feat(kanban): dispatcher runs in the gateway by default; retire standalone daemon

The kanban dispatcher is now embedded in the gateway process —
'gateway is the single dispatcher host' — removing the need for a
separate `hermes kanban daemon` or systemd unit. Typical user path
becomes: `hermes gateway start` + `hermes kanban create ...` and
ready tasks run on the next tick (60s default). The cost is ~300µs per
interval on an idle board; negligible.

Changes:
- config: new `kanban` section in DEFAULT_CONFIG with
  `dispatch_in_gateway: true` (default on) and
  `dispatch_interval_seconds: 60`. Additive — no \_config_version bump.
- gateway/run.py: new `_kanban_dispatcher_watcher()` background task,
  symmetric with `_kanban_notifier_watcher`. Reads config at boot;
  exits cleanly if the flag is off. Runs each tick via
  `asyncio.to_thread` so the SQLite WAL lock never blocks the loop.
  Sleeps in 1s slices so shutdown is snappy. Health telemetry mirrored
  from `_cmd_daemon` — warns when the ready queue is non-empty for
  6 consecutive ticks with 0 spawns. Env override
  `HERMES_KANBAN_DISPATCH_IN_GATEWAY=0` disables without editing
  config.yaml.
- hermes_cli/kanban.py: `_cmd_daemon` becomes a deprecation stub — no
  `--force`, exits 2 with migration guidance pointing at
  `hermes gateway start`. With `--force` (undocumented, help=SUPPRESS)
  the old standalone loop still runs, for headless hosts that can't run
  the gateway. Help text marks the subcommand DEPRECATED.
- hermes_cli/kanban.py: new `_check_dispatcher_presence()` helper —
  returns (running, human_message) by probing `gateway.status.get_running_pid`
  AND reading `kanban.dispatch_in_gateway`. Defensive: import/probe
  failures return (True, "") so we never cry wolf on partial installs.
- `hermes kanban create` prints a stderr warning when the task lands
  in 'ready' with an assignee but no dispatcher will pick it up. Skipped
  in `--json` mode so machine-parseable output stays clean. Skipped for
  triage/unassigned tasks (they can't dispatch regardless).
- `hermes kanban init` prints `hermes gateway start` as the next step
  (was: `hermes kanban daemon`).
- plugin_api.py: POST /tasks response includes a `warning` field when
  the same probe returns not-running, so the dashboard UI can surface
  a banner. Probe errors are swallowed silently — must never break
  create.
- dashboard dist/index.js: `createTask` threads the `warning` response
  field into the existing error-banner channel with 'Task created,
  but: ...'.
- toolsets.py: "spawned by `hermes kanban daemon`" description updated
  to "spawned by the kanban dispatcher (gateway-embedded by default)".
  Matching change to the tools/kanban_tools.py docstring.
- systemd unit: marked DEPRECATED in its Description + header comment,
  invokes the standalone daemon via the explicit `--force` flag so
  users who haven't migrated don't accidentally spawn duplicate
  dispatchers.
- docs: kanban.md 'Running the dispatcher as a service' section
  rewritten to describe gateway-embedded dispatch as the default; the
  standalone systemd instructions are gone. kanban-tutorial.md 'Start
  the daemon' block replaced with `hermes gateway start`. CLI command
  reference table now marks `hermes kanban daemon` DEPRECATED.

Tests (17 new):
- DEFAULT_CONFIG has kanban.dispatch_in_gateway=True and a sane
  interval.
- `_check_dispatcher_presence` returns running when gateway pid is
  found and flag is on; warns with `hermes gateway start` guidance
  when no gateway; warns with `dispatch_in_gateway` guidance when
  flag is off; silent on probe error.
- `hermes kanban create` (non-JSON) warns on stderr when no gateway
  and task is ready+assigned; stays silent when gateway is up; never
  warns on triage or unassigned tasks.
- `hermes kanban daemon` without --force prints DEPRECATED + exits 2.
- Argparse help for `kanban daemon` contains the word DEPRECATED.
- Gateway `_kanban_dispatcher_watcher` respects config flag=False
  (exits fast), respects HERMES_KANBAN_DISPATCH_IN_GATEWAY=0 env
  override, and treats truthy env as 'defer to config' (not force-on).
- Dashboard POST /tasks response carries `warning` when probe says
  no dispatcher; omits it when probe says running; skips probe on
  triage tasks; survives probe errors without breaking create.

E2E verified in an isolated HERMES_HOME: watcher exits in 0.000s when
flag is off, 0.000s on env override, gracefully stops within 3s of
`_running=False` with the flag on.

Integration issues fixed in the same pass:
- Stale 'hermes kanban daemon --assignee' refs in kanban-tutorial.md
  (that flag never existed; just bad author copy).
- Stale toolset description pointing at the retired daemon.
- Stale docstring in tools/kanban_tools.py for `_check_kanban_mode`.
- Systemd unit still invoking `hermes kanban daemon` without
  `--force`; now invokes with `--force` and is marked DEPRECATED.

.github/workflows/deploy-site.yml

@@ -53,6 +53,9 @@ jobs:
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
 
+      - name: Regenerate per-skill docs pages + catalogs
+        run: python3 website/scripts/generate-skill-docs.py
+
       - name: Build skills index (if not already present)
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-site-checks.yml

@@ -36,6 +36,9 @@ jobs:
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
 
+      - name: Regenerate per-skill docs pages + catalogs
+        run: python3 website/scripts/generate-skill-docs.py
+
       - name: Lint docs diagrams
         run: npm run lint:diagrams
         working-directory: website

AGENTS.md

@@ -240,6 +240,19 @@ npm run fmt       # prettier
 npm test          # vitest
 ```
 
+### TUI in the Dashboard (`hermes dashboard` → `/chat`)
+
+The dashboard embeds the real `hermes --tui` — **not** a rewrite.  See `hermes_cli/pty_bridge.py` + the `@app.websocket("/api/pty")` endpoint in `hermes_cli/web_server.py`.
+
+- Browser loads `web/src/pages/ChatPage.tsx`, which mounts xterm.js's `Terminal` with the WebGL renderer, `@xterm/addon-fit` for container-driven resize, and `@xterm/addon-unicode11` for modern wide-character widths.
+- `/api/pty?token=…` upgrades to a WebSocket; auth uses the same ephemeral `_SESSION_TOKEN` as REST, via query param (browsers can't set `Authorization` on WS upgrade).
+- The server spawns whatever `hermes --tui` would spawn, through `ptyprocess` (POSIX PTY — WSL works, native Windows does not).
+- Frames: raw PTY bytes each direction; resize via `\x1b[RESIZE:<cols>;<rows>]` intercepted on the server and applied with `TIOCSWINSZ`.
+
+**Do not re-implement the primary chat experience in React.** The main transcript, composer/input flow (including slash-command behavior), and PTY-backed terminal belong to the embedded `hermes --tui` — anything new you add to Ink shows up in the dashboard automatically. If you find yourself rebuilding the transcript or composer for the dashboard, stop and extend Ink instead.
+
+**Structured React UI around the TUI is allowed when it is not a second chat surface.** Sidebar widgets, inspectors, summaries, status panels, and similar supporting views (e.g. `ChatSidebar`, `ModelPickerDialog`, `ToolCall`) are fine when they complement the embedded TUI rather than replacing the transcript / composer / terminal. Keep their state independent of the PTY child's session and surface their failures non-destructively so the terminal pane keeps working unimpaired.
+
 ---
 
 ## Adding New Tools

Dockerfile

@@ -10,9 +10,11 @@ ENV PYTHONUNBUFFERED=1
 ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
 
 # Install system dependencies in one layer, clear APT cache
+# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
+# that would otherwise accumulate when hermes runs as PID 1. See #15012.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli && \
+        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini && \
     rm -rf /var/lib/apt/lists/*
 
 # Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
@@ -41,9 +43,15 @@ COPY --chown=hermes:hermes . .
 # Build web dashboard (Vite outputs to hermes_cli/web_dist/)
 RUN cd web && npm run build
 
+# ---------- Permissions ----------
+# Make install dir world-readable so any HERMES_UID can read it at runtime.
+# The venv needs to be traversable too.
+USER root
+RUN chmod -R a+rX /opt/hermes
+# Start as root so the entrypoint can usermod/groupmod + gosu.
+# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
+
 # ---------- Python virtualenv ----------
-RUN chown hermes:hermes /opt/hermes
-USER hermes
 RUN uv venv && \
     uv pip install --no-cache-dir -e ".[all]"
 
@@ -52,4 +60,4 @@ ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
 ENV HERMES_HOME=/opt/data
 ENV PATH="/opt/data/.local/bin:${PATH}"
 VOLUME [ "/opt/data" ]
-ENTRYPOINT [ "/opt/hermes/docker/entrypoint.sh" ]
+ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]

acp_adapter/server.py

@@ -60,7 +60,7 @@ from acp_adapter.events import (
     make_tool_progress_cb,
 )
 from acp_adapter.permissions import make_approval_callback
-from acp_adapter.session import SessionManager, SessionState
+from acp_adapter.session import SessionManager, SessionState, _expand_acp_enabled_toolsets
 
 logger = logging.getLogger(__name__)
 
@@ -287,7 +287,11 @@ class HermesACPAgent(acp.Agent):
         try:
             from model_tools import get_tool_definitions
 
-            enabled_toolsets = getattr(state.agent, "enabled_toolsets", None) or ["hermes-acp"]
+            enabled_toolsets = _expand_acp_enabled_toolsets(
+                getattr(state.agent, "enabled_toolsets", None) or ["hermes-acp"],
+                mcp_server_names=[server.name for server in mcp_servers],
+            )
+            state.agent.enabled_toolsets = enabled_toolsets
             disabled_toolsets = getattr(state.agent, "disabled_toolsets", None)
             state.agent.tools = get_tool_definitions(
                 enabled_toolsets=enabled_toolsets,
@@ -754,7 +758,9 @@ class HermesACPAgent(acp.Agent):
     def _cmd_tools(self, args: str, state: SessionState) -> str:
         try:
             from model_tools import get_tool_definitions
-            toolsets = getattr(state.agent, "enabled_toolsets", None) or ["hermes-acp"]
+            toolsets = _expand_acp_enabled_toolsets(
+                getattr(state.agent, "enabled_toolsets", None) or ["hermes-acp"]
+            )
             tools = get_tool_definitions(enabled_toolsets=toolsets, quiet_mode=True)
             if not tools:
                 return "No tools available."

acp_adapter/session.py

@@ -106,6 +106,24 @@ def _register_task_cwd(task_id: str, cwd: str) -> None:
         logger.debug("Failed to register ACP task cwd override", exc_info=True)
 
 
+def _expand_acp_enabled_toolsets(
+    toolsets: List[str] | None = None,
+    mcp_server_names: List[str] | None = None,
+) -> List[str]:
+    """Return ACP toolsets plus explicit MCP server toolsets for this session."""
+    expanded: List[str] = []
+    for name in list(toolsets or ["hermes-acp"]):
+        if name and name not in expanded:
+            expanded.append(name)
+
+    for server_name in list(mcp_server_names or []):
+        toolset_name = f"mcp-{server_name}"
+        if server_name and toolset_name not in expanded:
+            expanded.append(toolset_name)
+
+    return expanded
+
+
 def _clear_task_cwd(task_id: str) -> None:
     """Remove task-specific cwd overrides for an ACP session."""
     if not task_id:
@@ -537,9 +555,18 @@ class SessionManager:
         elif isinstance(model_cfg, str) and model_cfg.strip():
             default_model = model_cfg.strip()
 
+        configured_mcp_servers = [
+            name
+            for name, cfg in (config.get("mcp_servers") or {}).items()
+            if not isinstance(cfg, dict) or cfg.get("enabled", True) is not False
+        ]
+
         kwargs = {
             "platform": "acp",
-            "enabled_toolsets": ["hermes-acp"],
+            "enabled_toolsets": _expand_acp_enabled_toolsets(
+                ["hermes-acp"],
+                mcp_server_names=configured_mcp_servers,
+            ),
             "quiet_mode": True,
             "session_id": session_id,
             "model": model or default_model,

agent/anthropic_adapter.py

@@ -14,6 +14,8 @@ import copy
 import json
 import logging
 import os
+import platform
+import subprocess
 from pathlib import Path
 
 from hermes_constants import get_hermes_home
@@ -277,8 +279,9 @@ def _is_oauth_token(key: str) -> bool:
     Positively identifies Anthropic OAuth tokens by their key format:
     - ``sk-ant-`` prefix (but NOT ``sk-ant-api``) → setup tokens, managed keys
     - ``eyJ`` prefix → JWTs from the Anthropic OAuth flow
+    - ``cc-`` prefix → Claude Code OAuth access tokens (from CLAUDE_CODE_OAUTH_TOKEN)
 
-    Non-Anthropic keys (MiniMax, Alibaba, etc.) don't match either pattern
+    Non-Anthropic keys (MiniMax, Alibaba, etc.) don't match any pattern
     and correctly return False.
     """
     if not key:
@@ -292,6 +295,9 @@ def _is_oauth_token(key: str) -> bool:
     # JWTs from Anthropic OAuth flow
     if key.startswith("eyJ"):
         return True
+    # Claude Code OAuth access tokens (opaque, from CLAUDE_CODE_OAUTH_TOKEN)
+    if key.startswith("cc-"):
+        return True
     return False
 
 
@@ -384,7 +390,16 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
         "timeout": Timeout(timeout=float(_read_timeout), connect=10.0),
     }
     if normalized_base_url:
-        kwargs["base_url"] = normalized_base_url
+        # Azure Anthropic endpoints require an ``api-version`` query parameter.
+        # Pass it via default_query so the SDK appends it to every request URL
+        # without corrupting the base_url (appending it directly produces
+        # malformed paths like /anthropic?api-version=.../v1/messages).
+        _is_azure_endpoint = "azure.com" in normalized_base_url.lower()
+        if _is_azure_endpoint and "api-version" not in normalized_base_url:
+            kwargs["base_url"] = normalized_base_url.rstrip("/")
+            kwargs["default_query"] = {"api-version": "2025-04-15"}
+        else:
+            kwargs["base_url"] = normalized_base_url
     common_betas = _common_betas_for_base_url(normalized_base_url)
 
     if _is_kimi_coding_endpoint(base_url):
@@ -461,8 +476,72 @@ def build_anthropic_bedrock_client(region: str):
     )
 
 
+def _read_claude_code_credentials_from_keychain() -> Optional[Dict[str, Any]]:
+    """Read Claude Code OAuth credentials from the macOS Keychain.
+
+    Claude Code >=2.1.114 stores credentials in the macOS Keychain under the
+    service name "Claude Code-credentials" rather than (or in addition to)
+    the JSON file at ~/.claude/.credentials.json.
+
+    The password field contains a JSON string with the same claudeAiOauth
+    structure as the JSON file.
+
+    Returns dict with {accessToken, refreshToken?, expiresAt?} or None.
+    """
+    import platform
+    import subprocess
+
+    if platform.system() != "Darwin":
+        return None
+
+    try:
+        # Read the "Claude Code-credentials" generic password entry
+        result = subprocess.run(
+            ["security", "find-generic-password",
+             "-s", "Claude Code-credentials",
+             "-w"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+    except (OSError, subprocess.TimeoutExpired):
+        logger.debug("Keychain: security command not available or timed out")
+        return None
+
+    if result.returncode != 0:
+        logger.debug("Keychain: no entry found for 'Claude Code-credentials'")
+        return None
+
+    raw = result.stdout.strip()
+    if not raw:
+        return None
+
+    try:
+        data = json.loads(raw)
+    except json.JSONDecodeError:
+        logger.debug("Keychain: credentials payload is not valid JSON")
+        return None
+
+    oauth_data = data.get("claudeAiOauth")
+    if oauth_data and isinstance(oauth_data, dict):
+        access_token = oauth_data.get("accessToken", "")
+        if access_token:
+            return {
+                "accessToken": access_token,
+                "refreshToken": oauth_data.get("refreshToken", ""),
+                "expiresAt": oauth_data.get("expiresAt", 0),
+                "source": "macos_keychain",
+            }
+
+    return None
+
+
 def read_claude_code_credentials() -> Optional[Dict[str, Any]]:
-    """Read refreshable Claude Code OAuth credentials from ~/.claude/.credentials.json.
+    """Read refreshable Claude Code OAuth credentials.
+
+    Checks two sources in order:
+      1. macOS Keychain (Darwin only) — "Claude Code-credentials" entry
+      2. ~/.claude/.credentials.json file
 
     This intentionally excludes ~/.claude.json primaryApiKey. Opencode's
     subscription flow is OAuth/setup-token based with refreshable credentials,
@@ -471,6 +550,12 @@ def read_claude_code_credentials() -> Optional[Dict[str, Any]]:
 
     Returns dict with {accessToken, refreshToken?, expiresAt?} or None.
     """
+    # Try macOS Keychain first (covers Claude Code >=2.1.114)
+    kc_creds = _read_claude_code_credentials_from_keychain()
+    if kc_creds:
+        return kc_creds
+
+    # Fall back to JSON file
     cred_path = Path.home() / ".claude" / ".credentials.json"
     if cred_path.exists():
         try:
@@ -641,7 +726,9 @@ def _write_claude_code_credentials(
         existing["claudeAiOauth"] = oauth_data
 
         cred_path.parent.mkdir(parents=True, exist_ok=True)
-        cred_path.write_text(json.dumps(existing, indent=2), encoding="utf-8")
+        _tmp_cred = cred_path.with_suffix(".tmp")
+        _tmp_cred.write_text(json.dumps(existing, indent=2), encoding="utf-8")
+        _tmp_cred.replace(cred_path)
         # Restrict permissions (credentials file)
         cred_path.chmod(0o600)
     except (OSError, IOError) as e:
@@ -908,6 +995,26 @@ def read_hermes_oauth_credentials() -> Optional[Dict[str, Any]]:
 # ---------------------------------------------------------------------------
 
 
+def _is_bedrock_model_id(model: str) -> bool:
+    """Detect AWS Bedrock model IDs that use dots as namespace separators.
+
+    Bedrock model IDs come in two forms:
+    - Bare:    ``anthropic.claude-opus-4-7``
+    - Regional (inference profiles): ``us.anthropic.claude-sonnet-4-5-v1:0``
+
+    In both cases the dots separate namespace components, not version
+    numbers, and must be preserved verbatim for the Bedrock API.
+    """
+    lower = model.lower()
+    # Regional inference-profile prefixes
+    if any(lower.startswith(p) for p in ("global.", "us.", "eu.", "ap.", "jp.")):
+        return True
+    # Bare Bedrock model IDs: provider.model-family
+    if lower.startswith("anthropic."):
+        return True
+    return False
+
+
 def normalize_model_name(model: str, preserve_dots: bool = False) -> str:
     """Normalize a model name for the Anthropic API.
 
@@ -915,11 +1022,19 @@ def normalize_model_name(model: str, preserve_dots: bool = False) -> str:
     - Converts dots to hyphens in version numbers (OpenRouter uses dots,
       Anthropic uses hyphens: claude-opus-4.6 → claude-opus-4-6), unless
       preserve_dots is True (e.g. for Alibaba/DashScope: qwen3.5-plus).
+    - Preserves Bedrock model IDs (``anthropic.claude-opus-4-7``) and
+      regional inference profiles (``us.anthropic.claude-*``) whose dots
+      are namespace separators, not version separators.
     """
     lower = model.lower()
     if lower.startswith("anthropic/"):
         model = model[len("anthropic/"):]
     if not preserve_dots:
+        # Bedrock model IDs use dots as namespace separators
+        # (e.g. "anthropic.claude-opus-4-7", "us.anthropic.claude-*").
+        # These must not be converted to hyphens.  See issue #12295.
+        if _is_bedrock_model_id(model):
+            return model
         # OpenRouter uses dots for version separators (claude-opus-4.6),
         # Anthropic uses hyphens (claude-opus-4-6). Convert dots to hyphens.
         model = model.replace(".", "-")
@@ -1574,9 +1689,9 @@ def build_anthropic_kwargs(
 
     # ── Strip sampling params on 4.7+ ─────────────────────────────────
     # Opus 4.7 rejects any non-default temperature/top_p/top_k with a 400.
-    # Callers (auxiliary_client, flush_memories, etc.) may set these for
-    # older models; drop them here as a safety net so upstream 4.6 → 4.7
-    # migrations don't require coordinated edits everywhere.
+    # Callers (auxiliary_client, etc.) may set these for older models;
+    # drop them here as a safety net so upstream 4.6 → 4.7 migrations
+    # don't require coordinated edits everywhere.
     if _forbids_sampling_params(model):
         for _sampling_key in ("temperature", "top_p", "top_k"):
             kwargs.pop(_sampling_key, None)
@@ -1598,4 +1713,3 @@ def build_anthropic_kwargs(
     return kwargs
 
 
-

agent/auxiliary_client.py

@@ -42,6 +42,7 @@ import time
 from pathlib import Path  # noqa: F401 — used by test mocks
 from types import SimpleNamespace
 from typing import Any, Dict, List, Optional, Tuple
+from urllib.parse import urlparse, parse_qs, urlunparse
 
 from openai import OpenAI
 
@@ -52,6 +53,17 @@ from utils import base_url_host_matches, base_url_hostname, normalize_proxy_env_
 
 logger = logging.getLogger(__name__)
 
+
+def _extract_url_query_params(url: str):
+    """Extract query params from URL, return (clean_url, default_query dict or None)."""
+    parsed = urlparse(url)
+    if parsed.query:
+        clean = urlunparse(parsed._replace(query=""))
+        params = {k: v[0] for k, v in parse_qs(parsed.query).items()}
+        return clean, params
+    return url, None
+
+
 # Module-level flag: only warn once per process about stale OPENAI_BASE_URL.
 _stale_base_url_warned = False
 
@@ -74,6 +86,12 @@ _PROVIDER_ALIASES = {
     "minimax_cn": "minimax-cn",
     "claude": "anthropic",
     "claude-code": "anthropic",
+    "github": "copilot",
+    "github-copilot": "copilot",
+    "github-model": "copilot",
+    "github-models": "copilot",
+    "github-copilot-acp": "copilot-acp",
+    "copilot-acp-agent": "copilot-acp",
 }
 
 
@@ -89,10 +107,11 @@ def _normalize_aux_provider(provider: Optional[str]) -> str:
     if normalized == "main":
         # Resolve to the user's actual main provider so named custom providers
         # and non-aggregator providers (DeepSeek, Alibaba, etc.) work correctly.
-        main_prov = _read_main_provider()
+        main_prov = (_read_main_provider() or "").strip().lower()
         if main_prov and main_prov not in ("auto", "main", ""):
-            return main_prov
-        return "custom"
+            normalized = main_prov
+        else:
+            return "custom"
     return _PROVIDER_ALIASES.get(normalized, normalized)
 
 
@@ -383,7 +402,7 @@ class _CodexCompletionsAdapter:
         # Note: the Codex endpoint (chatgpt.com/backend-api/codex) does NOT
         # support max_output_tokens or temperature — omit to avoid 400 errors.
 
-        # Tools support for flush_memories and similar callers
+        # Tools support for auxiliary callers (e.g. skills_hub) that pass function schemas
         tools = kwargs.get("tools")
         if tools:
             converted = []
@@ -1150,8 +1169,10 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
         return None, None
     model = _read_main_model() or "gpt-4o-mini"
     logger.debug("Auxiliary client: custom endpoint (%s, api_mode=%s)", model, custom_mode or "chat_completions")
+    _clean_base, _dq = _extract_url_query_params(custom_base)
+    _extra = {"default_query": _dq} if _dq else {}
     if custom_mode == "codex_responses":
-        real_client = OpenAI(api_key=custom_key, base_url=custom_base)
+        real_client = OpenAI(api_key=custom_key, base_url=_clean_base, **_extra)
         return CodexAuxiliaryClient(real_client, model), model
     if custom_mode == "anthropic_messages":
         # Third-party Anthropic-compatible gateway (MiniMax, Zhipu GLM,
@@ -1165,12 +1186,12 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
                 "Custom endpoint declares api_mode=anthropic_messages but the "
                 "anthropic SDK is not installed — falling back to OpenAI-wire."
             )
-            return OpenAI(api_key=custom_key, base_url=custom_base), model
+            return OpenAI(api_key=custom_key, base_url=_clean_base, **_extra), model
         return (
             AnthropicAuxiliaryClient(real_client, model, custom_key, custom_base, is_oauth=False),
             model,
         )
-    return OpenAI(api_key=custom_key, base_url=custom_base), model
+    return OpenAI(api_key=custom_key, base_url=_clean_base, **_extra), model
 
 
 def _try_codex() -> Tuple[Optional[Any], Optional[str]]:
@@ -1342,6 +1363,111 @@ def _is_auth_error(exc: Exception) -> bool:
     return "error code: 401" in err_lower or "authenticationerror" in type(exc).__name__.lower()
 
 
+def _is_unsupported_parameter_error(exc: Exception, param: str) -> bool:
+    """Detect provider 400s for an unsupported request parameter.
+
+    Different OpenAI-compatible endpoints phrase the same class of error a few
+    ways: ``Unsupported parameter: X``, ``unsupported_parameter`` with a
+    ``param`` field, ``X is not supported``, ``unknown parameter: X``,
+    ``unrecognized request argument: X``.  We match on both the parameter
+    name and a generic "unsupported/unknown/unrecognized parameter" marker so
+    call sites can reactively retry without the offending key instead of
+    surfacing a noisy auxiliary failure.
+
+    Generalizes the temperature-specific detector that originally shipped
+    with PR #15621 so the same retry strategy can cover ``max_tokens``,
+    ``seed``, ``top_p``, and any future quirk. Credit @nicholasrae (PR #15416)
+    for the generalization pattern.
+    """
+    param_lower = (param or "").lower()
+    if not param_lower:
+        return False
+    err_lower = str(exc).lower()
+    if param_lower not in err_lower:
+        return False
+    return any(marker in err_lower for marker in (
+        "unsupported parameter",
+        "unsupported_parameter",
+        "not supported",
+        "does not support",
+        "unknown parameter",
+        "unrecognized request argument",
+        "unrecognized parameter",
+        "invalid parameter",
+    ))
+
+
+def _is_unsupported_temperature_error(exc: Exception) -> bool:
+    """Back-compat wrapper: detect API errors where the model rejects ``temperature``.
+
+    Delegates to :func:`_is_unsupported_parameter_error`; kept as a separate
+    public symbol because existing tests and call sites import it by name.
+    """
+    return _is_unsupported_parameter_error(exc, "temperature")
+
+
+def _evict_cached_clients(provider: str) -> None:
+    """Drop cached auxiliary clients for a provider so fresh creds are used."""
+    normalized = _normalize_aux_provider(provider)
+    with _client_cache_lock:
+        stale_keys = [
+            key for key in _client_cache
+            if _normalize_aux_provider(str(key[0])) == normalized
+        ]
+        for key in stale_keys:
+            client = _client_cache.get(key, (None, None, None))[0]
+            if client is not None:
+                _force_close_async_httpx(client)
+                try:
+                    close_fn = getattr(client, "close", None)
+                    if callable(close_fn):
+                        close_fn()
+                except Exception:
+                    pass
+            _client_cache.pop(key, None)
+
+
+def _refresh_provider_credentials(provider: str) -> bool:
+    """Refresh short-lived credentials for OAuth-backed auxiliary providers."""
+    normalized = _normalize_aux_provider(provider)
+    try:
+        if normalized == "openai-codex":
+            from hermes_cli.auth import resolve_codex_runtime_credentials
+
+            creds = resolve_codex_runtime_credentials(force_refresh=True)
+            if not str(creds.get("api_key", "") or "").strip():
+                return False
+            _evict_cached_clients(normalized)
+            return True
+        if normalized == "nous":
+            from hermes_cli.auth import resolve_nous_runtime_credentials
+
+            creds = resolve_nous_runtime_credentials(
+                min_key_ttl_seconds=max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
+                timeout_seconds=float(os.getenv("HERMES_NOUS_TIMEOUT_SECONDS", "15")),
+                force_mint=True,
+            )
+            if not str(creds.get("api_key", "") or "").strip():
+                return False
+            _evict_cached_clients(normalized)
+            return True
+        if normalized == "anthropic":
+            from agent.anthropic_adapter import read_claude_code_credentials, _refresh_oauth_token, resolve_anthropic_token
+
+            creds = read_claude_code_credentials()
+            token = _refresh_oauth_token(creds) if isinstance(creds, dict) and creds.get("refreshToken") else None
+            if not str(token or "").strip():
+                token = resolve_anthropic_token()
+            if not str(token or "").strip():
+                return False
+            _evict_cached_clients(normalized)
+            return True
+    except Exception as exc:
+        logger.debug("Auxiliary provider credential refresh failed for %s: %s", normalized, exc)
+        return False
+    return False
+
+
 def _try_payment_fallback(
     failed_provider: str,
     task: str = None,
@@ -1713,12 +1839,15 @@ def resolve_provider_client(
                 provider,
             )
             extra = {}
+            _clean_base, _dq = _extract_url_query_params(custom_base)
+            if _dq:
+                extra["default_query"] = _dq
             if base_url_host_matches(custom_base, "api.kimi.com"):
                 extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
             elif base_url_host_matches(custom_base, "api.githubcopilot.com"):
                 from hermes_cli.models import copilot_default_headers
                 extra["default_headers"] = copilot_default_headers()
-            client = OpenAI(api_key=custom_key, base_url=custom_base, **extra)
+            client = OpenAI(api_key=custom_key, base_url=_clean_base, **extra)
             client = _wrap_if_needed(client, final_model, custom_base)
             return (_to_async_client(client, final_model) if async_mode
                     else (client, final_model))
@@ -1736,7 +1865,7 @@ def resolve_provider_client(
                        "but no endpoint credentials found")
         return None, None
 
-    # ── Named custom providers (config.yaml custom_providers list) ───
+    # ── Named custom providers (config.yaml providers dict / custom_providers list) ───
     try:
         from hermes_cli.runtime_provider import _get_named_custom_provider
         custom_entry = _get_named_custom_provider(provider)
@@ -1747,16 +1876,53 @@ def resolve_provider_client(
             if not custom_key and custom_key_env:
                 custom_key = os.getenv(custom_key_env, "").strip()
             custom_key = custom_key or "no-key-required"
+            # An explicit per-task api_mode override (from _resolve_task_provider_model)
+            # wins; otherwise fall back to what the provider entry declared.
+            entry_api_mode = (api_mode or custom_entry.get("api_mode") or "").strip()
             if custom_base:
                 final_model = _normalize_resolved_model(
                     model or custom_entry.get("model") or _read_main_model() or "gpt-4o-mini",
                     provider,
                 )
-                client = OpenAI(api_key=custom_key, base_url=custom_base)
-                client = _wrap_if_needed(client, final_model, custom_base)
+                _clean_base2, _dq2 = _extract_url_query_params(custom_base)
+                _extra2 = {"default_query": _dq2} if _dq2 else {}
                 logger.debug(
-                    "resolve_provider_client: named custom provider %r (%s)",
-                    provider, final_model)
+                    "resolve_provider_client: named custom provider %r (%s, api_mode=%s)",
+                    provider, final_model, entry_api_mode or "chat_completions")
+                # anthropic_messages: route through the Anthropic Messages API
+                # via AnthropicAuxiliaryClient. Mirrors the anonymous-custom
+                # branch in _try_custom_endpoint(). See #15033.
+                if entry_api_mode == "anthropic_messages":
+                    try:
+                        from agent.anthropic_adapter import build_anthropic_client
+                        real_client = build_anthropic_client(custom_key, custom_base)
+                    except ImportError:
+                        logger.warning(
+                            "Named custom provider %r declares api_mode="
+                            "anthropic_messages but the anthropic SDK is not "
+                            "installed — falling back to OpenAI-wire.",
+                            provider,
+                        )
+                        client = OpenAI(api_key=custom_key, base_url=_clean_base2, **_extra2)
+                        return (_to_async_client(client, final_model) if async_mode
+                                else (client, final_model))
+                    sync_anthropic = AnthropicAuxiliaryClient(
+                        real_client, final_model, custom_key, custom_base, is_oauth=False,
+                    )
+                    if async_mode:
+                        return AsyncAnthropicAuxiliaryClient(sync_anthropic), final_model
+                    return sync_anthropic, final_model
+                client = OpenAI(api_key=custom_key, base_url=_clean_base2, **_extra2)
+                # codex_responses or inherited auto-detect (via _wrap_if_needed).
+                # _wrap_if_needed reads the closed-over `api_mode` (the task-level
+                # override). Named-provider entry api_mode=codex_responses also
+                # flows through here.
+                if entry_api_mode == "codex_responses" and not isinstance(
+                    client, CodexAuxiliaryClient
+                ):
+                    client = CodexAuxiliaryClient(client, final_model)
+                else:
+                    client = _wrap_if_needed(client, final_model, custom_base)
                 return (_to_async_client(client, final_model) if async_mode
                         else (client, final_model))
             logger.warning(
@@ -1889,6 +2055,39 @@ def resolve_provider_client(
                        "directly supported", provider)
         return None, None
 
+    elif pconfig.auth_type == "aws_sdk":
+        # AWS SDK providers (Bedrock) — use the Anthropic Bedrock client via
+        # boto3's credential chain (IAM roles, SSO, env vars, instance metadata).
+        try:
+            from agent.bedrock_adapter import has_aws_credentials, resolve_bedrock_region
+            from agent.anthropic_adapter import build_anthropic_bedrock_client
+        except ImportError:
+            logger.warning("resolve_provider_client: bedrock requested but "
+                           "boto3 or anthropic SDK not installed")
+            return None, None
+
+        if not has_aws_credentials():
+            logger.debug("resolve_provider_client: bedrock requested but "
+                         "no AWS credentials found")
+            return None, None
+
+        region = resolve_bedrock_region()
+        default_model = "anthropic.claude-haiku-4-5-20251001-v1:0"
+        final_model = _normalize_resolved_model(model or default_model, provider)
+        try:
+            real_client = build_anthropic_bedrock_client(region)
+        except ImportError as exc:
+            logger.warning("resolve_provider_client: cannot create Bedrock "
+                           "client: %s", exc)
+            return None, None
+        client = AnthropicAuxiliaryClient(
+            real_client, final_model, api_key="aws-sdk",
+            base_url=f"https://bedrock-runtime.{region}.amazonaws.com",
+        )
+        logger.debug("resolve_provider_client: bedrock (%s, %s)", final_model, region)
+        return (_to_async_client(client, final_model) if async_mode
+                else (client, final_model))
+
     elif pconfig.auth_type in ("oauth_device_code", "oauth_external"):
         # OAuth providers — route through their specific try functions
         if provider == "nous":
@@ -2623,8 +2822,8 @@ def _build_call_kwargs(
         temperature = fixed_temperature
 
     # Opus 4.7+ rejects any non-default temperature/top_p/top_k — silently
-    # drop here so auxiliary callers that hardcode temperature (e.g. 0.3 on
-    # flush_memories, 0 on structured-JSON extraction) don't 400 the moment
+    # drop here so auxiliary callers that hardcode temperature (e.g. 0 on
+    # structured-JSON extraction) don't 400 the moment
     # the aux model is flipped to 4.7.
     if temperature is not None:
         from agent.anthropic_adapter import _forbids_sampling_params
@@ -2712,7 +2911,7 @@ def call_llm(
 
     Args:
         task: Auxiliary task name ("compression", "vision", "web_extract",
-              "session_search", "skills_hub", "mcp", "flush_memories").
+              "session_search", "skills_hub", "mcp", "title_generation").
               Reads provider:model from config/env. Ignored if provider is set.
         provider: Explicit provider override.
         model: Explicit model override.
@@ -2815,13 +3014,45 @@ def call_llm(
     if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
         kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
 
-    # Handle max_tokens vs max_completion_tokens retry, then payment fallback.
+    # Handle unsupported temperature, max_tokens vs max_completion_tokens retry,
+    # then payment fallback.
     try:
         return _validate_llm_response(
             client.chat.completions.create(**kwargs), task)
     except Exception as first_err:
+        if "temperature" in kwargs and _is_unsupported_temperature_error(first_err):
+            retry_kwargs = dict(kwargs)
+            retry_kwargs.pop("temperature", None)
+            logger.info(
+                "Auxiliary %s: provider rejected temperature; retrying once without it",
+                task or "call",
+            )
+            try:
+                return _validate_llm_response(
+                    client.chat.completions.create(**retry_kwargs), task)
+            except Exception as retry_err:
+                retry_err_str = str(retry_err)
+                # If retry still fails, fall through to the max_tokens /
+                # payment / auth chains below using the temperature-stripped
+                # kwargs.  Re-raise only if the retry hit something those
+                # chains won't handle.
+                if not (
+                    _is_payment_error(retry_err)
+                    or _is_connection_error(retry_err)
+                    or _is_auth_error(retry_err)
+                    or "max_tokens" in retry_err_str
+                    or "unsupported_parameter" in retry_err_str
+                ):
+                    raise
+                first_err = retry_err
+                kwargs = retry_kwargs
+
         err_str = str(first_err)
-        if "max_tokens" in err_str or "unsupported_parameter" in err_str:
+        if max_tokens is not None and (
+            "max_tokens" in err_str
+            or "unsupported_parameter" in err_str
+            or _is_unsupported_parameter_error(first_err, "max_tokens")
+        ):
             kwargs.pop("max_tokens", None)
             kwargs["max_completion_tokens"] = max_tokens
             try:
@@ -2857,6 +3088,49 @@ def call_llm(
                 return _validate_llm_response(
                     refreshed_client.chat.completions.create(**kwargs), task)
 
+        # ── Auth refresh retry ───────────────────────────────────────
+        if (_is_auth_error(first_err)
+                and resolved_provider not in ("auto", "", None)
+                and not client_is_nous):
+            if _refresh_provider_credentials(resolved_provider):
+                logger.info(
+                    "Auxiliary %s: refreshed %s credentials after auth error, retrying",
+                    task or "call", resolved_provider,
+                )
+                retry_client, retry_model = (
+                    resolve_vision_provider_client(
+                        provider=resolved_provider,
+                        model=final_model,
+                        async_mode=False,
+                    )[1:]
+                    if task == "vision"
+                    else _get_cached_client(
+                        resolved_provider,
+                        resolved_model,
+                        base_url=resolved_base_url,
+                        api_key=resolved_api_key,
+                        api_mode=resolved_api_mode,
+                        main_runtime=main_runtime,
+                    )
+                )
+                if retry_client is not None:
+                    retry_kwargs = _build_call_kwargs(
+                        resolved_provider,
+                        retry_model or final_model,
+                        messages,
+                        temperature=temperature,
+                        max_tokens=max_tokens,
+                        tools=tools,
+                        timeout=effective_timeout,
+                        extra_body=effective_extra_body,
+                        base_url=resolved_base_url,
+                    )
+                    _retry_base = str(getattr(retry_client, "base_url", "") or "")
+                    if _is_anthropic_compat_endpoint(resolved_provider, _retry_base):
+                        retry_kwargs["messages"] = _convert_openai_images_to_anthropic(retry_kwargs["messages"])
+                    return _validate_llm_response(
+                        retry_client.chat.completions.create(**retry_kwargs), task)
+
         # ── Payment / credit exhaustion fallback ──────────────────────
         # When the resolved provider returns 402 or a credit-related error,
         # try alternative providers instead of giving up.  This handles the
@@ -3041,8 +3315,35 @@ async def async_call_llm(
         return _validate_llm_response(
             await client.chat.completions.create(**kwargs), task)
     except Exception as first_err:
+        if "temperature" in kwargs and _is_unsupported_temperature_error(first_err):
+            retry_kwargs = dict(kwargs)
+            retry_kwargs.pop("temperature", None)
+            logger.info(
+                "Auxiliary %s (async): provider rejected temperature; retrying once without it",
+                task or "call",
+            )
+            try:
+                return _validate_llm_response(
+                    await client.chat.completions.create(**retry_kwargs), task)
+            except Exception as retry_err:
+                retry_err_str = str(retry_err)
+                if not (
+                    _is_payment_error(retry_err)
+                    or _is_connection_error(retry_err)
+                    or _is_auth_error(retry_err)
+                    or "max_tokens" in retry_err_str
+                    or "unsupported_parameter" in retry_err_str
+                ):
+                    raise
+                first_err = retry_err
+                kwargs = retry_kwargs
+
         err_str = str(first_err)
-        if "max_tokens" in err_str or "unsupported_parameter" in err_str:
+        if max_tokens is not None and (
+            "max_tokens" in err_str
+            or "unsupported_parameter" in err_str
+            or _is_unsupported_parameter_error(first_err, "max_tokens")
+        ):
             kwargs.pop("max_tokens", None)
             kwargs["max_completion_tokens"] = max_tokens
             try:
@@ -3077,6 +3378,48 @@ async def async_call_llm(
                 return _validate_llm_response(
                     await refreshed_client.chat.completions.create(**kwargs), task)
 
+        # ── Auth refresh retry (mirrors sync call_llm) ───────────────
+        if (_is_auth_error(first_err)
+                and resolved_provider not in ("auto", "", None)
+                and not client_is_nous):
+            if _refresh_provider_credentials(resolved_provider):
+                logger.info(
+                    "Auxiliary %s (async): refreshed %s credentials after auth error, retrying",
+                    task or "call", resolved_provider,
+                )
+                if task == "vision":
+                    _, retry_client, retry_model = resolve_vision_provider_client(
+                        provider=resolved_provider,
+                        model=final_model,
+                        async_mode=True,
+                    )
+                else:
+                    retry_client, retry_model = _get_cached_client(
+                        resolved_provider,
+                        resolved_model,
+                        async_mode=True,
+                        base_url=resolved_base_url,
+                        api_key=resolved_api_key,
+                        api_mode=resolved_api_mode,
+                    )
+                if retry_client is not None:
+                    retry_kwargs = _build_call_kwargs(
+                        resolved_provider,
+                        retry_model or final_model,
+                        messages,
+                        temperature=temperature,
+                        max_tokens=max_tokens,
+                        tools=tools,
+                        timeout=effective_timeout,
+                        extra_body=effective_extra_body,
+                        base_url=resolved_base_url,
+                    )
+                    _retry_base = str(getattr(retry_client, "base_url", "") or "")
+                    if _is_anthropic_compat_endpoint(resolved_provider, _retry_base):
+                        retry_kwargs["messages"] = _convert_openai_images_to_anthropic(retry_kwargs["messages"])
+                    return _validate_llm_response(
+                        await retry_client.chat.completions.create(**retry_kwargs), task)
+
         # ── Payment / connection fallback (mirrors sync call_llm) ─────
         should_fallback = _is_payment_error(first_err) or _is_connection_error(first_err)
         is_auto = resolved_provider in ("auto", "", None)

agent/bedrock_adapter.py

@@ -87,6 +87,114 @@ def reset_client_cache():
     _bedrock_control_client_cache.clear()
 
 
+def invalidate_runtime_client(region: str) -> bool:
+    """Evict the cached ``bedrock-runtime`` client for a single region.
+
+    Per-region counterpart to :func:`reset_client_cache`. Used by the converse
+    call wrappers to discard clients whose underlying HTTP connection has
+    gone stale, so the next call allocates a fresh client (with a fresh
+    connection pool) instead of reusing a dead socket.
+
+    Returns True if a cached entry was evicted, False if the region was not
+    cached.
+    """
+    existed = region in _bedrock_runtime_client_cache
+    _bedrock_runtime_client_cache.pop(region, None)
+    return existed
+
+
+# ---------------------------------------------------------------------------
+# Stale-connection detection
+# ---------------------------------------------------------------------------
+#
+# boto3 caches its HTTPS connection pool inside the client object. When a
+# pooled connection is killed out from under us (NAT timeout, VPN flap,
+# server-side TCP RST, proxy idle cull, etc.), the next use surfaces as
+# one of a handful of low-level exceptions — most commonly
+# ``botocore.exceptions.ConnectionClosedError`` or
+# ``urllib3.exceptions.ProtocolError``. urllib3 also trips an internal
+# ``assert`` in a couple of paths (connection pool state checks, chunked
+# response readers) which bubbles up as a bare ``AssertionError`` with an
+# empty ``str(exc)``.
+#
+# In all of these cases the client is the problem, not the request: retrying
+# with the same cached client reproduces the failure until the process
+# restarts. The fix is to evict the region's cached client so the next
+# attempt builds a new one.
+
+_STALE_LIB_MODULE_PREFIXES = (
+    "urllib3.",
+    "botocore.",
+    "boto3.",
+)
+
+
+def _traceback_frames_modules(exc: BaseException):
+    """Yield ``__name__``-style module strings for each frame in exc's traceback."""
+    tb = getattr(exc, "__traceback__", None)
+    while tb is not None:
+        frame = tb.tb_frame
+        module = frame.f_globals.get("__name__", "")
+        yield module or ""
+        tb = tb.tb_next
+
+
+def is_stale_connection_error(exc: BaseException) -> bool:
+    """Return True if ``exc`` indicates a dead/stale Bedrock HTTP connection.
+
+    Matches:
+      * ``botocore.exceptions.ConnectionError`` and subclasses
+        (``ConnectionClosedError``, ``EndpointConnectionError``,
+        ``ReadTimeoutError``, ``ConnectTimeoutError``).
+      * ``urllib3.exceptions.ProtocolError`` / ``NewConnectionError`` /
+        ``ConnectionError`` (best-effort import — urllib3 is a transitive
+        dependency of botocore so it is always available in practice).
+      * Bare ``AssertionError`` raised from a frame inside urllib3, botocore,
+        or boto3. These are internal-invariant failures (typically triggered
+        by corrupted connection-pool state after a dropped socket) and are
+        recoverable by swapping the client.
+
+    Non-library ``AssertionError``s (from application code or tests) are
+    intentionally not matched — only library-internal asserts signal stale
+    connection state.
+    """
+    # botocore: the canonical signal — HTTPClientError is the umbrella for
+    # ConnectionClosedError, ReadTimeoutError, EndpointConnectionError,
+    # ConnectTimeoutError, and ProxyConnectionError. ConnectionError covers
+    # the same family via a different branch of the hierarchy.
+    try:
+        from botocore.exceptions import (
+            ConnectionError as BotoConnectionError,
+            HTTPClientError,
+        )
+        botocore_errors: tuple = (BotoConnectionError, HTTPClientError)
+    except ImportError:  # pragma: no cover — botocore always present with boto3
+        botocore_errors = ()
+    if botocore_errors and isinstance(exc, botocore_errors):
+        return True
+
+    # urllib3: low-level transport failures
+    try:
+        from urllib3.exceptions import (
+            ProtocolError,
+            NewConnectionError,
+            ConnectionError as Urllib3ConnectionError,
+        )
+        urllib3_errors = (ProtocolError, NewConnectionError, Urllib3ConnectionError)
+    except ImportError:  # pragma: no cover
+        urllib3_errors = ()
+    if urllib3_errors and isinstance(exc, urllib3_errors):
+        return True
+
+    # Library-internal AssertionError (urllib3 / botocore / boto3)
+    if isinstance(exc, AssertionError):
+        for module in _traceback_frames_modules(exc):
+            if any(module.startswith(prefix) for prefix in _STALE_LIB_MODULE_PREFIXES):
+                return True
+
+    return False
+
+
 # ---------------------------------------------------------------------------
 # AWS credential detection
 # ---------------------------------------------------------------------------
@@ -787,7 +895,17 @@ def call_converse(
         guardrail_config=guardrail_config,
     )
 
-    response = client.converse(**kwargs)
+    try:
+        response = client.converse(**kwargs)
+    except Exception as exc:
+        if is_stale_connection_error(exc):
+            logger.warning(
+                "bedrock: stale-connection error on converse(region=%s, model=%s): "
+                "%s — evicting cached client so the next call reconnects.",
+                region, model, type(exc).__name__,
+            )
+            invalidate_runtime_client(region)
+        raise
     return normalize_converse_response(response)
 
 
@@ -819,7 +937,17 @@ def call_converse_stream(
         guardrail_config=guardrail_config,
     )
 
-    response = client.converse_stream(**kwargs)
+    try:
+        response = client.converse_stream(**kwargs)
+    except Exception as exc:
+        if is_stale_connection_error(exc):
+            logger.warning(
+                "bedrock: stale-connection error on converse_stream(region=%s, "
+                "model=%s): %s — evicting cached client so the next call reconnects.",
+                region, model, type(exc).__name__,
+            )
+            invalidate_runtime_client(region)
+        raise
     return normalize_converse_stream_events(response)
 
 

agent/codex_responses_adapter.py

@@ -23,26 +23,52 @@ from agent.prompt_builder import DEFAULT_AGENT_IDENTITY
 logger = logging.getLogger(__name__)
 
 
+# Matches Codex/Harmony tool-call serialization that occasionally leaks into
+# assistant-message content when the model fails to emit a structured
+# ``function_call`` item.  Accepts the common forms:
+#
+#   to=functions.exec_command
+#   assistant to=functions.exec_command
+#   <|channel|>commentary to=functions.exec_command
+#
+# ``to=functions.<name>`` is the stable marker — the optional ``assistant`` or
+# Harmony channel prefix varies by degeneration mode.  Case-insensitive to
+# cover lowercase/uppercase ``assistant`` variants.
+_TOOL_CALL_LEAK_PATTERN = re.compile(
+    r"(?:^|[\s>|])to=functions\.[A-Za-z_][\w.]*",
+    re.IGNORECASE,
+)
+
+
 # ---------------------------------------------------------------------------
 # Multimodal content helpers
 # ---------------------------------------------------------------------------
 
-def _chat_content_to_responses_parts(content: Any) -> List[Dict[str, Any]]:
+def _chat_content_to_responses_parts(content: Any, *, role: str = "user") -> List[Dict[str, Any]]:
     """Convert chat-style multimodal content to Responses API input parts.
 
     Input:  ``[{"type":"text"|"image_url", ...}]`` (native OpenAI Chat format)
-    Output: ``[{"type":"input_text"|"input_image", ...}]`` (Responses format)
+    Output: ``[{"type":"input_text"|"output_text"|"input_image", ...}]`` (Responses format)
+
+    The ``role`` parameter controls the text content type:
+    - ``"user"`` (default) → ``"input_text"``
+    - ``"assistant"`` → ``"output_text"``
+
+    The Responses API rejects ``input_text`` inside assistant messages and
+    ``output_text`` inside user messages, so callers MUST pass the correct
+    role for the message being converted.
 
     Returns an empty list when ``content`` is not a list or contains no
     recognized parts — callers fall back to the string path.
     """
+    text_type = "output_text" if role == "assistant" else "input_text"
     if not isinstance(content, list):
         return []
     converted: List[Dict[str, Any]] = []
     for part in content:
         if isinstance(part, str):
             if part:
-                converted.append({"type": "input_text", "text": part})
+                converted.append({"type": text_type, "text": part})
             continue
         if not isinstance(part, dict):
             continue
@@ -50,7 +76,7 @@ def _chat_content_to_responses_parts(content: Any) -> List[Dict[str, Any]]:
         if ptype in {"text", "input_text", "output_text"}:
             text = part.get("text")
             if isinstance(text, str) and text:
-                converted.append({"type": "input_text", "text": text})
+                converted.append({"type": text_type, "text": text})
             continue
         if ptype in {"image_url", "input_image"}:
             image_ref = part.get("image_url")
@@ -201,6 +227,23 @@ def _responses_tools(tools: Optional[List[Dict[str, Any]]] = None) -> Optional[L
 # Message format conversion
 # ---------------------------------------------------------------------------
 
+_RESPONSE_MESSAGE_STATUSES = {"completed", "incomplete", "in_progress"}
+
+
+def _normalize_responses_message_status(value: Any, *, default: str = "completed") -> str:
+    """Normalize a Responses assistant message status for replay.
+
+    The API accepts completed/incomplete/in_progress on replayed assistant
+    output messages.  Preserve those exactly (modulo case/hyphen spelling) so
+    incomplete Codex continuation turns don't get falsely marked completed.
+    """
+    if isinstance(value, str):
+        status = value.strip().lower().replace("-", "_").replace(" ", "_")
+        if status in _RESPONSE_MESSAGE_STATUSES:
+            return status
+    return default
+
+
 def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
     """Convert internal chat-style messages to Responses input items."""
     items: List[Dict[str, Any]] = []
@@ -216,9 +259,10 @@ def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Di
         if role in {"user", "assistant"}:
             content = msg.get("content", "")
             if isinstance(content, list):
-                content_parts = _chat_content_to_responses_parts(content)
+                content_parts = _chat_content_to_responses_parts(content, role=role)
+                text_type = "output_text" if role == "assistant" else "input_text"
                 content_text = "".join(
-                    p.get("text", "") for p in content_parts if p.get("type") == "input_text"
+                    p.get("text", "") for p in content_parts if p.get("type") == text_type
                 )
             else:
                 content_parts = []
@@ -245,7 +289,57 @@ def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Di
                                 seen_item_ids.add(item_id)
                             has_codex_reasoning = True
 
-                if content_parts:
+                # Replay exact assistant message items (with id/phase) from
+                # previous turns so the API can maintain prefix-cache hits.
+                # OpenAI docs: "preserve and resend phase on all assistant
+                # messages — dropping it can degrade performance."
+                codex_message_items = msg.get("codex_message_items")
+                replayed_message_items = 0
+                if isinstance(codex_message_items, list):
+                    for raw_item in codex_message_items:
+                        if not isinstance(raw_item, dict):
+                            continue
+                        if raw_item.get("type") != "message" or raw_item.get("role") != "assistant":
+                            continue
+                        raw_content_parts = raw_item.get("content")
+                        if not isinstance(raw_content_parts, list):
+                            continue
+
+                        normalized_content_parts = []
+                        for part in raw_content_parts:
+                            if not isinstance(part, dict):
+                                continue
+                            part_type = str(part.get("type") or "").strip()
+                            if part_type not in {"output_text", "text"}:
+                                continue
+                            text = part.get("text", "")
+                            if text is None:
+                                text = ""
+                            if not isinstance(text, str):
+                                text = str(text)
+                            normalized_content_parts.append({"type": "output_text", "text": text})
+
+                        if not normalized_content_parts:
+                            continue
+
+                        replay_item = {
+                            "type": "message",
+                            "role": "assistant",
+                            "status": _normalize_responses_message_status(raw_item.get("status")),
+                            "content": normalized_content_parts,
+                        }
+                        item_id = raw_item.get("id")
+                        if isinstance(item_id, str) and item_id.strip():
+                            replay_item["id"] = item_id.strip()
+                        phase = raw_item.get("phase")
+                        if isinstance(phase, str) and phase.strip():
+                            replay_item["phase"] = phase.strip()
+                        items.append(replay_item)
+                        replayed_message_items += 1
+
+                if replayed_message_items > 0:
+                    pass
+                elif content_parts:
                     items.append({"role": "assistant", "content": content_parts})
                 elif content_text.strip():
                     items.append({"role": "assistant", "content": content_text})
@@ -405,6 +499,47 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
                 normalized.append(reasoning_item)
             continue
 
+        if item_type == "message":
+            role = item.get("role")
+            if role != "assistant":
+                raise ValueError(f"Codex Responses input[{idx}] message items must have role='assistant'.")
+            content = item.get("content")
+            if not isinstance(content, list):
+                raise ValueError(f"Codex Responses input[{idx}] message item must have content list.")
+            normalized_content = []
+            for part_idx, part in enumerate(content):
+                if not isinstance(part, dict):
+                    raise ValueError(
+                        f"Codex Responses input[{idx}] message content[{part_idx}] must be an object."
+                    )
+                part_type = part.get("type")
+                if part_type not in {"output_text", "text"}:
+                    raise ValueError(
+                        f"Codex Responses input[{idx}] message content[{part_idx}] has unsupported type {part_type!r}."
+                    )
+                text = part.get("text", "")
+                if text is None:
+                    text = ""
+                if not isinstance(text, str):
+                    text = str(text)
+                normalized_content.append({"type": "output_text", "text": text})
+            if not normalized_content:
+                raise ValueError(f"Codex Responses input[{idx}] message item must contain at least one text part.")
+            normalized_item: Dict[str, Any] = {
+                "type": "message",
+                "role": "assistant",
+                "status": _normalize_responses_message_status(item.get("status")),
+                "content": normalized_content,
+            }
+            item_id = item.get("id")
+            if isinstance(item_id, str) and item_id.strip():
+                normalized_item["id"] = item_id.strip()
+            phase = item.get("phase")
+            if isinstance(phase, str) and phase.strip():
+                normalized_item["phase"] = phase.strip()
+            normalized.append(normalized_item)
+            continue
+
         role = item.get("role")
         if role in {"user", "assistant"}:
             content = item.get("content", "")
@@ -412,13 +547,16 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
                 content = ""
             if isinstance(content, list):
                 # Multimodal content from ``_chat_messages_to_responses_input``
-                # is already in Responses format (``input_text`` / ``input_image``).
-                # Validate each part and pass through.
+                # is already in Responses format (``input_text`` / ``output_text``
+                # / ``input_image``).  Validate each part and pass through.
+                # Use the correct text type for the role — ``output_text`` for
+                # assistant messages, ``input_text`` for user messages.
+                text_type = "output_text" if role == "assistant" else "input_text"
                 validated: List[Dict[str, Any]] = []
                 for part_idx, part in enumerate(content):
                     if isinstance(part, str):
                         if part:
-                            validated.append({"type": "input_text", "text": part})
+                            validated.append({"type": text_type, "text": part})
                         continue
                     if not isinstance(part, dict):
                         raise ValueError(
@@ -429,7 +567,7 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
                         text = part.get("text", "")
                         if not isinstance(text, str):
                             text = str(text or "")
-                        validated.append({"type": "input_text", "text": text})
+                        validated.append({"type": text_type, "text": text})
                     elif ptype in {"input_image", "image_url"}:
                         image_ref = part.get("image_url", "")
                         detail = part.get("detail")
@@ -686,6 +824,7 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
     content_parts: List[str] = []
     reasoning_parts: List[str] = []
     reasoning_items_raw: List[Dict[str, Any]] = []
+    message_items_raw: List[Dict[str, Any]] = []
     tool_calls: List[Any] = []
     has_incomplete_items = response_status in {"queued", "in_progress", "incomplete"}
     saw_commentary_phase = False
@@ -704,6 +843,7 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
 
         if item_type == "message":
             item_phase = getattr(item, "phase", None)
+            normalized_phase = None
             if isinstance(item_phase, str):
                 normalized_phase = item_phase.strip().lower()
                 if normalized_phase in {"commentary", "analysis"}:
@@ -713,6 +853,18 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
             message_text = _extract_responses_message_text(item)
             if message_text:
                 content_parts.append(message_text)
+                raw_message_item: Dict[str, Any] = {
+                    "type": "message",
+                    "role": "assistant",
+                    "status": _normalize_responses_message_status(item_status),
+                    "content": [{"type": "output_text", "text": message_text}],
+                }
+                item_id = getattr(item, "id", None)
+                if isinstance(item_id, str) and item_id:
+                    raw_message_item["id"] = item_id
+                if normalized_phase:
+                    raw_message_item["phase"] = normalized_phase
+                message_items_raw.append(raw_message_item)
         elif item_type == "reasoning":
             reasoning_text = _extract_responses_reasoning_text(item)
             if reasoning_text:
@@ -787,6 +939,37 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
         if isinstance(out_text, str):
             final_text = out_text.strip()
 
+    # ── Tool-call leak recovery ──────────────────────────────────
+    # gpt-5.x on the Codex Responses API sometimes degenerates and emits
+    # what should be a structured `function_call` item as plain assistant
+    # text using the Harmony/Codex serialization (``to=functions.foo
+    # {json}`` or ``assistant to=functions.foo {json}``). The model
+    # intended to call a tool, but the intent never made it into
+    # ``response.output`` as a ``function_call`` item, so ``tool_calls``
+    # is empty here. If we pass this through, the parent sees a
+    # confident-looking summary with no audit trail (empty ``tool_trace``)
+    # and no tools actually ran — the Taiwan-embassy-email incident.
+    #
+    # Detection: leaked tokens always contain ``to=functions.<name>`` and
+    # the assistant message has no real tool calls. Treat it as incomplete
+    # so the existing Codex-incomplete continuation path (3 retries,
+    # handled in run_agent.py) gets a chance to re-elicit a proper
+    # ``function_call`` item. The existing loop already handles message
+    # append, dedup, and retry budget.
+    leaked_tool_call_text = False
+    if final_text and not tool_calls and _TOOL_CALL_LEAK_PATTERN.search(final_text):
+        leaked_tool_call_text = True
+        logger.warning(
+            "Codex response contains leaked tool-call text in assistant content "
+            "(no structured function_call items). Treating as incomplete so the "
+            "continuation path can re-elicit a proper tool call. Leaked snippet: %r",
+            final_text[:300],
+        )
+        # Clear the text so downstream code doesn't surface the garbage as
+        # a summary. The encrypted reasoning items (if any) are preserved
+        # so the model keeps its chain-of-thought on the retry.
+        final_text = ""
+
     assistant_message = SimpleNamespace(
         content=final_text,
         tool_calls=tool_calls,
@@ -794,10 +977,13 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
         reasoning_content=None,
         reasoning_details=None,
         codex_reasoning_items=reasoning_items_raw or None,
+        codex_message_items=message_items_raw or None,
     )
 
     if tool_calls:
         finish_reason = "tool_calls"
+    elif leaked_tool_call_text:
+        finish_reason = "incomplete"
     elif has_incomplete_items or (saw_commentary_phase and not saw_final_answer_phase):
         finish_reason = "incomplete"
     elif reasoning_items_raw and not final_text:

agent/context_compressor.py

@@ -294,6 +294,7 @@ class ContextCompressor(ContextEngine):
         self._context_probed = False
         self._context_probe_persistable = False
         self._previous_summary = None
+        self._last_summary_error = None
         self._last_compression_savings_pct = 100.0
         self._ineffective_compression_count = 0
 
@@ -317,6 +318,13 @@ class ContextCompressor(ContextEngine):
             int(context_length * self.threshold_percent),
             MINIMUM_CONTEXT_LENGTH,
         )
+        # Recalculate token budgets for the new context length so the
+        # compressor stays calibrated after a model switch (e.g. 200K → 32K).
+        target_tokens = int(self.threshold_tokens * self.summary_target_ratio)
+        self.tail_token_budget = target_tokens
+        self.max_summary_tokens = min(
+            int(context_length * 0.05), _SUMMARY_TOKENS_CEILING,
+        )
 
     def __init__(
         self,
@@ -389,6 +397,7 @@ class ContextCompressor(ContextEngine):
         self._last_compression_savings_pct: float = 100.0
         self._ineffective_compression_count: int = 0
         self._summary_failure_cooldown_until: float = 0.0
+        self._last_summary_error: Optional[str] = None
 
     def update_from_response(self, usage: Dict[str, Any]):
         """Update tracked token usage from API response."""
@@ -812,10 +821,12 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             self._previous_summary = summary
             self._summary_failure_cooldown_until = 0.0
             self._summary_model_fallen_back = False
+            self._last_summary_error = None
             return self._with_summary_prefix(summary)
         except RuntimeError:
             # No provider configured — long cooldown, unlikely to self-resolve
             self._summary_failure_cooldown_until = time.monotonic() + _SUMMARY_FAILURE_COOLDOWN_SECONDS
+            self._last_summary_error = "no auxiliary LLM provider configured"
             logging.warning("Context compression: no provider available for "
                             "summary. Middle turns will be dropped without summary "
                             "for %d seconds.",
@@ -853,6 +864,10 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             # Transient errors (timeout, rate limit, network) — shorter cooldown
             _transient_cooldown = 60
             self._summary_failure_cooldown_until = time.monotonic() + _transient_cooldown
+            err_text = str(e).strip() or e.__class__.__name__
+            if len(err_text) > 220:
+                err_text = err_text[:217].rstrip() + "..."
+            self._last_summary_error = err_text
             logging.warning(
                 "Failed to generate context summary: %s. "
                 "Further summary attempts paused for %d seconds.",
@@ -1099,6 +1114,21 @@ The user has requested that this compaction PRIORITISE preserving all informatio
 
         return max(cut_idx, head_end + 1)
 
+    # ------------------------------------------------------------------
+    # ContextEngine: manual /compress preflight
+    # ------------------------------------------------------------------
+
+    def has_content_to_compress(self, messages: List[Dict[str, Any]]) -> bool:
+        """Return True if there is a non-empty middle region to compact.
+
+        Overrides the ABC default so the gateway ``/compress`` guard can
+        skip the LLM call when the transcript is still entirely inside
+        the protected head/tail.
+        """
+        compress_start = self._align_boundary_forward(messages, self.protect_first_n)
+        compress_end = self._find_tail_cut_by_tokens(messages, compress_start)
+        return compress_start < compress_end
+
     # ------------------------------------------------------------------
     # Main compression entry point
     # ------------------------------------------------------------------

agent/context_engine.py

@@ -78,6 +78,7 @@ class ContextEngine(ABC):
         self,
         messages: List[Dict[str, Any]],
         current_tokens: int = None,
+        focus_topic: str = None,
     ) -> List[Dict[str, Any]]:
         """Compact the message list and return the new message list.
 
@@ -86,6 +87,12 @@ class ContextEngine(ABC):
         context budget. The implementation is free to summarize, build a
         DAG, or do anything else — as long as the returned list is a valid
         OpenAI-format message sequence.
+
+        Args:
+            focus_topic: Optional topic string from manual ``/compress <focus>``.
+                Engines that support guided compression should prioritise
+                preserving information related to this topic.  Engines that
+                don't support it may simply ignore this argument.
         """
 
     # -- Optional: pre-flight check ----------------------------------------
@@ -98,6 +105,21 @@ class ContextEngine(ABC):
         """
         return False
 
+    # -- Optional: manual /compress preflight ------------------------------
+
+    def has_content_to_compress(self, messages: List[Dict[str, Any]]) -> bool:
+        """Quick check: is there anything in ``messages`` that can be compacted?
+
+        Used by the gateway ``/compress`` command as a preflight guard —
+        returning False lets the gateway report "nothing to compress yet"
+        without making an LLM call.
+
+        Default returns True (always attempt).  Engines with a cheap way
+        to introspect their own head/tail boundaries should override this
+        to return False when the transcript is still entirely protected.
+        """
+        return True
+
     # -- Optional: session lifecycle ---------------------------------------
 
     def on_session_start(self, session_id: str, **kwargs) -> None:

agent/copilot_acp_client.py

@@ -46,6 +46,47 @@ def _resolve_args() -> list[str]:
     return shlex.split(raw)
 
 
+def _resolve_home_dir() -> str:
+    """Return a stable HOME for child ACP processes."""
+
+    try:
+        from hermes_constants import get_subprocess_home
+
+        profile_home = get_subprocess_home()
+        if profile_home:
+            return profile_home
+    except Exception:
+        pass
+
+    home = os.environ.get("HOME", "").strip()
+    if home:
+        return home
+
+    expanded = os.path.expanduser("~")
+    if expanded and expanded != "~":
+        return expanded
+
+    try:
+        import pwd
+
+        resolved = pwd.getpwuid(os.getuid()).pw_dir.strip()
+        if resolved:
+            return resolved
+    except Exception:
+        pass
+
+    # Last resort: /tmp (writable on any POSIX system). Avoids crashing the
+    # subprocess with no HOME; callers can set HERMES_HOME explicitly if they
+    # need a different writable dir.
+    return "/tmp"
+
+
+def _build_subprocess_env() -> dict[str, str]:
+    env = os.environ.copy()
+    env["HOME"] = _resolve_home_dir()
+    return env
+
+
 def _jsonrpc_error(message_id: Any, code: int, message: str) -> dict[str, Any]:
     return {
         "jsonrpc": "2.0",
@@ -382,6 +423,7 @@ class CopilotACPClient:
                 text=True,
                 bufsize=1,
                 cwd=self._acp_cwd,
+                env=_build_subprocess_env(),
             )
         except FileNotFoundError as exc:
             raise RuntimeError(

agent/credential_pool.py

@@ -455,6 +455,61 @@ class CredentialPool:
             logger.debug("Failed to sync from credentials file: %s", exc)
         return entry
 
+    def _sync_nous_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
+        """Sync a Nous pool entry from auth.json if tokens differ.
+
+        Nous OAuth refresh tokens are single-use.  When another process
+        (e.g. a concurrent cron) refreshes the token via
+        ``resolve_nous_runtime_credentials``, it writes fresh tokens to
+        auth.json under ``_auth_store_lock``.  The pool entry's tokens
+        become stale.  This method detects that and adopts the newer pair,
+        avoiding a "refresh token reuse" revocation on the Nous Portal.
+        """
+        if self.provider != "nous" or entry.source != "device_code":
+            return entry
+        try:
+            with _auth_store_lock():
+                auth_store = _load_auth_store()
+                state = _load_provider_state(auth_store, "nous")
+            if not state:
+                return entry
+            store_refresh = state.get("refresh_token", "")
+            store_access = state.get("access_token", "")
+            if store_refresh and store_refresh != entry.refresh_token:
+                logger.debug(
+                    "Pool entry %s: syncing tokens from auth.json (Nous refresh token changed)",
+                    entry.id,
+                )
+                field_updates: Dict[str, Any] = {
+                    "access_token": store_access,
+                    "refresh_token": store_refresh,
+                    "last_status": None,
+                    "last_status_at": None,
+                    "last_error_code": None,
+                }
+                if state.get("expires_at"):
+                    field_updates["expires_at"] = state["expires_at"]
+                if state.get("agent_key"):
+                    field_updates["agent_key"] = state["agent_key"]
+                if state.get("agent_key_expires_at"):
+                    field_updates["agent_key_expires_at"] = state["agent_key_expires_at"]
+                if state.get("inference_base_url"):
+                    field_updates["inference_base_url"] = state["inference_base_url"]
+                extra_updates = dict(entry.extra)
+                for extra_key in ("obtained_at", "expires_in", "agent_key_id",
+                                  "agent_key_expires_in", "agent_key_reused",
+                                  "agent_key_obtained_at"):
+                    val = state.get(extra_key)
+                    if val is not None:
+                        extra_updates[extra_key] = val
+                updated = replace(entry, extra=extra_updates, **field_updates)
+                self._replace_entry(entry, updated)
+                self._persist()
+                return updated
+        except Exception as exc:
+            logger.debug("Failed to sync Nous entry from auth.json: %s", exc)
+        return entry
+
     def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
         """Write refreshed pool entry tokens back to auth.json providers.
 
@@ -561,6 +616,9 @@ class CredentialPool:
                     last_refresh=refreshed.get("last_refresh"),
                 )
             elif self.provider == "nous":
+                synced = self._sync_nous_entry_from_auth_store(entry)
+                if synced is not entry:
+                    entry = synced
                 nous_state = {
                     "access_token": entry.access_token,
                     "refresh_token": entry.refresh_token,
@@ -635,6 +693,26 @@ class CredentialPool:
                     # Credentials file had a valid (non-expired) token — use it directly
                     logger.debug("Credentials file has valid token, using without refresh")
                     return synced
+            # For nous: another process may have consumed the refresh token
+            # between our proactive sync and the HTTP call.  Re-sync from
+            # auth.json and adopt the fresh tokens if available.
+            if self.provider == "nous":
+                synced = self._sync_nous_entry_from_auth_store(entry)
+                if synced.refresh_token != entry.refresh_token:
+                    logger.debug("Nous refresh failed but auth.json has newer tokens — adopting")
+                    updated = replace(
+                        synced,
+                        last_status=STATUS_OK,
+                        last_status_at=None,
+                        last_error_code=None,
+                        last_error_reason=None,
+                        last_error_message=None,
+                        last_error_reset_at=None,
+                    )
+                    self._replace_entry(synced, updated)
+                    self._persist()
+                    self._sync_device_code_entry_to_auth_store(updated)
+                    return updated
             self._mark_exhausted(entry, None)
             return None
 
@@ -698,6 +776,17 @@ class CredentialPool:
                 if synced is not entry:
                     entry = synced
                     cleared_any = True
+            # For nous entries, sync from auth.json before status checks.
+            # Another process may have successfully refreshed via
+            # resolve_nous_runtime_credentials(), making this entry's
+            # exhausted status stale.
+            if (self.provider == "nous"
+                    and entry.source == "device_code"
+                    and entry.last_status == STATUS_EXHAUSTED):
+                synced = self._sync_nous_entry_from_auth_store(entry)
+                if synced is not entry:
+                    entry = synced
+                    cleared_any = True
             if entry.last_status == STATUS_EXHAUSTED:
                 exhausted_until = _exhausted_until(entry)
                 if exhausted_until is not None and now < exhausted_until:
@@ -739,8 +828,11 @@ class CredentialPool:
 
         if self._strategy == STRATEGY_LEAST_USED and len(available) > 1:
             entry = min(available, key=lambda e: e.request_count)
+            # Increment usage counter so subsequent selections distribute load
+            updated = replace(entry, request_count=entry.request_count + 1)
+            self._replace_entry(entry, updated)
             self._current_id = entry.id
-            return entry
+            return updated
 
         if self._strategy == STRATEGY_ROUND_ROBIN and len(available) > 1:
             entry = available[0]
@@ -1056,6 +1148,18 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                     "inference_base_url": state.get("inference_base_url"),
                     "agent_key": state.get("agent_key"),
                     "agent_key_expires_at": state.get("agent_key_expires_at"),
+                    # Carry the mint/refresh timestamps into the pool so
+                    # freshness-sensitive consumers (self-heal hooks, pool
+                    # pruning by age) can distinguish just-minted credentials
+                    # from stale ones.  Without these, fresh device_code
+                    # entries get obtained_at=None and look older than they
+                    # are (#15099).
+                    "obtained_at": state.get("obtained_at"),
+                    "expires_in": state.get("expires_in"),
+                    "agent_key_id": state.get("agent_key_id"),
+                    "agent_key_expires_in": state.get("agent_key_expires_in"),
+                    "agent_key_reused": state.get("agent_key_reused"),
+                    "agent_key_obtained_at": state.get("agent_key_obtained_at"),
                     "tls": state.get("tls") if isinstance(state.get("tls"), dict) else None,
                     "label": seeded_label,
                 },
@@ -1066,9 +1170,10 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
         # env vars (COPILOT_GITHUB_TOKEN / GH_TOKEN).  They don't live in
         # the auth store or credential pool, so we resolve them here.
         try:
-            from hermes_cli.copilot_auth import resolve_copilot_token
+            from hermes_cli.copilot_auth import resolve_copilot_token, get_copilot_api_token
             token, source = resolve_copilot_token()
             if token:
+                api_token = get_copilot_api_token(token)
                 source_name = "gh_cli" if "gh" in source.lower() else f"env:{source}"
                 if not _is_suppressed(provider, source_name):
                     active_sources.add(source_name)
@@ -1080,7 +1185,7 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                         {
                             "source": source_name,
                             "auth_type": AUTH_TYPE_API_KEY,
-                            "access_token": token,
+                            "access_token": api_token,
                             "base_url": pconfig.inference_base_url if pconfig else "",
                             "label": source,
                         },

agent/error_classifier.py

@@ -45,6 +45,7 @@ class FailoverReason(enum.Enum):
 
     # Model
     model_not_found = "model_not_found"  # 404 or invalid model — fallback to different model
+    provider_policy_blocked = "provider_policy_blocked"  # Aggregator (e.g. OpenRouter) blocked the only endpoint due to account data/privacy policy
 
     # Request format
     format_error = "format_error"        # 400 bad request — abort or strip + retry
@@ -194,6 +195,29 @@ _MODEL_NOT_FOUND_PATTERNS = [
     "unsupported model",
 ]
 
+# OpenRouter aggregator policy-block patterns.
+#
+# When a user's OpenRouter account privacy setting (or a per-request
+# `provider.data_collection: deny` preference) excludes the only endpoint
+# serving a model, OpenRouter returns 404 with a *specific* message that is
+# distinct from "model not found":
+#
+#   "No endpoints available matching your guardrail restrictions and
+#    data policy. Configure: https://openrouter.ai/settings/privacy"
+#
+# We classify this as `provider_policy_blocked` rather than
+# `model_not_found` because:
+#   - The model *exists* — model_not_found is misleading in logs
+#   - Provider fallback won't help: the account-level setting applies to
+#     every call on the same OpenRouter account
+#   - The error body already contains the fix URL, so the user gets
+#     actionable guidance without us rewriting the message
+_PROVIDER_POLICY_BLOCKED_PATTERNS = [
+    "no endpoints available matching your guardrail",
+    "no endpoints available matching your data policy",
+    "no endpoints found matching your data policy",
+]
+
 # Auth patterns (non-status-code signals)
 _AUTH_PATTERNS = [
     "invalid api key",
@@ -319,6 +343,11 @@ def classify_api_error(
     """
     status_code = _extract_status_code(error)
     error_type = type(error).__name__
+    # Copilot/GitHub Models RateLimitError may not set .status_code; force 429
+    # so downstream rate-limit handling (classifier reason, pool rotation,
+    # fallback gating) fires correctly instead of misclassifying as generic.
+    if status_code is None and error_type == "RateLimitError":
+        status_code = 429
     body = _extract_error_body(error)
     error_code = _extract_error_code(body)
 
@@ -523,6 +552,17 @@ def _classify_by_status(
         return _classify_402(error_msg, result_fn)
 
     if status_code == 404:
+        # OpenRouter policy-block 404 — distinct from "model not found".
+        # The model exists; the user's account privacy setting excludes the
+        # only endpoint serving it. Falling back to another provider won't
+        # help (same account setting applies).  The error body already
+        # contains the fix URL, so just surface it.
+        if any(p in error_msg for p in _PROVIDER_POLICY_BLOCKED_PATTERNS):
+            return result_fn(
+                FailoverReason.provider_policy_blocked,
+                retryable=False,
+                should_fallback=False,
+            )
         if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
             return result_fn(
                 FailoverReason.model_not_found,
@@ -640,6 +680,12 @@ def _classify_400(
         )
 
     # Some providers return model-not-found as 400 instead of 404 (e.g. OpenRouter).
+    if any(p in error_msg for p in _PROVIDER_POLICY_BLOCKED_PATTERNS):
+        return result_fn(
+            FailoverReason.provider_policy_blocked,
+            retryable=False,
+            should_fallback=False,
+        )
     if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
         return result_fn(
             FailoverReason.model_not_found,
@@ -812,6 +858,15 @@ def _classify_by_message(
             should_fallback=True,
         )
 
+    # Provider policy-block (aggregator-side guardrail) — check before
+    # model_not_found so we don't mis-label as a missing model.
+    if any(p in error_msg for p in _PROVIDER_POLICY_BLOCKED_PATTERNS):
+        return result_fn(
+            FailoverReason.provider_policy_blocked,
+            retryable=False,
+            should_fallback=False,
+        )
+
     # Model not found patterns
     if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
         return result_fn(

agent/gemini_native_adapter.py

@@ -44,6 +44,97 @@ def is_native_gemini_base_url(base_url: str) -> bool:
     return not normalized.endswith("/openai")
 
 
+def probe_gemini_tier(
+    api_key: str,
+    base_url: str = DEFAULT_GEMINI_BASE_URL,
+    *,
+    model: str = "gemini-2.5-flash",
+    timeout: float = 10.0,
+) -> str:
+    """Probe a Google AI Studio API key and return its tier.
+
+    Returns one of:
+
+    - ``"free"``    -- key is on the free tier (unusable with Hermes)
+    - ``"paid"``    -- key is on a paid tier
+    - ``"unknown"`` -- probe failed; callers should proceed without blocking.
+    """
+    key = (api_key or "").strip()
+    if not key:
+        return "unknown"
+
+    normalized_base = str(base_url or DEFAULT_GEMINI_BASE_URL).strip().rstrip("/")
+    if not normalized_base:
+        normalized_base = DEFAULT_GEMINI_BASE_URL
+    if normalized_base.lower().endswith("/openai"):
+        normalized_base = normalized_base[: -len("/openai")]
+
+    url = f"{normalized_base}/models/{model}:generateContent"
+    payload = {
+        "contents": [{"role": "user", "parts": [{"text": "hi"}]}],
+        "generationConfig": {"maxOutputTokens": 1},
+    }
+
+    try:
+        with httpx.Client(timeout=timeout) as client:
+            resp = client.post(
+                url,
+                params={"key": key},
+                json=payload,
+                headers={"Content-Type": "application/json"},
+            )
+    except Exception as exc:
+        logger.debug("probe_gemini_tier: network error: %s", exc)
+        return "unknown"
+
+    headers_lower = {k.lower(): v for k, v in resp.headers.items()}
+    rpd_header = headers_lower.get("x-ratelimit-limit-requests-per-day")
+    if rpd_header:
+        try:
+            rpd_val = int(rpd_header)
+        except (TypeError, ValueError):
+            rpd_val = None
+        # Published free-tier daily caps (Dec 2025):
+        #   gemini-2.5-pro: 100, gemini-2.5-flash: 250, flash-lite: 1000
+        # Tier 1 starts at ~1500+ for Flash. We treat <= 1000 as free.
+        if rpd_val is not None and rpd_val <= 1000:
+            return "free"
+        if rpd_val is not None and rpd_val > 1000:
+            return "paid"
+
+    if resp.status_code == 429:
+        body_text = ""
+        try:
+            body_text = resp.text or ""
+        except Exception:
+            body_text = ""
+        if "free_tier" in body_text.lower():
+            return "free"
+        return "paid"
+
+    if 200 <= resp.status_code < 300:
+        return "paid"
+
+    return "unknown"
+
+
+def is_free_tier_quota_error(error_message: str) -> bool:
+    """Return True when a Gemini 429 message indicates free-tier exhaustion."""
+    if not error_message:
+        return False
+    return "free_tier" in error_message.lower()
+
+
+_FREE_TIER_GUIDANCE = (
+    "\n\nYour Google API key is on the free tier (<= 250 requests/day for "
+    "gemini-2.5-flash). Hermes typically makes 3-10 API calls per user turn, "
+    "so the free tier is exhausted in a handful of messages and cannot sustain "
+    "an agent session. Enable billing on your Google Cloud project and "
+    "regenerate the key in a billing-enabled project: "
+    "https://aistudio.google.com/apikey"
+)
+
+
 class GeminiAPIError(Exception):
     """Error shape compatible with Hermes retry/error classification."""
 
@@ -650,6 +741,12 @@ def gemini_http_error(response: httpx.Response) -> GeminiAPIError:
     else:
         message = f"Gemini returned HTTP {status}: {body_text[:500]}"
 
+    # Free-tier quota exhaustion -> append actionable guidance so users who
+    # bypassed the setup wizard (direct GOOGLE_API_KEY in .env) still learn
+    # that the free tier cannot sustain an agent session.
+    if status == 429 and is_free_tier_quota_error(err_message or body_text):
+        message = message + _FREE_TIER_GUIDANCE
+
     return GeminiAPIError(
         message,
         code=code,
@@ -704,6 +801,13 @@ class GeminiNativeClient:
         http_client: Optional[httpx.Client] = None,
         **_: Any,
     ) -> None:
+        if not (api_key or "").strip():
+            raise RuntimeError(
+                "Gemini native client requires an API key, but none was provided. "
+                "Set GOOGLE_API_KEY or GEMINI_API_KEY in your environment / ~/.hermes/.env "
+                "(get one at https://aistudio.google.com/app/apikey), or run `hermes setup` "
+                "to configure the Google provider."
+            )
         self.api_key = api_key
         normalized_base = (base_url or DEFAULT_GEMINI_BASE_URL).rstrip("/")
         if normalized_base.endswith("/openai"):

agent/gemini_schema.py

@@ -73,6 +73,20 @@ def sanitize_gemini_schema(schema: Any) -> Dict[str, Any]:
             ]
             continue
         cleaned[key] = value
+
+    # Gemini's Schema validator requires every ``enum`` entry to be a string,
+    # even when the parent ``type`` is ``integer`` / ``number`` / ``boolean``.
+    # OpenAI / OpenRouter / Anthropic accept typed enums (e.g. Discord's
+    # ``auto_archive_duration: {type: integer, enum: [60, 1440, 4320, 10080]}``),
+    # so we only drop the ``enum`` when it would collide with Gemini's rule.
+    # Keeping ``type: integer`` plus the human-readable description gives the
+    # model enough guidance; the tool handler still validates the value.
+    enum_val = cleaned.get("enum")
+    type_val = cleaned.get("type")
+    if isinstance(enum_val, list) and type_val in {"integer", "number", "boolean"}:
+        if any(not isinstance(item, str) for item in enum_val):
+            cleaned.pop("enum", None)
+
     return cleaned
 
 

agent/memory_manager.py

@@ -31,6 +31,7 @@ from __future__ import annotations
 import json
 import logging
 import re
+import inspect
 from typing import Any, Dict, List, Optional
 
 from agent.memory_provider import MemoryProvider
@@ -312,7 +313,39 @@ class MemoryManager:
                 )
         return "\n\n".join(parts)
 
-    def on_memory_write(self, action: str, target: str, content: str) -> None:
+    @staticmethod
+    def _provider_memory_write_metadata_mode(provider: MemoryProvider) -> str:
+        """Return how to pass metadata to a provider's memory-write hook."""
+        try:
+            signature = inspect.signature(provider.on_memory_write)
+        except (TypeError, ValueError):
+            return "keyword"
+
+        params = list(signature.parameters.values())
+        if any(p.kind == inspect.Parameter.VAR_KEYWORD for p in params):
+            return "keyword"
+        if "metadata" in signature.parameters:
+            return "keyword"
+
+        accepted = [
+            p for p in params
+            if p.kind in (
+                inspect.Parameter.POSITIONAL_ONLY,
+                inspect.Parameter.POSITIONAL_OR_KEYWORD,
+                inspect.Parameter.KEYWORD_ONLY,
+            )
+        ]
+        if len(accepted) >= 4:
+            return "positional"
+        return "legacy"
+
+    def on_memory_write(
+        self,
+        action: str,
+        target: str,
+        content: str,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> None:
         """Notify external providers when the built-in memory tool writes.
 
         Skips the builtin provider itself (it's the source of the write).
@@ -321,7 +354,15 @@ class MemoryManager:
             if provider.name == "builtin":
                 continue
             try:
-                provider.on_memory_write(action, target, content)
+                metadata_mode = self._provider_memory_write_metadata_mode(provider)
+                if metadata_mode == "keyword":
+                    provider.on_memory_write(
+                        action, target, content, metadata=dict(metadata or {})
+                    )
+                elif metadata_mode == "positional":
+                    provider.on_memory_write(action, target, content, dict(metadata or {}))
+                else:
+                    provider.on_memory_write(action, target, content)
             except Exception as e:
                 logger.debug(
                     "Memory provider '%s' on_memory_write failed: %s",

agent/memory_provider.py

@@ -26,7 +26,7 @@ Optional hooks (override to opt in):
   on_turn_start(turn, message, **kwargs) — per-turn tick with runtime context
   on_session_end(messages)               — end-of-session extraction
   on_pre_compress(messages) -> str       — extract before context compression
-  on_memory_write(action, target, content) — mirror built-in memory writes
+  on_memory_write(action, target, content, metadata=None) — mirror built-in memory writes
   on_delegation(task, result, **kwargs)  — parent-side observation of subagent work
 """
 
@@ -34,7 +34,7 @@ from __future__ import annotations
 
 import logging
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 logger = logging.getLogger(__name__)
 
@@ -220,12 +220,21 @@ class MemoryProvider(ABC):
           should all have ``env_var`` set and this method stays no-op).
         """
 
-    def on_memory_write(self, action: str, target: str, content: str) -> None:
+    def on_memory_write(
+        self,
+        action: str,
+        target: str,
+        content: str,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> None:
         """Called when the built-in memory tool writes an entry.
 
         action: 'add', 'replace', or 'remove'
         target: 'memory' or 'user'
         content: the entry content
+        metadata: structured provenance for the write, when available. Common
+          keys include ``write_origin``, ``execution_context``, ``session_id``,
+          ``parent_session_id``, ``platform``, and ``tool_name``.
 
         Use to mirror built-in memory writes to your backend.
         """

agent/model_metadata.py

@@ -6,6 +6,7 @@ and run_agent.py for pre-flight context checks.
 
 import ipaddress
 import logging
+import os
 import re
 import time
 from pathlib import Path
@@ -21,6 +22,25 @@ from hermes_constants import OPENROUTER_MODELS_URL
 
 logger = logging.getLogger(__name__)
 
+
+def _resolve_requests_verify() -> bool | str:
+    """Resolve SSL verify setting for `requests` calls from env vars.
+
+    The `requests` library only honours REQUESTS_CA_BUNDLE / CURL_CA_BUNDLE
+    by default. Hermes also honours HERMES_CA_BUNDLE (its own convention)
+    and SSL_CERT_FILE (used by the stdlib `ssl` module and by httpx), so
+    that a single env var can cover both `requests` and `httpx` callsites
+    inside the same process.
+
+    Returns either a filesystem path to a CA bundle, or True to defer to
+    the requests default (certifi).
+    """
+    for env_var in ("HERMES_CA_BUNDLE", "REQUESTS_CA_BUNDLE", "SSL_CERT_FILE"):
+        val = os.getenv(env_var)
+        if val and os.path.isfile(val):
+            return val
+    return True
+
 # Provider names that can appear as a "provider:" prefix before a model ID.
 # Only these are stripped — Ollama-style "model:tag" colons (e.g. "qwen3.5:27b")
 # are preserved so the full model name reaches cache lookups and server queries.
@@ -86,9 +106,11 @@ _endpoint_model_metadata_cache_time: Dict[str, float] = {}
 _ENDPOINT_MODEL_CACHE_TTL = 300
 
 # Descending tiers for context length probing when the model is unknown.
-# We start at 128K (a safe default for most modern models) and step down
-# on context-length errors until one works.
+# We start at 256K (covers GPT-5.x, many current large-context models) and
+# step down on context-length errors until one works.  Tier[0] is also the
+# default fallback when no detection method succeeds.
 CONTEXT_PROBE_TIERS = [
+    256_000,
     128_000,
     64_000,
     32_000,
@@ -123,9 +145,11 @@ DEFAULT_CONTEXT_LENGTHS = {
     "claude": 200000,
     # OpenAI — GPT-5 family (most have 400k; specific overrides first)
     # Source: https://developers.openai.com/api/docs/models
-    # GPT-5.5 (launched Apr 23 2026). Verified via live ChatGPT codex/models
-    # endpoint: bare slug `gpt-5.5`, no -pro/-mini variants. 400k context on Codex.
-    "gpt-5.5": 400000,
+    # GPT-5.5 (launched Apr 23 2026) is 1.05M on the direct OpenAI API and
+    # ChatGPT Codex OAuth caps it at 272K; both paths resolve via their own
+    # provider-aware branches (_resolve_codex_oauth_context_length + models.dev).
+    # This hardcoded value is only reached when every probe misses.
+    "gpt-5.5": 1050000,
     "gpt-5.4-nano": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4-mini": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4": 1050000,               # GPT-5.4, GPT-5.4 Pro (1.05M context)
@@ -141,7 +165,17 @@ DEFAULT_CONTEXT_LENGTHS = {
     "gemma-4-31b": 256000,
     "gemma-3": 131072,
     "gemma": 8192,  # fallback for older gemma models
-    # DeepSeek
+    # DeepSeek — V4 family ships with a 1M context window. The legacy
+    # aliases ``deepseek-chat`` / ``deepseek-reasoner`` are server-side
+    # mapped to the non-thinking / thinking modes of ``deepseek-v4-flash``
+    # and inherit the same 1M window. The ``deepseek`` substring entry
+    # below remains as a 128K fallback for older / unknown DeepSeek model
+    # ids (e.g. via custom endpoints).
+    # https://api-docs.deepseek.com/zh-cn/quick_start/pricing
+    "deepseek-v4-pro": 1_000_000,
+    "deepseek-v4-flash": 1_000_000,
+    "deepseek-chat": 1_000_000,
+    "deepseek-reasoner": 1_000_000,
     "deepseek": 128000,
     # Meta
     "llama": 131072,
@@ -494,7 +528,7 @@ def fetch_model_metadata(force_refresh: bool = False) -> Dict[str, Dict[str, Any
         return _model_metadata_cache
 
     try:
-        response = requests.get(OPENROUTER_MODELS_URL, timeout=10)
+        response = requests.get(OPENROUTER_MODELS_URL, timeout=10, verify=_resolve_requests_verify())
         response.raise_for_status()
         data = response.json()
 
@@ -561,6 +595,7 @@ def fetch_endpoint_model_metadata(
                     server_url.rstrip("/") + "/api/v1/models",
                     headers=headers,
                     timeout=10,
+                    verify=_resolve_requests_verify(),
                 )
                 response.raise_for_status()
                 payload = response.json()
@@ -609,7 +644,7 @@ def fetch_endpoint_model_metadata(
     for candidate in candidates:
         url = candidate.rstrip("/") + "/models"
         try:
-            response = requests.get(url, headers=headers, timeout=10)
+            response = requests.get(url, headers=headers, timeout=10, verify=_resolve_requests_verify())
             response.raise_for_status()
             payload = response.json()
             cache: Dict[str, Dict[str, Any]] = {}
@@ -640,9 +675,10 @@ def fetch_endpoint_model_metadata(
                 try:
                     # Try /v1/props first (current llama.cpp); fall back to /props for older builds
                     base = candidate.rstrip("/").replace("/v1", "")
-                    props_resp = requests.get(base + "/v1/props", headers=headers, timeout=5)
+                    _verify = _resolve_requests_verify()
+                    props_resp = requests.get(base + "/v1/props", headers=headers, timeout=5, verify=_verify)
                     if not props_resp.ok:
-                        props_resp = requests.get(base + "/props", headers=headers, timeout=5)
+                        props_resp = requests.get(base + "/props", headers=headers, timeout=5, verify=_verify)
                     if props_resp.ok:
                         props = props_resp.json()
                         gen_settings = props.get("default_generation_settings", {})
@@ -714,6 +750,22 @@ def get_cached_context_length(model: str, base_url: str) -> Optional[int]:
     return cache.get(key)
 
 
+def _invalidate_cached_context_length(model: str, base_url: str) -> None:
+    """Drop a stale cache entry so it gets re-resolved on the next lookup."""
+    key = f"{model}@{base_url}"
+    cache = _load_context_cache()
+    if key not in cache:
+        return
+    del cache[key]
+    path = _get_context_cache_path()
+    try:
+        path.parent.mkdir(parents=True, exist_ok=True)
+        with open(path, "w") as f:
+            yaml.dump({"context_lengths": cache}, f, default_flow_style=False)
+    except Exception as e:
+        logger.debug("Failed to invalidate context length cache entry %s: %s", key, e)
+
+
 def get_next_probe_tier(current_length: int) -> Optional[int]:
     """Return the next lower probe tier, or None if already at minimum."""
     for tier in CONTEXT_PROBE_TIERS:
@@ -991,7 +1043,7 @@ def _query_anthropic_context_length(model: str, base_url: str, api_key: str) ->
             "x-api-key": api_key,
             "anthropic-version": "2023-06-01",
         }
-        resp = requests.get(url, headers=headers, timeout=10)
+        resp = requests.get(url, headers=headers, timeout=10, verify=_resolve_requests_verify())
         if resp.status_code != 200:
             return None
         data = resp.json()
@@ -1005,6 +1057,116 @@ def _query_anthropic_context_length(model: str, base_url: str, api_key: str) ->
     return None
 
 
+# Known ChatGPT Codex OAuth context windows (observed via live
+# chatgpt.com/backend-api/codex/models probe, Apr 2026). These are the
+# `context_window` values, which are what Codex actually enforces — the
+# direct OpenAI API has larger limits for the same slugs, but Codex OAuth
+# caps lower (e.g. gpt-5.5 is 1.05M on the API, 272K on Codex).
+#
+# Used as a fallback when the live probe fails (no token, network error).
+# Longest keys first so substring match picks the most specific entry.
+_CODEX_OAUTH_CONTEXT_FALLBACK: Dict[str, int] = {
+    "gpt-5.1-codex-max": 272_000,
+    "gpt-5.1-codex-mini": 272_000,
+    "gpt-5.3-codex": 272_000,
+    "gpt-5.2-codex": 272_000,
+    "gpt-5.4-mini": 272_000,
+    "gpt-5.5": 272_000,
+    "gpt-5.4": 272_000,
+    "gpt-5.2": 272_000,
+    "gpt-5": 272_000,
+}
+
+
+_codex_oauth_context_cache: Dict[str, int] = {}
+_codex_oauth_context_cache_time: float = 0.0
+_CODEX_OAUTH_CONTEXT_CACHE_TTL = 3600  # 1 hour
+
+
+def _fetch_codex_oauth_context_lengths(access_token: str) -> Dict[str, int]:
+    """Probe the ChatGPT Codex /models endpoint for per-slug context windows.
+
+    Codex OAuth imposes its own context limits that differ from the direct
+    OpenAI API (e.g. gpt-5.5 is 1.05M on the API, 272K on Codex). The
+    `context_window` field in each model entry is the authoritative source.
+
+    Returns a ``{slug: context_window}`` dict. Empty on failure.
+    """
+    global _codex_oauth_context_cache, _codex_oauth_context_cache_time
+    now = time.time()
+    if (
+        _codex_oauth_context_cache
+        and now - _codex_oauth_context_cache_time < _CODEX_OAUTH_CONTEXT_CACHE_TTL
+    ):
+        return _codex_oauth_context_cache
+
+    try:
+        resp = requests.get(
+            "https://chatgpt.com/backend-api/codex/models?client_version=1.0.0",
+            headers={"Authorization": f"Bearer {access_token}"},
+            timeout=10,
+            verify=_resolve_requests_verify(),
+        )
+        if resp.status_code != 200:
+            logger.debug(
+                "Codex /models probe returned HTTP %s; falling back to hardcoded defaults",
+                resp.status_code,
+            )
+            return {}
+        data = resp.json()
+    except Exception as exc:
+        logger.debug("Codex /models probe failed: %s", exc)
+        return {}
+
+    entries = data.get("models", []) if isinstance(data, dict) else []
+    result: Dict[str, int] = {}
+    for item in entries:
+        if not isinstance(item, dict):
+            continue
+        slug = item.get("slug")
+        ctx = item.get("context_window")
+        if isinstance(slug, str) and isinstance(ctx, int) and ctx > 0:
+            result[slug.strip()] = ctx
+
+    if result:
+        _codex_oauth_context_cache = result
+        _codex_oauth_context_cache_time = now
+    return result
+
+
+def _resolve_codex_oauth_context_length(
+    model: str, access_token: str = ""
+) -> Optional[int]:
+    """Resolve a Codex OAuth model's real context window.
+
+    Prefers a live probe of chatgpt.com/backend-api/codex/models (when we
+    have a bearer token), then falls back to ``_CODEX_OAUTH_CONTEXT_FALLBACK``.
+    """
+    model_bare = _strip_provider_prefix(model).strip()
+    if not model_bare:
+        return None
+
+    if access_token:
+        live = _fetch_codex_oauth_context_lengths(access_token)
+        if model_bare in live:
+            return live[model_bare]
+        # Case-insensitive match in case casing drifts
+        model_lower = model_bare.lower()
+        for slug, ctx in live.items():
+            if slug.lower() == model_lower:
+                return ctx
+
+    # Fallback: longest-key-first substring match over hardcoded defaults.
+    model_lower = model_bare.lower()
+    for slug, ctx in sorted(
+        _CODEX_OAUTH_CONTEXT_FALLBACK.items(), key=lambda x: len(x[0]), reverse=True
+    ):
+        if slug in model_lower:
+            return ctx
+
+    return None
+
+
 def _resolve_nous_context_length(model: str) -> Optional[int]:
     """Resolve Nous Portal model context length via OpenRouter metadata.
 
@@ -1044,12 +1206,14 @@ def get_model_context_length(
     api_key: str = "",
     config_context_length: int | None = None,
     provider: str = "",
+    custom_providers: list | None = None,
 ) -> int:
     """Get the context length for a model.
 
     Resolution order:
     0. Explicit config override (model.context_length or custom_providers per-model)
     1. Persistent cache (previously discovered via probing)
+    1b. AWS Bedrock static table (must precede custom-endpoint probe)
     2. Active endpoint metadata (/models for explicit custom endpoints)
     3. Local server query (for local endpoints)
     4. Anthropic /v1/models API (API-key users only, not OAuth)
@@ -1063,6 +1227,23 @@ def get_model_context_length(
     if config_context_length is not None and isinstance(config_context_length, int) and config_context_length > 0:
         return config_context_length
 
+    # 0b. custom_providers per-model override — check before any probe.
+    # This closes the gap where /model switch and display paths used to fall
+    # back to 128K despite the user having a per-model context_length set.
+    # See #15779.
+    if custom_providers and base_url and model:
+        try:
+            from hermes_cli.config import get_custom_provider_context_length
+            cp_ctx = get_custom_provider_context_length(
+                model=model,
+                base_url=base_url,
+                custom_providers=custom_providers,
+            )
+            if cp_ctx:
+                return cp_ctx
+        except Exception:
+            pass  # fall through to probing
+
     # Normalise provider-prefixed model names (e.g. "local:model-name" →
     # "model-name") so cache lookups and server queries use the bare ID that
     # local servers actually know about.  Ollama "model:tag" colons are preserved.
@@ -1072,7 +1253,41 @@ def get_model_context_length(
     if base_url:
         cached = get_cached_context_length(model, base_url)
         if cached is not None:
-            return cached
+            # Invalidate stale Codex OAuth cache entries: pre-PR #14935 builds
+            # resolved gpt-5.x to the direct-API value (e.g. 1.05M) via
+            # models.dev and persisted it. Codex OAuth caps at 272K for every
+            # slug, so any cached Codex entry at or above 400K is a leftover
+            # from the old resolution path. Drop it and fall through to the
+            # live /models probe in step 5 below.
+            if provider == "openai-codex" and cached >= 400_000:
+                logger.info(
+                    "Dropping stale Codex cache entry %s@%s -> %s (pre-fix value); "
+                    "re-resolving via live /models probe",
+                    model, base_url, f"{cached:,}",
+                )
+                _invalidate_cached_context_length(model, base_url)
+            else:
+                return cached
+
+    # 1b. AWS Bedrock — use static context length table.
+    # Bedrock's ListFoundationModels API doesn't expose context window sizes,
+    # so we maintain a curated table in bedrock_adapter.py that reflects
+    # AWS-imposed limits (e.g. 200K for Claude models vs 1M on the native
+    # Anthropic API).  This must run BEFORE the custom-endpoint probe at
+    # step 2 — bedrock-runtime.<region>.amazonaws.com is not in
+    # _URL_TO_PROVIDER, so it would otherwise be treated as a custom endpoint,
+    # fail the /models probe (Bedrock doesn't expose that shape), and fall
+    # back to the 128K default before reaching the original step 4b branch.
+    if provider == "bedrock" or (
+        base_url
+        and base_url_hostname(base_url).startswith("bedrock-runtime.")
+        and base_url_host_matches(base_url, "amazonaws.com")
+    ):
+        try:
+            from agent.bedrock_adapter import get_bedrock_context_length
+            return get_bedrock_context_length(model)
+        except ImportError:
+            pass  # boto3 not installed — fall through to generic resolution
 
     # 2. Active endpoint metadata for truly custom/unknown endpoints.
     # Known providers (Copilot, OpenAI, Anthropic, etc.) skip this — their
@@ -1119,19 +1334,7 @@ def get_model_context_length(
         if ctx:
             return ctx
 
-    # 4b. AWS Bedrock — use static context length table.
-    # Bedrock's ListFoundationModels doesn't expose context window sizes,
-    # so we maintain a curated table in bedrock_adapter.py.
-    if provider == "bedrock" or (
-        base_url
-        and base_url_hostname(base_url).startswith("bedrock-runtime.")
-        and base_url_host_matches(base_url, "amazonaws.com")
-    ):
-        try:
-            from agent.bedrock_adapter import get_bedrock_context_length
-            return get_bedrock_context_length(model)
-        except ImportError:
-            pass  # boto3 not installed — fall through to generic resolution
+    # 4b. (Bedrock handled earlier at step 1b — before custom-endpoint probe.)
 
     # 5. Provider-aware lookups (before generic OpenRouter cache)
     # These are provider-specific and take priority over the generic OR cache,
@@ -1145,10 +1348,32 @@ def get_model_context_length(
             if inferred:
                 effective_provider = inferred
 
+    # 5a. Copilot live /models API — max_prompt_tokens from the user's account.
+    # This catches account-specific models (e.g. claude-opus-4.6-1m) that
+    # don't exist in models.dev. For models that ARE in models.dev, this
+    # returns the provider-enforced limit which is what users can actually use.
+    if effective_provider in ("copilot", "copilot-acp", "github-copilot"):
+        try:
+            from hermes_cli.models import get_copilot_model_context
+            ctx = get_copilot_model_context(model, api_key=api_key)
+            if ctx:
+                return ctx
+        except Exception:
+            pass  # Fall through to models.dev
+
     if effective_provider == "nous":
         ctx = _resolve_nous_context_length(model)
         if ctx:
             return ctx
+    if effective_provider == "openai-codex":
+        # Codex OAuth enforces lower context limits than the direct OpenAI
+        # API for the same slug (e.g. gpt-5.5 is 1.05M on the API but 272K
+        # on Codex). Authoritative source is Codex's own /models endpoint.
+        codex_ctx = _resolve_codex_oauth_context_length(model, access_token=api_key or "")
+        if codex_ctx:
+            if base_url:
+                save_context_length(model, base_url, codex_ctx)
+            return codex_ctx
     if effective_provider:
         from agent.models_dev import lookup_models_dev_context
         ctx = lookup_models_dev_context(effective_provider, model)
@@ -1158,7 +1383,7 @@ def get_model_context_length(
     # 6. OpenRouter live API metadata (provider-unaware fallback)
     metadata = fetch_model_metadata()
     if model in metadata:
-        return metadata[model].get("context_length", 128000)
+        return metadata[model].get("context_length", DEFAULT_FALLBACK_CONTEXT)
 
     # 8. Hardcoded defaults (fuzzy match — longest key first for specificity)
     # Only check `default_model in model` (is the key a substring of the input).

agent/nous_rate_guard.py

@@ -180,3 +180,145 @@ def format_remaining(seconds: float) -> str:
     h, remainder = divmod(s, 3600)
     m = remainder // 60
     return f"{h}h {m}m" if m else f"{h}h"
+
+
+# Buckets with reset windows shorter than this are treated as transient
+# (upstream jitter, secondary throttling) rather than a genuine quota
+# exhaustion worth a cross-session breaker trip.
+_MIN_RESET_FOR_BREAKER_SECONDS = 60.0
+
+
+def is_genuine_nous_rate_limit(
+    *,
+    headers: Optional[Mapping[str, str]] = None,
+    last_known_state: Optional[Any] = None,
+) -> bool:
+    """Decide whether a 429 from Nous Portal is a real account rate limit.
+
+    Nous Portal multiplexes multiple upstream providers (DeepSeek, Kimi,
+    MiMo, Hermes, ...) behind one endpoint.  A 429 can mean either:
+
+      (a) The caller's own RPM / RPH / TPM / TPH bucket on Nous is
+          exhausted — a genuine rate limit that will last until the
+          bucket resets.
+      (b) The upstream provider is out of capacity for a specific model
+          — transient, clears in seconds, and has nothing to do with
+          the caller's quota on Nous.
+
+    Tripping the cross-session breaker on (b) blocks ALL Nous requests
+    (and all models, since Nous is one provider key) for minutes even
+    though the caller's account is healthy and a different model would
+    have worked.  That's the bug users hit when DeepSeek V4 Pro 429s
+    trigger a breaker that then blocks Kimi 2.6 and MiMo V2.5 Pro.
+
+    We tell the two apart by looking at:
+
+      1. The 429 response's own ``x-ratelimit-*`` headers.  Nous emits
+         the full suite on every response including 429s.  An exhausted
+         bucket (``remaining == 0`` with a reset window >= 60s) is
+         proof of (a).
+      2. The last-known-good rate-limit state captured by
+         ``_capture_rate_limits()`` on the previous successful
+         response.  If any bucket there was already near-exhausted with
+         a substantial reset window, the current 429 is almost
+         certainly (a) continuing from that condition.
+
+    If neither signal fires, we treat the 429 as (b): fail the single
+    request, let the retry loop or model-switch proceed, and do NOT
+    write the cross-session breaker file.
+
+    Returns True when the evidence points at (a).
+    """
+    # Signal 1: current 429 response headers.
+    state = _parse_buckets_from_headers(headers)
+    if _has_exhausted_bucket(state):
+        return True
+
+    # Signal 2: last-known-good state from a recent successful response.
+    # Accepts either a RateLimitState (dataclass from rate_limit_tracker)
+    # or a dict of bucket snapshots.
+    if last_known_state is not None and _has_exhausted_bucket_in_object(last_known_state):
+        return True
+
+    return False
+
+
+def _parse_buckets_from_headers(
+    headers: Optional[Mapping[str, str]],
+) -> dict[str, tuple[Optional[int], Optional[float]]]:
+    """Extract (remaining, reset_seconds) per bucket from x-ratelimit-* headers.
+
+    Returns empty dict when no rate-limit headers are present.
+    """
+    if not headers:
+        return {}
+
+    lowered = {k.lower(): v for k, v in headers.items()}
+    if not any(k.startswith("x-ratelimit-") for k in lowered):
+        return {}
+
+    def _maybe_int(raw: Optional[str]) -> Optional[int]:
+        if raw is None:
+            return None
+        try:
+            return int(float(raw))
+        except (TypeError, ValueError):
+            return None
+
+    def _maybe_float(raw: Optional[str]) -> Optional[float]:
+        if raw is None:
+            return None
+        try:
+            return float(raw)
+        except (TypeError, ValueError):
+            return None
+
+    result: dict[str, tuple[Optional[int], Optional[float]]] = {}
+    for tag in ("requests", "requests-1h", "tokens", "tokens-1h"):
+        remaining = _maybe_int(lowered.get(f"x-ratelimit-remaining-{tag}"))
+        reset = _maybe_float(lowered.get(f"x-ratelimit-reset-{tag}"))
+        if remaining is not None or reset is not None:
+            result[tag] = (remaining, reset)
+    return result
+
+
+def _has_exhausted_bucket(
+    buckets: Mapping[str, tuple[Optional[int], Optional[float]]],
+) -> bool:
+    """Return True when any bucket has remaining == 0 AND a meaningful reset window."""
+    for remaining, reset in buckets.values():
+        if remaining is None or remaining > 0:
+            continue
+        if reset is None:
+            continue
+        if reset >= _MIN_RESET_FOR_BREAKER_SECONDS:
+            return True
+    return False
+
+
+def _has_exhausted_bucket_in_object(state: Any) -> bool:
+    """Check a RateLimitState-like object for an exhausted bucket.
+
+    Accepts the dataclass from ``agent.rate_limit_tracker`` (buckets
+    exposed as attributes ``requests_min``, ``requests_hour``,
+    ``tokens_min``, ``tokens_hour``) and falls back gracefully for any
+    object missing those attributes.
+    """
+    for attr in ("requests_min", "requests_hour", "tokens_min", "tokens_hour"):
+        bucket = getattr(state, attr, None)
+        if bucket is None:
+            continue
+        limit = getattr(bucket, "limit", 0) or 0
+        remaining = getattr(bucket, "remaining", 0) or 0
+        # Prefer the adjusted "remaining_seconds_now" property when present;
+        # fall back to raw reset_seconds.
+        reset = getattr(bucket, "remaining_seconds_now", None)
+        if reset is None:
+            reset = getattr(bucket, "reset_seconds", 0.0) or 0.0
+        if limit <= 0:
+            continue
+        if remaining > 0:
+            continue
+        if reset >= _MIN_RESET_FOR_BREAKER_SECONDS:
+            return True
+    return False

agent/onboarding.py

@@ -0,0 +1,144 @@
+"""
+Contextual first-touch onboarding hints.
+
+Instead of blocking first-run questionnaires, show a one-time hint the *first*
+time a user hits a behavior fork — message-while-running, first long-running
+tool, etc.  Each hint is shown once per install (tracked in ``config.yaml`` under
+``onboarding.seen.<flag>``) and then never again.
+
+Keep this module tiny and dependency-free so both the CLI and gateway can import
+it without pulling in heavy modules.
+"""
+
+from __future__ import annotations
+
+import logging
+from pathlib import Path
+from typing import Any, Mapping, Optional
+
+logger = logging.getLogger(__name__)
+
+
+# -------------------------------------------------------------------------
+# Flag names (stable — used as config.yaml keys under onboarding.seen)
+# -------------------------------------------------------------------------
+
+BUSY_INPUT_FLAG = "busy_input_prompt"
+TOOL_PROGRESS_FLAG = "tool_progress_prompt"
+
+
+# -------------------------------------------------------------------------
+# Hint content
+# -------------------------------------------------------------------------
+
+def busy_input_hint_gateway(mode: str) -> str:
+    """Hint shown the first time a user messages while the agent is busy.
+
+    ``mode`` is the effective busy_input_mode that was just applied, so the
+    message matches reality ("I just interrupted…" vs "I just queued…").
+    """
+    if mode == "queue":
+        return (
+            "💡 First-time tip — I queued your message instead of interrupting. "
+            "Send `/busy interrupt` to make new messages stop the current task "
+            "immediately, or `/busy status` to check. This notice won't appear again."
+        )
+    return (
+        "💡 First-time tip — I just interrupted my current task to answer you. "
+        "Send `/busy queue` to queue follow-ups for after the current task instead, "
+        "or `/busy status` to check. This notice won't appear again."
+    )
+
+
+def busy_input_hint_cli(mode: str) -> str:
+    """CLI version of the busy-input hint (plain text, no markdown)."""
+    if mode == "queue":
+        return (
+            "(tip) Your message was queued for the next turn. "
+            "Use /busy interrupt to make Enter stop the current run instead. "
+            "This tip only shows once."
+        )
+    return (
+        "(tip) Your message interrupted the current run. "
+        "Use /busy queue to queue messages for the next turn instead. "
+        "This tip only shows once."
+    )
+
+
+def tool_progress_hint_gateway() -> str:
+    return (
+        "💡 First-time tip — that tool took a while and I'm streaming every step. "
+        "If the progress messages feel noisy, send `/verbose` to cycle modes "
+        "(all → new → off). This notice won't appear again."
+    )
+
+
+def tool_progress_hint_cli() -> str:
+    return (
+        "(tip) That tool ran for a while. Use /verbose to cycle tool-progress "
+        "display modes (all -> new -> off -> verbose). This tip only shows once."
+    )
+
+
+# -------------------------------------------------------------------------
+# State read / write
+# -------------------------------------------------------------------------
+
+def _get_seen_dict(config: Mapping[str, Any]) -> Mapping[str, Any]:
+    onboarding = config.get("onboarding") if isinstance(config, Mapping) else None
+    if not isinstance(onboarding, Mapping):
+        return {}
+    seen = onboarding.get("seen")
+    return seen if isinstance(seen, Mapping) else {}
+
+
+def is_seen(config: Mapping[str, Any], flag: str) -> bool:
+    """Return True if the user has already been shown this first-touch hint."""
+    return bool(_get_seen_dict(config).get(flag))
+
+
+def mark_seen(config_path: Path, flag: str) -> bool:
+    """Persist ``onboarding.seen.<flag> = True`` to ``config_path``.
+
+    Uses the atomic YAML writer so a concurrent process can't observe a
+    partially-written file.  Returns True on success, False on any error
+    (including the config file being absent — onboarding is best-effort).
+    """
+    try:
+        import yaml
+        from utils import atomic_yaml_write
+    except Exception as e:  # pragma: no cover — dependency issue
+        logger.debug("onboarding: failed to import yaml/utils: %s", e)
+        return False
+
+    try:
+        cfg: dict = {}
+        if config_path.exists():
+            with open(config_path, encoding="utf-8") as f:
+                cfg = yaml.safe_load(f) or {}
+        if not isinstance(cfg.get("onboarding"), dict):
+            cfg["onboarding"] = {}
+        seen = cfg["onboarding"].get("seen")
+        if not isinstance(seen, dict):
+            seen = {}
+            cfg["onboarding"]["seen"] = seen
+        if seen.get(flag) is True:
+            return True  # already marked — nothing to do
+        seen[flag] = True
+        atomic_yaml_write(config_path, cfg)
+        return True
+    except Exception as e:
+        logger.debug("onboarding: failed to mark flag %s: %s", flag, e)
+        return False
+
+
+__all__ = [
+    "BUSY_INPUT_FLAG",
+    "TOOL_PROGRESS_FLAG",
+    "busy_input_hint_gateway",
+    "busy_input_hint_cli",
+    "tool_progress_hint_gateway",
+    "tool_progress_hint_cli",
+    "is_seen",
+    "mark_seen",
+]

agent/prompt_builder.py

@@ -176,6 +176,64 @@ SKILLS_GUIDANCE = (
     "Skills that aren't maintained become liabilities."
 )
 
+KANBAN_GUIDANCE = (
+    "# You are a Kanban worker\n"
+    "You were spawned by the Hermes Kanban dispatcher to execute ONE task from "
+    "the shared board at `~/.hermes/kanban.db`. Your task id is in "
+    "`$HERMES_KANBAN_TASK`; your workspace is `$HERMES_KANBAN_WORKSPACE`. "
+    "The `kanban_*` tools in your schema are your primary coordination surface — "
+    "they write directly to the shared SQLite DB and work regardless of terminal "
+    "backend (local/docker/modal/ssh).\n"
+    "\n"
+    "## Lifecycle\n"
+    "\n"
+    "1. **Orient.** Call `kanban_show()` first (no args — it defaults to your "
+    "task). The response includes title, body, parent-task handoffs (summary + "
+    "metadata), any prior attempts on this task if you're a retry, the full "
+    "comment thread, and a pre-formatted `worker_context` you can treat as "
+    "ground truth.\n"
+    "2. **Work inside the workspace.** `cd $HERMES_KANBAN_WORKSPACE` before "
+    "any file operations. The workspace is yours for this run. Don't modify "
+    "files outside it unless the task explicitly asks.\n"
+    "3. **Heartbeat on long operations.** Call `kanban_heartbeat(note=...)` "
+    "every few minutes during long subprocesses (training, encoding, crawling). "
+    "Skip heartbeats for short tasks.\n"
+    "4. **Block on genuine ambiguity.** If you need a human decision you cannot "
+    "infer (missing credentials, UX choice, paywalled source, peer output you "
+    "need first), call `kanban_block(reason=\"...\")` and stop. Don't guess. "
+    "The user will unblock with context and the dispatcher will respawn you.\n"
+    "5. **Complete with structured handoff.** Call `kanban_complete(summary=..., "
+    "metadata=...)`. `summary` is 1–3 human-readable sentences naming concrete "
+    "artifacts. `metadata` is machine-readable facts "
+    "(`{changed_files: [...], tests_run: N, decisions: [...]}`). Downstream "
+    "workers read both via their own `kanban_show`. Never put secrets / "
+    "tokens / raw PII in either field — run rows are durable forever.\n"
+    "6. **If follow-up work appears, create it; don't do it.** Use "
+    "`kanban_create(title=..., assignee=<right-profile>, parents=[your-task-id])` "
+    "to spawn a child task for the appropriate specialist profile instead of "
+    "scope-creeping into the next thing.\n"
+    "\n"
+    "## Orchestrator mode\n"
+    "\n"
+    "If your task is itself a decomposition task (e.g. a planner profile given "
+    "a high-level goal), use `kanban_create` to fan out into child tasks — one "
+    "per specialist, each with an explicit `assignee` and `parents=[...]` to "
+    "express dependencies. Then `kanban_complete` your own task with a summary "
+    "of the decomposition. Do NOT execute the work yourself; your job is "
+    "routing, not implementation.\n"
+    "\n"
+    "## Do NOT\n"
+    "\n"
+    "- Do not shell out to `hermes kanban <verb>` for board operations. Use "
+    "the `kanban_*` tools — they work across all terminal backends.\n"
+    "- Do not complete a task you didn't actually finish. Block it.\n"
+    "- Do not assign follow-up work to yourself. Assign it to the right "
+    "specialist profile.\n"
+    "- Do not call `delegate_task` as a board substitute. `delegate_task` is "
+    "for short reasoning subtasks inside your own run; board tasks are for "
+    "cross-agent handoffs that outlive one API loop."
+)
+
 TOOL_USE_ENFORCEMENT_GUIDANCE = (
     "# Tool-use enforcement\n"
     "You MUST use your tools to take action — do not describe what you would do "

agent/skill_commands.py

@@ -1,154 +1,29 @@
-"""Shared slash command helpers for skills and built-in prompt-style modes.
+"""Shared slash command helpers for skills.
 
 Shared between CLI (cli.py) and gateway (gateway/run.py) so both surfaces
-can invoke skills via /skill-name commands and prompt-only built-ins like
-/plan.
+can invoke skills via /skill-name commands.
 """
 
 import json
 import logging
 import re
-import subprocess
-from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, Optional
 
 from hermes_constants import display_hermes_home
+from agent.skill_preprocessing import (
+    expand_inline_shell as _expand_inline_shell,
+    load_skills_config as _load_skills_config,
+    substitute_template_vars as _substitute_template_vars,
+)
 
 logger = logging.getLogger(__name__)
 
 _skill_commands: Dict[str, Dict[str, Any]] = {}
-_PLAN_SLUG_RE = re.compile(r"[^a-z0-9]+")
 # 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,}")
 
-# Matches ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in SKILL.md.
-# Tokens that don't resolve (e.g. ${HERMES_SESSION_ID} with no session) are
-# left as-is so the user can debug them.
-_SKILL_TEMPLATE_RE = re.compile(r"\$\{(HERMES_SKILL_DIR|HERMES_SESSION_ID)\}")
-
-# Matches inline shell snippets like:  !`date +%Y-%m-%d`
-# Non-greedy, single-line only — no newlines inside the backticks.
-_INLINE_SHELL_RE = re.compile(r"!`([^`\n]+)`")
-
-# Cap inline-shell output so a runaway command can't blow out the context.
-_INLINE_SHELL_MAX_OUTPUT = 4000
-
-
-def _load_skills_config() -> dict:
-    """Load the ``skills`` section of config.yaml (best-effort)."""
-    try:
-        from hermes_cli.config import load_config
-
-        cfg = load_config() or {}
-        skills_cfg = cfg.get("skills")
-        if isinstance(skills_cfg, dict):
-            return skills_cfg
-    except Exception:
-        logger.debug("Could not read skills config", exc_info=True)
-    return {}
-
-
-def _substitute_template_vars(
-    content: str,
-    skill_dir: Path | None,
-    session_id: str | None,
-) -> str:
-    """Replace ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} in skill content.
-
-    Only substitutes tokens for which a concrete value is available —
-    unresolved tokens are left in place so the author can spot them.
-    """
-    if not content:
-        return content
-
-    skill_dir_str = str(skill_dir) if skill_dir else None
-
-    def _replace(match: re.Match) -> str:
-        token = match.group(1)
-        if token == "HERMES_SKILL_DIR" and skill_dir_str:
-            return skill_dir_str
-        if token == "HERMES_SESSION_ID" and session_id:
-            return str(session_id)
-        return match.group(0)
-
-    return _SKILL_TEMPLATE_RE.sub(_replace, content)
-
-
-def _run_inline_shell(command: str, cwd: Path | None, timeout: int) -> str:
-    """Execute a single inline-shell snippet and return its stdout (trimmed).
-
-    Failures return a short ``[inline-shell error: ...]`` marker instead of
-    raising, so one bad snippet can't wreck the whole skill message.
-    """
-    try:
-        completed = subprocess.run(
-            ["bash", "-c", command],
-            cwd=str(cwd) if cwd else None,
-            capture_output=True,
-            text=True,
-            timeout=max(1, int(timeout)),
-            check=False,
-        )
-    except subprocess.TimeoutExpired:
-        return f"[inline-shell timeout after {timeout}s: {command}]"
-    except FileNotFoundError:
-        return f"[inline-shell error: bash not found]"
-    except Exception as exc:
-        return f"[inline-shell error: {exc}]"
-
-    output = (completed.stdout or "").rstrip("\n")
-    if not output and completed.stderr:
-        output = completed.stderr.rstrip("\n")
-    if len(output) > _INLINE_SHELL_MAX_OUTPUT:
-        output = output[:_INLINE_SHELL_MAX_OUTPUT] + "…[truncated]"
-    return output
-
-
-def _expand_inline_shell(
-    content: str,
-    skill_dir: Path | None,
-    timeout: int,
-) -> str:
-    """Replace every !`cmd` snippet in ``content`` with its stdout.
-
-    Runs each snippet with the skill directory as CWD so relative paths in
-    the snippet work the way the author expects.
-    """
-    if "!`" not in content:
-        return content
-
-    def _replace(match: re.Match) -> str:
-        cmd = match.group(1).strip()
-        if not cmd:
-            return ""
-        return _run_inline_shell(cmd, skill_dir, timeout)
-
-    return _INLINE_SHELL_RE.sub(_replace, content)
-
-
-def build_plan_path(
-    user_instruction: str = "",
-    *,
-    now: datetime | None = None,
-) -> Path:
-    """Return the default workspace-relative markdown path for a /plan invocation.
-
-    Relative paths are intentional: file tools are task/backend-aware and resolve
-    them against the active working directory for local, docker, ssh, modal,
-    daytona, and similar terminal backends. That keeps the plan with the active
-    workspace instead of the Hermes host's global home directory.
-    """
-    slug_source = (user_instruction or "").strip().splitlines()[0] if user_instruction else ""
-    slug = _PLAN_SLUG_RE.sub("-", slug_source.lower()).strip("-")
-    if slug:
-        slug = "-".join(part for part in slug.split("-")[:8] if part)[:48].strip("-")
-    slug = slug or "conversation-plan"
-    timestamp = (now or datetime.now()).strftime("%Y-%m-%d_%H%M%S")
-    return Path(".hermes") / "plans" / f"{timestamp}-{slug}.md"
-
-
 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()
@@ -167,7 +42,9 @@ def _load_skill_payload(skill_identifier: str, task_id: str | None = None) -> tu
         else:
             normalized = raw_identifier.lstrip("/")
 
-        loaded_skill = json.loads(skill_view(normalized, task_id=task_id))
+        loaded_skill = json.loads(
+            skill_view(normalized, task_id=task_id, preprocess=False)
+        )
     except Exception:
         return None
 

agent/skill_preprocessing.py

@@ -0,0 +1,131 @@
+"""Shared SKILL.md preprocessing helpers."""
+
+import logging
+import re
+import subprocess
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+# Matches ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in SKILL.md.
+# Tokens that don't resolve (e.g. ${HERMES_SESSION_ID} with no session) are
+# left as-is so the user can debug them.
+_SKILL_TEMPLATE_RE = re.compile(r"\$\{(HERMES_SKILL_DIR|HERMES_SESSION_ID)\}")
+
+# Matches inline shell snippets like:  !`date +%Y-%m-%d`
+# Non-greedy, single-line only -- no newlines inside the backticks.
+_INLINE_SHELL_RE = re.compile(r"!`([^`\n]+)`")
+
+# Cap inline-shell output so a runaway command can't blow out the context.
+_INLINE_SHELL_MAX_OUTPUT = 4000
+
+
+def load_skills_config() -> dict:
+    """Load the ``skills`` section of config.yaml (best-effort)."""
+    try:
+        from hermes_cli.config import load_config
+
+        cfg = load_config() or {}
+        skills_cfg = cfg.get("skills")
+        if isinstance(skills_cfg, dict):
+            return skills_cfg
+    except Exception:
+        logger.debug("Could not read skills config", exc_info=True)
+    return {}
+
+
+def substitute_template_vars(
+    content: str,
+    skill_dir: Path | None,
+    session_id: str | None,
+) -> str:
+    """Replace ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} in skill content.
+
+    Only substitutes tokens for which a concrete value is available --
+    unresolved tokens are left in place so the author can spot them.
+    """
+    if not content:
+        return content
+
+    skill_dir_str = str(skill_dir) if skill_dir else None
+
+    def _replace(match: re.Match) -> str:
+        token = match.group(1)
+        if token == "HERMES_SKILL_DIR" and skill_dir_str:
+            return skill_dir_str
+        if token == "HERMES_SESSION_ID" and session_id:
+            return str(session_id)
+        return match.group(0)
+
+    return _SKILL_TEMPLATE_RE.sub(_replace, content)
+
+
+def run_inline_shell(command: str, cwd: Path | None, timeout: int) -> str:
+    """Execute a single inline-shell snippet and return its stdout (trimmed).
+
+    Failures return a short ``[inline-shell error: ...]`` marker instead of
+    raising, so one bad snippet can't wreck the whole skill message.
+    """
+    try:
+        completed = subprocess.run(
+            ["bash", "-c", command],
+            cwd=str(cwd) if cwd else None,
+            capture_output=True,
+            text=True,
+            timeout=max(1, int(timeout)),
+            check=False,
+        )
+    except subprocess.TimeoutExpired:
+        return f"[inline-shell timeout after {timeout}s: {command}]"
+    except FileNotFoundError:
+        return "[inline-shell error: bash not found]"
+    except Exception as exc:
+        return f"[inline-shell error: {exc}]"
+
+    output = (completed.stdout or "").rstrip("\n")
+    if not output and completed.stderr:
+        output = completed.stderr.rstrip("\n")
+    if len(output) > _INLINE_SHELL_MAX_OUTPUT:
+        output = output[:_INLINE_SHELL_MAX_OUTPUT] + "...[truncated]"
+    return output
+
+
+def expand_inline_shell(
+    content: str,
+    skill_dir: Path | None,
+    timeout: int,
+) -> str:
+    """Replace every !`cmd` snippet in ``content`` with its stdout.
+
+    Runs each snippet with the skill directory as CWD so relative paths in
+    the snippet work the way the author expects.
+    """
+    if "!`" not in content:
+        return content
+
+    def _replace(match: re.Match) -> str:
+        cmd = match.group(1).strip()
+        if not cmd:
+            return ""
+        return run_inline_shell(cmd, skill_dir, timeout)
+
+    return _INLINE_SHELL_RE.sub(_replace, content)
+
+
+def preprocess_skill_content(
+    content: str,
+    skill_dir: Path | None,
+    session_id: str | None = None,
+    skills_cfg: dict | None = None,
+) -> str:
+    """Apply configured SKILL.md template and inline-shell preprocessing."""
+    if not content:
+        return content
+
+    cfg = skills_cfg if isinstance(skills_cfg, dict) else load_skills_config()
+    if cfg.get("template_vars", True):
+        content = substitute_template_vars(content, skill_dir, session_id)
+    if cfg.get("inline_shell", False):
+        timeout = int(cfg.get("inline_shell_timeout", 10) or 10)
+        content = expand_inline_shell(content, skill_dir, timeout)
+    return content

agent/transports/__init__.py

@@ -23,9 +23,14 @@ def get_transport(api_mode: str):
     This allows gradual migration — call sites can check for None
     and fall back to the legacy code path.
     """
-    if not _REGISTRY:
-        _discover_transports()
     cls = _REGISTRY.get(api_mode)
+    if cls is None:
+        # The registry can be partially populated when a specific transport
+        # module was imported directly (for example chat_completions before
+        # codex).  Discover on misses, not only when the registry is empty, so
+        # test/order-dependent imports do not make valid api_modes unavailable.
+        _discover_transports()
+        cls = _REGISTRY.get(api_mode)
     if cls is None:
         return None
     return cls()

agent/transports/chat_completions.py

@@ -31,15 +31,15 @@ class ChatCompletionsTransport(ProviderTransport):
     def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> List[Dict[str, Any]]:
         """Messages are already in OpenAI format — sanitize Codex leaks only.
 
-        Strips Codex Responses API fields (``codex_reasoning_items`` on the
-        message, ``call_id``/``response_item_id`` on tool_calls) that strict
-        chat-completions providers reject with 400/422.
+        Strips Codex Responses API fields (``codex_reasoning_items`` /
+        ``codex_message_items`` on the message, ``call_id``/``response_item_id``
+        on tool_calls) that strict chat-completions providers reject with 400/422.
         """
         needs_sanitize = False
         for msg in messages:
             if not isinstance(msg, dict):
                 continue
-            if "codex_reasoning_items" in msg:
+            if "codex_reasoning_items" in msg or "codex_message_items" in msg:
                 needs_sanitize = True
                 break
             tool_calls = msg.get("tool_calls")
@@ -59,6 +59,7 @@ class ChatCompletionsTransport(ProviderTransport):
             if not isinstance(msg, dict):
                 continue
             msg.pop("codex_reasoning_items", None)
+            msg.pop("codex_message_items", None)
             tool_calls = msg.get("tool_calls")
             if isinstance(tool_calls, list):
                 for tc in tool_calls:

agent/transports/codex.py

@@ -120,6 +120,24 @@ class ResponsesApiTransport(ProviderTransport):
         if request_overrides:
             kwargs.update(request_overrides)
 
+        if is_codex_backend:
+            prompt_cache_key = kwargs.get("prompt_cache_key")
+            cache_scope_id = str(prompt_cache_key or session_id or "").strip()
+            if cache_scope_id:
+                existing_extra_headers = kwargs.get("extra_headers")
+                merged_extra_headers: Dict[str, str] = {}
+                if isinstance(existing_extra_headers, dict):
+                    merged_extra_headers.update(
+                        {
+                            str(key): str(value)
+                            for key, value in existing_extra_headers.items()
+                            if key and value is not None
+                        }
+                    )
+                merged_extra_headers["session_id"] = cache_scope_id
+                merged_extra_headers["x-client-request-id"] = cache_scope_id
+                kwargs["extra_headers"] = merged_extra_headers
+
         max_tokens = params.get("max_tokens")
         if max_tokens is not None and not is_codex_backend:
             kwargs["max_output_tokens"] = max_tokens
@@ -160,6 +178,8 @@ class ResponsesApiTransport(ProviderTransport):
         provider_data = {}
         if msg and hasattr(msg, "codex_reasoning_items") and msg.codex_reasoning_items:
             provider_data["codex_reasoning_items"] = msg.codex_reasoning_items
+        if msg and hasattr(msg, "codex_message_items") and msg.codex_message_items:
+            provider_data["codex_message_items"] = msg.codex_message_items
         if msg and hasattr(msg, "reasoning_details") and msg.reasoning_details:
             provider_data["reasoning_details"] = msg.reasoning_details
 

agent/transports/types.py

@@ -97,7 +97,7 @@ class NormalizedResponse:
     Response-level ``provider_data`` examples:
 
     * Anthropic: ``{"reasoning_details": [...]}``
-    * Codex: ``{"codex_reasoning_items": [...]}``
+    * Codex: ``{"codex_reasoning_items": [...], "codex_message_items": [...]}``
     * Others: ``None``
     """
 
@@ -126,6 +126,11 @@ class NormalizedResponse:
         pd = self.provider_data or {}
         return pd.get("codex_reasoning_items")
 
+    @property
+    def codex_message_items(self):
+        pd = self.provider_data or {}
+        return pd.get("codex_message_items")
+
 
 # ---------------------------------------------------------------------------
 # Factory helpers

batch_runner.py

@@ -951,13 +951,9 @@ class BatchRunner:
                     root_logger.setLevel(original_level)
         
         # Aggregate all batch statistics and update checkpoint
-        all_completed_prompts = list(completed_prompts_set)
         total_reasoning_stats = {"total_assistant_turns": 0, "turns_with_reasoning": 0, "turns_without_reasoning": 0}
-        
+
         for batch_result in results:
-            # Add newly completed prompts
-            all_completed_prompts.extend(batch_result.get("completed_prompts", []))
-            
             # Aggregate tool stats
             for tool_name, stats in batch_result.get("tool_stats", {}).items():
                 if tool_name not in total_tool_stats:
@@ -977,7 +973,7 @@ class BatchRunner:
         
         # Save final checkpoint (best-effort; incremental writes already happened)
         try:
-            checkpoint_data["completed_prompts"] = all_completed_prompts
+            checkpoint_data["completed_prompts"] = sorted(completed_prompts_set)
             self._save_checkpoint(checkpoint_data, lock=checkpoint_lock)
         except Exception as ckpt_err:
             print(f"⚠️  Warning: Failed to save final checkpoint: {ckpt_err}")

cli-config.yaml.example

@@ -326,6 +326,16 @@ compression:
   # To pin a specific model/provider for compression summaries, use the
   # auxiliary section below (auxiliary.compression.provider / model).
 
+# =============================================================================
+# Anthropic prompt caching TTL
+# =============================================================================
+# When prompt caching is active (Claude via OpenRouter or native Anthropic),
+# Anthropic supports two TTL tiers for cached prefixes: "5m" (default) and
+# "1h". Other values are ignored and "5m" is used.
+#
+prompt_caching:
+  cache_ttl: "5m" # use "1h" for long sessions with pauses between turns
+
 # =============================================================================
 # Auxiliary Models (Advanced — Experimental)
 # =============================================================================
@@ -780,9 +790,16 @@ code_execution:
 # Supports single tasks and batch mode (default 3 parallel, configurable).
 delegation:
   max_iterations: 50                          # Max tool-calling turns per child (default: 50)
-  # max_concurrent_children: 3                # Max parallel child agents (default: 3)
-  # max_spawn_depth: 1                        # Tree depth cap (1-3, default: 1 = flat). Raise to 2 or 3 to allow orchestrator children to spawn their own workers.
+  # max_concurrent_children: 3                # Max parallel child agents per batch (default: 3, floor: 1, no ceiling).
+                                              # WARNING: values above 10 multiply API cost linearly.
+  # max_spawn_depth: 1                        # Delegation tree depth cap (range: 1-3, default: 1 = flat).
+                                              # Raise to 2 to allow workers to spawn their own subagents.
+                                              # Requires role="orchestrator" on intermediate agents.
   # orchestrator_enabled: true                # Kill switch for role="orchestrator" children (default: true).
+  # subagent_auto_approve: false              # When a subagent hits a dangerous-command approval prompt, auto-deny (default: false)
+                                              # or auto-approve "once" (true) instead of blocking on stdin.
+                                              # The parent TUI owns stdin, so blocking would deadlock; non-interactive resolution is required.
+                                              # Both choices emit a logger.warning audit line. Flip to true only for cron/batch pipelines.
   # inherit_mcp_toolsets: true                # When explicit child toolsets are narrowed, also keep the parent's MCP toolsets (default: true). Set false for strict intersection.
   # model: "google/gemini-3-flash-preview"    # Override model for subagents (empty = inherit parent)
   # provider: "openrouter"                    # Override provider for subagents (empty = inherit parent)
@@ -807,7 +824,9 @@ delegation:
 # Display
 # =============================================================================
 display:
-  # Use compact banner mode
+  # Use compact banner mode (hides the ASCII-art banner, shows a single line).
+  #   true:  Compact single-line banner
+  #   false: Full ASCII banner with tool/skill summary (default)
   compact: false
 
   # Tool progress display level (CLI and gateway)
@@ -821,12 +840,15 @@ display:
   # Gateway-only natural mid-turn assistant updates.
   # When true, completed assistant status messages are sent as separate chat
   # messages. This is independent of tool_progress and gateway streaming.
+  #   true:  Send mid-turn assistant updates as separate messages (default)
+  #   false: Only send the final response
   interim_assistant_messages: true
 
-  # What Enter does when Hermes is already busy in the CLI.
+  # What Enter does when Hermes is already busy (CLI and gateway platforms).
   #   interrupt: Interrupt the current run and redirect Hermes (default)
   #   queue:     Queue your message for the next turn
-  # Ctrl+C always interrupts regardless of this setting.
+  # Ctrl+C (or /stop in gateway) always interrupts regardless of this setting.
+  # Toggle at runtime with /busy_input_mode <interrupt|queue>.
   busy_input_mode: interrupt
 
   # Background process notifications (gateway/messaging only).
@@ -842,17 +864,22 @@ display:
   # Play terminal bell when agent finishes a response.
   # Useful for long-running tasks — your terminal will ding when the agent is done.
   # Works over SSH. Most terminals can be configured to flash the taskbar or play a sound.
+  #   true:  Ring the terminal bell on each response
+  #   false: Silent (default)
   bell_on_complete: false
 
   # Show model reasoning/thinking before each response.
   # When enabled, a dim box shows the model's thought process above the response.
   # Toggle at runtime with /reasoning show or /reasoning hide.
+  #   true:  Show the reasoning box
+  #   false: Hide reasoning (default)
   show_reasoning: false
 
   # Stream tokens to the terminal as they arrive instead of waiting for the
   # full response. The response box opens on first token and text appears
   # line-by-line. Tool calls are still captured silently.
-  # Stream tokens to the terminal in real-time. Disable to wait for full responses.
+  #   true:  Stream tokens as they arrive (default)
+  #   false: Wait for the full response before rendering
   streaming: true
 
   # ───────────────────────────────────────────────────────────────────────────
@@ -862,10 +889,15 @@ display:
   # response box label, and branding text. Change at runtime with /skin <name>.
   #
   # Built-in skins:
-  #   default  — Classic Hermes gold/kawaii
-  #   ares     — Crimson/bronze war-god theme with spinner wings
-  #   mono     — Clean grayscale monochrome
-  #   slate    — Cool blue developer-focused
+  #   default        — Classic Hermes gold/kawaii
+  #   ares           — Crimson/bronze war-god theme with spinner wings
+  #   mono           — Clean grayscale monochrome
+  #   slate          — Cool blue developer-focused
+  #   daylight       — Bright light-mode theme
+  #   warm-lightmode — Warm paper-tone light-mode theme
+  #   poseidon       — Sea-green/teal Olympian theme
+  #   sisyphus       — Earthy stone-and-moss theme
+  #   charizard      — Fiery orange dragon theme
   #
   # Custom skins: drop a YAML file in ~/.hermes/skins/<name>.yaml
   # Schema (all fields optional, missing values inherit from default):

cli.py

@@ -22,6 +22,7 @@ import re
 import concurrent.futures
 import base64
 import atexit
+import errno
 import tempfile
 import time
 import uuid
@@ -416,6 +417,11 @@ def load_cli_config() -> Dict[str, Any]:
             "base_url": "",    # Direct OpenAI-compatible endpoint for subagents
             "api_key": "",     # API key for delegation.base_url (falls back to OPENAI_API_KEY)
         },
+        "onboarding": {
+            # First-touch hint flags (see agent/onboarding.py).  Each hint is
+            # shown once per install then latched here.
+            "seen": {},
+        },
     }
     
     # Track whether the config file explicitly set terminal config.
@@ -1688,7 +1694,6 @@ def _looks_like_slash_command(text: str) -> bool:
 from agent.skill_commands import (
     scan_skill_commands,
     build_skill_invocation_message,
-    build_plan_path,
     build_preloaded_skills_prompt,
 )
 
@@ -3084,6 +3089,8 @@ class HermesCLI:
             format_runtime_provider_error,
         )
 
+        _primary_exc = None
+        runtime = None
         try:
             runtime = resolve_runtime_provider(
                 requested=self.requested_provider,
@@ -3091,7 +3098,34 @@ class HermesCLI:
                 explicit_base_url=self._explicit_base_url,
             )
         except Exception as exc:
-            message = format_runtime_provider_error(exc)
+            _primary_exc = exc
+
+        # Primary provider auth failed — try fallback providers before giving up.
+        if runtime is None and _primary_exc is not None:
+            from hermes_cli.auth import AuthError
+            if isinstance(_primary_exc, AuthError):
+                _fb_chain = self._fallback_model if isinstance(self._fallback_model, list) else []
+                for _fb in _fb_chain:
+                    _fb_provider = (_fb.get("provider") or "").strip().lower()
+                    _fb_model = (_fb.get("model") or "").strip()
+                    if not _fb_provider or not _fb_model:
+                        continue
+                    try:
+                        runtime = resolve_runtime_provider(requested=_fb_provider)
+                        logger.warning(
+                            "Primary provider auth failed (%s). Falling through to fallback: %s/%s",
+                            _primary_exc, _fb_provider, _fb_model,
+                        )
+                        _cprint(f"⚠️  Primary auth failed — switching to fallback: {_fb_provider} / {_fb_model}")
+                        self.requested_provider = _fb_provider
+                        self.model = _fb_model
+                        _primary_exc = None
+                        break
+                    except Exception:
+                        continue
+
+        if runtime is None:
+            message = format_runtime_provider_error(_primary_exc) if _primary_exc else "Provider resolution failed."
             ChatConsole().print(f"[bold red]{message}[/]")
             return False
 
@@ -3148,7 +3182,14 @@ class HermesCLI:
         # the configured model (e.g. "qwen3.6-plus"), causing 400 errors.
         runtime_model = runtime.get("model")
         if runtime_model and isinstance(runtime_model, str):
-            self.model = runtime_model
+            # Only use runtime model if: model is unset, or model equals provider name
+            should_use_runtime_model = (
+                not self.model or  # No model configured yet
+                self.model == self.provider or  # Model is the provider slug
+                self.model == runtime.get("name")  # Model matches provider display name
+            )
+            if should_use_runtime_model:
+                self.model = runtime_model
 
         # If model is still empty (e.g. user ran `hermes auth add openai-codex`
         # without `hermes model`), fall back to the provider's first catalog
@@ -3254,6 +3295,23 @@ class HermesCLI:
                 _cprint(f"\033[1;31mSession not found: {self.session_id}{_RST}")
                 _cprint(f"{_DIM}Use a session ID from a previous CLI run (hermes sessions list).{_RST}")
                 return False
+            # If the requested session is the (empty) head of a compression
+            # chain, walk to the descendant that actually holds the messages.
+            # See #15000 and SessionDB.resolve_resume_session_id.
+            try:
+                resolved_id = self._session_db.resolve_resume_session_id(self.session_id)
+            except Exception:
+                resolved_id = self.session_id
+            if resolved_id and resolved_id != self.session_id:
+                ChatConsole().print(
+                    f"[{_DIM}]Session {_escape(self.session_id)} was compressed into "
+                    f"{_escape(resolved_id)}; resuming the descendant with your "
+                    f"transcript.[/]"
+                )
+                self.session_id = resolved_id
+                resolved_meta = self._session_db.get_session(self.session_id)
+                if resolved_meta:
+                    session_meta = resolved_meta
             restored = self._session_db.get_messages_as_conversation(self.session_id)
             if restored:
                 restored = [m for m in restored if m.get("role") != "session_meta"]
@@ -3472,6 +3530,22 @@ class HermesCLI:
             )
             return False
 
+        # If the requested session is the (empty) head of a compression chain,
+        # walk to the descendant that actually holds the messages. See #15000.
+        try:
+            resolved_id = self._session_db.resolve_resume_session_id(self.session_id)
+        except Exception:
+            resolved_id = self.session_id
+        if resolved_id and resolved_id != self.session_id:
+            self._console_print(
+                f"[dim]Session {self.session_id} was compressed into "
+                f"{resolved_id}; resuming the descendant with your transcript.[/]"
+            )
+            self.session_id = resolved_id
+            resolved_meta = self._session_db.get_session(self.session_id)
+            if resolved_meta:
+                session_meta = resolved_meta
+
         restored = self._session_db.get_messages_as_conversation(self.session_id)
         if restored:
             restored = [m for m in restored if m.get("role") != "session_meta"]
@@ -4250,7 +4324,7 @@ class HermesCLI:
 
         _cprint(f"\n  {_DIM}Tip: Just type your message to chat with Hermes!{_RST}")
         _cprint(f"  {_DIM}Multi-line: Alt+Enter for a new line{_RST}")
-        _cprint(f"  {_DIM}Draft editor: Ctrl+G{_RST}")
+        _cprint(f"  {_DIM}Draft editor: Ctrl+G (Alt+G in VSCode/Cursor){_RST}")
         if _is_termux_environment():
             _cprint(f"  {_DIM}Attach image: /image {_termux_example_image_path()} or start your prompt with a local image path{_RST}\n")
         else:
@@ -4600,10 +4674,6 @@ class HermesCLI:
     def new_session(self, silent=False):
         """Start a fresh session with a new session ID and cleared agent state."""
         if self.agent and self.conversation_history:
-            try:
-                self.agent.flush_memories(self.conversation_history)
-            except (Exception, KeyboardInterrupt):
-                pass
             # Trigger memory extraction on the old session before session_id rotates.
             self.agent.commit_memory_session(self.conversation_history)
             self._notify_session_boundary("on_session_finalize")
@@ -4686,6 +4756,22 @@ class HermesCLI:
             _cprint("  Use /history or `hermes sessions list` to see available sessions.")
             return
 
+        # If the target is the empty head of a compression chain, redirect to
+        # the descendant that actually holds the transcript. See #15000.
+        try:
+            resolved_id = self._session_db.resolve_resume_session_id(target_id)
+        except Exception:
+            resolved_id = target_id
+        if resolved_id and resolved_id != target_id:
+            _cprint(
+                f"  Session {target_id} was compressed into {resolved_id}; "
+                f"resuming the descendant with your transcript."
+            )
+            target_id = resolved_id
+            resolved_meta = self._session_db.get_session(target_id)
+            if resolved_meta:
+                session_meta = resolved_meta
+
         if target_id == self.session_id:
             _cprint("  Already on that session.")
             return
@@ -5072,27 +5158,29 @@ class HermesCLI:
         _cprint(f"  ✓ Model switched: {result.new_model}")
         _cprint(f"    Provider: {provider_label}")
 
+        # Context: always resolve via the provider-aware chain so Codex OAuth,
+        # Copilot, and Nous-enforced caps win over the raw models.dev entry
+        # (e.g. gpt-5.5 is 1.05M on openai but 272K on Codex OAuth).
         mi = result.model_info
+        try:
+            from hermes_cli.model_switch import resolve_display_context_length
+            ctx = resolve_display_context_length(
+                result.new_model,
+                result.target_provider,
+                base_url=result.base_url or self.base_url or "",
+                api_key=result.api_key or self.api_key or "",
+                model_info=mi,
+            )
+            if ctx:
+                _cprint(f"    Context: {ctx:,} tokens")
+        except Exception:
+            pass
         if mi:
-            if mi.context_window:
-                _cprint(f"    Context: {mi.context_window:,} tokens")
             if mi.max_output:
                 _cprint(f"    Max output: {mi.max_output:,} tokens")
             if mi.has_cost_data():
                 _cprint(f"    Cost: {mi.format_cost()}")
             _cprint(f"    Capabilities: {mi.format_capabilities()}")
-        else:
-            try:
-                from agent.model_metadata import get_model_context_length
-                ctx = get_model_context_length(
-                    result.new_model,
-                    base_url=result.base_url or self.base_url,
-                    api_key=result.api_key or self.api_key,
-                    provider=result.target_provider,
-                )
-                _cprint(f"    Context: {ctx:,} tokens")
-            except Exception:
-                pass
 
         cache_enabled = (
             (base_url_host_matches(result.base_url or "", "openrouter.ai") and "claude" in result.new_model.lower())
@@ -5193,24 +5281,22 @@ class HermesCLI:
         # Parse --provider and --global flags
         model_input, explicit_provider, persist_global = parse_model_flags(raw_args)
 
+        # Load providers for switch_model (picker path needs them below)
         user_provs = None
         custom_provs = None
+        try:
+            from hermes_cli.config import get_compatible_custom_providers, load_config
+            cfg = load_config()
+            user_provs = cfg.get("providers")
+            custom_provs = get_compatible_custom_providers(cfg)
+        except Exception:
+            pass
 
         # No args at all: open prompt_toolkit-native picker modal
         if not model_input and not explicit_provider:
             model_display = self.model or "unknown"
             provider_display = get_label(self.provider) if self.provider else "unknown"
 
-            user_provs = None
-            custom_provs = None
-            try:
-                from hermes_cli.config import get_compatible_custom_providers, load_config
-                cfg = load_config()
-                user_provs = cfg.get("providers")
-                custom_provs = get_compatible_custom_providers(cfg)
-            except Exception:
-                pass
-
             try:
                 providers = list_authenticated_providers(
                     current_provider=self.provider or "",
@@ -5297,29 +5383,26 @@ class HermesCLI:
         _cprint(f"  ✓ Model switched: {result.new_model}")
         _cprint(f"    Provider: {provider_label}")
 
-        # Rich metadata from models.dev
+        # Context: always resolve via the provider-aware chain so Codex OAuth,
+        # Copilot, and Nous-enforced caps win over the raw models.dev entry
+        # (e.g. gpt-5.5 is 1.05M on openai but 272K on Codex OAuth).
         mi = result.model_info
+        from hermes_cli.model_switch import resolve_display_context_length
+        ctx = resolve_display_context_length(
+            result.new_model,
+            result.target_provider,
+            base_url=result.base_url or self.base_url or "",
+            api_key=result.api_key or self.api_key or "",
+            model_info=mi,
+        )
+        if ctx:
+            _cprint(f"    Context: {ctx:,} tokens")
         if mi:
-            if mi.context_window:
-                _cprint(f"    Context: {mi.context_window:,} tokens")
             if mi.max_output:
                 _cprint(f"    Max output: {mi.max_output:,} tokens")
             if mi.has_cost_data():
                 _cprint(f"    Cost: {mi.format_cost()}")
             _cprint(f"    Capabilities: {mi.format_capabilities()}")
-        else:
-            # Fallback to old context length lookup
-            try:
-                from agent.model_metadata import get_model_context_length
-                ctx = get_model_context_length(
-                    result.new_model,
-                    base_url=result.base_url or self.base_url,
-                    api_key=result.api_key or self.api_key,
-                    provider=result.target_provider,
-                )
-                _cprint(f"    Context: {ctx:,} tokens")
-            except Exception:
-                pass
 
         # Cache notice
         cache_enabled = (
@@ -5378,79 +5461,6 @@ class HermesCLI:
         except Exception:
             return False
 
-    def _show_model_and_providers(self):
-        """Show current model + provider and list all authenticated providers.
-
-        Shows current model + provider, then lists all authenticated
-        providers with their available models.
-        """
-        from hermes_cli.models import (
-            curated_models_for_provider, list_available_providers,
-            normalize_provider, _PROVIDER_LABELS,
-            get_pricing_for_provider, format_model_pricing_table,
-        )
-        from hermes_cli.auth import resolve_provider as _resolve_provider
-
-        # Resolve current provider
-        raw_provider = normalize_provider(self.provider)
-        if raw_provider == "auto":
-            try:
-                current = _resolve_provider(
-                    self.requested_provider,
-                    explicit_api_key=self._explicit_api_key,
-                    explicit_base_url=self._explicit_base_url,
-                )
-            except Exception:
-                current = "openrouter"
-        else:
-            current = raw_provider
-        current_label = _PROVIDER_LABELS.get(current, current)
-
-        print(f"\n  Current: {self.model} via {current_label}")
-        print()
-
-        # Show all authenticated providers with their models
-        providers = list_available_providers()
-        authed = [p for p in providers if p["authenticated"]]
-        unauthed = [p for p in providers if not p["authenticated"]]
-
-        if authed:
-            print("  Authenticated providers & models:")
-            for p in authed:
-                is_active = p["id"] == current
-                marker = " ← active" if is_active else ""
-                print(f"    [{p['id']}]{marker}")
-                curated = curated_models_for_provider(p["id"])
-                # Fetch pricing for providers that support it (openrouter, nous)
-                pricing_map = get_pricing_for_provider(p["id"]) if p["id"] in ("openrouter", "nous") else {}
-                if curated and pricing_map:
-                    cur_model = self.model if is_active else ""
-                    for line in format_model_pricing_table(curated, pricing_map, current_model=cur_model):
-                        print(line)
-                elif curated:
-                    for mid, desc in curated:
-                        current_marker = " ← current" if (is_active and mid == self.model) else ""
-                        print(f"      {mid}{current_marker}")
-                elif p["id"] == "custom":
-                    from hermes_cli.models import _get_custom_base_url
-                    custom_url = _get_custom_base_url()
-                    if custom_url:
-                        print(f"      endpoint: {custom_url}")
-                    if is_active:
-                        print(f"      model: {self.model} ← current")
-                    print("      (use hermes model to change)")
-                else:
-                    print("      (use hermes model to change)")
-                print()
-
-        if unauthed:
-            names = ", ".join(p["label"] for p in unauthed)
-            print(f"  Not configured: {names}")
-            print("  Run: hermes setup")
-            print()
-
-        print("  To change model or provider, use: hermes model")
-
     def _output_console(self):
         """Use prompt_toolkit-safe Rich rendering once the TUI is live."""
         if getattr(self, "_app", None):
@@ -5808,7 +5818,28 @@ class HermesCLI:
 
         print(f"(._.) Unknown cron command: {subcommand}")
         print("  Available: list, add, edit, pause, resume, run, remove")
-    
+
+    def _handle_kanban_command(self, cmd: str):
+        """Handle the /kanban command — delegate to the shared kanban CLI.
+
+        The string form passed here is the user's full ``/kanban ...``
+        including the leading slash; we strip it and hand the remainder
+        to ``kanban.run_slash`` which returns a single formatted string.
+        """
+        from hermes_cli.kanban import run_slash
+
+        rest = cmd.strip()
+        if rest.startswith("/"):
+            rest = rest.lstrip("/")
+        if rest.startswith("kanban"):
+            rest = rest[len("kanban"):].lstrip()
+        try:
+            output = run_slash(rest)
+        except Exception as exc:  # pragma: no cover - defensive
+            output = f"(._.) kanban error: {exc}"
+        if output:
+            print(output)
+
     def _handle_skills_command(self, cmd: str):
         """Handle /skills slash command — delegates to hermes_cli.skills_hub."""
         from hermes_cli.skills_hub import handle_skills_slash
@@ -6026,16 +6057,12 @@ class HermesCLI:
             self._handle_resume_command(cmd_original)
         elif canonical == "model":
             self._handle_model_switch(cmd_original)
-        elif canonical == "provider":
-            self._show_model_and_providers()
         elif canonical == "gquota":
             self._handle_gquota_command(cmd_original)
 
         elif canonical == "personality":
             # Use original case (handler lowercases the personality name itself)
             self._handle_personality_command(cmd_original)
-        elif canonical == "plan":
-            self._handle_plan_command(cmd_original)
         elif canonical == "retry":
             retry_msg = self.retry_last()
             if retry_msg and hasattr(self, '_pending_input'):
@@ -6049,6 +6076,8 @@ class HermesCLI:
             self.save_conversation()
         elif canonical == "cron":
             self._handle_cron_command(cmd_original)
+        elif canonical == "kanban":
+            self._handle_kanban_command(cmd_original)
         elif canonical == "skills":
             with self._busy_command(self._slow_command_status(cmd_original)):
                 self._handle_skills_command(cmd_original)
@@ -6123,8 +6152,6 @@ class HermesCLI:
             self._handle_agents_command()
         elif canonical == "background":
             self._handle_background_command(cmd_original)
-        elif canonical == "btw":
-            self._handle_btw_command(cmd_original)
         elif canonical == "queue":
             # Extract prompt after "/queue " or "/q "
             parts = cmd_original.split(None, 1)
@@ -6165,6 +6192,8 @@ class HermesCLI:
             self._handle_skin_command(cmd_original)
         elif canonical == "voice":
             self._handle_voice_command(cmd_original)
+        elif canonical == "busy":
+            self._handle_busy_command(cmd_original)
         else:
             # Check for user-defined quick commands (bypass agent loop, no LLM call)
             base_cmd = cmd_lower.split()[0]
@@ -6270,32 +6299,6 @@ class HermesCLI:
         
         return True
     
-    def _handle_plan_command(self, cmd: str):
-        """Handle /plan [request] — load the bundled plan skill."""
-        parts = cmd.strip().split(maxsplit=1)
-        user_instruction = parts[1].strip() if len(parts) > 1 else ""
-
-        plan_path = build_plan_path(user_instruction)
-        msg = build_skill_invocation_message(
-            "/plan",
-            user_instruction,
-            task_id=self.session_id,
-            runtime_note=(
-                "Save the markdown plan with write_file to this exact relative path "
-                f"inside the active workspace/backend cwd: {plan_path}"
-            ),
-        )
-
-        if not msg:
-            ChatConsole().print("[bold red]Failed to load the bundled /plan skill[/]")
-            return
-
-        _cprint(f"  📝 Plan mode queued via skill. Markdown plan target: {plan_path}")
-        if hasattr(self, '_pending_input'):
-            self._pending_input.put(msg)
-        else:
-            ChatConsole().print("[bold red]Plan mode unavailable: input queue not initialized[/]")
-    
     def _handle_background_command(self, cmd: str):
         """Handle /background <prompt> — run a prompt in a separate background session.
 
@@ -6435,122 +6438,6 @@ class HermesCLI:
         self._background_tasks[task_id] = thread
         thread.start()
 
-    def _handle_btw_command(self, cmd: str):
-        """Handle /btw <question> — ephemeral side question using session context.
-
-        Snapshots the current conversation history, spawns a no-tools agent in
-        a background thread, and prints the answer without persisting anything
-        to the main session.
-        """
-        parts = cmd.strip().split(maxsplit=1)
-        if len(parts) < 2 or not parts[1].strip():
-            _cprint("  Usage: /btw <question>")
-            _cprint("  Example: /btw what module owns session title sanitization?")
-            _cprint("  Answers using session context. No tools, not persisted.")
-            return
-
-        question = parts[1].strip()
-        task_id = f"btw_{datetime.now().strftime('%H%M%S')}_{uuid.uuid4().hex[:6]}"
-
-        if not self._ensure_runtime_credentials():
-            _cprint("  (>_<) Cannot start /btw: no valid credentials.")
-            return
-
-        turn_route = self._resolve_turn_agent_config(question)
-        history_snapshot = list(self.conversation_history)
-
-        preview = question[:60] + ("..." if len(question) > 60 else "")
-        _cprint(f'  💬 /btw: "{preview}"')
-
-        def run_btw():
-            try:
-                btw_agent = AIAgent(
-                    model=turn_route["model"],
-                    api_key=turn_route["runtime"].get("api_key"),
-                    base_url=turn_route["runtime"].get("base_url"),
-                    provider=turn_route["runtime"].get("provider"),
-                    api_mode=turn_route["runtime"].get("api_mode"),
-                    acp_command=turn_route["runtime"].get("command"),
-                    acp_args=turn_route["runtime"].get("args"),
-                    max_iterations=8,
-                    enabled_toolsets=[],
-                    quiet_mode=True,
-                    verbose_logging=False,
-                    session_id=task_id,
-                    platform="cli",
-                    reasoning_config=self.reasoning_config,
-                    service_tier=self.service_tier,
-                    request_overrides=turn_route.get("request_overrides"),
-                    providers_allowed=self._providers_only,
-                    providers_ignored=self._providers_ignore,
-                    providers_order=self._providers_order,
-                    provider_sort=self._provider_sort,
-                    provider_require_parameters=self._provider_require_params,
-                    provider_data_collection=self._provider_data_collection,
-                    fallback_model=self._fallback_model,
-                    session_db=None,
-                    skip_memory=True,
-                    skip_context_files=True,
-                    persist_session=False,
-                )
-
-                btw_prompt = (
-                    "[Ephemeral /btw side question. Answer using the conversation "
-                    "context. No tools available. Be direct and concise.]\n\n"
-                    + question
-                )
-                result = btw_agent.run_conversation(
-                    user_message=btw_prompt,
-                    conversation_history=history_snapshot,
-                    task_id=task_id,
-                )
-
-                response = (result.get("final_response") or "") if result else ""
-                if not response and result and result.get("error"):
-                    response = f"Error: {result['error']}"
-
-                # TUI refresh before printing
-                if self._app:
-                    self._app.invalidate()
-                    time.sleep(0.05)
-                print()
-
-                if response:
-                    try:
-                        from hermes_cli.skin_engine import get_active_skin
-                        _skin = get_active_skin()
-                        _resp_color = _skin.get_color("response_border", "#4F6D4A")
-                    except Exception:
-                        _resp_color = "#4F6D4A"
-
-                    ChatConsole().print(Panel(
-                        _render_final_assistant_content(response, mode=self.final_response_markdown),
-                        title=f"[{_resp_color} bold]⚕ /btw[/]",
-                        title_align="left",
-                        border_style=_resp_color,
-                        box=rich_box.HORIZONTALS,
-                        padding=(1, 4),
-                    ))
-                else:
-                    _cprint("  💬 /btw: (no response)")
-
-                if self.bell_on_complete:
-                    sys.stdout.write("\a")
-                    sys.stdout.flush()
-
-            except Exception as e:
-                if self._app:
-                    self._app.invalidate()
-                    time.sleep(0.05)
-                print()
-                _cprint(f"  ❌ /btw failed: {e}")
-            finally:
-                if self._app:
-                    self._invalidate(min_interval=0)
-
-        thread = threading.Thread(target=run_btw, daemon=True, name=f"btw-{task_id}")
-        thread.start()
-
     @staticmethod
     def _try_launch_chrome_debug(port: int, system: str) -> bool:
         """Try to launch Chrome/Chromium with remote debugging enabled.
@@ -6685,6 +6572,13 @@ class HermesCLI:
                 print(f"   ⚠ Port {_port} is not reachable at {cdp_url}")
 
             os.environ["BROWSER_CDP_URL"] = cdp_url
+            # Eagerly start the CDP supervisor so pending_dialogs + frame_tree
+            # show up in the next browser_snapshot.  No-op if already started.
+            try:
+                from tools.browser_tool import _ensure_cdp_supervisor  # type: ignore[import-not-found]
+                _ensure_cdp_supervisor("default")
+            except Exception:
+                pass
             print()
             print("🌐 Browser connected to live Chrome via CDP")
             print(f"   Endpoint: {cdp_url}")
@@ -6706,7 +6600,8 @@ class HermesCLI:
             if current:
                 os.environ.pop("BROWSER_CDP_URL", None)
                 try:
-                    from tools.browser_tool import cleanup_all_browsers
+                    from tools.browser_tool import cleanup_all_browsers, _stop_cdp_supervisor
+                    _stop_cdp_supervisor("default")
                     cleanup_all_browsers()
                 except Exception:
                     pass
@@ -6919,6 +6814,36 @@ class HermesCLI:
         else:
             _cprint(f"  {_ACCENT}✓ Reasoning effort set to '{arg}' (session only){_RST}")
 
+    def _handle_busy_command(self, cmd: str):
+        """Handle /busy — control what Enter does while Hermes is working.
+
+        Usage:
+            /busy               Show current busy input mode
+            /busy status        Show current busy input mode
+            /busy queue         Queue input for the next turn instead of interrupting
+            /busy interrupt     Interrupt the current run on Enter (default)
+        """
+        parts = cmd.strip().split(maxsplit=1)
+        if len(parts) < 2 or parts[1].strip().lower() == "status":
+            _cprint(f"  {_ACCENT}Busy input mode: {self.busy_input_mode}{_RST}")
+            _cprint(f"  {_DIM}Enter while busy: {'queues for next turn' if self.busy_input_mode == 'queue' else 'interrupts current run'}{_RST}")
+            _cprint(f"  {_DIM}Usage: /busy [queue|interrupt|status]{_RST}")
+            return
+
+        arg = parts[1].strip().lower()
+        if arg not in {"queue", "interrupt"}:
+            _cprint(f"  {_DIM}(._.) Unknown argument: {arg}{_RST}")
+            _cprint(f"  {_DIM}Usage: /busy [queue|interrupt|status]{_RST}")
+            return
+
+        self.busy_input_mode = arg
+        if save_config_value("display.busy_input_mode", arg):
+            behavior = "Enter will queue follow-up input while Hermes is busy." if arg == "queue" else "Enter will interrupt the current run while Hermes is busy."
+            _cprint(f"  {_ACCENT}✓ Busy input mode set to '{arg}' (saved to config){_RST}")
+            _cprint(f"  {_DIM}{behavior}{_RST}")
+        else:
+            _cprint(f"  {_ACCENT}✓ Busy input mode set to '{arg}' (session only){_RST}")
+
     def _handle_fast_command(self, cmd: str):
         """Handle /fast — toggle fast mode (OpenAI Priority Processing / Anthropic Fast Mode)."""
         if not self._fast_command_available():
@@ -6997,51 +6922,52 @@ class HermesCLI:
                 focus_topic = parts[1].strip()
 
         original_count = len(self.conversation_history)
-        try:
-            from agent.model_metadata import estimate_messages_tokens_rough
-            from agent.manual_compression_feedback import summarize_manual_compression
-            original_history = list(self.conversation_history)
-            approx_tokens = estimate_messages_tokens_rough(original_history)
-            if focus_topic:
-                print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens), "
-                      f"focus: \"{focus_topic}\"...")
-            else:
-                print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens)...")
+        with self._busy_command("Compressing context..."):
+            try:
+                from agent.model_metadata import estimate_messages_tokens_rough
+                from agent.manual_compression_feedback import summarize_manual_compression
+                original_history = list(self.conversation_history)
+                approx_tokens = estimate_messages_tokens_rough(original_history)
+                if focus_topic:
+                    print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens), "
+                          f"focus: \"{focus_topic}\"...")
+                else:
+                    print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens)...")
 
-            compressed, _ = self.agent._compress_context(
-                original_history,
-                self.agent._cached_system_prompt or "",
-                approx_tokens=approx_tokens,
-                focus_topic=focus_topic or None,
-            )
-            self.conversation_history = compressed
-            # _compress_context ends the old session and creates a new child
-            # session on the agent (run_agent.py::_compress_context). Sync the
-            # CLI's session_id so /status, /resume, exit summary, and title
-            # generation all point at the live continuation session, not the
-            # ended parent. Without this, subsequent end_session() calls target
-            # the already-closed parent and the child is orphaned.
-            if (
-                getattr(self.agent, "session_id", None)
-                and self.agent.session_id != self.session_id
-            ):
-                self.session_id = self.agent.session_id
-                self._pending_title = None
-            new_tokens = estimate_messages_tokens_rough(self.conversation_history)
-            summary = summarize_manual_compression(
-                original_history,
-                self.conversation_history,
-                approx_tokens,
-                new_tokens,
-            )
-            icon = "🗜️" if summary["noop"] else "✅"
-            print(f"  {icon} {summary['headline']}")
-            print(f"     {summary['token_line']}")
-            if summary["note"]:
-                print(f"     {summary['note']}")
+                compressed, _ = self.agent._compress_context(
+                    original_history,
+                    self.agent._cached_system_prompt or "",
+                    approx_tokens=approx_tokens,
+                    focus_topic=focus_topic or None,
+                )
+                self.conversation_history = compressed
+                # _compress_context ends the old session and creates a new child
+                # session on the agent (run_agent.py::_compress_context). Sync the
+                # CLI's session_id so /status, /resume, exit summary, and title
+                # generation all point at the live continuation session, not the
+                # ended parent. Without this, subsequent end_session() calls target
+                # the already-closed parent and the child is orphaned.
+                if (
+                    getattr(self.agent, "session_id", None)
+                    and self.agent.session_id != self.session_id
+                ):
+                    self.session_id = self.agent.session_id
+                    self._pending_title = None
+                new_tokens = estimate_messages_tokens_rough(self.conversation_history)
+                summary = summarize_manual_compression(
+                    original_history,
+                    self.conversation_history,
+                    approx_tokens,
+                    new_tokens,
+                )
+                icon = "🗜️" if summary["noop"] else "✅"
+                print(f"  {icon} {summary['headline']}")
+                print(f"     {summary['token_line']}")
+                if summary["note"]:
+                    print(f"     {summary['note']}")
 
-        except Exception as e:
-            print(f"  ❌ Compression failed: {e}")
+            except Exception as e:
+                print(f"  ❌ Compression failed: {e}")
 
     def _handle_debug_command(self):
         """Handle /debug — upload debug report + logs and print paste URLs."""
@@ -7396,6 +7322,31 @@ class HermesCLI:
                     _cprint(f"  {line}")
                 except Exception:
                     pass
+                # First-touch onboarding: on the first tool in this process
+                # that takes longer than the threshold while we're in the
+                # noisiest progress mode, print a one-time hint about
+                # /verbose.  Latched on self so it fires at most once per
+                # process; persisted to config.yaml so it never fires again
+                # across processes either.
+                try:
+                    if (
+                        not getattr(self, "_long_tool_hint_fired", False)
+                        and self.tool_progress_mode == "all"
+                        and duration >= 30.0
+                    ):
+                        from agent.onboarding import (
+                            TOOL_PROGRESS_FLAG,
+                            is_seen,
+                            mark_seen,
+                            tool_progress_hint_cli,
+                        )
+                        if not is_seen(CLI_CONFIG, TOOL_PROGRESS_FLAG):
+                            self._long_tool_hint_fired = True
+                            _cprint(f"  {_DIM}{tool_progress_hint_cli()}{_RST}")
+                            mark_seen(_hermes_home / "config.yaml", TOOL_PROGRESS_FLAG)
+                            CLI_CONFIG.setdefault("onboarding", {}).setdefault("seen", {})[TOOL_PROGRESS_FLAG] = True
+                except Exception:
+                    pass
             self._invalidate()
             return
         if event_type != "tool.started":
@@ -9279,6 +9230,24 @@ class HermesCLI:
                                          f"agent_running={self._agent_running}\n")
                         except Exception:
                             pass
+                    # First-touch onboarding: on the very first busy-while-running
+                    # event for this install, print a one-line tip explaining the
+                    # /busy knob.  Flag persists to config.yaml and never fires
+                    # again.  Guarded for exceptions so onboarding can't break
+                    # the input loop.
+                    try:
+                        from agent.onboarding import (
+                            BUSY_INPUT_FLAG,
+                            busy_input_hint_cli,
+                            is_seen,
+                            mark_seen,
+                        )
+                        if not is_seen(CLI_CONFIG, BUSY_INPUT_FLAG):
+                            _cprint(f"  {_DIM}{busy_input_hint_cli(self.busy_input_mode)}{_RST}")
+                            mark_seen(_hermes_home / "config.yaml", BUSY_INPUT_FLAG)
+                            CLI_CONFIG.setdefault("onboarding", {}).setdefault("seen", {})[BUSY_INPUT_FLAG] = True
+                    except Exception:
+                        pass
                 else:
                     self._pending_input.put(payload)
                 event.app.current_buffer.reset(append_to_history=True)
@@ -9293,14 +9262,18 @@ class HermesCLI:
             """Ctrl+Enter (c-j) inserts a newline. Most terminals send c-j for Ctrl+Enter."""
             event.current_buffer.insert_text('\n')
 
-        @kb.add(
-            'c-g',
-            filter=Condition(
-                lambda: not self._clarify_state and not self._approval_state and not self._sudo_state and not self._secret_state
-            ),
+        # VSCode/Cursor bind Ctrl+G to "Find Next" at the editor level, so
+        # the keystroke never reaches the embedded terminal. Alt+G is unbound
+        # in those IDEs and arrives here as ('escape', 'g') — register it as
+        # a fallback so the editor handoff works inside Cursor/VSCode too.
+        _editor_filter = Condition(
+            lambda: not self._clarify_state and not self._approval_state and not self._sudo_state and not self._secret_state
         )
+
+        @kb.add('c-g', filter=_editor_filter)
+        @kb.add('escape', 'g', filter=_editor_filter)
         def handle_open_in_editor(event):
-            """Ctrl+G opens the current draft in an external editor."""
+            """Ctrl+G (or Alt+G in VSCode/Cursor) opens the current draft in an external editor."""
             cli_ref._open_external_editor(event.current_buffer)
 
         @kb.add('tab', eager=True)
@@ -9543,9 +9516,20 @@ class HermesCLI:
         
         @kb.add('c-d')
         def handle_ctrl_d(event):
-            """Handle Ctrl+D - exit."""
-            self._should_exit = True
-            event.app.exit()
+            """Ctrl+D: delete char under cursor (standard readline behaviour).
+            Only exit when the input is empty — same as bash/zsh. Pending
+            attached images count as input and block the EOF-exit so the
+            user doesn't lose them silently.
+            """
+            buf = event.app.current_buffer
+            if buf.text:
+                buf.delete()
+            elif self._attached_images:
+                # Empty text but pending attachments — no-op, don't exit.
+                return
+            else:
+                self._should_exit = True
+                event.app.exit()
 
         _modal_prompt_active = Condition(
             lambda: bool(self._secret_state or self._sudo_state)
@@ -9753,6 +9737,11 @@ class HermesCLI:
                 completer=_completer,
             ),
         )
+        # Keep prompt_toolkit on its simple tempfile path. Setting
+        # buffer.tempfile = "prompt.md" triggers its complex-tempfile branch,
+        # which tries to mkdir() the mkdtemp() directory again and raises
+        # EEXIST. The suffix keeps markdown highlighting without that bug.
+        input_area.buffer.tempfile_suffix = '.md'
 
         # Dynamic height: accounts for both explicit newlines AND visual
         # wrapping of long lines so the input area always fits its content.
@@ -10705,6 +10694,8 @@ class HermesCLI:
                 return  # silently suppress
             if isinstance(exc, KeyError) and "is not registered" in str(exc):
                 return  # suppress selector registration failures (#6393)
+            if isinstance(exc, OSError) and getattr(exc, "errno", None) == errno.EIO:
+                return  # suppress I/O errors from broken stdout on interrupt (#13710)
             # Fall back to default handler for everything else
             loop.default_exception_handler(context)
 
@@ -10737,9 +10728,11 @@ class HermesCLI:
         except (EOFError, KeyboardInterrupt, BrokenPipeError):
             pass
         except (KeyError, OSError) as _stdin_err:
-            # Catch selector registration failures from broken stdin (#6393).
-            # This is the fallback for cases that slip past the fstat() guard.
-            if "is not registered" in str(_stdin_err) or "Bad file descriptor" in str(_stdin_err):
+            # Catch selector registration failures from broken stdin (#6393)
+            # and I/O errors from broken stdout during interrupt (#13710).
+            if isinstance(_stdin_err, OSError) and getattr(_stdin_err, "errno", None) == errno.EIO:
+                pass  # suppress broken-stdout I/O errors on interrupt (#13710)
+            elif "is not registered" in str(_stdin_err) or "Bad file descriptor" in str(_stdin_err):
                 print(
                     f"\nError: stdin is not usable ({_stdin_err}).\n"
                     "This can happen with certain Python installations (e.g. uv-managed cPython on macOS).\n"
@@ -10758,12 +10751,6 @@ class HermesCLI:
                     self.agent.interrupt()
                 except Exception:
                     pass
-            # Flush memories before exit (only for substantial conversations)
-            if self.agent and self.conversation_history:
-                try:
-                    self.agent.flush_memories(self.conversation_history)
-                except (Exception, KeyboardInterrupt):
-                    pass
             # Shut down voice recorder (release persistent audio stream)
             if hasattr(self, '_voice_recorder') and self._voice_recorder:
                 try:

cron/jobs.py

@@ -16,7 +16,7 @@ import uuid
 from datetime import datetime, timedelta
 from pathlib import Path
 from hermes_constants import get_hermes_home
-from typing import Optional, Dict, List, Any
+from typing import Optional, Dict, List, Any, Union
 
 logger = logging.getLogger(__name__)
 
@@ -371,6 +371,39 @@ def save_jobs(jobs: List[Dict[str, Any]]):
         raise
 
 
+def _normalize_workdir(workdir: Optional[str]) -> Optional[str]:
+    """Normalize and validate a cron job workdir.
+
+    Rules:
+      - Empty / None → None (feature off, preserves old behaviour).
+      - ``~`` is expanded.  Relative paths are rejected — cron jobs run detached
+        from any shell cwd, so relative paths have no stable meaning.
+      - The path must exist and be a directory at create/update time.  We do
+        NOT re-check at run time (a user might briefly unmount the dir; the
+        scheduler will just fall back to old behaviour with a logged warning).
+
+    Returns the absolute path string, or None when disabled.
+    Raises ValueError on invalid input.
+    """
+    if workdir is None:
+        return None
+    raw = str(workdir).strip()
+    if not raw:
+        return None
+    expanded = Path(raw).expanduser()
+    if not expanded.is_absolute():
+        raise ValueError(
+            f"Cron workdir must be an absolute path (got {raw!r}). "
+            f"Cron jobs run detached from any shell cwd, so relative paths are ambiguous."
+        )
+    resolved = expanded.resolve()
+    if not resolved.exists():
+        raise ValueError(f"Cron workdir does not exist: {resolved}")
+    if not resolved.is_dir():
+        raise ValueError(f"Cron workdir is not a directory: {resolved}")
+    return str(resolved)
+
+
 def create_job(
     prompt: str,
     schedule: str,
@@ -384,7 +417,9 @@ def create_job(
     provider: Optional[str] = None,
     base_url: Optional[str] = None,
     script: Optional[str] = None,
+    context_from: Optional[Union[str, List[str]]] = None,
     enabled_toolsets: Optional[List[str]] = None,
+    workdir: Optional[str] = None,
 ) -> Dict[str, Any]:
     """
     Create a new cron job.
@@ -404,9 +439,18 @@ def create_job(
         script: Optional path to a Python script whose stdout is injected into the
                 prompt each run.  The script runs before the agent turn, and its output
                 is prepended as context.  Useful for data collection / change detection.
+        context_from: Optional job ID (or list of job IDs) whose most recent output
+                      is injected into the prompt as context before each run.
+                      Useful for chaining cron jobs: job A finds data, job B processes it.
         enabled_toolsets: Optional list of toolset names to restrict the agent to.
                           When set, only tools from these toolsets are loaded, reducing
                           token overhead. When omitted, all default tools are loaded.
+        workdir: Optional absolute path.  When set, the job runs as if launched
+                from that directory: AGENTS.md / CLAUDE.md / .cursorrules from
+                that directory are injected into the system prompt, and the
+                terminal/file/code_exec tools use it as their working directory
+                (via TERMINAL_CWD).  When unset, the old behaviour is preserved
+                (no context files injected, tools use the scheduler's cwd).
 
     Returns:
         The created job dict
@@ -439,6 +483,15 @@ def create_job(
     normalized_script = normalized_script or None
     normalized_toolsets = [str(t).strip() for t in enabled_toolsets if str(t).strip()] if enabled_toolsets else None
     normalized_toolsets = normalized_toolsets or None
+    normalized_workdir = _normalize_workdir(workdir)
+
+    # Normalize context_from: accept str or list of str, store as list or None
+    if isinstance(context_from, str):
+        context_from = [context_from.strip()] if context_from.strip() else None
+    elif isinstance(context_from, list):
+        context_from = [str(j).strip() for j in context_from if str(j).strip()] or None
+    else:
+        context_from = None
 
     label_source = (prompt or (normalized_skills[0] if normalized_skills else None)) or "cron job"
     job = {
@@ -451,6 +504,7 @@ def create_job(
         "provider": normalized_provider,
         "base_url": normalized_base_url,
         "script": normalized_script,
+        "context_from": context_from,
         "schedule": parsed_schedule,
         "schedule_display": parsed_schedule.get("display", schedule),
         "repeat": {
@@ -471,6 +525,7 @@ def create_job(
         "deliver": deliver,
         "origin": origin,  # Tracks where job was created for "origin" delivery
         "enabled_toolsets": normalized_toolsets,
+        "workdir": normalized_workdir,
     }
 
     jobs = load_jobs()
@@ -504,6 +559,15 @@ def update_job(job_id: str, updates: Dict[str, Any]) -> Optional[Dict[str, Any]]
         if job["id"] != job_id:
             continue
 
+        # Validate / normalize workdir if present in updates.  Empty string or
+        # None both mean "clear the field" (restore old behaviour).
+        if "workdir" in updates:
+            _wd = updates["workdir"]
+            if _wd in (None, "", False):
+                updates["workdir"] = None
+            else:
+                updates["workdir"] = _normalize_workdir(_wd)
+
         updated = _apply_skill_fields({**job, **updates})
         schedule_changed = "schedule" in updates
 

cron/scheduler.py

@@ -671,6 +671,47 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
                 f"{prompt}"
             )
 
+    # Inject output from referenced cron jobs as context.
+    context_from = job.get("context_from")
+    if context_from:
+        from cron.jobs import OUTPUT_DIR
+        if isinstance(context_from, str):
+            context_from = [context_from]
+        for source_job_id in context_from:
+            # Guard against path traversal — valid job IDs are 12-char hex strings
+            if not source_job_id or not all(c in "0123456789abcdef" for c in source_job_id):
+                logger.warning("context_from: skipping invalid job_id %r", source_job_id)
+                continue
+            try:
+                job_output_dir = OUTPUT_DIR / source_job_id
+                if not job_output_dir.exists():
+                    continue  # silent skip — no output yet
+                output_files = sorted(
+                    job_output_dir.glob("*.md"),
+                    key=lambda f: f.stat().st_mtime,
+                    reverse=True,
+                )
+                if not output_files:
+                    continue  # silent skip — no output yet
+                latest_output = output_files[0].read_text(encoding="utf-8").strip()
+                # Truncate to 8K characters to avoid prompt bloat
+                _MAX_CONTEXT_CHARS = 8000
+                if len(latest_output) > _MAX_CONTEXT_CHARS:
+                    latest_output = latest_output[:_MAX_CONTEXT_CHARS] + "\n\n[... output truncated ...]"
+                if latest_output:
+                    prompt = (
+                        f"## Output from job '{source_job_id}'\n"
+                        "The following is the most recent output from a preceding "
+                        "cron job. Use it as context for your analysis.\n\n"
+                        f"```\n{latest_output}\n```\n\n"
+                        f"{prompt}"
+                    )
+                else:
+                    continue  # silent skip — empty output
+            except (OSError, PermissionError) as e:
+                logger.warning("context_from: failed to read output for job %r: %s", source_job_id, e)
+                # silent skip — do not pollute the prompt with error messages
+
     # Always prepend cron execution guidance so the agent knows how
     # delivery works and can suppress delivery when appropriate.
     cron_hint = (
@@ -795,6 +836,30 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         chat_name=origin.get("chat_name", "") if origin else "",
     )
 
+    # Per-job working directory.  When set (and validated at create/update
+    # time), we point TERMINAL_CWD at it so:
+    #   - build_context_files_prompt() picks up AGENTS.md / CLAUDE.md /
+    #     .cursorrules from the job's project dir, AND
+    #   - the terminal, file, and code-exec tools run commands from there.
+    #
+    # tick() serializes workdir-jobs outside the parallel pool, so mutating
+    # os.environ["TERMINAL_CWD"] here is safe for those jobs.  For workdir-less
+    # jobs we leave TERMINAL_CWD untouched — preserves the original behaviour
+    # (skip_context_files=True, tools use whatever cwd the scheduler has).
+    _job_workdir = (job.get("workdir") or "").strip() or None
+    if _job_workdir and not Path(_job_workdir).is_dir():
+        # Directory was removed between create-time validation and now.  Log
+        # and drop back to old behaviour rather than crashing the job.
+        logger.warning(
+            "Job '%s': configured workdir %r no longer exists — running without it",
+            job_id, _job_workdir,
+        )
+        _job_workdir = None
+    _prior_terminal_cwd = os.environ.get("TERMINAL_CWD", "_UNSET_")
+    if _job_workdir:
+        os.environ["TERMINAL_CWD"] = _job_workdir
+        logger.info("Job '%s': using workdir %s", job_id, _job_workdir)
+
     try:
         # Re-read .env and config.yaml fresh every run so provider/key
         # changes take effect without a gateway restart.
@@ -871,6 +936,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             resolve_runtime_provider,
             format_runtime_provider_error,
         )
+        from hermes_cli.auth import AuthError
         try:
             runtime_kwargs = {
                 "requested": job.get("provider") or os.getenv("HERMES_INFERENCE_PROVIDER"),
@@ -878,6 +944,28 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             if job.get("base_url"):
                 runtime_kwargs["explicit_base_url"] = job.get("base_url")
             runtime = resolve_runtime_provider(**runtime_kwargs)
+        except AuthError as auth_exc:
+            # Primary provider auth failed — try fallback chain before giving up.
+            logger.warning("Job '%s': primary auth failed (%s), trying fallback", job_id, auth_exc)
+            fb = _cfg.get("fallback_providers") or _cfg.get("fallback_model")
+            fb_list = (fb if isinstance(fb, list) else [fb]) if fb else []
+            runtime = None
+            for entry in fb_list:
+                if not isinstance(entry, dict):
+                    continue
+                try:
+                    fb_kwargs = {"requested": entry.get("provider")}
+                    if entry.get("base_url"):
+                        fb_kwargs["explicit_base_url"] = entry["base_url"]
+                    if entry.get("api_key"):
+                        fb_kwargs["explicit_api_key"] = entry["api_key"]
+                    runtime = resolve_runtime_provider(**fb_kwargs)
+                    logger.info("Job '%s': fallback resolved to %s", job_id, runtime.get("provider"))
+                    break
+                except Exception as fb_exc:
+                    logger.debug("Job '%s': fallback %s failed: %s", job_id, entry.get("provider"), fb_exc)
+            if runtime is None:
+                raise RuntimeError(format_runtime_provider_error(auth_exc)) from auth_exc
         except Exception as exc:
             message = format_runtime_provider_error(exc)
             raise RuntimeError(message) from exc
@@ -920,7 +1008,10 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             enabled_toolsets=_resolve_cron_enabled_toolsets(job, _cfg),
             disabled_toolsets=["cronjob", "messaging", "clarify"],
             quiet_mode=True,
-            skip_context_files=True,  # Don't inject SOUL.md/AGENTS.md from scheduler cwd
+            # When a workdir is configured, inject AGENTS.md / CLAUDE.md /
+            # .cursorrules from that directory; otherwise preserve the old
+            # behaviour (don't inject SOUL.md/AGENTS.md from the scheduler cwd).
+            skip_context_files=not bool(_job_workdir),
             skip_memory=True,  # Cron system prompts would corrupt user representations
             platform="cron",
             session_id=_cron_session_id,
@@ -1059,6 +1150,14 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         return False, output, "", error_msg
 
     finally:
+        # Restore TERMINAL_CWD to whatever it was before this job ran.  We
+        # only ever mutate it when the job has a workdir; see the setup block
+        # at the top of run_job for the serialization guarantee.
+        if _job_workdir:
+            if _prior_terminal_cwd == "_UNSET_":
+                os.environ.pop("TERMINAL_CWD", None)
+            else:
+                os.environ["TERMINAL_CWD"] = _prior_terminal_cwd
         # Clean up ContextVar session/delivery state for this job.
         clear_session_vars(_ctx_tokens)
         if _session_db:
@@ -1186,14 +1285,28 @@ def tick(verbose: bool = True, adapters=None, loop=None) -> int:
                 mark_job_run(job["id"], False, str(e))
                 return False
 
-        # Run all due jobs concurrently, each in its own ContextVar copy
-        # so session/delivery state stays isolated per-thread.
-        with concurrent.futures.ThreadPoolExecutor(max_workers=_max_workers) as _tick_pool:
-            _futures = []
-            for job in due_jobs:
-                _ctx = contextvars.copy_context()
-                _futures.append(_tick_pool.submit(_ctx.run, _process_job, job))
-            _results = [f.result() for f in _futures]
+        # Partition due jobs: those with a per-job workdir mutate
+        # os.environ["TERMINAL_CWD"] inside run_job, which is process-global —
+        # so they MUST run sequentially to avoid corrupting each other.  Jobs
+        # without a workdir leave env untouched and stay parallel-safe.
+        workdir_jobs = [j for j in due_jobs if (j.get("workdir") or "").strip()]
+        parallel_jobs = [j for j in due_jobs if not (j.get("workdir") or "").strip()]
+
+        _results: list = []
+
+        # Sequential pass for workdir jobs.
+        for job in workdir_jobs:
+            _ctx = contextvars.copy_context()
+            _results.append(_ctx.run(_process_job, job))
+
+        # Parallel pass for the rest — same behaviour as before.
+        if parallel_jobs:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=_max_workers) as _tick_pool:
+                _futures = []
+                for job in parallel_jobs:
+                    _ctx = contextvars.copy_context()
+                    _futures.append(_tick_pool.submit(_ctx.run, _process_job, job))
+                _results.extend(f.result() for f in _futures)
 
         return sum(_results)
     finally:

docker-compose.yml

@@ -0,0 +1,52 @@
+#
+# docker-compose.yml for Hermes Agent
+#
+# Usage:
+#   HERMES_UID=$(id -u) HERMES_GID=$(id -g) docker compose up -d
+#
+# Set HERMES_UID / HERMES_GID to the host user that owns ~/.hermes so
+# files created inside the container stay readable/writable on the host.
+# The entrypoint remaps the internal `hermes` user to these values via
+# usermod/groupmod + gosu.
+#
+# Security notes:
+#   - The dashboard service binds to 127.0.0.1 by default. It stores API
+#     keys; exposing it on LAN without auth is unsafe. If you want remote
+#     access, use an SSH tunnel or put it behind a reverse proxy that
+#     adds authentication — do NOT pass --insecure --host 0.0.0.0.
+#   - The gateway's API server is off unless you uncomment API_SERVER_KEY
+#     and API_SERVER_HOST. See docs/user-guide/api-server.md before doing
+#     this on an internet-facing host.
+#
+services:
+  gateway:
+    build: .
+    image: hermes-agent
+    container_name: hermes
+    restart: unless-stopped
+    network_mode: host
+    volumes:
+      - ~/.hermes:/opt/data
+    environment:
+      - HERMES_UID=${HERMES_UID:-10000}
+      - HERMES_GID=${HERMES_GID:-10000}
+      # To expose the OpenAI-compatible API server beyond localhost,
+      # uncomment BOTH lines (API_SERVER_KEY is mandatory for auth):
+      # - API_SERVER_HOST=0.0.0.0
+      # - API_SERVER_KEY=${API_SERVER_KEY}
+    command: ["gateway", "run"]
+
+  dashboard:
+    image: hermes-agent
+    container_name: hermes-dashboard
+    restart: unless-stopped
+    network_mode: host
+    depends_on:
+      - gateway
+    volumes:
+      - ~/.hermes:/opt/data
+    environment:
+      - HERMES_UID=${HERMES_UID:-10000}
+      - HERMES_GID=${HERMES_GID:-10000}
+    # Localhost-only. For remote access, tunnel via `ssh -L 9119:localhost:9119`.
+    command: ["dashboard", "--host", "127.0.0.1", "--no-open"]

docker/entrypoint.sh

@@ -22,9 +22,18 @@ if [ "$(id -u)" = "0" ]; then
         groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
     fi
 
+    # Fix ownership of the data volume. When HERMES_UID remaps the hermes user,
+    # files created by previous runs (under the old UID) become inaccessible.
+    # Always chown -R when UID was remapped; otherwise only if top-level is wrong.
     actual_hermes_uid=$(id -u hermes)
-    if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
-        echo "$HERMES_HOME is not owned by $actual_hermes_uid, fixing"
+    needs_chown=false
+    if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "10000" ]; then
+        needs_chown=true
+    elif [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
+        needs_chown=true
+    fi
+    if [ "$needs_chown" = true ]; then
+        echo "Fixing ownership of $HERMES_HOME to hermes ($actual_hermes_uid)"
         # In rootless Podman the container's "root" is mapped to an unprivileged
         # host UID — chown will fail.  That's fine: the volume is already owned
         # by the mapped user on the host side.
@@ -32,6 +41,15 @@ if [ "$(id -u)" = "0" ]; then
             echo "Warning: chown failed (rootless container?) — continuing anyway"
     fi
 
+    # Ensure config.yaml is readable by the hermes runtime user even if it was
+    # edited on the host after initial ownership setup. Must run here (as root)
+    # rather than after the gosu drop, otherwise a non-root caller like
+    # `docker run -u $(id -u):$(id -g)` hits "Operation not permitted" (#15865).
+    if [ -f "$HERMES_HOME/config.yaml" ]; then
+        chown hermes:hermes "$HERMES_HOME/config.yaml" 2>/dev/null || true
+        chmod 640 "$HERMES_HOME/config.yaml" 2>/dev/null || true
+    fi
+
     echo "Dropping root privileges"
     exec gosu hermes "$0" "$@"
 fi
@@ -58,13 +76,6 @@ if [ ! -f "$HERMES_HOME/config.yaml" ]; then
     cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
 fi
 
-# Ensure the main config file remains accessible to the hermes runtime user
-# even if it was edited on the host after initial ownership setup.
-if [ -f "$HERMES_HOME/config.yaml" ]; then
-    chown hermes:hermes "$HERMES_HOME/config.yaml"
-    chmod 640 "$HERMES_HOME/config.yaml"
-fi
-
 # SOUL.md
 if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
     cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"

gateway/config.py

@@ -135,7 +135,7 @@ class SessionResetPolicy:
             mode=mode if mode is not None else "both",
             at_hour=at_hour if at_hour is not None else 4,
             idle_minutes=idle_minutes if idle_minutes is not None else 1440,
-            notify=notify if notify is not None else True,
+            notify=_coerce_bool(notify, True),
             notify_exclude_platforms=tuple(exclude) if exclude is not None else ("api_server", "webhook"),
         )
 
@@ -178,7 +178,7 @@ class PlatformConfig:
             home_channel = HomeChannel.from_dict(data["home_channel"])
         
         return cls(
-            enabled=data.get("enabled", False),
+            enabled=_coerce_bool(data.get("enabled"), False),
             token=data.get("token"),
             api_key=data.get("api_key"),
             home_channel=home_channel,
@@ -435,7 +435,7 @@ class GatewayConfig:
             reset_triggers=data.get("reset_triggers", ["/new", "/reset"]),
             quick_commands=quick_commands,
             sessions_dir=sessions_dir,
-            always_log_local=data.get("always_log_local", True),
+            always_log_local=_coerce_bool(data.get("always_log_local"), True),
             stt_enabled=_coerce_bool(stt_enabled, True),
             group_sessions_per_user=_coerce_bool(group_sessions_per_user, True),
             thread_sessions_per_user=_coerce_bool(thread_sessions_per_user, False),
@@ -687,6 +687,11 @@ def load_gateway_config() -> GatewayConfig:
                     os.environ["TELEGRAM_REACTIONS"] = str(telegram_cfg["reactions"]).lower()
                 if "proxy_url" in telegram_cfg and not os.getenv("TELEGRAM_PROXY"):
                     os.environ["TELEGRAM_PROXY"] = str(telegram_cfg["proxy_url"]).strip()
+                if "group_allowed_chats" in telegram_cfg and not os.getenv("TELEGRAM_GROUP_ALLOWED_USERS"):
+                    gac = telegram_cfg["group_allowed_chats"]
+                    if isinstance(gac, list):
+                        gac = ",".join(str(v) for v in gac)
+                    os.environ["TELEGRAM_GROUP_ALLOWED_USERS"] = str(gac)
                 if "disable_link_previews" in telegram_cfg:
                     plat_data = platforms_data.setdefault(Platform.TELEGRAM.value, {})
                     if not isinstance(plat_data, dict):

gateway/platforms/api_server.py

@@ -9,6 +9,7 @@ Exposes an HTTP server with endpoints:
 - GET  /v1/models                  — lists hermes-agent as an available model
 - POST /v1/runs                    — start a run, returns run_id immediately (202)
 - GET  /v1/runs/{run_id}/events    — SSE stream of structured lifecycle events
+- POST /v1/runs/{run_id}/stop    — interrupt a running agent
 - GET  /health                     — health check
 - GET  /health/detailed            — rich status for cross-container dashboard probing
 
@@ -586,6 +587,9 @@ class APIServerAdapter(BasePlatformAdapter):
         self._run_streams: Dict[str, "asyncio.Queue[Optional[Dict]]"] = {}
         # Creation timestamps for orphaned-run TTL sweep
         self._run_streams_created: Dict[str, float] = {}
+        # Active run agent/task references for stop support
+        self._active_run_agents: Dict[str, Any] = {}
+        self._active_run_tasks: Dict[str, "asyncio.Task"] = {}
         self._session_db: Optional[Any] = None  # Lazy-init SessionDB for session continuity
 
     @staticmethod
@@ -1204,10 +1208,12 @@ class APIServerAdapter(BasePlatformAdapter):
 
         If the client disconnects mid-stream, ``agent.interrupt()`` is
         called so the agent stops issuing upstream LLM calls, then the
-        asyncio task is cancelled.  When ``store=True`` the full response
-        is persisted to the ResponseStore in a ``finally`` block so GET
-        /v1/responses/{id} and ``previous_response_id`` chaining work the
-        same as the batch path.
+        asyncio task is cancelled.  When ``store=True`` an initial
+        ``in_progress`` snapshot is persisted immediately after
+        ``response.created`` and disconnects update it to an
+        ``incomplete`` snapshot so GET /v1/responses/{id} and
+        ``previous_response_id`` chaining still have something to
+        recover from.
         """
         import queue as _q
 
@@ -1269,6 +1275,60 @@ class APIServerAdapter(BasePlatformAdapter):
         final_response_text = ""
         agent_error: Optional[str] = None
         usage: Dict[str, int] = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
+        terminal_snapshot_persisted = False
+
+        def _persist_response_snapshot(
+            response_env: Dict[str, Any],
+            *,
+            conversation_history_snapshot: Optional[List[Dict[str, Any]]] = None,
+        ) -> None:
+            if not store:
+                return
+            if conversation_history_snapshot is None:
+                conversation_history_snapshot = list(conversation_history)
+                conversation_history_snapshot.append({"role": "user", "content": user_message})
+            self._response_store.put(response_id, {
+                "response": response_env,
+                "conversation_history": conversation_history_snapshot,
+                "instructions": instructions,
+                "session_id": session_id,
+            })
+            if conversation:
+                self._response_store.set_conversation(conversation, response_id)
+
+        def _persist_incomplete_if_needed() -> None:
+            """Persist an ``incomplete`` snapshot if no terminal one was written.
+
+            Called from both the client-disconnect (``ConnectionResetError``)
+            and server-cancellation (``asyncio.CancelledError``) paths so
+            GET /v1/responses/{id} and ``previous_response_id`` chaining keep
+            working after abrupt stream termination.
+            """
+            if not store or terminal_snapshot_persisted:
+                return
+            incomplete_text = "".join(final_text_parts) or final_response_text
+            incomplete_items: List[Dict[str, Any]] = list(emitted_items)
+            if incomplete_text:
+                incomplete_items.append({
+                    "type": "message",
+                    "role": "assistant",
+                    "content": [{"type": "output_text", "text": incomplete_text}],
+                })
+            incomplete_env = _envelope("incomplete")
+            incomplete_env["output"] = incomplete_items
+            incomplete_env["usage"] = {
+                "input_tokens": usage.get("input_tokens", 0),
+                "output_tokens": usage.get("output_tokens", 0),
+                "total_tokens": usage.get("total_tokens", 0),
+            }
+            incomplete_history = list(conversation_history)
+            incomplete_history.append({"role": "user", "content": user_message})
+            if incomplete_text:
+                incomplete_history.append({"role": "assistant", "content": incomplete_text})
+            _persist_response_snapshot(
+                incomplete_env,
+                conversation_history_snapshot=incomplete_history,
+            )
 
         try:
             # response.created — initial envelope, status=in_progress
@@ -1278,6 +1338,7 @@ class APIServerAdapter(BasePlatformAdapter):
                 "type": "response.created",
                 "response": created_env,
             })
+            _persist_response_snapshot(created_env)
             last_activity = time.monotonic()
 
             async def _open_message_item() -> None:
@@ -1534,6 +1595,18 @@ class APIServerAdapter(BasePlatformAdapter):
                     "output_tokens": usage.get("output_tokens", 0),
                     "total_tokens": usage.get("total_tokens", 0),
                 }
+                _failed_history = list(conversation_history)
+                _failed_history.append({"role": "user", "content": user_message})
+                if final_response_text or agent_error:
+                    _failed_history.append({
+                        "role": "assistant",
+                        "content": final_response_text or agent_error,
+                    })
+                _persist_response_snapshot(
+                    failed_env,
+                    conversation_history_snapshot=_failed_history,
+                )
+                terminal_snapshot_persisted = True
                 await _write_event("response.failed", {
                     "type": "response.failed",
                     "response": failed_env,
@@ -1546,30 +1619,24 @@ class APIServerAdapter(BasePlatformAdapter):
                     "output_tokens": usage.get("output_tokens", 0),
                     "total_tokens": usage.get("total_tokens", 0),
                 }
+                full_history = list(conversation_history)
+                full_history.append({"role": "user", "content": user_message})
+                if isinstance(result, dict) and result.get("messages"):
+                    full_history.extend(result["messages"])
+                else:
+                    full_history.append({"role": "assistant", "content": final_response_text})
+                _persist_response_snapshot(
+                    completed_env,
+                    conversation_history_snapshot=full_history,
+                )
+                terminal_snapshot_persisted = True
                 await _write_event("response.completed", {
                     "type": "response.completed",
                     "response": completed_env,
                 })
 
-                # Persist for future chaining / GET retrieval, mirroring
-                # the batch path behavior.
-                if store:
-                    full_history = list(conversation_history)
-                    full_history.append({"role": "user", "content": user_message})
-                    if isinstance(result, dict) and result.get("messages"):
-                        full_history.extend(result["messages"])
-                    else:
-                        full_history.append({"role": "assistant", "content": final_response_text})
-                    self._response_store.put(response_id, {
-                        "response": completed_env,
-                        "conversation_history": full_history,
-                        "instructions": instructions,
-                        "session_id": session_id,
-                    })
-                    if conversation:
-                        self._response_store.set_conversation(conversation, response_id)
-
         except (ConnectionResetError, ConnectionAbortedError, BrokenPipeError, OSError):
+            _persist_incomplete_if_needed()
             # Client disconnected — interrupt the agent so it stops
             # making upstream LLM calls, then cancel the task.
             agent = agent_ref[0] if agent_ref else None
@@ -1585,6 +1652,22 @@ class APIServerAdapter(BasePlatformAdapter):
                 except (asyncio.CancelledError, Exception):
                     pass
             logger.info("SSE client disconnected; interrupted agent task %s", response_id)
+        except asyncio.CancelledError:
+            # Server-side cancellation (e.g. shutdown, request timeout) —
+            # persist an incomplete snapshot so GET /v1/responses/{id} and
+            # previous_response_id chaining still work, then re-raise so the
+            # runtime's cancellation semantics are respected.
+            _persist_incomplete_if_needed()
+            agent = agent_ref[0] if agent_ref else None
+            if agent is not None:
+                try:
+                    agent.interrupt("SSE task cancelled")
+                except Exception:
+                    pass
+            if not agent_task.done():
+                agent_task.cancel()
+            logger.info("SSE task cancelled; persisted incomplete snapshot for %s", response_id)
+            raise
 
         return response
 
@@ -2362,6 +2445,7 @@ class APIServerAdapter(BasePlatformAdapter):
                     stream_delta_callback=_text_cb,
                     tool_progress_callback=event_cb,
                 )
+                self._active_run_agents[run_id] = agent
                 def _run_sync():
                     r = agent.run_conversation(
                         user_message=user_message,
@@ -2401,8 +2485,11 @@ class APIServerAdapter(BasePlatformAdapter):
                     q.put_nowait(None)
                 except Exception:
                     pass
+                self._active_run_agents.pop(run_id, None)
+                self._active_run_tasks.pop(run_id, None)
 
         task = asyncio.create_task(_run_and_close())
+        self._active_run_tasks[run_id] = task
         try:
             self._background_tasks.add(task)
         except TypeError:
@@ -2461,6 +2548,44 @@ class APIServerAdapter(BasePlatformAdapter):
 
         return response
 
+    async def _handle_stop_run(self, request: "web.Request") -> "web.Response":
+        """POST /v1/runs/{run_id}/stop — interrupt a running agent."""
+        auth_err = self._check_auth(request)
+        if auth_err:
+            return auth_err
+
+        run_id = request.match_info["run_id"]
+        agent = self._active_run_agents.get(run_id)
+        task = self._active_run_tasks.get(run_id)
+
+        if agent is None and task is None:
+            return web.json_response(_openai_error(f"Run not found: {run_id}", code="run_not_found"), status=404)
+
+        if agent is not None:
+            try:
+                agent.interrupt("Stop requested via API")
+            except Exception:
+                pass
+
+        if task is not None and not task.done():
+            task.cancel()
+            # Bounded wait: run_conversation() executes in the default
+            # executor thread which task.cancel() cannot preempt — we rely on
+            # agent.interrupt() above to break the loop. Cap the wait so a
+            # slow/unresponsive interrupt can't hang this handler.
+            try:
+                await asyncio.wait_for(asyncio.shield(task), timeout=5.0)
+            except asyncio.TimeoutError:
+                logger.warning(
+                    "[api_server] stop for run %s timed out after 5s; "
+                    "agent may still be finishing the current step",
+                    run_id,
+                )
+            except (asyncio.CancelledError, Exception):
+                pass
+
+        return web.json_response({"run_id": run_id, "status": "stopping"})
+
     async def _sweep_orphaned_runs(self) -> None:
         """Periodically clean up run streams that were never consumed."""
         while True:
@@ -2475,6 +2600,8 @@ class APIServerAdapter(BasePlatformAdapter):
                 logger.debug("[api_server] sweeping orphaned run %s", run_id)
                 self._run_streams.pop(run_id, None)
                 self._run_streams_created.pop(run_id, None)
+                self._active_run_agents.pop(run_id, None)
+                self._active_run_tasks.pop(run_id, None)
 
     # ------------------------------------------------------------------
     # BasePlatformAdapter interface
@@ -2510,6 +2637,7 @@ class APIServerAdapter(BasePlatformAdapter):
             # Structured event streaming
             self._app.router.add_post("/v1/runs", self._handle_runs)
             self._app.router.add_get("/v1/runs/{run_id}/events", self._handle_run_events)
+            self._app.router.add_post("/v1/runs/{run_id}/stop", self._handle_stop_run)
             # Start background sweep to clean up orphaned (unconsumed) run streams
             sweep_task = asyncio.create_task(self._sweep_orphaned_runs())
             try:

gateway/platforms/base.py

@@ -148,7 +148,102 @@ def _detect_macos_system_proxy() -> str | None:
     return None
 
 
-def resolve_proxy_url(platform_env_var: str | None = None) -> str | None:
+def _split_host_port(value: str) -> tuple[str, int | None]:
+    raw = str(value or "").strip()
+    if not raw:
+        return "", None
+    if "://" in raw:
+        parsed = urlsplit(raw)
+        return (parsed.hostname or "").lower().rstrip("."), parsed.port
+    if raw.startswith("[") and "]" in raw:
+        host, _, rest = raw[1:].partition("]")
+        port = None
+        if rest.startswith(":") and rest[1:].isdigit():
+            port = int(rest[1:])
+        return host.lower().rstrip("."), port
+    if raw.count(":") == 1:
+        host, _, maybe_port = raw.rpartition(":")
+        if maybe_port.isdigit():
+            return host.lower().rstrip("."), int(maybe_port)
+    return raw.lower().strip("[]").rstrip("."), None
+
+
+def _no_proxy_entries() -> list[str]:
+    entries: list[str] = []
+    for key in ("NO_PROXY", "no_proxy"):
+        raw = os.environ.get(key, "")
+        entries.extend(part.strip() for part in raw.split(",") if part.strip())
+    return entries
+
+
+def _no_proxy_entry_matches(entry: str, host: str, port: int | None = None) -> bool:
+    token = str(entry or "").strip().lower()
+    if not token:
+        return False
+    if token == "*":
+        return True
+
+    token_host, token_port = _split_host_port(token)
+    if token_port is not None and port is not None and token_port != port:
+        return False
+    if token_port is not None and port is None:
+        return False
+    if not token_host:
+        return False
+
+    try:
+        network = ipaddress.ip_network(token_host, strict=False)
+        try:
+            return ipaddress.ip_address(host) in network
+        except ValueError:
+            return False
+    except ValueError:
+        pass
+
+    try:
+        token_ip = ipaddress.ip_address(token_host)
+        try:
+            return ipaddress.ip_address(host) == token_ip
+        except ValueError:
+            return False
+    except ValueError:
+        pass
+
+    if token_host.startswith("*."):
+        suffix = token_host[1:]
+        return host.endswith(suffix)
+    if token_host.startswith("."):
+        return host == token_host[1:] or host.endswith(token_host)
+    return host == token_host or host.endswith(f".{token_host}")
+
+
+def should_bypass_proxy(target_hosts: str | list[str] | tuple[str, ...] | set[str] | None) -> bool:
+    """Return True when NO_PROXY/no_proxy matches at least one target host.
+
+    Supports exact hosts, domain suffixes, wildcard suffixes, IP literals,
+    CIDR ranges, optional host:port entries, and ``*``.
+    """
+    entries = _no_proxy_entries()
+    if not entries or not target_hosts:
+        return False
+    if isinstance(target_hosts, str):
+        candidates = [target_hosts]
+    else:
+        candidates = list(target_hosts)
+    for candidate in candidates:
+        host, port = _split_host_port(str(candidate))
+        if not host:
+            continue
+        if any(_no_proxy_entry_matches(entry, host, port) for entry in entries):
+            return True
+    return False
+
+
+def resolve_proxy_url(
+    platform_env_var: str | None = None,
+    *,
+    target_hosts: str | list[str] | tuple[str, ...] | set[str] | None = None,
+) -> str | None:
     """Return a proxy URL from env vars, or macOS system proxy.
 
     Check order:
@@ -156,18 +251,26 @@ def resolve_proxy_url(platform_env_var: str | None = None) -> str | None:
       1. HTTPS_PROXY / HTTP_PROXY / ALL_PROXY (and lowercase variants)
       2. macOS system proxy via ``scutil --proxy`` (auto-detect)
 
-    Returns *None* if no proxy is found.
+    Returns *None* if no proxy is found, or if NO_PROXY/no_proxy matches one
+    of ``target_hosts``.
     """
     if platform_env_var:
         value = (os.environ.get(platform_env_var) or "").strip()
         if value:
+            if should_bypass_proxy(target_hosts):
+                return None
             return normalize_proxy_url(value)
     for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY",
                 "https_proxy", "http_proxy", "all_proxy"):
         value = (os.environ.get(key) or "").strip()
         if value:
+            if should_bypass_proxy(target_hosts):
+                return None
             return normalize_proxy_url(value)
-    return normalize_proxy_url(_detect_macos_system_proxy())
+    detected = normalize_proxy_url(_detect_macos_system_proxy())
+    if detected and should_bypass_proxy(target_hosts):
+        return None
+    return detected
 
 
 def proxy_kwargs_for_bot(proxy_url: str | None) -> dict:
@@ -922,7 +1025,20 @@ class BasePlatformAdapter(ABC):
         self._post_delivery_callbacks: Dict[str, Any] = {}
         self._expected_cancelled_tasks: set[asyncio.Task] = set()
         self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
-        # Chats where auto-TTS on voice input is disabled (set by /voice off)
+        # Auto-TTS on voice input: ``_auto_tts_default`` is the global default
+        # (``voice.auto_tts`` in config.yaml, pushed by GatewayRunner on connect).
+        # Per-chat overrides live in two sets populated from ``_voice_mode``:
+        #   - ``_auto_tts_enabled_chats``: chat explicitly opted in via ``/voice on``
+        #     or ``/voice tts`` (mode is ``voice_only`` or ``all``). Fires even when
+        #     the global default is False.
+        #   - ``_auto_tts_disabled_chats``: chat explicitly opted out via
+        #     ``/voice off`` (mode is ``off``). Suppresses auto-TTS even when the
+        #     global default is True.
+        # The gate in _process_message() is:
+        #   fire if chat in _auto_tts_enabled_chats
+        #     OR (_auto_tts_default and chat not in _auto_tts_disabled_chats)
+        self._auto_tts_default: bool = False
+        self._auto_tts_enabled_chats: set = set()
         self._auto_tts_disabled_chats: set = set()
         # Chats where typing indicator is paused (e.g. during approval waits).
         # _keep_typing skips send_typing when the chat_id is in this set.
@@ -944,6 +1060,21 @@ class BasePlatformAdapter(ABC):
     def fatal_error_retryable(self) -> bool:
         return self._fatal_error_retryable
 
+    def _should_auto_tts_for_chat(self, chat_id: str) -> bool:
+        """Whether auto-TTS on voice input should fire for ``chat_id``.
+
+        Decision layers (Issue #16007):
+          1. Explicit ``/voice on`` or ``/voice tts`` → always fire (even if
+             ``voice.auto_tts`` is False).
+          2. Explicit ``/voice off`` → never fire.
+          3. Fall back to the global ``voice.auto_tts`` config default.
+        """
+        if chat_id in self._auto_tts_enabled_chats:
+            return True
+        if chat_id in self._auto_tts_disabled_chats:
+            return False
+        return bool(self._auto_tts_default)
+
     def set_fatal_error_handler(self, handler: Callable[["BasePlatformAdapter"], Awaitable[None] | None]) -> None:
         self._fatal_error_handler = handler
 
@@ -2111,12 +2242,14 @@ class BasePlatformAdapter(ABC):
                     logger.info("[%s] extract_local_files found %d file(s) in response", self.name, len(local_files))
                 
                 # Auto-TTS: if voice message, generate audio FIRST (before sending text)
-                # Skipped when the chat has voice mode disabled (/voice off)
+                # Gated via ``_should_auto_tts_for_chat``: fires when the chat has
+                # an explicit ``/voice on|tts`` opt-in OR when ``voice.auto_tts`` is
+                # True globally and no ``/voice off`` has been issued.
                 _tts_path = None
-                if (event.message_type == MessageType.VOICE
+                if (self._should_auto_tts_for_chat(event.source.chat_id)
+                        and event.message_type == MessageType.VOICE
                         and text_content
-                        and not media_files
-                        and event.source.chat_id not in self._auto_tts_disabled_chats):
+                        and not media_files):
                     try:
                         from tools.tts_tool import text_to_speech_tool, check_tts_requirements
                         if check_tts_requirements():
@@ -2440,6 +2573,9 @@ class BasePlatformAdapter(ABC):
         user_id_alt: Optional[str] = None,
         chat_id_alt: Optional[str] = None,
         is_bot: bool = False,
+        guild_id: Optional[str] = None,
+        parent_chat_id: Optional[str] = None,
+        message_id: Optional[str] = None,
     ) -> SessionSource:
         """Helper to build a SessionSource for this platform."""
         # Normalize empty topic to None
@@ -2457,6 +2593,9 @@ class BasePlatformAdapter(ABC):
             user_id_alt=user_id_alt,
             chat_id_alt=chat_id_alt,
             is_bot=is_bot,
+            guild_id=str(guild_id) if guild_id else None,
+            parent_chat_id=str(parent_chat_id) if parent_chat_id else None,
+            message_id=str(message_id) if message_id else None,
         )
     
     @abstractmethod

gateway/platforms/bluebubbles.py

@@ -99,6 +99,7 @@ def _normalize_server_url(raw: str) -> str:
 
 class BlueBubblesAdapter(BasePlatformAdapter):
     platform = Platform.BLUEBUBBLES
+    SUPPORTS_MESSAGE_EDITING = False
     MAX_MESSAGE_LENGTH = MAX_TEXT_LENGTH
 
     def __init__(self, config: PlatformConfig):
@@ -391,6 +392,13 @@ class BlueBubblesAdapter(BasePlatformAdapter):
     # Text sending
     # ------------------------------------------------------------------
 
+    @staticmethod
+    def truncate_message(content: str, max_length: int = MAX_TEXT_LENGTH) -> List[str]:
+        # Use the base splitter but skip pagination indicators — iMessage
+        # bubbles flow naturally without "(1/3)" suffixes.
+        chunks = BasePlatformAdapter.truncate_message(content, max_length)
+        return [re.sub(r"\s*\(\d+/\d+\)$", "", c) for c in chunks]
+
     async def send(
         self,
         chat_id: str,
@@ -398,10 +406,19 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        text = strip_markdown(content or "")
+        text = self.format_message(content)
         if not text:
             return SendResult(success=False, error="BlueBubbles send requires text")
-        chunks = self.truncate_message(text, max_length=self.MAX_MESSAGE_LENGTH)
+        # Split on paragraph breaks first (double newlines) so each thought
+        # becomes its own iMessage bubble, then truncate any that are still
+        # too long.
+        paragraphs = [p.strip() for p in re.split(r'\n\s*\n', text) if p.strip()]
+        chunks: List[str] = []
+        for para in (paragraphs or [text]):
+            if len(para) <= self.MAX_MESSAGE_LENGTH:
+                chunks.append(para)
+            else:
+                chunks.extend(self.truncate_message(para, max_length=self.MAX_MESSAGE_LENGTH))
         last = SendResult(success=True)
         for chunk in chunks:
             guid = await self._resolve_chat_guid(chat_id)

gateway/platforms/discord.py

@@ -2246,10 +2246,6 @@ class DiscordAdapter(BasePlatformAdapter):
         async def slash_usage(interaction: discord.Interaction):
             await self._run_simple_slash(interaction, "/usage")
 
-        @tree.command(name="provider", description="Show available providers")
-        async def slash_provider(interaction: discord.Interaction):
-            await self._run_simple_slash(interaction, "/provider")
-
         @tree.command(name="help", description="Show available commands")
         async def slash_help(interaction: discord.Interaction):
             await self._run_simple_slash(interaction, "/help")
@@ -2319,11 +2315,6 @@ class DiscordAdapter(BasePlatformAdapter):
         async def slash_background(interaction: discord.Interaction, prompt: str):
             await self._run_simple_slash(interaction, f"/background {prompt}", "Background task started~")
 
-        @tree.command(name="btw", description="Ephemeral side question using session context")
-        @discord.app_commands.describe(question="Your side question (no tools, not persisted)")
-        async def slash_btw(interaction: discord.Interaction, question: str):
-            await self._run_simple_slash(interaction, f"/btw {question}")
-
         # ── Auto-register any gateway-available commands not yet on the tree ──
         # This ensures new commands added to COMMAND_REGISTRY in
         # hermes_cli/commands.py automatically appear as Discord slash
@@ -2719,7 +2710,12 @@ class DiscordAdapter(BasePlatformAdapter):
         return os.getenv("DISCORD_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no", "off")
 
     def _discord_free_response_channels(self) -> set:
-        """Return Discord channel IDs where no bot mention is required."""
+        """Return Discord channel IDs where no bot mention is required.
+
+        A single ``"*"`` entry (either from a list or a comma-separated
+        string) is preserved in the returned set so callers can short-circuit
+        on wildcard membership, consistent with ``allowed_channels``.
+        """
         raw = self.config.extra.get("free_response_channels")
         if raw is None:
             raw = os.getenv("DISCORD_FREE_RESPONSE_CHANNELS", "")
@@ -3212,14 +3208,14 @@ class DiscordAdapter(BasePlatformAdapter):
             allowed_channels_raw = os.getenv("DISCORD_ALLOWED_CHANNELS", "")
             if allowed_channels_raw:
                 allowed_channels = {ch.strip() for ch in allowed_channels_raw.split(",") if ch.strip()}
-                if not (channel_ids & allowed_channels):
+                if "*" not in allowed_channels and not (channel_ids & allowed_channels):
                     logger.debug("[%s] Ignoring message in non-allowed channel: %s", self.name, channel_ids)
                     return
 
             # Check ignored channels - never respond even when mentioned
             ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
             ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
-            if channel_ids & ignored_channels:
+            if "*" in ignored_channels or (channel_ids & ignored_channels):
                 logger.debug("[%s] Ignoring message in ignored channel: %s", self.name, channel_ids)
                 return
 
@@ -3233,7 +3229,11 @@ class DiscordAdapter(BasePlatformAdapter):
             voice_linked_ids = {str(ch_id) for ch_id in self._voice_text_channels.values()}
             current_channel_id = str(message.channel.id)
             is_voice_linked_channel = current_channel_id in voice_linked_ids
-            is_free_channel = bool(channel_ids & free_channels) or is_voice_linked_channel
+            is_free_channel = (
+                "*" in free_channels
+                or bool(channel_ids & free_channels)
+                or is_voice_linked_channel
+            )
 
             # Skip the mention check if the message is in a thread where
             # the bot has previously participated (auto-created or replied in).
@@ -3256,6 +3256,7 @@ class DiscordAdapter(BasePlatformAdapter):
             if auto_thread and not skip_thread and not is_voice_linked_channel and not is_reply_message:
                 thread = await self._auto_create_thread(message)
                 if thread:
+                    parent_channel_id = str(message.channel.id)
                     is_thread = True
                     thread_id = str(thread.id)
                     auto_threaded_channel = thread
@@ -3315,6 +3316,9 @@ class DiscordAdapter(BasePlatformAdapter):
             thread_id=thread_id,
             chat_topic=chat_topic,
             is_bot=getattr(message.author, "bot", False),
+            guild_id=str(message.guild.id) if message.guild else None,
+            parent_chat_id=parent_channel_id,
+            message_id=str(message.id),
         )
 
         # Build media URLs -- download image attachments to local cache so the
@@ -3866,6 +3870,15 @@ if DISCORD_AVAILABLE:
 
             self.resolved = True
             model_id = interaction.data["values"][0]
+            self.clear_items()
+            await interaction.response.edit_message(
+                embed=discord.Embed(
+                    title="⚙ Switching Model",
+                    description=f"Switching to `{model_id}`...",
+                    color=discord.Color.blue(),
+                ),
+                view=None,
+            )
 
             try:
                 result_text = await self.on_model_selected(
@@ -3876,14 +3889,13 @@ if DISCORD_AVAILABLE:
             except Exception as exc:
                 result_text = f"Error switching model: {exc}"
 
-            self.clear_items()
-            await interaction.response.edit_message(
+            await interaction.edit_original_response(
                 embed=discord.Embed(
                     title="⚙ Model Switched",
                     description=result_text,
                     color=discord.Color.green(),
                 ),
-                view=self,
+                view=None,
             )
 
         async def _on_back(self, interaction: discord.Interaction):

gateway/platforms/matrix.py

@@ -532,6 +532,20 @@ class MatrixAdapter(BasePlatformAdapter):
                 )
                 await crypto_store.open()
 
+                # Bind the store to the runtime device_id before any
+                # put_account() runs. PgCryptoStore defaults _device_id
+                # to "" and its crypto_account UPSERT never updates the
+                # device_id column on conflict — so once put_account
+                # writes blank, it stays blank forever. That breaks
+                # every downstream device-scoped olm operation: peer
+                # to-device ciphertext can't find our identity key and
+                # no megolm sessions ever land. Setting _device_id here
+                # (in-memory; the on-disk row may not exist yet) makes
+                # the first put_account write the correct value.
+                # DeviceID is a NewType(str) so plain str works at runtime.
+                if client.device_id:
+                    await crypto_store.put_device_id(client.device_id)
+
                 crypto_state = _CryptoStateStore(state_store, self._joined_rooms)
                 olm = OlmMachine(client, crypto_store, crypto_state)
 

gateway/platforms/telegram.py

@@ -703,7 +703,6 @@ class TelegramAdapter(BasePlatformAdapter):
                 "write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
             }
 
-            proxy_url = resolve_proxy_url("TELEGRAM_PROXY")
             disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
             fallback_ips = self._fallback_ips()
             if not fallback_ips:
@@ -714,6 +713,8 @@ class TelegramAdapter(BasePlatformAdapter):
                     ", ".join(fallback_ips),
                 )
 
+            proxy_targets = ["api.telegram.org", *fallback_ips]
+            proxy_url = resolve_proxy_url("TELEGRAM_PROXY", target_hosts=proxy_targets)
             if fallback_ips and not proxy_url and not disable_fallback:
                 logger.info(
                     "[%s] Telegram fallback IPs active: %s",

gateway/platforms/telegram_network.py

@@ -43,10 +43,10 @@ _DOH_PROVIDERS: list[dict] = [
 _SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
 
 
-def _resolve_proxy_url() -> str | None:
+def _resolve_proxy_url(target_hosts=None) -> str | None:
     # Delegate to shared implementation (env vars + macOS system proxy detection)
     from gateway.platforms.base import resolve_proxy_url
-    return resolve_proxy_url("TELEGRAM_PROXY")
+    return resolve_proxy_url("TELEGRAM_PROXY", target_hosts=target_hosts)
 
 
 class TelegramFallbackTransport(httpx.AsyncBaseTransport):
@@ -60,7 +60,7 @@ class TelegramFallbackTransport(httpx.AsyncBaseTransport):
 
     def __init__(self, fallback_ips: Iterable[str], **transport_kwargs):
         self._fallback_ips = [ip for ip in dict.fromkeys(_normalize_fallback_ips(fallback_ips))]
-        proxy_url = _resolve_proxy_url()
+        proxy_url = _resolve_proxy_url(target_hosts=[_TELEGRAM_API_HOST, *self._fallback_ips])
         if proxy_url and "proxy" not in transport_kwargs:
             transport_kwargs["proxy"] = proxy_url
         self._primary = httpx.AsyncHTTPTransport(**transport_kwargs)

gateway/session.py

@@ -60,6 +60,10 @@ from .config import (
     SessionResetPolicy,  # noqa: F401 — re-exported via gateway/__init__.py
     HomeChannel,
 )
+from .whatsapp_identity import (
+    canonical_whatsapp_identifier,
+    normalize_whatsapp_identifier,
+)
 
 
 @dataclass
@@ -83,6 +87,9 @@ class SessionSource:
     user_id_alt: Optional[str] = None  # Platform-specific stable alt ID (Signal UUID, Feishu union_id)
     chat_id_alt: Optional[str] = None  # Signal group internal ID
     is_bot: bool = False  # True when the message author is a bot/webhook (Discord)
+    guild_id: Optional[str] = None  # Discord guild / Slack workspace / Matrix server scope
+    parent_chat_id: Optional[str] = None  # Parent channel when chat_id refers to a thread
+    message_id: Optional[str] = None  # ID of the triggering message (for pin/reply/react)
     
     @property
     def description(self) -> str:
@@ -120,8 +127,14 @@ class SessionSource:
             d["user_id_alt"] = self.user_id_alt
         if self.chat_id_alt:
             d["chat_id_alt"] = self.chat_id_alt
+        if self.guild_id:
+            d["guild_id"] = self.guild_id
+        if self.parent_chat_id:
+            d["parent_chat_id"] = self.parent_chat_id
+        if self.message_id:
+            d["message_id"] = self.message_id
         return d
-    
+
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "SessionSource":
         return cls(
@@ -135,6 +148,9 @@ class SessionSource:
             chat_topic=data.get("chat_topic"),
             user_id_alt=data.get("user_id_alt"),
             chat_id_alt=data.get("chat_id_alt"),
+            guild_id=data.get("guild_id"),
+            parent_chat_id=data.get("parent_chat_id"),
+            message_id=data.get("message_id"),
         )
     
 
@@ -186,6 +202,31 @@ that requires raw IDs).  Discord is excluded because mentions use ``<@user_id>``
 and the LLM needs the real ID to tag users."""
 
 
+def _discord_tools_loaded() -> bool:
+    """True iff the agent will actually have Discord tools this session.
+
+    Two conditions must hold:
+      1. The `discord` or `discord_admin` toolset is enabled for the
+         Discord platform via `hermes tools` (opt-in, default OFF).
+      2. `DISCORD_BOT_TOKEN` is set — the tool's `check_fn` gates on it
+         at registry time, so the toolset being enabled in config is not
+         enough if the token isn't configured.
+
+    Returns False (safe default — keeps the stale-API disclaimer) on any
+    error so a bad config can't silently promise tools the agent lacks.
+    """
+    if not (os.environ.get("DISCORD_BOT_TOKEN") or "").strip():
+        return False
+    try:
+        from hermes_cli.config import load_config
+        from hermes_cli.tools_config import _get_platform_tools
+        cfg = load_config()
+        enabled = _get_platform_tools(cfg, "discord", include_default_mcp_servers=False)
+        return "discord" in enabled or "discord_admin" in enabled
+    except Exception:
+        return False
+
+
 def build_session_context_prompt(
     context: SessionContext,
     *,
@@ -273,13 +314,44 @@ def build_session_context_prompt(
             "that you can only read messages sent directly to you and respond."
         )
     elif context.source.platform == Platform.DISCORD:
+        # Inject the Discord IDs block only when the agent actually has
+        # Discord tools loaded this session — i.e. the user opted into
+        # `discord` / `discord_admin` via `hermes tools` AND the bot
+        # token is configured.  Otherwise keep the stale-API disclaimer
+        # honest so we never promise tools the agent lacks.
+        if _discord_tools_loaded():
+            src = context.source
+            id_lines = ["", "**Discord IDs (for the `discord` / `discord_admin` tools):**"]
+            if src.guild_id:
+                id_lines.append(f"  - Guild: `{src.guild_id}`")
+            if src.thread_id and src.parent_chat_id:
+                id_lines.append(f"  - Parent channel: `{src.parent_chat_id}`")
+                id_lines.append(f"  - Thread: `{src.thread_id}` (use as `channel_id` for fetch_messages etc.)")
+            else:
+                id_lines.append(f"  - Channel: `{src.chat_id}`")
+            if src.message_id:
+                id_lines.append(f"  - Triggering message: `{src.message_id}`")
+            lines.extend(id_lines)
+        else:
+            lines.append("")
+            lines.append(
+                "**Platform notes:** You are running inside Discord. "
+                "You do NOT have access to Discord-specific APIs — you cannot search "
+                "channel history, pin messages, manage roles, or list server members. "
+                "Do not promise to perform these actions. If the user asks, explain "
+                "that you can only read messages sent directly to you and respond."
+            )
+    elif context.source.platform == Platform.BLUEBUBBLES:
         lines.append("")
         lines.append(
-            "**Platform notes:** You are running inside Discord. "
-            "You do NOT have access to Discord-specific APIs — you cannot search "
-            "channel history, pin messages, manage roles, or list server members. "
-            "Do not promise to perform these actions. If the user asks, explain "
-            "that you can only read messages sent directly to you and respond."
+            "**Platform notes:** You are responding via iMessage. "
+            "Keep responses short and conversational — think texts, not essays. "
+            "Structure longer replies as separate short thoughts, each separated "
+            "by a blank line (double newline). Each block between blank lines "
+            "will be delivered as its own iMessage bubble, so write accordingly: "
+            "one idea per bubble, 1–3 sentences each. "
+            "If the user needs a detailed answer, give the short version first "
+            "and offer to elaborate."
         )
 
     # Connected platforms
@@ -367,11 +439,11 @@ class SessionEntry:
     auto_reset_reason: Optional[str] = None  # "idle" or "daily"
     reset_had_activity: bool = False  # whether the expired session had any messages
     
-    # Set by the background expiry watcher after it successfully flushes
-    # memories for this session.  Persisted to sessions.json so the flag
-    # survives gateway restarts (the old in-memory _pre_flushed_sessions
-    # set was lost on restart, causing redundant re-flushes).
-    memory_flushed: bool = False
+    # Set by the background expiry watcher after it finalizes an expired
+    # session (invoking on_session_finalize hooks and evicting the cached
+    # agent).  Persisted to sessions.json so the flag survives gateway
+    # restarts — prevents redundant finalization runs.
+    expiry_finalized: bool = False
 
     # When True the next call to get_or_create_session() will auto-reset
     # this session (create a new session_id) so the user starts fresh.
@@ -407,7 +479,7 @@ class SessionEntry:
             "last_prompt_tokens": self.last_prompt_tokens,
             "estimated_cost_usd": self.estimated_cost_usd,
             "cost_status": self.cost_status,
-            "memory_flushed": self.memory_flushed,
+            "expiry_finalized": self.expiry_finalized,
             "suspended": self.suspended,
             "resume_pending": self.resume_pending,
             "resume_reason": self.resume_reason,
@@ -459,7 +531,7 @@ class SessionEntry:
             last_prompt_tokens=data.get("last_prompt_tokens", 0),
             estimated_cost_usd=data.get("estimated_cost_usd", 0.0),
             cost_status=data.get("cost_status", "unknown"),
-            memory_flushed=data.get("memory_flushed", False),
+            expiry_finalized=data.get("expiry_finalized", data.get("memory_flushed", False)),
             suspended=data.get("suspended", False),
             resume_pending=data.get("resume_pending", False),
             resume_reason=data.get("resume_reason"),
@@ -518,15 +590,24 @@ def build_session_key(
     """
     platform = source.platform.value
     if source.chat_type == "dm":
-        if source.chat_id:
+        dm_chat_id = source.chat_id
+        if source.platform == Platform.WHATSAPP:
+            dm_chat_id = canonical_whatsapp_identifier(source.chat_id)
+
+        if dm_chat_id:
             if source.thread_id:
-                return f"agent:main:{platform}:dm:{source.chat_id}:{source.thread_id}"
-            return f"agent:main:{platform}:dm:{source.chat_id}"
+                return f"agent:main:{platform}:dm:{dm_chat_id}:{source.thread_id}"
+            return f"agent:main:{platform}:dm:{dm_chat_id}"
         if source.thread_id:
             return f"agent:main:{platform}:dm:{source.thread_id}"
         return f"agent:main:{platform}:dm"
 
     participant_id = source.user_id_alt or source.user_id
+    if participant_id and source.platform == Platform.WHATSAPP:
+        # Same JID/LID-flip bug as the DM case: without canonicalisation, a
+        # single group member gets two isolated per-user sessions when the
+        # bridge reshuffles alias forms.
+        participant_id = canonical_whatsapp_identifier(str(participant_id)) or participant_id
     key_parts = ["agent:main", platform, source.chat_type]
 
     if source.chat_id:
@@ -1151,6 +1232,7 @@ class SessionStore:
                     reasoning_content=message.get("reasoning_content") if message.get("role") == "assistant" else None,
                     reasoning_details=message.get("reasoning_details") if message.get("role") == "assistant" else None,
                     codex_reasoning_items=message.get("codex_reasoning_items") if message.get("role") == "assistant" else None,
+                    codex_message_items=message.get("codex_message_items") if message.get("role") == "assistant" else None,
                 )
             except Exception as e:
                 logger.debug("Session DB operation failed: %s", e)
@@ -1183,6 +1265,7 @@ class SessionStore:
                         reasoning_content=msg.get("reasoning_content") if role == "assistant" else None,
                         reasoning_details=msg.get("reasoning_details") if role == "assistant" else None,
                         codex_reasoning_items=msg.get("codex_reasoning_items") if role == "assistant" else None,
+                        codex_message_items=msg.get("codex_message_items") if role == "assistant" else None,
                     )
             except Exception as e:
                 logger.debug("Failed to rewrite transcript in DB: %s", e)

gateway/whatsapp_identity.py

@@ -0,0 +1,135 @@
+"""Shared helpers for canonicalising WhatsApp sender identity.
+
+WhatsApp's bridge can surface the same human under two different JID shapes
+within a single conversation:
+
+- LID form: ``999999999999999@lid``
+- Phone form: ``15551234567@s.whatsapp.net``
+
+Both the authorisation path (:mod:`gateway.run`) and the session-key path
+(:mod:`gateway.session`) need to collapse these aliases to a single stable
+identity. This module is the single source of truth for that resolution so
+the two paths can never drift apart.
+
+Public helpers:
+
+- :func:`normalize_whatsapp_identifier` — strip JID/LID/device/plus syntax
+  down to the bare numeric identifier.
+- :func:`canonical_whatsapp_identifier` — walk the bridge's
+  ``lid-mapping-*.json`` files and return a stable canonical identity
+  across phone/LID variants.
+- :func:`expand_whatsapp_aliases` — return the full alias set for an
+  identifier. Used by authorisation code that needs to match any known
+  form of a sender against an allow-list.
+
+Plugins that need per-sender behaviour on WhatsApp (role-based routing,
+per-contact authorisation, policy gating in a gateway hook) should use
+``canonical_whatsapp_identifier`` so their bookkeeping lines up with
+Hermes' own session keys.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Set
+
+from hermes_constants import get_hermes_home
+
+
+def normalize_whatsapp_identifier(value: str) -> str:
+    """Strip WhatsApp JID/LID syntax down to its stable numeric identifier.
+
+    Accepts any of the identifier shapes the WhatsApp bridge may emit:
+    ``"60123456789@s.whatsapp.net"``, ``"60123456789:47@s.whatsapp.net"``,
+    ``"60123456789@lid"``, or a bare ``"+601****6789"`` / ``"60123456789"``.
+    Returns just the numeric identifier (``"60123456789"``) suitable for
+    equality comparisons.
+
+    Useful for plugins that want to match sender IDs against
+    user-supplied config (phone numbers in ``config.yaml``) without
+    worrying about which variant the bridge happens to deliver.
+    """
+    return (
+        str(value or "")
+        .strip()
+        .replace("+", "", 1)
+        .split(":", 1)[0]
+        .split("@", 1)[0]
+    )
+
+
+def expand_whatsapp_aliases(identifier: str) -> Set[str]:
+    """Resolve WhatsApp phone/LID aliases via bridge session mapping files.
+
+    Returns the set of all identifiers transitively reachable through the
+    bridge's ``$HERMES_HOME/whatsapp/session/lid-mapping-*.json`` files,
+    starting from ``identifier``. The result always includes the
+    normalized input itself, so callers can safely ``in`` check against
+    the return value without a separate fallback branch.
+
+    Returns an empty set if ``identifier`` normalizes to empty.
+    """
+    normalized = normalize_whatsapp_identifier(identifier)
+    if not normalized:
+        return set()
+
+    session_dir = get_hermes_home() / "whatsapp" / "session"
+    resolved: Set[str] = set()
+    queue = [normalized]
+
+    while queue:
+        current = queue.pop(0)
+        if not current or current in resolved:
+            continue
+
+        resolved.add(current)
+        for suffix in ("", "_reverse"):
+            mapping_path = session_dir / f"lid-mapping-{current}{suffix}.json"
+            if not mapping_path.exists():
+                continue
+            try:
+                mapped = normalize_whatsapp_identifier(
+                    json.loads(mapping_path.read_text(encoding="utf-8"))
+                )
+            except Exception:
+                continue
+            if mapped and mapped not in resolved:
+                queue.append(mapped)
+
+    return resolved
+
+
+def canonical_whatsapp_identifier(identifier: str) -> str:
+    """Return a stable WhatsApp sender identity across phone-JID/LID variants.
+
+    WhatsApp may surface the same person under either a phone-format JID
+    (``60123456789@s.whatsapp.net``) or a LID (``1234567890@lid``). This
+    applies to a DM ``chat_id`` *and* to the ``participant_id`` of a
+    member inside a group chat — both represent a user identity, and the
+    bridge may flip between the two for the same human.
+
+    This helper reads the bridge's ``whatsapp/session/lid-mapping-*.json``
+    files, walks the mapping transitively, and picks the shortest
+    (numeric-preferred) alias as the canonical identity.
+    :func:`gateway.session.build_session_key` uses this for both WhatsApp
+    DM chat_ids and WhatsApp group participant_ids, so callers get the
+    same session-key identity Hermes itself uses.
+
+    Plugins that need per-sender behaviour (role-based routing,
+    authorisation, per-contact policy) should use this so their
+    bookkeeping lines up with Hermes' session bookkeeping even when
+    the bridge reshuffles aliases.
+
+    Returns an empty string if ``identifier`` normalizes to empty. If no
+    mapping files exist yet (fresh bridge install), returns the
+    normalized input unchanged.
+    """
+    normalized = normalize_whatsapp_identifier(identifier)
+    if not normalized:
+        return ""
+
+    # expand_whatsapp_aliases always includes `normalized` itself in the
+    # returned set, so the min() below degrades gracefully to `normalized`
+    # when no lid-mapping files are present.
+    aliases = expand_whatsapp_aliases(normalized)
+    return min(aliases, key=lambda candidate: (len(candidate), candidate))

hermes_cli/auth_commands.py

@@ -110,18 +110,40 @@ def _display_source(source: str) -> str:
     return source.split(":", 1)[1] if source.startswith("manual:") else source
 
 
+def _classify_exhausted_status(entry) -> tuple[str, bool]:
+    code = getattr(entry, "last_error_code", None)
+    reason = str(getattr(entry, "last_error_reason", "") or "").strip().lower()
+    message = str(getattr(entry, "last_error_message", "") or "").strip().lower()
+
+    if code == 429 or any(token in reason for token in ("rate_limit", "usage_limit", "quota", "exhausted")) or any(
+        token in message for token in ("rate limit", "usage limit", "quota", "too many requests")
+    ):
+        return "rate-limited", True
+
+    if code in {401, 403} or any(token in reason for token in ("invalid_token", "invalid_grant", "unauthorized", "forbidden", "auth")) or any(
+        token in message for token in ("unauthorized", "forbidden", "expired", "revoked", "invalid token", "authentication")
+    ):
+        return "auth failed", False
+
+    return "exhausted", True
+
+
+
 def _format_exhausted_status(entry) -> str:
     if entry.last_status != STATUS_EXHAUSTED:
         return ""
+    label, show_retry_window = _classify_exhausted_status(entry)
     reason = getattr(entry, "last_error_reason", None)
     reason_text = f" {reason}" if isinstance(reason, str) and reason.strip() else ""
     code = f" ({entry.last_error_code})" if entry.last_error_code else ""
+    if not show_retry_window:
+        return f" {label}{reason_text}{code} (re-auth may be required)"
     exhausted_until = _exhausted_until(entry)
     if exhausted_until is None:
-        return f" exhausted{reason_text}{code}"
+        return f" {label}{reason_text}{code}"
     remaining = max(0, int(math.ceil(exhausted_until - time.time())))
     if remaining <= 0:
-        return f" exhausted{reason_text}{code} (ready to retry)"
+        return f" {label}{reason_text}{code} (ready to retry)"
     minutes, seconds = divmod(remaining, 60)
     hours, minutes = divmod(minutes, 60)
     days, hours = divmod(hours, 24)
@@ -133,7 +155,7 @@ def _format_exhausted_status(entry) -> str:
         wait = f"{minutes}m {seconds}s"
     else:
         wait = f"{seconds}s"
-    return f" exhausted{reason_text}{code} ({wait} left)"
+    return f" {label}{reason_text}{code} ({wait} left)"
 
 
 def auth_add_command(args) -> None:
@@ -386,6 +408,44 @@ def auth_reset_command(args) -> None:
     print(f"Reset status on {count} {provider} credentials")
 
 
+def auth_status_command(args) -> None:
+    provider = _normalize_provider(getattr(args, "provider", "") or "")
+    if not provider:
+        raise SystemExit("Provider is required. Example: `hermes auth status spotify`.")
+    status = auth_mod.get_auth_status(provider)
+    if not status.get("logged_in"):
+        reason = status.get("error")
+        if reason:
+            print(f"{provider}: logged out ({reason})")
+        else:
+            print(f"{provider}: logged out")
+        return
+
+    print(f"{provider}: logged in")
+    for key in ("auth_type", "client_id", "redirect_uri", "scope", "expires_at", "api_base_url"):
+        value = status.get(key)
+        if value:
+            print(f"  {key}: {value}")
+
+
+def auth_logout_command(args) -> None:
+    auth_mod.logout_command(SimpleNamespace(provider=getattr(args, "provider", None)))
+
+
+def auth_spotify_command(args) -> None:
+    action = str(getattr(args, "spotify_action", "") or "login").strip().lower()
+    if action in {"", "login"}:
+        auth_mod.login_spotify_command(args)
+        return
+    if action == "status":
+        auth_status_command(SimpleNamespace(provider="spotify"))
+        return
+    if action == "logout":
+        auth_logout_command(SimpleNamespace(provider="spotify"))
+        return
+    raise SystemExit(f"Unknown Spotify auth action: {action}")
+
+
 def _interactive_auth() -> None:
     """Interactive credential pool management when `hermes auth` is called bare."""
     # Show current pool status first
@@ -583,5 +643,14 @@ def auth_command(args) -> None:
     if action == "reset":
         auth_reset_command(args)
         return
+    if action == "status":
+        auth_status_command(args)
+        return
+    if action == "logout":
+        auth_logout_command(args)
+        return
+    if action == "spotify":
+        auth_spotify_command(args)
+        return
     # No subcommand — launch interactive mode
     _interactive_auth()

hermes_cli/azure_detect.py

@@ -0,0 +1,300 @@
+"""Azure Foundry endpoint auto-detection.
+
+Inspect an Azure AI Foundry / Azure OpenAI endpoint to determine:
+  - API transport (OpenAI-style ``chat_completions`` vs
+    Anthropic-style ``anthropic_messages``)
+  - Available models (best effort — Azure does not expose a deployment
+    listing via the inference API key, but Azure OpenAI v1 endpoints
+    return the resource's model catalog via ``GET /models``)
+  - Context length for each discovered/entered model, via the existing
+    :func:`agent.model_metadata.get_model_context_length` resolver.
+
+Rationale:
+
+Azure has no pure-API-key deployment-listing endpoint — per Microsoft,
+deployment enumeration requires ARM management-plane auth.  Azure
+OpenAI v1 endpoints ``{resource}.openai.azure.com/openai/v1`` do return
+a ``/models`` list, but it reflects the resource's *available* models
+rather than the user's *deployed* deployment names.  In practice it is
+still a useful hint — the user picks a familiar model name and we look
+up its context length from the catalog.
+
+The detector never crashes on errors (every HTTP call is wrapped in a
+broad try/except).  Callers get a :class:`DetectionResult` with whatever
+information could be gathered, and fall back to manual entry for the
+rest.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import re
+from dataclasses import dataclass, field
+from typing import Optional
+from urllib import request as urllib_request
+from urllib.error import HTTPError, URLError
+from urllib.parse import urlparse, urlunparse
+
+logger = logging.getLogger(__name__)
+
+
+# Default Azure OpenAI ``api-version`` to probe with.  The v1 GA endpoint
+# accepts requests without ``api-version`` entirely, so this is only used
+# as a fallback for pre-v1 resources that still require it.
+_AZURE_OPENAI_PROBE_API_VERSIONS = (
+    "2025-04-01-preview",
+    "2024-10-21",  # oldest GA that supports /models
+)
+
+# Default Azure Anthropic ``api-version``.  Matches the value used by
+# ``agent/anthropic_adapter.py`` when building the Anthropic client.
+_AZURE_ANTHROPIC_API_VERSION = "2025-04-15"
+
+
+@dataclass
+class DetectionResult:
+    """Everything auto-detection could gather from a base URL + API key."""
+
+    #: Detected API transport: ``"chat_completions"``,
+    #: ``"anthropic_messages"``, or ``None`` when detection failed.
+    api_mode: Optional[str] = None
+
+    #: Deployment / model IDs returned by ``/models`` (best effort).
+    #: Empty when the endpoint doesn't expose the list with an API key.
+    models: list[str] = field(default_factory=list)
+
+    #: Lowercased host from the base URL (used for display messages).
+    hostname: str = ""
+
+    #: Human-readable reason the detector chose ``api_mode``.  Useful
+    #: for explaining auto-detection to the user in the wizard.
+    reason: str = ""
+
+    #: ``True`` when ``/models`` returned a valid OpenAI-shaped payload.
+    models_probe_ok: bool = False
+
+    #: ``True`` when the URL was determined to be an Anthropic-style
+    #: endpoint (from path suffix or live probe).
+    is_anthropic: bool = False
+
+
+def _http_get_json(url: str, api_key: str, timeout: float = 6.0) -> tuple[int, Optional[dict]]:
+    """GET a URL with ``api-key`` + ``Authorization`` headers.  Return
+    ``(status_code, parsed_json_or_None)``.  Never raises."""
+    req = urllib_request.Request(url, method="GET")
+    # Azure OpenAI uses ``api-key``.  Some Azure deployments (and
+    # Anthropic-style routes) use ``Authorization: Bearer``.  Send both
+    # so we probe once per URL rather than twice.
+    req.add_header("api-key", api_key)
+    req.add_header("Authorization", f"Bearer {api_key}")
+    req.add_header("User-Agent", "hermes-agent/azure-detect")
+    try:
+        with urllib_request.urlopen(req, timeout=timeout) as resp:
+            body = resp.read()
+            try:
+                return resp.status, json.loads(body.decode("utf-8", errors="replace"))
+            except Exception:
+                return resp.status, None
+    except HTTPError as exc:
+        return exc.code, None
+    except (URLError, TimeoutError, OSError) as exc:
+        logger.debug("azure_detect: GET %s failed: %s", url, exc)
+        return 0, None
+    except Exception as exc:  # pragma: no cover — defensive
+        logger.debug("azure_detect: GET %s unexpected error: %s", url, exc)
+        return 0, None
+
+
+def _strip_trailing_v1(url: str) -> str:
+    """Strip trailing ``/v1`` or ``/v1/`` so we can construct sub-paths."""
+    return re.sub(r"/v1/?$", "", url.rstrip("/"))
+
+
+def _looks_like_anthropic_path(url: str) -> bool:
+    """Return True when the URL's path ends in ``/anthropic`` or
+    contains a ``/anthropic/`` segment.  Used by Azure Foundry
+    resources that route Claude traffic through a dedicated path."""
+    try:
+        parsed = urlparse(url)
+        path = (parsed.path or "").lower().rstrip("/")
+        return path.endswith("/anthropic") or "/anthropic/" in path + "/"
+    except Exception:
+        return False
+
+
+def _extract_model_ids(payload: dict) -> list[str]:
+    """Extract a list of model IDs from an OpenAI-shaped ``/models``
+    response.  Returns ``[]`` on any shape mismatch."""
+    data = payload.get("data") if isinstance(payload, dict) else None
+    if not isinstance(data, list):
+        return []
+    ids: list[str] = []
+    for item in data:
+        if not isinstance(item, dict):
+            continue
+        # OpenAI shape: {"id": "gpt-5.4", "object": "model", ...}
+        mid = item.get("id") or item.get("model") or item.get("name")
+        if isinstance(mid, str) and mid:
+            ids.append(mid)
+    return ids
+
+
+def _probe_openai_models(base_url: str, api_key: str) -> tuple[bool, list[str]]:
+    """Probe ``<base>/models`` for an OpenAI-shaped response.
+
+    Returns ``(ok, models)``.  ``ok`` is True iff the endpoint accepted
+    us as an OpenAI-style caller (200 OK + OpenAI-shaped JSON body).
+    """
+    base_url = base_url.rstrip("/")
+
+    # Azure OpenAI v1: {resource}.openai.azure.com/openai/v1 — no
+    # api-version required for GA paths, so probe without first.
+    candidates = [f"{base_url}/models"]
+    # Fallback: explicit api-version for pre-v1 resources
+    for v in _AZURE_OPENAI_PROBE_API_VERSIONS:
+        candidates.append(f"{base_url}/models?api-version={v}")
+
+    for url in candidates:
+        status, body = _http_get_json(url, api_key)
+        if status == 200 and body is not None:
+            ids = _extract_model_ids(body)
+            if ids:
+                logger.info(
+                    "azure_detect: /models probe OK at %s (%d models)",
+                    url, len(ids),
+                )
+                return True, ids
+            # 200 + empty list still counts as "OpenAI shape, no models
+            # listed" — let the user proceed with manual entry.
+            if isinstance(body, dict) and "data" in body:
+                return True, []
+    return False, []
+
+
+def _probe_anthropic_messages(base_url: str, api_key: str) -> bool:
+    """Send a zero-token request to ``<base>/v1/messages`` and check
+    whether the endpoint at least *recognises* the Anthropic Messages
+    shape (any 4xx that mentions ``messages`` or ``model``, or a 400
+    ``invalid_request`` with an Anthropic error shape).  Never completes
+    a real chat.
+    """
+    base = _strip_trailing_v1(base_url)
+    url = f"{base}/v1/messages?api-version={_AZURE_ANTHROPIC_API_VERSION}"
+    payload = json.dumps({
+        "model": "probe",
+        "max_tokens": 1,
+        "messages": [{"role": "user", "content": "ping"}],
+    }).encode("utf-8")
+    req = urllib_request.Request(url, method="POST", data=payload)
+    req.add_header("api-key", api_key)
+    req.add_header("Authorization", f"Bearer {api_key}")
+    req.add_header("anthropic-version", "2023-06-01")
+    req.add_header("content-type", "application/json")
+    req.add_header("User-Agent", "hermes-agent/azure-detect")
+    try:
+        with urllib_request.urlopen(req, timeout=6.0) as resp:
+            # Should never 200 — "probe" isn't a real deployment.  But
+            # if it does, the endpoint definitely speaks Anthropic.
+            return resp.status < 500
+    except HTTPError as exc:
+        # 4xx with an Anthropic-shaped error body = Anthropic endpoint.
+        try:
+            body = exc.read().decode("utf-8", errors="replace")
+            lowered = body.lower()
+            if "anthropic" in lowered or '"type"' in lowered and '"error"' in lowered:
+                return True
+            # Pre-Azure-v1 Azure Foundry returns a plain 404 for
+            # Anthropic-style calls on non-Anthropic deployments.  A
+            # 400 "model not found" IS Anthropic though.
+            if exc.code == 400 and ("messages" in lowered or "model" in lowered):
+                return True
+            return False
+        except Exception:
+            return False
+    except (URLError, TimeoutError, OSError):
+        return False
+    except Exception:  # pragma: no cover
+        return False
+
+
+def detect(base_url: str, api_key: str) -> DetectionResult:
+    """Inspect an Azure endpoint and describe its transport + models.
+
+    Call this from the wizard before asking the user to pick an API
+    mode manually.  The caller should treat the returned
+    :class:`DetectionResult` as *advisory* — if ``api_mode`` is None,
+    fall back to asking the user.
+    """
+    result = DetectionResult()
+
+    try:
+        parsed = urlparse(base_url)
+        result.hostname = (parsed.hostname or "").lower()
+    except Exception:
+        result.hostname = ""
+
+    # 1. Path sniff.  Azure Foundry exposes Anthropic-style deployments
+    #    under a dedicated ``/anthropic`` path.
+    if _looks_like_anthropic_path(base_url):
+        result.is_anthropic = True
+        result.api_mode = "anthropic_messages"
+        result.reason = "URL path ends in /anthropic → Anthropic Messages API"
+        return result
+
+    # 2. Try the OpenAI-style /models probe.  If this works, the
+    #    endpoint definitely speaks OpenAI wire.
+    ok, models = _probe_openai_models(base_url, api_key)
+    if ok:
+        result.models_probe_ok = True
+        result.models = models
+        result.api_mode = "chat_completions"
+        result.reason = (
+            f"GET /models returned {len(models)} model(s) — OpenAI-style endpoint"
+            if models
+            else "GET /models returned an OpenAI-shaped empty list — OpenAI-style endpoint"
+        )
+        return result
+
+    # 3. Fallback: probe the Anthropic Messages shape.  Slower and more
+    #    intrusive than /models, so only run it when the OpenAI probe
+    #    failed.
+    if _probe_anthropic_messages(base_url, api_key):
+        result.is_anthropic = True
+        result.api_mode = "anthropic_messages"
+        result.reason = "Endpoint accepts Anthropic Messages shape"
+        return result
+
+    # Nothing matched.  Caller falls back to manual selection.
+    result.reason = (
+        "Could not probe endpoint (private network, missing model list, or "
+        "non-standard path) — falling back to manual API-mode selection"
+    )
+    return result
+
+
+def lookup_context_length(model: str, base_url: str, api_key: str) -> Optional[int]:
+    """Thin wrapper around :func:`agent.model_metadata.get_model_context_length`
+    that returns ``None`` when only the fallback default (128k) would
+    fire, so the wizard can distinguish "we actually know this" from
+    "we guessed."""
+    try:
+        from agent.model_metadata import (
+            DEFAULT_FALLBACK_CONTEXT,
+            get_model_context_length,
+        )
+    except Exception:
+        return None
+
+    try:
+        n = get_model_context_length(model, base_url=base_url, api_key=api_key)
+    except Exception as exc:
+        logger.debug("azure_detect: context length lookup failed: %s", exc)
+        return None
+
+    if isinstance(n, int) and n > 0 and n != DEFAULT_FALLBACK_CONTEXT:
+        return n
+    return None
+
+
+__all__ = ["DetectionResult", "detect", "lookup_context_length"]

hermes_cli/banner.py

@@ -238,6 +238,52 @@ def get_git_banner_state(repo_dir: Optional[Path] = None) -> Optional[dict]:
     return {"upstream": upstream, "local": local, "ahead": max(ahead, 0)}
 
 
+_RELEASE_URL_BASE = "https://github.com/NousResearch/hermes-agent/releases/tag"
+_latest_release_cache: Optional[tuple] = None  # (tag, url) once resolved
+
+
+def get_latest_release_tag(repo_dir: Optional[Path] = None) -> Optional[tuple]:
+    """Return ``(tag, release_url)`` for the latest git tag, or None.
+
+    Local-only — runs ``git describe --tags --abbrev=0`` against the
+    Hermes checkout. Cached per-process. Release URL always points at the
+    canonical NousResearch/hermes-agent repo (forks don't get a link).
+    """
+    global _latest_release_cache
+    if _latest_release_cache is not None:
+        return _latest_release_cache or None
+
+    repo_dir = repo_dir or _resolve_repo_dir()
+    if repo_dir is None:
+        _latest_release_cache = ()  # falsy sentinel — skip future lookups
+        return None
+
+    try:
+        result = subprocess.run(
+            ["git", "describe", "--tags", "--abbrev=0"],
+            capture_output=True,
+            text=True,
+            timeout=3,
+            cwd=str(repo_dir),
+        )
+    except Exception:
+        _latest_release_cache = ()
+        return None
+
+    if result.returncode != 0:
+        _latest_release_cache = ()
+        return None
+
+    tag = (result.stdout or "").strip()
+    if not tag:
+        _latest_release_cache = ()
+        return None
+
+    url = f"{_RELEASE_URL_BASE}/{tag}"
+    _latest_release_cache = (tag, url)
+    return _latest_release_cache
+
+
 def format_banner_version_label() -> str:
     """Return the version label shown in the startup banner title."""
     base = f"Hermes Agent v{VERSION} ({RELEASE_DATE})"
@@ -519,9 +565,16 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
     agent_name = _skin_branding("agent_name", "Hermes Agent")
     title_color = _skin_color("banner_title", "#FFD700")
     border_color = _skin_color("banner_border", "#CD7F32")
+    version_label = format_banner_version_label()
+    release_info = get_latest_release_tag()
+    if release_info:
+        _tag, _url = release_info
+        title_markup = f"[bold {title_color}][link={_url}]{version_label}[/link][/]"
+    else:
+        title_markup = f"[bold {title_color}]{version_label}[/]"
     outer_panel = Panel(
         layout_table,
-        title=f"[bold {title_color}]{format_banner_version_label()}[/]",
+        title=title_markup,
         border_style=border_color,
         padding=(0, 2),
     )

hermes_cli/commands.py

@@ -77,16 +77,14 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("rollback", "List or restore filesystem checkpoints", "Session",
                args_hint="[number]"),
     CommandDef("snapshot", "Create or restore state snapshots of Hermes config/state", "Session",
-               aliases=("snap",), args_hint="[create|restore <id>|prune]"),
+               cli_only=True, aliases=("snap",), args_hint="[create|restore <id>|prune]"),
     CommandDef("stop", "Kill all running background processes", "Session"),
     CommandDef("approve", "Approve a pending dangerous command", "Session",
                gateway_only=True, args_hint="[session|always]"),
     CommandDef("deny", "Deny a pending dangerous command", "Session",
                gateway_only=True),
     CommandDef("background", "Run a prompt in the background", "Session",
-               aliases=("bg",), args_hint="<prompt>"),
-    CommandDef("btw", "Ephemeral side question using session context (no tools, not persisted)", "Session",
-               args_hint="<question>"),
+               aliases=("bg", "btw"), args_hint="<prompt>"),
     CommandDef("agents", "Show active agents and running tasks", "Session",
                aliases=("tasks",)),
     CommandDef("queue", "Queue a prompt for the next turn (doesn't interrupt)", "Session",
@@ -103,10 +101,10 @@ COMMAND_REGISTRY: list[CommandDef] = [
     # Configuration
     CommandDef("config", "Show current configuration", "Configuration",
                cli_only=True),
-    CommandDef("model", "Switch model for this session", "Configuration", args_hint="[model] [--provider name] [--global]"),
-    CommandDef("provider", "Show available providers and current provider",
-               "Configuration"),
-    CommandDef("gquota", "Show Google Gemini Code Assist quota usage", "Info"),
+    CommandDef("model", "Switch model for this session", "Configuration",
+               aliases=("provider",), args_hint="[model] [--provider name] [--global]"),
+    CommandDef("gquota", "Show Google Gemini Code Assist quota usage", "Info",
+               cli_only=True),
 
     CommandDef("personality", "Set a predefined personality", "Configuration",
                args_hint="[name]"),
@@ -124,9 +122,12 @@ COMMAND_REGISTRY: list[CommandDef] = [
                args_hint="[normal|fast|status]",
                subcommands=("normal", "fast", "status", "on", "off")),
     CommandDef("skin", "Show or change the display skin/theme", "Configuration",
-               args_hint="[name]"),
+               cli_only=True, args_hint="[name]"),
     CommandDef("voice", "Toggle voice mode", "Configuration",
                args_hint="[on|off|tts|status]", subcommands=("on", "off", "tts", "status")),
+    CommandDef("busy", "Control what Enter does while Hermes is working", "Configuration",
+               cli_only=True, args_hint="[queue|interrupt|status]",
+               subcommands=("queue", "interrupt", "status")),
 
     # Tools & Skills
     CommandDef("tools", "Manage tools: /tools [list|disable|enable] [name...]", "Tools & Skills",
@@ -139,7 +140,13 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("cron", "Manage scheduled tasks", "Tools & Skills",
                cli_only=True, args_hint="[subcommand]",
                subcommands=("list", "add", "create", "edit", "pause", "resume", "run", "remove")),
-    CommandDef("reload", "Reload .env variables into the running session", "Tools & Skills"),
+    CommandDef("kanban", "Multi-profile collaboration board (tasks, links, comments)",
+               "Tools & Skills", args_hint="[subcommand]",
+               subcommands=("list", "ls", "show", "create", "assign", "link", "unlink",
+                            "claim", "comment", "complete", "block", "unblock", "archive",
+                            "tail", "dispatch", "context", "init", "gc")),
+    CommandDef("reload", "Reload .env variables into the running session", "Tools & Skills",
+               cli_only=True),
     CommandDef("reload-mcp", "Reload MCP servers from config", "Tools & Skills",
                aliases=("reload_mcp",)),
     CommandDef("browser", "Connect browser tools to your live Chrome via CDP", "Tools & Skills",
@@ -317,7 +324,7 @@ def should_bypass_active_session(command_name: str | None) -> bool:
     safety net in gateway.run discards any command text that reaches
     the pending queue — which meant a mid-run /model (or /reasoning,
     /voice, /insights, /title, /resume, /retry, /undo, /compress,
-    /usage, /provider, /reload-mcp, /sethome, /reset) would silently
+    /usage, /reload-mcp, /sethome, /reset) would silently
     interrupt the agent AND get discarded, producing a zero-char
     response. See issue #5057 / PRs #6252, #10370, #4665.
 

hermes_cli/config.py

@@ -466,6 +466,12 @@ DEFAULT_CONFIG = {
         "record_sessions": False,  # Auto-record browser sessions as WebM videos
         "allow_private_urls": False,  # Allow navigating to private/internal IPs (localhost, 192.168.x.x, etc.)
         "cdp_url": "",  # Optional persistent CDP endpoint for attaching to an existing Chromium/Chrome
+        # CDP supervisor — dialog + frame detection via a persistent WebSocket.
+        # Active only when a CDP-capable backend is attached (Browserbase or
+        # local Chrome via /browser connect). See
+        # website/docs/developer-guide/browser-supervisor.md.
+        "dialog_policy": "must_respond",  # must_respond | auto_dismiss | auto_accept
+        "dialog_timeout_s": 300,  # Safety auto-dismiss after N seconds under must_respond
         "camofox": {
             # When true, Hermes sends a stable profile-scoped userId to Camofox
             # so the server maps it to a persistent Firefox profile automatically.
@@ -486,7 +492,27 @@ DEFAULT_CONFIG = {
     # exceed this are rejected with guidance to use offset+limit.
     # 100K chars ≈ 25–35K tokens across typical tokenisers.
     "file_read_max_chars": 100_000,
-    
+
+    # Tool-output truncation thresholds. When terminal output or a
+    # single read_file page exceeds these limits, Hermes truncates the
+    # payload sent to the model (keeping head + tail for terminal,
+    # enforcing pagination for read_file). Tuning these trades context
+    # footprint against how much raw output the model can see in one
+    # shot. Ported from anomalyco/opencode PR #23770.
+    #
+    # - max_bytes:       terminal_tool output cap, in chars
+    #                    (default 50_000 ≈ 12-15K tokens).
+    # - max_lines:       read_file pagination cap — the maximum `limit`
+    #                    a single read_file call can request before
+    #                    being clamped (default 2000).
+    # - max_line_length: per-line cap applied when read_file emits a
+    #                    line-numbered view (default 2000 chars).
+    "tool_output": {
+        "max_bytes": 50_000,
+        "max_lines": 2000,
+        "max_line_length": 2000,
+    },
+
     "compression": {
         "enabled": True,
         "threshold": 0.50,            # compress when context usage exceeds this ratio
@@ -495,6 +521,12 @@ DEFAULT_CONFIG = {
 
     },
 
+    # Anthropic prompt caching (Claude via OpenRouter or native Anthropic API).
+    # cache_ttl must be "5m" or "1h" (Anthropic-supported tiers); other values are ignored.
+    "prompt_caching": {
+        "cache_ttl": "5m",
+    },
+
     # AWS Bedrock provider configuration.
     # Only used when model.provider is "bedrock".
     "bedrock": {
@@ -580,14 +612,6 @@ DEFAULT_CONFIG = {
             "timeout": 30,
             "extra_body": {},
         },
-        "flush_memories": {
-            "provider": "auto",
-            "model": "",
-            "base_url": "",
-            "api_key": "",
-            "timeout": 30,
-            "extra_body": {},
-        },
         "title_generation": {
             "provider": "auto",
             "model": "",
@@ -751,6 +775,15 @@ DEFAULT_CONFIG = {
         # warning log if out of range.
         "max_spawn_depth": 1,        # depth cap (1 = flat [default], 2 = orchestrator→leaf, 3 = three-level)
         "orchestrator_enabled": True,  # kill switch for role="orchestrator"
+        # When a subagent hits a dangerous-command approval prompt, the parent's
+        # prompt_toolkit TUI owns stdin — a thread-local input() call from the
+        # subagent worker would deadlock the parent UI. To avoid the deadlock,
+        # subagent threads ALWAYS resolve approvals non-interactively:
+        #   false (default) → auto-deny with a logger.warning audit line (safe)
+        #   true             → auto-approve "once" with a logger.warning audit line
+        # Flip to true only if you trust delegated work to run dangerous cmds
+        # without human review (cron pipelines, batch automation, etc.).
+        "subagent_auto_approve": False,
     },
 
     # Ephemeral prefill messages file — JSON list of {role, content} dicts
@@ -807,7 +840,7 @@ DEFAULT_CONFIG = {
         "auto_thread": True,           # Auto-create threads on @mention in channels (like Slack)
         "reactions": True,             # Add 👀/✅/❌ reactions to messages during processing
         "channel_prompts": {},         # Per-channel ephemeral system prompts (forum parents apply to child threads)
-        # discord_server tool: restrict which actions the agent may call.
+        # discord / discord_admin tools: restrict which actions the agent may call.
         # Default (empty) = all actions allowed (subject to bot privileged intents).
         # Accepts comma-separated string ("list_guilds,list_channels,fetch_messages")
         # or YAML list. Unknown names are dropped with a warning at load time.
@@ -904,6 +937,24 @@ DEFAULT_CONFIG = {
         "max_parallel_jobs": None,
     },
 
+    # Kanban multi-agent coordination — controls the dispatcher loop that
+    # spawns workers for ready tasks. The dispatcher ticks every N seconds
+    # (default 60), reclaims stale claims, promotes dependency-satisfied
+    # todos to ready, and fires `hermes -p <assignee> chat -q ...` for
+    # each claimable ready task. One dispatcher per profile is sufficient;
+    # running more than one on the same kanban.db will race for claims.
+    "kanban": {
+        # Run the dispatcher inside the gateway process. On by default —
+        # the cost is ~300µs every `dispatch_interval_seconds` when idle,
+        # and gateway is the supervisor users already have. Set to false
+        # only if you run the dispatcher as a separate systemd unit or
+        # don't want the gateway to spawn workers.
+        "dispatch_in_gateway": True,
+        # Seconds between dispatcher ticks (idle or not). Lower = snappier
+        # pickup of newly-ready tasks; higher = less SQL pressure.
+        "dispatch_interval_seconds": 60,
+    },
+
     # execute_code settings — controls the tool used for programmatic tool calls.
     "code_execution": {
         # Execution mode:
@@ -926,6 +977,27 @@ DEFAULT_CONFIG = {
         "backup_count": 3,     # Number of rotated backup files to keep
     },
 
+    # Remotely-hosted model catalog manifest.  When enabled, the CLI fetches
+    # curated model lists for OpenRouter and Nous Portal from this URL,
+    # falling back to the in-repo snapshot on network failure.  Lets us
+    # update model picker lists without shipping a hermes-agent release.
+    # The default URL is served by the docs site GitHub Pages deploy.
+    "model_catalog": {
+        "enabled": True,
+        "url": "https://hermes-agent.nousresearch.com/docs/api/model-catalog.json",
+        # Disk cache TTL in hours.  Beyond this, the CLI refetches on the
+        # next /model or `hermes model` invocation; network failures
+        # silently fall back to the stale cache.
+        "ttl_hours": 24,
+        # Optional per-provider override URLs for third parties that want
+        # to self-host their own curation list using the same schema.
+        # Example:
+        #   providers:
+        #     openrouter:
+        #       url: https://example.com/my-curation.json
+        "providers": {},
+    },
+
     # Network settings — workarounds for connectivity issues.
     "network": {
         # Force IPv4 connections.  On servers with broken or unreachable IPv6,
@@ -962,6 +1034,13 @@ DEFAULT_CONFIG = {
         "min_interval_hours": 24,
     },
 
+    # Contextual first-touch onboarding hints (see agent/onboarding.py).
+    # Each hint is shown once per install and then latched here so it
+    # never fires again.  Users can wipe the section to re-see all hints.
+    "onboarding": {
+        "seen": {},
+    },
+
     # Config schema version - bump this when adding new required fields
     "_config_version": 22,
 }
@@ -1338,6 +1417,21 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
+    "AZURE_FOUNDRY_API_KEY": {
+        "description": "Azure Foundry API key for custom Azure endpoints",
+        "prompt": "Azure Foundry API Key",
+        "url": "https://ai.azure.com/",
+        "password": True,
+        "category": "provider",
+    },
+    "AZURE_FOUNDRY_BASE_URL": {
+        "description": "Azure Foundry base URL (set via 'hermes model' for endpoint-specific config)",
+        "prompt": "Azure Foundry base URL",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
 
     # ── Tool API keys ──
     "EXA_API_KEY": {
@@ -2173,6 +2267,71 @@ def get_compatible_custom_providers(
     return compatible
 
 
+def get_custom_provider_context_length(
+    model: str,
+    base_url: str,
+    custom_providers: Optional[List[Dict[str, Any]]] = None,
+    config: Optional[Dict[str, Any]] = None,
+) -> Optional[int]:
+    """Look up a per-model ``context_length`` override from ``custom_providers``.
+
+    Matches any entry whose ``base_url`` equals ``base_url`` (trailing-slash
+    insensitive) and returns ``custom_providers[i].models.<model>.context_length``
+    if present and valid.  Returns ``None`` when no override applies.
+
+    This is the single source of truth for custom-provider context overrides,
+    used by:
+      * ``AIAgent.__init__`` (startup resolution)
+      * ``AIAgent.switch_model`` (mid-session ``/model`` switch)
+      * ``hermes_cli.model_switch.resolve_display_context_length`` (``/model`` confirmation display)
+      * ``gateway.run._format_session_info`` (``/info`` display)
+      * ``agent.model_metadata.get_model_context_length`` (when custom_providers is threaded through)
+
+    Before this helper existed, the lookup was duplicated in ``run_agent.py``'s
+    startup path only; every other path (notably ``/model`` switch) fell back
+    to the 128K default.  See #15779.
+    """
+    if not model or not base_url:
+        return None
+    if custom_providers is None:
+        try:
+            custom_providers = get_compatible_custom_providers(config)
+        except Exception:
+            if config is None:
+                return None
+            raw = config.get("custom_providers")
+            custom_providers = raw if isinstance(raw, list) else []
+    if not isinstance(custom_providers, list):
+        return None
+
+    target_url = (base_url or "").rstrip("/")
+    if not target_url:
+        return None
+
+    for entry in custom_providers:
+        if not isinstance(entry, dict):
+            continue
+        entry_url = (entry.get("base_url") or "").rstrip("/")
+        if not entry_url or entry_url != target_url:
+            continue
+        models = entry.get("models")
+        if not isinstance(models, dict):
+            continue
+        model_cfg = models.get(model)
+        if not isinstance(model_cfg, dict):
+            continue
+        raw_ctx = model_cfg.get("context_length")
+        if raw_ctx is None:
+            continue
+        try:
+            ctx = int(raw_ctx)
+        except (TypeError, ValueError):
+            continue
+        if ctx > 0:
+            return ctx
+    return None
+
+
 def check_config_version() -> Tuple[int, int]:
     """
     Check config version.

hermes_cli/copilot_auth.py

@@ -275,6 +275,99 @@ def copilot_device_code_login(
     return None
 
 
+# ─── Copilot Token Exchange ────────────────────────────────────────────────
+
+# Module-level cache for exchanged Copilot API tokens.
+# Maps raw_token_fingerprint -> (api_token, expires_at_epoch).
+_jwt_cache: dict[str, tuple[str, float]] = {}
+_JWT_REFRESH_MARGIN_SECONDS = 120  # refresh 2 min before expiry
+
+# Token exchange endpoint and headers (matching VS Code / Copilot CLI)
+_TOKEN_EXCHANGE_URL = "https://api.github.com/copilot_internal/v2/token"
+_EDITOR_VERSION = "vscode/1.104.1"
+_EXCHANGE_USER_AGENT = "GitHubCopilotChat/0.26.7"
+
+
+def _token_fingerprint(raw_token: str) -> str:
+    """Short fingerprint of a raw token for cache keying (avoids storing full token)."""
+    import hashlib
+    return hashlib.sha256(raw_token.encode()).hexdigest()[:16]
+
+
+def exchange_copilot_token(raw_token: str, *, timeout: float = 10.0) -> tuple[str, float]:
+    """Exchange a raw GitHub token for a short-lived Copilot API token.
+
+    Calls ``GET https://api.github.com/copilot_internal/v2/token`` with
+    the raw GitHub token and returns ``(api_token, expires_at)``.
+
+    The returned token is a semicolon-separated string (not a standard JWT)
+    used as ``Authorization: Bearer <token>`` for Copilot API requests.
+
+    Results are cached in-process and reused until close to expiry.
+    Raises ``ValueError`` on failure.
+    """
+    import urllib.request
+
+    fp = _token_fingerprint(raw_token)
+
+    # Check cache first
+    cached = _jwt_cache.get(fp)
+    if cached:
+        api_token, expires_at = cached
+        if time.time() < expires_at - _JWT_REFRESH_MARGIN_SECONDS:
+            return api_token, expires_at
+
+    req = urllib.request.Request(
+        _TOKEN_EXCHANGE_URL,
+        method="GET",
+        headers={
+            "Authorization": f"token {raw_token}",
+            "User-Agent": _EXCHANGE_USER_AGENT,
+            "Accept": "application/json",
+            "Editor-Version": _EDITOR_VERSION,
+        },
+    )
+
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            data = json.loads(resp.read().decode())
+    except Exception as exc:
+        raise ValueError(f"Copilot token exchange failed: {exc}") from exc
+
+    api_token = data.get("token", "")
+    expires_at = data.get("expires_at", 0)
+    if not api_token:
+        raise ValueError("Copilot token exchange returned empty token")
+
+    # Convert expires_at to float if needed
+    expires_at = float(expires_at) if expires_at else time.time() + 1800
+
+    _jwt_cache[fp] = (api_token, expires_at)
+    logger.debug(
+        "Copilot token exchanged, expires_at=%s",
+        expires_at,
+    )
+    return api_token, expires_at
+
+
+def get_copilot_api_token(raw_token: str) -> str:
+    """Exchange a raw GitHub token for a Copilot API token, with fallback.
+
+    Convenience wrapper: returns the exchanged token on success, or the
+    raw token unchanged if the exchange fails (e.g. network error, unsupported
+    account type). This preserves existing behaviour for accounts that don't
+    need exchange while enabling access to internal-only models for those that do.
+    """
+    if not raw_token:
+        return raw_token
+    try:
+        api_token, _ = exchange_copilot_token(raw_token)
+        return api_token
+    except Exception as exc:
+        logger.debug("Copilot token exchange failed, using raw token: %s", exc)
+        return raw_token
+
+
 # ─── Copilot API Headers ───────────────────────────────────────────────────
 
 def copilot_request_headers(

hermes_cli/cron.py

@@ -93,6 +93,9 @@ def cron_list(show_all: bool = False):
         script = job.get("script")
         if script:
             print(f"    Script:    {script}")
+        workdir = job.get("workdir")
+        if workdir:
+            print(f"    Workdir:   {workdir}")
 
         # Execution history
         last_status = job.get("last_status")
@@ -168,6 +171,7 @@ def cron_create(args):
         skill=getattr(args, "skill", None),
         skills=_normalize_skills(getattr(args, "skill", None), getattr(args, "skills", None)),
         script=getattr(args, "script", None),
+        workdir=getattr(args, "workdir", None),
     )
     if not result.get("success"):
         print(color(f"Failed to create job: {result.get('error', 'unknown error')}", Colors.RED))
@@ -180,6 +184,8 @@ def cron_create(args):
     job_data = result.get("job", {})
     if job_data.get("script"):
         print(f"  Script: {job_data['script']}")
+    if job_data.get("workdir"):
+        print(f"  Workdir: {job_data['workdir']}")
     print(f"  Next run: {result['next_run_at']}")
     return 0
 
@@ -218,6 +224,7 @@ def cron_edit(args):
         repeat=getattr(args, "repeat", None),
         skills=final_skills,
         script=getattr(args, "script", None),
+        workdir=getattr(args, "workdir", None),
     )
     if not result.get("success"):
         print(color(f"Failed to update job: {result.get('error', 'unknown error')}", Colors.RED))
@@ -233,6 +240,8 @@ def cron_edit(args):
         print("  Skills: none")
     if updated.get("script"):
         print(f"  Script: {updated['script']}")
+    if updated.get("workdir"):
+        print(f"  Workdir: {updated['workdir']}")
     return 0
 
 

hermes_cli/doctor.py

@@ -29,6 +29,7 @@ if _env_path.exists():
 load_dotenv(PROJECT_ROOT / ".env", override=False, encoding="utf-8")
 
 from hermes_cli.colors import Colors, color
+from hermes_cli.models import _HERMES_USER_AGENT
 from hermes_constants import OPENROUTER_MODELS_URL
 from utils import base_url_host_matches
 
@@ -295,16 +296,37 @@ def run_doctor(args):
             except Exception:
                 pass
             try:
-                from hermes_cli.auth import resolve_provider as _resolve_provider
+                from hermes_cli.config import get_compatible_custom_providers as _compatible_custom_providers
+                from hermes_cli.providers import resolve_provider_full as _resolve_provider_full
             except Exception:
-                _resolve_provider = None
+                _compatible_custom_providers = None
+                _resolve_provider_full = None
+
+            custom_providers = []
+            if _compatible_custom_providers is not None:
+                try:
+                    custom_providers = _compatible_custom_providers(cfg)
+                except Exception:
+                    custom_providers = []
+
+            user_providers = cfg.get("providers")
+            if isinstance(user_providers, dict):
+                known_providers.update(str(name).strip().lower() for name in user_providers if str(name).strip())
+            for entry in custom_providers:
+                if not isinstance(entry, dict):
+                    continue
+                name = str(entry.get("name") or "").strip()
+                if name:
+                    known_providers.add("custom:" + name.lower().replace(" ", "-"))
 
             canonical_provider = provider
-            if provider and _resolve_provider is not None and provider != "auto":
-                try:
-                    canonical_provider = _resolve_provider(provider)
-                except Exception:
-                    canonical_provider = None
+            if (
+                provider
+                and _resolve_provider_full is not None
+                and provider not in ("auto", "custom")
+            ):
+                provider_def = _resolve_provider_full(provider, user_providers, custom_providers)
+                canonical_provider = provider_def.id if provider_def is not None else None
 
             if provider and provider != "auto":
                 if canonical_provider is None or (known_providers and canonical_provider not in known_providers):
@@ -957,7 +979,10 @@ def run_doctor(args):
                 if base_url_host_matches(_base, "api.kimi.com") and _base.rstrip("/").endswith("/coding"):
                     _base = _base.rstrip("/") + "/v1"
                 _url = (_base.rstrip("/") + "/models") if _base else _default_url
-                _headers = {"Authorization": f"Bearer {_key}"}
+                _headers = {
+                    "Authorization": f"Bearer {_key}",
+                    "User-Agent": _HERMES_USER_AGENT,
+                }
                 if base_url_host_matches(_base, "api.kimi.com"):
                     _headers["User-Agent"] = "claude-code/0.1.0"
                 _resp = httpx.get(

hermes_cli/dump.py

@@ -267,6 +267,8 @@ def run_dump(args):
         ("ANTHROPIC_API_KEY", "anthropic"),
         ("ANTHROPIC_TOKEN", "anthropic_token"),
         ("NOUS_API_KEY", "nous"),
+        ("GOOGLE_API_KEY", "google/gemini"),
+        ("GEMINI_API_KEY", "gemini"),
         ("GLM_API_KEY", "glm/zai"),
         ("ZAI_API_KEY", "zai"),
         ("KIMI_API_KEY", "kimi"),

hermes_cli/fallback_cmd.py

@@ -0,0 +1,361 @@
+"""
+hermes fallback — manage the fallback provider chain.
+
+Fallback providers are tried in order when the primary model fails with
+rate-limit, overload, or connection errors. See:
+https://hermes-agent.nousresearch.com/docs/user-guide/features/fallback-providers
+
+Subcommands:
+  hermes fallback [list]   Show the current fallback chain (default when no subcommand)
+  hermes fallback add      Pick provider + model via the same picker as `hermes model`,
+                           then append the selection to the chain
+  hermes fallback remove   Pick an entry to delete from the chain
+  hermes fallback clear    Remove all fallback entries
+
+Storage: ``fallback_providers`` in ``~/.hermes/config.yaml`` (top-level, list of
+``{provider, model, base_url?, api_mode?}`` dicts).  The legacy single-dict
+``fallback_model`` format is migrated to the new list format on first add.
+"""
+from __future__ import annotations
+
+import copy
+from typing import Any, Dict, List, Optional
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _read_chain(config: Dict[str, Any]) -> List[Dict[str, Any]]:
+    """Return the normalized fallback chain as a list of dicts.
+
+    Accepts both the new list format (``fallback_providers``) and the legacy
+    single-dict format (``fallback_model``).  The returned list is always a
+    fresh copy — callers can mutate without touching the config dict.
+    """
+    chain = config.get("fallback_providers") or []
+    if isinstance(chain, list):
+        result = [dict(e) for e in chain if isinstance(e, dict) and e.get("provider") and e.get("model")]
+        if result:
+            return result
+    legacy = config.get("fallback_model")
+    if isinstance(legacy, dict) and legacy.get("provider") and legacy.get("model"):
+        return [dict(legacy)]
+    if isinstance(legacy, list):
+        return [dict(e) for e in legacy if isinstance(e, dict) and e.get("provider") and e.get("model")]
+    return []
+
+
+def _write_chain(config: Dict[str, Any], chain: List[Dict[str, Any]]) -> None:
+    """Persist the chain to ``fallback_providers`` and clear legacy key."""
+    config["fallback_providers"] = chain
+    # Drop the legacy single-dict key on write so there's only one source of truth.
+    if "fallback_model" in config:
+        config.pop("fallback_model", None)
+
+
+def _format_entry(entry: Dict[str, Any]) -> str:
+    """One-line human-readable rendering of a fallback entry."""
+    provider = entry.get("provider", "?")
+    model = entry.get("model", "?")
+    base = entry.get("base_url")
+    suffix = f"  [{base}]" if base else ""
+    return f"{model}  (via {provider}){suffix}"
+
+
+def _extract_fallback_from_model_cfg(model_cfg: Any) -> Optional[Dict[str, Any]]:
+    """Pull the ``{provider, model, base_url?, api_mode?}`` dict from a ``config["model"]`` snapshot."""
+    if not isinstance(model_cfg, dict):
+        return None
+    provider = (model_cfg.get("provider") or "").strip()
+    # The picker writes the selected model to ``model.default``.
+    model = (model_cfg.get("default") or model_cfg.get("model") or "").strip()
+    if not provider or not model:
+        return None
+    entry: Dict[str, Any] = {"provider": provider, "model": model}
+    base_url = (model_cfg.get("base_url") or "").strip()
+    if base_url:
+        entry["base_url"] = base_url
+    api_mode = (model_cfg.get("api_mode") or "").strip()
+    if api_mode:
+        entry["api_mode"] = api_mode
+    return entry
+
+
+def _snapshot_auth_active_provider() -> Any:
+    """Return the current ``active_provider`` in auth.json, or a sentinel if unavailable."""
+    try:
+        from hermes_cli.auth import _load_auth_store
+        store = _load_auth_store()
+        return store.get("active_provider")
+    except Exception:
+        return None
+
+
+def _restore_auth_active_provider(value: Any) -> None:
+    """Write back a previously snapshotted ``active_provider`` value."""
+    try:
+        from hermes_cli.auth import _auth_store_lock, _load_auth_store, _save_auth_store
+        with _auth_store_lock():
+            store = _load_auth_store()
+            store["active_provider"] = value
+            _save_auth_store(store)
+    except Exception:
+        # Best-effort — if auth.json can't be restored, the user's primary
+        # provider may have been deactivated by the picker.  They can re-run
+        # `hermes model` to fix it.  Don't fail the fallback add.
+        pass
+
+
+# ---------------------------------------------------------------------------
+# Subcommand handlers
+# ---------------------------------------------------------------------------
+
+def cmd_fallback_list(args) -> None:  # noqa: ARG001
+    """Print the current fallback chain."""
+    from hermes_cli.config import load_config
+
+    config = load_config()
+    chain = _read_chain(config)
+
+    print()
+    if not chain:
+        print("  No fallback providers configured.")
+        print()
+        print("  Add one with:  hermes fallback add")
+        print()
+        return
+
+    primary = _describe_primary(config)
+    if primary:
+        print(f"  Primary:   {primary}")
+        print()
+    print(f"  Fallback chain ({len(chain)} {'entry' if len(chain) == 1 else 'entries'}):")
+    for i, entry in enumerate(chain, 1):
+        print(f"    {i}. {_format_entry(entry)}")
+    print()
+    print("  Tried in order when the primary fails (rate-limit, 5xx, connection errors).")
+    print("  Docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/fallback-providers")
+    print()
+
+
+def _describe_primary(config: Dict[str, Any]) -> Optional[str]:
+    """One-line description of the primary model for display purposes."""
+    model_cfg = config.get("model")
+    if isinstance(model_cfg, dict):
+        provider = (model_cfg.get("provider") or "?").strip() or "?"
+        model = (model_cfg.get("default") or model_cfg.get("model") or "?").strip() or "?"
+        return f"{model}  (via {provider})"
+    if isinstance(model_cfg, str) and model_cfg.strip():
+        return model_cfg.strip()
+    return None
+
+
+def cmd_fallback_add(args) -> None:
+    """Launch the same picker as `hermes model`, then append the selection to the chain."""
+    from hermes_cli.main import _require_tty, select_provider_and_model
+    from hermes_cli.config import load_config, save_config
+
+    _require_tty("fallback add")
+
+    # Snapshot BEFORE the picker runs so we can distinguish "user actually
+    # picked something" from "user cancelled" by comparing before/after.
+    before_cfg = load_config()
+    model_before = copy.deepcopy(before_cfg.get("model"))
+    active_provider_before = _snapshot_auth_active_provider()
+
+    print()
+    print("  Adding a fallback provider.  The picker below is the same one used by")
+    print("  `hermes model` — select the provider + model you want as a fallback.")
+    print()
+
+    try:
+        select_provider_and_model(args=args)
+    except SystemExit:
+        # Some provider flows exit on auth failure — restore state and re-raise.
+        _restore_model_cfg(model_before)
+        _restore_auth_active_provider(active_provider_before)
+        raise
+
+    # Read the post-picker state to see what the user selected.
+    after_cfg = load_config()
+    model_after = after_cfg.get("model")
+
+    new_entry = _extract_fallback_from_model_cfg(model_after)
+    if not new_entry:
+        # Picker didn't complete (user cancelled or flow bailed).  Nothing to do.
+        _restore_model_cfg(model_before)
+        _restore_auth_active_provider(active_provider_before)
+        print()
+        print("  No fallback added.")
+        return
+
+    # Picker picked the same thing that's already the primary → nothing changed,
+    # and there's nothing useful to add as a fallback to itself.
+    primary_entry = _extract_fallback_from_model_cfg(model_before)
+    if primary_entry and primary_entry["provider"] == new_entry["provider"] \
+            and primary_entry["model"] == new_entry["model"]:
+        _restore_model_cfg(model_before)
+        _restore_auth_active_provider(active_provider_before)
+        print()
+        print(f"  Selected model matches the current primary ({_format_entry(new_entry)}).")
+        print("  A provider cannot be a fallback for itself — no change.")
+        return
+
+    # Reload the config with the primary restored, then append the new entry
+    # to ``fallback_providers``.  We deliberately re-load (rather than mutating
+    # ``after_cfg``) because the picker may have touched other top-level keys
+    # (custom_providers, providers credentials) that we want to keep.
+    _restore_model_cfg(model_before)
+    _restore_auth_active_provider(active_provider_before)
+
+    final_cfg = load_config()
+    chain = _read_chain(final_cfg)
+
+    # Reject exact-duplicate fallback entries.
+    for existing in chain:
+        if existing.get("provider") == new_entry["provider"] \
+                and existing.get("model") == new_entry["model"]:
+            print()
+            print(f"  {_format_entry(new_entry)} is already in the fallback chain — skipped.")
+            return
+
+    chain.append(new_entry)
+    _write_chain(final_cfg, chain)
+    save_config(final_cfg)
+
+    print()
+    print(f"  Added fallback: {_format_entry(new_entry)}")
+    print(f"  Chain is now {len(chain)} {'entry' if len(chain) == 1 else 'entries'} long.")
+    print()
+    print("  Run `hermes fallback list` to view, or `hermes fallback remove` to delete.")
+
+
+def _restore_model_cfg(model_before: Any) -> None:
+    """Restore ``config["model"]`` to a previously-captured snapshot."""
+    from hermes_cli.config import load_config, save_config
+
+    cfg = load_config()
+    if model_before is None:
+        cfg.pop("model", None)
+    else:
+        cfg["model"] = copy.deepcopy(model_before)
+    save_config(cfg)
+
+
+def cmd_fallback_remove(args) -> None:  # noqa: ARG001
+    """Pick an entry from the chain and remove it."""
+    from hermes_cli.config import load_config, save_config
+
+    config = load_config()
+    chain = _read_chain(config)
+
+    if not chain:
+        print()
+        print("  No fallback providers configured — nothing to remove.")
+        print()
+        return
+
+    choices = [_format_entry(e) for e in chain]
+    choices.append("Cancel")
+
+    try:
+        from hermes_cli.setup import _curses_prompt_choice
+        idx = _curses_prompt_choice("Select a fallback to remove:", choices, 0)
+    except Exception:
+        idx = _numbered_pick("Select a fallback to remove:", choices)
+
+    if idx is None or idx < 0 or idx >= len(chain):
+        print()
+        print("  Cancelled — no change.")
+        return
+
+    removed = chain.pop(idx)
+    _write_chain(config, chain)
+    save_config(config)
+
+    print()
+    print(f"  Removed fallback: {_format_entry(removed)}")
+    if chain:
+        print(f"  Chain is now {len(chain)} {'entry' if len(chain) == 1 else 'entries'} long.")
+    else:
+        print("  Fallback chain is now empty.")
+    print()
+
+
+def cmd_fallback_clear(args) -> None:  # noqa: ARG001
+    """Remove all fallback entries (with confirmation)."""
+    from hermes_cli.config import load_config, save_config
+
+    config = load_config()
+    chain = _read_chain(config)
+
+    if not chain:
+        print()
+        print("  No fallback providers configured — nothing to clear.")
+        print()
+        return
+
+    print()
+    print(f"  Current fallback chain ({len(chain)} {'entry' if len(chain) == 1 else 'entries'}):")
+    for i, entry in enumerate(chain, 1):
+        print(f"    {i}. {_format_entry(entry)}")
+    print()
+    try:
+        resp = input("  Clear all entries? [y/N]: ").strip().lower()
+    except (KeyboardInterrupt, EOFError):
+        print()
+        print("  Cancelled.")
+        return
+    if resp not in ("y", "yes"):
+        print("  Cancelled — no change.")
+        return
+
+    _write_chain(config, [])
+    save_config(config)
+    print()
+    print("  Fallback chain cleared.")
+    print()
+
+
+def _numbered_pick(question: str, choices: List[str]) -> Optional[int]:
+    """Fallback numbered-list picker when curses is unavailable."""
+    print(question)
+    for i, c in enumerate(choices, 1):
+        print(f"  {i}. {c}")
+    print()
+    while True:
+        try:
+            val = input(f"Choice [1-{len(choices)}]: ").strip()
+            if not val:
+                return None
+            idx = int(val) - 1
+            if 0 <= idx < len(choices):
+                return idx
+            print(f"Please enter 1-{len(choices)}")
+        except ValueError:
+            print("Please enter a number")
+        except (KeyboardInterrupt, EOFError):
+            print()
+            return None
+
+
+# ---------------------------------------------------------------------------
+# Dispatch
+# ---------------------------------------------------------------------------
+
+def cmd_fallback(args) -> None:
+    """Top-level dispatcher for ``hermes fallback [subcommand]``."""
+    sub = getattr(args, "fallback_command", None)
+    if sub in (None, "", "list", "ls"):
+        cmd_fallback_list(args)
+    elif sub == "add":
+        cmd_fallback_add(args)
+    elif sub in ("remove", "rm"):
+        cmd_fallback_remove(args)
+    elif sub == "clear":
+        cmd_fallback_clear(args)
+    else:
+        print(f"Unknown fallback subcommand: {sub}")
+        print("Use one of: list, add, remove, clear")
+        raise SystemExit(2)

hermes_cli/hooks.py

@@ -125,6 +125,7 @@ _DEFAULT_PAYLOADS = {
         "task_id": "test-task",
         "tool_call_id": "test-call",
         "result": '{"output": "hello"}',
+        "duration_ms": 42,
     },
     "pre_llm_call": {
         "session_id": "test-session",

hermes_cli/model_catalog.py

@@ -0,0 +1,329 @@
+"""Remote model catalog fetcher.
+
+The Hermes docs site hosts a JSON manifest of curated models for providers
+we want to update without shipping a release (currently OpenRouter and
+Nous Portal). This module fetches, validates, and caches that manifest,
+falling back to the in-repo hardcoded lists when the network is unavailable.
+
+Pipeline
+--------
+1. ``get_catalog()`` — returns a parsed manifest dict.
+   - Checks in-process cache (invalidated by TTL).
+   - Reads disk cache at ``~/.hermes/cache/model_catalog.json``.
+   - Fetches the master URL if disk cache is stale or missing.
+   - On any fetch failure, keeps using the stale cache (or empty dict).
+
+2. ``get_curated_openrouter_models()`` / ``get_curated_nous_models()`` —
+   thin accessors returning the shapes existing callers expect. Each
+   falls back to the in-repo hardcoded list on any lookup failure.
+
+Schema (version 1)
+------------------
+::
+
+    {
+      "version": 1,
+      "updated_at": "2026-04-25T22:00:00Z",
+      "metadata": {...},                # free-form
+      "providers": {
+        "openrouter": {
+          "metadata": {...},            # free-form
+          "models": [
+            {"id": "vendor/model", "description": "recommended",
+             "metadata": {...}}          # free-form, model-level
+          ]
+        },
+        "nous": {...}
+      }
+    }
+
+Unknown fields are ignored — extra metadata can be added at either level
+without bumping ``version``. ``version`` bumps are reserved for
+breaking changes (renaming ``providers``, changing ``models`` shape).
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import time
+import urllib.error
+import urllib.request
+from pathlib import Path
+from typing import Any
+
+from hermes_cli import __version__ as _HERMES_VERSION
+
+logger = logging.getLogger(__name__)
+
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+
+DEFAULT_CATALOG_URL = (
+    "https://hermes-agent.nousresearch.com/docs/api/model-catalog.json"
+)
+DEFAULT_TTL_HOURS = 24
+DEFAULT_FETCH_TIMEOUT = 8.0
+SUPPORTED_SCHEMA_VERSION = 1
+
+_HERMES_USER_AGENT = f"hermes-cli/{_HERMES_VERSION}"
+
+# In-process cache to avoid repeated disk + parse work across multiple
+# calls within the same session. Invalidated by TTL against the disk file's
+# mtime, so calling code never has to think about this.
+_catalog_cache: dict[str, Any] | None = None
+_catalog_cache_source_mtime: float = 0.0
+
+
+# ---------------------------------------------------------------------------
+# Config
+# ---------------------------------------------------------------------------
+
+
+def _load_catalog_config() -> dict[str, Any]:
+    """Load the ``model_catalog`` config block with defaults filled in."""
+    try:
+        from hermes_cli.config import load_config
+        cfg = load_config() or {}
+    except Exception:
+        cfg = {}
+
+    raw = cfg.get("model_catalog")
+    if not isinstance(raw, dict):
+        raw = {}
+
+    return {
+        "enabled": bool(raw.get("enabled", True)),
+        "url": str(raw.get("url") or DEFAULT_CATALOG_URL),
+        "ttl_hours": float(raw.get("ttl_hours") or DEFAULT_TTL_HOURS),
+        "providers": raw.get("providers") if isinstance(raw.get("providers"), dict) else {},
+    }
+
+
+def _cache_path() -> Path:
+    """Return the disk cache path. Import lazily so tests can monkeypatch home."""
+    from hermes_constants import get_hermes_home
+    return get_hermes_home() / "cache" / "model_catalog.json"
+
+
+# ---------------------------------------------------------------------------
+# Fetch + validate + cache
+# ---------------------------------------------------------------------------
+
+
+def _fetch_manifest(url: str, timeout: float) -> dict[str, Any] | None:
+    """HTTP GET the manifest URL and return a parsed dict, or None on failure."""
+    try:
+        req = urllib.request.Request(
+            url,
+            headers={
+                "Accept": "application/json",
+                "User-Agent": _HERMES_USER_AGENT,
+            },
+        )
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            data = json.loads(resp.read().decode())
+    except (urllib.error.URLError, TimeoutError, json.JSONDecodeError, OSError) as exc:
+        logger.info("model catalog fetch failed (%s): %s", url, exc)
+        return None
+    except Exception as exc:  # pragma: no cover — defensive
+        logger.info("model catalog fetch errored (%s): %s", url, exc)
+        return None
+
+    if not _validate_manifest(data):
+        logger.info("model catalog at %s failed schema validation", url)
+        return None
+
+    return data
+
+
+def _validate_manifest(data: Any) -> bool:
+    """Return True when ``data`` matches the minimum manifest shape."""
+    if not isinstance(data, dict):
+        return False
+    version = data.get("version")
+    if not isinstance(version, int) or version > SUPPORTED_SCHEMA_VERSION:
+        # Future schema version we don't understand — refuse rather than
+        # guess. Older schemas (version < 1) aren't supported either.
+        return False
+    providers = data.get("providers")
+    if not isinstance(providers, dict):
+        return False
+    for pname, pblock in providers.items():
+        if not isinstance(pname, str) or not isinstance(pblock, dict):
+            return False
+        models = pblock.get("models")
+        if not isinstance(models, list):
+            return False
+        for m in models:
+            if not isinstance(m, dict):
+                return False
+            if not isinstance(m.get("id"), str) or not m["id"].strip():
+                return False
+    return True
+
+
+def _read_disk_cache() -> tuple[dict[str, Any] | None, float]:
+    """Return ``(data_or_none, mtime)``. mtime is 0 if file is missing."""
+    path = _cache_path()
+    try:
+        mtime = path.stat().st_mtime
+    except (OSError, FileNotFoundError):
+        return (None, 0.0)
+    try:
+        with open(path) as fh:
+            data = json.load(fh)
+    except (OSError, json.JSONDecodeError):
+        return (None, 0.0)
+    if not _validate_manifest(data):
+        return (None, 0.0)
+    return (data, mtime)
+
+
+def _write_disk_cache(data: dict[str, Any]) -> None:
+    path = _cache_path()
+    try:
+        path.parent.mkdir(parents=True, exist_ok=True)
+        tmp = path.with_suffix(path.suffix + ".tmp")
+        with open(tmp, "w") as fh:
+            json.dump(data, fh, indent=2)
+            fh.write("\n")
+        os.replace(tmp, path)
+    except OSError as exc:
+        logger.info("model catalog cache write failed: %s", exc)
+
+
+# ---------------------------------------------------------------------------
+# Public API
+# ---------------------------------------------------------------------------
+
+
+def get_catalog(*, force_refresh: bool = False) -> dict[str, Any]:
+    """Return the parsed model catalog manifest, or an empty dict on failure.
+
+    Callers should treat a missing provider/model as "use the in-repo fallback"
+    — never raise from this function so the CLI keeps working offline.
+    """
+    global _catalog_cache, _catalog_cache_source_mtime
+
+    cfg = _load_catalog_config()
+    if not cfg["enabled"]:
+        return {}
+
+    ttl_seconds = max(0.0, cfg["ttl_hours"] * 3600.0)
+
+    disk_data, disk_mtime = _read_disk_cache()
+    now = time.time()
+    disk_fresh = disk_data is not None and (now - disk_mtime) < ttl_seconds
+
+    # In-process cache hit: disk hasn't changed since we loaded it and still fresh.
+    if (
+        not force_refresh
+        and _catalog_cache is not None
+        and disk_data is not None
+        and disk_mtime == _catalog_cache_source_mtime
+        and disk_fresh
+    ):
+        return _catalog_cache
+
+    # Disk is fresh enough — use it without a network hit.
+    if not force_refresh and disk_fresh and disk_data is not None:
+        _catalog_cache = disk_data
+        _catalog_cache_source_mtime = disk_mtime
+        return disk_data
+
+    # Need to (re)fetch. If it fails, fall back to any stale disk copy.
+    fetched = _fetch_manifest(cfg["url"], DEFAULT_FETCH_TIMEOUT)
+    if fetched is not None:
+        _write_disk_cache(fetched)
+        new_disk_data, new_mtime = _read_disk_cache()
+        if new_disk_data is not None:
+            _catalog_cache = new_disk_data
+            _catalog_cache_source_mtime = new_mtime
+            return new_disk_data
+        _catalog_cache = fetched
+        _catalog_cache_source_mtime = now
+        return fetched
+
+    if disk_data is not None:
+        _catalog_cache = disk_data
+        _catalog_cache_source_mtime = disk_mtime
+        return disk_data
+
+    return {}
+
+
+def _fetch_provider_override(provider: str) -> dict[str, Any] | None:
+    """If ``model_catalog.providers.<name>.url`` is set, fetch that instead."""
+    cfg = _load_catalog_config()
+    if not cfg["enabled"]:
+        return None
+    provider_cfg = cfg["providers"].get(provider)
+    if not isinstance(provider_cfg, dict):
+        return None
+    override_url = provider_cfg.get("url")
+    if not isinstance(override_url, str) or not override_url.strip():
+        return None
+    # Override fetches skip the disk cache because they're usually
+    # third-party self-hosted. Re-request on every call but with a short
+    # timeout so they don't block the picker.
+    return _fetch_manifest(override_url.strip(), DEFAULT_FETCH_TIMEOUT)
+
+
+def _get_provider_block(provider: str) -> dict[str, Any] | None:
+    """Return the provider's manifest block, respecting per-provider overrides."""
+    override = _fetch_provider_override(provider)
+    if override is not None:
+        block = override.get("providers", {}).get(provider)
+        if isinstance(block, dict):
+            return block
+
+    catalog = get_catalog()
+    if not catalog:
+        return None
+    block = catalog.get("providers", {}).get(provider)
+    return block if isinstance(block, dict) else None
+
+
+def get_curated_openrouter_models() -> list[tuple[str, str]] | None:
+    """Return OpenRouter's curated ``[(id, description), ...]`` from the manifest.
+
+    Returns ``None`` when the manifest is unavailable, so callers can fall
+    back to their hardcoded list.
+    """
+    block = _get_provider_block("openrouter")
+    if not block:
+        return None
+    out: list[tuple[str, str]] = []
+    for m in block.get("models", []):
+        mid = str(m.get("id") or "").strip()
+        if not mid:
+            continue
+        desc = str(m.get("description") or "")
+        out.append((mid, desc))
+    return out or None
+
+
+def get_curated_nous_models() -> list[str] | None:
+    """Return Nous Portal's curated list of model ids from the manifest.
+
+    Returns ``None`` when the manifest is unavailable.
+    """
+    block = _get_provider_block("nous")
+    if not block:
+        return None
+    out: list[str] = []
+    for m in block.get("models", []):
+        mid = str(m.get("id") or "").strip()
+        if mid:
+            out.append(mid)
+    return out or None
+
+
+def reset_cache() -> None:
+    """Clear the in-process cache. Used by tests and ``hermes model --refresh``."""
+    global _catalog_cache, _catalog_cache_source_mtime
+    _catalog_cache = None
+    _catalog_cache_source_mtime = 0.0

hermes_cli/model_normalize.py

@@ -12,8 +12,12 @@ Different LLM providers expect model identifiers in different formats:
   model IDs, but Claude still uses hyphenated native names like
   ``claude-sonnet-4-6``.
 - **OpenCode Go** preserves dots in model names: ``minimax-m2.7``.
-- **DeepSeek** only accepts two model identifiers:
-  ``deepseek-chat`` and ``deepseek-reasoner``.
+- **DeepSeek** accepts ``deepseek-chat`` (V3), ``deepseek-reasoner``
+  (R1-family), and the first-class V-series IDs (``deepseek-v4-pro``,
+  ``deepseek-v4-flash``, and any future ``deepseek-v<N>-*``).  Older
+  Hermes revisions folded every non-reasoner input into
+  ``deepseek-chat``, which on aggregators routes to V3 — so a user
+  picking V4 Pro was silently downgraded.
 - **Custom** and remaining providers pass the name through as-is.
 
 This module centralises that translation so callers can simply write::
@@ -25,6 +29,7 @@ Inspired by Clawdbot's ``normalizeAnthropicModelId`` pattern.
 
 from __future__ import annotations
 
+import re
 from typing import Optional
 
 # ---------------------------------------------------------------------------
@@ -100,6 +105,15 @@ _MATCHING_PREFIX_STRIP_PROVIDERS: frozenset[str] = frozenset({
     "custom",
 })
 
+# Providers whose APIs require lowercase model IDs.  Xiaomi's
+# ``api.xiaomimimo.com`` rejects mixed-case names like ``MiMo-V2.5-Pro``
+# that users might copy from marketing docs — it only accepts
+# ``mimo-v2.5-pro``.  After stripping a matching provider prefix, these
+# providers also get ``.lower()`` applied.
+_LOWERCASE_MODEL_PROVIDERS: frozenset[str] = frozenset({
+    "xiaomi",
+})
+
 # ---------------------------------------------------------------------------
 # DeepSeek special handling
 # ---------------------------------------------------------------------------
@@ -115,17 +129,30 @@ _DEEPSEEK_REASONER_KEYWORDS: frozenset[str] = frozenset({
 })
 
 _DEEPSEEK_CANONICAL_MODELS: frozenset[str] = frozenset({
-    "deepseek-chat",
-    "deepseek-reasoner",
+    "deepseek-chat",       # V3 on DeepSeek direct and most aggregators
+    "deepseek-reasoner",   # R1-family reasoning model
+    "deepseek-v4-pro",     # V4 Pro — first-class model ID
+    "deepseek-v4-flash",   # V4 Flash — first-class model ID
 })
 
+# First-class V-series IDs (``deepseek-v4-pro``, ``deepseek-v4-flash``,
+# future ``deepseek-v5-*``, dated variants like ``deepseek-v4-flash-20260423``).
+# Verified empirically 2026-04-24: DeepSeek's Chat Completions API returns
+# ``provider: DeepSeek`` / ``model: deepseek-v4-flash-20260423`` when called
+# with ``model=deepseek/deepseek-v4-flash``, so these names are not aliases
+# of ``deepseek-chat`` and must not be folded into it.
+_DEEPSEEK_V_SERIES_RE = re.compile(r"^deepseek-v\d+([-.].+)?$")
+
 
 def _normalize_for_deepseek(model_name: str) -> str:
-    """Map any model input to one of DeepSeek's two accepted identifiers.
+    """Map a model input to a DeepSeek-accepted identifier.
 
     Rules:
-    - Already ``deepseek-chat`` or ``deepseek-reasoner`` -> pass through.
-    - Contains any reasoner keyword (r1, think, reasoning, cot, reasoner)
+    - Already a known canonical (``deepseek-chat``/``deepseek-reasoner``/
+      ``deepseek-v4-pro``/``deepseek-v4-flash``) -> pass through.
+    - Matches the V-series pattern ``deepseek-v<digit>...`` -> pass through
+      (covers future ``deepseek-v5-*`` and dated variants without a release).
+    - Contains a reasoner keyword (r1, think, reasoning, cot, reasoner)
       -> ``deepseek-reasoner``.
     - Everything else -> ``deepseek-chat``.
 
@@ -133,13 +160,17 @@ def _normalize_for_deepseek(model_name: str) -> str:
         model_name: The bare model name (vendor prefix already stripped).
 
     Returns:
-        One of ``"deepseek-chat"`` or ``"deepseek-reasoner"``.
+        A DeepSeek-accepted model identifier.
     """
     bare = _strip_vendor_prefix(model_name).lower()
 
     if bare in _DEEPSEEK_CANONICAL_MODELS:
         return bare
 
+    # V-series first-class IDs (v4-pro, v4-flash, future v5-*, dated variants)
+    if _DEEPSEEK_V_SERIES_RE.match(bare):
+        return bare
+
     # Check for reasoner-like keywords anywhere in the name
     for keyword in _DEEPSEEK_REASONER_KEYWORDS:
         if keyword in bare:
@@ -347,6 +378,9 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 
         >>> normalize_model_for_provider("claude-sonnet-4.6", "zai")
         'claude-sonnet-4.6'
+
+        >>> normalize_model_for_provider("MiMo-V2.5-Pro", "xiaomi")
+        'mimo-v2.5-pro'
     """
     name = (model_input or "").strip()
     if not name:
@@ -410,7 +444,12 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 
     # --- Direct providers: repair matching provider prefixes only ---
     if provider in _MATCHING_PREFIX_STRIP_PROVIDERS:
-        return _strip_matching_provider_prefix(name, provider)
+        result = _strip_matching_provider_prefix(name, provider)
+        # Some providers require lowercase model IDs (e.g. Xiaomi's API
+        # rejects "MiMo-V2.5-Pro" but accepts "mimo-v2.5-pro").
+        if provider in _LOWERCASE_MODEL_PROVIDERS:
+            result = result.lower()
+        return result
 
     # --- Authoritative native providers: preserve user-facing slugs as-is ---
     if provider in _AUTHORITATIVE_NATIVE_PROVIDERS:

hermes_cli/model_switch.py

@@ -527,6 +527,49 @@ def _resolve_alias_fallback(
     return None
 
 
+def resolve_display_context_length(
+    model: str,
+    provider: str,
+    base_url: str = "",
+    api_key: str = "",
+    model_info: Optional[ModelInfo] = None,
+    custom_providers: list | None = None,
+) -> Optional[int]:
+    """Resolve the context length to show in /model output.
+
+    models.dev reports per-vendor context (e.g. gpt-5.5 = 1.05M on openai)
+    but provider-enforced limits can be lower (e.g. Codex OAuth caps the
+    same slug at 272k). The authoritative source is
+    ``agent.model_metadata.get_model_context_length`` which already knows
+    about Codex OAuth, Copilot, Nous, and falls back to models.dev for the
+    rest.
+
+    When ``custom_providers`` is provided, per-model ``context_length``
+    overrides from ``custom_providers[].models.<id>.context_length`` are
+    honored — this closes #15779 where ``/model`` switch ignored user-set
+    overrides.
+
+    Prefer the provider-aware value; fall back to ``model_info.context_window``
+    only if the resolver returns nothing.
+    """
+    try:
+        from agent.model_metadata import get_model_context_length
+        ctx = get_model_context_length(
+            model,
+            base_url=base_url or "",
+            api_key=api_key or "",
+            provider=provider or None,
+            custom_providers=custom_providers,
+        )
+        if ctx:
+            return int(ctx)
+    except Exception:
+        pass
+    if model_info is not None and model_info.context_window:
+        return int(model_info.context_window)
+    return None
+
+
 # ---------------------------------------------------------------------------
 # Core model-switching pipeline
 # ---------------------------------------------------------------------------
@@ -771,7 +814,10 @@ def switch_model(
 
     if provider_changed or explicit_provider:
         try:
-            runtime = resolve_runtime_provider(requested=target_provider)
+            runtime = resolve_runtime_provider(
+                requested=target_provider,
+                target_model=new_model,
+            )
             api_key = runtime.get("api_key", "")
             base_url = runtime.get("base_url", "")
             api_mode = runtime.get("api_mode", "")
@@ -788,10 +834,18 @@ def switch_model(
             )
     else:
         try:
-            runtime = resolve_runtime_provider(requested=current_provider)
-            api_key = runtime.get("api_key", "")
-            base_url = runtime.get("base_url", "")
-            api_mode = runtime.get("api_mode", "")
+            runtime = resolve_runtime_provider(
+                requested=current_provider,
+                target_model=new_model,
+            )
+            # If resolution fell through to "custom" (e.g. named custom provider like
+            # "ollama-launch" that resolve_runtime_provider doesn't know), keep existing
+            # credentials. Otherwise use the resolved values (picks up credential rotation,
+            # base_url adjustments for OpenCode, etc.).
+            if runtime.get("provider") != "custom":
+                api_key = runtime.get("api_key", "")
+                base_url = runtime.get("base_url", "")
+                api_mode = runtime.get("api_mode", "")
         except Exception:
             pass
 
@@ -815,6 +869,7 @@ def switch_model(
             target_provider,
             api_key=api_key,
             base_url=base_url,
+            api_mode=api_mode or None,
         )
     except Exception as e:
         validation = {
@@ -824,16 +879,31 @@ def switch_model(
             "message": f"Could not validate `{new_model}`: {e}",
         }
 
+    # Override rejection if model is in the user's saved provider config.
+    # API /v1/models may not list cloud/aliased models even though the server supports them.
     if not validation.get("accepted"):
-        msg = validation.get("message", "Invalid model")
-        return ModelSwitchResult(
-            success=False,
-            new_model=new_model,
-            target_provider=target_provider,
-            provider_label=provider_label,
-            is_global=is_global,
-            error_message=msg,
-        )
+        override = False
+        if user_providers:
+            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
+        if override:
+            validation = {"accepted": True, "persist": True, "recognized": False, "message": validation.get("message", "")}
+        else:
+            msg = validation.get("message", "Invalid model")
+            return ModelSwitchResult(
+                success=False,
+                new_model=new_model,
+                target_provider=target_provider,
+                provider_label=provider_label,
+                is_global=is_global,
+                error_message=msg,
+            )
 
     # Apply auto-correction if validation found a closer match
     if validation.get("corrected_model"):
@@ -936,7 +1006,7 @@ def list_authenticated_providers(
     from hermes_cli.auth import PROVIDER_REGISTRY
     from hermes_cli.models import (
         OPENROUTER_MODELS, _PROVIDER_MODELS,
-        _MODELS_DEV_PREFERRED, _merge_with_models_dev,
+        _MODELS_DEV_PREFERRED, _merge_with_models_dev, provider_model_ids,
     )
 
     results: List[dict] = []
@@ -984,6 +1054,14 @@ def list_authenticated_providers(
 
         # Check if any env var is set
         has_creds = any(os.environ.get(ev) for ev in env_vars)
+        if not has_creds:
+            try:
+                from hermes_cli.auth import _load_auth_store
+                store = _load_auth_store()
+                if store and hermes_id in store.get("credential_pool", {}):
+                    has_creds = True
+            except Exception:
+                pass
         if not has_creds:
             continue
 
@@ -1095,11 +1173,14 @@ def list_authenticated_providers(
         if not has_creds:
             continue
 
-        # Use curated list — look up by Hermes slug, fall back to overlay key
-        model_ids = curated.get(hermes_slug, []) or curated.get(pid, [])
-        # Merge with models.dev for preferred providers (same rationale as above).
-        if hermes_slug in _MODELS_DEV_PREFERRED:
-            model_ids = _merge_with_models_dev(hermes_slug, model_ids)
+        if hermes_slug in {"copilot", "copilot-acp"}:
+            model_ids = provider_model_ids(hermes_slug)
+        else:
+            # Use curated list — look up by Hermes slug, fall back to overlay key
+            model_ids = curated.get(hermes_slug, []) or curated.get(pid, [])
+            # Merge with models.dev for preferred providers (same rationale as above).
+            if hermes_slug in _MODELS_DEV_PREFERRED:
+                model_ids = _merge_with_models_dev(hermes_slug, model_ids)
         total = len(model_ids)
         top = model_ids[:max_models]
 
@@ -1222,6 +1303,15 @@ def list_authenticated_providers(
                     if m and m not in models_list:
                         models_list.append(m)
 
+            # Official OpenAI API rows in providers: often have base_url but no
+            # explicit models: dict — avoid a misleading zero count in /model.
+            if not models_list:
+                url_lower = str(api_url).strip().lower()
+                if "api.openai.com" in url_lower:
+                    fb = curated.get("openai") or []
+                    if fb:
+                        models_list = list(fb)
+
             # Try to probe /v1/models if URL is set (but don't block on it)
             # For now just show what we know from config
             results.append({

hermes_cli/models.py

@@ -33,6 +33,8 @@ COPILOT_REASONING_EFFORTS_O_SERIES = ["low", "medium", "high"]
 # (model_id, display description shown in menus)
 OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("moonshotai/kimi-k2.6",            "recommended"),
+    ("deepseek/deepseek-v4-pro",        ""),
+    ("deepseek/deepseek-v4-flash",      ""),
     ("anthropic/claude-opus-4.7",       ""),
     ("anthropic/claude-opus-4.6",       ""),
     ("anthropic/claude-sonnet-4.6",     ""),
@@ -40,7 +42,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("anthropic/claude-sonnet-4.5",     ""),
     ("anthropic/claude-haiku-4.5",      ""),
     ("openrouter/elephant-alpha",       "free"),
-    ("openai/gpt-5.4",                  ""),
+    ("openai/gpt-5.5",                  ""),
     ("openai/gpt-5.4-mini",             ""),
     ("xiaomi/mimo-v2.5-pro",             ""),
     ("xiaomi/mimo-v2.5",                 ""),
@@ -63,7 +65,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("nvidia/nemotron-3-super-120b-a12b:free", "free"),
     ("arcee-ai/trinity-large-preview:free", "free"),
     ("arcee-ai/trinity-large-thinking",  ""),
-    ("openai/gpt-5.4-pro",              ""),
+    ("openai/gpt-5.5-pro",              ""),
     ("openai/gpt-5.4-nano",             ""),
 ]
 
@@ -109,6 +111,8 @@ def _codex_curated_models() -> list[str]:
 _PROVIDER_MODELS: dict[str, list[str]] = {
     "nous": [
         "moonshotai/kimi-k2.6",
+        "deepseek/deepseek-v4-pro",
+        "deepseek/deepseek-v4-flash",
         "xiaomi/mimo-v2.5-pro",
         "xiaomi/mimo-v2.5",
         "anthropic/claude-opus-4.7",
@@ -116,7 +120,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "anthropic/claude-sonnet-4.6",
         "anthropic/claude-sonnet-4.5",
         "anthropic/claude-haiku-4.5",
-        "openai/gpt-5.4",
+        "openai/gpt-5.5",
         "openai/gpt-5.4-mini",
         "openai/gpt-5.3-codex",
         "google/gemini-3-pro-preview",
@@ -135,9 +139,21 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "x-ai/grok-4.20-beta",
         "nvidia/nemotron-3-super-120b-a12b",
         "arcee-ai/trinity-large-thinking",
-        "openai/gpt-5.4-pro",
+        "openai/gpt-5.5-pro",
         "openai/gpt-5.4-nano",
     ],
+    # Native OpenAI Chat Completions (api.openai.com). Used by /model counts and
+    # provider_model_ids fallback when /v1/models is unavailable.
+    "openai": [
+        "gpt-5.4",
+        "gpt-5.4-mini",
+        "gpt-5-mini",
+        "gpt-5.3-codex",
+        "gpt-5.2-codex",
+        "gpt-4.1",
+        "gpt-4o",
+        "gpt-4o-mini",
+    ],
     "openai-codex": _codex_curated_models(),
     "copilot-acp": [
         "copilot-acp",
@@ -151,10 +167,13 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "gpt-4.1",
         "gpt-4o",
         "gpt-4o-mini",
-        "claude-opus-4.6",
         "claude-sonnet-4.6",
+        "claude-sonnet-4",
         "claude-sonnet-4.5",
         "claude-haiku-4.5",
+        "gemini-3.1-pro-preview",
+        "gemini-3-pro-preview",
+        "gemini-3-flash-preview",
         "gemini-2.5-pro",
         "grok-code-fast-1",
     ],
@@ -246,6 +265,8 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "claude-haiku-4-5-20251001",
     ],
     "deepseek": [
+        "deepseek-v4-pro",
+        "deepseek-v4-flash",
         "deepseek-chat",
         "deepseek-reasoner",
     ],
@@ -362,6 +383,9 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "us.meta.llama4-maverick-17b-instruct-v1:0",
         "us.meta.llama4-scout-17b-instruct-v1:0",
     ],
+    # Azure Foundry: user-provided endpoint and model.
+    # Empty list because models depend on the endpoint configuration.
+    "azure-foundry": [],
 }
 
 # Vercel AI Gateway: derive the bare-model-id catalog from the curated
@@ -676,7 +700,7 @@ def get_nous_recommended_aux_model(
 # ---------------------------------------------------------------------------
 # Canonical provider list — single source of truth for provider identity.
 # Every code path that lists, displays, or iterates providers derives from
-# this list:  hermes model, /model, /provider, list_authenticated_providers.
+# this list:  hermes model, /model, list_authenticated_providers.
 #
 # Fields:
 #   slug        — internal provider ID (used in config.yaml, --provider flag)
@@ -719,6 +743,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("opencode-zen",   "OpenCode Zen",             "OpenCode Zen (35+ curated models, pay-as-you-go)"),
     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)"),
 ]
 
 # Derived dicts — used throughout the codebase
@@ -851,7 +876,16 @@ def fetch_openrouter_models(
     if _openrouter_catalog_cache is not None and not force_refresh:
         return list(_openrouter_catalog_cache)
 
-    fallback = list(OPENROUTER_MODELS)
+    # Prefer the remotely-hosted catalog manifest; fall back to the in-repo
+    # snapshot when the manifest is unreachable. Both are curated lists that
+    # drive the picker; the OpenRouter live /v1/models filter (tool support,
+    # free pricing) is applied on top either way.
+    try:
+        from hermes_cli.model_catalog import get_curated_openrouter_models
+        remote = get_curated_openrouter_models()
+    except Exception:
+        remote = None
+    fallback = list(remote) if remote else list(OPENROUTER_MODELS)
     preferred_ids = [mid for mid, _ in fallback]
 
     try:
@@ -904,6 +938,24 @@ def model_ids(*, force_refresh: bool = False) -> list[str]:
     return [mid for mid, _ in fetch_openrouter_models(force_refresh=force_refresh)]
 
 
+def get_curated_nous_model_ids() -> list[str]:
+    """Return the curated Nous Portal model-id list.
+
+    Prefers the remotely-hosted catalog manifest (published under
+    ``website/static/api/model-catalog.json``); falls back to the in-repo
+    snapshot in ``_PROVIDER_MODELS["nous"]`` when the manifest is
+    unreachable. Always returns a list (never None).
+    """
+    try:
+        from hermes_cli.model_catalog import get_curated_nous_models
+        remote = get_curated_nous_models()
+    except Exception:
+        remote = None
+    if remote:
+        return list(remote)
+    return list(_PROVIDER_MODELS.get("nous", []))
+
+
 def _ai_gateway_model_is_free(pricing: Any) -> bool:
     """Return True if an AI Gateway model has $0 input AND output pricing."""
     if not isinstance(pricing, dict):
@@ -1104,7 +1156,10 @@ def fetch_models_with_pricing(
         return _pricing_cache[cache_key]
 
     url = cache_key.rstrip("/") + "/v1/models"
-    headers: dict[str, str] = {"Accept": "application/json"}
+    headers: dict[str, str] = {
+        "Accept": "application/json",
+        "User-Agent": _HERMES_USER_AGENT,
+    }
     if api_key:
         headers["Authorization"] = f"Bearer {api_key}"
 
@@ -1355,27 +1410,93 @@ def curated_models_for_provider(
     return [(m, "") for m in models]
 
 
-def detect_provider_for_model(
+def _provider_keys(provider: str) -> set[str]:
+    key = (provider or "").strip().lower()
+    normalized = normalize_provider(provider)
+    return {k for k in (key, normalized) if k}
+
+
+def _model_in_provider_catalog(name_lower: str, providers: set[str]) -> bool:
+    return any(
+        name_lower == model.lower()
+        for provider in providers
+        for model in _PROVIDER_MODELS.get(provider, [])
+    )
+
+
+_AGGREGATOR_PROVIDERS = frozenset(
+    {"nous", "openrouter", "ai-gateway", "copilot", "kilocode"}
+)
+
+
+def _resolve_static_model_alias(
+    name_lower: str,
+    current_keys: set[str],
+) -> Optional[tuple[str, str]]:
+    """Resolve short aliases (e.g. sonnet/opus) using static catalogs only."""
+    try:
+        from hermes_cli.model_switch import MODEL_ALIASES
+    except Exception:
+        return None
+
+    identity = MODEL_ALIASES.get(name_lower)
+    if identity is None:
+        return None
+
+    vendor = identity.vendor
+    family = identity.family
+
+    def _match(provider: str) -> Optional[str]:
+        models = _PROVIDER_MODELS.get(provider, [])
+        if not models:
+            return None
+        prefix = (
+            f"{vendor}/{family}"
+            if provider in _AGGREGATOR_PROVIDERS
+            else family
+        ).lower()
+        for model in models:
+            if model.lower().startswith(prefix):
+                return model
+        return None
+
+    for provider in current_keys:
+        if matched := _match(provider):
+            return provider, matched
+
+    for provider in _PROVIDER_MODELS:
+        if provider in current_keys or provider in _AGGREGATOR_PROVIDERS:
+            continue
+        if matched := _match(provider):
+            return provider, matched
+
+    for provider in _AGGREGATOR_PROVIDERS:
+        if provider in current_keys and (matched := _match(provider)):
+            return provider, matched
+
+    return None
+
+
+def detect_static_provider_for_model(
     model_name: str,
     current_provider: str,
 ) -> Optional[tuple[str, str]]:
-    """Auto-detect the best provider for a model name.
+    """Auto-detect a provider from static catalogs only.
 
-    Returns ``(provider_id, model_name)`` — the model name may be remapped
-    (e.g. bare ``deepseek-chat`` → ``deepseek/deepseek-chat`` for OpenRouter).
+    Returns ``(provider_id, model_name)``. The model name may be remapped
+    when a static alias or bare provider name resolves to a catalog default.
     Returns ``None`` when no confident match is found.
-
-    Priority:
-    0. Bare provider name → switch to that provider's default model
-    1. Direct provider with credentials (highest)
-    2. Direct provider without credentials → remap to OpenRouter slug
-    3. OpenRouter catalog match
     """
     name = (model_name or "").strip()
     if not name:
         return None
 
     name_lower = name.lower()
+    current_keys = _provider_keys(current_provider)
+
+    alias_match = _resolve_static_model_alias(name_lower, current_keys)
+    if alias_match:
+        return alias_match
 
     # --- Step 0: bare provider name typed as model ---
     # If someone types `/model nous` or `/model anthropic`, treat it as a
@@ -1388,64 +1509,49 @@ def detect_provider_for_model(
         if (
             resolved_provider in _PROVIDER_LABELS
             and default_models
-            and resolved_provider != normalize_provider(current_provider)
+            and resolved_provider not in current_keys
         ):
             return (resolved_provider, default_models[0])
 
     # Aggregators list other providers' models — never auto-switch TO them
-    _AGGREGATORS = {"nous", "openrouter", "ai-gateway", "copilot", "kilocode"}
-
     # If the model belongs to the current provider's catalog, don't suggest switching
-    current_models = _PROVIDER_MODELS.get(current_provider, [])
-    if any(name_lower == m.lower() for m in current_models):
+    if _model_in_provider_catalog(name_lower, current_keys):
         return None
 
     # --- Step 1: check static provider catalogs for a direct match ---
-    direct_match: Optional[str] = None
     for pid, models in _PROVIDER_MODELS.items():
-        if pid == current_provider or pid in _AGGREGATORS:
+        if pid in current_keys or pid in _AGGREGATOR_PROVIDERS:
             continue
         if any(name_lower == m.lower() for m in models):
-            direct_match = pid
-            break
+            return (pid, name)
 
-    if direct_match:
-        # Check if we have credentials for this provider — env vars,
-        # credential pool, or auth store entries.
-        has_creds = False
-        try:
-            from hermes_cli.auth import PROVIDER_REGISTRY
-            pconfig = PROVIDER_REGISTRY.get(direct_match)
-            if pconfig:
-                for env_var in pconfig.api_key_env_vars:
-                    if os.getenv(env_var, "").strip():
-                        has_creds = True
-                        break
-        except Exception:
-            pass
-        # Also check credential pool and auth store — covers OAuth,
-        # Claude Code tokens, and other non-env-var credentials (#10300).
-        if not has_creds:
-            try:
-                from agent.credential_pool import load_pool
-                pool = load_pool(direct_match)
-                if pool.has_credentials():
-                    has_creds = True
-            except Exception:
-                pass
-        if not has_creds:
-            try:
-                from hermes_cli.auth import _load_auth_store
-                store = _load_auth_store()
-                if direct_match in store.get("providers", {}) or direct_match in store.get("credential_pool", {}):
-                    has_creds = True
-            except Exception:
-                pass
+    return None
 
-        # Always return the direct provider match.  If credentials are
-        # missing, the client init will give a clear error rather than
-        # silently routing through the wrong provider (#10300).
-        return (direct_match, name)
+
+def detect_provider_for_model(
+    model_name: str,
+    current_provider: str,
+) -> Optional[tuple[str, str]]:
+    """Auto-detect the best provider for a model name.
+
+    Returns ``(provider_id, model_name)`` — the model name may be remapped
+    (e.g. bare ``deepseek-chat`` → ``deepseek/deepseek-chat`` for OpenRouter).
+    Returns ``None`` when no confident match is found.
+
+    Priority:
+    0. Bare provider name → switch to that provider's default model
+    1. Direct provider static catalog match
+    2. OpenRouter catalog match
+    """
+    name = (model_name or "").strip()
+    if not name:
+        return None
+
+    static_match = detect_static_provider_for_model(name, current_provider)
+    if static_match:
+        return static_match
+    if _model_in_provider_catalog(name.lower(), _provider_keys(current_provider)):
+        return None
 
     # --- Step 2: check OpenRouter catalog ---
     # First try exact match (handles provider/model format)
@@ -1736,6 +1842,17 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
         live = fetch_ollama_cloud_models(force_refresh=force_refresh)
         if live:
             return live
+    if normalized == "openai":
+        api_key = os.getenv("OPENAI_API_KEY", "").strip()
+        if api_key:
+            base_raw = os.getenv("OPENAI_BASE_URL", "").strip().rstrip("/")
+            base = base_raw or "https://api.openai.com/v1"
+            try:
+                live = fetch_api_models(api_key, base)
+                if live:
+                    return live
+            except Exception:
+                pass
     if normalized == "custom":
         base_url = _get_custom_base_url()
         if base_url:
@@ -1890,6 +2007,51 @@ def fetch_github_model_catalog(
     return None
 
 
+# ─── Copilot catalog context-window helpers ─────────────────────────────────
+
+# Module-level cache: {model_id: max_prompt_tokens}
+_copilot_context_cache: dict[str, int] = {}
+_copilot_context_cache_time: float = 0.0
+_COPILOT_CONTEXT_CACHE_TTL = 3600  # 1 hour
+
+
+def get_copilot_model_context(model_id: str, api_key: Optional[str] = None) -> Optional[int]:
+    """Look up max_prompt_tokens for a Copilot model from the live /models API.
+
+    Results are cached in-process for 1 hour to avoid repeated API calls.
+    Returns the token limit or None if not found.
+    """
+    global _copilot_context_cache, _copilot_context_cache_time
+
+    # Serve from cache if fresh
+    if _copilot_context_cache and (time.time() - _copilot_context_cache_time < _COPILOT_CONTEXT_CACHE_TTL):
+        if model_id in _copilot_context_cache:
+            return _copilot_context_cache[model_id]
+        # Cache is fresh but model not in it — don't re-fetch
+        return None
+
+    # Fetch and populate cache
+    catalog = fetch_github_model_catalog(api_key=api_key)
+    if not catalog:
+        return None
+
+    cache: dict[str, int] = {}
+    for item in catalog:
+        mid = str(item.get("id") or "").strip()
+        if not mid:
+            continue
+        caps = item.get("capabilities") or {}
+        limits = caps.get("limits") or {}
+        max_prompt = limits.get("max_prompt_tokens")
+        if isinstance(max_prompt, int) and max_prompt > 0:
+            cache[mid] = max_prompt
+
+    _copilot_context_cache = cache
+    _copilot_context_cache_time = time.time()
+
+    return cache.get(model_id)
+
+
 def _is_github_models_base_url(base_url: Optional[str]) -> bool:
     normalized = (base_url or "").strip().rstrip("/").lower()
     return (
@@ -1923,6 +2085,7 @@ _COPILOT_MODEL_ALIASES = {
     "openai/o4-mini": "gpt-5-mini",
     "anthropic/claude-opus-4.6": "claude-opus-4.6",
     "anthropic/claude-sonnet-4.6": "claude-sonnet-4.6",
+    "anthropic/claude-sonnet-4": "claude-sonnet-4",
     "anthropic/claude-sonnet-4.5": "claude-sonnet-4.5",
     "anthropic/claude-haiku-4.5": "claude-haiku-4.5",
     # Dash-notation fallbacks: Hermes' default Claude IDs elsewhere use
@@ -1932,10 +2095,12 @@ _COPILOT_MODEL_ALIASES = {
     # "model_not_supported".  See issue #6879.
     "claude-opus-4-6": "claude-opus-4.6",
     "claude-sonnet-4-6": "claude-sonnet-4.6",
+    "claude-sonnet-4-0": "claude-sonnet-4",
     "claude-sonnet-4-5": "claude-sonnet-4.5",
     "claude-haiku-4-5": "claude-haiku-4.5",
     "anthropic/claude-opus-4-6": "claude-opus-4.6",
     "anthropic/claude-sonnet-4-6": "claude-sonnet-4.6",
+    "anthropic/claude-sonnet-4-0": "claude-sonnet-4",
     "anthropic/claude-sonnet-4-5": "claude-sonnet-4.5",
     "anthropic/claude-haiku-4-5": "claude-haiku-4.5",
 }
@@ -2160,8 +2325,15 @@ def probe_api_models(
     api_key: Optional[str],
     base_url: Optional[str],
     timeout: float = 5.0,
+    api_mode: Optional[str] = None,
 ) -> dict[str, Any]:
-    """Probe an OpenAI-compatible ``/models`` endpoint with light URL heuristics."""
+    """Probe a ``/models`` endpoint with light URL heuristics.
+
+    For ``anthropic_messages`` mode, uses ``x-api-key`` and
+    ``anthropic-version`` headers (Anthropic's native auth) instead of
+    ``Authorization: Bearer``.  The response shape (``data[].id``) is
+    identical, so the same parser works for both.
+    """
     normalized = (base_url or "").strip().rstrip("/")
     if not normalized:
         return {
@@ -2193,7 +2365,10 @@ def probe_api_models(
 
     tried: list[str] = []
     headers: dict[str, str] = {"User-Agent": _HERMES_USER_AGENT}
-    if api_key:
+    if api_key and api_mode == "anthropic_messages":
+        headers["x-api-key"] = api_key
+        headers["anthropic-version"] = "2023-06-01"
+    elif api_key:
         headers["Authorization"] = f"Bearer {api_key}"
     if normalized.startswith(COPILOT_BASE_URL):
         headers.update(copilot_default_headers())
@@ -2235,7 +2410,10 @@ def _fetch_ai_gateway_models(timeout: float = 5.0) -> Optional[list[str]]:
         base_url = AI_GATEWAY_BASE_URL
 
     url = base_url.rstrip("/") + "/models"
-    headers: dict[str, str] = {"Authorization": f"Bearer {api_key}"}
+    headers: dict[str, str] = {
+        "Authorization": f"Bearer {api_key}",
+        "User-Agent": _HERMES_USER_AGENT,
+    }
     req = urllib.request.Request(url, headers=headers)
     try:
         with urllib.request.urlopen(req, timeout=timeout) as resp:
@@ -2255,13 +2433,14 @@ def fetch_api_models(
     api_key: Optional[str],
     base_url: Optional[str],
     timeout: float = 5.0,
+    api_mode: Optional[str] = None,
 ) -> Optional[list[str]]:
     """Fetch the list of available model IDs from the provider's ``/models`` endpoint.
 
     Returns a list of model ID strings, or ``None`` if the endpoint could not
     be reached (network error, timeout, auth failure, etc.).
     """
-    return probe_api_models(api_key, base_url, timeout=timeout).get("models")
+    return probe_api_models(api_key, base_url, timeout=timeout, api_mode=api_mode).get("models")
 
 
 # ---------------------------------------------------------------------------
@@ -2389,6 +2568,7 @@ def validate_requested_model(
     *,
     api_key: Optional[str] = None,
     base_url: Optional[str] = None,
+    api_mode: Optional[str] = None,
 ) -> dict[str, Any]:
     """
     Validate a ``/model`` value for the active provider.
@@ -2430,7 +2610,11 @@ def validate_requested_model(
         }
 
     if normalized == "custom":
-        probe = probe_api_models(api_key, base_url)
+        # Try probing with correct auth for the api_mode.
+        if api_mode == "anthropic_messages":
+            probe = probe_api_models(api_key, base_url, api_mode=api_mode)
+        else:
+            probe = probe_api_models(api_key, base_url)
         api_models = probe.get("models")
         if api_models is not None:
             if requested_for_lookup in set(api_models):
@@ -2469,8 +2653,8 @@ def validate_requested_model(
                 )
 
             return {
-                "accepted": False,
-                "persist": False,
+                "accepted": True,
+                "persist": True,
                 "recognized": False,
                 "message": message,
             }
@@ -2479,12 +2663,17 @@ def validate_requested_model(
             f"Note: could not reach this custom endpoint's model listing at `{probe.get('probed_url')}`. "
             f"Hermes will still save `{requested}`, but the endpoint should expose `/models` for verification."
         )
+        if api_mode == "anthropic_messages":
+            message += (
+                "\n  Many Anthropic-compatible proxies do not implement the Models API "
+                "(GET /v1/models).  The model name has been accepted without verification."
+            )
         if probe.get("suggested_base_url"):
             message += f"\n  If this server expects `/v1`, try base URL: `{probe.get('suggested_base_url')}`"
 
         return {
-            "accepted": False,
-            "persist": False,
+            "accepted": api_mode == "anthropic_messages",
+            "persist": True,
             "recognized": False,
             "message": message,
         }
@@ -2572,10 +2761,100 @@ def validate_requested_model(
                 ),
             }
 
+    # Native Anthropic provider: /v1/models requires x-api-key (or Bearer for
+    # OAuth) plus anthropic-version headers.  The generic OpenAI-style probe
+    # below uses plain Bearer auth and 401s against Anthropic, so dispatch to
+    # the native fetcher which handles both API keys and Claude-Code OAuth
+    # tokens.  (The api_mode=="anthropic_messages" branch below handles the
+    # Messages-API transport case separately.)
+    if normalized == "anthropic":
+        anthropic_models = _fetch_anthropic_models()
+        if anthropic_models is not None:
+            if requested_for_lookup in set(anthropic_models):
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "message": None,
+                }
+            auto = get_close_matches(requested_for_lookup, anthropic_models, n=1, cutoff=0.9)
+            if auto:
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "corrected_model": auto[0],
+                    "message": f"Auto-corrected `{requested}` → `{auto[0]}`",
+                }
+            suggestions = get_close_matches(requested, anthropic_models, n=3, cutoff=0.5)
+            suggestion_text = ""
+            if suggestions:
+                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
+            # Accept anyway — Anthropic sometimes gates newer/preview models
+            # (e.g. snapshot IDs, early-access releases) behind accounts
+            # even though they aren't listed on /v1/models.
+            return {
+                "accepted": True,
+                "persist": True,
+                "recognized": False,
+                "message": (
+                    f"Note: `{requested}` was not found in Anthropic's /v1/models listing. "
+                    f"It may still work if you have early-access or snapshot IDs."
+                    f"{suggestion_text}"
+                ),
+            }
+        # _fetch_anthropic_models returned None — no token resolvable or
+        # network failure.  Fall through to the generic warning below.
+
+    # Anthropic Messages API: many proxies don't implement /v1/models.
+    # Try probing with correct auth; if it fails, accept with a warning.
+    if api_mode == "anthropic_messages":
+        api_models = fetch_api_models(api_key, base_url, api_mode=api_mode)
+        if api_models is not None:
+            if requested_for_lookup in set(api_models):
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "message": None,
+                }
+            auto = get_close_matches(requested_for_lookup, api_models, n=1, cutoff=0.9)
+            if auto:
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "corrected_model": auto[0],
+                    "message": f"Auto-corrected `{requested}` → `{auto[0]}`",
+                }
+        # Probe failed or model not found — accept anyway (proxy likely
+        # doesn't implement the Anthropic Models API).
+        return {
+            "accepted": True,
+            "persist": True,
+            "recognized": False,
+            "message": (
+                f"Note: could not verify `{requested}` against this endpoint's "
+                f"model listing.  Many Anthropic-compatible proxies do not "
+                f"implement GET /v1/models.  The model name has been accepted "
+                f"without verification."
+            ),
+        }
+
     # Probe the live API to check if the model actually exists
     api_models = fetch_api_models(api_key, base_url)
 
     if api_models is not None:
+        # Gemini's OpenAI-compat /v1beta/openai/models endpoint returns IDs
+        # prefixed with "models/" (e.g. "models/gemini-2.5-flash") — native
+        # Gemini-API convention.  Our curated list and user input both use
+        # the bare ID, so a direct set-membership check drops every known
+        # Gemini model.  Strip the prefix before comparison.  See #12532.
+        if normalized == "gemini":
+            api_models = [
+                m[len("models/"):] if isinstance(m, str) and m.startswith("models/") else m
+                for m in api_models
+            ]
         if requested_for_lookup in set(api_models):
             # API confirmed the model exists
             return {

hermes_cli/oneshot.py

@@ -0,0 +1,202 @@
+"""Oneshot (-z) mode: send a prompt, get the final content block, exit.
+
+Bypasses cli.py entirely.  No banner, no spinner, no session_id line,
+no stderr chatter.  Just the agent's final text to stdout.
+
+Toolsets = whatever the user has configured for "cli" in `hermes tools`.
+Rules / memory / AGENTS.md / preloaded skills = same as a normal chat turn.
+Approvals = auto-bypassed (HERMES_YOLO_MODE=1 is set for the call).
+Working directory = the user's CWD (AGENTS.md etc. resolve from there as usual).
+
+Model / provider selection mirrors `hermes chat`:
+    - Both optional. If omitted, use the user's configured default.
+    - If both given, pair them exactly as given.
+    - If only --model given, auto-detect the provider that serves it.
+    - If only --provider given, error out (ambiguous — caller must pick a model).
+
+Env var fallbacks (used when the corresponding arg is not passed):
+    - HERMES_INFERENCE_MODEL
+    - HERMES_INFERENCE_PROVIDER  (already read by resolve_runtime_provider)
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+import sys
+from contextlib import redirect_stderr, redirect_stdout
+from typing import Optional
+
+
+def run_oneshot(
+    prompt: str,
+    model: Optional[str] = None,
+    provider: Optional[str] = None,
+) -> int:
+    """Execute a single prompt and print only the final content block.
+
+    Args:
+        prompt: The user message to send.
+        model: Optional model override. Falls back to HERMES_INFERENCE_MODEL
+            env var, then config.yaml's model.default / model.model.
+        provider: Optional provider override. Falls back to
+            HERMES_INFERENCE_PROVIDER env var, then config.yaml's model.provider,
+            then "auto".
+
+    Returns the exit code.  Caller should sys.exit() with the return.
+    """
+    # Silence every stdlib logger for the duration.  AIAgent, tools, and
+    # provider adapters all log to stderr through the root logger; file
+    # handlers added by setup_logging() keep working (they're attached to
+    # the root logger's handler list, not affected by level), but no
+    # bytes reach the terminal.
+    logging.disable(logging.CRITICAL)
+
+    # --provider without --model is ambiguous: carrying the user's configured
+    # model across to a different provider is usually wrong (that provider may
+    # not host it), and silently picking the provider's catalog default hides
+    # the mismatch.  Require the caller to be explicit.  Validate BEFORE the
+    # stderr redirect so the message actually reaches the terminal.
+    env_model_early = os.getenv("HERMES_INFERENCE_MODEL", "").strip()
+    if provider and not ((model or "").strip() or env_model_early):
+        sys.stderr.write(
+            "hermes -z: --provider requires --model (or HERMES_INFERENCE_MODEL). "
+            "Pass both explicitly, or neither to use your configured defaults.\n"
+        )
+        return 2
+
+    # Auto-approve any shell / tool approvals.  Non-interactive by
+    # definition — a prompt would hang forever.
+    os.environ["HERMES_YOLO_MODE"] = "1"
+    os.environ["HERMES_ACCEPT_HOOKS"] = "1"
+
+    # Redirect stderr AND stdout to devnull for the entire call tree.
+    # We'll print the final response to the real stdout at the end.
+    real_stdout = sys.stdout
+    devnull = open(os.devnull, "w")
+
+    try:
+        with redirect_stdout(devnull), redirect_stderr(devnull):
+            response = _run_agent(prompt, model=model, provider=provider)
+    finally:
+        try:
+            devnull.close()
+        except Exception:
+            pass
+
+    if response:
+        real_stdout.write(response)
+        if not response.endswith("\n"):
+            real_stdout.write("\n")
+        real_stdout.flush()
+    return 0
+
+
+def _run_agent(
+    prompt: str,
+    model: Optional[str] = None,
+    provider: Optional[str] = None,
+) -> str:
+    """Build an AIAgent exactly like a normal CLI chat turn would, then
+    run a single conversation.  Returns the final response string."""
+    # Imports are local so they don't run when hermes is invoked for
+    # other commands (keeps top-level CLI startup cheap).
+    from hermes_cli.config import load_config
+    from hermes_cli.models import detect_provider_for_model
+    from hermes_cli.runtime_provider import resolve_runtime_provider
+    from hermes_cli.tools_config import _get_platform_tools
+    from run_agent import AIAgent
+
+    cfg = load_config()
+
+    # Resolve effective model: explicit arg → env var → config.
+    model_cfg = cfg.get("model") or {}
+    if isinstance(model_cfg, str):
+        cfg_model = model_cfg
+    else:
+        cfg_model = model_cfg.get("default") or model_cfg.get("model") or ""
+
+    env_model = os.getenv("HERMES_INFERENCE_MODEL", "").strip()
+    effective_model = (model or "").strip() or env_model or cfg_model
+
+    # Resolve effective provider: explicit arg → (auto-detect from model if
+    # model was explicit) → env / config (handled inside resolve_runtime_provider).
+    #
+    # When --model is given without --provider, auto-detect the provider that
+    # serves that model — same semantic as `/model <name>` in an interactive
+    # session.  Without this, resolve_runtime_provider() would fall back to
+    # the user's configured default provider, which may not host the model
+    # the caller just asked for.
+    effective_provider = (provider or "").strip() or None
+    if effective_provider is None and (model or env_model):
+        # Only auto-detect when the model was explicitly requested via arg or
+        # env var (not when it came from config — that's the "use my defaults"
+        # path and the configured provider is already correct).
+        explicit_model = (model or "").strip() or env_model
+        if explicit_model:
+            cfg_provider = ""
+            if isinstance(model_cfg, dict):
+                cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
+            current_provider = (
+                cfg_provider
+                or os.getenv("HERMES_INFERENCE_PROVIDER", "").strip().lower()
+                or "auto"
+            )
+            detected = detect_provider_for_model(explicit_model, current_provider)
+            if detected:
+                effective_provider, effective_model = detected
+
+    runtime = resolve_runtime_provider(
+        requested=effective_provider,
+        target_model=effective_model or None,
+    )
+
+    # Pull in whatever toolsets the user has enabled for "cli".
+    # sorted() gives stable ordering; set→list for AIAgent's signature.
+    toolsets_list = sorted(_get_platform_tools(cfg, "cli"))
+
+    agent = AIAgent(
+        api_key=runtime.get("api_key"),
+        base_url=runtime.get("base_url"),
+        provider=runtime.get("provider"),
+        api_mode=runtime.get("api_mode"),
+        model=effective_model,
+        enabled_toolsets=toolsets_list,
+        quiet_mode=True,
+        platform="cli",
+        credential_pool=runtime.get("credential_pool"),
+        # Interactive callbacks are intentionally NOT wired beyond this
+        # one.  In oneshot mode there's no user sitting at a terminal:
+        #   - clarify  → returns a synthetic "pick a default" instruction
+        #                so the agent continues instead of stalling on
+        #                the tool's built-in "not available" error
+        #   - sudo password prompt → terminal_tool gates on
+        #                HERMES_INTERACTIVE which we never set
+        #   - shell-hook approval → auto-approved via HERMES_ACCEPT_HOOKS=1
+        #                (set above); also falls back to deny on non-tty
+        #   - dangerous-command approval → bypassed via HERMES_YOLO_MODE=1
+        #   - skill secret capture → returns gracefully when no callback set
+        clarify_callback=_oneshot_clarify_callback,
+    )
+
+    # Belt-and-braces: make sure AIAgent doesn't invoke any streaming
+    # display callbacks that would bypass our stdout capture.
+    agent.suppress_status_output = True
+    agent.stream_delta_callback = None
+    agent.tool_gen_callback = None
+
+    return agent.chat(prompt) or ""
+
+
+def _oneshot_clarify_callback(question: str, choices=None) -> str:
+    """Clarify is disabled in oneshot mode — tell the agent to pick a
+    default and proceed instead of stalling or erroring."""
+    if choices:
+        return (
+            f"[oneshot mode: no user available. Pick the best option from "
+            f"{choices} using your own judgment and continue.]"
+        )
+    return (
+        "[oneshot mode: no user available. Make the most reasonable "
+        "assumption you can and continue.]"
+    )

hermes_cli/plugins.py

@@ -71,6 +71,14 @@ VALID_HOOKS: Set[str] = {
     "on_session_finalize",
     "on_session_reset",
     "subagent_stop",
+    # Gateway pre-dispatch hook. Fired once per incoming MessageEvent
+    # after the internal-event guard but BEFORE auth/pairing and agent
+    # dispatch. Plugins may return a dict to influence flow:
+    #   {"action": "skip",    "reason": "..."}  -> drop message (no reply)
+    #   {"action": "rewrite", "text": "..."}    -> replace event.text, continue
+    #   {"action": "allow"}  /  None             -> normal dispatch
+    # Kwargs: event: MessageEvent, gateway: GatewayRunner, session_store.
+    "pre_gateway_dispatch",
 }
 
 ENTRY_POINTS_GROUP = "hermes_agent.plugins"

hermes_cli/providers.py

@@ -116,6 +116,10 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         transport="openai_chat",
         base_url_env_var="DASHSCOPE_BASE_URL",
     ),
+    "alibaba-coding-plan": HermesOverlay(
+        transport="openai_chat",
+        base_url_env_var="ALIBABA_CODING_PLAN_BASE_URL",
+    ),
     "vercel": HermesOverlay(
         transport="openai_chat",
         is_aggregator=True,
@@ -163,6 +167,12 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         transport="openai_chat",
         base_url_env_var="OLLAMA_BASE_URL",
     ),
+    # Azure Foundry: supports both OpenAI-style and Anthropic-style endpoints.
+    # The transport is determined at runtime from config.yaml model.api_mode.
+    "azure-foundry": HermesOverlay(
+        transport="openai_chat",  # default; overridden by api_mode in config
+        base_url_env_var="AZURE_FOUNDRY_BASE_URL",
+    ),
 }
 
 
@@ -259,6 +269,9 @@ ALIASES: Dict[str, str] = {
     "aliyun": "alibaba",
     "qwen": "alibaba",
     "alibaba-cloud": "alibaba",
+    "alibaba_coding": "alibaba-coding-plan",
+    "alibaba-coding": "alibaba-coding-plan",
+    "alibaba_coding_plan": "alibaba-coding-plan",
 
     # google-gemini-cli (OAuth + Code Assist)
     "gemini-cli": "google-gemini-cli",

hermes_cli/pty_bridge.py

@@ -0,0 +1,229 @@
+"""PTY bridge for `hermes dashboard` chat tab.
+
+Wraps a child process behind a pseudo-terminal so its ANSI output can be
+streamed to a browser-side terminal emulator (xterm.js) and typed
+keystrokes can be fed back in.  The only caller today is the
+``/api/pty`` WebSocket endpoint in ``hermes_cli.web_server``.
+
+Design constraints:
+
+* **POSIX-only.**  Hermes Agent supports Windows exclusively via WSL, which
+  exposes a native POSIX PTY via ``openpty(3)``.  Native Windows Python
+  has no PTY; :class:`PtyUnavailableError` is raised with a user-readable
+  install/platform message so the dashboard can render a banner instead of
+  crashing.
+* **Zero Node dependency on the server side.**  We use :mod:`ptyprocess`,
+  which is a pure-Python wrapper around the OS calls.  The browser talks
+  to the same ``hermes --tui`` binary it would launch from the CLI, so
+  every TUI feature (slash popover, model picker, tool rows, markdown,
+  skin engine, clarify/sudo/approval prompts) ships automatically.
+* **Byte-safe I/O.**  Reads and writes go through the PTY master fd
+  directly — we avoid :class:`ptyprocess.PtyProcessUnicode` because
+  streaming ANSI is inherently byte-oriented and UTF-8 boundaries may land
+  mid-read.
+"""
+
+from __future__ import annotations
+
+import errno
+import fcntl
+import os
+import select
+import signal
+import struct
+import sys
+import termios
+import time
+from typing import Optional, Sequence
+
+try:
+    import ptyprocess  # type: ignore
+    _PTY_AVAILABLE = not sys.platform.startswith("win")
+except ImportError:  # pragma: no cover - dev env without ptyprocess
+    ptyprocess = None  # type: ignore
+    _PTY_AVAILABLE = False
+
+
+__all__ = ["PtyBridge", "PtyUnavailableError"]
+
+
+class PtyUnavailableError(RuntimeError):
+    """Raised when a PTY cannot be created on this platform.
+
+    Today this means native Windows (no ConPTY bindings) or a dev
+    environment missing the ``ptyprocess`` dependency.  The dashboard
+    surfaces the message to the user as a chat-tab banner.
+    """
+
+
+class PtyBridge:
+    """Thin wrapper around ``ptyprocess.PtyProcess`` for byte streaming.
+
+    Not thread-safe.  A single bridge is owned by the WebSocket handler
+    that spawned it; the reader runs in an executor thread while writes
+    happen on the event-loop thread.  Both sides are OK because the
+    kernel PTY is the actual synchronization point — we never call
+    :mod:`ptyprocess` methods concurrently, we only call ``os.read`` and
+    ``os.write`` on the master fd, which is safe.
+    """
+
+    def __init__(self, proc: "ptyprocess.PtyProcess"):  # type: ignore[name-defined]
+        self._proc = proc
+        self._fd: int = proc.fd
+        self._closed = False
+
+    # -- lifecycle --------------------------------------------------------
+
+    @classmethod
+    def is_available(cls) -> bool:
+        """True if a PTY can be spawned on this platform."""
+        return bool(_PTY_AVAILABLE)
+
+    @classmethod
+    def spawn(
+        cls,
+        argv: Sequence[str],
+        *,
+        cwd: Optional[str] = None,
+        env: Optional[dict] = None,
+        cols: int = 80,
+        rows: int = 24,
+    ) -> "PtyBridge":
+        """Spawn ``argv`` behind a new PTY and return a bridge.
+
+        Raises :class:`PtyUnavailableError` if the platform can't host a
+        PTY.  Raises :class:`FileNotFoundError` or :class:`OSError` for
+        ordinary exec failures (missing binary, bad cwd, etc.).
+        """
+        if not _PTY_AVAILABLE:
+            if sys.platform.startswith("win"):
+                raise PtyUnavailableError(
+                    "Pseudo-terminals are unavailable on this platform. "
+                    "Hermes Agent supports Windows only via WSL."
+                )
+            if ptyprocess is None:
+                raise PtyUnavailableError(
+                    "The `ptyprocess` package is missing. "
+                    "Install with: pip install ptyprocess "
+                    "(or pip install -e '.[pty]')."
+                )
+            raise PtyUnavailableError("Pseudo-terminals are unavailable.")
+        # Let caller-supplied env fully override inheritance; if they pass
+        # None we inherit the server's env (same semantics as subprocess).
+        spawn_env = os.environ.copy() if env is None else env
+        proc = ptyprocess.PtyProcess.spawn(  # type: ignore[union-attr]
+            list(argv),
+            cwd=cwd,
+            env=spawn_env,
+            dimensions=(rows, cols),
+        )
+        return cls(proc)
+
+    @property
+    def pid(self) -> int:
+        return int(self._proc.pid)
+
+    def is_alive(self) -> bool:
+        if self._closed:
+            return False
+        try:
+            return bool(self._proc.isalive())
+        except Exception:
+            return False
+
+    # -- I/O --------------------------------------------------------------
+
+    def read(self, timeout: float = 0.2) -> Optional[bytes]:
+        """Read up to 64 KiB of raw bytes from the PTY master.
+
+        Returns:
+            * bytes — zero or more bytes of child output
+            * empty bytes (``b""``) — no data available within ``timeout``
+            * None — child has exited and the master fd is at EOF
+
+        Never blocks longer than ``timeout`` seconds.  Safe to call after
+        :meth:`close`; returns ``None`` in that case.
+        """
+        if self._closed:
+            return None
+        try:
+            readable, _, _ = select.select([self._fd], [], [], timeout)
+        except (OSError, ValueError):
+            return None
+        if not readable:
+            return b""
+        try:
+            data = os.read(self._fd, 65536)
+        except OSError as exc:
+            # EIO on Linux = slave side closed.  EBADF = already closed.
+            if exc.errno in (errno.EIO, errno.EBADF):
+                return None
+            raise
+        if not data:
+            return None
+        return data
+
+    def write(self, data: bytes) -> None:
+        """Write raw bytes to the PTY master (i.e. the child's stdin)."""
+        if self._closed or not data:
+            return
+        # os.write can return a short write under load; loop until drained.
+        view = memoryview(data)
+        while view:
+            try:
+                n = os.write(self._fd, view)
+            except OSError as exc:
+                if exc.errno in (errno.EIO, errno.EBADF, errno.EPIPE):
+                    return
+                raise
+            if n <= 0:
+                return
+            view = view[n:]
+
+    def resize(self, cols: int, rows: int) -> None:
+        """Forward a terminal resize to the child via ``TIOCSWINSZ``."""
+        if self._closed:
+            return
+        # struct winsize: rows, cols, xpixel, ypixel (all unsigned short)
+        winsize = struct.pack("HHHH", max(1, rows), max(1, cols), 0, 0)
+        try:
+            fcntl.ioctl(self._fd, termios.TIOCSWINSZ, winsize)
+        except OSError:
+            pass
+
+    # -- teardown ---------------------------------------------------------
+
+    def close(self) -> None:
+        """Terminate the child (SIGTERM → 0.5s grace → SIGKILL) and close fds.
+
+        Idempotent.  Reaping the child is important so we don't leak
+        zombies across the lifetime of the dashboard process.
+        """
+        if self._closed:
+            return
+        self._closed = True
+
+        # SIGHUP is the conventional "your terminal went away" signal.
+        # We escalate if the child ignores it.
+        for sig in (signal.SIGHUP, signal.SIGTERM, signal.SIGKILL):
+            if not self._proc.isalive():
+                break
+            try:
+                self._proc.kill(sig)
+            except Exception:
+                pass
+            deadline = time.monotonic() + 0.5
+            while self._proc.isalive() and time.monotonic() < deadline:
+                time.sleep(0.02)
+
+        try:
+            self._proc.close(force=True)
+        except Exception:
+            pass
+
+    # Context-manager sugar — handy in tests and ad-hoc scripts.
+    def __enter__(self) -> "PtyBridge":
+        return self
+
+    def __exit__(self, *_exc) -> None:
+        self.close()

hermes_cli/runtime_provider.py

@@ -36,6 +36,29 @@ def _normalize_custom_provider_name(value: str) -> str:
     return value.strip().lower().replace(" ", "-")
 
 
+def _loopback_hostname(host: str) -> bool:
+    h = (host or "").lower().rstrip(".")
+    return h in {"localhost", "127.0.0.1", "::1", "0.0.0.0"}
+
+
+def _config_base_url_trustworthy_for_bare_custom(cfg_base_url: str, cfg_provider: str) -> bool:
+    """Decide whether ``model.base_url`` may back bare ``custom`` runtime resolution.
+
+    GitHub #14676: the model picker can select Custom while ``model.provider`` still reflects a
+    previous provider. Reject non-loopback URLs unless the YAML provider is already ``custom``,
+    so a stale OpenRouter/Z.ai base_url cannot hijack local ``custom`` sessions.
+    """
+    cfg_provider_norm = (cfg_provider or "").strip().lower()
+    bu = (cfg_base_url or "").strip()
+    if not bu:
+        return False
+    if cfg_provider_norm == "custom":
+        return True
+    if base_url_host_matches(bu, "openrouter.ai"):
+        return False
+    return _loopback_hostname(base_url_hostname(bu))
+
+
 def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
     """Auto-detect api_mode from the resolved base URL.
 
@@ -160,8 +183,16 @@ def _resolve_runtime_from_pool_entry(
     requested_provider: str,
     model_cfg: Optional[Dict[str, Any]] = None,
     pool: Optional[CredentialPool] = None,
+    target_model: Optional[str] = None,
 ) -> Dict[str, Any]:
     model_cfg = model_cfg or _get_model_config()
+    # When the caller is resolving for a specific target model (e.g. a /model
+    # mid-session switch), prefer that over the persisted model.default. This
+    # prevents api_mode being computed from a stale config default that no
+    # longer matches the model actually being used — the bug that caused
+    # opencode-zen /v1 to be stripped for chat_completions requests when
+    # config.default was still a Claude model.
+    effective_model = (target_model or model_cfg.get("default") or "")
     base_url = (getattr(entry, "runtime_base_url", None) or getattr(entry, "base_url", None) or "").rstrip("/")
     api_key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
     api_mode = "chat_completions"
@@ -190,6 +221,19 @@ def _resolve_runtime_from_pool_entry(
     elif provider == "copilot":
         api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
         base_url = base_url or PROVIDER_REGISTRY["copilot"].inference_base_url
+    elif provider == "azure-foundry":
+        # Azure Foundry: read api_mode and base_url from config
+        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
+        if cfg_provider == "azure-foundry":
+            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
+            if cfg_base_url:
+                base_url = cfg_base_url
+            configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
+            if configured_mode:
+                api_mode = configured_mode
+        # For Anthropic-style endpoints, strip /v1 suffix
+        if api_mode == "anthropic_messages":
+            base_url = re.sub(r"/v1/?$", "", base_url)
     else:
         configured_provider = str(model_cfg.get("provider") or "").strip().lower()
         # Honour model.base_url from config.yaml when the configured provider
@@ -207,7 +251,7 @@ def _resolve_runtime_from_pool_entry(
             api_mode = configured_mode
         elif provider in ("opencode-zen", "opencode-go"):
             from hermes_cli.models import opencode_model_api_mode
-            api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
+            api_mode = opencode_model_api_mode(provider, effective_model)
         else:
             # Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
             # Kimi /coding, api.openai.com → codex_responses, api.x.ai →
@@ -323,12 +367,16 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
                 # Found match by provider key
                 base_url = entry.get("api") or entry.get("url") or entry.get("base_url") or ""
                 if base_url:
-                    return {
+                    result = {
                         "name": entry.get("name", ep_name),
                         "base_url": base_url.strip(),
                         "api_key": resolved_api_key,
                         "model": entry.get("default_model", ""),
                     }
+                    api_mode = _parse_api_mode(entry.get("api_mode"))
+                    if api_mode:
+                        result["api_mode"] = api_mode
+                    return result
             # Also check the 'name' field if present
             display_name = entry.get("name", "")
             if display_name:
@@ -337,12 +385,16 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
                     # Found match by display name
                     base_url = entry.get("api") or entry.get("url") or entry.get("base_url") or ""
                     if base_url:
-                        return {
+                        result = {
                             "name": display_name,
                             "base_url": base_url.strip(),
                             "api_key": resolved_api_key,
                             "model": entry.get("default_model", ""),
                         }
+                        api_mode = _parse_api_mode(entry.get("api_mode"))
+                        if api_mode:
+                            result["api_mode"] = api_mode
+                        return result
 
     # Fall back to custom_providers: list (legacy format)
     custom_providers = config.get("custom_providers")
@@ -464,6 +516,7 @@ def _resolve_openrouter_runtime(
     cfg_provider = cfg_provider.strip().lower()
 
     env_openrouter_base_url = os.getenv("OPENROUTER_BASE_URL", "").strip()
+    env_custom_base_url = os.getenv("CUSTOM_BASE_URL", "").strip()
 
     # Use config base_url when available and the provider context matches.
     # OPENAI_BASE_URL env var is no longer consulted — config.yaml is
@@ -473,11 +526,14 @@ def _resolve_openrouter_runtime(
         if requested_norm == "auto":
             if not cfg_provider or cfg_provider == "auto":
                 use_config_base_url = True
-        elif requested_norm == "custom" and cfg_provider == "custom":
+        elif requested_norm == "custom" and _config_base_url_trustworthy_for_bare_custom(
+            cfg_base_url, cfg_provider
+        ):
             use_config_base_url = True
 
     base_url = (
         (explicit_base_url or "").strip()
+        or env_custom_base_url
         or (cfg_base_url.strip() if use_config_base_url else "")
         or env_openrouter_base_url
         or OPENROUTER_BASE_URL
@@ -546,6 +602,71 @@ def _resolve_openrouter_runtime(
     }
 
 
+def _resolve_azure_foundry_runtime(
+    *,
+    requested_provider: str,
+    model_cfg: Dict[str, Any],
+    explicit_api_key: Optional[str] = None,
+    explicit_base_url: Optional[str] = None,
+) -> Dict[str, Any]:
+    """Resolve an Azure Foundry runtime entry.
+
+    Reads ``model.base_url`` + ``model.api_mode`` from config.yaml (or
+    explicit overrides), pulls the API key from ``.env`` / env var, and
+    strips a trailing ``/v1`` for Anthropic-style endpoints because the
+    Anthropic SDK appends ``/v1/messages`` internally.
+
+    Raises :class:`AuthError` when required values are missing.
+    """
+    explicit_api_key = str(explicit_api_key or "").strip()
+    explicit_base_url_clean = str(explicit_base_url or "").strip().rstrip("/")
+
+    cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
+    cfg_base_url = ""
+    cfg_api_mode = "chat_completions"
+    if cfg_provider == "azure-foundry":
+        cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
+        cfg_api_mode = _parse_api_mode(model_cfg.get("api_mode")) or "chat_completions"
+
+    env_base_url = os.getenv("AZURE_FOUNDRY_BASE_URL", "").strip().rstrip("/")
+    base_url = explicit_base_url_clean or cfg_base_url or env_base_url
+    if not base_url:
+        raise AuthError(
+            "Azure Foundry requires a base URL. Set it via 'hermes model' or "
+            "the AZURE_FOUNDRY_BASE_URL environment variable."
+        )
+
+    api_key = explicit_api_key
+    if not api_key:
+        try:
+            from hermes_cli.config import get_env_value
+            api_key = get_env_value("AZURE_FOUNDRY_API_KEY") or ""
+        except Exception:
+            api_key = ""
+    if not api_key:
+        api_key = os.getenv("AZURE_FOUNDRY_API_KEY", "").strip()
+    if not api_key:
+        raise AuthError(
+            "Azure Foundry requires an API key. Set AZURE_FOUNDRY_API_KEY in "
+            "~/.hermes/.env or run 'hermes model' to configure."
+        )
+
+    # Anthropic SDK appends /v1/messages itself, so strip any trailing /v1
+    # we inherited from the configured base_url to avoid double-/v1 paths.
+    if cfg_api_mode == "anthropic_messages":
+        base_url = re.sub(r"/v1/?$", "", base_url)
+
+    source = "explicit" if (explicit_api_key or explicit_base_url) else "config"
+    return {
+        "provider": "azure-foundry",
+        "api_mode": cfg_api_mode,
+        "base_url": base_url,
+        "api_key": api_key,
+        "source": source,
+        "requested_provider": requested_provider,
+    }
+
+
 def _resolve_explicit_runtime(
     *,
     provider: str,
@@ -635,6 +756,15 @@ def _resolve_explicit_runtime(
             "requested_provider": requested_provider,
         }
 
+    # Azure Foundry: user-configured endpoint with selectable API mode
+    if provider == "azure-foundry":
+        return _resolve_azure_foundry_runtime(
+            requested_provider=requested_provider,
+            model_cfg=model_cfg,
+            explicit_api_key=explicit_api_key,
+            explicit_base_url=explicit_base_url,
+        )
+
     pconfig = PROVIDER_REGISTRY.get(provider)
     if pconfig and pconfig.auth_type == "api_key":
         env_url = ""
@@ -689,10 +819,54 @@ def resolve_runtime_provider(
     requested: Optional[str] = None,
     explicit_api_key: Optional[str] = None,
     explicit_base_url: Optional[str] = None,
+    target_model: Optional[str] = None,
 ) -> Dict[str, Any]:
-    """Resolve runtime provider credentials for agent execution."""
+    """Resolve runtime provider credentials for agent execution.
+
+    target_model: Optional override for model_cfg.get("default") when
+    computing provider-specific api_mode (e.g. OpenCode Zen/Go where different
+    models route through different API surfaces). Callers performing an
+    explicit mid-session model switch should pass the new model here so
+    api_mode is derived from the model they are switching TO, not the stale
+    persisted default. Other callers can leave it None to preserve existing
+    behavior (api_mode derived from config).
+    """
     requested_provider = resolve_requested_provider(requested)
 
+    # Azure Anthropic short-circuit: when explicitly targeting an Azure endpoint
+    # with provider="anthropic", bypass _resolve_named_custom_runtime (which would
+    # return provider="custom" with chat_completions api_mode and no valid key).
+    # Instead, use the Azure key directly with anthropic_messages api_mode.
+    _eff_base = (explicit_base_url or "").strip()
+    if requested_provider == "anthropic" and "azure.com" in _eff_base:
+        _azure_key = (
+            (explicit_api_key or "").strip()
+            or os.getenv("AZURE_ANTHROPIC_KEY", "").strip()
+            or os.getenv("ANTHROPIC_API_KEY", "").strip()
+        )
+        return {
+            "provider": "anthropic",
+            "api_mode": "anthropic_messages",
+            "base_url": _eff_base.rstrip("/"),
+            "api_key": _azure_key,
+            "source": "azure-explicit",
+            "requested_provider": requested_provider,
+        }
+
+    # Azure Foundry: user-configured endpoint with selectable API mode
+    # (OpenAI-style chat_completions or Anthropic-style anthropic_messages).
+    # Resolve before the custom-runtime / pool / generic paths so Azure
+    # config is always picked up from model.base_url + model.api_mode,
+    # regardless of whether the caller passed explicit_* args.
+    if requested_provider == "azure-foundry":
+        azure_runtime = _resolve_azure_foundry_runtime(
+            requested_provider=requested_provider,
+            model_cfg=_get_model_config(),
+            explicit_api_key=explicit_api_key,
+            explicit_base_url=explicit_base_url,
+        )
+        return azure_runtime
+
     custom_runtime = _resolve_named_custom_runtime(
         requested_provider=requested_provider,
         explicit_api_key=explicit_api_key,
@@ -772,6 +946,7 @@ def resolve_runtime_provider(
                 requested_provider=requested_provider,
                 model_cfg=model_cfg,
                 pool=pool,
+                target_model=target_model,
             )
 
     if provider == "nous":
@@ -870,13 +1045,6 @@ def resolve_runtime_provider(
 
     # Anthropic (native Messages API)
     if provider == "anthropic":
-        from agent.anthropic_adapter import resolve_anthropic_token
-        token = resolve_anthropic_token()
-        if not token:
-            raise AuthError(
-                "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
-                "run 'claude setup-token', or authenticate with 'claude /login'."
-            )
         # Allow base URL override from config.yaml model.base_url, but only
         # when the configured provider is anthropic — otherwise a non-Anthropic
         # base_url (e.g. Codex endpoint) would leak into Anthropic requests.
@@ -885,6 +1053,33 @@ def resolve_runtime_provider(
         if cfg_provider == "anthropic":
             cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
         base_url = cfg_base_url or "https://api.anthropic.com"
+
+        # For Azure AI Foundry endpoints, use ANTHROPIC_API_KEY directly —
+        # Claude Code OAuth tokens (sk-ant-oat01) are not accepted by Azure.
+        # Azure keys don't start with "sk-ant-" so resolve_anthropic_token()
+        # would find the Claude Code OAuth token first (priority 3) and return
+        # that instead, causing 401s. Detect Azure endpoints and use the env
+        # key directly to bypass the OAuth priority chain.
+        _is_azure_endpoint = "azure.com" in base_url.lower() or (
+            cfg_base_url and "azure.com" in cfg_base_url.lower()
+        )
+        if _is_azure_endpoint:
+            token = (
+                os.getenv("AZURE_ANTHROPIC_KEY", "").strip()
+                or os.getenv("ANTHROPIC_API_KEY", "").strip()
+            )
+            if not token:
+                raise AuthError(
+                    "No Azure Anthropic API key found. Set AZURE_ANTHROPIC_KEY or ANTHROPIC_API_KEY."
+                )
+        else:
+            from agent.anthropic_adapter import resolve_anthropic_token
+            token = resolve_anthropic_token()
+            if not token:
+                raise AuthError(
+                    "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
+                    "run 'claude setup-token', or authenticate with 'claude /login'."
+                )
         return {
             "provider": "anthropic",
             "api_mode": "anthropic_messages",
@@ -990,7 +1185,11 @@ def resolve_runtime_provider(
                 api_mode = configured_mode
             elif provider in ("opencode-zen", "opencode-go"):
                 from hermes_cli.models import opencode_model_api_mode
-                api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
+                # Prefer the target_model from the caller (explicit mid-session
+                # switch) over the stale model.default; see _resolve_runtime_from_pool_entry
+                # for the same rationale.
+                _effective = target_model or model_cfg.get("default", "")
+                api_mode = opencode_model_api_mode(provider, _effective)
             else:
                 # Auto-detect Anthropic-compatible endpoints by URL convention
                 # (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)

hermes_cli/setup.py

@@ -500,6 +500,15 @@ def _print_setup_summary(config: dict, hermes_home):
     if get_env_value("HASS_TOKEN"):
         tool_status.append(("Smart Home (Home Assistant)", True, None))
 
+    # Spotify (OAuth via hermes auth spotify — check auth.json, not env vars)
+    try:
+        from hermes_cli.auth import get_provider_auth_state
+        _spotify_state = get_provider_auth_state("spotify") or {}
+        if _spotify_state.get("access_token") or _spotify_state.get("refresh_token"):
+            tool_status.append(("Spotify (PKCE OAuth)", True, None))
+    except Exception:
+        pass
+
     # Skills Hub
     if get_env_value("GITHUB_TOKEN"):
         tool_status.append(("Skills Hub (GitHub)", True, None))
@@ -2854,17 +2863,6 @@ SETUP_SECTIONS = [
     ("agent", "Agent Settings", setup_agent_settings),
 ]
 
-# The returning-user menu intentionally omits standalone TTS because model setup
-# already includes TTS selection and tools setup covers the rest of the provider
-# configuration. Keep this list in the same order as the visible menu entries.
-RETURNING_USER_MENU_SECTION_KEYS = [
-    "model",
-    "terminal",
-    "gateway",
-    "tools",
-    "agent",
-]
-
 
 def run_setup_wizard(args):
     """Run the interactive setup wizard.
@@ -2889,6 +2887,9 @@ def run_setup_wizard(args):
         save_config(copy.deepcopy(DEFAULT_CONFIG))
         print_success("Configuration reset to defaults.")
 
+    reconfigure_requested = bool(getattr(args, "reconfigure", False))
+    quick_requested = bool(getattr(args, "quick", False))
+
     config = load_config()
     hermes_home = get_hermes_home()
 
@@ -2980,50 +2981,36 @@ def run_setup_wizard(args):
     migration_ran = False
 
     if is_existing:
-        # ── Returning User Menu ──
-        print()
-        print_header("Welcome Back!")
-        print_success("You already have Hermes configured.")
-        print()
-
-        menu_choices = [
-            "Quick Setup - configure missing items only",
-            "Full Setup - reconfigure everything",
-            "Model & Provider",
-            "Terminal Backend",
-            "Messaging Platforms (Gateway)",
-            "Tools",
-            "Agent Settings",
-            "Exit",
-        ]
-        choice = prompt_choice("What would you like to do?", menu_choices, 0)
-
-        if choice == 0:
-            # Quick setup
+        # Existing install — default is the full-wizard reconfigure flow.
+        # Every prompt shows the current value as its default, so pressing
+        # Enter keeps it.  Opt into `--quick` for the narrow "just fill in
+        # missing items" flow (useful after a partial OpenClaw migration
+        # or when a required API key got cleared).
+        if quick_requested:
             _run_quick_setup(config, hermes_home)
             return
-        elif choice == 1:
-            # Full setup — fall through to run all sections
-            pass
-        elif choice == 7:
-            print_info("Exiting. Run 'hermes setup' again when ready.")
-            return
-        elif 2 <= choice <= 6:
-            # Individual section — map by key, not by position.
-            # SETUP_SECTIONS includes TTS but the returning-user menu skips it,
-            # so positional indexing (choice - 2) would dispatch the wrong section.
-            section_key = RETURNING_USER_MENU_SECTION_KEYS[choice - 2]
-            section = next((s for s in SETUP_SECTIONS if s[0] == section_key), None)
-            if section:
-                _, label, func = section
-                func(config)
-                save_config(config)
-                _print_setup_summary(config, hermes_home)
-            return
+
+        print()
+        print_header("Reconfigure")
+        print_success("You already have Hermes configured.")
+        print_info("Running the full wizard — each prompt shows your current value.")
+        print_info("Press Enter to keep it, or type a new value to change it.")
+        print_info("")
+        print_info("Tip: jump straight to a section with 'hermes setup model|terminal|")
+        print_info("     gateway|tools|agent', or fill only missing items with --quick.")
+        # Fall through to the "Full Setup — run all sections" block below.
+        # --reconfigure is now the default on existing installs; the flag
+        # is preserved for backwards compatibility but is a no-op here.
     else:
         # ── First-Time Setup ──
         print()
 
+        # --reconfigure / --quick on a fresh install are meaningless — fall
+        # through to the normal first-time flow.
+        if reconfigure_requested or quick_requested:
+            print_info("No existing configuration found — running first-time setup.")
+            print()
+
         # Offer OpenClaw migration before configuration begins
         migration_ran = _offer_openclaw_migration(hermes_home)
         if migration_ran:

hermes_cli/status.py

@@ -164,19 +164,26 @@ def show_status(args):
         qwen_status = {}
 
     nous_logged_in = bool(nous_status.get("logged_in"))
+    nous_error = nous_status.get("error")
+    nous_label = "logged in" if nous_logged_in else "not logged in (run: hermes auth add nous --type oauth)"
     print(
         f"  {'Nous Portal':<12}  {check_mark(nous_logged_in)} "
-        f"{'logged in' if nous_logged_in else 'not logged in (run: hermes model)'}"
+        f"{nous_label}"
     )
-    if nous_logged_in:
-        portal_url = nous_status.get("portal_base_url") or "(unknown)"
-        access_exp = _format_iso_timestamp(nous_status.get("access_expires_at"))
-        key_exp = _format_iso_timestamp(nous_status.get("agent_key_expires_at"))
-        refresh_label = "yes" if nous_status.get("has_refresh_token") else "no"
+    portal_url = nous_status.get("portal_base_url") or "(unknown)"
+    access_exp = _format_iso_timestamp(nous_status.get("access_expires_at"))
+    key_exp = _format_iso_timestamp(nous_status.get("agent_key_expires_at"))
+    refresh_label = "yes" if nous_status.get("has_refresh_token") else "no"
+    if nous_logged_in or portal_url != "(unknown)" or nous_error:
         print(f"    Portal URL: {portal_url}")
+    if nous_logged_in or nous_status.get("access_expires_at"):
         print(f"    Access exp: {access_exp}")
+    if nous_logged_in or nous_status.get("agent_key_expires_at"):
         print(f"    Key exp:    {key_exp}")
+    if nous_logged_in or nous_status.get("has_refresh_token"):
         print(f"    Refresh:    {refresh_label}")
+    if nous_error and not nous_logged_in:
+        print(f"    Error:      {nous_error}")
 
     codex_logged_in = bool(codex_status.get("logged_in"))
     print(

hermes_cli/tips.py

@@ -10,8 +10,7 @@ import random
 
 TIPS = [
     # --- Slash Commands ---
-    "/btw <question> asks a quick side question without tools or history — great for clarifications.",
-    "/background <prompt> runs a task in a separate session while your current one stays free.",
+    "/background <prompt> (alias /bg or /btw) runs a task in a separate session while your current one stays free.",
     "/branch forks the current session so you can explore a different direction without losing progress.",
     "/compress manually compresses conversation context when things get long.",
     "/rollback lists filesystem checkpoints — restore files the agent modified to any prior state.",
@@ -127,7 +126,7 @@ TIPS = [
 
     # --- Tools & Capabilities ---
     "execute_code runs Python scripts that call Hermes tools programmatically — results stay out of context.",
-    "delegate_task spawns up to 3 concurrent sub-agents by default (configurable via delegation.max_concurrent_children) with isolated contexts for parallel work.",
+    "delegate_task spawns up to 3 concurrent sub-agents by default (delegation.max_concurrent_children) with isolated contexts for parallel work.",
     "web_extract works on PDF URLs — pass any PDF link and it converts to markdown.",
     "search_files is ripgrep-backed and faster than grep — use it instead of terminal grep.",
     "patch uses 9 fuzzy matching strategies so minor whitespace differences won't break edits.",

hermes_cli/tools_config.py

@@ -67,25 +67,59 @@ CONFIGURABLE_TOOLSETS = [
     ("messaging",       "📨 Cross-Platform Messaging",  "send_message"),
     ("rl",              "🧪 RL Training",               "Tinker-Atropos training tools"),
     ("homeassistant",    "🏠 Home Assistant",           "smart home device control"),
+    ("spotify",          "🎵 Spotify",                  "playback, search, playlists, library"),
+    ("discord",         "💬 Discord (read/participate)", "fetch messages, search members, create thread"),
+    ("discord_admin",   "🛡️  Discord Server Admin",    "list channels/roles, pin, assign roles"),
 ]
 
 # Toolsets that are OFF by default for new installs.
 # They're still in _HERMES_CORE_TOOLS (available at runtime if enabled),
 # but the setup checklist won't pre-select them for first-time users.
-_DEFAULT_OFF_TOOLSETS = {"moa", "homeassistant", "rl"}
+_DEFAULT_OFF_TOOLSETS = {"moa", "homeassistant", "rl", "spotify", "discord", "discord_admin"}
+
+# Platform-scoped toolsets: only appear in the `hermes tools` checklist for
+# these platforms, and only resolve/save for these platforms.  A toolset
+# absent from this map is available on every platform (current behaviour).
+#
+# Use this for tools whose APIs only make sense on one platform (Discord
+# server admin, Slack workspace admin, etc.).  Keeps every other platform's
+# checklist from filling up with irrelevant toggles.
+_TOOLSET_PLATFORM_RESTRICTIONS: Dict[str, Set[str]] = {
+    "discord": {"discord"},
+    "discord_admin": {"discord"},
+}
+
+
+def _toolset_allowed_for_platform(ts_key: str, platform: str) -> bool:
+    """Return True if ``ts_key`` is configurable on ``platform``.
+
+    Toolsets without a restriction entry are allowed everywhere (the default).
+    """
+    allowed = _TOOLSET_PLATFORM_RESTRICTIONS.get(ts_key)
+    return allowed is None or platform in allowed
 
 
 def _get_effective_configurable_toolsets():
     """Return CONFIGURABLE_TOOLSETS + any plugin-provided toolsets.
 
     Plugin toolsets are appended at the end so they appear after the
-    built-in toolsets in the TUI checklist.
+    built-in toolsets in the TUI checklist. A plugin whose toolset key
+    already appears in ``CONFIGURABLE_TOOLSETS`` is skipped — bundled
+    plugins (e.g. ``plugins/spotify``) share their toolset key with the
+    built-in entry, and we want the built-in label/description to win.
+    Without the dedupe, ``hermes tools`` → "reconfigure existing" would
+    list the same toolset twice.
     """
     result = list(CONFIGURABLE_TOOLSETS)
+    seen = {ts_key for ts_key, _, _ in result}
     try:
         from hermes_cli.plugins import discover_plugins, get_plugin_toolsets
         discover_plugins()  # idempotent — ensures plugins are loaded
-        result.extend(get_plugin_toolsets())
+        for entry in get_plugin_toolsets():
+            if entry[0] in seen:
+                continue
+            seen.add(entry[0])
+            result.append(entry)
     except Exception:
         pass
     return result
@@ -361,6 +395,18 @@ TOOL_CATEGORIES = {
             },
         ],
     },
+    "spotify": {
+        "name": "Spotify",
+        "icon": "🎵",
+        "providers": [
+            {
+                "name": "Spotify Web API",
+                "tag": "PKCE OAuth — opens the setup wizard",
+                "env_vars": [],
+                "post_setup": "spotify",
+            },
+        ],
+    },
     "rl": {
         "name": "RL Training",
         "icon": "🧪",
@@ -461,6 +507,35 @@ def _run_post_setup(post_setup_key: str):
             _print_warning("    kittentts install timed out (>5min)")
             _print_info(f"    Run manually: python -m pip install -U '{wheel_url}' soundfile")
 
+    elif post_setup_key == "spotify":
+        # Run the full `hermes auth spotify` flow — if the user has no
+        # client_id yet, this drops them into the interactive wizard
+        # (opens the Spotify dashboard, prompts for client_id, persists
+        # to ~/.hermes/.env), then continues straight into PKCE. If they
+        # already have an app, it skips the wizard and just does OAuth.
+        from types import SimpleNamespace
+        try:
+            from hermes_cli.auth import login_spotify_command
+        except Exception as exc:
+            _print_warning(f"    Could not load Spotify auth: {exc}")
+            _print_info("    Run manually: hermes auth spotify")
+            return
+        _print_info("    Starting Spotify login...")
+        try:
+            login_spotify_command(SimpleNamespace(
+                client_id=None, redirect_uri=None, scope=None,
+                no_browser=False, timeout=None,
+            ))
+            _print_success("    Spotify authenticated")
+        except SystemExit as exc:
+            # User aborted the wizard, or OAuth failed — don't fail the
+            # toolset enable; they can retry with `hermes auth spotify`.
+            _print_warning(f"    Spotify login did not complete: {exc}")
+            _print_info("    Run later: hermes auth spotify")
+        except Exception as exc:
+            _print_warning(f"    Spotify login failed: {exc}")
+            _print_info("    Run manually: hermes auth spotify")
+
     elif post_setup_key == "rl_training":
         try:
             __import__("tinker_atropos")
@@ -549,7 +624,7 @@ def _get_platform_tools(
     include_default_mcp_servers: bool = True,
 ) -> Set[str]:
     """Resolve which individual toolset names are enabled for a platform."""
-    from toolsets import resolve_toolset
+    from toolsets import resolve_toolset, TOOLSETS
 
     platform_toolsets = config.get("platform_toolsets") or {}
     toolset_names = platform_toolsets.get(platform)
@@ -563,6 +638,8 @@ def _get_platform_tools(
     toolset_names = [str(ts) for ts in toolset_names]
 
     configurable_keys = {ts_key for ts_key, _, _ in CONFIGURABLE_TOOLSETS}
+    plugin_ts_keys = _get_plugin_toolset_keys()
+    platform_default_keys = {p["default_toolset"] for p in PLATFORMS.values()}
 
     # If the saved list contains any configurable keys directly, the user
     # has explicitly configured this platform — use direct membership.
@@ -572,7 +649,10 @@ def _get_platform_tools(
     has_explicit_config = any(ts in configurable_keys for ts in toolset_names)
 
     if has_explicit_config:
-        enabled_toolsets = {ts for ts in toolset_names if ts in configurable_keys}
+        enabled_toolsets = {
+            ts for ts in toolset_names
+            if ts in configurable_keys and _toolset_allowed_for_platform(ts, platform)
+        }
     else:
         # No explicit config — fall back to resolving composite toolset names
         # (e.g. "hermes-cli") to individual tool names and reverse-mapping.
@@ -582,19 +662,59 @@ def _get_platform_tools(
 
         enabled_toolsets = set()
         for ts_key, _, _ in CONFIGURABLE_TOOLSETS:
+            if not _toolset_allowed_for_platform(ts_key, platform):
+                continue
             ts_tools = set(resolve_toolset(ts_key))
             if ts_tools and ts_tools.issubset(all_tool_names):
                 enabled_toolsets.add(ts_key)
+
         default_off = set(_DEFAULT_OFF_TOOLSETS)
-        if platform in default_off:
+        # Legacy safety: if the platform's own name matches a default-off
+        # toolset (e.g. `homeassistant` platform + `homeassistant` toolset),
+        # keep that toolset enabled on first install.  Skip this dodge for
+        # platform-restricted toolsets — those are always opt-in even on
+        # their own platform (e.g. `discord` + `discord` should stay OFF).
+        if platform in default_off and platform not in _TOOLSET_PLATFORM_RESTRICTIONS:
             default_off.remove(platform)
         enabled_toolsets -= default_off
 
-    # Plugin toolsets: enabled by default unless explicitly disabled.
+    # Recover non-configurable platform toolsets (e.g. discord, feishu_doc,
+    # feishu_drive).  These are part of the platform's default composite but
+    # absent from CONFIGURABLE_TOOLSETS, so they can't appear in the TUI
+    # checklist or in a user-saved config.  Must run in BOTH branches —
+    # otherwise saving via `hermes tools` (which flips has_explicit_config
+    # to True) silently drops them.
+    platform_tool_universe = set(resolve_toolset(PLATFORMS[platform]["default_toolset"]))
+    configurable_tool_universe = set()
+    for ck in configurable_keys:
+        configurable_tool_universe.update(resolve_toolset(ck))
+    claimed = set()
+    for ts_key in enabled_toolsets:
+        claimed.update(resolve_toolset(ts_key))
+    skip = configurable_keys | plugin_ts_keys | platform_default_keys
+    skip |= {k for k in TOOLSETS if k.startswith("hermes-")}
+    skip |= set(_DEFAULT_OFF_TOOLSETS) - {platform}
+    for ts_key, ts_def in TOOLSETS.items():
+        if ts_key in skip:
+            continue
+        if ts_def.get("includes"):
+            continue
+        ts_tools = set(resolve_toolset(ts_key))
+        if not ts_tools or not ts_tools.issubset(platform_tool_universe):
+            continue
+        if ts_tools.issubset(configurable_tool_universe):
+            continue
+        if not ts_tools.issubset(claimed):
+            enabled_toolsets.add(ts_key)
+            claimed.update(ts_tools)
+
+    # Plugin toolsets: enabled by default unless explicitly disabled, or
+    # unless the toolset is in _DEFAULT_OFF_TOOLSETS (e.g. spotify —
+    # shipped as a bundled plugin but user must opt in via `hermes tools`
+    # so we don't ship 7 Spotify tool schemas to users who don't use it).
     # A plugin toolset is "known" for a platform once `hermes tools`
     # has been saved for that platform (tracked via known_plugin_toolsets).
     # Unknown plugins default to enabled; known-but-absent = disabled.
-    plugin_ts_keys = _get_plugin_toolset_keys()
     if plugin_ts_keys:
         known_map = config.get("known_plugin_toolsets", {})
         known_for_platform = set(known_map.get(platform, []))
@@ -602,6 +722,9 @@ def _get_platform_tools(
             if pts in toolset_names:
                 # Explicitly listed in config — enabled
                 enabled_toolsets.add(pts)
+            elif pts in _DEFAULT_OFF_TOOLSETS:
+                # Opt-in plugin toolset — stay off until user picks it
+                continue
             elif pts not in known_for_platform:
                 # New plugin not yet seen by hermes tools — default enabled
                 enabled_toolsets.add(pts)
@@ -609,7 +732,6 @@ def _get_platform_tools(
 
     # Preserve any explicit non-configurable toolset entries (for example,
     # custom toolsets or MCP server names saved in platform_toolsets).
-    platform_default_keys = {p["default_toolset"] for p in PLATFORMS.values()}
     explicit_passthrough = {
         ts
         for ts in toolset_names
@@ -655,6 +777,14 @@ def _save_platform_tools(config: dict, platform: str, enabled_toolset_keys: Set[
     """
     config.setdefault("platform_toolsets", {})
 
+    # Drop platform-scoped toolsets that don't apply here.  Prevents the
+    # "Configure all platforms" checklist (or a hand-edited config.yaml)
+    # from turning on, say, the `discord` toolset for Telegram.
+    enabled_toolset_keys = {
+        ts for ts in enabled_toolset_keys
+        if _toolset_allowed_for_platform(ts, platform)
+    }
+
     # Get the set of all configurable toolset keys (built-in + plugin)
     configurable_keys = {ts_key for ts_key, _, _ in CONFIGURABLE_TOOLSETS}
     plugin_keys = _get_plugin_toolset_keys()
@@ -669,6 +799,7 @@ def _save_platform_tools(config: dict, platform: str, enabled_toolset_keys: Set[
     existing_toolsets = config.get("platform_toolsets", {}).get(platform, [])
     if not isinstance(existing_toolsets, list):
         existing_toolsets = []
+    existing_toolsets = [str(ts) for ts in existing_toolsets]
 
     # Preserve any entries that are NOT configurable toolsets and NOT platform
     # defaults (i.e. only MCP server names should be preserved)
@@ -676,6 +807,11 @@ def _save_platform_tools(config: dict, platform: str, enabled_toolset_keys: Set[
         entry for entry in existing_toolsets
         if entry not in configurable_keys and entry not in platform_default_keys
     }
+    # Opening `hermes tools` is the user's opt-in to reconfigure tools, so treat
+    # saving from the picker as consent to clear the "no_mcp" sentinel. The
+    # picker has no checkbox for no_mcp, so without this users who once set it
+    # by hand could never re-enable MCP servers through the UI.
+    preserved_entries.discard("no_mcp")
 
     # Merge preserved entries with new enabled toolsets
     config["platform_toolsets"][platform] = sorted(enabled_toolset_keys | preserved_entries)
@@ -783,7 +919,7 @@ def _estimate_tool_tokens() -> Dict[str, int]:
     return _tool_token_cache
 
 
-def _prompt_toolset_checklist(platform_label: str, enabled: Set[str]) -> Set[str]:
+def _prompt_toolset_checklist(platform_label: str, enabled: Set[str], platform: str = "cli") -> Set[str]:
     """Multi-select checklist of toolsets. Returns set of selected toolset keys."""
     from hermes_cli.curses_ui import curses_checklist
     from toolsets import resolve_toolset
@@ -791,7 +927,12 @@ def _prompt_toolset_checklist(platform_label: str, enabled: Set[str]) -> Set[str
     # Pre-compute per-tool token counts (cached after first call).
     tool_tokens = _estimate_tool_tokens()
 
-    effective = _get_effective_configurable_toolsets()
+    effective_all = _get_effective_configurable_toolsets()
+    # Drop platform-scoped toolsets that don't apply to this platform.
+    effective = [
+        (k, l, d) for (k, l, d) in effective_all
+        if _toolset_allowed_for_platform(k, platform)
+    ]
 
     labels = []
     for ts_key, ts_label, ts_desc in effective:
@@ -1705,7 +1846,7 @@ def tools_command(args=None, first_install: bool = False, config: dict = None):
             checklist_preselected = current_enabled - _DEFAULT_OFF_TOOLSETS
 
             # Show checklist
-            new_enabled = _prompt_toolset_checklist(pinfo["label"], checklist_preselected)
+            new_enabled = _prompt_toolset_checklist(pinfo["label"], checklist_preselected, pkey)
 
             added = new_enabled - current_enabled
             removed = current_enabled - new_enabled
@@ -2061,7 +2202,11 @@ def _apply_mcp_change(config: dict, targets: List[str], action: str) -> Set[str]
 
 def _print_tools_list(enabled_toolsets: set, mcp_servers: dict, platform: str = "cli"):
     """Print a summary of enabled/disabled toolsets and MCP tool filters."""
-    effective = _get_effective_configurable_toolsets()
+    effective_all = _get_effective_configurable_toolsets()
+    effective = [
+        (k, l, d) for (k, l, d) in effective_all
+        if _toolset_allowed_for_platform(k, platform)
+    ]
     builtin_keys = {ts_key for ts_key, _, _ in CONFIGURABLE_TOOLSETS}
 
     print(f"Built-in toolsets ({platform}):")
@@ -2127,6 +2272,20 @@ def tools_disable_enable_command(args):
             _print_error(f"Unknown toolset '{name}'")
         toolset_targets = [t for t in toolset_targets if t in valid_toolsets]
 
+    # Reject platform-scoped toolsets on platforms that don't allow them.
+    restricted_targets = [
+        t for t in toolset_targets
+        if not _toolset_allowed_for_platform(t, platform)
+    ]
+    if restricted_targets:
+        for name in restricted_targets:
+            allowed = sorted(_TOOLSET_PLATFORM_RESTRICTIONS.get(name) or set())
+            _print_error(
+                f"Toolset '{name}' is not available on platform '{platform}' "
+                f"(only: {', '.join(allowed)})"
+            )
+        toolset_targets = [t for t in toolset_targets if t not in restricted_targets]
+
     if toolset_targets:
         _apply_toolset_change(config, platform, toolset_targets, action)
 

hermes_cli/web_server.py

@@ -49,7 +49,7 @@ from hermes_cli.config import (
 from gateway.status import get_running_pid, read_runtime_status
 
 try:
-    from fastapi import FastAPI, HTTPException, Request
+    from fastapi import FastAPI, HTTPException, Request, WebSocket, WebSocketDisconnect
     from fastapi.middleware.cors import CORSMiddleware
     from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
     from fastapi.staticfiles import StaticFiles
@@ -73,6 +73,10 @@ app = FastAPI(title="Hermes Agent", version=__version__)
 _SESSION_TOKEN = secrets.token_urlsafe(32)
 _SESSION_HEADER_NAME = "X-Hermes-Session-Token"
 
+# In-browser Chat tab (/chat, /api/pty, …).  Off unless ``hermes dashboard --tui``
+# or HERMES_DASHBOARD_TUI=1.  Set from :func:`start_server`.
+_DASHBOARD_EMBEDDED_CHAT_ENABLED = False
+
 # Simple rate limiter for the reveal endpoint
 _reveal_timestamps: List[float] = []
 _REVEAL_MAX_PER_WINDOW = 5
@@ -283,7 +287,7 @@ _SCHEMA_OVERRIDES: Dict[str, Dict[str, Any]] = {
     "display.busy_input_mode": {
         "type": "select",
         "description": "Input behavior while agent is running",
-        "options": ["queue", "interrupt", "block"],
+        "options": ["interrupt", "queue"],
     },
     "memory.provider": {
         "type": "select",
@@ -1529,26 +1533,30 @@ def _submit_anthropic_pkce(session_id: str, code_input: str) -> Dict[str, Any]:
         with urllib.request.urlopen(req, timeout=20) as resp:
             result = json.loads(resp.read().decode())
     except Exception as e:
-        sess["status"] = "error"
-        sess["error_message"] = f"Token exchange failed: {e}"
+        with _oauth_sessions_lock:
+            sess["status"] = "error"
+            sess["error_message"] = f"Token exchange failed: {e}"
         return {"ok": False, "status": "error", "message": sess["error_message"]}
 
     access_token = result.get("access_token", "")
     refresh_token = result.get("refresh_token", "")
     expires_in = int(result.get("expires_in") or 3600)
     if not access_token:
-        sess["status"] = "error"
-        sess["error_message"] = "No access token returned"
+        with _oauth_sessions_lock:
+            sess["status"] = "error"
+            sess["error_message"] = "No access token returned"
         return {"ok": False, "status": "error", "message": sess["error_message"]}
 
     expires_at_ms = int(time.time() * 1000) + (expires_in * 1000)
     try:
         _save_anthropic_oauth_creds(access_token, refresh_token, expires_at_ms)
     except Exception as e:
-        sess["status"] = "error"
-        sess["error_message"] = f"Save failed: {e}"
+        with _oauth_sessions_lock:
+            sess["status"] = "error"
+            sess["error_message"] = f"Save failed: {e}"
         return {"ok": False, "status": "error", "message": sess["error_message"]}
-    sess["status"] = "approved"
+    with _oauth_sessions_lock:
+        sess["status"] = "approved"
     _log.info("oauth/pkce: anthropic login completed (session=%s)", session_id)
     return {"ok": True, "status": "approved"}
 
@@ -2263,6 +2271,329 @@ async def get_usage_analytics(days: int = 30):
         db.close()
 
 
+# ---------------------------------------------------------------------------
+# /api/pty — PTY-over-WebSocket bridge for the dashboard "Chat" tab.
+#
+# The endpoint spawns the same ``hermes --tui`` binary the CLI uses, behind
+# a POSIX pseudo-terminal, and forwards bytes + resize escapes across a
+# WebSocket.  The browser renders the ANSI through xterm.js (see
+# web/src/pages/ChatPage.tsx).
+#
+# Auth: ``?token=<session_token>`` query param (browsers can't set
+# Authorization on the WS upgrade).  Same ephemeral ``_SESSION_TOKEN`` as
+# REST.  Localhost-only — we defensively reject non-loopback clients even
+# though uvicorn binds to 127.0.0.1.
+# ---------------------------------------------------------------------------
+
+import re
+import asyncio
+
+from hermes_cli.pty_bridge import PtyBridge, PtyUnavailableError
+
+_RESIZE_RE = re.compile(rb"\x1b\[RESIZE:(\d+);(\d+)\]")
+_PTY_READ_CHUNK_TIMEOUT = 0.2
+_VALID_CHANNEL_RE = re.compile(r"^[A-Za-z0-9._-]{1,128}$")
+# Starlette's TestClient reports the peer as "testclient"; treat it as
+# loopback so tests don't need to rewrite request scope.
+_LOOPBACK_HOSTS = frozenset({"127.0.0.1", "::1", "localhost", "testclient"})
+
+# 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
+# drops AND the publisher has disconnected.
+_event_channels: dict[str, set] = {}
+_event_lock = asyncio.Lock()
+
+
+def _resolve_chat_argv(
+    resume: Optional[str] = None,
+    sidecar_url: Optional[str] = None,
+) -> tuple[list[str], Optional[str], Optional[dict]]:
+    """Resolve the argv + cwd + env for the chat PTY.
+
+    Default: whatever ``hermes --tui`` would run.  Tests monkeypatch this
+    function to inject a tiny fake command (``cat``, ``sh -c 'printf …'``)
+    so nothing has to build Node or the TUI bundle.
+
+    Session resume is propagated via the ``HERMES_TUI_RESUME`` env var —
+    matching what ``hermes_cli.main._launch_tui`` does for the CLI path.
+    Appending ``--resume <id>`` to argv doesn't work because ``ui-tui`` does
+    not parse its argv.
+
+    `sidecar_url` (when set) is forwarded as ``HERMES_TUI_SIDECAR_URL`` so
+    the spawned ``tui_gateway.entry`` can mirror dispatcher emits to the
+    dashboard's ``/api/pub`` endpoint (see :func:`pub_ws`).
+    """
+    from hermes_cli.main import PROJECT_ROOT, _make_tui_argv
+
+    argv, cwd = _make_tui_argv(PROJECT_ROOT / "ui-tui", tui_dev=False)
+    env: Optional[dict] = None
+
+    if resume or sidecar_url:
+        env = os.environ.copy()
+
+        if resume:
+            env["HERMES_TUI_RESUME"] = resume
+
+        if sidecar_url:
+            env["HERMES_TUI_SIDECAR_URL"] = sidecar_url
+
+    return list(argv), str(cwd) if cwd else None, env
+
+
+def _build_sidecar_url(channel: str) -> Optional[str]:
+    """ws:// URL the PTY child should publish events to, or None when unbound."""
+    host = getattr(app.state, "bound_host", None)
+    port = getattr(app.state, "bound_port", None)
+
+    if not host or not port:
+        return None
+
+    netloc = f"[{host}]:{port}" if ":" in host and not host.startswith("[") else f"{host}:{port}"
+    qs = urllib.parse.urlencode({"token": _SESSION_TOKEN, "channel": channel})
+
+    return f"ws://{netloc}/api/pub?{qs}"
+
+
+async def _broadcast_event(channel: str, payload: str) -> None:
+    """Fan out one publisher frame to every subscriber on `channel`."""
+    async with _event_lock:
+        subs = list(_event_channels.get(channel, ()))
+
+    for sub in subs:
+        try:
+            await sub.send_text(payload)
+        except Exception:
+            # Subscriber went away mid-send; the /api/events finally clause
+            # will remove it from the registry on its next iteration.
+            pass
+
+
+def _channel_or_close_code(ws: WebSocket) -> Optional[str]:
+    """Return the channel id from the query string or None if invalid."""
+    channel = ws.query_params.get("channel", "")
+
+    return channel if _VALID_CHANNEL_RE.match(channel) else None
+
+
+@app.websocket("/api/pty")
+async def pty_ws(ws: WebSocket) -> None:
+    if not _DASHBOARD_EMBEDDED_CHAT_ENABLED:
+        await ws.close(code=4403)
+        return
+
+    # --- auth + loopback check (before accept so we can close cleanly) ---
+    token = ws.query_params.get("token", "")
+    expected = _SESSION_TOKEN
+    if not hmac.compare_digest(token.encode(), expected.encode()):
+        await ws.close(code=4401)
+        return
+
+    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
+
+    await ws.accept()
+
+    # --- spawn PTY ------------------------------------------------------
+    resume = ws.query_params.get("resume") or None
+    channel = _channel_or_close_code(ws)
+    sidecar_url = _build_sidecar_url(channel) if channel else None
+
+    try:
+        argv, cwd, env = _resolve_chat_argv(resume=resume, sidecar_url=sidecar_url)
+    except SystemExit as exc:
+        # _make_tui_argv calls sys.exit(1) when node/npm is missing.
+        await ws.send_text(f"\r\n\x1b[31mChat unavailable: {exc}\x1b[0m\r\n")
+        await ws.close(code=1011)
+        return
+
+
+    try:
+        bridge = PtyBridge.spawn(argv, cwd=cwd, env=env)
+    except PtyUnavailableError as exc:
+        await ws.send_text(f"\r\n\x1b[31mChat unavailable: {exc}\x1b[0m\r\n")
+        await ws.close(code=1011)
+        return
+    except (FileNotFoundError, OSError) as exc:
+        await ws.send_text(f"\r\n\x1b[31mChat failed to start: {exc}\x1b[0m\r\n")
+        await ws.close(code=1011)
+        return
+
+    loop = asyncio.get_running_loop()
+
+    # --- reader task: PTY master → WebSocket ----------------------------
+    async def pump_pty_to_ws() -> None:
+        while True:
+            chunk = await loop.run_in_executor(
+                None, bridge.read, _PTY_READ_CHUNK_TIMEOUT
+            )
+            if chunk is None:  # EOF
+                return
+            if not chunk:  # no data this tick; yield control and retry
+                await asyncio.sleep(0)
+                continue
+            try:
+                await ws.send_bytes(chunk)
+            except Exception:
+                return
+
+    reader_task = asyncio.create_task(pump_pty_to_ws())
+
+    # --- writer loop: WebSocket → PTY master ----------------------------
+    try:
+        while True:
+            msg = await ws.receive()
+            msg_type = msg.get("type")
+            if msg_type == "websocket.disconnect":
+                break
+            raw = msg.get("bytes")
+            if raw is None:
+                text = msg.get("text")
+                raw = text.encode("utf-8") if isinstance(text, str) else b""
+            if not raw:
+                continue
+
+            # Resize escape is consumed locally, never written to the PTY.
+            match = _RESIZE_RE.match(raw)
+            if match and match.end() == len(raw):
+                cols = int(match.group(1))
+                rows = int(match.group(2))
+                bridge.resize(cols=cols, rows=rows)
+                continue
+
+            bridge.write(raw)
+    except WebSocketDisconnect:
+        pass
+    finally:
+        reader_task.cancel()
+        try:
+            await reader_task
+        except (asyncio.CancelledError, Exception):
+            pass
+        bridge.close()
+
+
+# ---------------------------------------------------------------------------
+# /api/ws — JSON-RPC WebSocket sidecar for the dashboard "Chat" tab.
+#
+# Drives the same `tui_gateway.dispatch` surface Ink uses over stdio, so the
+# dashboard can render structured metadata (model badge, tool-call sidebar,
+# slash launcher, session info) alongside the xterm.js terminal that PTY
+# already paints. Both transports bind to the same session id when one is
+# active, so a tool.start emitted by the agent fans out to both sinks.
+# ---------------------------------------------------------------------------
+
+
+@app.websocket("/api/ws")
+async def gateway_ws(ws: WebSocket) -> None:
+    if not _DASHBOARD_EMBEDDED_CHAT_ENABLED:
+        await ws.close(code=4403)
+        return
+
+    token = ws.query_params.get("token", "")
+    if not hmac.compare_digest(token.encode(), _SESSION_TOKEN.encode()):
+        await ws.close(code=4401)
+        return
+
+    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
+
+    from tui_gateway.ws import handle_ws
+
+    await handle_ws(ws)
+
+
+# ---------------------------------------------------------------------------
+# /api/pub + /api/events — chat-tab event broadcast.
+#
+# The PTY-side ``tui_gateway.entry`` opens /api/pub at startup (driven by
+# HERMES_TUI_SIDECAR_URL set in /api/pty's PTY env) and writes every
+# dispatcher emit through it.  The dashboard fans those frames out to any
+# subscriber that opened /api/events on the same channel id.  This is what
+# gives the React sidebar its tool-call feed without breaking the PTY
+# child's stdio handshake with Ink.
+# ---------------------------------------------------------------------------
+
+
+@app.websocket("/api/pub")
+async def pub_ws(ws: WebSocket) -> None:
+    if not _DASHBOARD_EMBEDDED_CHAT_ENABLED:
+        await ws.close(code=4403)
+        return
+
+    token = ws.query_params.get("token", "")
+    if not hmac.compare_digest(token.encode(), _SESSION_TOKEN.encode()):
+        await ws.close(code=4401)
+        return
+
+    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
+
+    channel = _channel_or_close_code(ws)
+    if not channel:
+        await ws.close(code=4400)
+        return
+
+    await ws.accept()
+
+    try:
+        while True:
+            await _broadcast_event(channel, await ws.receive_text())
+    except WebSocketDisconnect:
+        pass
+
+
+@app.websocket("/api/events")
+async def events_ws(ws: WebSocket) -> None:
+    if not _DASHBOARD_EMBEDDED_CHAT_ENABLED:
+        await ws.close(code=4403)
+        return
+
+    token = ws.query_params.get("token", "")
+    if not hmac.compare_digest(token.encode(), _SESSION_TOKEN.encode()):
+        await ws.close(code=4401)
+        return
+
+    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
+
+    channel = _channel_or_close_code(ws)
+    if not channel:
+        await ws.close(code=4400)
+        return
+
+    await ws.accept()
+
+    async with _event_lock:
+        _event_channels.setdefault(channel, set()).add(ws)
+
+    try:
+        while True:
+            # Subscribers don't speak — the receive() just blocks until
+            # disconnect so the connection stays open as long as the
+            # browser holds it.
+            await ws.receive_text()
+    except WebSocketDisconnect:
+        pass
+    finally:
+        async with _event_lock:
+            subs = _event_channels.get(channel)
+
+            if subs is not None:
+                subs.discard(ws)
+
+                if not subs:
+                    _event_channels.pop(channel, None)
+
+
 def mount_spa(application: FastAPI):
     """Mount the built SPA. Falls back to index.html for client-side routing.
 
@@ -2284,8 +2615,10 @@ def mount_spa(application: FastAPI):
     def _serve_index():
         """Return index.html with the session token injected."""
         html = _index_path.read_text()
+        chat_js = "true" if _DASHBOARD_EMBEDDED_CHAT_ENABLED else "false"
         token_script = (
-            f'<script>window.__HERMES_SESSION_TOKEN__="{_SESSION_TOKEN}";</script>'
+            f'<script>window.__HERMES_SESSION_TOKEN__="{_SESSION_TOKEN}";'
+            f"window.__HERMES_DASHBOARD_EMBEDDED_CHAT__={chat_js};</script>"
         )
         html = html.replace("</head>", f"{token_script}</head>", 1)
         return HTMLResponse(
@@ -2798,10 +3131,15 @@ def start_server(
     port: int = 9119,
     open_browser: bool = True,
     allow_public: bool = False,
+    *,
+    embedded_chat: bool = False,
 ):
     """Start the web UI server."""
     import uvicorn
 
+    global _DASHBOARD_EMBEDDED_CHAT_ENABLED
+    _DASHBOARD_EMBEDDED_CHAT_ENABLED = embedded_chat
+
     _LOCALHOST = ("127.0.0.1", "localhost", "::1")
     if host not in _LOCALHOST and not allow_public:
         raise SystemExit(
@@ -2817,7 +3155,10 @@ def start_server(
 
     # Record the bound host so host_header_middleware can validate incoming
     # Host headers against it. Defends against DNS rebinding (GHSA-ppp5-vxwm-4cf7).
+    # bound_port is also stashed so /api/pty can build the back-WS URL the
+    # PTY child uses to publish events to the dashboard sidebar.
     app.state.bound_host = host
+    app.state.bound_port = port
 
     if open_browser:
         import webbrowser

hermes_state.py

@@ -31,7 +31,7 @@ T = TypeVar("T")
 
 DEFAULT_DB_PATH = get_hermes_home() / "state.db"
 
-SCHEMA_VERSION = 8
+SCHEMA_VERSION = 9
 
 SCHEMA_SQL = """
 CREATE TABLE IF NOT EXISTS schema_version (
@@ -83,7 +83,8 @@ CREATE TABLE IF NOT EXISTS messages (
     reasoning TEXT,
     reasoning_content TEXT,
     reasoning_details TEXT,
-    codex_reasoning_items TEXT
+    codex_reasoning_items TEXT,
+    codex_message_items TEXT
 );
 
 CREATE TABLE IF NOT EXISTS state_meta (
@@ -356,6 +357,15 @@ class SessionDB:
                 except sqlite3.OperationalError:
                     pass  # Column already exists
                 cursor.execute("UPDATE schema_version SET version = 8")
+            if current_version < 9:
+                # v9: preserve replayable Codex assistant message ids/phases so
+                # follow-up turns can rebuild Responses API message items instead
+                # of flattening everything to plain assistant text.
+                try:
+                    cursor.execute('ALTER TABLE messages ADD COLUMN "codex_message_items" TEXT')
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 9")
 
         # Unique title index — always ensure it exists (safe to run after migrations
         # since the title column is guaranteed to exist at this point)
@@ -956,6 +966,7 @@ class SessionDB:
         reasoning_content: str = None,
         reasoning_details: Any = None,
         codex_reasoning_items: Any = None,
+        codex_message_items: Any = None,
     ) -> int:
         """
         Append a message to a session. Returns the message row ID.
@@ -972,6 +983,10 @@ class SessionDB:
             json.dumps(codex_reasoning_items)
             if codex_reasoning_items else None
         )
+        codex_message_items_json = (
+            json.dumps(codex_message_items)
+            if codex_message_items else None
+        )
         tool_calls_json = json.dumps(tool_calls) if tool_calls else None
 
         # Pre-compute tool call count
@@ -983,8 +998,9 @@ class SessionDB:
             cursor = conn.execute(
                 """INSERT INTO messages (session_id, role, content, tool_call_id,
                    tool_calls, tool_name, timestamp, token_count, finish_reason,
-                   reasoning, reasoning_content, reasoning_details, codex_reasoning_items)
-                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
+                   reasoning, reasoning_content, reasoning_details, codex_reasoning_items,
+                   codex_message_items)
+                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
                 (
                     session_id,
                     role,
@@ -999,6 +1015,7 @@ class SessionDB:
                     reasoning_content,
                     reasoning_details_json,
                     codex_items_json,
+                    codex_message_items_json,
                 ),
             )
             msg_id = cursor.lastrowid
@@ -1039,6 +1056,71 @@ class SessionDB:
             result.append(msg)
         return result
 
+    def resolve_resume_session_id(self, session_id: str) -> str:
+        """Redirect a resume target to the descendant session that holds the messages.
+
+        Context compression ends the current session and forks a new child session
+        (linked via ``parent_session_id``). The flush cursor is reset, so the
+        child is where new messages actually land — the parent ends up with
+        ``message_count = 0`` rows unless messages had already been flushed to
+        it before compression. See #15000.
+
+        This helper walks ``parent_session_id`` forward from ``session_id`` and
+        returns the first descendant in the chain that has at least one message
+        row. If the original session already has messages, or no descendant
+        has any, the original ``session_id`` is returned unchanged.
+
+        The chain is always walked via the child whose ``started_at`` is
+        latest; that matches the single-chain shape that compression creates.
+        A depth cap (32) guards against accidental loops in malformed data.
+        """
+        if not session_id:
+            return session_id
+
+        with self._lock:
+            # If this session already has messages, nothing to redirect.
+            try:
+                row = self._conn.execute(
+                    "SELECT 1 FROM messages WHERE session_id = ? LIMIT 1",
+                    (session_id,),
+                ).fetchone()
+            except Exception:
+                return session_id
+            if row is not None:
+                return session_id
+
+            # Walk descendants: at each step, pick the most-recently-started
+                # child session; stop once we find one with messages.
+            current = session_id
+            seen = {current}
+            for _ in range(32):
+                try:
+                    child_row = self._conn.execute(
+                        "SELECT id FROM sessions "
+                        "WHERE parent_session_id = ? "
+                        "ORDER BY started_at DESC, id DESC LIMIT 1",
+                        (current,),
+                    ).fetchone()
+                except Exception:
+                    return session_id
+                if child_row is None:
+                    return session_id
+                child_id = child_row["id"] if hasattr(child_row, "keys") else child_row[0]
+                if not child_id or child_id in seen:
+                    return session_id
+                seen.add(child_id)
+                try:
+                    msg_row = self._conn.execute(
+                        "SELECT 1 FROM messages WHERE session_id = ? LIMIT 1",
+                        (child_id,),
+                    ).fetchone()
+                except Exception:
+                    return session_id
+                if msg_row is not None:
+                    return child_id
+                current = child_id
+        return session_id
+
     def get_messages_as_conversation(self, session_id: str) -> List[Dict[str, Any]]:
         """
         Load messages in the OpenAI conversation format (role + content dicts).
@@ -1047,7 +1129,8 @@ class SessionDB:
         with self._lock:
             cursor = self._conn.execute(
                 "SELECT role, content, tool_call_id, tool_calls, tool_name, "
-                "reasoning, reasoning_content, reasoning_details, codex_reasoning_items "
+                "reasoning, reasoning_content, reasoning_details, codex_reasoning_items, "
+                "codex_message_items "
                 "FROM messages WHERE session_id = ? ORDER BY timestamp, id",
                 (session_id,),
             )
@@ -1085,6 +1168,12 @@ class SessionDB:
                     except (json.JSONDecodeError, TypeError):
                         logger.warning("Failed to deserialize codex_reasoning_items, falling back to None")
                         msg["codex_reasoning_items"] = None
+                if row["codex_message_items"]:
+                    try:
+                        msg["codex_message_items"] = json.loads(row["codex_message_items"])
+                    except (json.JSONDecodeError, TypeError):
+                        logger.warning("Failed to deserialize codex_message_items, falling back to None")
+                        msg["codex_message_items"] = None
             messages.append(msg)
         return messages
 

model_tools.py

@@ -24,6 +24,7 @@ import json
 import asyncio
 import logging
 import threading
+import time
 from typing import Dict, Any, List, Optional, Tuple
 
 from tools.registry import discover_builtin_tools, registry
@@ -288,30 +289,34 @@ def get_tool_definitions(
                 filtered_tools[i] = {"type": "function", "function": dynamic_schema}
                 break
 
-    # Rebuild discord_server schema based on the bot's privileged intents
-    # (detected from GET /applications/@me) and the user's action allowlist
-    # in config.  Hides actions the bot's intents don't support so the
-    # model never attempts them, and annotates fetch_messages when the
+    # Rebuild discord / discord_admin schemas based on the bot's privileged
+    # intents (detected from GET /applications/@me) and the user's action
+    # allowlist in config.  Hides actions the bot's intents don't support so
+    # the model never attempts them, and annotates fetch_messages when the
     # MESSAGE_CONTENT intent is missing.
-    if "discord_server" in available_tool_names:
-        try:
-            from tools.discord_tool import get_dynamic_schema
-            dynamic = get_dynamic_schema()
-        except Exception:  # pragma: no cover — defensive, fall back to static
-            dynamic = None
-        if dynamic is None:
-            # Tool filtered out entirely (empty allowlist or detection disabled
-            # the only remaining actions).  Drop it from the schema list.
-            filtered_tools = [
-                t for t in filtered_tools
-                if t.get("function", {}).get("name") != "discord_server"
-            ]
-            available_tool_names.discard("discord_server")
-        else:
-            for i, td in enumerate(filtered_tools):
-                if td.get("function", {}).get("name") == "discord_server":
-                    filtered_tools[i] = {"type": "function", "function": dynamic}
-                    break
+    _discord_schema_fns = {
+        "discord": "get_dynamic_schema_core",
+        "discord_admin": "get_dynamic_schema_admin",
+    }
+    for discord_tool_name in _discord_schema_fns:
+        if discord_tool_name in available_tool_names:
+            try:
+                from tools import discord_tool as _dt
+                schema_fn = getattr(_dt, _discord_schema_fns[discord_tool_name])
+                dynamic = schema_fn()
+            except Exception:
+                dynamic = None
+            if dynamic is None:
+                filtered_tools = [
+                    t for t in filtered_tools
+                    if t.get("function", {}).get("name") != discord_tool_name
+                ]
+                available_tool_names.discard(discord_tool_name)
+            else:
+                for i, td in enumerate(filtered_tools):
+                    if td.get("function", {}).get("name") == discord_tool_name:
+                        filtered_tools[i] = {"type": "function", "function": dynamic}
+                        break
 
     # Strip web tool cross-references from browser_navigate description when
     # web_search / web_extract are not available.  The static schema says
@@ -343,6 +348,18 @@ def get_tool_definitions(
     global _last_resolved_tool_names
     _last_resolved_tool_names = [t["function"]["name"] for t in filtered_tools]
 
+    # Sanitize schemas for broad backend compatibility. llama.cpp's
+    # json-schema-to-grammar converter (used by its OAI server to build
+    # GBNF tool-call parsers) rejects some shapes that cloud providers
+    # silently accept — bare "type": "object" with no properties,
+    # string-valued schema nodes from malformed MCP servers, etc. This
+    # is a no-op for schemas that are already well-formed.
+    try:
+        from tools.schema_sanitizer import sanitize_tool_schemas
+        filtered_tools = sanitize_tool_schemas(filtered_tools)
+    except Exception as e:  # pragma: no cover — defensive
+        logger.warning("Schema sanitization skipped: %s", e)
+
     return filtered_tools
 
 
@@ -452,9 +469,9 @@ def _coerce_number(value: str, integer_only: bool = False):
         f = float(value)
     except (ValueError, OverflowError):
         return value
-    # Guard against inf/nan before int() conversion
+    # Guard against inf/nan — not JSON-serializable, keep original string
     if f != f or f == float("inf") or f == float("-inf"):
-        return f
+        return value
     # If it looks like an integer (no fractional part), return int
     if f == int(f):
         return int(f)
@@ -551,6 +568,14 @@ def handle_function_call(
             except Exception:
                 pass  # file_tools may not be loaded yet
 
+        # Measure tool dispatch latency so post_tool_call and
+        # transform_tool_result hooks can observe per-tool duration.
+        # Inspired by Claude Code 2.1.119, which added ``duration_ms`` to
+        # PostToolUse hook inputs so plugin authors can build latency
+        # dashboards, budget alerts, and regression canaries without having
+        # to wrap every tool manually.  We use monotonic() so the value is
+        # unaffected by wall-clock adjustments during the call.
+        _dispatch_start = time.monotonic()
         if function_name == "execute_code":
             # Prefer the caller-provided list so subagents can't overwrite
             # the parent's tool set via the process-global.
@@ -566,6 +591,7 @@ def handle_function_call(
                 task_id=task_id,
                 user_task=user_task,
             )
+        duration_ms = int((time.monotonic() - _dispatch_start) * 1000)
 
         try:
             from hermes_cli.plugins import invoke_hook
@@ -577,6 +603,7 @@ def handle_function_call(
                 task_id=task_id or "",
                 session_id=session_id or "",
                 tool_call_id=tool_call_id or "",
+                duration_ms=duration_ms,
             )
         except Exception:
             pass
@@ -597,6 +624,7 @@ def handle_function_call(
                 task_id=task_id or "",
                 session_id=session_id or "",
                 tool_call_id=tool_call_id or "",
+                duration_ms=duration_ms,
             )
             for hook_result in hook_results:
                 if isinstance(hook_result, str):

nix/lib.nix

@@ -156,7 +156,7 @@
       for entry in "''${ENTRIES[@]}"; do
         IFS=":" read -r ATTR FOLDER NIX_FILE <<< "$entry"
         echo "==> .#$ATTR ($FOLDER -> $NIX_FILE)"
-        OUTPUT=$(nix build ".#$ATTR.npmDeps" --no-link --print-build-logs 2>&1)
+        OUTPUT=$(nix build ".#$ATTR.npmDeps" --no-link --rebuild --print-build-logs 2>&1)
         STATUS=$?
         if [ "$STATUS" -eq 0 ]; then
           echo "    ok"

nix/web.nix

@@ -4,7 +4,7 @@ let
   src = ../web;
   npmDeps = pkgs.fetchNpmDeps {
     inherit src;
-    hash = "sha256-TS/vrCHbdvXkPcAPxImKzAd2pdDCrKlgYZkXBMQ+TEg=";
+    hash = "sha256-4Z8KQ69QhO83X6zff+5urWBv6MME686MhTTMdwSl65o=";
   };
 
   npm = hermesNpmLib.mkNpmPassthru { folder = "web"; attr = "web"; pname = "hermes-web"; };

plugins/example-dashboard/dashboard/dist/index.js

@@ -91,4 +91,29 @@
 
   // Register this plugin — the dashboard picks it up automatically.
   window.__HERMES_PLUGINS__.register("example", ExamplePage);
+
+  // ─────────────────────────────────────────────────────────────────────
+  // Page-scoped slot demo: inject a small banner at the top of /sessions.
+  //
+  // Built-in pages expose named slots (<page>:top, <page>:bottom) that
+  // plugins can populate without overriding the whole route. The
+  // manifest lists the slots we use in its `slots` array so the shell
+  // knows to render <PluginSlot name="sessions:top" /> there.
+  // ─────────────────────────────────────────────────────────────────────
+  function SessionsTopBanner() {
+    return React.createElement(Card, {
+      className: "border-dashed",
+    },
+      React.createElement(CardContent, { className: "flex items-center gap-3 py-2" },
+        React.createElement(Badge, { variant: "outline" }, "Example"),
+        React.createElement("span", {
+          className: "text-xs text-muted-foreground",
+        }, "This banner was injected into the Sessions page by the example plugin via the ",
+          React.createElement("code", { className: "font-courier" }, "sessions:top"),
+          " slot."),
+      ),
+    );
+  }
+
+  window.__HERMES_PLUGINS__.registerSlot("example", "sessions:top", SessionsTopBanner);
 })();

plugins/example-dashboard/dashboard/manifest.json

@@ -8,6 +8,7 @@
     "path": "/example",
     "position": "after:skills"
   },
+  "slots": ["sessions:top"],
   "entry": "dist/index.js",
   "api": "plugin_api.py"
 }

plugins/kanban/dashboard/dist/style.css

@@ -0,0 +1,752 @@
+/*
+ * Hermes Kanban — dashboard plugin styles.
+ *
+ * All colors reference theme CSS vars so the board reskins with the
+ * active dashboard theme. No hardcoded palette.
+ */
+
+.hermes-kanban {
+  width: 100%;
+}
+
+/* ---- Columns layout -------------------------------------------------- */
+
+.hermes-kanban-columns {
+  display: grid;
+  grid-template-columns: repeat(auto-fit, minmax(260px, 1fr));
+  gap: 0.75rem;
+  align-items: start;
+}
+
+.hermes-kanban-column {
+  display: flex;
+  flex-direction: column;
+  background: color-mix(in srgb, var(--color-card) 85%, transparent);
+  border: 1px solid var(--color-border);
+  border-radius: var(--radius);
+  padding: 0.5rem;
+  min-height: 200px;
+  max-height: calc(100vh - 220px);
+  transition: border-color 120ms ease, background-color 120ms ease;
+}
+
+.hermes-kanban-column--drop {
+  border-color: var(--color-ring);
+  background: color-mix(in srgb, var(--color-ring) 8%, var(--color-card));
+}
+
+.hermes-kanban-column-header {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  padding: 0.25rem 0.25rem 0.35rem;
+  font-weight: 600;
+  font-size: 0.85rem;
+  color: var(--color-foreground);
+}
+
+.hermes-kanban-column-label {
+  flex: 1;
+  letter-spacing: 0.01em;
+}
+
+.hermes-kanban-column-count {
+  font-variant-numeric: tabular-nums;
+  color: var(--color-muted-foreground);
+  font-size: 0.75rem;
+  font-weight: 500;
+}
+
+.hermes-kanban-column-add {
+  appearance: none;
+  background: transparent;
+  border: 1px solid var(--color-border);
+  color: var(--color-foreground);
+  border-radius: var(--radius-sm, 0.25rem);
+  width: 22px;
+  height: 22px;
+  line-height: 1;
+  font-size: 1rem;
+  cursor: pointer;
+}
+.hermes-kanban-column-add:hover {
+  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
+}
+
+.hermes-kanban-column-sub {
+  padding: 0 0.25rem 0.5rem;
+  font-size: 0.7rem;
+  color: var(--color-muted-foreground);
+  border-bottom: 1px solid color-mix(in srgb, var(--color-border) 60%, transparent);
+  margin-bottom: 0.5rem;
+}
+
+.hermes-kanban-column-body {
+  display: flex;
+  flex-direction: column;
+  gap: 0.45rem;
+  overflow-y: auto;
+  padding-right: 0.1rem;
+}
+
+.hermes-kanban-empty {
+  padding: 1.5rem 0.5rem;
+  text-align: center;
+  font-size: 0.75rem;
+  color: var(--color-muted-foreground);
+  border: 1px dashed color-mix(in srgb, var(--color-border) 70%, transparent);
+  border-radius: var(--radius-sm, 0.25rem);
+}
+
+/* ---- Status dots ----------------------------------------------------- */
+
+.hermes-kanban-dot {
+  display: inline-block;
+  width: 0.5rem;
+  height: 0.5rem;
+  border-radius: 999px;
+  background: var(--color-muted-foreground);
+}
+.hermes-kanban-dot-triage   { background: #b47dd6; }  /* lilac — fresh/unspecified */
+.hermes-kanban-dot-todo     { background: var(--color-muted-foreground); }
+.hermes-kanban-dot-ready    { background: #d4b348; }  /* amber */
+.hermes-kanban-dot-running  { background: #3fb97d; }  /* green */
+.hermes-kanban-dot-blocked  { background: var(--color-destructive, #d14a4a); }
+.hermes-kanban-dot-done     { background: #4a8cd1; }  /* blue */
+.hermes-kanban-dot-archived { background: var(--color-border); }
+
+/* ---- Progress pill (N/M child tasks done) --------------------------- */
+
+.hermes-kanban-progress {
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-size: 0.62rem;
+  padding: 0.05rem 0.35rem;
+  border-radius: 999px;
+  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
+  border: 1px solid color-mix(in srgb, var(--color-border) 80%, transparent);
+  color: var(--color-muted-foreground);
+  letter-spacing: 0.02em;
+}
+.hermes-kanban-progress--full {
+  background: color-mix(in srgb, #3fb97d 22%, transparent);
+  border-color: color-mix(in srgb, #3fb97d 45%, transparent);
+  color: var(--color-foreground);
+}
+
+/* ---- Lanes (per-profile sub-grouping inside Running) ---------------- */
+
+.hermes-kanban-lane {
+  display: flex;
+  flex-direction: column;
+  gap: 0.35rem;
+  padding: 0.25rem 0 0.35rem;
+  border-top: 1px dashed color-mix(in srgb, var(--color-border) 70%, transparent);
+}
+.hermes-kanban-lane:first-child {
+  border-top: 0;
+  padding-top: 0;
+}
+.hermes-kanban-lane-head {
+  display: flex;
+  align-items: center;
+  gap: 0.4rem;
+  font-size: 0.65rem;
+  text-transform: uppercase;
+  letter-spacing: 0.08em;
+  color: var(--color-muted-foreground);
+  padding: 0 0.1rem;
+}
+.hermes-kanban-lane-name {
+  font-weight: 600;
+  font-family: var(--font-mono, ui-monospace, monospace);
+}
+.hermes-kanban-lane-count {
+  margin-left: auto;
+  font-variant-numeric: tabular-nums;
+}
+
+/* ---- Card ------------------------------------------------------------ */
+
+.hermes-kanban-card {
+  cursor: grab;
+  transition: transform 100ms ease, box-shadow 100ms ease;
+}
+.hermes-kanban-card:hover {
+  box-shadow: 0 1px 0 0 var(--color-ring) inset, 0 0 0 1px var(--color-ring) inset;
+}
+.hermes-kanban-card:active {
+  cursor: grabbing;
+  transform: scale(0.995);
+}
+
+.hermes-kanban-card-content {
+  padding: 0.5rem 0.6rem !important;
+  display: flex;
+  flex-direction: column;
+  gap: 0.3rem;
+}
+
+.hermes-kanban-card-row {
+  display: flex;
+  align-items: center;
+  gap: 0.35rem;
+  flex-wrap: wrap;
+}
+
+.hermes-kanban-card-id {
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-size: 0.65rem;
+  color: var(--color-muted-foreground);
+  letter-spacing: 0.03em;
+}
+
+.hermes-kanban-card-title {
+  font-size: 0.85rem;
+  font-weight: 500;
+  line-height: 1.3;
+  color: var(--color-foreground);
+  word-break: break-word;
+}
+
+.hermes-kanban-card-meta {
+  font-size: 0.7rem;
+  color: var(--color-muted-foreground);
+  gap: 0.55rem;
+}
+
+.hermes-kanban-priority {
+  font-size: 0.6rem !important;
+  padding: 0.05rem 0.3rem !important;
+  background: color-mix(in srgb, var(--color-ring) 18%, transparent);
+  color: var(--color-foreground);
+  border: 1px solid color-mix(in srgb, var(--color-ring) 40%, transparent);
+}
+
+.hermes-kanban-tag {
+  font-size: 0.6rem !important;
+  padding: 0.05rem 0.3rem !important;
+}
+
+.hermes-kanban-assignee {
+  font-weight: 500;
+  color: color-mix(in srgb, var(--color-foreground) 80%, var(--color-muted-foreground));
+}
+.hermes-kanban-unassigned {
+  font-style: italic;
+}
+.hermes-kanban-ago {
+  margin-left: auto;
+}
+
+/* ---- Inline create --------------------------------------------------- */
+
+.hermes-kanban-inline-create {
+  display: flex;
+  flex-direction: column;
+  gap: 0.35rem;
+  padding: 0.5rem;
+  margin-bottom: 0.5rem;
+  background: color-mix(in srgb, var(--color-card) 70%, transparent);
+  border: 1px dashed var(--color-border);
+  border-radius: var(--radius-sm, 0.25rem);
+}
+
+/* ---- Drawer (task detail side panel) --------------------------------- */
+
+.hermes-kanban-drawer-shade {
+  position: fixed;
+  inset: 0;
+  background: rgba(0, 0, 0, 0.45);
+  z-index: 60;
+  display: flex;
+  justify-content: flex-end;
+}
+
+.hermes-kanban-drawer {
+  width: min(480px, 92vw);
+  height: 100vh;
+  background: var(--color-card);
+  border-left: 1px solid var(--color-border);
+  display: flex;
+  flex-direction: column;
+  box-shadow: -4px 0 18px rgba(0, 0, 0, 0.35);
+  animation: hermes-kanban-drawer-in 180ms ease-out;
+}
+
+@keyframes hermes-kanban-drawer-in {
+  from { transform: translateX(100%); opacity: 0.3; }
+  to   { transform: translateX(0);    opacity: 1; }
+}
+
+.hermes-kanban-drawer-head {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  padding: 0.6rem 0.8rem;
+  border-bottom: 1px solid var(--color-border);
+  font-family: var(--font-mono, ui-monospace, monospace);
+}
+
+.hermes-kanban-drawer-close {
+  appearance: none;
+  background: transparent;
+  border: 0;
+  color: var(--color-muted-foreground);
+  font-size: 1.25rem;
+  line-height: 1;
+  cursor: pointer;
+  padding: 0 0.25rem;
+}
+.hermes-kanban-drawer-close:hover { color: var(--color-foreground); }
+
+.hermes-kanban-drawer-body {
+  flex: 1;
+  overflow-y: auto;
+  padding: 0.9rem;
+  display: flex;
+  flex-direction: column;
+  gap: 0.85rem;
+}
+
+.hermes-kanban-drawer-title {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  font-size: 1rem;
+  font-weight: 600;
+}
+
+.hermes-kanban-drawer-meta {
+  display: flex;
+  flex-direction: column;
+  gap: 0.15rem;
+  padding: 0.5rem 0.6rem;
+  background: color-mix(in srgb, var(--color-foreground) 4%, transparent);
+  border: 1px solid var(--color-border);
+  border-radius: var(--radius-sm, 0.25rem);
+}
+
+.hermes-kanban-meta-row {
+  display: flex;
+  gap: 0.5rem;
+  font-size: 0.72rem;
+}
+.hermes-kanban-meta-label {
+  width: 92px;
+  color: var(--color-muted-foreground);
+}
+.hermes-kanban-meta-value {
+  color: var(--color-foreground);
+  word-break: break-word;
+}
+
+.hermes-kanban-actions {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 0.3rem;
+}
+
+.hermes-kanban-section {
+  display: flex;
+  flex-direction: column;
+  gap: 0.35rem;
+}
+
+.hermes-kanban-section-head {
+  font-size: 0.72rem;
+  font-weight: 600;
+  text-transform: uppercase;
+  letter-spacing: 0.07em;
+  color: var(--color-muted-foreground);
+}
+
+.hermes-kanban-pre {
+  margin: 0;
+  padding: 0.45rem 0.55rem;
+  white-space: pre-wrap;
+  word-break: break-word;
+  background: color-mix(in srgb, var(--color-foreground) 4%, transparent);
+  border: 1px solid var(--color-border);
+  border-radius: var(--radius-sm, 0.25rem);
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-size: 0.72rem;
+  color: var(--color-foreground);
+}
+
+.hermes-kanban-comment {
+  border-left: 2px solid color-mix(in srgb, var(--color-ring) 35%, transparent);
+  padding-left: 0.5rem;
+  display: flex;
+  flex-direction: column;
+  gap: 0.2rem;
+}
+
+.hermes-kanban-comment-head {
+  display: flex;
+  gap: 0.5rem;
+  font-size: 0.7rem;
+}
+.hermes-kanban-comment-author {
+  font-weight: 600;
+  color: var(--color-foreground);
+}
+.hermes-kanban-comment-ago {
+  color: var(--color-muted-foreground);
+}
+
+.hermes-kanban-event {
+  display: flex;
+  gap: 0.5rem;
+  font-size: 0.7rem;
+  color: var(--color-muted-foreground);
+  font-family: var(--font-mono, ui-monospace, monospace);
+}
+.hermes-kanban-event-kind {
+  color: var(--color-foreground);
+  min-width: 6rem;
+}
+.hermes-kanban-event-payload {
+  color: var(--color-muted-foreground);
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+  max-width: 280px;
+}
+
+.hermes-kanban-drawer-comment-row {
+  display: flex;
+  gap: 0.4rem;
+  padding: 0.55rem 0.75rem;
+  border-top: 1px solid var(--color-border);
+  background: color-mix(in srgb, var(--color-card) 90%, transparent);
+}
+
+.hermes-kanban-count {
+  display: inline-flex;
+  gap: 0.2rem;
+  align-items: center;
+}
+
+/* ---- Selection chrome ----------------------------------------------- */
+
+.hermes-kanban-card--selected :where(.hermes-kanban-card-content) {
+  box-shadow: 0 0 0 2px var(--color-ring) inset,
+              0 0 0 1px var(--color-ring) inset;
+  background: color-mix(in srgb, var(--color-ring) 6%, var(--color-card));
+}
+
+.hermes-kanban-card-check {
+  width: 0.85rem;
+  height: 0.85rem;
+  margin: 0;
+  cursor: pointer;
+  accent-color: var(--color-ring);
+}
+
+/* ---- Bulk action bar ------------------------------------------------ */
+
+.hermes-kanban-bulk {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  padding: 0.4rem 0.75rem;
+  background: color-mix(in srgb, var(--color-ring) 10%, var(--color-card));
+  border: 1px solid color-mix(in srgb, var(--color-ring) 40%, var(--color-border));
+  border-radius: var(--radius-sm, 0.25rem);
+  flex-wrap: wrap;
+}
+.hermes-kanban-bulk-count {
+  font-weight: 600;
+  font-size: 0.75rem;
+  padding-right: 0.25rem;
+}
+.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-btn:hover {
+  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
+}
+.hermes-kanban-bulk-reassign {
+  display: flex;
+  align-items: center;
+  gap: 0.25rem;
+  padding-left: 0.5rem;
+  border-left: 1px solid color-mix(in srgb, var(--color-border) 70%, transparent);
+}
+
+/* ---- Dependency editor chips --------------------------------------- */
+
+.hermes-kanban-deps-row {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  margin-bottom: 0.4rem;
+}
+.hermes-kanban-deps-label {
+  font-size: 0.68rem;
+  text-transform: uppercase;
+  letter-spacing: 0.08em;
+  color: var(--color-muted-foreground);
+  min-width: 4rem;
+}
+.hermes-kanban-deps-chips {
+  display: flex;
+  gap: 0.3rem;
+  flex-wrap: wrap;
+  flex: 1;
+}
+.hermes-kanban-deps-empty {
+  font-size: 0.7rem;
+  color: var(--color-muted-foreground);
+  font-style: italic;
+}
+.hermes-kanban-dep-chip {
+  display: inline-flex;
+  align-items: center;
+  gap: 0.15rem;
+  padding: 0.1rem 0.35rem;
+  background: color-mix(in srgb, var(--color-foreground) 6%, transparent);
+  border: 1px solid var(--color-border);
+  border-radius: var(--radius-sm, 0.25rem);
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-size: 0.68rem;
+  color: var(--color-foreground);
+}
+.hermes-kanban-dep-chip-x {
+  appearance: none;
+  background: transparent;
+  border: 0;
+  color: var(--color-muted-foreground);
+  cursor: pointer;
+  font-size: 0.85rem;
+  line-height: 1;
+  padding: 0 0.15rem;
+}
+.hermes-kanban-dep-chip-x:hover { color: var(--color-destructive, #d14a4a); }
+
+/* ---- Inline edit affordances --------------------------------------- */
+
+.hermes-kanban-editable {
+  cursor: pointer;
+  border-bottom: 1px dotted color-mix(in srgb, var(--color-border) 80%, transparent);
+}
+.hermes-kanban-editable:hover {
+  color: var(--color-foreground);
+  border-bottom-color: var(--color-ring);
+}
+
+.hermes-kanban-drawer-title-text {
+  cursor: pointer;
+}
+.hermes-kanban-drawer-title-text:hover {
+  text-decoration: underline;
+  text-decoration-color: var(--color-ring);
+  text-decoration-style: dotted;
+  text-underline-offset: 3px;
+}
+
+.hermes-kanban-edit-row {
+  display: flex;
+  align-items: center;
+  gap: 0.35rem;
+  width: 100%;
+}
+
+.hermes-kanban-section-head-row {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  gap: 0.5rem;
+}
+.hermes-kanban-edit-link {
+  appearance: none;
+  background: transparent;
+  border: 0;
+  color: var(--color-muted-foreground);
+  font-size: 0.7rem;
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+  cursor: pointer;
+  padding: 0;
+}
+.hermes-kanban-edit-link:hover { color: var(--color-ring); }
+
+.hermes-kanban-textarea {
+  width: 100%;
+  min-height: 8rem;
+  background: var(--color-card);
+  color: var(--color-foreground);
+  border: 1px solid var(--color-border);
+  border-radius: var(--radius-sm, 0.25rem);
+  padding: 0.5rem 0.6rem;
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-size: 0.8rem;
+  line-height: 1.5;
+  resize: vertical;
+}
+.hermes-kanban-textarea:focus {
+  outline: none;
+  border-color: var(--color-ring);
+  box-shadow: 0 0 0 2px color-mix(in srgb, var(--color-ring) 30%, transparent);
+}
+
+/* ---- Markdown rendering -------------------------------------------- */
+
+.hermes-kanban-md {
+  font-size: 0.8rem;
+  line-height: 1.55;
+  color: var(--color-foreground);
+}
+.hermes-kanban-md p  { margin: 0.25rem 0; }
+.hermes-kanban-md h1,
+.hermes-kanban-md h2,
+.hermes-kanban-md h3,
+.hermes-kanban-md h4 {
+  margin: 0.6rem 0 0.2rem;
+  line-height: 1.25;
+}
+.hermes-kanban-md h1 { font-size: 1.05rem; }
+.hermes-kanban-md h2 { font-size: 0.95rem; }
+.hermes-kanban-md h3 { font-size: 0.88rem; }
+.hermes-kanban-md h4 { font-size: 0.82rem; }
+.hermes-kanban-md ul {
+  margin: 0.25rem 0 0.25rem 1.1rem;
+  padding: 0;
+}
+.hermes-kanban-md li { margin: 0.1rem 0; }
+.hermes-kanban-md a {
+  color: var(--color-ring);
+  text-decoration: underline;
+}
+.hermes-kanban-md code {
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-size: 0.75rem;
+  padding: 0.05rem 0.3rem;
+  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
+  border-radius: 3px;
+}
+.hermes-kanban-md-code {
+  margin: 0.35rem 0;
+  padding: 0.5rem 0.6rem;
+  background: color-mix(in srgb, var(--color-foreground) 5%, transparent);
+  border: 1px solid var(--color-border);
+  border-radius: var(--radius-sm, 0.25rem);
+  overflow-x: auto;
+}
+.hermes-kanban-md-code code {
+  background: transparent;
+  padding: 0;
+  font-size: 0.75rem;
+  white-space: pre;
+}
+.hermes-kanban-md strong { font-weight: 600; }
+
+/* ---- Touch-drag proxy ---------------------------------------------- */
+
+.hermes-kanban-touch-proxy {
+  pointer-events: none;
+  opacity: 0.85;
+  box-shadow: 0 8px 20px rgba(0, 0, 0, 0.35);
+  transform: scale(1.02);
+  transition: none;
+}
+
+
+/* ---- Staleness tiers ------------------------------------------------ */
+
+.hermes-kanban-card--stale-amber :where(.hermes-kanban-card-content) {
+  box-shadow: 0 0 0 1px #d4b34888 inset;
+}
+.hermes-kanban-card--stale-amber:hover :where(.hermes-kanban-card-content) {
+  box-shadow: 0 0 0 2px #d4b348 inset;
+}
+.hermes-kanban-card--stale-red :where(.hermes-kanban-card-content) {
+  box-shadow: 0 0 0 1px var(--color-destructive, #d14a4a) inset,
+              0 0 8px color-mix(in srgb, var(--color-destructive, #d14a4a) 30%, transparent);
+}
+.hermes-kanban-card--stale-red:hover :where(.hermes-kanban-card-content) {
+  box-shadow: 0 0 0 2px var(--color-destructive, #d14a4a) inset,
+              0 0 10px color-mix(in srgb, var(--color-destructive, #d14a4a) 45%, transparent);
+}
+
+/* ---- Worker log pane ------------------------------------------------ */
+
+.hermes-kanban-log {
+  max-height: 340px;
+  overflow: auto;
+  white-space: pre;
+  font-size: 0.7rem;
+  line-height: 1.45;
+}
+
+
+/* ---- Run history (per-attempt log in the drawer) ------------------- */
+
+.hermes-kanban-run {
+  border-left: 2px solid var(--color-border);
+  padding: 0.35rem 0.5rem;
+  margin-bottom: 0.4rem;
+  background: color-mix(in srgb, var(--color-foreground) 3%, transparent);
+  border-radius: var(--radius-sm, 0.25rem);
+}
+.hermes-kanban-run--active  { border-left-color: #3fb97d; }
+.hermes-kanban-run--completed { border-left-color: #4a8cd1; }
+.hermes-kanban-run--ended { border-left-color: #6b7280; }  /* generic fallback when outcome is unset */
+.hermes-kanban-run--blocked { border-left-color: var(--color-destructive, #d14a4a); }
+.hermes-kanban-run--crashed,
+.hermes-kanban-run--timed_out,
+.hermes-kanban-run--gave_up,
+.hermes-kanban-run--spawn_failed {
+  border-left-color: var(--color-destructive, #d14a4a);
+  background: color-mix(in srgb, var(--color-destructive, #d14a4a) 6%, transparent);
+}
+.hermes-kanban-run--reclaimed { border-left-color: #d4b348; }
+
+.hermes-kanban-run-head {
+  display: flex;
+  align-items: center;
+  gap: 0.6rem;
+  font-size: 0.7rem;
+}
+.hermes-kanban-run-outcome {
+  font-family: var(--font-mono, ui-monospace, monospace);
+  font-weight: 600;
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+  color: var(--color-foreground);
+}
+.hermes-kanban-run-profile {
+  color: var(--color-muted-foreground);
+}
+.hermes-kanban-run-elapsed {
+  font-variant-numeric: tabular-nums;
+  color: var(--color-muted-foreground);
+}
+.hermes-kanban-run-ago {
+  margin-left: auto;
+  color: var(--color-muted-foreground);
+}
+.hermes-kanban-run-summary {
+  font-size: 0.75rem;
+  padding: 0.2rem 0 0;
+  color: var(--color-foreground);
+}
+.hermes-kanban-run-error {
+  font-size: 0.7rem;
+  color: var(--color-destructive, #d14a4a);
+  padding: 0.15rem 0 0;
+  font-family: var(--font-mono, ui-monospace, monospace);
+}
+.hermes-kanban-run-meta {
+  display: block;
+  font-size: 0.65rem;
+  padding: 0.15rem 0 0;
+  color: var(--color-muted-foreground);
+  white-space: pre-wrap;
+  word-break: break-word;
+  font-family: var(--font-mono, ui-monospace, monospace);
+}

plugins/kanban/dashboard/manifest.json

@@ -0,0 +1,14 @@
+{
+  "name": "kanban",
+  "label": "Kanban",
+  "description": "Multi-agent collaboration board — drag-drop cards across columns, read comment threads, see which profile is running what",
+  "icon": "Package",
+  "version": "1.0.0",
+  "tab": {
+    "path": "/kanban",
+    "position": "after:skills"
+  },
+  "entry": "dist/index.js",
+  "css": "dist/style.css",
+  "api": "plugin_api.py"
+}

plugins/kanban/dashboard/plugin_api.py

@@ -0,0 +1,845 @@
+"""Kanban dashboard plugin — backend API routes.
+
+Mounted at /api/plugins/kanban/ by the dashboard plugin system.
+
+This layer is intentionally thin: every handler is a small wrapper around
+``hermes_cli.kanban_db`` or a direct SQL query. Writes use the same code
+paths the CLI and gateway ``/kanban`` command use, so the three surfaces
+cannot drift.
+
+Live updates arrive via the ``/events`` WebSocket, which tails the
+append-only ``task_events`` table on a short poll interval (WAL mode lets
+reads run alongside the dispatcher's IMMEDIATE write transactions).
+
+Security note
+-------------
+The dashboard's HTTP auth middleware (``web_server.auth_middleware``)
+explicitly skips ``/api/plugins/`` — plugin routes are unauthenticated by
+design because the dashboard binds to localhost by default. For the
+WebSocket we still require the session token as a ``?token=`` query
+parameter (browsers cannot set the ``Authorization`` header on an upgrade
+request), matching the established pattern used by the in-browser PTY
+bridge in ``hermes_cli/web_server.py``. If you run the dashboard with
+``--host 0.0.0.0``, every plugin route — kanban included — becomes
+reachable from the network. Don't do that on a shared host.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import hmac
+import json
+import logging
+import sqlite3
+import time
+from dataclasses import asdict
+from typing import Any, Optional
+
+from fastapi import APIRouter, HTTPException, Query, WebSocket, WebSocketDisconnect, status as http_status
+from pydantic import BaseModel, Field
+
+from hermes_cli import kanban_db
+
+log = logging.getLogger(__name__)
+
+router = APIRouter()
+
+
+# ---------------------------------------------------------------------------
+# Auth helper — WebSocket only (HTTP routes live behind the dashboard's
+# existing plugin-bypass; this is documented above).
+# ---------------------------------------------------------------------------
+
+def _check_ws_token(provided: Optional[str]) -> bool:
+    """Constant-time compare against the dashboard session token.
+
+    Imported lazily so the plugin still loads in test contexts where the
+    dashboard web_server module isn't importable (e.g. the bare-FastAPI
+    test harness).
+    """
+    if not provided:
+        return False
+    try:
+        from hermes_cli import web_server as _ws
+    except Exception:
+        # No dashboard context (tests). Accept so the tail loop is still
+        # testable; in production the dashboard module always imports
+        # cleanly because it's the caller.
+        return True
+    expected = getattr(_ws, "_SESSION_TOKEN", None)
+    if not expected:
+        return True
+    return hmac.compare_digest(str(provided), str(expected))
+
+
+def _conn():
+    """Open a kanban_db connection, creating the schema on first use.
+
+    Every handler that mutates the DB goes through this so the plugin
+    self-heals on a fresh install (no user-visible "no such table"
+    error if somebody hits POST /tasks before GET /board).
+    ``init_db`` is idempotent.
+    """
+    try:
+        kanban_db.init_db()
+    except Exception as exc:
+        log.warning("kanban init_db failed: %s", exc)
+    return kanban_db.connect()
+
+
+# ---------------------------------------------------------------------------
+# Serialization helpers
+# ---------------------------------------------------------------------------
+
+# Columns shown by the dashboard, in left-to-right order. "archived" is
+# available via a filter toggle rather than a visible column.
+BOARD_COLUMNS: list[str] = [
+    "triage", "todo", "ready", "running", "blocked", "done",
+]
+
+
+def _task_dict(task: kanban_db.Task) -> dict[str, Any]:
+    d = asdict(task)
+    # Add derived age metrics so the UI can colour stale cards without
+    # computing deltas client-side.
+    d["age"] = kanban_db.task_age(task)
+    # Keep body short on list endpoints; full body comes from /tasks/:id.
+    return d
+
+
+def _event_dict(event: kanban_db.Event) -> dict[str, Any]:
+    return {
+        "id": event.id,
+        "task_id": event.task_id,
+        "kind": event.kind,
+        "payload": event.payload,
+        "created_at": event.created_at,
+        "run_id": event.run_id,
+    }
+
+
+def _comment_dict(c: kanban_db.Comment) -> dict[str, Any]:
+    return {
+        "id": c.id,
+        "task_id": c.task_id,
+        "author": c.author,
+        "body": c.body,
+        "created_at": c.created_at,
+    }
+
+
+def _run_dict(r: kanban_db.Run) -> dict[str, Any]:
+    """Serialise a Run for the drawer's Run history section."""
+    return {
+        "id": r.id,
+        "task_id": r.task_id,
+        "profile": r.profile,
+        "step_key": r.step_key,
+        "status": r.status,
+        "claim_lock": r.claim_lock,
+        "claim_expires": r.claim_expires,
+        "worker_pid": r.worker_pid,
+        "max_runtime_seconds": r.max_runtime_seconds,
+        "last_heartbeat_at": r.last_heartbeat_at,
+        "started_at": r.started_at,
+        "ended_at": r.ended_at,
+        "outcome": r.outcome,
+        "summary": r.summary,
+        "metadata": r.metadata,
+        "error": r.error,
+    }
+
+
+def _links_for(conn: sqlite3.Connection, task_id: str) -> dict[str, list[str]]:
+    """Return {'parents': [...], 'children': [...]} for a task."""
+    parents = [
+        r["parent_id"]
+        for r in conn.execute(
+            "SELECT parent_id FROM task_links WHERE child_id = ? ORDER BY parent_id",
+            (task_id,),
+        )
+    ]
+    children = [
+        r["child_id"]
+        for r in conn.execute(
+            "SELECT child_id FROM task_links WHERE parent_id = ? ORDER BY child_id",
+            (task_id,),
+        )
+    ]
+    return {"parents": parents, "children": children}
+
+
+# ---------------------------------------------------------------------------
+# GET /board
+# ---------------------------------------------------------------------------
+
+@router.get("/board")
+def get_board(
+    tenant: Optional[str] = Query(None, description="Filter to a single tenant"),
+    include_archived: bool = Query(False),
+):
+    """Return the full board grouped by status column.
+
+    ``_conn()`` auto-initializes ``kanban.db`` on first call so a fresh
+    install doesn't surface a "failed to load" error on the plugin tab.
+    """
+    conn = _conn()
+    try:
+        tasks = kanban_db.list_tasks(
+            conn, tenant=tenant, include_archived=include_archived
+        )
+        # Pre-fetch link counts per task (cheap: one query).
+        link_counts: dict[str, dict[str, int]] = {}
+        for row in conn.execute(
+            "SELECT parent_id, child_id FROM task_links"
+        ).fetchall():
+            link_counts.setdefault(row["parent_id"], {"parents": 0, "children": 0})[
+                "children"
+            ] += 1
+            link_counts.setdefault(row["child_id"], {"parents": 0, "children": 0})[
+                "parents"
+            ] += 1
+
+        # Comment + event counts (both cheap aggregates).
+        comment_counts: dict[str, int] = {
+            r["task_id"]: r["n"]
+            for r in conn.execute(
+                "SELECT task_id, COUNT(*) AS n FROM task_comments GROUP BY task_id"
+            )
+        }
+
+        # Progress rollup: for each parent, how many children are done / total.
+        # One pass over task_links joined with child status — cheaper than
+        # N per-task queries and the plugin uses it to render "N/M".
+        progress: dict[str, dict[str, int]] = {}
+        for row in conn.execute(
+            "SELECT l.parent_id AS pid, t.status AS cstatus "
+            "FROM task_links l JOIN tasks t ON t.id = l.child_id"
+        ).fetchall():
+            p = progress.setdefault(row["pid"], {"done": 0, "total": 0})
+            p["total"] += 1
+            if row["cstatus"] == "done":
+                p["done"] += 1
+
+        latest_event_id = conn.execute(
+            "SELECT COALESCE(MAX(id), 0) AS m FROM task_events"
+        ).fetchone()["m"]
+
+        columns: dict[str, list[dict]] = {c: [] for c in BOARD_COLUMNS}
+        if include_archived:
+            columns["archived"] = []
+
+        for t in tasks:
+            d = _task_dict(t)
+            d["link_counts"] = link_counts.get(t.id, {"parents": 0, "children": 0})
+            d["comment_count"] = comment_counts.get(t.id, 0)
+            d["progress"] = progress.get(t.id)  # None when the task has no children
+            col = t.status if t.status in columns else "todo"
+            columns[col].append(d)
+
+        # Stable per-column ordering already applied by list_tasks
+        # (priority DESC, created_at ASC), keep as-is.
+
+        # List of known tenants for the UI filter dropdown.
+        tenants = [
+            r["tenant"]
+            for r in conn.execute(
+                "SELECT DISTINCT tenant FROM tasks WHERE tenant IS NOT NULL ORDER BY tenant"
+            )
+        ]
+        # List of distinct assignees for the lane-by-profile sub-grouping.
+        assignees = [
+            r["assignee"]
+            for r in conn.execute(
+                "SELECT DISTINCT assignee FROM tasks WHERE assignee IS NOT NULL "
+                "AND status != 'archived' ORDER BY assignee"
+            )
+        ]
+
+        return {
+            "columns": [
+                {"name": name, "tasks": columns[name]} for name in columns.keys()
+            ],
+            "tenants": tenants,
+            "assignees": assignees,
+            "latest_event_id": int(latest_event_id),
+            "now": int(time.time()),
+        }
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# GET /tasks/:id
+# ---------------------------------------------------------------------------
+
+@router.get("/tasks/{task_id}")
+def get_task(task_id: str):
+    conn = _conn()
+    try:
+        task = kanban_db.get_task(conn, task_id)
+        if task is None:
+            raise HTTPException(status_code=404, detail=f"task {task_id} not found")
+        return {
+            "task": _task_dict(task),
+            "comments": [_comment_dict(c) for c in kanban_db.list_comments(conn, task_id)],
+            "events": [_event_dict(e) for e in kanban_db.list_events(conn, task_id)],
+            "links": _links_for(conn, task_id),
+            "runs": [_run_dict(r) for r in kanban_db.list_runs(conn, task_id)],
+        }
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# POST /tasks
+# ---------------------------------------------------------------------------
+
+class CreateTaskBody(BaseModel):
+    title: str
+    body: Optional[str] = None
+    assignee: Optional[str] = None
+    tenant: Optional[str] = None
+    priority: int = 0
+    workspace_kind: str = "scratch"
+    workspace_path: Optional[str] = None
+    parents: list[str] = Field(default_factory=list)
+    triage: bool = False
+    idempotency_key: Optional[str] = None
+    max_runtime_seconds: Optional[int] = None
+    skills: Optional[list[str]] = None
+
+
+@router.post("/tasks")
+def create_task(payload: CreateTaskBody):
+    conn = _conn()
+    try:
+        task_id = kanban_db.create_task(
+            conn,
+            title=payload.title,
+            body=payload.body,
+            assignee=payload.assignee,
+            created_by="dashboard",
+            workspace_kind=payload.workspace_kind,
+            workspace_path=payload.workspace_path,
+            tenant=payload.tenant,
+            priority=payload.priority,
+            parents=payload.parents,
+            triage=payload.triage,
+            idempotency_key=payload.idempotency_key,
+            max_runtime_seconds=payload.max_runtime_seconds,
+            skills=payload.skills,
+        )
+        task = kanban_db.get_task(conn, task_id)
+        body: dict[str, Any] = {"task": _task_dict(task) if task else None}
+        # Surface a dispatcher-presence warning so the UI can show a
+        # banner when a `ready` task would otherwise sit idle because no
+        # gateway is running (or dispatch_in_gateway=false). Only emit
+        # for ready+assigned tasks; triage/todo are expected to wait,
+        # and unassigned tasks can't be dispatched regardless.
+        if task and task.status == "ready" and task.assignee:
+            try:
+                from hermes_cli.kanban import _check_dispatcher_presence
+                running, message = _check_dispatcher_presence()
+                if not running and message:
+                    body["warning"] = message
+            except Exception:
+                # Probe failure must never block the create itself.
+                pass
+        return body
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# PATCH /tasks/:id  (status / assignee / priority / title / body)
+# ---------------------------------------------------------------------------
+
+class UpdateTaskBody(BaseModel):
+    status: Optional[str] = None
+    assignee: Optional[str] = None
+    priority: Optional[int] = None
+    title: Optional[str] = None
+    body: Optional[str] = None
+    result: Optional[str] = None
+    block_reason: Optional[str] = None
+    # Structured handoff fields — forwarded to complete_task when status
+    # transitions to 'done'. Dashboard parity with ``hermes kanban
+    # complete --summary ... --metadata ...``.
+    summary: Optional[str] = None
+    metadata: Optional[dict] = None
+
+
+@router.patch("/tasks/{task_id}")
+def update_task(task_id: str, payload: UpdateTaskBody):
+    conn = _conn()
+    try:
+        task = kanban_db.get_task(conn, task_id)
+        if task is None:
+            raise HTTPException(status_code=404, detail=f"task {task_id} not found")
+
+        # --- assignee ----------------------------------------------------
+        if payload.assignee is not None:
+            try:
+                ok = kanban_db.assign_task(
+                    conn, task_id, payload.assignee or None,
+                )
+            except RuntimeError as e:
+                raise HTTPException(status_code=409, detail=str(e))
+            if not ok:
+                raise HTTPException(status_code=404, detail="task not found")
+
+        # --- status -------------------------------------------------------
+        if payload.status is not None:
+            s = payload.status
+            ok = True
+            if s == "done":
+                ok = kanban_db.complete_task(
+                    conn, task_id,
+                    result=payload.result,
+                    summary=payload.summary,
+                    metadata=payload.metadata,
+                )
+            elif s == "blocked":
+                ok = kanban_db.block_task(conn, task_id, reason=payload.block_reason)
+            elif s == "ready":
+                # Re-open a blocked task, or just an explicit status set.
+                current = kanban_db.get_task(conn, task_id)
+                if current and current.status == "blocked":
+                    ok = kanban_db.unblock_task(conn, task_id)
+                else:
+                    # Direct status write for drag-drop (todo -> ready etc).
+                    ok = _set_status_direct(conn, task_id, "ready")
+            elif s == "archived":
+                ok = kanban_db.archive_task(conn, task_id)
+            elif s in ("todo", "running", "triage"):
+                ok = _set_status_direct(conn, task_id, s)
+            else:
+                raise HTTPException(status_code=400, detail=f"unknown status: {s}")
+            if not ok:
+                raise HTTPException(
+                    status_code=409,
+                    detail=f"status transition to {s!r} not valid from current state",
+                )
+
+        # --- priority -----------------------------------------------------
+        if payload.priority is not None:
+            with kanban_db.write_txn(conn):
+                conn.execute(
+                    "UPDATE tasks SET priority = ? WHERE id = ?",
+                    (int(payload.priority), task_id),
+                )
+                conn.execute(
+                    "INSERT INTO task_events (task_id, kind, payload, created_at) "
+                    "VALUES (?, 'reprioritized', ?, ?)",
+                    (task_id, json.dumps({"priority": int(payload.priority)}),
+                     int(time.time())),
+                )
+
+        # --- title / body -------------------------------------------------
+        if payload.title is not None or payload.body is not None:
+            with kanban_db.write_txn(conn):
+                sets, vals = [], []
+                if payload.title is not None:
+                    if not payload.title.strip():
+                        raise HTTPException(status_code=400, detail="title cannot be empty")
+                    sets.append("title = ?")
+                    vals.append(payload.title.strip())
+                if payload.body is not None:
+                    sets.append("body = ?")
+                    vals.append(payload.body)
+                vals.append(task_id)
+                conn.execute(
+                    f"UPDATE tasks SET {', '.join(sets)} WHERE id = ?", vals,
+                )
+                conn.execute(
+                    "INSERT INTO task_events (task_id, kind, payload, created_at) "
+                    "VALUES (?, 'edited', NULL, ?)",
+                    (task_id, int(time.time())),
+                )
+
+        updated = kanban_db.get_task(conn, task_id)
+        return {"task": _task_dict(updated) if updated else None}
+    finally:
+        conn.close()
+
+
+def _set_status_direct(
+    conn: sqlite3.Connection, task_id: str, new_status: str,
+) -> bool:
+    """Direct status write for drag-drop moves that aren't covered by the
+    structured complete/block/unblock/archive verbs (e.g. todo<->ready,
+    running<->ready). Appends a ``status`` event row for the live feed.
+
+    When this transitions OFF ``running`` to anything other than the
+    terminal verbs above (which own their own run closing), we close the
+    active run with outcome='reclaimed' so attempt history isn't
+    orphaned. ``running -> ready`` via drag-drop is the common case
+    (user yanking a stuck worker back to the queue).
+    """
+    with kanban_db.write_txn(conn):
+        # Snapshot current state so we know whether to close a run.
+        prev = conn.execute(
+            "SELECT status, current_run_id FROM tasks WHERE id = ?",
+            (task_id,),
+        ).fetchone()
+        if prev is None:
+            return False
+        was_running = prev["status"] == "running"
+
+        cur = conn.execute(
+            "UPDATE tasks SET status = ?, "
+            "  claim_lock = CASE WHEN ? = 'running' THEN claim_lock ELSE NULL END, "
+            "  claim_expires = CASE WHEN ? = 'running' THEN claim_expires ELSE NULL END, "
+            "  worker_pid = CASE WHEN ? = 'running' THEN worker_pid ELSE NULL END "
+            "WHERE id = ?",
+            (new_status, new_status, new_status, new_status, task_id),
+        )
+        if cur.rowcount != 1:
+            return False
+        run_id = None
+        if was_running and new_status != "running" and prev["current_run_id"]:
+            run_id = kanban_db._end_run(
+                conn, task_id,
+                outcome="reclaimed", status="reclaimed",
+                summary=f"status changed to {new_status} (dashboard/direct)",
+            )
+        conn.execute(
+            "INSERT INTO task_events (task_id, run_id, kind, payload, created_at) "
+            "VALUES (?, ?, 'status', ?, ?)",
+            (task_id, run_id, json.dumps({"status": new_status}), int(time.time())),
+        )
+    # If we re-opened something, children may have gone stale.
+    if new_status in ("done", "ready"):
+        kanban_db.recompute_ready(conn)
+    return True
+
+
+# ---------------------------------------------------------------------------
+# Comments
+# ---------------------------------------------------------------------------
+
+class CommentBody(BaseModel):
+    body: str
+    author: Optional[str] = "dashboard"
+
+
+@router.post("/tasks/{task_id}/comments")
+def add_comment(task_id: str, payload: CommentBody):
+    if not payload.body.strip():
+        raise HTTPException(status_code=400, detail="body is required")
+    conn = _conn()
+    try:
+        if kanban_db.get_task(conn, task_id) is None:
+            raise HTTPException(status_code=404, detail=f"task {task_id} not found")
+        kanban_db.add_comment(
+            conn, task_id, author=payload.author or "dashboard", body=payload.body,
+        )
+        return {"ok": True}
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# Links
+# ---------------------------------------------------------------------------
+
+class LinkBody(BaseModel):
+    parent_id: str
+    child_id: str
+
+
+@router.post("/links")
+def add_link(payload: LinkBody):
+    conn = _conn()
+    try:
+        kanban_db.link_tasks(conn, payload.parent_id, payload.child_id)
+        return {"ok": True}
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    finally:
+        conn.close()
+
+
+@router.delete("/links")
+def delete_link(parent_id: str = Query(...), child_id: str = Query(...)):
+    conn = _conn()
+    try:
+        ok = kanban_db.unlink_tasks(conn, parent_id, child_id)
+        return {"ok": bool(ok)}
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# Bulk actions (multi-select on the board)
+# ---------------------------------------------------------------------------
+
+class BulkTaskBody(BaseModel):
+    ids: list[str]
+    status: Optional[str] = None
+    assignee: Optional[str] = None  # "" or None = unassign
+    priority: Optional[int] = None
+    archive: bool = False
+
+
+@router.post("/tasks/bulk")
+def bulk_update(payload: BulkTaskBody):
+    """Apply the same patch to every id in ``payload.ids``.
+
+    This is an *independent* iteration — per-task failures don't abort
+    siblings. Returns per-id outcome so the UI can surface partials.
+    """
+    ids = [i for i in (payload.ids or []) if i]
+    if not ids:
+        raise HTTPException(status_code=400, detail="ids is required")
+    results: list[dict] = []
+    conn = _conn()
+    try:
+        for tid in ids:
+            entry: dict[str, Any] = {"id": tid, "ok": True}
+            try:
+                task = kanban_db.get_task(conn, tid)
+                if task is None:
+                    entry.update(ok=False, error="not found")
+                    results.append(entry)
+                    continue
+                if payload.archive:
+                    if not kanban_db.archive_task(conn, tid):
+                        entry.update(ok=False, error="archive refused")
+                if payload.status is not None and not payload.archive:
+                    s = payload.status
+                    if s == "done":
+                        ok = kanban_db.complete_task(conn, tid)
+                    elif s == "blocked":
+                        ok = kanban_db.block_task(conn, tid)
+                    elif s == "ready":
+                        cur = kanban_db.get_task(conn, tid)
+                        if cur and cur.status == "blocked":
+                            ok = kanban_db.unblock_task(conn, tid)
+                        else:
+                            ok = _set_status_direct(conn, tid, "ready")
+                    elif s in ("todo", "running", "triage"):
+                        ok = _set_status_direct(conn, tid, s)
+                    else:
+                        entry.update(ok=False, error=f"unknown status {s!r}")
+                        results.append(entry)
+                        continue
+                    if not ok:
+                        entry.update(ok=False, error=f"transition to {s!r} refused")
+                if payload.assignee is not None:
+                    try:
+                        if not kanban_db.assign_task(
+                            conn, tid, payload.assignee or None,
+                        ):
+                            entry.update(ok=False, error="assign refused")
+                    except RuntimeError as e:
+                        entry.update(ok=False, error=str(e))
+                if payload.priority is not None:
+                    with kanban_db.write_txn(conn):
+                        conn.execute(
+                            "UPDATE tasks SET priority = ? WHERE id = ?",
+                            (int(payload.priority), tid),
+                        )
+                        conn.execute(
+                            "INSERT INTO task_events (task_id, kind, payload, created_at) "
+                            "VALUES (?, 'reprioritized', ?, ?)",
+                            (tid, json.dumps({"priority": int(payload.priority)}),
+                             int(time.time())),
+                        )
+            except Exception as e:  # defensive — one bad id shouldn't kill the batch
+                entry.update(ok=False, error=str(e))
+            results.append(entry)
+        return {"results": results}
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# Plugin config (read dashboard.kanban.* defaults from config.yaml)
+# ---------------------------------------------------------------------------
+
+@router.get("/config")
+def get_config():
+    """Return kanban dashboard preferences from ~/.hermes/config.yaml.
+
+    Reads the ``dashboard.kanban`` section if present; defaults otherwise.
+    Used by the UI to pre-select tenant filters, toggle markdown rendering,
+    or set column-width preferences without a round-trip per page load.
+    """
+    try:
+        from hermes_cli.config import load_config
+        cfg = load_config() or {}
+    except Exception:
+        cfg = {}
+    dash_cfg = (cfg.get("dashboard") or {})
+    # dashboard.kanban may itself be a dict; fall back to {}.
+    k_cfg = dash_cfg.get("kanban") or {}
+    return {
+        "default_tenant": k_cfg.get("default_tenant") or "",
+        "lane_by_profile": bool(k_cfg.get("lane_by_profile", True)),
+        "include_archived_by_default": bool(k_cfg.get("include_archived_by_default", False)),
+        "render_markdown": bool(k_cfg.get("render_markdown", True)),
+    }
+
+
+# ---------------------------------------------------------------------------
+# Stats (per-profile / per-status counts + oldest-ready age)
+# ---------------------------------------------------------------------------
+
+@router.get("/stats")
+def get_stats():
+    """Per-status + per-assignee counts + oldest-ready age.
+
+    Designed for the dashboard HUD and for router profiles that need to
+    answer "is this specialist overloaded?" without scanning the whole
+    board themselves.
+    """
+    conn = _conn()
+    try:
+        return kanban_db.board_stats(conn)
+    finally:
+        conn.close()
+
+
+@router.get("/assignees")
+def get_assignees():
+    """Known profiles + per-profile task counts.
+
+    Returns the union of ``~/.hermes/profiles/*`` on disk and every
+    distinct assignee currently used on the board. The dashboard uses
+    this to populate its assignee dropdown so a freshly-created profile
+    appears in the picker before it's been given any task.
+    """
+    conn = _conn()
+    try:
+        return {"assignees": kanban_db.known_assignees(conn)}
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# Worker log (read-only; file written by _default_spawn)
+# ---------------------------------------------------------------------------
+
+@router.get("/tasks/{task_id}/log")
+def get_task_log(task_id: str, tail: Optional[int] = Query(None, ge=1, le=2_000_000)):
+    """Return the worker's stdout/stderr log.
+
+    ``tail`` caps the response size (bytes) so the dashboard drawer
+    doesn't paginate megabytes into the browser. Returns 404 if the task
+    has never spawned. The on-disk log is rotated at 2 MiB per
+    ``_rotate_worker_log`` — a single ``.log.1`` is kept, no further
+    generations, so disk usage per task is bounded at ~4 MiB.
+    """
+    conn = _conn()
+    try:
+        task = kanban_db.get_task(conn, task_id)
+    finally:
+        conn.close()
+    if task is None:
+        raise HTTPException(status_code=404, detail=f"task {task_id} not found")
+    content = kanban_db.read_worker_log(task_id, tail_bytes=tail)
+    log_path = kanban_db.worker_log_path(task_id)
+    size = log_path.stat().st_size if log_path.exists() else 0
+    return {
+        "task_id": task_id,
+        "path": str(log_path),
+        "exists": content is not None,
+        "size_bytes": size,
+        "content": content or "",
+        # Truncated when the on-disk file was larger than the tail cap.
+        "truncated": bool(tail and size > tail),
+    }
+
+
+# ---------------------------------------------------------------------------
+# Dispatch nudge (optional quick-path so the UI doesn't wait 60 s)
+# ---------------------------------------------------------------------------
+
+@router.post("/dispatch")
+def dispatch(dry_run: bool = Query(False), max_n: int = Query(8, alias="max")):
+    conn = _conn()
+    try:
+        result = kanban_db.dispatch_once(
+            conn, dry_run=dry_run, max_spawn=max_n,
+        )
+        # DispatchResult is a dataclass.
+        try:
+            return asdict(result)
+        except TypeError:
+            return {"result": str(result)}
+    finally:
+        conn.close()
+
+
+# ---------------------------------------------------------------------------
+# WebSocket: /events?since=<event_id>
+# ---------------------------------------------------------------------------
+
+# Poll interval for the event tail loop. SQLite WAL + 300 ms polling is
+# the simplest and most robust approach; it adds a fraction of a percent
+# of CPU and has no shared state to synchronize across workers.
+_EVENT_POLL_SECONDS = 0.3
+
+
+@router.websocket("/events")
+async def stream_events(ws: WebSocket):
+    # Enforce the dashboard session token as a query param — browsers can't
+    # set Authorization on a WS upgrade. This matches how the PTY bridge
+    # authenticates in hermes_cli/web_server.py.
+    token = ws.query_params.get("token")
+    if not _check_ws_token(token):
+        await ws.close(code=http_status.WS_1008_POLICY_VIOLATION)
+        return
+    await ws.accept()
+    try:
+        since_raw = ws.query_params.get("since", "0")
+        try:
+            cursor = int(since_raw)
+        except ValueError:
+            cursor = 0
+
+        def _fetch_new(cursor_val: int) -> tuple[int, list[dict]]:
+            conn = kanban_db.connect()
+            try:
+                rows = conn.execute(
+                    "SELECT id, task_id, run_id, kind, payload, created_at "
+                    "FROM task_events WHERE id > ? ORDER BY id ASC LIMIT 200",
+                    (cursor_val,),
+                ).fetchall()
+                out: list[dict] = []
+                new_cursor = cursor_val
+                for r in rows:
+                    try:
+                        payload = json.loads(r["payload"]) if r["payload"] else None
+                    except Exception:
+                        payload = None
+                    out.append({
+                        "id": r["id"],
+                        "task_id": r["task_id"],
+                        "run_id": r["run_id"],
+                        "kind": r["kind"],
+                        "payload": payload,
+                        "created_at": r["created_at"],
+                    })
+                    new_cursor = r["id"]
+                return new_cursor, out
+            finally:
+                conn.close()
+
+        while True:
+            cursor, events = await asyncio.to_thread(_fetch_new, cursor)
+            if events:
+                await ws.send_json({"events": events, "cursor": cursor})
+            await asyncio.sleep(_EVENT_POLL_SECONDS)
+    except WebSocketDisconnect:
+        return
+    except Exception as exc:  # defensive: never crash the dashboard worker
+        log.warning("Kanban event stream error: %s", exc)
+        try:
+            await ws.close()
+        except Exception:
+            pass

plugins/kanban/systemd/hermes-kanban-dispatcher.service

@@ -0,0 +1,32 @@
+# DEPRECATED — the kanban dispatcher now runs inside the gateway by
+# default (config key: kanban.dispatch_in_gateway, default true). To
+# migrate:
+#
+#     systemctl --user disable --now hermes-kanban-dispatcher.service
+#     # then make sure a gateway is running; e.g. a systemd user unit
+#     # for `hermes gateway start`. The gateway hosts the dispatcher.
+#
+# This unit is kept for users who truly cannot run the gateway (host
+# policy forbids long-lived services, etc.). It now invokes the
+# standalone dispatcher via the explicit --force flag, so nobody
+# accidentally keeps two dispatchers racing against the same
+# kanban.db. Running this unit AND a gateway with
+# dispatch_in_gateway=true is NOT supported.
+
+[Unit]
+Description=Hermes Kanban dispatcher (DEPRECATED standalone daemon — prefer gateway-embedded dispatch)
+Documentation=https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban
+After=network.target
+
+[Service]
+Type=simple
+ExecStart=/usr/bin/env hermes kanban daemon --force --interval 60 --pidfile %t/hermes-kanban-dispatcher.pid
+Restart=on-failure
+RestartSec=5
+# Log to the journal via stdout/stderr; the dispatcher also writes per-task
+# worker output to $HERMES_HOME/kanban/logs/<task>.log.
+StandardOutput=journal
+StandardError=journal
+
+[Install]
+WantedBy=default.target

plugins/memory/hindsight/README.md

@@ -59,7 +59,8 @@ Config file: `~/.hermes/hindsight/config.json`
 
 | Key | Default | Description |
 |-----|---------|-------------|
-| `bank_id` | `hermes` | Memory bank name |
+| `bank_id` | `hermes` | Memory bank name (static fallback used when `bank_id_template` is unset or resolves empty) |
+| `bank_id_template` | — | Optional template to derive the bank name dynamically. Placeholders: `{profile}`, `{workspace}`, `{platform}`, `{user}`, `{session}`. Example: `hermes-{profile}` isolates memory per active Hermes profile. Empty placeholders collapse cleanly (e.g. `hermes-{user}` with no user becomes `hermes`). |
 | `bank_mission` | — | Reflect mission (identity/framing for reflect reasoning). Applied via Banks API. |
 | `bank_retain_mission` | — | Retain mission (steers what gets extracted). Applied via Banks API. |
 

plugins/memory/hindsight/__init__.py

@@ -3,6 +3,8 @@
 Long-term memory with knowledge graph, entity resolution, and multi-strategy
 retrieval. Supports cloud (API key) and local modes.
 
+Configurable timeout via HINDSIGHT_TIMEOUT env var or config.json.
+
 Original PR #1811 by benfrank241, adapted to MemoryProvider ABC.
 
 Config via environment variables:
@@ -11,6 +13,7 @@ Config via environment variables:
   HINDSIGHT_BUDGET                 — recall budget: low/mid/high (default: mid)
   HINDSIGHT_API_URL                — API endpoint
   HINDSIGHT_MODE                   — cloud or local (default: cloud)
+  HINDSIGHT_TIMEOUT                — API request timeout in seconds (default: 120)
   HINDSIGHT_RETAIN_TAGS            — comma-separated tags attached to retained memories
   HINDSIGHT_RETAIN_SOURCE          — metadata source value attached to retained memories
   HINDSIGHT_RETAIN_USER_PREFIX     — label used before user turns in retained transcripts
@@ -23,6 +26,7 @@ Or via $HERMES_HOME/hindsight/config.json (profile-scoped), falling back to
 from __future__ import annotations
 
 import asyncio
+import importlib
 import json
 import logging
 import os
@@ -40,6 +44,7 @@ logger = logging.getLogger(__name__)
 _DEFAULT_API_URL = "https://api.hindsight.vectorize.io"
 _DEFAULT_LOCAL_URL = "http://localhost:8888"
 _MIN_CLIENT_VERSION = "0.4.22"
+_DEFAULT_TIMEOUT = 120  # seconds — cloud API can take 30-40s per request
 _VALID_BUDGETS = {"low", "mid", "high"}
 _PROVIDER_DEFAULT_MODELS = {
     "openai": "gpt-4o-mini",
@@ -54,6 +59,22 @@ _PROVIDER_DEFAULT_MODELS = {
 }
 
 
+def _check_local_runtime() -> tuple[bool, str | None]:
+    """Return whether local embedded Hindsight imports cleanly.
+
+    On older CPUs, importing the local Hindsight stack can raise a runtime
+    error from NumPy before the daemon starts. Treat that as "unavailable"
+    so Hermes can degrade gracefully instead of repeatedly trying to start
+    a broken local memory backend.
+    """
+    try:
+        importlib.import_module("hindsight")
+        importlib.import_module("hindsight_embed.daemon_embed_manager")
+        return True, None
+    except Exception as exc:
+        return False, str(exc)
+
+
 # ---------------------------------------------------------------------------
 # Dedicated event loop for Hindsight async calls (one per process, reused).
 # Avoids creating ephemeral loops that leak aiohttp sessions.
@@ -81,13 +102,18 @@ def _get_loop() -> asyncio.AbstractEventLoop:
         return _loop
 
 
-def _run_sync(coro, timeout: float = 120.0):
+def _run_sync(coro, timeout: float = _DEFAULT_TIMEOUT):
     """Schedule *coro* on the shared loop and block until done."""
     loop = _get_loop()
     future = asyncio.run_coroutine_threadsafe(coro, loop)
     return future.result(timeout=timeout)
 
 
+# ---------------------------------------------------------------------------
+# Backward-compatible alias — instances use self._run_sync() instead.
+# ---------------------------------------------------------------------------
+
+
 # ---------------------------------------------------------------------------
 # Tool schemas
 # ---------------------------------------------------------------------------
@@ -233,6 +259,126 @@ def _utc_timestamp() -> str:
     return datetime.now(timezone.utc).isoformat(timespec="milliseconds").replace("+00:00", "Z")
 
 
+def _embedded_profile_name(config: dict[str, Any]) -> str:
+    """Return the Hindsight embedded profile name for this Hermes config."""
+    profile = config.get("profile", "hermes")
+    return str(profile or "hermes")
+
+
+def _load_simple_env(path) -> dict[str, str]:
+    """Parse a simple KEY=VALUE env file, ignoring comments and blank lines."""
+    if not path.exists():
+        return {}
+
+    values: dict[str, str] = {}
+    for line in path.read_text(encoding="utf-8").splitlines():
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, value = line.split("=", 1)
+        values[key.strip()] = value.strip()
+    return values
+
+
+def _build_embedded_profile_env(config: dict[str, Any], *, llm_api_key: str | None = None) -> dict[str, str]:
+    """Build the profile-scoped env file that standalone hindsight-embed consumes."""
+    current_key = llm_api_key
+    if current_key is None:
+        current_key = (
+            config.get("llmApiKey")
+            or config.get("llm_api_key")
+            or os.environ.get("HINDSIGHT_LLM_API_KEY", "")
+        )
+
+    current_provider = config.get("llm_provider", "")
+    current_model = config.get("llm_model", "")
+    current_base_url = config.get("llm_base_url") or os.environ.get("HINDSIGHT_API_LLM_BASE_URL", "")
+
+    # The embedded daemon expects OpenAI wire format for these providers.
+    daemon_provider = "openai" if current_provider in ("openai_compatible", "openrouter") else current_provider
+
+    env_values = {
+        "HINDSIGHT_API_LLM_PROVIDER": str(daemon_provider),
+        "HINDSIGHT_API_LLM_API_KEY": str(current_key or ""),
+        "HINDSIGHT_API_LLM_MODEL": str(current_model),
+        "HINDSIGHT_API_LOG_LEVEL": "info",
+    }
+    if current_base_url:
+        env_values["HINDSIGHT_API_LLM_BASE_URL"] = str(current_base_url)
+    return env_values
+
+
+def _embedded_profile_env_path(config: dict[str, Any]):
+    from pathlib import Path
+
+    return Path.home() / ".hindsight" / "profiles" / f"{_embedded_profile_name(config)}.env"
+
+
+def _materialize_embedded_profile_env(config: dict[str, Any], *, llm_api_key: str | None = None):
+    """Write the profile-scoped env file that standalone hindsight-embed uses."""
+    profile_env = _embedded_profile_env_path(config)
+    profile_env.parent.mkdir(parents=True, exist_ok=True)
+    env_values = _build_embedded_profile_env(config, llm_api_key=llm_api_key)
+    profile_env.write_text(
+        "".join(f"{key}={value}\n" for key, value in env_values.items()),
+        encoding="utf-8",
+    )
+    return profile_env
+
+def _sanitize_bank_segment(value: str) -> str:
+    """Sanitize a bank_id_template placeholder value.
+
+    Bank IDs should be safe for URL paths and filesystem use. Replaces any
+    character that isn't alphanumeric, dash, or underscore with a dash, and
+    collapses runs of dashes.
+    """
+    if not value:
+        return ""
+    out = []
+    prev_dash = False
+    for ch in str(value):
+        if ch.isalnum() or ch == "-" or ch == "_":
+            out.append(ch)
+            prev_dash = False
+        else:
+            if not prev_dash:
+                out.append("-")
+                prev_dash = True
+    return "".join(out).strip("-_")
+
+
+def _resolve_bank_id_template(template: str, fallback: str, **placeholders: str) -> str:
+    """Resolve a bank_id template string with the given placeholders.
+
+    Supported placeholders (each is sanitized before substitution):
+      {profile}   — active Hermes profile name (from agent_identity)
+      {workspace} — Hermes workspace name (from agent_workspace)
+      {platform}  — "cli", "telegram", "discord", etc.
+      {user}      — platform user id (gateway sessions)
+      {session}   — current session id
+
+    Missing/empty placeholders are rendered as the empty string and then
+    collapsed — e.g. ``hermes-{user}`` with no user becomes ``hermes``.
+
+    If the template is empty, resolution falls back to *fallback*.
+    Returns the sanitized bank id.
+    """
+    if not template:
+        return fallback
+    sanitized = {k: _sanitize_bank_segment(v) for k, v in placeholders.items()}
+    try:
+        rendered = template.format(**sanitized)
+    except (KeyError, IndexError) as exc:
+        logger.warning("Invalid bank_id_template %r: %s — using fallback %r",
+                       template, exc, fallback)
+        return fallback
+    while "--" in rendered:
+        rendered = rendered.replace("--", "-")
+    while "__" in rendered:
+        rendered = rendered.replace("__", "_")
+    rendered = rendered.strip("-_")
+    return rendered or fallback
+
+
 # ---------------------------------------------------------------------------
 # MemoryProvider implementation
 # ---------------------------------------------------------------------------
@@ -262,13 +408,17 @@ class HindsightMemoryProvider(MemoryProvider):
         self._chat_type = ""
         self._thread_id = ""
         self._agent_identity = ""
+        self._agent_workspace = ""
         self._turn_index = 0
         self._client = None
+        self._timeout = _DEFAULT_TIMEOUT
         self._prefetch_result = ""
         self._prefetch_lock = threading.Lock()
         self._prefetch_thread = None
         self._sync_thread = None
         self._session_id = ""
+        self._parent_session_id = ""
+        self._document_id = ""
 
         # Tags
         self._tags: list[str] | None = None
@@ -293,6 +443,7 @@ class HindsightMemoryProvider(MemoryProvider):
         # Bank
         self._bank_mission = ""
         self._bank_retain_mission: str | None = None
+        self._bank_id_template = ""
 
     @property
     def name(self) -> str:
@@ -302,9 +453,16 @@ class HindsightMemoryProvider(MemoryProvider):
         try:
             cfg = _load_config()
             mode = cfg.get("mode", "cloud")
-            if mode in ("local", "local_embedded", "local_external"):
+            if mode in ("local", "local_embedded"):
+                available, _ = _check_local_runtime()
+                return available
+            if mode == "local_external":
                 return True
-            has_key = bool(cfg.get("apiKey") or os.environ.get("HINDSIGHT_API_KEY", ""))
+            has_key = bool(
+                cfg.get("apiKey")
+                or cfg.get("api_key")
+                or os.environ.get("HINDSIGHT_API_KEY", "")
+            )
             has_url = bool(cfg.get("api_url") or os.environ.get("HINDSIGHT_API_URL", ""))
             return has_key or has_url
         except Exception:
@@ -363,7 +521,7 @@ class HindsightMemoryProvider(MemoryProvider):
         else:
             deps_to_install = [cloud_dep]
 
-        print(f"\n  Checking dependencies...")
+        print("\n  Checking dependencies...")
         uv_path = shutil.which("uv")
         if not uv_path:
             print("  ⚠ uv not found — install it: curl -LsSf https://astral.sh/uv/install.sh | sh")
@@ -374,14 +532,14 @@ class HindsightMemoryProvider(MemoryProvider):
                     [uv_path, "pip", "install", "--python", sys.executable, "--quiet", "--upgrade"] + deps_to_install,
                     check=True, timeout=120, capture_output=True,
                 )
-                print(f"  ✓ Dependencies up to date")
+                print("  ✓ Dependencies up to date")
             except Exception as e:
                 print(f"  ⚠ Install failed: {e}")
                 print(f"  Run manually: uv pip install --python {sys.executable} {' '.join(deps_to_install)}")
 
         # Step 3: Mode-specific config
         if mode == "cloud":
-            print(f"\n  Get your API key at https://ui.hindsight.vectorize.io\n")
+            print("\n  Get your API key at https://ui.hindsight.vectorize.io\n")
             existing_key = os.environ.get("HINDSIGHT_API_KEY", "")
             if existing_key:
                 masked = f"...{existing_key[-4:]}" if len(existing_key) > 4 else "set"
@@ -434,13 +592,19 @@ class HindsightMemoryProvider(MemoryProvider):
             sys.stdout.write("  LLM API key: ")
             sys.stdout.flush()
             llm_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
-            if llm_key:
-                env_writes["HINDSIGHT_LLM_API_KEY"] = llm_key
+            # Always write explicitly (including empty) so the provider sees ""
+            # rather than a missing variable.  The daemon reads from .env at
+            # startup and fails when HINDSIGHT_LLM_API_KEY is unset.
+            env_writes["HINDSIGHT_LLM_API_KEY"] = llm_key
 
         # Step 4: Save everything
         provider_config["bank_id"] = "hermes"
         provider_config["recall_budget"] = "mid"
-        bank_id = "hermes"
+        # Read existing timeout from config if present, otherwise use default
+        existing_timeout = self._config.get("timeout") if self._config else None
+        timeout_val = existing_timeout if existing_timeout else _DEFAULT_TIMEOUT
+        provider_config["timeout"] = timeout_val
+        env_writes["HINDSIGHT_TIMEOUT"] = str(timeout_val)
         config["memory"]["provider"] = "hindsight"
         save_config(config)
 
@@ -466,10 +630,32 @@ class HindsightMemoryProvider(MemoryProvider):
                     new_lines.append(f"{k}={v}")
             env_path.write_text("\n".join(new_lines) + "\n")
 
+        if mode == "local_embedded":
+            materialized_config = dict(provider_config)
+            config_path = Path(hermes_home) / "hindsight" / "config.json"
+            try:
+                materialized_config = json.loads(config_path.read_text(encoding="utf-8"))
+            except Exception:
+                pass
+
+            llm_api_key = env_writes.get("HINDSIGHT_LLM_API_KEY", "")
+            if not llm_api_key:
+                llm_api_key = _load_simple_env(Path(hermes_home) / ".env").get("HINDSIGHT_LLM_API_KEY", "")
+            if not llm_api_key:
+                llm_api_key = _load_simple_env(_embedded_profile_env_path(materialized_config)).get(
+                    "HINDSIGHT_API_LLM_API_KEY",
+                    "",
+                )
+
+            _materialize_embedded_profile_env(
+                materialized_config,
+                llm_api_key=llm_api_key or None,
+            )
+
         print(f"\n  ✓ Hindsight memory configured ({mode} mode)")
         if env_writes:
-            print(f"  API keys saved to .env")
-        print(f"\n  Start a new session to activate.\n")
+            print("  API keys saved to .env")
+        print("\n  Start a new session to activate.\n")
 
     def get_config_schema(self):
         return [
@@ -485,7 +671,8 @@ class HindsightMemoryProvider(MemoryProvider):
             {"key": "llm_base_url", "description": "Endpoint URL (e.g. http://192.168.1.10:8080/v1)", "default": "", "when": {"mode": "local_embedded", "llm_provider": "openai_compatible"}},
             {"key": "llm_api_key", "description": "LLM API key (optional for openai_compatible)", "secret": True, "env_var": "HINDSIGHT_LLM_API_KEY", "when": {"mode": "local_embedded"}},
             {"key": "llm_model", "description": "LLM model", "default": "gpt-4o-mini", "default_from": {"field": "llm_provider", "map": _PROVIDER_DEFAULT_MODELS}, "when": {"mode": "local_embedded"}},
-            {"key": "bank_id", "description": "Memory bank name", "default": "hermes"},
+            {"key": "bank_id", "description": "Memory bank name (static fallback when bank_id_template is unset)", "default": "hermes"},
+            {"key": "bank_id_template", "description": "Optional template to derive bank_id dynamically. Placeholders: {profile}, {workspace}, {platform}, {user}, {session}. Example: hermes-{profile}", "default": ""},
             {"key": "bank_mission", "description": "Mission/purpose description for the memory bank"},
             {"key": "bank_retain_mission", "description": "Custom extraction prompt for memory retention"},
             {"key": "recall_budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
@@ -505,12 +692,19 @@ class HindsightMemoryProvider(MemoryProvider):
             {"key": "recall_max_tokens", "description": "Maximum tokens for recall results", "default": 4096},
             {"key": "recall_max_input_chars", "description": "Maximum input query length for auto-recall", "default": 800},
             {"key": "recall_prompt_preamble", "description": "Custom preamble for recalled memories in context"},
+            {"key": "timeout", "description": "API request timeout in seconds", "default": _DEFAULT_TIMEOUT},
         ]
 
     def _get_client(self):
         """Return the cached Hindsight client (created once, reused)."""
         if self._client is None:
             if self._mode == "local_embedded":
+                available, reason = _check_local_runtime()
+                if not available:
+                    raise RuntimeError(
+                        "Hindsight local runtime is unavailable"
+                        + (f": {reason}" if reason else "")
+                    )
                 from hindsight import HindsightEmbedded
                 HindsightEmbedded.__del__ = lambda self: None
                 llm_provider = self._config.get("llm_provider", "")
@@ -529,16 +723,30 @@ class HindsightMemoryProvider(MemoryProvider):
                 self._client = HindsightEmbedded(**kwargs)
             else:
                 from hindsight_client import Hindsight
-                kwargs = {"base_url": self._api_url, "timeout": 30.0}
+                timeout = self._timeout or _DEFAULT_TIMEOUT
+                kwargs = {"base_url": self._api_url, "timeout": float(timeout)}
                 if self._api_key:
                     kwargs["api_key"] = self._api_key
-                logger.debug("Creating Hindsight cloud client (url=%s, has_key=%s)",
-                             self._api_url, bool(self._api_key))
+                logger.debug("Creating Hindsight cloud client (url=%s, has_key=%s, timeout=%s)",
+                             self._api_url, bool(self._api_key), kwargs["timeout"])
                 self._client = Hindsight(**kwargs)
         return self._client
 
+    def _run_sync(self, coro):
+        """Schedule *coro* on the shared loop using the configured timeout."""
+        return _run_sync(coro, timeout=self._timeout)
+
     def initialize(self, session_id: str, **kwargs) -> None:
         self._session_id = str(session_id or "").strip()
+        self._parent_session_id = str(kwargs.get("parent_session_id", "") or "").strip()
+
+        # Each process lifecycle gets its own document_id. Reusing session_id
+        # alone caused overwrites on /resume — the reloaded session starts
+        # with an empty _session_turns, so the next retain would replace the
+        # previously stored content. session_id stays in tags so processes
+        # for the same session remain filterable together.
+        start_ts = datetime.now().strftime("%Y%m%d_%H%M%S_%f")
+        self._document_id = f"{self._session_id}-{start_ts}"
 
         # Check client version and auto-upgrade if needed
         try:
@@ -548,7 +756,9 @@ class HindsightMemoryProvider(MemoryProvider):
             if Version(installed) < Version(_MIN_CLIENT_VERSION):
                 logger.warning("hindsight-client %s is outdated (need >=%s), attempting upgrade...",
                                installed, _MIN_CLIENT_VERSION)
-                import shutil, subprocess, sys
+                import shutil
+                import subprocess
+                import sys
                 uv_path = shutil.which("uv")
                 if uv_path:
                     try:
@@ -575,19 +785,41 @@ class HindsightMemoryProvider(MemoryProvider):
         self._chat_type = str(kwargs.get("chat_type") or "").strip()
         self._thread_id = str(kwargs.get("thread_id") or "").strip()
         self._agent_identity = str(kwargs.get("agent_identity") or "").strip()
+        self._agent_workspace = str(kwargs.get("agent_workspace") or "").strip()
         self._turn_index = 0
         self._session_turns = []
         self._mode = self._config.get("mode", "cloud")
+        # Read timeout from config or env var, fall back to default
+        self._timeout = self._config.get("timeout") or int(os.environ.get("HINDSIGHT_TIMEOUT", str(_DEFAULT_TIMEOUT)))
         # "local" is a legacy alias for "local_embedded"
         if self._mode == "local":
             self._mode = "local_embedded"
+        if self._mode == "local_embedded":
+            available, reason = _check_local_runtime()
+            if not available:
+                logger.warning(
+                    "Hindsight local mode disabled because its runtime could not be imported: %s",
+                    reason,
+                )
+                self._mode = "disabled"
+                return
         self._api_key = self._config.get("apiKey") or self._config.get("api_key") or os.environ.get("HINDSIGHT_API_KEY", "")
         default_url = _DEFAULT_LOCAL_URL if self._mode in ("local_embedded", "local_external") else _DEFAULT_API_URL
         self._api_url = self._config.get("api_url") or os.environ.get("HINDSIGHT_API_URL", default_url)
         self._llm_base_url = self._config.get("llm_base_url", "")
 
         banks = self._config.get("banks", {}).get("hermes", {})
-        self._bank_id = self._config.get("bank_id") or banks.get("bankId", "hermes")
+        static_bank_id = self._config.get("bank_id") or banks.get("bankId", "hermes")
+        self._bank_id_template = self._config.get("bank_id_template", "") or ""
+        self._bank_id = _resolve_bank_id_template(
+            self._bank_id_template,
+            fallback=static_bank_id,
+            profile=self._agent_identity,
+            workspace=self._agent_workspace,
+            platform=self._platform,
+            user=self._user_id,
+            session=self._session_id,
+        )
         budget = self._config.get("recall_budget") or self._config.get("budget") or banks.get("budget", "mid")
         self._budget = budget if budget in _VALID_BUDGETS else "mid"
 
@@ -640,6 +872,10 @@ class HindsightMemoryProvider(MemoryProvider):
             pass
         logger.info("Hindsight initialized: mode=%s, api_url=%s, bank=%s, budget=%s, memory_mode=%s, prefetch_method=%s, client=%s",
                      self._mode, self._api_url, self._bank_id, self._budget, self._memory_mode, self._prefetch_method, _client_version)
+        if self._bank_id_template:
+            logger.debug("Hindsight bank resolved from template %r: profile=%s workspace=%s platform=%s user=%s -> bank=%s",
+                         self._bank_id_template, self._agent_identity, self._agent_workspace,
+                         self._platform, self._user_id, self._bank_id)
         logger.debug("Hindsight config: auto_retain=%s, auto_recall=%s, retain_every_n=%d, "
                      "retain_async=%s, retain_context=%s, recall_max_tokens=%d, recall_max_input_chars=%d, tags=%s, recall_tags=%s",
                      self._auto_retain, self._auto_recall, self._retain_every_n_turns,
@@ -669,42 +905,13 @@ class HindsightMemoryProvider(MemoryProvider):
                     # Update the profile .env to match our current config so
                     # the daemon always starts with the right settings.
                     # If the config changed and the daemon is running, stop it.
-                    from pathlib import Path as _Path
-                    profile_env = _Path.home() / ".hindsight" / "profiles" / f"{profile}.env"
-                    current_key = self._config.get("llm_api_key") or os.environ.get("HINDSIGHT_LLM_API_KEY", "")
-                    current_provider = self._config.get("llm_provider", "")
-                    current_model = self._config.get("llm_model", "")
-                    current_base_url = self._config.get("llm_base_url") or os.environ.get("HINDSIGHT_API_LLM_BASE_URL", "")
-                    # Map openai_compatible/openrouter → openai for the daemon (OpenAI wire format)
-                    daemon_provider = "openai" if current_provider in ("openai_compatible", "openrouter") else current_provider
-
-                    # Read saved profile config
-                    saved = {}
-                    if profile_env.exists():
-                        for line in profile_env.read_text().splitlines():
-                            if "=" in line and not line.startswith("#"):
-                                k, v = line.split("=", 1)
-                                saved[k.strip()] = v.strip()
-
-                    config_changed = (
-                        saved.get("HINDSIGHT_API_LLM_PROVIDER") != daemon_provider or
-                        saved.get("HINDSIGHT_API_LLM_MODEL") != current_model or
-                        saved.get("HINDSIGHT_API_LLM_API_KEY") != current_key or
-                        saved.get("HINDSIGHT_API_LLM_BASE_URL", "") != current_base_url
-                    )
+                    profile_env = _embedded_profile_env_path(self._config)
+                    expected_env = _build_embedded_profile_env(self._config)
+                    saved = _load_simple_env(profile_env)
+                    config_changed = saved != expected_env
 
                     if config_changed:
-                        # Write updated profile .env
-                        profile_env.parent.mkdir(parents=True, exist_ok=True)
-                        env_lines = (
-                            f"HINDSIGHT_API_LLM_PROVIDER={daemon_provider}\n"
-                            f"HINDSIGHT_API_LLM_API_KEY={current_key}\n"
-                            f"HINDSIGHT_API_LLM_MODEL={current_model}\n"
-                            f"HINDSIGHT_API_LOG_LEVEL=info\n"
-                        )
-                        if current_base_url:
-                            env_lines += f"HINDSIGHT_API_LLM_BASE_URL={current_base_url}\n"
-                        profile_env.write_text(env_lines)
+                        profile_env = _materialize_embedded_profile_env(self._config)
                         if client._manager.is_running(profile):
                             with open(log_path, "a") as f:
                                 f.write("\n=== Config changed, restarting daemon ===\n")
@@ -777,7 +984,7 @@ class HindsightMemoryProvider(MemoryProvider):
                 client = self._get_client()
                 if self._prefetch_method == "reflect":
                     logger.debug("Prefetch: calling reflect (bank=%s, query_len=%d)", self._bank_id, len(query))
-                    resp = _run_sync(client.areflect(bank_id=self._bank_id, query=query, budget=self._budget))
+                    resp = self._run_sync(client.areflect(bank_id=self._bank_id, query=query, budget=self._budget))
                     text = resp.text or ""
                 else:
                     recall_kwargs: dict = {
@@ -791,7 +998,7 @@ class HindsightMemoryProvider(MemoryProvider):
                         recall_kwargs["types"] = self._recall_types
                     logger.debug("Prefetch: calling recall (bank=%s, query_len=%d, budget=%s)",
                                  self._bank_id, len(query), self._budget)
-                    resp = _run_sync(client.arecall(**recall_kwargs))
+                    resp = self._run_sync(client.arecall(**recall_kwargs))
                     num_results = len(resp.results) if resp.results else 0
                     logger.debug("Prefetch: recall returned %d results", num_results)
                     text = "\n".join(f"- {r.text}" for r in resp.results if r.text) if resp.results else ""
@@ -888,7 +1095,7 @@ class HindsightMemoryProvider(MemoryProvider):
         if session_id:
             self._session_id = str(session_id).strip()
 
-        turn = json.dumps(self._build_turn_messages(user_content, assistant_content))
+        turn = json.dumps(self._build_turn_messages(user_content, assistant_content), ensure_ascii=False)
         self._session_turns.append(turn)
         self._turn_counter += 1
         self._turn_index = self._turn_counter
@@ -902,6 +1109,12 @@ class HindsightMemoryProvider(MemoryProvider):
                      len(self._session_turns), sum(len(t) for t in self._session_turns))
         content = "[" + ",".join(self._session_turns) + "]"
 
+        lineage_tags: list[str] = []
+        if self._session_id:
+            lineage_tags.append(f"session:{self._session_id}")
+        if self._parent_session_id:
+            lineage_tags.append(f"parent:{self._parent_session_id}")
+
         def _sync():
             try:
                 client = self._get_client()
@@ -912,15 +1125,16 @@ class HindsightMemoryProvider(MemoryProvider):
                         message_count=len(self._session_turns) * 2,
                         turn_index=self._turn_index,
                     ),
+                    tags=lineage_tags or None,
                 )
                 item.pop("bank_id", None)
                 item.pop("retain_async", None)
                 logger.debug("Hindsight retain: bank=%s, doc=%s, async=%s, content_len=%d, num_turns=%d",
-                             self._bank_id, self._session_id, self._retain_async, len(content), len(self._session_turns))
-                _run_sync(client.aretain_batch(
+                             self._bank_id, self._document_id, self._retain_async, len(content), len(self._session_turns))
+                self._run_sync(client.aretain_batch(
                     bank_id=self._bank_id,
                     items=[item],
-                    document_id=self._session_id,
+                    document_id=self._document_id,
                     retain_async=self._retain_async,
                 ))
                 logger.debug("Hindsight retain succeeded")
@@ -957,7 +1171,7 @@ class HindsightMemoryProvider(MemoryProvider):
                 )
                 logger.debug("Tool hindsight_retain: bank=%s, content_len=%d, context=%s",
                              self._bank_id, len(content), context)
-                _run_sync(client.aretain(**retain_kwargs))
+                self._run_sync(client.aretain(**retain_kwargs))
                 logger.debug("Tool hindsight_retain: success")
                 return json.dumps({"result": "Memory stored successfully."})
             except Exception as e:
@@ -980,7 +1194,7 @@ class HindsightMemoryProvider(MemoryProvider):
                     recall_kwargs["types"] = self._recall_types
                 logger.debug("Tool hindsight_recall: bank=%s, query_len=%d, budget=%s",
                              self._bank_id, len(query), self._budget)
-                resp = _run_sync(client.arecall(**recall_kwargs))
+                resp = self._run_sync(client.arecall(**recall_kwargs))
                 num_results = len(resp.results) if resp.results else 0
                 logger.debug("Tool hindsight_recall: %d results", num_results)
                 if not resp.results:
@@ -998,7 +1212,7 @@ class HindsightMemoryProvider(MemoryProvider):
             try:
                 logger.debug("Tool hindsight_reflect: bank=%s, query_len=%d, budget=%s",
                              self._bank_id, len(query), self._budget)
-                resp = _run_sync(client.areflect(
+                resp = self._run_sync(client.areflect(
                     bank_id=self._bank_id, query=query, budget=self._budget
                 ))
                 logger.debug("Tool hindsight_reflect: response_len=%d", len(resp.text or ""))
@@ -1011,7 +1225,6 @@ class HindsightMemoryProvider(MemoryProvider):
 
     def shutdown(self) -> None:
         logger.debug("Hindsight shutdown: waiting for background threads")
-        global _loop, _loop_thread
         for t in (self._prefetch_thread, self._sync_thread):
             if t and t.is_alive():
                 t.join(timeout=5.0)
@@ -1026,17 +1239,21 @@ class HindsightMemoryProvider(MemoryProvider):
                     except RuntimeError:
                         pass
                 else:
-                    _run_sync(self._client.aclose())
+                    self._run_sync(self._client.aclose())
             except Exception:
                 pass
             self._client = None
-        # Stop the background event loop so no tasks are pending at exit
-        if _loop is not None and _loop.is_running():
-            _loop.call_soon_threadsafe(_loop.stop)
-            if _loop_thread is not None:
-                _loop_thread.join(timeout=5.0)
-            _loop = None
-            _loop_thread = None
+        # The module-global background event loop (_loop / _loop_thread)
+        # is intentionally NOT stopped here. It is shared across every
+        # HindsightMemoryProvider instance in the process — the plugin
+        # loader creates a new provider per AIAgent, and the gateway
+        # creates one AIAgent per concurrent chat session. Stopping the
+        # loop from one provider's shutdown() strands the aiohttp
+        # ClientSession + TCPConnector owned by every sibling provider
+        # on a dead loop, which surfaces as the "Unclosed client session"
+        # / "Unclosed connector" warnings reported in #11923. The loop
+        # runs on a daemon thread and is reclaimed on process exit;
+        # per-session cleanup happens via self._client.aclose() above.
 
 
 def register(ctx) -> None:

plugins/memory/openviking/__init__.py

@@ -43,7 +43,7 @@ _TIMEOUT = 30.0
 # ---------------------------------------------------------------------------
 # Process-level atexit safety net — ensures pending sessions are committed
 # even if shutdown_memory_provider is never called (e.g. gateway crash,
-# SIGKILL, or exception in _async_flush_memories preventing shutdown).
+# SIGKILL, or exception in the session expiry watcher preventing shutdown).
 # ---------------------------------------------------------------------------
 _last_active_provider: Optional["OpenVikingMemoryProvider"] = None
 

plugins/spotify/__init__.py

@@ -0,0 +1,66 @@
+"""Spotify integration plugin — bundled, auto-loaded.
+
+Registers 7 tools (playback, devices, queue, search, playlists, albums,
+library) into the ``spotify`` toolset. Each tool's handler is gated by
+``_check_spotify_available()`` — when the user has not run ``hermes auth
+spotify``, the tools remain registered (so they appear in ``hermes
+tools``) but the runtime check prevents dispatch.
+
+Why a plugin instead of a top-level ``tools/`` file?
+
+- ``plugins/`` is where third-party service integrations live (see
+  ``plugins/image_gen/`` for the backend-provider pattern, ``plugins/
+  disk-cleanup/`` for the standalone pattern). ``tools/`` is reserved
+  for foundational capabilities (terminal, read_file, web_search, etc.).
+- Mirroring the image_gen plugin layout (``plugins/<category>/<backend>/``
+  for categories, flat ``plugins/<name>/`` for standalones) makes new
+  service integrations a pattern contributors can copy.
+- Bundled + ``kind: backend`` auto-loads on startup just like image_gen
+  backends — no user opt-in needed, no ``plugins.enabled`` config.
+
+The Spotify auth flow (``hermes auth spotify``), CLI plumbing, and docs
+are unchanged. This move is purely structural.
+"""
+
+from __future__ import annotations
+
+from plugins.spotify.tools import (
+    SPOTIFY_ALBUMS_SCHEMA,
+    SPOTIFY_DEVICES_SCHEMA,
+    SPOTIFY_LIBRARY_SCHEMA,
+    SPOTIFY_PLAYBACK_SCHEMA,
+    SPOTIFY_PLAYLISTS_SCHEMA,
+    SPOTIFY_QUEUE_SCHEMA,
+    SPOTIFY_SEARCH_SCHEMA,
+    _check_spotify_available,
+    _handle_spotify_albums,
+    _handle_spotify_devices,
+    _handle_spotify_library,
+    _handle_spotify_playback,
+    _handle_spotify_playlists,
+    _handle_spotify_queue,
+    _handle_spotify_search,
+)
+
+_TOOLS = (
+    ("spotify_playback",  SPOTIFY_PLAYBACK_SCHEMA,  _handle_spotify_playback,  "🎵"),
+    ("spotify_devices",   SPOTIFY_DEVICES_SCHEMA,   _handle_spotify_devices,   "🔈"),
+    ("spotify_queue",     SPOTIFY_QUEUE_SCHEMA,     _handle_spotify_queue,     "📻"),
+    ("spotify_search",    SPOTIFY_SEARCH_SCHEMA,    _handle_spotify_search,    "🔎"),
+    ("spotify_playlists", SPOTIFY_PLAYLISTS_SCHEMA, _handle_spotify_playlists, "📚"),
+    ("spotify_albums",    SPOTIFY_ALBUMS_SCHEMA,    _handle_spotify_albums,    "💿"),
+    ("spotify_library",   SPOTIFY_LIBRARY_SCHEMA,   _handle_spotify_library,   "❤️"),
+)
+
+
+def register(ctx) -> None:
+    """Register all Spotify tools. Called once by the plugin loader."""
+    for name, schema, handler, emoji in _TOOLS:
+        ctx.register_tool(
+            name=name,
+            toolset="spotify",
+            schema=schema,
+            handler=handler,
+            check_fn=_check_spotify_available,
+            emoji=emoji,
+        )

plugins/spotify/client.py

@@ -0,0 +1,435 @@
+"""Thin Spotify Web API helper used by Hermes native tools."""
+
+from __future__ import annotations
+
+import json
+from typing import Any, Dict, Iterable, Optional
+from urllib.parse import urlparse
+
+import httpx
+
+from hermes_cli.auth import (
+    AuthError,
+    resolve_spotify_runtime_credentials,
+)
+
+
+class SpotifyError(RuntimeError):
+    """Base Spotify tool error."""
+
+
+class SpotifyAuthRequiredError(SpotifyError):
+    """Raised when the user needs to authenticate with Spotify first."""
+
+
+class SpotifyAPIError(SpotifyError):
+    """Structured Spotify API failure."""
+
+    def __init__(
+        self,
+        message: str,
+        *,
+        status_code: Optional[int] = None,
+        response_body: Optional[str] = None,
+    ) -> None:
+        super().__init__(message)
+        self.status_code = status_code
+        self.response_body = response_body
+        self.path = None
+
+
+class SpotifyClient:
+    def __init__(self) -> None:
+        self._runtime = self._resolve_runtime(refresh_if_expiring=True)
+
+    def _resolve_runtime(self, *, force_refresh: bool = False, refresh_if_expiring: bool = True) -> Dict[str, Any]:
+        try:
+            return resolve_spotify_runtime_credentials(
+                force_refresh=force_refresh,
+                refresh_if_expiring=refresh_if_expiring,
+            )
+        except AuthError as exc:
+            raise SpotifyAuthRequiredError(str(exc)) from exc
+
+    @property
+    def base_url(self) -> str:
+        return str(self._runtime.get("base_url") or "").rstrip("/")
+
+    def _headers(self) -> Dict[str, str]:
+        return {
+            "Authorization": f"Bearer {self._runtime['access_token']}",
+            "Content-Type": "application/json",
+        }
+
+    def request(
+        self,
+        method: str,
+        path: str,
+        *,
+        params: Optional[Dict[str, Any]] = None,
+        json_body: Optional[Dict[str, Any]] = None,
+        allow_retry_on_401: bool = True,
+        empty_response: Optional[Dict[str, Any]] = None,
+    ) -> Any:
+        url = f"{self.base_url}{path}"
+        response = httpx.request(
+            method,
+            url,
+            headers=self._headers(),
+            params=_strip_none(params),
+            json=_strip_none(json_body) if json_body is not None else None,
+            timeout=30.0,
+        )
+        if response.status_code == 401 and allow_retry_on_401:
+            self._runtime = self._resolve_runtime(force_refresh=True, refresh_if_expiring=True)
+            return self.request(
+                method,
+                path,
+                params=params,
+                json_body=json_body,
+                allow_retry_on_401=False,
+            )
+        if response.status_code >= 400:
+            self._raise_api_error(response, method=method, path=path)
+        if response.status_code == 204 or not response.content:
+            return empty_response or {"success": True, "status_code": response.status_code, "empty": True}
+        if "application/json" in response.headers.get("content-type", ""):
+            return response.json()
+        return {"success": True, "text": response.text}
+
+    def _raise_api_error(self, response: httpx.Response, *, method: str, path: str) -> None:
+        detail = response.text.strip()
+        message = _friendly_spotify_error_message(
+            status_code=response.status_code,
+            detail=_extract_spotify_error_detail(response, fallback=detail),
+            method=method,
+            path=path,
+            retry_after=response.headers.get("Retry-After"),
+        )
+        error = SpotifyAPIError(message, status_code=response.status_code, response_body=detail)
+        error.path = path
+        raise error
+
+    def get_devices(self) -> Any:
+        return self.request("GET", "/me/player/devices")
+
+    def transfer_playback(self, *, device_id: str, play: bool = False) -> Any:
+        return self.request("PUT", "/me/player", json_body={
+            "device_ids": [device_id],
+            "play": play,
+        })
+
+    def get_playback_state(self, *, market: Optional[str] = None) -> Any:
+        return self.request(
+            "GET",
+            "/me/player",
+            params={"market": market},
+            empty_response={
+                "status_code": 204,
+                "empty": True,
+                "message": "No active Spotify playback session was found. Open Spotify on a device and start playback, or transfer playback to an available device.",
+            },
+        )
+
+    def get_currently_playing(self, *, market: Optional[str] = None) -> Any:
+        return self.request(
+            "GET",
+            "/me/player/currently-playing",
+            params={"market": market},
+            empty_response={
+                "status_code": 204,
+                "empty": True,
+                "message": "Spotify is not currently playing anything. Start playback in Spotify and try again.",
+            },
+        )
+
+    def start_playback(
+        self,
+        *,
+        device_id: Optional[str] = None,
+        context_uri: Optional[str] = None,
+        uris: Optional[list[str]] = None,
+        offset: Optional[Dict[str, Any]] = None,
+        position_ms: Optional[int] = None,
+    ) -> Any:
+        return self.request(
+            "PUT",
+            "/me/player/play",
+            params={"device_id": device_id},
+            json_body={
+                "context_uri": context_uri,
+                "uris": uris,
+                "offset": offset,
+                "position_ms": position_ms,
+            },
+        )
+
+    def pause_playback(self, *, device_id: Optional[str] = None) -> Any:
+        return self.request("PUT", "/me/player/pause", params={"device_id": device_id})
+
+    def skip_next(self, *, device_id: Optional[str] = None) -> Any:
+        return self.request("POST", "/me/player/next", params={"device_id": device_id})
+
+    def skip_previous(self, *, device_id: Optional[str] = None) -> Any:
+        return self.request("POST", "/me/player/previous", params={"device_id": device_id})
+
+    def seek(self, *, position_ms: int, device_id: Optional[str] = None) -> Any:
+        return self.request("PUT", "/me/player/seek", params={
+            "position_ms": position_ms,
+            "device_id": device_id,
+        })
+
+    def set_repeat(self, *, state: str, device_id: Optional[str] = None) -> Any:
+        return self.request("PUT", "/me/player/repeat", params={"state": state, "device_id": device_id})
+
+    def set_shuffle(self, *, state: bool, device_id: Optional[str] = None) -> Any:
+        return self.request("PUT", "/me/player/shuffle", params={"state": str(bool(state)).lower(), "device_id": device_id})
+
+    def set_volume(self, *, volume_percent: int, device_id: Optional[str] = None) -> Any:
+        return self.request("PUT", "/me/player/volume", params={
+            "volume_percent": volume_percent,
+            "device_id": device_id,
+        })
+
+    def get_queue(self) -> Any:
+        return self.request("GET", "/me/player/queue")
+
+    def add_to_queue(self, *, uri: str, device_id: Optional[str] = None) -> Any:
+        return self.request("POST", "/me/player/queue", params={"uri": uri, "device_id": device_id})
+
+    def search(
+        self,
+        *,
+        query: str,
+        search_types: list[str],
+        limit: int = 10,
+        offset: int = 0,
+        market: Optional[str] = None,
+        include_external: Optional[str] = None,
+    ) -> Any:
+        return self.request("GET", "/search", params={
+            "q": query,
+            "type": ",".join(search_types),
+            "limit": limit,
+            "offset": offset,
+            "market": market,
+            "include_external": include_external,
+        })
+
+    def get_my_playlists(self, *, limit: int = 20, offset: int = 0) -> Any:
+        return self.request("GET", "/me/playlists", params={"limit": limit, "offset": offset})
+
+    def get_playlist(self, *, playlist_id: str, market: Optional[str] = None) -> Any:
+        return self.request("GET", f"/playlists/{playlist_id}", params={"market": market})
+
+    def create_playlist(
+        self,
+        *,
+        name: str,
+        public: bool = False,
+        collaborative: bool = False,
+        description: Optional[str] = None,
+    ) -> Any:
+        return self.request("POST", "/me/playlists", json_body={
+            "name": name,
+            "public": public,
+            "collaborative": collaborative,
+            "description": description,
+        })
+
+    def add_playlist_items(
+        self,
+        *,
+        playlist_id: str,
+        uris: list[str],
+        position: Optional[int] = None,
+    ) -> Any:
+        return self.request("POST", f"/playlists/{playlist_id}/items", json_body={
+            "uris": uris,
+            "position": position,
+        })
+
+    def remove_playlist_items(
+        self,
+        *,
+        playlist_id: str,
+        uris: list[str],
+        snapshot_id: Optional[str] = None,
+    ) -> Any:
+        return self.request("DELETE", f"/playlists/{playlist_id}/items", json_body={
+            "items": [{"uri": uri} for uri in uris],
+            "snapshot_id": snapshot_id,
+        })
+
+    def update_playlist_details(
+        self,
+        *,
+        playlist_id: str,
+        name: Optional[str] = None,
+        public: Optional[bool] = None,
+        collaborative: Optional[bool] = None,
+        description: Optional[str] = None,
+    ) -> Any:
+        return self.request("PUT", f"/playlists/{playlist_id}", json_body={
+            "name": name,
+            "public": public,
+            "collaborative": collaborative,
+            "description": description,
+        })
+
+    def get_album(self, *, album_id: str, market: Optional[str] = None) -> Any:
+        return self.request("GET", f"/albums/{album_id}", params={"market": market})
+
+    def get_album_tracks(self, *, album_id: str, limit: int = 20, offset: int = 0, market: Optional[str] = None) -> Any:
+        return self.request("GET", f"/albums/{album_id}/tracks", params={
+            "limit": limit,
+            "offset": offset,
+            "market": market,
+        })
+
+    def get_saved_tracks(self, *, limit: int = 20, offset: int = 0, market: Optional[str] = None) -> Any:
+        return self.request("GET", "/me/tracks", params={"limit": limit, "offset": offset, "market": market})
+
+    def save_library_items(self, *, uris: list[str]) -> Any:
+        return self.request("PUT", "/me/library", params={"uris": ",".join(uris)})
+
+    def library_contains(self, *, uris: list[str]) -> Any:
+        return self.request("GET", "/me/library/contains", params={"uris": ",".join(uris)})
+
+    def get_saved_albums(self, *, limit: int = 20, offset: int = 0, market: Optional[str] = None) -> Any:
+        return self.request("GET", "/me/albums", params={"limit": limit, "offset": offset, "market": market})
+
+    def remove_saved_tracks(self, *, track_ids: list[str]) -> Any:
+        uris = [f"spotify:track:{track_id}" for track_id in track_ids]
+        return self.request("DELETE", "/me/library", params={"uris": ",".join(uris)})
+
+    def remove_saved_albums(self, *, album_ids: list[str]) -> Any:
+        uris = [f"spotify:album:{album_id}" for album_id in album_ids]
+        return self.request("DELETE", "/me/library", params={"uris": ",".join(uris)})
+
+    def get_recently_played(
+        self,
+        *,
+        limit: int = 20,
+        after: Optional[int] = None,
+        before: Optional[int] = None,
+    ) -> Any:
+        return self.request("GET", "/me/player/recently-played", params={
+            "limit": limit,
+            "after": after,
+            "before": before,
+        })
+
+
+def _extract_spotify_error_detail(response: httpx.Response, *, fallback: str) -> str:
+    detail = fallback
+    try:
+        payload = response.json()
+        if isinstance(payload, dict):
+            error_obj = payload.get("error")
+            if isinstance(error_obj, dict):
+                detail = str(error_obj.get("message") or detail)
+            elif isinstance(error_obj, str):
+                detail = error_obj
+    except Exception:
+        pass
+    return detail.strip()
+
+
+def _friendly_spotify_error_message(
+    *,
+    status_code: int,
+    detail: str,
+    method: str,
+    path: str,
+    retry_after: Optional[str],
+) -> str:
+    normalized_detail = detail.lower()
+    is_playback_path = path.startswith("/me/player")
+
+    if status_code == 401:
+        return "Spotify authentication failed or expired. Run `hermes auth spotify` again."
+
+    if status_code == 403:
+        if is_playback_path:
+            return (
+                "Spotify rejected this playback request. Playback control usually requires a Spotify Premium account "
+                "and an active Spotify Connect device."
+            )
+        if "scope" in normalized_detail or "permission" in normalized_detail:
+            return "Spotify rejected the request because the current auth scope is insufficient. Re-run `hermes auth spotify` to refresh permissions."
+        return "Spotify rejected the request. The account may not have permission for this action."
+
+    if status_code == 404:
+        if is_playback_path:
+            return "Spotify could not find an active playback device or player session for this request."
+        return "Spotify resource not found."
+
+    if status_code == 429:
+        message = "Spotify rate limit exceeded."
+        if retry_after:
+            message += f" Retry after {retry_after} seconds."
+        return message
+
+    if detail:
+        return detail
+    return f"Spotify API request failed with status {status_code}."
+
+
+def _strip_none(payload: Optional[Dict[str, Any]]) -> Dict[str, Any]:
+    if not payload:
+        return {}
+    return {key: value for key, value in payload.items() if value is not None}
+
+
+def normalize_spotify_id(value: str, expected_type: Optional[str] = None) -> str:
+    cleaned = (value or "").strip()
+    if not cleaned:
+        raise SpotifyError("Spotify id/uri/url is required.")
+    if cleaned.startswith("spotify:"):
+        parts = cleaned.split(":")
+        if len(parts) >= 3:
+            item_type = parts[1]
+            if expected_type and item_type != expected_type:
+                raise SpotifyError(f"Expected a Spotify {expected_type}, got {item_type}.")
+            return parts[2]
+    if "open.spotify.com" in cleaned:
+        parsed = urlparse(cleaned)
+        path_parts = [part for part in parsed.path.split("/") if part]
+        if len(path_parts) >= 2:
+            item_type, item_id = path_parts[0], path_parts[1]
+            if expected_type and item_type != expected_type:
+                raise SpotifyError(f"Expected a Spotify {expected_type}, got {item_type}.")
+            return item_id
+    return cleaned
+
+
+def normalize_spotify_uri(value: str, expected_type: Optional[str] = None) -> str:
+    cleaned = (value or "").strip()
+    if not cleaned:
+        raise SpotifyError("Spotify URI/url/id is required.")
+    if cleaned.startswith("spotify:"):
+        if expected_type:
+            parts = cleaned.split(":")
+            if len(parts) >= 3 and parts[1] != expected_type:
+                raise SpotifyError(f"Expected a Spotify {expected_type}, got {parts[1]}.")
+        return cleaned
+    item_id = normalize_spotify_id(cleaned, expected_type)
+    if expected_type:
+        return f"spotify:{expected_type}:{item_id}"
+    return cleaned
+
+
+def normalize_spotify_uris(values: Iterable[str], expected_type: Optional[str] = None) -> list[str]:
+    uris: list[str] = []
+    for value in values:
+        uri = normalize_spotify_uri(str(value), expected_type)
+        if uri not in uris:
+            uris.append(uri)
+    if not uris:
+        raise SpotifyError("At least one Spotify item is required.")
+    return uris
+
+
+def compact_json(data: Any) -> str:
+    return json.dumps(data, ensure_ascii=False)

plugins/spotify/plugin.yaml

@@ -0,0 +1,13 @@
+name: spotify
+version: 1.0.0
+description: "Native Spotify integration — 7 tools (playback, devices, queue, search, playlists, albums, library) using Spotify Web API + PKCE OAuth. Auth via `hermes auth spotify`. Tools gate on `providers.spotify` in ~/.hermes/auth.json."
+author: NousResearch
+kind: backend
+provides_tools:
+  - spotify_playback
+  - spotify_devices
+  - spotify_queue
+  - spotify_search
+  - spotify_playlists
+  - spotify_albums
+  - spotify_library

plugins/spotify/tools.py

@@ -0,0 +1,454 @@
+"""Native Spotify tools for Hermes (registered via plugins/spotify)."""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List
+
+from hermes_cli.auth import get_auth_status
+from plugins.spotify.client import (
+    SpotifyAPIError,
+    SpotifyAuthRequiredError,
+    SpotifyClient,
+    SpotifyError,
+    normalize_spotify_id,
+    normalize_spotify_uri,
+    normalize_spotify_uris,
+)
+from tools.registry import tool_error, tool_result
+
+
+def _check_spotify_available() -> bool:
+    try:
+        return bool(get_auth_status("spotify").get("logged_in"))
+    except Exception:
+        return False
+
+
+def _spotify_client() -> SpotifyClient:
+    return SpotifyClient()
+
+
+def _spotify_tool_error(exc: Exception) -> str:
+    if isinstance(exc, (SpotifyError, SpotifyAuthRequiredError)):
+        return tool_error(str(exc))
+    if isinstance(exc, SpotifyAPIError):
+        return tool_error(str(exc), status_code=exc.status_code)
+    return tool_error(f"Spotify tool failed: {type(exc).__name__}: {exc}")
+
+
+def _coerce_limit(raw: Any, *, default: int = 20, minimum: int = 1, maximum: int = 50) -> int:
+    try:
+        value = int(raw)
+    except Exception:
+        value = default
+    return max(minimum, min(maximum, value))
+
+
+def _coerce_bool(raw: Any, default: bool = False) -> bool:
+    if isinstance(raw, bool):
+        return raw
+    if isinstance(raw, str):
+        cleaned = raw.strip().lower()
+        if cleaned in {"1", "true", "yes", "on"}:
+            return True
+        if cleaned in {"0", "false", "no", "off"}:
+            return False
+    return default
+
+
+def _as_list(raw: Any) -> List[str]:
+    if raw is None:
+        return []
+    if isinstance(raw, list):
+        return [str(item).strip() for item in raw if str(item).strip()]
+    return [str(raw).strip()] if str(raw).strip() else []
+
+
+def _describe_empty_playback(payload: Any, *, action: str) -> dict | None:
+    if not isinstance(payload, dict) or not payload.get("empty"):
+        return None
+    if action == "get_currently_playing":
+        return {
+            "success": True,
+            "action": action,
+            "is_playing": False,
+            "status_code": payload.get("status_code", 204),
+            "message": payload.get("message") or "Spotify is not currently playing anything.",
+        }
+    if action == "get_state":
+        return {
+            "success": True,
+            "action": action,
+            "has_active_device": False,
+            "status_code": payload.get("status_code", 204),
+            "message": payload.get("message") or "No active Spotify playback session was found.",
+        }
+    return None
+
+
+def _handle_spotify_playback(args: dict, **kw) -> str:
+    action = str(args.get("action") or "get_state").strip().lower()
+    client = _spotify_client()
+    try:
+        if action == "get_state":
+            payload = client.get_playback_state(market=args.get("market"))
+            empty_result = _describe_empty_playback(payload, action=action)
+            return tool_result(empty_result or payload)
+        if action == "get_currently_playing":
+            payload = client.get_currently_playing(market=args.get("market"))
+            empty_result = _describe_empty_playback(payload, action=action)
+            return tool_result(empty_result or payload)
+        if action == "play":
+            offset = args.get("offset")
+            if isinstance(offset, dict):
+                payload_offset = {k: v for k, v in offset.items() if v is not None}
+            else:
+                payload_offset = None
+            uris = normalize_spotify_uris(_as_list(args.get("uris")), "track") if args.get("uris") else None
+            context_uri = None
+            if args.get("context_uri"):
+                raw_context = str(args.get("context_uri"))
+                context_type = None
+                if raw_context.startswith("spotify:album:") or "/album/" in raw_context:
+                    context_type = "album"
+                elif raw_context.startswith("spotify:playlist:") or "/playlist/" in raw_context:
+                    context_type = "playlist"
+                elif raw_context.startswith("spotify:artist:") or "/artist/" in raw_context:
+                    context_type = "artist"
+                context_uri = normalize_spotify_uri(raw_context, context_type)
+            result = client.start_playback(
+                device_id=args.get("device_id"),
+                context_uri=context_uri,
+                uris=uris,
+                offset=payload_offset,
+                position_ms=args.get("position_ms"),
+            )
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "pause":
+            result = client.pause_playback(device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "next":
+            result = client.skip_next(device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "previous":
+            result = client.skip_previous(device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "seek":
+            if args.get("position_ms") is None:
+                return tool_error("position_ms is required for action='seek'")
+            result = client.seek(position_ms=int(args["position_ms"]), device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "set_repeat":
+            state = str(args.get("state") or "").strip().lower()
+            if state not in {"track", "context", "off"}:
+                return tool_error("state must be one of: track, context, off")
+            result = client.set_repeat(state=state, device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "set_shuffle":
+            result = client.set_shuffle(state=_coerce_bool(args.get("state")), device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "set_volume":
+            if args.get("volume_percent") is None:
+                return tool_error("volume_percent is required for action='set_volume'")
+            result = client.set_volume(volume_percent=max(0, min(100, int(args["volume_percent"]))), device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "result": result})
+        if action == "recently_played":
+            after = args.get("after")
+            before = args.get("before")
+            if after and before:
+                return tool_error("Provide only one of 'after' or 'before'")
+            return tool_result(client.get_recently_played(
+                limit=_coerce_limit(args.get("limit"), default=20),
+                after=int(after) if after is not None else None,
+                before=int(before) if before is not None else None,
+            ))
+        return tool_error(f"Unknown spotify_playback action: {action}")
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+def _handle_spotify_devices(args: dict, **kw) -> str:
+    action = str(args.get("action") or "list").strip().lower()
+    client = _spotify_client()
+    try:
+        if action == "list":
+            return tool_result(client.get_devices())
+        if action == "transfer":
+            device_id = str(args.get("device_id") or "").strip()
+            if not device_id:
+                return tool_error("device_id is required for action='transfer'")
+            result = client.transfer_playback(device_id=device_id, play=_coerce_bool(args.get("play")))
+            return tool_result({"success": True, "action": action, "result": result})
+        return tool_error(f"Unknown spotify_devices action: {action}")
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+def _handle_spotify_queue(args: dict, **kw) -> str:
+    action = str(args.get("action") or "get").strip().lower()
+    client = _spotify_client()
+    try:
+        if action == "get":
+            return tool_result(client.get_queue())
+        if action == "add":
+            uri = normalize_spotify_uri(str(args.get("uri") or ""), None)
+            result = client.add_to_queue(uri=uri, device_id=args.get("device_id"))
+            return tool_result({"success": True, "action": action, "uri": uri, "result": result})
+        return tool_error(f"Unknown spotify_queue action: {action}")
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+def _handle_spotify_search(args: dict, **kw) -> str:
+    client = _spotify_client()
+    query = str(args.get("query") or "").strip()
+    if not query:
+        return tool_error("query is required")
+    raw_types = _as_list(args.get("types") or args.get("type") or ["track"])
+    search_types = [value.lower() for value in raw_types if value.lower() in {"album", "artist", "playlist", "track", "show", "episode", "audiobook"}]
+    if not search_types:
+        return tool_error("types must contain one or more of: album, artist, playlist, track, show, episode, audiobook")
+    try:
+        return tool_result(client.search(
+            query=query,
+            search_types=search_types,
+            limit=_coerce_limit(args.get("limit"), default=10),
+            offset=max(0, int(args.get("offset") or 0)),
+            market=args.get("market"),
+            include_external=args.get("include_external"),
+        ))
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+def _handle_spotify_playlists(args: dict, **kw) -> str:
+    action = str(args.get("action") or "list").strip().lower()
+    client = _spotify_client()
+    try:
+        if action == "list":
+            return tool_result(client.get_my_playlists(
+                limit=_coerce_limit(args.get("limit"), default=20),
+                offset=max(0, int(args.get("offset") or 0)),
+            ))
+        if action == "get":
+            playlist_id = normalize_spotify_id(str(args.get("playlist_id") or ""), "playlist")
+            return tool_result(client.get_playlist(playlist_id=playlist_id, market=args.get("market")))
+        if action == "create":
+            name = str(args.get("name") or "").strip()
+            if not name:
+                return tool_error("name is required for action='create'")
+            return tool_result(client.create_playlist(
+                name=name,
+                public=_coerce_bool(args.get("public")),
+                collaborative=_coerce_bool(args.get("collaborative")),
+                description=args.get("description"),
+            ))
+        if action == "add_items":
+            playlist_id = normalize_spotify_id(str(args.get("playlist_id") or ""), "playlist")
+            uris = normalize_spotify_uris(_as_list(args.get("uris")))
+            return tool_result(client.add_playlist_items(
+                playlist_id=playlist_id,
+                uris=uris,
+                position=args.get("position"),
+            ))
+        if action == "remove_items":
+            playlist_id = normalize_spotify_id(str(args.get("playlist_id") or ""), "playlist")
+            uris = normalize_spotify_uris(_as_list(args.get("uris")))
+            return tool_result(client.remove_playlist_items(
+                playlist_id=playlist_id,
+                uris=uris,
+                snapshot_id=args.get("snapshot_id"),
+            ))
+        if action == "update_details":
+            playlist_id = normalize_spotify_id(str(args.get("playlist_id") or ""), "playlist")
+            return tool_result(client.update_playlist_details(
+                playlist_id=playlist_id,
+                name=args.get("name"),
+                public=args.get("public"),
+                collaborative=args.get("collaborative"),
+                description=args.get("description"),
+            ))
+        return tool_error(f"Unknown spotify_playlists action: {action}")
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+def _handle_spotify_albums(args: dict, **kw) -> str:
+    action = str(args.get("action") or "get").strip().lower()
+    client = _spotify_client()
+    try:
+        album_id = normalize_spotify_id(str(args.get("album_id") or args.get("id") or ""), "album")
+        if action == "get":
+            return tool_result(client.get_album(album_id=album_id, market=args.get("market")))
+        if action == "tracks":
+            return tool_result(client.get_album_tracks(
+                album_id=album_id,
+                limit=_coerce_limit(args.get("limit"), default=20),
+                offset=max(0, int(args.get("offset") or 0)),
+                market=args.get("market"),
+            ))
+        return tool_error(f"Unknown spotify_albums action: {action}")
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+def _handle_spotify_library(args: dict, **kw) -> str:
+    """Unified handler for saved tracks + saved albums (formerly two tools)."""
+    kind = str(args.get("kind") or "").strip().lower()
+    if kind not in {"tracks", "albums"}:
+        return tool_error("kind must be one of: tracks, albums")
+    action = str(args.get("action") or "list").strip().lower()
+    item_type = "track" if kind == "tracks" else "album"
+    client = _spotify_client()
+    try:
+        if action == "list":
+            limit = _coerce_limit(args.get("limit"), default=20)
+            offset = max(0, int(args.get("offset") or 0))
+            market = args.get("market")
+            if kind == "tracks":
+                return tool_result(client.get_saved_tracks(limit=limit, offset=offset, market=market))
+            return tool_result(client.get_saved_albums(limit=limit, offset=offset, market=market))
+        if action == "save":
+            uris = normalize_spotify_uris(_as_list(args.get("uris") or args.get("items")), item_type)
+            return tool_result(client.save_library_items(uris=uris))
+        if action == "remove":
+            ids = [normalize_spotify_id(item, item_type) for item in _as_list(args.get("ids") or args.get("items"))]
+            if not ids:
+                return tool_error("ids/items is required for action='remove'")
+            if kind == "tracks":
+                return tool_result(client.remove_saved_tracks(track_ids=ids))
+            return tool_result(client.remove_saved_albums(album_ids=ids))
+        return tool_error(f"Unknown spotify_library action: {action}")
+    except Exception as exc:
+        return _spotify_tool_error(exc)
+
+
+COMMON_STRING = {"type": "string"}
+
+SPOTIFY_PLAYBACK_SCHEMA = {
+    "name": "spotify_playback",
+    "description": "Control Spotify playback, inspect the active playback state, or fetch recently played tracks.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "action": {"type": "string", "enum": ["get_state", "get_currently_playing", "play", "pause", "next", "previous", "seek", "set_repeat", "set_shuffle", "set_volume", "recently_played"]},
+            "device_id": COMMON_STRING,
+            "market": COMMON_STRING,
+            "context_uri": COMMON_STRING,
+            "uris": {"type": "array", "items": COMMON_STRING},
+            "offset": {"type": "object"},
+            "position_ms": {"type": "integer"},
+            "state": {"description": "For set_repeat use track/context/off. For set_shuffle use boolean-like true/false.", "oneOf": [{"type": "string"}, {"type": "boolean"}]},
+            "volume_percent": {"type": "integer"},
+            "limit": {"type": "integer", "description": "For recently_played: number of tracks (max 50)"},
+            "after": {"type": "integer", "description": "For recently_played: Unix ms cursor (after this timestamp)"},
+            "before": {"type": "integer", "description": "For recently_played: Unix ms cursor (before this timestamp)"},
+        },
+        "required": ["action"],
+    },
+}
+
+SPOTIFY_DEVICES_SCHEMA = {
+    "name": "spotify_devices",
+    "description": "List Spotify Connect devices or transfer playback to a different device.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "action": {"type": "string", "enum": ["list", "transfer"]},
+            "device_id": COMMON_STRING,
+            "play": {"type": "boolean"},
+        },
+        "required": ["action"],
+    },
+}
+
+SPOTIFY_QUEUE_SCHEMA = {
+    "name": "spotify_queue",
+    "description": "Inspect the user's Spotify queue or add an item to it.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "action": {"type": "string", "enum": ["get", "add"]},
+            "uri": COMMON_STRING,
+            "device_id": COMMON_STRING,
+        },
+        "required": ["action"],
+    },
+}
+
+SPOTIFY_SEARCH_SCHEMA = {
+    "name": "spotify_search",
+    "description": "Search the Spotify catalog for tracks, albums, artists, playlists, shows, or episodes.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "query": COMMON_STRING,
+            "types": {"type": "array", "items": COMMON_STRING},
+            "type": COMMON_STRING,
+            "limit": {"type": "integer"},
+            "offset": {"type": "integer"},
+            "market": COMMON_STRING,
+            "include_external": COMMON_STRING,
+        },
+        "required": ["query"],
+    },
+}
+
+SPOTIFY_PLAYLISTS_SCHEMA = {
+    "name": "spotify_playlists",
+    "description": "List, inspect, create, update, and modify Spotify playlists.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "action": {"type": "string", "enum": ["list", "get", "create", "add_items", "remove_items", "update_details"]},
+            "playlist_id": COMMON_STRING,
+            "market": COMMON_STRING,
+            "limit": {"type": "integer"},
+            "offset": {"type": "integer"},
+            "name": COMMON_STRING,
+            "description": COMMON_STRING,
+            "public": {"type": "boolean"},
+            "collaborative": {"type": "boolean"},
+            "uris": {"type": "array", "items": COMMON_STRING},
+            "position": {"type": "integer"},
+            "snapshot_id": COMMON_STRING,
+        },
+        "required": ["action"],
+    },
+}
+
+SPOTIFY_ALBUMS_SCHEMA = {
+    "name": "spotify_albums",
+    "description": "Fetch Spotify album metadata or album tracks.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "action": {"type": "string", "enum": ["get", "tracks"]},
+            "album_id": COMMON_STRING,
+            "id": COMMON_STRING,
+            "market": COMMON_STRING,
+            "limit": {"type": "integer"},
+            "offset": {"type": "integer"},
+        },
+        "required": ["action"],
+    },
+}
+
+SPOTIFY_LIBRARY_SCHEMA = {
+    "name": "spotify_library",
+    "description": "List, save, or remove the user's saved Spotify tracks or albums. Use `kind` to select which.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "kind": {"type": "string", "enum": ["tracks", "albums"], "description": "Which library to operate on"},
+            "action": {"type": "string", "enum": ["list", "save", "remove"]},
+            "limit": {"type": "integer"},
+            "offset": {"type": "integer"},
+            "market": COMMON_STRING,
+            "uris": {"type": "array", "items": COMMON_STRING},
+            "ids": {"type": "array", "items": COMMON_STRING},
+            "items": {"type": "array", "items": COMMON_STRING},
+        },
+        "required": ["kind", "action"],
+    },
+}

pyproject.toml

@@ -78,6 +78,16 @@ termux = [
 ]
 dingtalk = ["dingtalk-stream>=0.20,<1", "alibabacloud-dingtalk>=2.0.0", "qrcode>=7.0,<8"]
 feishu = ["lark-oapi>=1.5.3,<2", "qrcode>=7.0,<8"]
+google = [
+  # Required by the google-workspace skill (Gmail, Calendar, Drive, Contacts,
+  # Sheets, Docs).  Declared here so packagers (Nix, Homebrew) ship them with
+  # the [all] extra and users don't hit runtime `pip install` paths that fail
+  # in environments without pip (e.g. Nix-managed Python).
+  "google-api-python-client>=2.100,<3",
+  "google-auth-oauthlib>=1.0,<2",
+  "google-auth-httplib2>=0.2,<1",
+]
+# `hermes dashboard` (localhost SPA + API).  Not in core to keep the default install lean.
 web = ["fastapi>=0.104.0,<1", "uvicorn[standard]>=0.24.0,<1"]
 rl = [
   "atroposlib @ git+https://github.com/NousResearch/atropos.git@c20c85256e5a45ad31edf8b7276e9c5ee1995a30",
@@ -109,6 +119,7 @@ all = [
   "hermes-agent[voice]",
   "hermes-agent[dingtalk]",
   "hermes-agent[feishu]",
+  "hermes-agent[google]",
   "hermes-agent[mistral]",
   "hermes-agent[bedrock]",
   "hermes-agent[web]",

scripts/build_model_catalog.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+"""Build the Hermes Model Catalog — a centralized JSON manifest of curated models.
+
+This script reads the in-repo hardcoded curated lists (``OPENROUTER_MODELS``,
+``_PROVIDER_MODELS["nous"]``) and writes them to a JSON manifest that the
+Hermes CLI fetches at runtime. Publishing the catalog through the docs site
+lets maintainers update model lists without shipping a Hermes release.
+
+The runtime fetcher falls back to the same in-repo hardcoded lists if the
+manifest is unreachable, so this script is a convenience for keeping the
+manifest in sync — not a source of truth.
+
+Usage::
+
+    python scripts/build_model_catalog.py
+
+Output: ``website/static/api/model-catalog.json``
+
+Live URL (after ``deploy-site.yml`` runs on merge to main):
+``https://hermes-agent.nousresearch.com/docs/api/model-catalog.json``
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import sys
+from datetime import datetime, timezone
+
+REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+sys.path.insert(0, REPO_ROOT)
+
+# Ensure HERMES_HOME is set for imports that touch it at module level.
+os.environ.setdefault("HERMES_HOME", os.path.join(os.path.expanduser("~"), ".hermes"))
+
+from hermes_cli.models import OPENROUTER_MODELS, _PROVIDER_MODELS  # noqa: E402
+
+OUTPUT_PATH = os.path.join(REPO_ROOT, "website", "static", "api", "model-catalog.json")
+CATALOG_VERSION = 1
+
+
+def build_catalog() -> dict:
+    return {
+        "version": CATALOG_VERSION,
+        "updated_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
+        "metadata": {
+            "source": "hermes-agent repo",
+            "docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog",
+        },
+        "providers": {
+            "openrouter": {
+                "metadata": {
+                    "display_name": "OpenRouter",
+                    "note": (
+                        "Descriptions drive picker badges. Live /api/v1/models "
+                        "filters curated ids by tool-calling support and free pricing."
+                    ),
+                },
+                "models": [
+                    {"id": mid, "description": desc}
+                    for mid, desc in OPENROUTER_MODELS
+                ],
+            },
+            "nous": {
+                "metadata": {
+                    "display_name": "Nous Portal",
+                    "note": (
+                        "Free-tier gating is determined live via Portal pricing "
+                        "(partition_nous_models_by_tier), not this manifest."
+                    ),
+                },
+                "models": [
+                    {"id": mid}
+                    for mid in _PROVIDER_MODELS.get("nous", [])
+                ],
+            },
+        },
+    }
+
+
+def main() -> int:
+    catalog = build_catalog()
+    os.makedirs(os.path.dirname(OUTPUT_PATH), exist_ok=True)
+    with open(OUTPUT_PATH, "w") as fh:
+        json.dump(catalog, fh, indent=2)
+        fh.write("\n")
+
+    print(f"Wrote {OUTPUT_PATH}")
+    for provider, block in catalog["providers"].items():
+        print(f"  {provider}: {len(block['models'])} models")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/install.sh

@@ -29,10 +29,25 @@ BOLD='\033[1m'
 REPO_URL_SSH="git@github.com:NousResearch/hermes-agent.git"
 REPO_URL_HTTPS="https://github.com/NousResearch/hermes-agent.git"
 HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
-INSTALL_DIR="${HERMES_INSTALL_DIR:-$HERMES_HOME/hermes-agent}"
+# INSTALL_DIR is resolved AFTER arg parsing and OS detection so we can pick an
+# FHS-style layout for root installs.  Track whether the user gave us an
+# explicit directory — if so we never override it.
+if [ -n "${HERMES_INSTALL_DIR:-}" ]; then
+    INSTALL_DIR="$HERMES_INSTALL_DIR"
+    INSTALL_DIR_EXPLICIT=true
+else
+    INSTALL_DIR=""
+    INSTALL_DIR_EXPLICIT=false
+fi
 PYTHON_VERSION="3.11"
 NODE_VERSION="22"
 
+# FHS-style root install layout (set by resolve_install_layout when applicable):
+#   code at /usr/local/lib/hermes-agent, command at /usr/local/bin/hermes,
+#   data still at /root/.hermes (HERMES_HOME).  Matches Claude Code / Codex CLI
+#   and keeps Docker bind-mounted /root/ volumes lean.
+ROOT_FHS_LAYOUT=false
+
 # Options
 USE_VENV=true
 RUN_SETUP=true
@@ -64,6 +79,7 @@ while [[ $# -gt 0 ]]; do
             ;;
         --dir)
             INSTALL_DIR="$2"
+            INSTALL_DIR_EXPLICIT=true
             shift 2
             ;;
         --hermes-home)
@@ -79,9 +95,20 @@ while [[ $# -gt 0 ]]; do
             echo "  --no-venv      Don't create virtual environment"
             echo "  --skip-setup   Skip interactive setup wizard"
             echo "  --branch NAME  Git branch to install (default: main)"
-            echo "  --dir PATH     Installation directory (default: ~/.hermes/hermes-agent)"
+            echo "  --dir PATH     Installation directory"
+            echo "                   default (non-root):  ~/.hermes/hermes-agent"
+            echo "                   default (root, Linux): /usr/local/lib/hermes-agent"
             echo "  --hermes-home PATH  Data directory (default: ~/.hermes, or \$HERMES_HOME)"
             echo "  -h, --help     Show this help"
+            echo ""
+            echo "Notes:"
+            echo "  When running as root on Linux, Hermes installs the code under"
+            echo "  /usr/local/lib/hermes-agent and links the command into"
+            echo "  /usr/local/bin/hermes (FHS layout — matches Claude Code / Codex CLI)."
+            echo "  Data, config, sessions, and logs still live in \$HERMES_HOME"
+            echo "  (default /root/.hermes).  This keeps Docker bind-mounted volumes"
+            echo "  small and ensures the command is on PATH for all shells."
+            echo "  Existing installs at \$HERMES_HOME/hermes-agent are preserved in-place."
             exit 0
             ;;
         *)
@@ -163,9 +190,60 @@ is_termux() {
     [ -n "${TERMUX_VERSION:-}" ] || [[ "${PREFIX:-}" == *"com.termux/files/usr"* ]]
 }
 
+# Decide where the repo checkout + venv live, and where the `hermes` command
+# symlink goes.  Called after detect_os so $OS/$DISTRO are known.
+#
+# Defaults:
+#   - Non-root, any OS:       INSTALL_DIR = $HERMES_HOME/hermes-agent
+#                             command link in $HOME/.local/bin
+#   - Termux (any uid):       INSTALL_DIR = $HERMES_HOME/hermes-agent
+#                             command link in $PREFIX/bin (already on PATH)
+#   - Root on Linux (new):    INSTALL_DIR = /usr/local/lib/hermes-agent
+#                             command link in /usr/local/bin
+#                             (unless a legacy install already exists at
+#                              $HERMES_HOME/hermes-agent — then preserve it)
+#
+# Always no-op when the user set --dir or $HERMES_INSTALL_DIR.
+resolve_install_layout() {
+    if [ "$INSTALL_DIR_EXPLICIT" = true ]; then
+        log_info "Install directory: $INSTALL_DIR (explicit)"
+        return 0
+    fi
+
+    # Termux: package manager manages /data/data/..., keep code in HERMES_HOME.
+    if is_termux; then
+        INSTALL_DIR="$HERMES_HOME/hermes-agent"
+        return 0
+    fi
+
+    # Root on Linux: prefer FHS layout unless a legacy install already exists.
+    # macOS root installs keep the legacy layout because /usr/local/ on macOS
+    # is Homebrew territory and we don't want to fight that.
+    if [ "$OS" = "linux" ] && [ "$(id -u)" -eq 0 ]; then
+        if [ -d "$HERMES_HOME/hermes-agent/.git" ]; then
+            INSTALL_DIR="$HERMES_HOME/hermes-agent"
+            log_info "Existing install detected at $INSTALL_DIR — keeping legacy layout"
+            log_info "  (new root installs use /usr/local/lib/hermes-agent)"
+            return 0
+        fi
+        INSTALL_DIR="/usr/local/lib/hermes-agent"
+        ROOT_FHS_LAYOUT=true
+        log_info "Root install on Linux — using FHS layout"
+        log_info "  Code:    $INSTALL_DIR"
+        log_info "  Command: /usr/local/bin/hermes"
+        log_info "  Data:    $HERMES_HOME (unchanged)"
+        return 0
+    fi
+
+    # Default: non-root, non-Termux → legacy user-scoped layout.
+    INSTALL_DIR="$HERMES_HOME/hermes-agent"
+}
+
 get_command_link_dir() {
     if is_termux && [ -n "${PREFIX:-}" ]; then
         echo "$PREFIX/bin"
+    elif [ "$ROOT_FHS_LAYOUT" = true ]; then
+        echo "/usr/local/bin"
     else
         echo "$HOME/.local/bin"
     fi
@@ -174,6 +252,8 @@ get_command_link_dir() {
 get_command_link_display_dir() {
     if is_termux && [ -n "${PREFIX:-}" ]; then
         echo '$PREFIX/bin'
+    elif [ "$ROOT_FHS_LAYOUT" = true ]; then
+        echo '/usr/local/bin'
     else
         echo '~/.local/bin'
     fi
@@ -975,6 +1055,14 @@ setup_path() {
         return 0
     fi
 
+    # FHS layout: /usr/local/bin is on PATH for every standard shell, nothing to inject.
+    if [ "$ROOT_FHS_LAYOUT" = true ]; then
+        export PATH="$command_link_dir:$PATH"
+        log_info "/usr/local/bin is already on PATH for all shells"
+        log_success "hermes command ready"
+        return 0
+    fi
+
     # Check if ~/.local/bin is on PATH; if not, add it to shell config.
     # Detect the user's actual login shell (not the shell running this script,
     # which is always bash when piped from curl).
@@ -1339,12 +1427,12 @@ print_success() {
     echo ""
 
     # Show file locations
-    echo -e "${CYAN}${BOLD}📁 Your files (all in ~/.hermes/):${NC}"
+    echo -e "${CYAN}${BOLD}📁 Your files:${NC}"
     echo ""
-    echo -e "   ${YELLOW}Config:${NC}    ~/.hermes/config.yaml"
-    echo -e "   ${YELLOW}API Keys:${NC}  ~/.hermes/.env"
-    echo -e "   ${YELLOW}Data:${NC}      ~/.hermes/cron/, sessions/, logs/"
-    echo -e "   ${YELLOW}Code:${NC}      ~/.hermes/hermes-agent/"
+    echo -e "   ${YELLOW}Config:${NC}    $HERMES_HOME/config.yaml"
+    echo -e "   ${YELLOW}API Keys:${NC}  $HERMES_HOME/.env"
+    echo -e "   ${YELLOW}Data:${NC}      $HERMES_HOME/cron/, sessions/, logs/"
+    echo -e "   ${YELLOW}Code:${NC}      $INSTALL_DIR"
     echo ""
 
     echo -e "${CYAN}─────────────────────────────────────────────────────────${NC}"
@@ -1364,6 +1452,9 @@ print_success() {
     if [ "$DISTRO" = "termux" ]; then
         echo -e "${YELLOW}⚡ 'hermes' was linked into $(get_command_link_display_dir), which is already on PATH in Termux.${NC}"
         echo ""
+    elif [ "$ROOT_FHS_LAYOUT" = true ]; then
+        echo -e "${YELLOW}⚡ 'hermes' was linked into /usr/local/bin and is ready to use — no shell reload needed.${NC}"
+        echo ""
     else
         echo -e "${YELLOW}⚡ Reload your shell to use 'hermes' command:${NC}"
         echo ""
@@ -1415,6 +1506,7 @@ main() {
     print_banner
 
     detect_os
+    resolve_install_layout
     install_uv
     check_python
     check_git

scripts/release.py

@@ -43,10 +43,16 @@ AUTHOR_MAP = {
     "teknium1@gmail.com": "teknium1",
     "teknium@nousresearch.com": "teknium1",
     "127238744+teknium1@users.noreply.github.com": "teknium1",
+    "focusflow.app.help@gmail.com": "yes999zc",
     "343873859@qq.com": "DrStrangerUJN",
+    "uzmpsk.dilekakbas@gmail.com": "dlkakbs",
     "jefferson@heimdallstrategy.com": "Mind-Dragon",
     "130918800+devorun@users.noreply.github.com": "devorun",
     "maks.mir@yahoo.com": "say8hi",
+    "web3blind@users.noreply.github.com": "web3blind",
+    "julia@alexland.us": "alexg0bot",
+    "1060770+benjaminsehl@users.noreply.github.com": "benjaminsehl",
+    "nerijusn76@gmail.com": "Nerijusas",
     # contributors (from noreply pattern)
     "david.vv@icloud.com": "davidvv",
     "wangqiang@wangqiangdeMac-mini.local": "xiaoqiang243",
@@ -58,13 +64,21 @@ AUTHOR_MAP = {
     "keifergu@tencent.com": "keifergu",
     "kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
     "abner.the.foreman@agentmail.to": "Abnertheforeman",
+    "thomasgeorgevii09@gmail.com": "tochukwuada",
     "harryykyle1@gmail.com": "hharry11",
     "kshitijk4poor@gmail.com": "kshitijk4poor",
+    "keira.voss94@gmail.com": "keiravoss94",
     "16443023+stablegenius49@users.noreply.github.com": "stablegenius49",
+    "fqsy1416@gmail.com": "EKKOLearnAI",
+    "simbamax99@gmail.com": "simbam99",
+    "iris@growthpillars.co": "irispillars",
     "185121704+stablegenius49@users.noreply.github.com": "stablegenius49",
     "101283333+batuhankocyigit@users.noreply.github.com": "batuhankocyigit",
     "255305877+ismell0992-afk@users.noreply.github.com": "ismell0992-afk",
+    "cyprian@ironin.pl": "iRonin",
     "valdi.jorge@gmail.com": "jvcl",
+    "q19dcp@gmail.com": "aj-nt",
+    "ebukau84@gmail.com": "UgwujaGeorge",
     "francip@gmail.com": "francip",
     "omni@comelse.com": "omnissiah-comelse",
     "oussama.redcode@gmail.com": "mavrickdeveloper",
@@ -77,10 +91,13 @@ AUTHOR_MAP = {
     "77628552+raulvidis@users.noreply.github.com": "raulvidis",
     "145567217+Aum08Desai@users.noreply.github.com": "Aum08Desai",
     "256820943+kshitij-eliza@users.noreply.github.com": "kshitij-eliza",
+    "jiechengwu@pony.ai": "Jason2031",
     "44278268+shitcoinsherpa@users.noreply.github.com": "shitcoinsherpa",
     "104278804+Sertug17@users.noreply.github.com": "Sertug17",
     "112503481+caentzminger@users.noreply.github.com": "caentzminger",
     "258577966+voidborne-d@users.noreply.github.com": "voidborne-d",
+    "liusway405@gmail.com": "voidborne-d",
+    "xydarcher@uestc.edu.cn": "Readon",
     "sir_even@icloud.com": "sirEven",
     "36056348+sirEven@users.noreply.github.com": "sirEven",
     "70424851+insecurejezza@users.noreply.github.com": "insecurejezza",
@@ -103,6 +120,7 @@ AUTHOR_MAP = {
     "30841158+n-WN@users.noreply.github.com": "n-WN",
     "tsuijinglei@gmail.com": "hiddenpuppy",
     "jerome@clawwork.ai": "HiddenPuppy",
+    "jerome.benoit@sap.com": "jerome-benoit",
     "wysie@users.noreply.github.com": "Wysie",
     "leoyuan0099@gmail.com": "keyuyuan",
     "bxzt2006@163.com": "Only-Code-A",
@@ -163,11 +181,47 @@ AUTHOR_MAP = {
     "jaisehgal11299@gmail.com": "jaisup",
     "percydikec@gmail.com": "PercyDikec",
     "noonou7@gmail.com": "HenkDz",
+    # Azure Foundry salvage (PRs #9029, #4599, #10086, #8766)
+    "tech@smartlogics.net": "TechPrototyper",
+    "637186+HangGlidersRule@users.noreply.github.com": "HangGlidersRule",
+    "pein892@gmail.com": "pein892",
     "dean.kerr@gmail.com": "deankerr",
     "socrates1024@gmail.com": "socrates1024",
     "seanalt555@gmail.com": "Salt-555",
     "satelerd@gmail.com": "satelerd",
     "dan@danlynn.com": "danklynn",
+    "mattmaximo@hotmail.com": "MattMaximo",
+    "149063006+j3ffffff@users.noreply.github.com": "j3ffffff",
+    "A-FdL-Prog@users.noreply.github.com": "A-FdL-Prog",
+    "l0hde@users.noreply.github.com": "l0hde",
+    "difujia@users.noreply.github.com": "difujia",
+    "vominh1919@gmail.com": "vominh1919",
+    "yue.gu2023@gmail.com": "YueLich",
+    "51783311+andyylin@users.noreply.github.com": "andyylin",
+    "me@jakubkrcmar.cz": "jakubkrcmar",
+    "prasadus92@gmail.com": "prasadus92",
+    "michael@make.software": "mssteuer",
+    "der@konsi.org": "konsisumer",
+    "abogale2@gmail.com": "amanuel2",
+    "alexazzjjtt@163.com": "alexzhu0",
+    "pub_forgreatagent@antgroup.com": "AntAISecurityLab",
+    "252620095+briandevans@users.noreply.github.com": "briandevans",
+    "danielrpike9@gmail.com": "Bartok9",
+    "skozyuk@cruxexperts.com": "CruxExperts",
+    "154585401+LeonSGP43@users.noreply.github.com": "LeonSGP43",
+    "mgparkprint@gmail.com": "vlwkaos",
+    "tranquil_flow@protonmail.com": "Tranquil-Flow",
+    "wangshengyang2004@163.com": "Wangshengyang2004",
+    "hasan.ali13381@gmail.com": "H-Ali13381",
+    "xienb@proton.me": "XieNBi",
+    "139681654+maymuneth@users.noreply.github.com": "maymuneth",
+    "zengwei@nightq.cn": "nightq",
+    "1434494126@qq.com": "5park1e",
+    "158153005+5park1e@users.noreply.github.com": "5park1e",
+    "innocarpe@gmail.com": "innocarpe",
+    "noreply@ked.com": "qike-ms",
+    "andrekurait@gmail.com": "AndreKurait",
+    "bsgdigital@users.noreply.github.com": "bsgdigital",
     "numman.ali@gmail.com": "nummanali",
     "rohithsaimidigudla@gmail.com": "whitehatjr1001",
     "0xNyk@users.noreply.github.com": "0xNyk",
@@ -186,6 +240,11 @@ AUTHOR_MAP = {
     "bryan@intertwinesys.com": "bryanyoung",
     "christo.mitov@gmail.com": "christomitov",
     "hermes@nousresearch.com": "NousResearch",
+    "reginaldasr@gmail.com": "ReginaldasR",
+    "ntconguit@gmail.com": "0xharryriddle",
+    "agent@wildcat.local": "ericnicolaides",
+    "georgex8001@gmail.com": "georgex8001",
+    "stefan@dimagents.ai": "dimitrovi",
     "hermes@noushq.ai": "benbarclay",
     "chinmingcock@gmail.com": "ChimingLiu",
     "openclaw@sparklab.ai": "openclaw",
@@ -334,6 +393,9 @@ AUTHOR_MAP = {
     "brian@bde.io": "briandevans",
     "hubin_ll@qq.com": "LLQWQ",
     "memosr_email@gmail.com": "memosr",
+    "jperlow@gmail.com": "perlowja",
+    "tangyuanjc@JCdeAIfenshendeMac-mini.local": "tangyuanjc",
+    "harryplusplus@gmail.com": "harryplusplus",
     "anthhub@163.com": "anthhub",
     "shenuu@gmail.com": "shenuu",
     "xiayh17@gmail.com": "xiayh0107",
@@ -357,6 +419,7 @@ AUTHOR_MAP = {
     "105142614+VTRiot@users.noreply.github.com": "VTRiot",
     "vivien000812@gmail.com": "iamagenius00",
     "89228157+Feranmi10@users.noreply.github.com": "Feranmi10",
+    "oluwadareferanmi11@gmail.com": "Feranmi10",
     "simon@gtcl.us": "simon-gtcl",
     "suzukaze.haduki@gmail.com": "houko",
     "cliff@cigii.com": "cgarwood82",
@@ -437,6 +500,12 @@ AUTHOR_MAP = {
     "topcheer@me.com": "topcheer",
     "walli@tencent.com": "walli",
     "zhuofengwang@tencent.com": "Zhuofeng-Wang",
+    # April 2026 salvage-PR batch (#14920, #14986, #14966)
+    "mrunmayeerane17@gmail.com": "mrunmayee17",
+    "69489633+camaragon@users.noreply.github.com": "camaragon",
+    "shamork@outlook.com": "shamork",
+    # April 2026 Discord Copilot /model salvage (#15030)
+    "cshong2017@outlook.com": "Nicecsh",
     # no-github-match — keep as display names
     "clio-agent@sisyphuslabs.ai": "Sisyphus",
     "marco@rutimka.de": "Marco Rutsch",
@@ -444,6 +513,9 @@ AUTHOR_MAP = {
     "zhangxicen@example.com": "zhangxicen",
     "codex@openai.invalid": "teknium1",
     "screenmachine@gmail.com": "teknium1",
+    "chenzeshi@live.com": "chen1749144759",
+    "mor.aleksandr@yahoo.com": "MorAlekss",
+    "ash@users.noreply.github.com": "ash",
 }