"unexpected base_url {base_url!r}"
-
-    def test_explicit_overrides_applied_on_api_key_branch(self, tmp_path, monkeypatch):
-        """Explicit base_url/api_key from the caller must override the
-        registered provider's defaults on the API-key branch.  Used by
-        _try_activate_fallback to route a fallback through a built-in
-        provider name but targeting a user-supplied endpoint."""
-        _write_config(tmp_path, {
-            "model": {"provider": "openrouter", "default": "anthropic/claude-sonnet-4.6"},
-        })
-        monkeypatch.setenv("KIMI_API_KEY", "builtin-kimi-key")
-        from agent.auxiliary_client import resolve_provider_client
-        from openai import OpenAI
-        client, _ = resolve_provider_client(
-            "kimi-coding", model="kimi-k2", raw_codex=True,
-            explicit_base_url="https://override.example.com",
-            explicit_api_key="override-key",
-        )
-        assert isinstance(client, OpenAI)
-        assert "override.example.com" in str(client.base_url)
-        assert client.api_key == "override-key"

tests/agent/test_context_compressor.py

@@ -640,30 +640,6 @@ class TestCompressWithClient:
                 for tc in msg["tool_calls"]:
                     assert tc["id"] in answered_ids
 
-    def test_sanitizer_matches_responses_call_id_when_id_differs(self, compressor):
-        msgs = [
-            {
-                "role": "assistant",
-                "content": "",
-                "tool_calls": [
-                    {
-                        "id": "fc_123",
-                        "call_id": "call_123",
-                        "response_item_id": "fc_123",
-                        "type": "function",
-                        "function": {"name": "search_files", "arguments": "{}"},
-                    }
-                ],
-            },
-            {"role": "tool", "tool_call_id": "call_123", "content": "result"},
-        ]
-
-        sanitized = compressor._sanitize_tool_pairs(msgs)
-
-        assert [m.get("tool_call_id") for m in sanitized if m.get("role") == "tool"] == [
-            "call_123"
-        ]
-
     def test_summary_role_avoids_consecutive_user_messages(self):
         """Summary role should alternate with the last head message to avoid consecutive same-role messages."""
         mock_client = MagicMock()
@@ -1143,34 +1119,6 @@ class TestTokenBudgetTailProtection:
         # At least one old tool result should have been pruned
         assert pruned >= 1
 
-    def test_prune_short_conv_protects_entire_tail(self, budget_compressor):
-        """Regression guard for PR #17025.
-
-        When ``len(messages) <= protect_tail_count`` and a token budget is
-        also set, every message must be protected. The previous code used
-        ``min(protect_tail_count, len(result) - 1)`` which capped the floor
-        one below the full length, leaving the oldest message eligible for
-        pruning.
-        """
-        c = budget_compressor
-        # 4 messages, protect_tail_count=4 -- nothing should be pruned.
-        # Oldest message is a large tool result; on the buggy path it falls
-        # outside the protected window and gets summarized.
-        messages = [
-            {"role": "tool", "content": "x" * 5000, "tool_call_id": "c0"},
-            {"role": "assistant", "content": "ack"},
-            {"role": "user", "content": "recent"},
-            {"role": "assistant", "content": "reply"},
-        ]
-        result, pruned = c._prune_old_tool_results(
-            messages,
-            protect_tail_count=4,
-            protect_tail_tokens=1_000_000,  # budget large enough to protect all
-        )
-        assert pruned == 0
-        # Tool result at index 0 must be preserved verbatim
-        assert result[0]["content"] == "x" * 5000
-
     def test_prune_without_token_budget_uses_message_count(self, budget_compressor):
         """Without protect_tail_tokens, falls back to message-count behavior."""
         c = budget_compressor

tests/agent/test_credential_pool.py

@@ -348,64 +348,6 @@ def test_load_pool_seeds_env_api_key(tmp_path, monkeypatch):
     assert entry.access_token == "sk-or-seeded"
 
 
-
-def test_load_pool_prefers_dotenv_over_stale_os_environ(tmp_path, monkeypatch):
-    """Regression for #18254: stale OPENROUTER_API_KEY in os.environ (inherited
-    from a parent shell) must NOT shadow the fresh key in ~/.hermes/.env when
-    seeding the credential pool. Before the fix, `get_env_value()` preferred
-    os.environ and silently wrote the stale value into auth.json, causing
-    persistent 401 errors after key rotation.
-    """
-    hermes_home = tmp_path / "hermes"
-    hermes_home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
-
-    # Simulate the bug: parent shell exported a stale test key
-    monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-STALE-from-shell")
-
-    # User edited ~/.hermes/.env with the fresh key
-    (hermes_home / ".env").write_text(
-        "OPENROUTER_API_KEY=sk-or-FRESH-from-dotenv\n"
-    )
-
-    _write_auth_store(tmp_path, {"version": 1, "providers": {}})
-
-    from agent.credential_pool import load_pool
-    pool = load_pool("openrouter")
-    entry = pool.select()
-
-    assert entry is not None
-    assert entry.source == "env:OPENROUTER_API_KEY"
-    # The fresh key from .env must win over the stale shell export
-    assert entry.access_token == "sk-or-FRESH-from-dotenv", (
-        f"Expected .env to win, got {entry.access_token!r}"
-    )
-
-
-def test_load_pool_falls_back_to_os_environ_when_dotenv_empty(tmp_path, monkeypatch):
-    """When ~/.hermes/.env does not define OPENROUTER_API_KEY (typical Docker /
-    K8s / systemd deployment), seeding must still pick up the key from
-    os.environ. Guards against regressions that would break production
-    deployments relying on runtime-injected env vars.
-    """
-    hermes_home = tmp_path / "hermes"
-    hermes_home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
-    monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-from-runtime-env")
-
-    # .env exists but does not define OPENROUTER_API_KEY
-    (hermes_home / ".env").write_text("SOME_OTHER_VAR=unrelated\n")
-
-    _write_auth_store(tmp_path, {"version": 1, "providers": {}})
-
-    from agent.credential_pool import load_pool
-    pool = load_pool("openrouter")
-    entry = pool.select()
-
-    assert entry is not None
-    assert entry.access_token == "sk-or-from-runtime-env"
-
-
 def test_load_pool_removes_stale_seeded_env_entry(tmp_path, monkeypatch):
     monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes"))
     monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)

tests/agent/test_curator.py

@@ -86,22 +86,9 @@ def test_curator_config_overrides(curator_env, monkeypatch):
 # should_run_now
 # ---------------------------------------------------------------------------
 
-def test_first_run_defers(curator_env):
-    """The FIRST observation of the curator (fresh install, no state file)
-    must NOT trigger an immediate run. The curator is designed to run after
-    a full ``interval_hours`` of skill activity, not on the first background
-    tick after installation. Fixes #18373.
-    """
+def test_first_run_always_eligible(curator_env):
     c = curator_env["curator"]
-    # No state file — should defer and seed last_run_at.
-    assert c.should_run_now() is False
-    state = c.load_state()
-    assert state.get("last_run_at") is not None, (
-        "first observation should seed last_run_at so the interval clock "
-        "starts ticking instead of firing immediately next tick"
-    )
-    # A second immediate call still returns False (seeded, not yet stale).
-    assert c.should_run_now() is False
+    assert c.should_run_now() is True
 
 
 def test_recent_run_blocks(curator_env):
@@ -278,77 +265,6 @@ def test_run_review_records_state(curator_env):
     assert state["last_run_summary"] is not None
 
 
-def test_dry_run_does_not_advance_state(curator_env, monkeypatch):
-    """Dry-run previews must not bump last_run_at or run_count. A preview
-    shouldn't defer the next scheduled real pass or look like a real run in
-    `hermes curator status`. Fixes #18373.
-    """
-    c = curator_env["curator"]
-    skills_dir = curator_env["home"] / "skills"
-    _write_skill(skills_dir, "a")
-
-    # Stub the LLM so the test doesn't need a provider.
-    monkeypatch.setattr(
-        c, "_run_llm_review",
-        lambda prompt: {
-            "final": "", "summary": "dry preview", "model": "", "provider": "",
-            "tool_calls": [], "error": None,
-        },
-    )
-
-    c.run_curator_review(synchronous=True, dry_run=True)
-    state = c.load_state()
-    assert state.get("last_run_at") is None, "dry-run must not seed last_run_at"
-    assert state.get("run_count", 0) == 0, "dry-run must not bump run_count"
-    assert "dry-run" in (state.get("last_run_summary") or ""), (
-        "dry-run summary should be labeled so status output is unambiguous"
-    )
-
-
-def test_dry_run_injects_report_only_banner(curator_env, monkeypatch):
-    """The dry-run prompt must carry a banner instructing the LLM not to
-    call any mutating tool. This is defense in depth — the caller also
-    skips automatic transitions — but the LLM prompt is the only guard
-    against the model calling skill_manage directly."""
-    c = curator_env["curator"]
-    skills_dir = curator_env["home"] / "skills"
-    _write_skill(skills_dir, "a")
-
-    captured = {}
-    def _stub(prompt):
-        captured["prompt"] = prompt
-        return {"final": "", "summary": "s", "model": "", "provider": "",
-                "tool_calls": [], "error": None}
-    monkeypatch.setattr(c, "_run_llm_review", _stub)
-
-    c.run_curator_review(synchronous=True, dry_run=True)
-    assert "DRY-RUN" in captured["prompt"]
-    assert "DO NOT" in captured["prompt"]
-
-
-def test_dry_run_skips_automatic_transitions(curator_env, monkeypatch):
-    """Dry-run must not call apply_automatic_transitions — the auto pass
-    archives skills deterministically, and a preview must not touch the
-    filesystem."""
-    c = curator_env["curator"]
-    skills_dir = curator_env["home"] / "skills"
-    _write_skill(skills_dir, "a")
-
-    called = {"n": 0}
-    def _explode(*_a, **_kw):
-        called["n"] += 1
-        return {"checked": 0, "marked_stale": 0, "archived": 0, "reactivated": 0}
-    monkeypatch.setattr(c, "apply_automatic_transitions", _explode)
-    monkeypatch.setattr(
-        c, "_run_llm_review",
-        lambda p: {"final": "", "summary": "s", "model": "", "provider": "",
-                   "tool_calls": [], "error": None},
-    )
-
-    c.run_curator_review(synchronous=True, dry_run=True)
-    assert called["n"] == 0, "dry-run must skip apply_automatic_transitions"
-
-
 def test_run_review_synchronous_invokes_llm_stub(curator_env, monkeypatch):
     c = curator_env["curator"]
     skills_dir = curator_env["home"] / "skills"
@@ -411,32 +327,12 @@ def test_maybe_run_curator_runs_when_eligible(curator_env, monkeypatch):
     c = curator_env["curator"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
-    # Seed last_run_at far in the past so the interval gate opens — the
-    # "no state" path intentionally defers the first run now (#18373).
-    long_ago = datetime.now(timezone.utc) - timedelta(hours=c.get_interval_hours() * 2)
-    c.save_state({"last_run_at": long_ago.isoformat(), "paused": False})
     # Force idle over threshold
     result = c.maybe_run_curator(idle_for_seconds=99999.0)
     assert result is not None
     assert "started_at" in result
 
 
-def test_maybe_run_curator_defers_on_fresh_install(curator_env):
-    """Fresh install (no curator state file) must NOT fire the curator on
-    the first gateway tick. The first observation seeds last_run_at and
-    returns None. Fixes #18373."""
-    c = curator_env["curator"]
-    skills_dir = curator_env["home"] / "skills"
-    _write_skill(skills_dir, "a")
-    # Infinite idle — the only thing that should block the run is the new
-    # deferred-first-run gate.
-    result = c.maybe_run_curator(idle_for_seconds=99999.0)
-    assert result is None
-    # And the next tick still defers (we seeded last_run_at to "now").
-    result2 = c.maybe_run_curator(idle_for_seconds=99999.0)
-    assert result2 is None
-
-
 def test_maybe_run_curator_swallows_exceptions(curator_env, monkeypatch):
     c = curator_env["curator"]
 
@@ -467,19 +363,6 @@ def test_state_atomic_write_no_tmp_leftovers(curator_env):
         assert not p.name.startswith(".curator_state_"), f"tmp leftover: {p.name}"
 
 
-def test_state_preserves_last_report_path(curator_env):
-    c = curator_env["curator"]
-    c.save_state({
-        "last_run_at": "2026-04-30T12:00:00+00:00",
-        "last_run_summary": "ok",
-        "last_report_path": "/tmp/curator-report",
-        "paused": False,
-        "run_count": 1,
-    })
-    state = c.load_state()
-    assert state["last_report_path"] == "/tmp/curator-report"
-
-
 def test_curator_review_prompt_has_invariants():
     """Core invariants must be in the review prompt text."""
     from agent.curator import CURATOR_REVIEW_PROMPT

tests/agent/test_curator_backup.py

@@ -1,594 +0,0 @@
-"""Tests for agent/curator_backup.py — snapshot + rollback of the skills tree."""
-
-from __future__ import annotations
-
-import importlib
-import json
-import os
-import sys
-import tarfile
-import tempfile
-from pathlib import Path
-
-import pytest
-
-
-@pytest.fixture
-def backup_env(monkeypatch, tmp_path):
-    """Isolate HERMES_HOME + reload modules so every test starts clean."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    (home / "skills").mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-
-    # Reload so get_hermes_home picks up the env var fresh.
-    import hermes_constants
-    importlib.reload(hermes_constants)
-    from agent import curator_backup
-    importlib.reload(curator_backup)
-    return {"home": home, "skills": home / "skills", "cb": curator_backup}
-
-
-def _write_skill(skills_dir: Path, name: str, body: str = "body") -> Path:
-    d = skills_dir / name
-    d.mkdir(parents=True, exist_ok=True)
-    (d / "SKILL.md").write_text(
-        f"---\nname: {name}\ndescription: t\nversion: 1.0\n---\n\n{body}\n",
-        encoding="utf-8",
-    )
-    return d
-
-
-# ---------------------------------------------------------------------------
-# snapshot_skills
-# ---------------------------------------------------------------------------
-
-def test_snapshot_creates_tarball_and_manifest(backup_env):
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    _write_skill(backup_env["skills"], "beta")
-
-    snap = cb.snapshot_skills(reason="test")
-    assert snap is not None, "snapshot should succeed with a populated skills dir"
-    assert (snap / "skills.tar.gz").exists()
-    manifest = json.loads((snap / "manifest.json").read_text())
-    assert manifest["reason"] == "test"
-    assert manifest["skill_files"] == 2
-    assert manifest["archive_bytes"] > 0
-
-
-def test_snapshot_excludes_backups_dir_itself(backup_env):
-    """The backup must NOT contain .curator_backups/ — that would recurse
-    with every subsequent snapshot and balloon disk usage."""
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    snap1 = cb.snapshot_skills(reason="first")
-    assert snap1 is not None
-    snap2 = cb.snapshot_skills(reason="second")
-    assert snap2 is not None
-    with tarfile.open(snap2 / "skills.tar.gz") as tf:
-        names = tf.getnames()
-    assert not any(n.startswith(".curator_backups") for n in names), (
-        "second snapshot must not contain the first snapshot recursively"
-    )
-
-
-def test_snapshot_excludes_hub_dir(backup_env):
-    """.hub/ is managed by the skills hub. Rolling it back would break
-    lockfile invariants, so the snapshot omits it entirely."""
-    cb = backup_env["cb"]
-    hub = backup_env["skills"] / ".hub"
-    hub.mkdir()
-    (hub / "lock.json").write_text("{}")
-    _write_skill(backup_env["skills"], "alpha")
-    snap = cb.snapshot_skills(reason="t")
-    assert snap is not None
-    with tarfile.open(snap / "skills.tar.gz") as tf:
-        names = tf.getnames()
-    assert not any(n.startswith(".hub") for n in names)
-
-
-def test_snapshot_disabled_returns_none(backup_env, monkeypatch):
-    cb = backup_env["cb"]
-    monkeypatch.setattr(cb, "is_enabled", lambda: False)
-    _write_skill(backup_env["skills"], "alpha")
-    assert cb.snapshot_skills() is None
-    # And no backup dir should have been created
-    assert not (backup_env["skills"] / ".curator_backups").exists()
-
-
-def test_snapshot_uniquifies_when_same_second(backup_env, monkeypatch):
-    """Two snapshots in the same wallclock second must not clobber each
-    other. The module appends a counter to the second snapshot's id."""
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    frozen = "2026-05-01T12-00-00Z"
-    monkeypatch.setattr(cb, "_utc_id", lambda now=None: frozen)
-    s1 = cb.snapshot_skills(reason="a")
-    s2 = cb.snapshot_skills(reason="b")
-    assert s1 is not None and s2 is not None
-    assert s1.name == frozen
-    assert s2.name == f"{frozen}-01"
-
-
-def test_snapshot_prunes_to_keep_count(backup_env, monkeypatch):
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    monkeypatch.setattr(cb, "get_keep", lambda: 3)
-
-    # Create 5 snapshots with monotonically increasing fake ids
-    ids = [f"2026-05-0{i}T00-00-00Z" for i in range(1, 6)]
-    for i, fid in enumerate(ids):
-        monkeypatch.setattr(cb, "_utc_id", lambda now=None, _f=fid: _f)
-        cb.snapshot_skills(reason=f"n{i}")
-
-    remaining = sorted(p.name for p in (backup_env["skills"] / ".curator_backups").iterdir())
-    # Newest 3 kept (lex order == date order for this id format)
-    assert remaining == ids[2:], f"expected newest 3, got {remaining}"
-
-
-# ---------------------------------------------------------------------------
-# list_backups / _resolve_backup
-# ---------------------------------------------------------------------------
-
-def test_list_backups_empty(backup_env):
-    cb = backup_env["cb"]
-    assert cb.list_backups() == []
-
-
-def test_list_backups_returns_manifest_data(backup_env):
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    cb.snapshot_skills(reason="m1")
-    rows = cb.list_backups()
-    assert len(rows) == 1
-    assert rows[0]["reason"] == "m1"
-    assert rows[0]["skill_files"] == 1
-
-
-def test_resolve_backup_newest_when_no_id(backup_env, monkeypatch):
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    ids = ["2026-05-01T00-00-00Z", "2026-05-02T00-00-00Z"]
-    for fid in ids:
-        monkeypatch.setattr(cb, "_utc_id", lambda now=None, _f=fid: _f)
-        cb.snapshot_skills()
-    resolved = cb._resolve_backup(None)
-    assert resolved is not None
-    assert resolved.name == "2026-05-02T00-00-00Z", (
-        "resolve(None) must return newest regular snapshot"
-    )
-
-
-def test_resolve_backup_unknown_id_returns_none(backup_env):
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    cb.snapshot_skills()
-    assert cb._resolve_backup("not-an-id") is None
-
-
-# ---------------------------------------------------------------------------
-# rollback
-# ---------------------------------------------------------------------------
-
-def test_rollback_restores_deleted_skill(backup_env):
-    """The whole point of this feature: user loses a skill, rollback
-    brings it back."""
-    cb = backup_env["cb"]
-    skills = backup_env["skills"]
-    user_skill = _write_skill(skills, "my-personal-workflow", body="important content")
-    cb.snapshot_skills(reason="pre-simulated-curator")
-
-    # Simulate curator archiving it out of existence
-    import shutil as _sh
-    _sh.rmtree(user_skill)
-    assert not user_skill.exists()
-
-    ok, msg, _ = cb.rollback()
-    assert ok, f"rollback failed: {msg}"
-    assert user_skill.exists(), "my-personal-workflow should be restored"
-    assert "important content" in (user_skill / "SKILL.md").read_text()
-
-
-def test_rollback_is_itself_undoable(backup_env):
-    """A rollback creates its own safety snapshot before replacing the
-    tree, so the user can undo a mistaken rollback. The safety snapshot
-    is a real tarball with reason='pre-rollback to <id>' — it's
-    listed by list_backups() just like any other snapshot and can be
-    restored the same way."""
-    cb = backup_env["cb"]
-    skills = backup_env["skills"]
-    _write_skill(skills, "v1")
-    cb.snapshot_skills(reason="snapshot-of-v1")
-
-    # Overwrite with a new skill state
-    import shutil as _sh
-    _sh.rmtree(skills / "v1")
-    _write_skill(skills, "v2")
-
-    ok, _, _ = cb.rollback()
-    assert ok
-    assert (skills / "v1").exists()
-
-    # list_backups should show a safety snapshot tagged "pre-rollback to <target-id>"
-    rows = cb.list_backups()
-    pre_rollback_entries = [r for r in rows if "pre-rollback" in (r.get("reason") or "")]
-    assert len(pre_rollback_entries) >= 1, (
-        f"expected a pre-rollback safety snapshot in list_backups(), got: "
-        f"{[(r.get('id'), r.get('reason')) for r in rows]}"
-    )
-    # And the transient staging dir must be gone (it's implementation detail)
-    backups_dir = skills / ".curator_backups"
-    staging_dirs = [p for p in backups_dir.iterdir() if p.name.startswith(".rollback-staging-")]
-    assert staging_dirs == [], (
-        f"staging dir should be cleaned up on success, got: {staging_dirs}"
-    )
-
-
-def test_rollback_no_snapshots_returns_error(backup_env):
-    cb = backup_env["cb"]
-    ok, msg, _ = cb.rollback()
-    assert not ok
-    assert "no matching backup" in msg.lower() or "no snapshot" in msg.lower()
-
-
-def test_rollback_rejects_unsafe_tarball(backup_env, monkeypatch):
-    """Tarballs with absolute paths or .. components must be refused even
-    if someone crafts a malicious snapshot. Defense in depth — normal
-    curator snapshots never produce these."""
-    cb = backup_env["cb"]
-    skills = backup_env["skills"]
-    _write_skill(skills, "alpha")
-    cb.snapshot_skills(reason="legit")
-
-    # Hand-craft a malicious tarball replacing the legit one
-    rows = cb.list_backups()
-    snap_dir = Path(rows[0]["path"])
-    mal = snap_dir / "skills.tar.gz"
-    mal.unlink()
-    with tarfile.open(mal, "w:gz") as tf:
-        evil = tempfile.NamedTemporaryFile(delete=False, suffix=".md")
-        evil.write(b"evil")
-        evil.close()
-        tf.add(evil.name, arcname="../../etc/evil.md")
-        os.unlink(evil.name)
-
-    ok, msg, _ = cb.rollback()
-    assert not ok
-    assert "unsafe" in msg.lower() or "refus" in msg.lower() or "extract" in msg.lower()
-
-
-# ---------------------------------------------------------------------------
-# Integration with run_curator_review
-# ---------------------------------------------------------------------------
-
-def test_real_run_takes_pre_snapshot(backup_env, monkeypatch):
-    """A real (non-dry) curator pass must snapshot the tree before calling
-    apply_automatic_transitions. This is the safety net #18373 asked for."""
-    cb = backup_env["cb"]
-    skills = backup_env["skills"]
-    _write_skill(skills, "alpha")
-
-    # Reload curator module against the freshly-env'd hermes_constants
-    from agent import curator
-    importlib.reload(curator)
-
-    # Stub out LLM review and auto transitions — we only care about the
-    # snapshot side-effect.
-    monkeypatch.setattr(
-        curator, "_run_llm_review",
-        lambda p: {"final": "", "summary": "s", "model": "", "provider": "",
-                   "tool_calls": [], "error": None},
-    )
-    monkeypatch.setattr(
-        curator, "apply_automatic_transitions",
-        lambda now=None: {"checked": 1, "marked_stale": 0, "archived": 0, "reactivated": 0},
-    )
-
-    curator.run_curator_review(synchronous=True)
-    # Pre-run snapshot should exist
-    rows = cb.list_backups()
-    assert any(r.get("reason") == "pre-curator-run" for r in rows), (
-        f"expected a pre-curator-run snapshot, got {[r.get('reason') for r in rows]}"
-    )
-
-
-def test_dry_run_skips_snapshot(backup_env, monkeypatch):
-    """Dry-run previews must not spend disk on a snapshot — they don't
-    mutate anything, so there's nothing to back up."""
-    cb = backup_env["cb"]
-    skills = backup_env["skills"]
-    _write_skill(skills, "alpha")
-
-    from agent import curator
-    importlib.reload(curator)
-    monkeypatch.setattr(
-        curator, "_run_llm_review",
-        lambda p: {"final": "", "summary": "s", "model": "", "provider": "",
-                   "tool_calls": [], "error": None},
-    )
-
-    curator.run_curator_review(synchronous=True, dry_run=True)
-    rows = cb.list_backups()
-    assert not any(r.get("reason") == "pre-curator-run" for r in rows), (
-        "dry-run must not create a pre-run snapshot"
-    )
-
-
-# ---------------------------------------------------------------------------
-# cron-jobs backup + rollback (the part issue #18671's follow-up adds)
-# ---------------------------------------------------------------------------
-
-
-def _write_cron_jobs(home: Path, jobs: list) -> Path:
-    """Write a synthetic cron/jobs.json under HERMES_HOME. Returns the path.
-    Mirrors cron.jobs.save_jobs() wrapper shape: `{"jobs": [...], "updated_at": ...}`.
-    """
-    cron_dir = home / "cron"
-    cron_dir.mkdir(parents=True, exist_ok=True)
-    path = cron_dir / "jobs.json"
-    path.write_text(
-        json.dumps({"jobs": jobs, "updated_at": "2026-05-01T00:00:00Z"}, indent=2),
-        encoding="utf-8",
-    )
-    return path
-
-
-def _reload_cron_jobs(home: Path):
-    """Reload cron.jobs so its module-level HERMES_DIR picks up the tmp HOME."""
-    import hermes_constants
-    importlib.reload(hermes_constants)
-    if "cron.jobs" in sys.modules:
-        import cron.jobs as _cj
-        importlib.reload(_cj)
-    else:
-        import cron.jobs as _cj  # noqa: F401
-    import cron.jobs as cj
-    return cj
-
-
-def test_snapshot_includes_cron_jobs(backup_env):
-    """With a cron/jobs.json present, snapshot writes cron-jobs.json and records it in manifest."""
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    _write_cron_jobs(backup_env["home"], [
-        {"id": "job-a", "name": "a", "schedule": "every 1h", "skills": ["alpha"]},
-        {"id": "job-b", "name": "b", "schedule": "every 2h", "skill": "alpha"},
-    ])
-
-    snap = cb.snapshot_skills(reason="test")
-    assert snap is not None
-    assert (snap / cb.CRON_JOBS_FILENAME).exists()
-
-    mf = json.loads((snap / "manifest.json").read_text(encoding="utf-8"))
-    assert mf["cron_jobs"]["backed_up"] is True
-    assert mf["cron_jobs"]["jobs_count"] == 2
-
-
-def test_snapshot_without_cron_jobs_file_still_succeeds(backup_env):
-    """No cron/jobs.json on disk → snapshot succeeds, manifest records absence."""
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    # Deliberately do not create ~/.hermes/cron/jobs.json
-
-    snap = cb.snapshot_skills(reason="test")
-    assert snap is not None
-    assert not (snap / cb.CRON_JOBS_FILENAME).exists()
-
-    mf = json.loads((snap / "manifest.json").read_text(encoding="utf-8"))
-    assert mf["cron_jobs"]["backed_up"] is False
-    assert "cron/jobs.json" in mf["cron_jobs"]["reason"]
-
-
-def test_snapshot_cron_jobs_malformed_json_still_captured(backup_env):
-    """Malformed jobs.json is still copied to the snapshot (fidelity over
-    validation); the manifest notes the parse warning."""
-    cb = backup_env["cb"]
-    _write_skill(backup_env["skills"], "alpha")
-    (backup_env["home"] / "cron").mkdir()
-    (backup_env["home"] / "cron" / "jobs.json").write_text("{oh no", encoding="utf-8")
-
-    snap = cb.snapshot_skills(reason="test")
-    assert snap is not None
-    # Raw file was copied even though we couldn't parse it
-    assert (snap / cb.CRON_JOBS_FILENAME).read_text() == "{oh no"
-
-    mf = json.loads((snap / "manifest.json").read_text(encoding="utf-8"))
-    assert mf["cron_jobs"]["backed_up"] is True
-    assert mf["cron_jobs"]["jobs_count"] == 0
-    assert "parse_warning" in mf["cron_jobs"]
-
-
-def test_rollback_restores_cron_skill_links(backup_env):
-    """End-to-end: snapshot with job [alpha,beta], curator-style in-place
-    rewrite to [umbrella], then rollback → skills restored to [alpha,beta]."""
-    cb = backup_env["cb"]
-    home = backup_env["home"]
-    _write_skill(backup_env["skills"], "alpha")
-    _write_skill(backup_env["skills"], "beta")
-    _write_skill(backup_env["skills"], "umbrella")
-
-    cj = _reload_cron_jobs(home)
-    cj.create_job(name="weekly", prompt="p", schedule="every 7d",
-                  skills=["alpha", "beta"])
-
-    snap = cb.snapshot_skills(reason="pre-curator-run")
-    assert snap is not None
-
-    # Simulate the curator's in-place cron rewrite after consolidation
-    cj.rewrite_skill_refs(
-        consolidated={"alpha": "umbrella", "beta": "umbrella"},
-        pruned=[],
-    )
-    live_after_curator = cj.load_jobs()
-    assert live_after_curator[0]["skills"] == ["umbrella"]
-
-    # Now roll back
-    ok, msg, _ = cb.rollback(backup_id=snap.name)
-    assert ok, msg
-    assert "cron links" in msg
-
-    live_after_rollback = cj.load_jobs()
-    # skills restored; legacy `skill` mirror follows first element
-    assert live_after_rollback[0]["skills"] == ["alpha", "beta"]
-
-
-def test_rollback_only_touches_skill_fields(backup_env):
-    """Every field other than skills/skill must remain untouched across rollback.
-    Schedule, enabled, prompt, timestamps — all live state, hands off."""
-    cb = backup_env["cb"]
-    home = backup_env["home"]
-    _write_skill(backup_env["skills"], "alpha")
-
-    # Hand-rolled jobs.json with varied fields (no real create_job — we want
-    # exact field control).
-    _write_cron_jobs(home, [{
-        "id": "stable-id",
-        "name": "original-name",
-        "prompt": "original prompt",
-        "schedule": "every 1h",
-        "skills": ["alpha"],
-        "enabled": True,
-        "last_run_at": "2026-04-01T00:00:00Z",
-    }])
-    snap = cb.snapshot_skills(reason="pre-curator-run")
-    assert snap is not None
-
-    # User/scheduler activity AFTER the snapshot: rename the job, change
-    # the schedule, update timestamps, and (curator) rewrite the skills list.
-    cj = _reload_cron_jobs(home)
-    jobs = cj.load_jobs()
-    jobs[0]["name"] = "renamed-since-snapshot"
-    jobs[0]["schedule"] = "every 30m"
-    jobs[0]["last_run_at"] = "2026-05-01T12:00:00Z"
-    jobs[0]["skills"] = ["umbrella"]  # pretend curator did this
-    cj.save_jobs(jobs)
-
-    ok, _, _ = cb.rollback(backup_id=snap.name)
-    assert ok
-
-    after = cj.load_jobs()
-    job = after[0]
-    # skills: restored
-    assert job["skills"] == ["alpha"]
-    # everything else: untouched (live state preserved)
-    assert job["name"] == "renamed-since-snapshot"
-    assert job["schedule"] == "every 30m"
-    assert job["last_run_at"] == "2026-05-01T12:00:00Z"
-    assert job["prompt"] == "original prompt"
-
-
-def test_rollback_skips_jobs_the_user_deleted(backup_env):
-    """If the user deleted a cron job after the snapshot, rollback must
-    NOT resurrect it — the user's delete is a later, explicit choice."""
-    cb = backup_env["cb"]
-    home = backup_env["home"]
-    _write_skill(backup_env["skills"], "alpha")
-
-    _write_cron_jobs(home, [
-        {"id": "keep-me", "name": "keep", "schedule": "every 1h", "skills": ["alpha"]},
-        {"id": "delete-me", "name": "gone", "schedule": "every 1h", "skills": ["alpha"]},
-    ])
-    snap = cb.snapshot_skills(reason="pre-curator-run")
-
-    # User deletes one job after the snapshot
-    cj = _reload_cron_jobs(home)
-    cj.save_jobs([j for j in cj.load_jobs() if j["id"] != "delete-me"])
-
-    ok, _, _ = cb.rollback(backup_id=snap.name)
-    assert ok
-
-    live_after = cj.load_jobs()
-    live_ids = {j["id"] for j in live_after}
-    assert "keep-me" in live_ids
-    assert "delete-me" not in live_ids  # not resurrected
-
-
-def test_rollback_leaves_new_jobs_untouched(backup_env):
-    """Jobs created AFTER the snapshot must pass through rollback unchanged."""
-    cb = backup_env["cb"]
-    home = backup_env["home"]
-    _write_skill(backup_env["skills"], "alpha")
-    _write_cron_jobs(home, [
-        {"id": "original", "name": "o", "schedule": "every 1h", "skills": ["alpha"]},
-    ])
-    snap = cb.snapshot_skills(reason="pre-curator-run")
-
-    cj = _reload_cron_jobs(home)
-    jobs = cj.load_jobs()
-    jobs.append({"id": "new-after-snapshot", "name": "new",
-                 "schedule": "every 15m", "skills": ["brand-new-skill"]})
-    cj.save_jobs(jobs)
-
-    ok, _, _ = cb.rollback(backup_id=snap.name)
-    assert ok
-
-    live = cj.load_jobs()
-    by_id = {j["id"]: j for j in live}
-    assert "new-after-snapshot" in by_id
-    # New job's fields completely preserved
-    assert by_id["new-after-snapshot"]["skills"] == ["brand-new-skill"]
-    assert by_id["new-after-snapshot"]["schedule"] == "every 15m"
-
-
-def test_rollback_with_snapshot_missing_cron_succeeds(backup_env):
-    """Older snapshots (created before this feature shipped) have no
-    cron-jobs.json. Rollback must still restore the skills tree and not
-    error out."""
-    cb = backup_env["cb"]
-    home = backup_env["home"]
-    _write_skill(backup_env["skills"], "alpha")
-
-    # No cron/jobs.json at snapshot time — simulates a pre-feature snapshot
-    snap = cb.snapshot_skills(reason="test")
-    assert snap is not None
-    assert not (snap / cb.CRON_JOBS_FILENAME).exists()
-
-    # Later the user created a cron job
-    _write_cron_jobs(home, [
-        {"id": "later-job", "name": "l", "schedule": "every 1h", "skills": ["x"]},
-    ])
-
-    ok, msg, _ = cb.rollback(backup_id=snap.name)
-    # Main rollback still succeeds; cron report notes the missing file.
-    assert ok, msg
-    # Jobs.json untouched (nothing to restore from)
-    cj = _reload_cron_jobs(home)
-    jobs = cj.load_jobs()
-    assert jobs[0]["id"] == "later-job"
-    assert jobs[0]["skills"] == ["x"]
-
-
-def test_restore_cron_skill_links_standalone(backup_env):
-    """Unit-level test on _restore_cron_skill_links without the full rollback.
-    Verifies the report structure carefully."""
-    cb = backup_env["cb"]
-    home = backup_env["home"]
-
-    # Prime a snapshot dir manually with cron-jobs.json
-    backups_dir = home / "skills" / ".curator_backups" / "fake-id"
-    backups_dir.mkdir(parents=True)
-    (backups_dir / cb.CRON_JOBS_FILENAME).write_text(json.dumps([
-        {"id": "job-1", "name": "one", "skills": ["narrow-a", "narrow-b"]},
-        {"id": "job-2", "name": "two", "skill": "legacy-single"},
-        {"id": "job-gone", "name": "deleted", "skills": ["whatever"]},
-    ]), encoding="utf-8")
-
-    # Live jobs: job-1 got rewritten, job-2 unchanged, job-gone deleted
-    _write_cron_jobs(home, [
-        {"id": "job-1", "name": "one", "skills": ["umbrella"], "schedule": "every 1h"},
-        {"id": "job-2", "name": "two", "skill": "legacy-single", "schedule": "every 1h"},
-        {"id": "job-new", "name": "new", "skills": ["x"], "schedule": "every 1h"},
-    ])
-    _reload_cron_jobs(home)
-
-    report = cb._restore_cron_skill_links(backups_dir)
-    assert report["attempted"] is True
-    assert report["error"] is None
-    assert report["unchanged"] == 1  # job-2 matched
-    assert len(report["restored"]) == 1  # job-1 got restored
-    assert report["restored"][0]["job_id"] == "job-1"
-    assert report["restored"][0]["to"]["skills"] == ["narrow-a", "narrow-b"]
-    assert len(report["skipped_missing"]) == 1
-    assert report["skipped_missing"][0]["job_id"] == "job-gone"

tests/agent/test_curator_classification.py

@@ -548,266 +548,3 @@ def test_reconcile_model_block_visible_in_full_report(curator_env):
     md = (run_dir / "REPORT.md").read_text()
     assert "duplicate content, now a subsection" in md
     assert "pre-curator junk" in md
-
-
-# ---------------------------------------------------------------------------
-# _extract_absorbed_into_declarations — authoritative signal from delete calls
-# ---------------------------------------------------------------------------
-
-
-def test_extract_absorbed_into_picks_up_consolidation(curator_env):
-    """Delete call with absorbed_into=<umbrella> yields a declaration."""
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {
-            "name": "skill_manage",
-            "arguments": json.dumps({
-                "action": "delete",
-                "name": "narrow-skill",
-                "absorbed_into": "umbrella",
-            }),
-        },
-    ])
-    assert declarations == {
-        "narrow-skill": {"into": "umbrella", "declared": True},
-    }
-
-
-def test_extract_absorbed_into_empty_string_is_explicit_prune(curator_env):
-    """absorbed_into='' is recorded as an explicit prune declaration."""
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {
-            "name": "skill_manage",
-            "arguments": json.dumps({
-                "action": "delete",
-                "name": "stale",
-                "absorbed_into": "",
-            }),
-        },
-    ])
-    assert declarations == {"stale": {"into": "", "declared": True}}
-
-
-def test_extract_absorbed_into_missing_arg_ignored(curator_env):
-    """Delete call without absorbed_into is skipped — fallback to heuristic."""
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {
-            "name": "skill_manage",
-            "arguments": json.dumps({
-                "action": "delete",
-                "name": "legacy-skill",
-            }),
-        },
-    ])
-    assert declarations == {}
-
-
-def test_extract_absorbed_into_ignores_non_delete_actions(curator_env):
-    """Patch, create, write_file etc. must not leak into declarations."""
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {
-            "name": "skill_manage",
-            "arguments": json.dumps({
-                "action": "patch",
-                "name": "umbrella",
-                "old_string": "...",
-                "new_string": "...",
-                "absorbed_into": "something",  # bogus on non-delete, must be ignored
-            }),
-        },
-    ])
-    assert declarations == {}
-
-
-def test_extract_absorbed_into_accepts_dict_arguments(curator_env):
-    """arguments can arrive as a dict (defensive path) — still works."""
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {
-            "name": "skill_manage",
-            "arguments": {
-                "action": "delete",
-                "name": "narrow",
-                "absorbed_into": "umbrella",
-            },
-        },
-    ])
-    assert declarations == {"narrow": {"into": "umbrella", "declared": True}}
-
-
-def test_extract_absorbed_into_strips_whitespace(curator_env):
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {
-            "name": "skill_manage",
-            "arguments": json.dumps({
-                "action": "delete",
-                "name": "  narrow  ",
-                "absorbed_into": "  umbrella  ",
-            }),
-        },
-    ])
-    assert declarations == {"narrow": {"into": "umbrella", "declared": True}}
-
-
-def test_extract_absorbed_into_ignores_non_skill_manage_calls(curator_env):
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {"name": "terminal", "arguments": json.dumps({"command": "ls"})},
-        {"name": "read_file", "arguments": json.dumps({"path": "/tmp/x"})},
-    ])
-    assert declarations == {}
-
-
-def test_extract_absorbed_into_handles_malformed_arguments(curator_env):
-    """Garbage JSON in arguments must not crash the extractor."""
-    declarations = curator_env._extract_absorbed_into_declarations([
-        {"name": "skill_manage", "arguments": "{not json"},
-        {"name": "skill_manage", "arguments": None},
-        {"name": "skill_manage"},  # no arguments key at all
-    ])
-    assert declarations == {}
-
-
-# ---------------------------------------------------------------------------
-# _reconcile_classification with absorbed_into declarations (authoritative)
-# ---------------------------------------------------------------------------
-
-
-def test_reconcile_absorbed_into_beats_everything_else(curator_env):
-    """Model declared absorbed_into at delete; YAML/heuristic disagree — declaration wins.
-
-    This is the exact #18671 regression: the model forgets to emit the YAML
-    summary block, the heuristic's substring match misses because the
-    umbrella's patch content doesn't literally contain the old skill's
-    slug. Previously this fell through to 'no-evidence fallback' prune,
-    which dropped the cron ref instead of rewriting. With absorbed_into
-    declared, the model tells us directly.
-    """
-    out = curator_env._reconcile_classification(
-        removed=["pr-review-format"],
-        heuristic={"consolidated": [], "pruned": [{"name": "pr-review-format"}]},
-        model_block={"consolidations": [], "prunings": []},  # model forgot YAML block
-        destinations={"hermes-agent-dev"},
-        absorbed_declarations={
-            "pr-review-format": {"into": "hermes-agent-dev", "declared": True},
-        },
-    )
-    assert len(out["consolidated"]) == 1
-    assert out["pruned"] == []
-    e = out["consolidated"][0]
-    assert e["name"] == "pr-review-format"
-    assert e["into"] == "hermes-agent-dev"
-    assert "absorbed_into" in e["source"]
-
-
-def test_reconcile_absorbed_into_empty_is_explicit_prune(curator_env):
-    """absorbed_into='' takes precedence and routes to pruned, not fallback."""
-    out = curator_env._reconcile_classification(
-        removed=["stale"],
-        heuristic={"consolidated": [], "pruned": [{"name": "stale"}]},
-        model_block={"consolidations": [], "prunings": []},
-        destinations=set(),
-        absorbed_declarations={
-            "stale": {"into": "", "declared": True},
-        },
-    )
-    assert out["consolidated"] == []
-    assert len(out["pruned"]) == 1
-    assert "model-declared prune" in out["pruned"][0]["source"]
-
-
-def test_reconcile_absorbed_into_nonexistent_target_falls_through(curator_env):
-    """If the declared umbrella doesn't exist in destinations, fall through to
-    heuristic/YAML logic. Shouldn't happen in practice (the tool validates at
-    delete time) but the reconciler is defensive."""
-    out = curator_env._reconcile_classification(
-        removed=["thing"],
-        heuristic={
-            "consolidated": [{"name": "thing", "into": "real-umbrella", "evidence": "..."}],
-            "pruned": [],
-        },
-        model_block={"consolidations": [], "prunings": []},
-        destinations={"real-umbrella"},
-        absorbed_declarations={
-            "thing": {"into": "ghost-umbrella", "declared": True},
-        },
-    )
-    assert len(out["consolidated"]) == 1
-    assert out["consolidated"][0]["into"] == "real-umbrella"
-    assert "tool-call audit" in out["consolidated"][0]["source"]
-
-
-def test_reconcile_declaration_preserves_yaml_reason(curator_env):
-    """When the model both declared absorbed_into AND emitted YAML with reason,
-    the reason carries through so REPORT.md still has it."""
-    out = curator_env._reconcile_classification(
-        removed=["narrow"],
-        heuristic={"consolidated": [], "pruned": []},
-        model_block={
-            "consolidations": [{
-                "from": "narrow",
-                "into": "umbrella",
-                "reason": "duplicate of umbrella's main content",
-            }],
-            "prunings": [],
-        },
-        destinations={"umbrella"},
-        absorbed_declarations={
-            "narrow": {"into": "umbrella", "declared": True},
-        },
-    )
-    assert len(out["consolidated"]) == 1
-    e = out["consolidated"][0]
-    assert e["into"] == "umbrella"
-    assert "absorbed_into" in e["source"]
-    assert e["reason"] == "duplicate of umbrella's main content"
-
-
-def test_reconcile_without_declarations_preserves_legacy_behavior(curator_env):
-    """Backward compat: no absorbed_declarations arg → all existing logic intact."""
-    out = curator_env._reconcile_classification(
-        removed=["thing"],
-        heuristic={
-            "consolidated": [{"name": "thing", "into": "umbrella", "evidence": "..."}],
-            "pruned": [],
-        },
-        model_block={"consolidations": [], "prunings": []},
-        destinations={"umbrella"},
-        # no absorbed_declarations — defaults to None → behaves identically to pre-change
-    )
-    assert len(out["consolidated"]) == 1
-    assert out["consolidated"][0]["into"] == "umbrella"
-
-
-def test_reconcile_mixed_declarations_and_legacy_calls(curator_env):
-    """Real-world run: some deletes declared absorbed_into, some didn't.
-    Declared ones use the authoritative path; others fall through to YAML/heuristic.
-    """
-    out = curator_env._reconcile_classification(
-        removed=["declared-cons", "declared-prune", "legacy-cons", "legacy-prune"],
-        heuristic={
-            "consolidated": [
-                {"name": "legacy-cons", "into": "umbrella-a", "evidence": "..."},
-            ],
-            "pruned": [{"name": "legacy-prune"}],
-        },
-        model_block={"consolidations": [], "prunings": []},
-        destinations={"umbrella-a", "umbrella-b"},
-        absorbed_declarations={
-            "declared-cons": {"into": "umbrella-b", "declared": True},
-            "declared-prune": {"into": "", "declared": True},
-        },
-    )
-    cons_by_name = {e["name"]: e for e in out["consolidated"]}
-    pruned_by_name = {e["name"]: e for e in out["pruned"]}
-
-    assert "declared-cons" in cons_by_name
-    assert cons_by_name["declared-cons"]["into"] == "umbrella-b"
-    assert "absorbed_into" in cons_by_name["declared-cons"]["source"]
-
-    assert "legacy-cons" in cons_by_name
-    assert cons_by_name["legacy-cons"]["into"] == "umbrella-a"
-    assert "tool-call audit" in cons_by_name["legacy-cons"]["source"]
-
-    assert "declared-prune" in pruned_by_name
-    assert "model-declared prune" in pruned_by_name["declared-prune"]["source"]
-
-    assert "legacy-prune" in pruned_by_name
-    assert "no-evidence fallback" in pruned_by_name["legacy-prune"]["source"]

tests/agent/test_curator_reports.py

@@ -270,167 +270,3 @@ def test_state_transitions_captured_in_report(curator_env):
     assert "State transitions" in md
     assert "getting-old" in md
     assert "active → stale" in md
-
-
-# ---------------------------------------------------------------------------
-# Cron job skill reference rewriting (curator ↔ cron integration)
-# ---------------------------------------------------------------------------
-#
-# When the curator consolidates skill X into umbrella Y during a run, any
-# cron job that listed X in its ``skills`` field would fail to load X at
-# run time — the scheduler logs a warning and skips it, so the scheduled
-# job runs without the instructions it was scheduled to follow. These
-# tests verify that _write_run_report calls into cron.jobs to repair
-# those references and records what it did in both run.json and
-# cron_rewrites.json.
-
-
-@pytest.fixture
-def curator_env_with_cron(curator_env, monkeypatch):
-    """Extend curator_env with an initialized + repointed cron.jobs module."""
-    home = curator_env["home"]
-    (home / "cron").mkdir(exist_ok=True)
-    (home / "cron" / "output").mkdir(exist_ok=True)
-
-    import importlib
-    import cron.jobs as jobs_mod
-    importlib.reload(jobs_mod)
-    monkeypatch.setattr(jobs_mod, "HERMES_DIR", home)
-    monkeypatch.setattr(jobs_mod, "CRON_DIR", home / "cron")
-    monkeypatch.setattr(jobs_mod, "JOBS_FILE", home / "cron" / "jobs.json")
-    monkeypatch.setattr(jobs_mod, "OUTPUT_DIR", home / "cron" / "output")
-
-    return {**curator_env, "jobs": jobs_mod}
-
-
-def test_curator_rewrites_cron_skills_when_skill_consolidated(curator_env_with_cron):
-    """A skill consolidated into an umbrella should be rewritten in any
-    cron job's skills list; the rewrite should be visible in run.json
-    and cron_rewrites.json."""
-    curator = curator_env_with_cron["curator"]
-    jobs = curator_env_with_cron["jobs"]
-
-    # Create a cron job that depends on a soon-to-be-consolidated skill
-    job = jobs.create_job(
-        prompt="",
-        schedule="every 1h",
-        skills=["foo"],
-        name="foo-watcher",
-    )
-
-    # Simulate a curator pass that consolidated `foo` → `foo-umbrella`
-    before = [{"name": "foo", "state": "active", "pinned": False}]
-    after = [{"name": "foo-umbrella", "state": "active", "pinned": False}]
-
-    run_dir = curator._write_run_report(
-        started_at=datetime.now(timezone.utc),
-        elapsed_seconds=3.0,
-        auto_counts={"checked": 1, "marked_stale": 0, "archived": 0, "reactivated": 0},
-        auto_summary="no changes",
-        before_report=before,
-        before_names={"foo"},
-        after_report=after,
-        llm_meta=_make_llm_meta(
-            final="Consolidated foo into foo-umbrella.",
-            tool_calls=[
-                {
-                    "name": "skill_manage",
-                    "arguments": json.dumps({
-                        "action": "write_file",
-                        "name": "foo-umbrella",
-                        "file_path": "references/foo.md",
-                        "file_content": "from foo",
-                    }),
-                },
-            ],
-        ),
-    )
-
-    # Cron job is rewritten on disk
-    loaded = jobs.get_job(job["id"])
-    assert loaded["skills"] == ["foo-umbrella"]
-    assert loaded["skill"] == "foo-umbrella"
-
-    # Rewrite is recorded in run.json
-    payload = json.loads((run_dir / "run.json").read_text())
-    assert payload["cron_rewrites"]["jobs_updated"] == 1
-    assert payload["counts"]["cron_jobs_rewritten"] == 1
-    rewrites = payload["cron_rewrites"]["rewrites"]
-    assert len(rewrites) == 1
-    assert rewrites[0]["mapped"] == {"foo": "foo-umbrella"}
-
-    # Separate cron_rewrites.json is written for convenience
-    cron_file = run_dir / "cron_rewrites.json"
-    assert cron_file.exists()
-    detail = json.loads(cron_file.read_text())
-    assert detail["jobs_updated"] == 1
-
-    # Markdown surfaces the change
-    md = (run_dir / "REPORT.md").read_text()
-    assert "Cron job skill references rewritten" in md
-    assert "foo-watcher" in md
-    assert "foo-umbrella" in md
-
-
-def test_curator_drops_pruned_skill_from_cron_job(curator_env_with_cron):
-    """A pruned (no-umbrella) skill should be dropped from the cron
-    job's skill list entirely — there's no forwarding target."""
-    curator = curator_env_with_cron["curator"]
-    jobs = curator_env_with_cron["jobs"]
-
-    job = jobs.create_job(
-        prompt="",
-        schedule="every 1h",
-        skills=["keep", "stale-one"],
-    )
-
-    before = [{"name": "stale-one", "state": "active", "pinned": False}]
-    after: list = []  # stale-one was archived with no target
-
-    run_dir = curator._write_run_report(
-        started_at=datetime.now(timezone.utc),
-        elapsed_seconds=1.0,
-        auto_counts={"checked": 1, "marked_stale": 0, "archived": 1, "reactivated": 0},
-        auto_summary="1 archived",
-        before_report=before,
-        before_names={"stale-one"},
-        after_report=after,
-        llm_meta=_make_llm_meta(),  # no tool calls → classifier marks it pruned
-    )
-
-    loaded = jobs.get_job(job["id"])
-    assert loaded["skills"] == ["keep"]
-
-    payload = json.loads((run_dir / "run.json").read_text())
-    assert payload["cron_rewrites"]["jobs_updated"] == 1
-    rewrites = payload["cron_rewrites"]["rewrites"]
-    assert rewrites[0]["dropped"] == ["stale-one"]
-
-
-def test_curator_report_has_no_cron_section_when_nothing_changes(curator_env_with_cron):
-    """When the curator run doesn't touch any skills, cron jobs are
-    untouched and cron_rewrites.json is not even written."""
-    curator = curator_env_with_cron["curator"]
-    jobs = curator_env_with_cron["jobs"]
-
-    jobs.create_job(prompt="", schedule="every 1h", skills=["foo"])
-
-    run_dir = curator._write_run_report(
-        started_at=datetime.now(timezone.utc),
-        elapsed_seconds=1.0,
-        auto_counts={"checked": 0, "marked_stale": 0, "archived": 0, "reactivated": 0},
-        auto_summary="no changes",
-        before_report=[{"name": "foo", "state": "active", "pinned": False}],
-        before_names={"foo"},
-        after_report=[{"name": "foo", "state": "active", "pinned": False}],
-        llm_meta=_make_llm_meta(),
-    )
-
-    # No rewrites → no separate file, no section in md
-    assert not (run_dir / "cron_rewrites.json").exists()
-    md = (run_dir / "REPORT.md").read_text()
-    assert "Cron job skill references rewritten" not in md
-
-    payload = json.loads((run_dir / "run.json").read_text())
-    assert payload["cron_rewrites"]["jobs_updated"] == 0
-    assert payload["counts"]["cron_jobs_rewritten"] == 0

tests/agent/test_moonshot_schema.py

@@ -115,15 +115,9 @@ class TestMissingTypeFilled:
 
 
 class TestAnyOfParentType:
-    """Rule 2: type must not appear at the anyOf parent level.
+    """Rule 2: type must not appear at the anyOf parent level."""
 
-    When an anyOf contains a null-type branch, Moonshot rejects it.
-    The sanitizer collapses the anyOf: single non-null branch is promoted,
-    multiple non-null branches have null removed from the list.
-    """
-
-    def test_anyof_null_branch_collapsed_to_single_type(self):
-        """anyOf [string, null] → plain string (anyOf removed)."""
+    def test_parent_type_stripped_when_anyof_present(self):
         params = {
             "type": "object",
             "properties": {
@@ -138,46 +132,25 @@ class TestAnyOfParentType:
         }
         out = sanitize_moonshot_tool_parameters(params)
         from_format = out["properties"]["from_format"]
-        # null branch removed, anyOf collapsed to the single non-null type
-        assert "anyOf" not in from_format
-        assert from_format["type"] == "string"
+        assert "type" not in from_format
+        assert "anyOf" in from_format
 
-    def test_anyof_multiple_non_null_preserved(self):
-        """anyOf [string, integer] (no null) → kept as-is with parent type stripped."""
+    def test_anyof_children_missing_type_get_filled(self):
         params = {
             "type": "object",
             "properties": {
-                "mode": {
+                "value": {
                     "anyOf": [
                         {"type": "string"},
-                        {"type": "integer"},
+                        {"description": "A typeless option"},
                     ],
                 },
             },
         }
         out = sanitize_moonshot_tool_parameters(params)
-        mode = out["properties"]["mode"]
-        assert "anyOf" in mode
-        assert "type" not in mode  # parent type stripped
-
-    def test_anyof_enum_with_null_collapsed(self):
-        """anyOf [{enum: [...], type: string}, {type: null}] → enum + type only."""
-        params = {
-            "type": "object",
-            "properties": {
-                "db_type": {
-                    "anyOf": [
-                        {"enum": ["mysql", "postgresql", ""]},
-                        {"type": "null"},
-                    ],
-                },
-            },
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        db_type = out["properties"]["db_type"]
-        assert "anyOf" not in db_type
-        assert db_type["type"] == "string"
-        assert db_type["enum"] == ["mysql", "postgresql"]  # "" stripped by enum cleanup
+        children = out["properties"]["value"]["anyOf"]
+        assert children[0]["type"] == "string"
+        assert "type" in children[1]
 
 
 class TestTopLevelGuarantees:
@@ -253,7 +226,7 @@ class TestRealWorldMCPShape:
     """End-to-end: a realistic MCP-style schema that used to 400 on Moonshot."""
 
     def test_combined_rewrites(self):
-        # Shape: missing type on a property, anyOf with parent type + null, array
+        # Shape: missing type on a property, anyOf with parent type, array
         # items without type — all in one tool.
         params = {
             "type": "object",
@@ -275,125 +248,7 @@ class TestRealWorldMCPShape:
         }
         out = sanitize_moonshot_tool_parameters(params)
         assert out["properties"]["query"]["type"] == "string"
-        # anyOf with null collapsed to plain type
-        assert "anyOf" not in out["properties"]["filter"]
-        assert out["properties"]["filter"]["type"] == "string"
+        assert "type" not in out["properties"]["filter"]
+        assert out["properties"]["filter"]["anyOf"][0]["type"] == "string"
         assert out["properties"]["tags"]["items"]["type"] == "string"
         assert out["required"] == ["query"]
-
-
-class TestEnumNullStripping:
-    """Rule 3: Moonshot rejects null/empty-string inside enum arrays."""
-
-    def test_enum_null_value_stripped(self):
-        """enum containing Python None must have it removed for Moonshot."""
-        params = {
-            "type": "object",
-            "properties": {
-                "db_type": {
-                    "type": "string",
-                    "enum": ["mysql", "postgresql", None],
-                },
-            },
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        db_type = out["properties"]["db_type"]
-        assert None not in db_type["enum"]
-        assert "mysql" in db_type["enum"]
-        assert "postgresql" in db_type["enum"]
-
-    def test_enum_empty_string_stripped(self):
-        """enum containing empty string '' must have it removed for Moonshot."""
-        params = {
-            "type": "object",
-            "properties": {
-                "db_type": {
-                    "type": "string",
-                    "enum": ["mysql", "postgresql", ""],
-                },
-            },
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        db_type = out["properties"]["db_type"]
-        assert "" not in db_type["enum"]
-        assert db_type["enum"] == ["mysql", "postgresql"]
-
-    def test_enum_all_null_becomes_no_enum(self):
-        """enum that only had null/empty values is dropped entirely."""
-        params = {
-            "type": "object",
-            "properties": {
-                "val": {
-                    "type": "string",
-                    "enum": [None, ""],
-                },
-            },
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        assert "enum" not in out["properties"]["val"]
-
-    def test_dataslayer_db_type_after_mcp_normalize(self):
-        """Real-world: dataslayer db_type anyOf+enum after MCP normalization."""
-        # This is the exact shape after _normalize_mcp_input_schema runs:
-        # anyOf collapsed, but enum still has null + empty string
-        params = {
-            "type": "object",
-            "properties": {
-                "datasource": {"type": "string"},
-                "db_type": {
-                    "enum": ["mysql", "mariadb", "postgresql", "sqlserver", "oracle", "", None],
-                    "type": "string",
-                    "nullable": True,
-                    "default": None,
-                },
-            },
-            "required": ["datasource"],
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        db_type = out["properties"]["db_type"]
-        assert "nullable" not in db_type, "nullable keyword must be stripped"
-        assert None not in db_type["enum"]
-        assert "" not in db_type["enum"]
-        assert db_type["enum"] == ["mysql", "mariadb", "postgresql", "sqlserver", "oracle"]
-        assert db_type["type"] == "string"
-
-    def test_enum_on_object_type_not_stripped(self):
-        """enum on non-scalar types (object) should NOT be touched."""
-        params = {
-            "type": "object",
-            "properties": {
-                "config": {
-                    "type": "object",
-                    "properties": {},
-                    "enum": [{}, None],
-                },
-            },
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        # object-typed enum should pass through unchanged
-        assert "enum" in out["properties"]["config"]
-
-    def test_anyof_collapse_still_runs_nullable_and_enum_cleanup(self):
-        """After anyOf collapses to a single non-null branch, the merged
-        node must still have ``nullable`` stripped and null/empty-string
-        values removed from enum — not skipped by the early anyOf return.
-        """
-        params = {
-            "type": "object",
-            "properties": {
-                "db_type": {
-                    "anyOf": [
-                        {"enum": ["mysql", "postgresql", "", None]},
-                        {"type": "null"},
-                    ],
-                    "nullable": True,
-                },
-            },
-        }
-        out = sanitize_moonshot_tool_parameters(params)
-        db_type = out["properties"]["db_type"]
-        assert "anyOf" not in db_type
-        assert "nullable" not in db_type, "nullable must be stripped after anyOf collapse"
-        assert db_type["type"] == "string"
-        assert db_type["enum"] == ["mysql", "postgresql"], \
-            "null/empty enum values must be stripped after anyOf collapse"

tests/agent/test_openrouter_response_cache.py

@@ -1,284 +0,0 @@
-"""Tests for OpenRouter response caching header injection."""
-
-from types import SimpleNamespace
-from unittest.mock import patch
-
-import pytest
-
-
-# ---------------------------------------------------------------------------
-# build_or_headers
-# ---------------------------------------------------------------------------
-
-class TestBuildOrHeaders:
-    """Test the build_or_headers() helper in agent/auxiliary_client.py."""
-
-    def test_base_attribution_always_present(self):
-        """Attribution headers must always be included regardless of cache setting."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": False})
-        assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
-        assert headers["X-OpenRouter-Title"] == "Hermes Agent"
-        assert headers["X-OpenRouter-Categories"] == "productivity,cli-agent"
-
-    def test_cache_enabled(self):
-        """When response_cache is True, X-OpenRouter-Cache header is set."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True})
-        assert headers["X-OpenRouter-Cache"] == "true"
-
-    def test_cache_disabled(self):
-        """When response_cache is False, no cache header is sent."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": False})
-        assert "X-OpenRouter-Cache" not in headers
-        assert "X-OpenRouter-Cache-TTL" not in headers
-
-    def test_cache_disabled_by_default_empty_config(self):
-        """Empty config dict means no cache headers (response_cache defaults to False)."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={})
-        assert "X-OpenRouter-Cache" not in headers
-
-    def test_ttl_default(self):
-        """Default TTL (300) is included when cache is enabled."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 300})
-        assert headers["X-OpenRouter-Cache-TTL"] == "300"
-
-    def test_ttl_custom(self):
-        """Custom TTL values within range are sent."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 3600})
-        assert headers["X-OpenRouter-Cache-TTL"] == "3600"
-
-    def test_ttl_max(self):
-        """Maximum TTL (86400) is accepted."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 86400})
-        assert headers["X-OpenRouter-Cache-TTL"] == "86400"
-
-    def test_ttl_out_of_range_too_high(self):
-        """TTL above 86400 is silently ignored (no TTL header sent)."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 100000})
-        assert "X-OpenRouter-Cache-TTL" not in headers
-        # But cache is still enabled
-        assert headers["X-OpenRouter-Cache"] == "true"
-
-    def test_ttl_out_of_range_zero(self):
-        """TTL of 0 is below minimum — no TTL header sent."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 0})
-        assert "X-OpenRouter-Cache-TTL" not in headers
-
-    def test_ttl_negative(self):
-        """Negative TTL is ignored."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": -5})
-        assert "X-OpenRouter-Cache-TTL" not in headers
-
-    def test_ttl_not_a_number(self):
-        """Non-numeric TTL is ignored."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": "five"})
-        assert "X-OpenRouter-Cache-TTL" not in headers
-
-    def test_ttl_float_truncated(self):
-        """Float TTL values are truncated to int."""
-        from agent.auxiliary_client import build_or_headers
-
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 600.7})
-        assert headers["X-OpenRouter-Cache-TTL"] == "600"
-
-    def test_returns_fresh_dict(self):
-        """Each call returns a new dict so mutations don't leak."""
-        from agent.auxiliary_client import build_or_headers
-
-        cfg = {"response_cache": True}
-        h1 = build_or_headers(or_config=cfg)
-        h2 = build_or_headers(or_config=cfg)
-        assert h1 is not h2
-        assert h1 == h2
-
-    def test_none_config_falls_back_to_load_config(self):
-        """When or_config is None, build_or_headers reads from load_config()."""
-        from agent.auxiliary_client import build_or_headers
-
-        fake_cfg = {
-            "openrouter": {"response_cache": True, "response_cache_ttl": 900},
-        }
-        with patch("hermes_cli.config.load_config", return_value=fake_cfg):
-            headers = build_or_headers(or_config=None)
-        assert headers["X-OpenRouter-Cache"] == "true"
-        assert headers["X-OpenRouter-Cache-TTL"] == "900"
-
-    def test_none_config_load_config_fails_gracefully(self):
-        """When load_config() fails, build_or_headers still returns base headers."""
-        from agent.auxiliary_client import build_or_headers
-
-        with patch("hermes_cli.config.load_config", side_effect=RuntimeError("boom")):
-            headers = build_or_headers(or_config=None)
-        # Should have base attribution but no cache headers
-        assert "HTTP-Referer" in headers
-        assert "X-OpenRouter-Cache" not in headers
-
-
-# ---------------------------------------------------------------------------
-# Environment variable overrides
-# ---------------------------------------------------------------------------
-
-class TestEnvVarOverrides:
-    """Test env var precedence over config.yaml for response caching."""
-
-    def test_env_enables_cache(self, monkeypatch):
-        """HERMES_OPENROUTER_CACHE=true enables cache even when config disables it."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", "true")
-        headers = build_or_headers(or_config={"response_cache": False})
-        assert headers["X-OpenRouter-Cache"] == "true"
-
-    def test_env_disables_cache(self, monkeypatch):
-        """HERMES_OPENROUTER_CACHE=false disables cache even when config enables it."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", "false")
-        headers = build_or_headers(or_config={"response_cache": True})
-        assert "X-OpenRouter-Cache" not in headers
-
-    @pytest.mark.parametrize("value", ["1", "true", "TRUE", "yes", "Yes", "on"])
-    def test_truthy_values(self, monkeypatch, value):
-        """Various truthy strings enable caching."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", value)
-        headers = build_or_headers(or_config={})
-        assert headers["X-OpenRouter-Cache"] == "true"
-
-    @pytest.mark.parametrize("value", ["0", "false", "no", "off", "maybe", ""])
-    def test_non_truthy_values(self, monkeypatch, value):
-        """Non-truthy strings do not enable caching (empty falls through to config)."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", value)
-        # Empty string falls through to config; others are explicitly non-truthy
-        if value == "":
-            # Empty env var falls through to config default (False)
-            headers = build_or_headers(or_config={"response_cache": False})
-        else:
-            headers = build_or_headers(or_config={"response_cache": True})
-        assert "X-OpenRouter-Cache" not in headers
-
-    def test_env_ttl_overrides_config(self, monkeypatch):
-        """HERMES_OPENROUTER_CACHE_TTL overrides config TTL."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", "true")
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE_TTL", "1800")
-        headers = build_or_headers(or_config={"response_cache_ttl": 300})
-        assert headers["X-OpenRouter-Cache-TTL"] == "1800"
-
-    @pytest.mark.parametrize("ttl", ["0", "86401", "abc", "-1", "12.5"])
-    def test_invalid_env_ttl_dropped(self, monkeypatch, ttl):
-        """Invalid TTL env values are ignored; cache still enabled without TTL."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", "1")
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE_TTL", ttl)
-        headers = build_or_headers(or_config={})
-        assert headers["X-OpenRouter-Cache"] == "true"
-        assert "X-OpenRouter-Cache-TTL" not in headers
-
-    @pytest.mark.parametrize("ttl", ["1", "300", "86400"])
-    def test_valid_env_ttl_boundaries(self, monkeypatch, ttl):
-        """Boundary TTL values (1, 300, 86400) are accepted."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE", "yes")
-        monkeypatch.setenv("HERMES_OPENROUTER_CACHE_TTL", ttl)
-        assert build_or_headers(or_config={})["X-OpenRouter-Cache-TTL"] == ttl
-
-    def test_no_env_vars_falls_through_to_config(self, monkeypatch):
-        """Without env vars, config.yaml controls behavior."""
-        from agent.auxiliary_client import build_or_headers
-
-        monkeypatch.delenv("HERMES_OPENROUTER_CACHE", raising=False)
-        monkeypatch.delenv("HERMES_OPENROUTER_CACHE_TTL", raising=False)
-        headers = build_or_headers(or_config={"response_cache": True, "response_cache_ttl": 600})
-        assert headers["X-OpenRouter-Cache"] == "true"
-        assert headers["X-OpenRouter-Cache-TTL"] == "600"
-
-class TestDefaultConfig:
-    """Verify the openrouter config section is in DEFAULT_CONFIG."""
-
-    def test_openrouter_section_exists(self):
-        from hermes_cli.config import DEFAULT_CONFIG
-
-        assert "openrouter" in DEFAULT_CONFIG
-        or_cfg = DEFAULT_CONFIG["openrouter"]
-        assert or_cfg["response_cache"] is True
-        assert or_cfg["response_cache_ttl"] == 300
-
-
-# ---------------------------------------------------------------------------
-# _check_openrouter_cache_status
-# ---------------------------------------------------------------------------
-
-class TestCheckOpenrouterCacheStatus:
-    """Test the _check_openrouter_cache_status method on AIAgent."""
-
-    def _make_agent(self):
-        """Create a minimal AIAgent-like object with just the method under test."""
-        from run_agent import AIAgent
-
-        # Use object.__new__ to skip __init__, then set the attributes we need
-        agent = object.__new__(AIAgent)
-        agent._or_cache_hits = 0
-        return agent
-
-    def test_hit_increments_counter(self):
-        agent = self._make_agent()
-        resp = SimpleNamespace(headers={"x-openrouter-cache-status": "HIT"})
-        agent._check_openrouter_cache_status(resp)
-        assert agent._or_cache_hits == 1
-        # Second hit increments
-        agent._check_openrouter_cache_status(resp)
-        assert agent._or_cache_hits == 2
-
-    def test_miss_does_not_increment(self):
-        agent = self._make_agent()
-        resp = SimpleNamespace(headers={"x-openrouter-cache-status": "MISS"})
-        agent._check_openrouter_cache_status(resp)
-        assert getattr(agent, "_or_cache_hits", 0) == 0
-
-    def test_no_header_is_noop(self):
-        agent = self._make_agent()
-        resp = SimpleNamespace(headers={})
-        agent._check_openrouter_cache_status(resp)
-        assert getattr(agent, "_or_cache_hits", 0) == 0
-
-    def test_none_response_is_safe(self):
-        agent = self._make_agent()
-        agent._check_openrouter_cache_status(None)  # no crash
-
-    def test_no_headers_attr_is_safe(self):
-        agent = self._make_agent()
-        agent._check_openrouter_cache_status(object())  # no crash
-
-    def test_case_insensitive(self):
-        agent = self._make_agent()
-        resp = SimpleNamespace(headers={"x-openrouter-cache-status": "hit"})
-        agent._check_openrouter_cache_status(resp)
-        assert agent._or_cache_hits == 1

tests/agent/test_skill_commands.py

@@ -125,58 +125,6 @@ class TestScanSkillCommands:
         assert "/knowledge-brain" in result
         assert result["/knowledge-brain"]["name"] == "knowledge-brain"
 
-    def test_get_skill_commands_rescans_when_platform_scope_changes(self, tmp_path):
-        """Platform-specific disabled-skill caches must not leak across platforms.
-
-        Regression test for #14536: a gateway process serving Telegram
-        and Discord concurrently would seed the process-global cache
-        with whichever platform scanned first, and subsequent
-        ``get_skill_commands()`` calls from the other platform silently
-        inherited that filter.
-        """
-        import agent.skill_commands as sc_mod
-        from agent.skill_commands import get_skill_commands
-
-        def _disabled_skills():
-            platform = os.getenv("HERMES_PLATFORM")
-            if platform == "telegram":
-                return {"telegram-only"}
-            if platform == "discord":
-                return {"discord-only"}
-            return set()
-
-        with (
-            patch("tools.skills_tool.SKILLS_DIR", tmp_path),
-            patch("tools.skills_tool._get_disabled_skill_names", side_effect=_disabled_skills),
-            patch.object(sc_mod, "_skill_commands", {}),
-            patch.object(sc_mod, "_skill_commands_platform", None),
-        ):
-            _make_skill(tmp_path, "shared")
-            _make_skill(tmp_path, "telegram-only")
-            _make_skill(tmp_path, "discord-only")
-
-            with patch.dict(os.environ, {"HERMES_PLATFORM": "telegram"}):
-                telegram_commands = dict(get_skill_commands())
-
-            assert "/shared" in telegram_commands
-            assert "/discord-only" in telegram_commands
-            assert "/telegram-only" not in telegram_commands
-
-            with patch.dict(os.environ, {"HERMES_PLATFORM": "discord"}):
-                discord_commands = dict(get_skill_commands())
-
-            assert "/shared" in discord_commands
-            assert "/telegram-only" in discord_commands
-            assert "/discord-only" not in discord_commands
-
-            # Switching back to telegram must also rescan — not re-serve
-            # the discord view that was just cached.
-            with patch.dict(os.environ, {"HERMES_PLATFORM": "telegram"}):
-                telegram_again = dict(get_skill_commands())
-
-            assert "/telegram-only" not in telegram_again
-            assert "/discord-only" in telegram_again
-
 
     def test_special_chars_stripped_from_cmd_key(self, tmp_path):
         """Skill names with +, /, or other special chars produce clean cmd keys."""

tests/agent/test_skill_utils.py

@@ -1,58 +0,0 @@
-"""Tests for agent/skill_utils.py — extract_skill_conditions metadata handling."""
-
-from agent.skill_utils import extract_skill_conditions
-
-
-def test_metadata_as_dict_with_hermes():
-    """Normal case: metadata is a dict containing hermes keys."""
-    frontmatter = {
-        "metadata": {
-            "hermes": {
-                "fallback_for_toolsets": ["toolset_a"],
-                "requires_toolsets": ["toolset_b"],
-                "fallback_for_tools": ["tool_x"],
-                "requires_tools": ["tool_y"],
-            }
-        }
-    }
-    result = extract_skill_conditions(frontmatter)
-    assert result["fallback_for_toolsets"] == ["toolset_a"]
-    assert result["requires_toolsets"] == ["toolset_b"]
-    assert result["fallback_for_tools"] == ["tool_x"]
-    assert result["requires_tools"] == ["tool_y"]
-
-
-def test_metadata_as_string_does_not_crash():
-    """Bug case: metadata is a non-dict truthy value (e.g. a YAML string)."""
-    frontmatter = {"metadata": "some text"}
-    result = extract_skill_conditions(frontmatter)
-    assert result == {
-        "fallback_for_toolsets": [],
-        "requires_toolsets": [],
-        "fallback_for_tools": [],
-        "requires_tools": [],
-    }
-
-
-def test_metadata_as_none():
-    """metadata key is present but set to null/None."""
-    frontmatter = {"metadata": None}
-    result = extract_skill_conditions(frontmatter)
-    assert result == {
-        "fallback_for_toolsets": [],
-        "requires_toolsets": [],
-        "fallback_for_tools": [],
-        "requires_tools": [],
-    }
-
-
-def test_metadata_missing_entirely():
-    """metadata key is absent from frontmatter."""
-    frontmatter = {"name": "my-skill", "description": "Does stuff."}
-    result = extract_skill_conditions(frontmatter)
-    assert result == {
-        "fallback_for_toolsets": [],
-        "requires_toolsets": [],
-        "fallback_for_tools": [],
-        "requires_tools": [],
-    }

tests/agent/test_tool_guardrails.py

@@ -1,238 +0,0 @@
-"""Pure tool-call guardrail primitive tests."""
-
-import json
-
-from agent.tool_guardrails import (
-    ToolCallGuardrailConfig,
-    ToolCallGuardrailController,
-    ToolCallSignature,
-    canonical_tool_args,
-)
-
-
-def test_tool_call_signature_hashes_canonical_nested_unicode_args_without_exposing_raw_args():
-    args_a = {
-        "z": [{"β": "☤", "a": 1}],
-        "a": {"y": 2, "x": "secret-token-value"},
-    }
-    args_b = {
-        "a": {"x": "secret-token-value", "y": 2},
-        "z": [{"a": 1, "β": "☤"}],
-    }
-
-    assert canonical_tool_args(args_a) == canonical_tool_args(args_b)
-    sig_a = ToolCallSignature.from_call("web_search", args_a)
-    sig_b = ToolCallSignature.from_call("web_search", args_b)
-
-    assert sig_a == sig_b
-    assert len(sig_a.args_hash) == 64
-    metadata = sig_a.to_metadata()
-    assert metadata == {"tool_name": "web_search", "args_hash": sig_a.args_hash}
-    assert "secret-token-value" not in json.dumps(metadata)
-    assert "☤" not in json.dumps(metadata)
-
-
-def test_default_config_is_soft_warning_only_with_hard_stop_disabled():
-    cfg = ToolCallGuardrailConfig()
-
-    assert cfg.warnings_enabled is True
-    assert cfg.hard_stop_enabled is False
-    assert cfg.exact_failure_warn_after == 2
-    assert cfg.same_tool_failure_warn_after == 3
-    assert cfg.no_progress_warn_after == 2
-    assert cfg.exact_failure_block_after == 5
-    assert cfg.same_tool_failure_halt_after == 8
-    assert cfg.no_progress_block_after == 5
-
-
-def test_config_parses_nested_warn_and_hard_stop_thresholds():
-    cfg = ToolCallGuardrailConfig.from_mapping(
-        {
-            "warnings_enabled": False,
-            "hard_stop_enabled": True,
-            "warn_after": {
-                "exact_failure": 3,
-                "same_tool_failure": 4,
-                "idempotent_no_progress": 5,
-            },
-            "hard_stop_after": {
-                "exact_failure": 6,
-                "same_tool_failure": 7,
-                "idempotent_no_progress": 8,
-            },
-        }
-    )
-
-    assert cfg.warnings_enabled is False
-    assert cfg.hard_stop_enabled is True
-    assert cfg.exact_failure_warn_after == 3
-    assert cfg.same_tool_failure_warn_after == 4
-    assert cfg.no_progress_warn_after == 5
-    assert cfg.exact_failure_block_after == 6
-    assert cfg.same_tool_failure_halt_after == 7
-    assert cfg.no_progress_block_after == 8
-
-
-def test_default_repeated_identical_failed_call_warns_without_blocking():
-    controller = ToolCallGuardrailController()
-    args = {"query": "same"}
-
-    decisions = []
-    for _ in range(5):
-        assert controller.before_call("web_search", args).action == "allow"
-        decisions.append(
-            controller.after_call("web_search", args, '{"error":"boom"}', failed=True)
-        )
-
-    assert decisions[0].action == "allow"
-    assert [d.action for d in decisions[1:]] == ["warn", "warn", "warn", "warn"]
-    assert {d.code for d in decisions[1:]} == {"repeated_exact_failure_warning"}
-    assert controller.before_call("web_search", args).action == "allow"
-    assert controller.halt_decision is None
-
-
-def test_hard_stop_enabled_blocks_repeated_exact_failure_before_next_execution():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(
-            hard_stop_enabled=True,
-            exact_failure_warn_after=2,
-            exact_failure_block_after=2,
-            same_tool_failure_halt_after=99,
-        )
-    )
-    args = {"query": "same"}
-
-    assert controller.before_call("web_search", args).action == "allow"
-    first = controller.after_call("web_search", args, '{"error":"boom"}', failed=True)
-    assert first.action == "allow"
-
-    assert controller.before_call("web_search", args).action == "allow"
-    second = controller.after_call("web_search", args, '{"error":"boom"}', failed=True)
-    assert second.action == "warn"
-    assert second.code == "repeated_exact_failure_warning"
-
-    blocked = controller.before_call("web_search", args)
-    assert blocked.action == "block"
-    assert blocked.code == "repeated_exact_failure_block"
-    assert blocked.count == 2
-
-
-def test_success_resets_exact_signature_failure_streak():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(hard_stop_enabled=True, exact_failure_block_after=2, same_tool_failure_halt_after=99)
-    )
-    args = {"query": "same"}
-
-    controller.after_call("web_search", args, '{"error":"boom"}', failed=True)
-    controller.after_call("web_search", args, '{"ok":true}', failed=False)
-
-    assert controller.before_call("web_search", args).action == "allow"
-    controller.after_call("web_search", args, '{"error":"boom"}', failed=True)
-    assert controller.before_call("web_search", args).action == "allow"
-
-
-def test_same_tool_varying_args_warns_by_default_without_halting():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(same_tool_failure_warn_after=2, same_tool_failure_halt_after=3)
-    )
-
-    first = controller.after_call("terminal", {"command": "cmd-1"}, '{"exit_code":1}', failed=True)
-    second = controller.after_call("terminal", {"command": "cmd-2"}, '{"exit_code":1}', failed=True)
-    third = controller.after_call("terminal", {"command": "cmd-3"}, '{"exit_code":1}', failed=True)
-    fourth = controller.after_call("terminal", {"command": "cmd-4"}, '{"exit_code":1}', failed=True)
-
-    assert first.action == "allow"
-    assert [second.action, third.action, fourth.action] == ["warn", "warn", "warn"]
-    assert {second.code, third.code, fourth.code} == {"same_tool_failure_warning"}
-    assert controller.halt_decision is None
-
-
-def test_hard_stop_enabled_halts_same_tool_varying_args_failure_streak():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(
-            hard_stop_enabled=True,
-            exact_failure_block_after=99,
-            same_tool_failure_warn_after=2,
-            same_tool_failure_halt_after=3,
-        )
-    )
-
-    first = controller.after_call("terminal", {"command": "cmd-1"}, '{"exit_code":1}', failed=True)
-    assert first.action == "allow"
-    second = controller.after_call("terminal", {"command": "cmd-2"}, '{"exit_code":1}', failed=True)
-    assert second.action == "warn"
-    assert second.code == "same_tool_failure_warning"
-    third = controller.after_call("terminal", {"command": "cmd-3"}, '{"exit_code":1}', failed=True)
-    assert third.action == "halt"
-    assert third.code == "same_tool_failure_halt"
-    assert third.count == 3
-
-
-def test_idempotent_no_progress_repeated_result_warns_without_blocking_by_default():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(no_progress_warn_after=2, no_progress_block_after=2)
-    )
-    args = {"path": "/tmp/same.txt"}
-    result = "same file contents"
-
-    for _ in range(4):
-        assert controller.before_call("read_file", args).action == "allow"
-        decision = controller.after_call("read_file", args, result, failed=False)
-
-    assert decision.action == "warn"
-    assert decision.code == "idempotent_no_progress_warning"
-    assert controller.before_call("read_file", args).action == "allow"
-    assert controller.halt_decision is None
-
-
-def test_hard_stop_enabled_blocks_idempotent_no_progress_future_repeat():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(
-            hard_stop_enabled=True,
-            no_progress_warn_after=2,
-            no_progress_block_after=2,
-        )
-    )
-    args = {"path": "/tmp/same.txt"}
-    result = "same file contents"
-
-    assert controller.before_call("read_file", args).action == "allow"
-    assert controller.after_call("read_file", args, result, failed=False).action == "allow"
-    assert controller.before_call("read_file", args).action == "allow"
-    warn = controller.after_call("read_file", args, result, failed=False)
-    assert warn.action == "warn"
-    assert warn.code == "idempotent_no_progress_warning"
-
-    blocked = controller.before_call("read_file", args)
-    assert blocked.action == "block"
-    assert blocked.code == "idempotent_no_progress_block"
-
-
-def test_mutating_or_unknown_tools_are_not_blocked_for_repeated_identical_success_output_by_default():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(no_progress_warn_after=2, no_progress_block_after=2)
-    )
-
-    for _ in range(3):
-        assert controller.before_call("write_file", {"path": "/tmp/x", "content": "x"}).action == "allow"
-        assert controller.after_call("write_file", {"path": "/tmp/x", "content": "x"}, "ok", failed=False).action == "allow"
-        assert controller.before_call("custom_tool", {"x": 1}).action == "allow"
-        assert controller.after_call("custom_tool", {"x": 1}, "ok", failed=False).action == "allow"
-
-
-def test_reset_for_turn_clears_bounded_guardrail_state():
-    controller = ToolCallGuardrailController(
-        ToolCallGuardrailConfig(hard_stop_enabled=True, exact_failure_block_after=2, no_progress_block_after=2)
-    )
-    controller.after_call("web_search", {"query": "same"}, '{"error":"boom"}', failed=True)
-    controller.after_call("web_search", {"query": "same"}, '{"error":"boom"}', failed=True)
-    controller.after_call("read_file", {"path": "/tmp/x"}, "same", failed=False)
-    controller.after_call("read_file", {"path": "/tmp/x"}, "same", failed=False)
-
-    assert controller.before_call("web_search", {"query": "same"}).action == "block"
-    assert controller.before_call("read_file", {"path": "/tmp/x"}).action == "block"
-
-    controller.reset_for_turn()
-
-    assert controller.before_call("web_search", {"query": "same"}).action == "allow"
-    assert controller.before_call("read_file", {"path": "/tmp/x"}).action == "allow"

tests/cli/test_manual_compress.py

@@ -21,21 +21,20 @@ def test_manual_compress_reports_noop_without_success_banner(capsys):
     shell.agent = MagicMock()
     shell.agent.compression_enabled = True
     shell.agent._cached_system_prompt = ""
-    shell.agent.tools = None
     shell.agent.session_id = shell.session_id  # no-op compression: no split
     shell.agent._compress_context.return_value = (list(history), "")
 
-    def _estimate(messages, **_kwargs):
+    def _estimate(messages):
         assert messages == history
         return 100
 
-    with patch("agent.model_metadata.estimate_request_tokens_rough", side_effect=_estimate):
+    with patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate):
         shell._manual_compress()
 
     output = capsys.readouterr().out
     assert "No changes from compression" in output
     assert "✅ Compressed" not in output
-    assert "Approx request size: ~100 tokens (unchanged)" in output
+    assert "Rough transcript estimate: ~100 tokens (unchanged)" in output
 
 
 def test_manual_compress_explains_when_token_estimate_rises(capsys):
@@ -50,23 +49,22 @@ def test_manual_compress_explains_when_token_estimate_rises(capsys):
     shell.agent = MagicMock()
     shell.agent.compression_enabled = True
     shell.agent._cached_system_prompt = ""
-    shell.agent.tools = None
     shell.agent.session_id = shell.session_id  # no-op: no split
     shell.agent._compress_context.return_value = (compressed, "")
 
-    def _estimate(messages, **_kwargs):
+    def _estimate(messages):
         if messages == history:
             return 100
         if messages == compressed:
             return 120
         raise AssertionError(f"unexpected transcript: {messages!r}")
 
-    with patch("agent.model_metadata.estimate_request_tokens_rough", side_effect=_estimate):
+    with patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate):
         shell._manual_compress()
 
     output = capsys.readouterr().out
     assert "✅ Compressed: 4 → 3 messages" in output
-    assert "Approx request size: ~100 → ~120 tokens" in output
+    assert "Rough transcript estimate: ~100 → ~120 tokens" in output
     assert "denser summaries" in output
 
 
@@ -91,7 +89,6 @@ def test_manual_compress_syncs_session_id_after_split():
     shell.agent = MagicMock()
     shell.agent.compression_enabled = True
     shell.agent._cached_system_prompt = ""
-    shell.agent.tools = None
     # Simulate _compress_context mutating agent.session_id as a side effect.
     def _fake_compress(*args, **kwargs):
         shell.agent.session_id = new_child_id
@@ -100,7 +97,7 @@ def test_manual_compress_syncs_session_id_after_split():
     shell.agent.session_id = old_id  # starts in sync
     shell._pending_title = "stale title"
 
-    with patch("agent.model_metadata.estimate_request_tokens_rough", return_value=100):
+    with patch("agent.model_metadata.estimate_messages_tokens_rough", return_value=100):
         shell._manual_compress()
 
     # CLI session_id must now point at the continuation child, not the parent.
@@ -121,12 +118,11 @@ def test_manual_compress_no_sync_when_session_id_unchanged():
     shell.agent = MagicMock()
     shell.agent.compression_enabled = True
     shell.agent._cached_system_prompt = ""
-    shell.agent.tools = None
     shell.agent.session_id = shell.session_id
     shell.agent._compress_context.return_value = (list(history), "")
     shell._pending_title = "keep me"
 
-    with patch("agent.model_metadata.estimate_request_tokens_rough", return_value=100):
+    with patch("agent.model_metadata.estimate_messages_tokens_rough", return_value=100):
         shell._manual_compress()
 
     # No split → pending title untouched.

tests/cron/test_rewrite_skill_refs.py

@@ -1,289 +0,0 @@
-"""Tests for cron.jobs.rewrite_skill_refs — the curator integration that
-keeps scheduled cron jobs pointing at the right skill names after a
-consolidation / pruning pass.
-
-Bug this fixes: when the curator consolidates skill X into umbrella Y,
-any cron job whose ``skills`` list contains X would silently fail to
-load X at run time (the scheduler logs a warning and skips it), so the
-job runs without the instructions it was scheduled to follow.
-"""
-
-from __future__ import annotations
-
-import sys
-from pathlib import Path
-
-import pytest
-
-# Ensure project root is importable
-sys.path.insert(0, str(Path(__file__).parent.parent.parent))
-
-
-@pytest.fixture
-def cron_env(tmp_path, monkeypatch):
-    """Isolated cron environment with temp HERMES_HOME."""
-    hermes_home = tmp_path / ".hermes"
-    hermes_home.mkdir()
-    (hermes_home / "cron").mkdir()
-    (hermes_home / "cron" / "output").mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
-
-    import cron.jobs as jobs_mod
-    monkeypatch.setattr(jobs_mod, "HERMES_DIR", hermes_home)
-    monkeypatch.setattr(jobs_mod, "CRON_DIR", hermes_home / "cron")
-    monkeypatch.setattr(jobs_mod, "JOBS_FILE", hermes_home / "cron" / "jobs.json")
-    monkeypatch.setattr(jobs_mod, "OUTPUT_DIR", hermes_home / "cron" / "output")
-
-    return hermes_home
-
-
-class TestRewriteSkillRefsNoop:
-    """No jobs, no rewrites, no map — every combination of empty inputs."""
-
-    def test_empty_map_and_no_jobs(self, cron_env):
-        from cron.jobs import rewrite_skill_refs
-
-        report = rewrite_skill_refs(consolidated={}, pruned=[])
-        assert report == {"rewrites": [], "jobs_updated": 0, "jobs_scanned": 0}
-
-    def test_jobs_exist_but_map_empty(self, cron_env):
-        from cron.jobs import create_job, rewrite_skill_refs
-
-        create_job(prompt="", schedule="every 1h", skills=["foo"])
-        report = rewrite_skill_refs(consolidated={}, pruned=[])
-        assert report["jobs_updated"] == 0
-        # Early return: we don't even scan when there's nothing to apply.
-        assert report["jobs_scanned"] == 0
-
-    def test_jobs_exist_but_no_match(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(prompt="", schedule="every 1h", skills=["foo"])
-        report = rewrite_skill_refs(
-            consolidated={"unrelated": "umbrella"},
-            pruned=["other"],
-        )
-        assert report["jobs_updated"] == 0
-        assert report["jobs_scanned"] == 1
-        # Job untouched
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == ["foo"]
-
-
-class TestRewriteSkillRefsConsolidation:
-    """Consolidated skills should be replaced with their umbrella target."""
-
-    def test_single_skill_replaced(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(prompt="", schedule="every 1h", skills=["legacy-skill"])
-        report = rewrite_skill_refs(
-            consolidated={"legacy-skill": "umbrella-skill"},
-            pruned=[],
-        )
-
-        assert report["jobs_updated"] == 1
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == ["umbrella-skill"]
-        # Legacy ``skill`` field realigned
-        assert loaded["skill"] == "umbrella-skill"
-
-    def test_multiple_skills_one_consolidated(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(
-            prompt="",
-            schedule="every 1h",
-            skills=["keep-a", "legacy", "keep-b"],
-        )
-        rewrite_skill_refs(consolidated={"legacy": "umbrella"}, pruned=[])
-
-        loaded = get_job(job["id"])
-        # Ordering preserved, legacy replaced in-place
-        assert loaded["skills"] == ["keep-a", "umbrella", "keep-b"]
-
-    def test_umbrella_already_in_list_dedupes(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        # Job already loads the umbrella AND the legacy sub-skill
-        job = create_job(
-            prompt="",
-            schedule="every 1h",
-            skills=["umbrella", "legacy"],
-        )
-        rewrite_skill_refs(consolidated={"legacy": "umbrella"}, pruned=[])
-
-        loaded = get_job(job["id"])
-        # No duplicate — the umbrella stays exactly once
-        assert loaded["skills"] == ["umbrella"]
-
-    def test_rewrite_report_records_mapping(self, cron_env):
-        from cron.jobs import create_job, rewrite_skill_refs
-
-        job = create_job(
-            prompt="",
-            schedule="every 1h",
-            skills=["a", "b"],
-            name="my-job",
-        )
-        report = rewrite_skill_refs(
-            consolidated={"a": "umbrella-a", "b": "umbrella-b"},
-            pruned=[],
-        )
-
-        assert len(report["rewrites"]) == 1
-        entry = report["rewrites"][0]
-        assert entry["job_id"] == job["id"]
-        assert entry["job_name"] == "my-job"
-        assert entry["before"] == ["a", "b"]
-        assert entry["after"] == ["umbrella-a", "umbrella-b"]
-        assert entry["mapped"] == {"a": "umbrella-a", "b": "umbrella-b"}
-        assert entry["dropped"] == []
-
-
-class TestRewriteSkillRefsPruning:
-    """Pruned skills should be dropped outright (no forwarding target)."""
-
-    def test_pruned_skill_dropped(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(
-            prompt="",
-            schedule="every 1h",
-            skills=["keep", "stale"],
-        )
-        report = rewrite_skill_refs(consolidated={}, pruned=["stale"])
-
-        assert report["jobs_updated"] == 1
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == ["keep"]
-        assert loaded["skill"] == "keep"
-
-    def test_all_skills_pruned_leaves_empty_list(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(prompt="", schedule="every 1h", skills=["gone"])
-        rewrite_skill_refs(consolidated={}, pruned=["gone"])
-
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == []
-        assert loaded["skill"] is None
-
-    def test_pruned_report_records_drops(self, cron_env):
-        from cron.jobs import create_job, rewrite_skill_refs
-
-        create_job(prompt="", schedule="every 1h", skills=["keep", "stale"])
-        report = rewrite_skill_refs(consolidated={}, pruned=["stale"])
-
-        entry = report["rewrites"][0]
-        assert entry["dropped"] == ["stale"]
-        assert entry["mapped"] == {}
-
-
-class TestRewriteSkillRefsMixed:
-    """Consolidation + pruning in the same pass."""
-
-    def test_mixed_consolidation_and_pruning(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(
-            prompt="",
-            schedule="every 1h",
-            skills=["keep", "legacy", "stale"],
-        )
-        rewrite_skill_refs(
-            consolidated={"legacy": "umbrella"},
-            pruned=["stale"],
-        )
-
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == ["keep", "umbrella"]
-
-    def test_skill_in_both_maps_wins_as_consolidated(self, cron_env):
-        """Defensive: if a skill appears in both lists (shouldn't happen
-        in practice), prefer consolidation — it has a forwarding target,
-        which is the more useful outcome."""
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        job = create_job(prompt="", schedule="every 1h", skills=["ambiguous"])
-        rewrite_skill_refs(
-            consolidated={"ambiguous": "umbrella"},
-            pruned=["ambiguous"],
-        )
-
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == ["umbrella"]
-
-
-class TestRewriteSkillRefsMultipleJobs:
-    """Multiple jobs, some affected, some not."""
-
-    def test_only_affected_jobs_reported(self, cron_env):
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        j1 = create_job(prompt="", schedule="every 1h", skills=["legacy"])
-        j2 = create_job(prompt="", schedule="every 1h", skills=["untouched"])
-        j3 = create_job(prompt="", schedule="every 1h", skills=[])
-
-        report = rewrite_skill_refs(
-            consolidated={"legacy": "umbrella"},
-            pruned=[],
-        )
-
-        assert report["jobs_updated"] == 1
-        assert report["jobs_scanned"] == 3
-        assert len(report["rewrites"]) == 1
-        assert report["rewrites"][0]["job_id"] == j1["id"]
-
-        # Untouched jobs stay put
-        assert get_job(j2["id"])["skills"] == ["untouched"]
-        assert get_job(j3["id"])["skills"] == []
-
-    def test_legacy_skill_field_also_rewritten(self, cron_env):
-        """Old jobs may have the legacy single-skill ``skill`` field
-        set instead of ``skills``. Both paths should be rewritten."""
-        from cron.jobs import create_job, get_job, rewrite_skill_refs
-
-        # Create via the legacy ``skill`` argument
-        job = create_job(
-            prompt="",
-            schedule="every 1h",
-            skill="legacy",
-        )
-        rewrite_skill_refs(consolidated={"legacy": "umbrella"}, pruned=[])
-
-        loaded = get_job(job["id"])
-        assert loaded["skills"] == ["umbrella"]
-        assert loaded["skill"] == "umbrella"
-
-
-class TestRewriteSkillRefsPersistence:
-    """Rewrites persist to disk and survive a reload."""
-
-    def test_changes_persist_across_reload(self, cron_env):
-        import json
-        from cron.jobs import create_job, rewrite_skill_refs, JOBS_FILE
-
-        create_job(prompt="", schedule="every 1h", skills=["legacy"])
-        rewrite_skill_refs(consolidated={"legacy": "umbrella"}, pruned=[])
-
-        # Read raw file contents
-        data = json.loads(JOBS_FILE.read_text())
-        assert data["jobs"][0]["skills"] == ["umbrella"]
-        assert data["jobs"][0]["skill"] == "umbrella"
-
-    def test_noop_does_not_rewrite_file(self, cron_env):
-        from cron.jobs import create_job, rewrite_skill_refs, JOBS_FILE
-
-        create_job(prompt="", schedule="every 1h", skills=["keep"])
-        mtime_before = JOBS_FILE.stat().st_mtime_ns
-
-        # Nothing in the map matches
-        report = rewrite_skill_refs(
-            consolidated={"unrelated": "umbrella"},
-            pruned=["other"],
-        )
-
-        assert report["jobs_updated"] == 0
-        # File untouched — no pointless disk write
-        assert JOBS_FILE.stat().st_mtime_ns == mtime_before