Merge remote-tracking branch 'origin/main' into feat/dashboard-chat

Follow-up for #13862 — the post-init api_mode upgrade at __init__ (direct OpenAI /
gpt-5-requires-responses path) runs AFTER the eager transport warm. Clear the cache
so the stale chat_completions entry is evicted.

Cosmetic: correctness was already fine since _get_transport() keys by current
api_mode, but this avoids leaving unused cache state behind.

AGENTS.md

@@ -243,6 +243,17 @@ 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`.
+
+**Never add a parallel chat surface in React.** If you catch yourself re-implementing slash popover / model picker / tool cards for the dashboard, stop — the TUI already does those, and anything new you add to Ink will appear in the dashboard automatically.
+
 ---
 
 ## Adding New Tools

CONTRIBUTING.md

@@ -88,7 +88,7 @@ cp cli-config.yaml.example ~/.hermes/config.yaml
 touch ~/.hermes/.env
 
 # Add at minimum an LLM provider key:
-echo 'OPENROUTER_API_KEY=sk-or-v1-your-key' >> ~/.hermes/.env
+echo "OPENROUTER_API_KEY=***" >> ~/.hermes/.env
 ```
 
 ### Run

Dockerfile

@@ -12,7 +12,7 @@ ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
 # Install system dependencies in one layer, clear APT cache
 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 && \
+        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli && \
     rm -rf /var/lib/apt/lists/*
 
 # Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
@@ -50,5 +50,6 @@ RUN uv venv && \
 # ---------- Runtime ----------
 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" ]

README.md

@@ -173,7 +173,6 @@ python -m pytest tests/ -q
 - 💬 [Discord](https://discord.gg/NousResearch)
 - 📚 [Skills Hub](https://agentskills.io)
 - 🐛 [Issues](https://github.com/NousResearch/hermes-agent/issues)
-- 💡 [Discussions](https://github.com/NousResearch/hermes-agent/discussions)
 - 🔌 [HermesClaw](https://github.com/AaronWong1999/hermesclaw) — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account.
 
 ---

agent/anthropic_adapter.py

@@ -117,6 +117,63 @@ def _get_anthropic_max_output(model: str) -> int:
     return best_val
 
 
+def _resolve_positive_anthropic_max_tokens(value) -> Optional[int]:
+    """Return ``value`` floored to a positive int, or ``None`` if it is not a
+    finite positive number. Ported from openclaw/openclaw#66664.
+
+    Anthropic's Messages API rejects ``max_tokens`` values that are 0,
+    negative, non-integer, or non-finite with HTTP 400. Python's ``or``
+    idiom (``max_tokens or fallback``) correctly catches ``0`` but lets
+    negative ints and fractional floats (``-1``, ``0.5``) through to the
+    API, producing a user-visible failure instead of a local error.
+    """
+    # Booleans are a subclass of int — exclude explicitly so ``True`` doesn't
+    # silently become 1 and ``False`` doesn't become 0.
+    if isinstance(value, bool):
+        return None
+    if not isinstance(value, (int, float)):
+        return None
+    try:
+        import math
+        if not math.isfinite(value):
+            return None
+    except Exception:
+        return None
+    floored = int(value)  # truncates toward zero for floats
+    return floored if floored > 0 else None
+
+
+def _resolve_anthropic_messages_max_tokens(
+    requested,
+    model: str,
+    context_length: Optional[int] = None,
+) -> int:
+    """Resolve the ``max_tokens`` budget for an Anthropic Messages call.
+
+    Prefers ``requested`` when it is a positive finite number; otherwise
+    falls back to the model's output ceiling. Raises ``ValueError`` if no
+    positive budget can be resolved (should not happen with current model
+    table defaults, but guards against a future regression where
+    ``_get_anthropic_max_output`` could return ``0``).
+
+    Separately, callers apply a context-window clamp — this resolver does
+    not, to keep the positive-value contract independent of endpoint
+    specifics.
+
+    Ported from openclaw/openclaw#66664 (resolveAnthropicMessagesMaxTokens).
+    """
+    resolved = _resolve_positive_anthropic_max_tokens(requested)
+    if resolved is not None:
+        return resolved
+    fallback = _get_anthropic_max_output(model)
+    if fallback > 0:
+        return fallback
+    raise ValueError(
+        f"Anthropic Messages adapter requires a positive max_tokens value for "
+        f"model {model!r}; got {requested!r} and no model default resolved."
+    )
+
+
 def _supports_adaptive_thinking(model: str) -> bool:
     """Return True for Claude 4.6+ models that support adaptive thinking."""
     return any(v in model for v in _ADAPTIVE_THINKING_SUBSTRINGS)
@@ -1083,6 +1140,31 @@ def convert_messages_to_anthropic(
                     "name": fn.get("name", ""),
                     "input": parsed_args,
                 })
+            # Kimi's /coding endpoint (Anthropic protocol) requires assistant
+            # tool-call messages to carry reasoning_content when thinking is
+            # enabled server-side.  Preserve it as a thinking block so Kimi
+            # can validate the message history.  See hermes-agent#13848.
+            #
+            # Accept empty string "" — _copy_reasoning_content_for_api()
+            # injects "" as a tier-3 fallback for Kimi tool-call messages
+            # that had no reasoning.  Kimi requires the field to exist, even
+            # if empty.
+            #
+            # Prepend (not append): Anthropic protocol requires thinking
+            # blocks before text and tool_use blocks.
+            #
+            # Guard: only add when reasoning_details didn't already contribute
+            # thinking blocks.  On native Anthropic, reasoning_details produces
+            # signed thinking blocks — adding another unsigned one from
+            # reasoning_content would create a duplicate (same text) that gets
+            # downgraded to a spurious text block on the last assistant message.
+            reasoning_content = m.get("reasoning_content")
+            _already_has_thinking = any(
+                isinstance(b, dict) and b.get("type") in ("thinking", "redacted_thinking")
+                for b in blocks
+            )
+            if isinstance(reasoning_content, str) and not _already_has_thinking:
+                blocks.insert(0, {"type": "thinking", "thinking": reasoning_content})
             # Anthropic rejects empty assistant content
             effective = blocks or content
             if not effective or effective == "":
@@ -1238,6 +1320,7 @@ def convert_messages_to_anthropic(
     #    cache markers can interfere with signature validation.
     _THINKING_TYPES = frozenset(("thinking", "redacted_thinking"))
     _is_third_party = _is_third_party_anthropic_endpoint(base_url)
+    _is_kimi = _is_kimi_coding_endpoint(base_url)
 
     last_assistant_idx = None
     for i in range(len(result) - 1, -1, -1):
@@ -1249,7 +1332,25 @@ def convert_messages_to_anthropic(
         if m.get("role") != "assistant" or not isinstance(m.get("content"), list):
             continue
 
-        if _is_third_party or idx != last_assistant_idx:
+        if _is_kimi:
+            # Kimi's /coding endpoint enables thinking server-side and
+            # requires unsigned thinking blocks on replayed assistant
+            # tool-call messages.  Strip signed Anthropic blocks (Kimi
+            # can't validate signatures) but preserve the unsigned ones
+            # we synthesised from reasoning_content above.
+            new_content = []
+            for b in m["content"]:
+                if not isinstance(b, dict) or b.get("type") not in _THINKING_TYPES:
+                    new_content.append(b)
+                    continue
+                if b.get("signature") or b.get("data"):
+                    # Anthropic-signed block — Kimi can't validate, strip
+                    continue
+                # Unsigned thinking (synthesised from reasoning_content) —
+                # keep it: Kimi needs it for message-history validation.
+                new_content.append(b)
+            m["content"] = new_content or [{"type": "text", "text": "(empty)"}]
+        elif _is_third_party or idx != last_assistant_idx:
             # Third-party endpoint: strip ALL thinking blocks from every
             # assistant message — signatures are Anthropic-proprietary.
             # Direct Anthropic: strip from non-latest assistant messages only.
@@ -1347,7 +1448,12 @@ def build_anthropic_kwargs(
 
     model = normalize_model_name(model, preserve_dots=preserve_dots)
     # effective_max_tokens = output cap for this call (≠ total context window)
-    effective_max_tokens = max_tokens or _get_anthropic_max_output(model)
+    # Use the resolver helper so non-positive values (negative ints,
+    # fractional floats, NaN, non-numeric) fail locally with a clear error
+    # rather than 400-ing at the Anthropic API. See openclaw/openclaw#66664.
+    effective_max_tokens = _resolve_anthropic_messages_max_tokens(
+        max_tokens, model, context_length=context_length
+    )
 
     # Clamp output cap to fit inside the total context window.
     # Only matters for small custom endpoints where context_length < native
@@ -1560,42 +1666,3 @@ def normalize_anthropic_response(
         ),
         finish_reason,
     )
-
-
-def normalize_anthropic_response_v2(
-    response,
-    strip_tool_prefix: bool = False,
-) -> "NormalizedResponse":
-    """Normalize Anthropic response to NormalizedResponse.
-
-    Wraps the existing normalize_anthropic_response() and maps its output
-    to the shared transport types.  This allows incremental migration —
-    one call site at a time — without changing the original function.
-    """
-    from agent.transports.types import NormalizedResponse, build_tool_call
-
-    assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
-
-    tool_calls = None
-    if assistant_msg.tool_calls:
-        tool_calls = [
-            build_tool_call(
-                id=tc.id,
-                name=tc.function.name,
-                arguments=tc.function.arguments,
-            )
-            for tc in assistant_msg.tool_calls
-        ]
-
-    provider_data = {}
-    if getattr(assistant_msg, "reasoning_details", None):
-        provider_data["reasoning_details"] = assistant_msg.reasoning_details
-
-    return NormalizedResponse(
-        content=assistant_msg.content,
-        tool_calls=tool_calls,
-        finish_reason=finish_reason,
-        reasoning=getattr(assistant_msg, "reasoning", None),
-        usage=None,  # Anthropic usage is on the raw response, not the normaliser
-        provider_data=provider_data or None,
-    )

agent/auxiliary_client.py

@@ -134,6 +134,7 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "gemini": "gemini-3-flash-preview",
     "zai": "glm-4.5-flash",
     "kimi-coding": "kimi-k2-turbo-preview",
+    "stepfun": "step-3.5-flash",
     "kimi-coding-cn": "kimi-k2-turbo-preview",
     "minimax": "MiniMax-M2.7",
     "minimax-cn": "MiniMax-M2.7",

agent/context_compressor.py

@@ -64,6 +64,47 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
+def _content_text_for_contains(content: Any) -> str:
+    """Return a best-effort text view of message content.
+
+    Used only for substring checks when we need to know whether we've already
+    appended a note to a message. Keeps multimodal lists intact elsewhere.
+    """
+    if content is None:
+        return ""
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        parts: list[str] = []
+        for item in content:
+            if isinstance(item, str):
+                parts.append(item)
+            elif isinstance(item, dict):
+                text = item.get("text")
+                if isinstance(text, str):
+                    parts.append(text)
+        return "\n".join(part for part in parts if part)
+    return str(content)
+
+
+def _append_text_to_content(content: Any, text: str, *, prepend: bool = False) -> Any:
+    """Append or prepend plain text to message content safely.
+
+    Compression sometimes needs to add a note or merge a summary into an
+    existing message. Message content may be plain text or a multimodal list of
+    blocks, so direct string concatenation is not always safe.
+    """
+    if content is None:
+        return text
+    if isinstance(content, str):
+        return text + content if prepend else content + text
+    if isinstance(content, list):
+        text_block = {"type": "text", "text": text}
+        return [text_block, *content] if prepend else [*content, text_block]
+    rendered = str(content)
+    return text + rendered if prepend else rendered + text
+
+
 def _truncate_tool_call_args_json(args: str, head_chars: int = 200) -> str:
     """Shrink long string values inside a tool-call arguments JSON blob while
     preserving JSON validity.
@@ -807,7 +848,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                 )
                 self.summary_model = ""  # empty = use main model
                 self._summary_failure_cooldown_until = 0.0  # no cooldown
-                return self._generate_summary(turns_to_summarize)  # retry immediately
+                return self._generate_summary(turns_to_summarize, focus_topic=focus_topic)  # retry immediately
 
             # Transient errors (timeout, rate limit, network) — shorter cooldown
             _transient_cooldown = 60
@@ -1144,10 +1185,13 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         for i in range(compress_start):
             msg = messages[i].copy()
             if i == 0 and msg.get("role") == "system":
-                existing = msg.get("content") or ""
+                existing = msg.get("content")
                 _compression_note = "[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
-                if _compression_note not in existing:
-                    msg["content"] = existing + "\n\n" + _compression_note
+                if _compression_note not in _content_text_for_contains(existing):
+                    msg["content"] = _append_text_to_content(
+                        existing,
+                        "\n\n" + _compression_note if isinstance(existing, str) and existing else _compression_note,
+                    )
             compressed.append(msg)
 
         # If LLM summary failed, insert a static fallback so the model
@@ -1191,12 +1235,15 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         for i in range(compress_end, n_messages):
             msg = messages[i].copy()
             if _merge_summary_into_tail and i == compress_end:
-                original = msg.get("content") or ""
-                msg["content"] = (
+                merged_prefix = (
                     summary
                     + "\n\n--- END OF CONTEXT SUMMARY — "
                     "respond to the message below, not the summary above ---\n\n"
-                    + original
+                )
+                msg["content"] = _append_text_to_content(
+                    msg.get("content"),
+                    merged_prefix,
+                    prepend=True,
                 )
                 _merge_summary_into_tail = False
             compressed.append(msg)

agent/error_classifier.py

@@ -220,12 +220,25 @@ _TRANSPORT_ERROR_TYPES = frozenset({
     "ConnectionAbortedError", "BrokenPipeError",
     "TimeoutError", "ReadError",
     "ServerDisconnectedError",
+    # SSL/TLS transport errors — transient mid-stream handshake/record
+    # failures that should retry rather than surface as a stalled session.
+    # ssl.SSLError subclasses OSError (caught by isinstance) but we list
+    # the type names here so provider-wrapped SSL errors (e.g. when the
+    # SDK re-raises without preserving the exception chain) still classify
+    # as transport rather than falling through to the unknown bucket.
+    "SSLError", "SSLZeroReturnError", "SSLWantReadError",
+    "SSLWantWriteError", "SSLEOFError", "SSLSyscallError",
     # OpenAI SDK errors (not subclasses of Python builtins)
     "APIConnectionError",
     "APITimeoutError",
 })
 
-# Server disconnect patterns (no status code, but transport-level)
+# Server disconnect patterns (no status code, but transport-level).
+# These are the "ambiguous" patterns — a plain connection close could be
+# transient transport hiccup OR server-side context overflow rejection
+# (common when the API gateway disconnects instead of returning an HTTP
+# error for oversized requests).  A large session + one of these patterns
+# triggers the context-overflow-with-compression recovery path.
 _SERVER_DISCONNECT_PATTERNS = [
     "server disconnected",
     "peer closed connection",
@@ -236,6 +249,40 @@ _SERVER_DISCONNECT_PATTERNS = [
     "incomplete chunked read",
 ]
 
+# SSL/TLS transient failure patterns — intentionally distinct from
+# _SERVER_DISCONNECT_PATTERNS above.
+#
+# An SSL alert mid-stream is almost always a transport-layer hiccup
+# (flaky network, mid-session TLS renegotiation failure, load balancer
+# dropping the connection) — NOT a server-side context overflow signal.
+# So we want the retry path but NOT the compression path; lumping these
+# into _SERVER_DISCONNECT_PATTERNS would trigger unnecessary (and
+# expensive) context compression on any large-session SSL hiccup.
+#
+# The OpenSSL library constructs error codes by prepending a format string
+# to the uppercased alert reason; OpenSSL 3.x changed the separator
+# (e.g. `SSLV3_ALERT_BAD_RECORD_MAC` → `SSL/TLS_ALERT_BAD_RECORD_MAC`),
+# which silently stopped matching anything explicit.  Matching on the
+# stable substrings (`bad record mac`, `ssl alert`, `tls alert`, etc.)
+# survives future OpenSSL format churn without code changes.
+_SSL_TRANSIENT_PATTERNS = [
+    # Space-separated (human-readable form, Python ssl module, most SDKs)
+    "bad record mac",
+    "ssl alert",
+    "tls alert",
+    "ssl handshake failure",
+    "tlsv1 alert",
+    "sslv3 alert",
+    # Underscore-separated (OpenSSL error code tokens, e.g.
+    # `ERR_SSL_SSL/TLS_ALERT_BAD_RECORD_MAC`, `SSLV3_ALERT_BAD_RECORD_MAC`)
+    "bad_record_mac",
+    "ssl_alert",
+    "tls_alert",
+    "tls_alert_internal_error",
+    # Python ssl module prefix, e.g. "[SSL: BAD_RECORD_MAC]"
+    "[ssl:",
+]
+
 
 # ── Classification pipeline ─────────────────────────────────────────────
 
@@ -255,9 +302,10 @@ def classify_api_error(
       2. HTTP status code + message-aware refinement
       3. Error code classification (from body)
       4. Message pattern matching (billing vs rate_limit vs context vs auth)
-      5. Transport error heuristics
+      5. SSL/TLS transient alert patterns → retry as timeout
       6. Server disconnect + large session → context overflow
-      7. Fallback: unknown (retryable with backoff)
+      7. Transport error heuristics
+      8. Fallback: unknown (retryable with backoff)
 
     Args:
         error: The exception from the API call.
@@ -388,7 +436,18 @@ def classify_api_error(
     if classified is not None:
         return classified
 
-    # ── 5. Server disconnect + large session → context overflow ─────
+    # ── 5. SSL/TLS transient errors → retry as timeout (not compression) ──
+    # SSL alerts mid-stream are transport hiccups, not server-side context
+    # overflow signals.  Classify before the disconnect check so a large
+    # session doesn't incorrectly trigger context compression when the real
+    # cause is a flaky TLS handshake.  Also matches when the error is
+    # wrapped in a generic exception whose message string carries the SSL
+    # alert text but the type isn't ssl.SSLError (happens with some SDKs
+    # that re-raise without chaining).
+    if any(p in error_msg for p in _SSL_TRANSIENT_PATTERNS):
+        return _result(FailoverReason.timeout, retryable=True)
+
+    # ── 6. Server disconnect + large session → context overflow ─────
     # Must come BEFORE generic transport error catch — a disconnect on
     # a large session is more likely context overflow than a transient
     # transport hiccup.  Without this ordering, RemoteProtocolError
@@ -405,12 +464,12 @@ def classify_api_error(
             )
         return _result(FailoverReason.timeout, retryable=True)
 
-    # ── 6. Transport / timeout heuristics ───────────────────────────
+    # ── 7. Transport / timeout heuristics ───────────────────────────
 
     if error_type in _TRANSPORT_ERROR_TYPES or isinstance(error, (TimeoutError, ConnectionError, OSError)):
         return _result(FailoverReason.timeout, retryable=True)
 
-    # ── 7. Fallback: unknown ────────────────────────────────────────
+    # ── 8. Fallback: unknown ────────────────────────────────────────
 
     return _result(FailoverReason.unknown, retryable=True)
 
@@ -470,11 +529,16 @@ def _classify_by_status(
                 retryable=False,
                 should_fallback=True,
             )
-        # Generic 404 — could be model or endpoint
+        # Generic 404 with no "model not found" signal — could be a wrong
+        # endpoint path (common with local llama.cpp / Ollama / vLLM when
+        # the URL is slightly misconfigured), a proxy routing glitch, or
+        # a transient backend issue.  Classifying these as model_not_found
+        # silently falls back to a different provider and tells the model
+        # the model is missing, which is wrong and wastes a turn.  Treat
+        # as unknown so the retry loop surfaces the real error instead.
         return result_fn(
-            FailoverReason.model_not_found,
-            retryable=False,
-            should_fallback=True,
+            FailoverReason.unknown,
+            retryable=True,
         )
 
     if status_code == 413:

agent/model_metadata.py

@@ -4,6 +4,7 @@ Pure utility functions with no AIAgent dependency. Used by ContextCompressor
 and run_agent.py for pre-flight context checks.
 """
 
+import ipaddress
 import logging
 import re
 import time
@@ -25,7 +26,7 @@ logger = logging.getLogger(__name__)
 # are preserved so the full model name reaches cache lookups and server queries.
 _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
-    "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "anthropic", "deepseek",
+    "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "stepfun", "minimax", "minimax-cn", "anthropic", "deepseek",
     "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
     "qwen-oauth",
     "xiaomi",
@@ -36,7 +37,7 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
     "github-models", "kimi", "moonshot", "kimi-cn", "moonshot-cn", "claude", "deep-seek",
     "ollama",
-    "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
+    "stepfun", "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
     "mimo", "xiaomi-mimo",
     "arcee-ai", "arceeai",
     "xai", "x-ai", "x.ai", "grok",
@@ -51,6 +52,13 @@ _OLLAMA_TAG_PATTERN = re.compile(
 )
 
 
+# Tailscale's CGNAT range (RFC 6598). `ipaddress.is_private` excludes this
+# block, so without an explicit check Ollama reached over Tailscale (e.g.
+# `http://100.77.243.5:11434`) wouldn't be treated as local and its stream
+# read / stale timeouts wouldn't get auto-bumped. Built once at import time.
+_TAILSCALE_CGNAT = ipaddress.IPv4Network("100.64.0.0/10")
+
+
 def _strip_provider_prefix(model: str) -> str:
     """Strip a recognised provider prefix from a model string.
 
@@ -125,6 +133,8 @@ DEFAULT_CONTEXT_LENGTHS = {
     # Google
     "gemini": 1048576,
     # Gemma (open models served via AI Studio)
+    "gemma-4": 256000,  # Gemma 4 family
+    "gemma4": 256000,  # Ollama-style naming (e.g. gemma4:31b-cloud)
     "gemma-4-31b": 256000,
     "gemma-3": 131072,
     "gemma": 8192,  # fallback for older gemma models
@@ -177,6 +187,8 @@ DEFAULT_CONTEXT_LENGTHS = {
     "mimo-v2-pro": 1000000,
     "mimo-v2-omni": 256000,
     "mimo-v2-flash": 256000,
+    "mimo-v2.5-pro": 1000000,
+    "mimo-v2.5": 1000000,
     "zai-org/GLM-5": 202752,
 }
 
@@ -191,6 +203,7 @@ _CONTEXT_LENGTH_KEYS = (
     "max_seq_len",
     "n_ctx_train",
     "n_ctx",
+    "ctx_size",
 )
 
 _MAX_COMPLETION_KEYS = (
@@ -234,9 +247,12 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "chatgpt.com": "openai",
     "api.anthropic.com": "anthropic",
     "api.z.ai": "zai",
+    "open.bigmodel.cn": "zai",
     "api.moonshot.ai": "kimi-coding",
     "api.moonshot.cn": "kimi-coding-cn",
     "api.kimi.com": "kimi-coding",
+    "api.stepfun.ai": "stepfun",
+    "api.stepfun.com": "stepfun",
     "api.arcee.ai": "arcee",
     "api.minimax": "minimax",
     "dashscope.aliyuncs.com": "alibaba",
@@ -281,7 +297,15 @@ def _is_known_provider_base_url(base_url: str) -> bool:
 
 
 def is_local_endpoint(base_url: str) -> bool:
-    """Return True if base_url points to a local machine (localhost / RFC-1918 / WSL)."""
+    """Return True if base_url points to a local machine.
+
+    Recognises loopback (``localhost``, ``127.0.0.0/8``, ``::1``),
+    container-internal DNS names (``host.docker.internal`` et al.),
+    RFC-1918 private ranges (``10/8``, ``172.16/12``, ``192.168/16``),
+    link-local, and Tailscale CGNAT (``100.64.0.0/10``). Tailscale CGNAT
+    is included so remote-but-trusted Ollama boxes reached over a
+    Tailscale mesh get the same timeout auto-bumps as localhost Ollama.
+    """
     normalized = _normalize_base_url(base_url)
     if not normalized:
         return False
@@ -296,14 +320,17 @@ def is_local_endpoint(base_url: str) -> bool:
     # Docker / Podman / Lima internal DNS names (e.g. host.docker.internal)
     if any(host.endswith(suffix) for suffix in _CONTAINER_LOCAL_SUFFIXES):
         return True
-    # RFC-1918 private ranges and link-local
-    import ipaddress
+    # RFC-1918 private ranges, link-local, and Tailscale CGNAT
     try:
         addr = ipaddress.ip_address(host)
-        return addr.is_private or addr.is_loopback or addr.is_link_local
+        if addr.is_private or addr.is_loopback or addr.is_link_local:
+            return True
+        if isinstance(addr, ipaddress.IPv4Address) and addr in _TAILSCALE_CGNAT:
+            return True
     except ValueError:
         pass
     # Bare IP that looks like a private range (e.g. 172.26.x.x for WSL)
+    # or Tailscale CGNAT (100.64.x.x–100.127.x.x).
     parts = host.split(".")
     if len(parts) == 4:
         try:
@@ -314,6 +341,8 @@ def is_local_endpoint(base_url: str) -> bool:
                 return True
             if first == 192 and second == 168:
                 return True
+            if first == 100 and 64 <= second <= 127:
+                return True
         except ValueError:
             pass
     return False

agent/models_dev.py

@@ -146,6 +146,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "openai-codex": "openai",
     "zai": "zai",
     "kimi-coding": "kimi-for-coding",
+    "stepfun": "stepfun",
     "kimi-coding-cn": "kimi-for-coding",
     "minimax": "minimax",
     "minimax-cn": "minimax-cn",

agent/skill_utils.py

@@ -435,7 +435,7 @@ def iter_skill_index_files(skills_dir: Path, filename: str):
     Excludes ``.git``, ``.github``, ``.hub`` directories.
     """
     matches = []
-    for root, dirs, files in os.walk(skills_dir):
+    for root, dirs, files in os.walk(skills_dir, followlinks=True):
         dirs[:] = [d for d in dirs if d not in EXCLUDED_SKILL_DIRS]
         if filename in files:
             matches.append(Path(root) / filename)

agent/transports/anthropic.py

@@ -78,23 +78,50 @@ class AnthropicTransport(ProviderTransport):
     def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
         """Normalize Anthropic response to NormalizedResponse.
 
-        kwargs:
-            strip_tool_prefix: bool — strip 'mcp_mcp_' prefixes from tool names.
+        Calls the adapter's v1 normalize and maps the (SimpleNamespace, finish_reason)
+        tuple to the shared NormalizedResponse type.
         """
-        from agent.anthropic_adapter import normalize_anthropic_response_v2
+        from agent.anthropic_adapter import normalize_anthropic_response
+        from agent.transports.types import build_tool_call
 
         strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
-        return normalize_anthropic_response_v2(response, strip_tool_prefix=strip_tool_prefix)
+        assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
+
+        tool_calls = None
+        if assistant_msg.tool_calls:
+            tool_calls = [
+                build_tool_call(id=tc.id, name=tc.function.name, arguments=tc.function.arguments)
+                for tc in assistant_msg.tool_calls
+            ]
+
+        provider_data = {}
+        if getattr(assistant_msg, "reasoning_details", None):
+            provider_data["reasoning_details"] = assistant_msg.reasoning_details
+
+        return NormalizedResponse(
+            content=assistant_msg.content,
+            tool_calls=tool_calls,
+            finish_reason=finish_reason,
+            reasoning=getattr(assistant_msg, "reasoning", None),
+            usage=None,
+            provider_data=provider_data or None,
+        )
 
     def validate_response(self, response: Any) -> bool:
-        """Check Anthropic response structure is valid."""
+        """Check Anthropic response structure is valid.
+
+        An empty content list is legitimate when ``stop_reason == "end_turn"``
+        — the model's canonical way of signalling "nothing more to add" after
+        a tool turn that already delivered the user-facing text. Treating it
+        as invalid falsely retries a completed response.
+        """
         if response is None:
             return False
         content_blocks = getattr(response, "content", None)
         if not isinstance(content_blocks, list):
             return False
         if not content_blocks:
-            return False
+            return getattr(response, "stop_reason", None) == "end_turn"
         return True
 
     def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:

agent/usage_pricing.py

@@ -533,10 +533,22 @@ def normalize_usage(
         prompt_total = _to_int(getattr(response_usage, "prompt_tokens", 0))
         output_tokens = _to_int(getattr(response_usage, "completion_tokens", 0))
         details = getattr(response_usage, "prompt_tokens_details", None)
+        # Primary: OpenAI-style prompt_tokens_details. Fallback: Anthropic-style
+        # top-level fields that some OpenAI-compatible proxies (OpenRouter, Vercel
+        # AI Gateway, Cline) expose when routing Claude models — without this
+        # fallback, cache writes are undercounted as 0 and cache reads can be
+        # missed when the proxy only surfaces them at the top level.
+        # Port of cline/cline#10266.
         cache_read_tokens = _to_int(getattr(details, "cached_tokens", 0) if details else 0)
+        if not cache_read_tokens:
+            cache_read_tokens = _to_int(getattr(response_usage, "cache_read_input_tokens", 0))
         cache_write_tokens = _to_int(
             getattr(details, "cache_write_tokens", 0) if details else 0
         )
+        if not cache_write_tokens:
+            cache_write_tokens = _to_int(
+                getattr(response_usage, "cache_creation_input_tokens", 0)
+            )
         input_tokens = max(0, prompt_total - cache_read_tokens - cache_write_tokens)
 
     reasoning_tokens = 0

cli-config.yaml.example

@@ -776,6 +776,7 @@ delegation:
   # 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.
   # orchestrator_enabled: true                # Kill switch for role="orchestrator" children (default: true).
+  # 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)
   #                                           # Resolves full credentials (base_url, api_key) automatically.

cli.py

@@ -108,6 +108,11 @@ def _strip_reasoning_tags(text: str) -> str:
     ``<thought>`` (Gemma 4).  Must stay in sync with
     ``run_agent.py::_strip_think_blocks`` and the stream consumer's
     ``_OPEN_THINK_TAGS`` / ``_CLOSE_THINK_TAGS`` tuples.
+
+    Also strips tool-call XML blocks some open models leak into visible
+    content (``<tool_call>``, ``<function_calls>``, Gemma-style
+    ``<function name="…">…</function>``). Ported from
+    openclaw/openclaw#67318.
     """
     cleaned = text
     for tag in _REASONING_TAGS:
@@ -132,6 +137,31 @@ def _strip_reasoning_tags(text: str) -> str:
             cleaned,
             flags=re.IGNORECASE,
         )
+    # Tool-call XML blocks (openclaw/openclaw#67318).
+    for tc_tag in ("tool_call", "tool_calls", "tool_result",
+                   "function_call", "function_calls"):
+        cleaned = re.sub(
+            rf"<{tc_tag}\b[^>]*>.*?</{tc_tag}>\s*",
+            "",
+            cleaned,
+            flags=re.DOTALL | re.IGNORECASE,
+        )
+    # <function name="..."> — boundary + attribute gated to avoid prose FPs.
+    cleaned = re.sub(
+        r'(?:(?<=^)|(?<=[\n\r.!?:]))[ \t]*'
+        r'<function\b[^>]*\bname\s*=[^>]*>'
+        r'(?:(?:(?!</function>).)*)</function>\s*',
+        '',
+        cleaned,
+        flags=re.DOTALL | re.IGNORECASE,
+    )
+    # Stray tool-call close tags.
+    cleaned = re.sub(
+        r'</(?:tool_call|tool_calls|tool_result|function_call|function_calls|function)>\s*',
+        '',
+        cleaned,
+        flags=re.IGNORECASE,
+    )
     return cleaned.strip()
 
 
@@ -914,6 +944,32 @@ def _cleanup_worktree(info: Dict[str, str] = None) -> None:
     print(f"\033[32m✓ Worktree cleaned up: {wt_path}\033[0m")
 
 
+def _run_state_db_auto_maintenance(session_db) -> None:
+    """Call ``SessionDB.maybe_auto_prune_and_vacuum`` using current config.
+
+    Reads the ``sessions:`` section from config.yaml via
+    :func:`hermes_cli.config.load_config` (the authoritative loader that
+    deep-merges DEFAULT_CONFIG, so unmigrated configs still get default
+    values). Honours ``auto_prune`` / ``retention_days`` /
+    ``vacuum_after_prune`` / ``min_interval_hours``, and delegates to the
+    DB. Never raises — maintenance must never block interactive startup.
+    """
+    if session_db is None:
+        return
+    try:
+        from hermes_cli.config import load_config as _load_full_config
+        cfg = (_load_full_config().get("sessions") or {})
+        if not cfg.get("auto_prune", False):
+            return
+        session_db.maybe_auto_prune_and_vacuum(
+            retention_days=int(cfg.get("retention_days", 90)),
+            min_interval_hours=int(cfg.get("min_interval_hours", 24)),
+            vacuum=bool(cfg.get("vacuum_after_prune", True)),
+        )
+    except Exception as exc:
+        logger.debug("state.db auto-maintenance skipped: %s", exc)
+
+
 def _prune_stale_worktrees(repo_root: str, max_age_hours: int = 24) -> None:
     """Remove stale worktrees and orphaned branches on startup.
 
@@ -1961,7 +2017,13 @@ class HermesCLI:
             self._session_db = SessionDB()
         except Exception as e:
             logger.warning("Failed to initialize SessionDB — session will NOT be indexed for search: %s", e)
-        
+
+        # Opportunistic state.db maintenance — runs at most once per
+        # min_interval_hours, tracked via state_meta in state.db itself so
+        # it's shared across all Hermes processes for this HERMES_HOME.
+        # Never blocks startup on failure.
+        _run_state_db_auto_maintenance(self._session_db)
+
         # Deferred title: stored in memory until the session is created in the DB
         self._pending_title: Optional[str] = None
         

docker/entrypoint.sh

@@ -68,4 +68,19 @@ if [ -d "$INSTALL_DIR/skills" ]; then
     python3 "$INSTALL_DIR/tools/skills_sync.py"
 fi
 
+# Final exec: two supported invocation patterns.
+#
+#   docker run <image>                 -> exec `hermes` with no args (legacy default)
+#   docker run <image> chat -q "..."   -> exec `hermes chat -q "..."` (legacy wrap)
+#   docker run <image> sleep infinity  -> exec `sleep infinity` directly
+#   docker run <image> bash            -> exec `bash` directly
+#
+# If the first positional arg resolves to an executable on PATH, we assume the
+# caller wants to run it directly (needed by the launcher which runs long-lived
+# `sleep infinity` sandbox containers — see tools/environments/docker.py).
+# Otherwise we treat the args as a hermes subcommand and wrap with `hermes`,
+# preserving the documented `docker run <image> <subcommand>` behavior.
+if [ $# -gt 0 ] && command -v "$1" >/dev/null 2>&1; then
+    exec "$@"
+fi
 exec hermes "$@"

gateway/config.py

@@ -616,6 +616,8 @@ def load_gateway_config() -> GatewayConfig:
                     if isinstance(frc, list):
                         frc = ",".join(str(v) for v in frc)
                     os.environ["SLACK_FREE_RESPONSE_CHANNELS"] = str(frc)
+                if "reactions" in slack_cfg and not os.getenv("SLACK_REACTIONS"):
+                    os.environ["SLACK_REACTIONS"] = str(slack_cfg["reactions"]).lower()
 
             # Discord settings → env vars (env vars take precedence)
             discord_cfg = yaml_cfg.get("discord", {})

gateway/hooks.py

@@ -135,9 +135,22 @@ class HookRegistry:
             except Exception as e:
                 print(f"[hooks] Error loading hook {hook_dir.name}: {e}", flush=True)
 
+    def _resolve_handlers(self, event_type: str) -> List[Callable]:
+        """Return all handlers that should fire for ``event_type``.
+
+        Exact matches fire first, followed by wildcard matches (e.g.
+        ``command:*`` matches ``command:reset``).
+        """
+        handlers = list(self._handlers.get(event_type, []))
+        if ":" in event_type:
+            base = event_type.split(":")[0]
+            wildcard_key = f"{base}:*"
+            handlers.extend(self._handlers.get(wildcard_key, []))
+        return handlers
+
     async def emit(self, event_type: str, context: Optional[Dict[str, Any]] = None) -> None:
         """
-        Fire all handlers registered for an event.
+        Fire all handlers registered for an event, discarding return values.
 
         Supports wildcard matching: handlers registered for "command:*" will
         fire for any "command:..." event. Handlers registered for a base type
@@ -151,16 +164,7 @@ class HookRegistry:
         if context is None:
             context = {}
 
-        # Collect handlers: exact match + wildcard match
-        handlers = list(self._handlers.get(event_type, []))
-
-        # Check for wildcard patterns (e.g., "command:*" matches "command:reset")
-        if ":" in event_type:
-            base = event_type.split(":")[0]
-            wildcard_key = f"{base}:*"
-            handlers.extend(self._handlers.get(wildcard_key, []))
-
-        for fn in handlers:
+        for fn in self._resolve_handlers(event_type):
             try:
                 result = fn(event_type, context)
                 # Support both sync and async handlers
@@ -168,3 +172,32 @@ class HookRegistry:
                     await result
             except Exception as e:
                 print(f"[hooks] Error in handler for '{event_type}': {e}", flush=True)
+
+    async def emit_collect(
+        self,
+        event_type: str,
+        context: Optional[Dict[str, Any]] = None,
+    ) -> List[Any]:
+        """Fire handlers and return their non-None return values in order.
+
+        Like :meth:`emit` but captures each handler's return value. Used for
+        decision-style hooks (e.g. ``command:<name>`` policies that want to
+        allow/deny/rewrite the command before normal dispatch).
+
+        Exceptions from individual handlers are logged but do not abort the
+        remaining handlers.
+        """
+        if context is None:
+            context = {}
+
+        results: List[Any] = []
+        for fn in self._resolve_handlers(event_type):
+            try:
+                result = fn(event_type, context)
+                if asyncio.iscoroutine(result):
+                    result = await result
+                if result is not None:
+                    results.append(result)
+            except Exception as e:
+                print(f"[hooks] Error in handler for '{event_type}': {e}", flush=True)
+        return results

gateway/platforms/discord.py

@@ -2129,10 +2129,42 @@ class DiscordAdapter(BasePlatformAdapter):
         # This ensures new commands added to COMMAND_REGISTRY in
         # hermes_cli/commands.py automatically appear as Discord slash
         # commands without needing a manual entry here.
+        def _build_auto_slash_command(_name: str, _description: str, _args_hint: str = ""):
+            """Build a discord.app_commands.Command that proxies to _run_simple_slash."""
+            discord_name = _name.lower()[:32]
+            desc = (_description or f"Run /{_name}")[:100]
+            has_args = bool(_args_hint)
+
+            if has_args:
+                def _make_args_handler(__name: str, __hint: str):
+                    @discord.app_commands.describe(args=f"Arguments: {__hint}"[:100])
+                    async def _handler(interaction: discord.Interaction, args: str = ""):
+                        await self._run_simple_slash(
+                            interaction, f"/{__name} {args}".strip()
+                        )
+                    _handler.__name__ = f"auto_slash_{__name.replace('-', '_')}"
+                    return _handler
+
+                handler = _make_args_handler(_name, _args_hint)
+            else:
+                def _make_simple_handler(__name: str):
+                    async def _handler(interaction: discord.Interaction):
+                        await self._run_simple_slash(interaction, f"/{__name}")
+                    _handler.__name__ = f"auto_slash_{__name.replace('-', '_')}"
+                    return _handler
+
+                handler = _make_simple_handler(_name)
+
+            return discord.app_commands.Command(
+                name=discord_name,
+                description=desc,
+                callback=handler,
+            )
+
+        already_registered: set[str] = set()
         try:
             from hermes_cli.commands import COMMAND_REGISTRY, _is_gateway_available, _resolve_config_gates
 
-            already_registered = set()
             try:
                 already_registered = {cmd.name for cmd in tree.get_commands()}
             except Exception:
@@ -2147,38 +2179,10 @@ class DiscordAdapter(BasePlatformAdapter):
                 discord_name = cmd_def.name.lower()[:32]
                 if discord_name in already_registered:
                     continue
-                # Skip aliases that overlap with already-registered names
-                # (aliases for explicitly registered commands are handled above).
-                desc = (cmd_def.description or f"Run /{cmd_def.name}")[:100]
-                has_args = bool(cmd_def.args_hint)
-
-                if has_args:
-                    # Command takes optional arguments — create handler with
-                    # an optional ``args`` string parameter.
-                    def _make_args_handler(_name: str, _hint: str):
-                        @discord.app_commands.describe(args=f"Arguments: {_hint}"[:100])
-                        async def _handler(interaction: discord.Interaction, args: str = ""):
-                            await self._run_simple_slash(
-                                interaction, f"/{_name} {args}".strip()
-                            )
-                        _handler.__name__ = f"auto_slash_{_name.replace('-', '_')}"
-                        return _handler
-
-                    handler = _make_args_handler(cmd_def.name, cmd_def.args_hint)
-                else:
-                    # Parameterless command.
-                    def _make_simple_handler(_name: str):
-                        async def _handler(interaction: discord.Interaction):
-                            await self._run_simple_slash(interaction, f"/{_name}")
-                        _handler.__name__ = f"auto_slash_{_name.replace('-', '_')}"
-                        return _handler
-
-                    handler = _make_simple_handler(cmd_def.name)
-
-                auto_cmd = discord.app_commands.Command(
-                    name=discord_name,
-                    description=desc,
-                    callback=handler,
+                auto_cmd = _build_auto_slash_command(
+                    cmd_def.name,
+                    cmd_def.description,
+                    cmd_def.args_hint,
                 )
                 try:
                     tree.add_command(auto_cmd)
@@ -2195,6 +2199,35 @@ class DiscordAdapter(BasePlatformAdapter):
         except Exception as e:
             logger.warning("Discord auto-register from COMMAND_REGISTRY failed: %s", e)
 
+        # ── Plugin-registered slash commands ──
+        # Plugins register via PluginContext.register_command(); we mirror
+        # those into Discord's native slash picker so users get the same
+        # autocomplete UX as for built-in commands. No per-platform plugin
+        # API needed — plugin commands are platform-agnostic.
+        try:
+            from hermes_cli.commands import _iter_plugin_command_entries
+
+            for plugin_name, plugin_desc, plugin_args_hint in _iter_plugin_command_entries():
+                discord_name = plugin_name.lower()[:32]
+                if discord_name in already_registered:
+                    continue
+                auto_cmd = _build_auto_slash_command(
+                    plugin_name,
+                    plugin_desc,
+                    plugin_args_hint,
+                )
+                try:
+                    tree.add_command(auto_cmd)
+                    already_registered.add(discord_name)
+                except Exception:
+                    # Silently skip commands that fail registration (e.g.
+                    # name conflict with a subcommand group).
+                    pass
+        except Exception as e:
+            logger.warning(
+                "Discord auto-register from plugin commands failed: %s", e
+            )
+
         # Register skills under a single /skill command group with category
         # subcommand groups.  This uses 1 top-level slot instead of N,
         # supporting up to 25 categories × 25 skills = 625 skills.

gateway/platforms/email.py

@@ -545,6 +545,7 @@ class EmailAdapter(BasePlatformAdapter):
         caption: Optional[str] = None,
         file_name: Optional[str] = None,
         reply_to: Optional[str] = None,
+        **kwargs,
     ) -> SendResult:
         """Send a file as an email attachment."""
         try:

gateway/platforms/feishu.py

@@ -14,6 +14,35 @@ Supports:
 - Interactive card button-click events routed as synthetic COMMAND events
 - Webhook anomaly tracking (matches openclaw createWebhookAnomalyTracker)
 - Verification token validation as second auth layer (matches openclaw)
+
+Feishu identity model
+---------------------
+Feishu uses three user-ID tiers (official docs:
+https://open.feishu.cn/document/home/user-identity-introduction/introduction):
+
+  open_id  (ou_xxx)  — **App-scoped**.  The same person gets a different
+                        open_id under each Feishu app.  Always available in
+                        event payloads without extra permissions.
+  user_id  (u_xxx)   — **Tenant-scoped**.  Stable within a company but
+                        requires the ``contact:user.employee_id:readonly``
+                        scope.  May not be present.
+  union_id (on_xxx)  — **Developer-scoped**.  Same across all apps owned by
+                        one developer/ISV.  Best cross-app stable ID.
+
+For bots specifically:
+
+  app_id              — The application's canonical credential identifier.
+  bot open_id         — Returned by ``/bot/v3/info``.  This is the bot's own
+                        open_id *within its app context* and is what Feishu
+                        puts in ``mentions[].id.open_id`` when someone
+                        @-mentions the bot.  Used for mention gating only.
+
+In single-bot mode (what Hermes currently supports), open_id works as a
+de-facto unique user identifier since there is only one app context.
+
+Session-key participant isolation prefers ``union_id`` (via user_id_alt)
+over ``open_id`` (via user_id) so that sessions stay stable if the same
+user is seen through different apps in the future.
 """
 
 from __future__ import annotations
@@ -35,7 +64,7 @@ from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 from types import SimpleNamespace
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Sequence
 from urllib.error import HTTPError, URLError
 from urllib.parse import urlencode
 from urllib.request import Request, urlopen
@@ -73,7 +102,9 @@ try:
         UpdateMessageRequest,
         UpdateMessageRequestBody,
     )
+    from lark_oapi.core import AccessTokenType, HttpMethod
     from lark_oapi.core.const import FEISHU_DOMAIN, LARK_DOMAIN
+    from lark_oapi.core.model import BaseRequest
     from lark_oapi.event.callback.model.p2_card_action_trigger import (
         CallBackCard,
         P2CardActionTriggerResponse,
@@ -234,6 +265,8 @@ FALLBACK_ATTACHMENT_TEXT = "[Attachment]"
 _PREFERRED_LOCALES = ("zh_cn", "en_us")
 _MARKDOWN_SPECIAL_CHARS_RE = re.compile(r"([\\`*_{}\[\]()#+\-!|>~])")
 _MENTION_PLACEHOLDER_RE = re.compile(r"@_user_\d+")
+_MENTION_BOUNDARY_CHARS = frozenset(" \t\n\r.,;:!?、，。；：！？()[]{}<>\"'`")
+_TRAILING_TERMINAL_PUNCT = frozenset(" \t\n\r.!?。！？")
 _WHITESPACE_RE = re.compile(r"\s+")
 _SUPPORTED_CARD_TEXT_KEYS = (
     "title",
@@ -277,12 +310,36 @@ class FeishuPostMediaRef:
     resource_type: str = "file"
 
 
+@dataclass(frozen=True)
+class FeishuMentionRef:
+    name: str = ""
+    open_id: str = ""
+    is_all: bool = False
+    is_self: bool = False
+
+
+@dataclass(frozen=True)
+class _FeishuBotIdentity:
+    open_id: str = ""
+    user_id: str = ""
+    name: str = ""
+
+    def matches(self, *, open_id: str, user_id: str, name: str) -> bool:
+        # Precedence: open_id > user_id > name. IDs are authoritative when both
+        # sides have them; the next tier is only considered when either side
+        # lacks the current one.
+        if open_id and self.open_id:
+            return open_id == self.open_id
+        if user_id and self.user_id:
+            return user_id == self.user_id
+        return bool(self.name) and name == self.name
+
+
 @dataclass(frozen=True)
 class FeishuPostParseResult:
     text_content: str
     image_keys: List[str] = field(default_factory=list)
     media_refs: List[FeishuPostMediaRef] = field(default_factory=list)
-    mentioned_ids: List[str] = field(default_factory=list)
 
 
 @dataclass(frozen=True)
@@ -292,14 +349,14 @@ class FeishuNormalizedMessage:
     preferred_message_type: str = "text"
     image_keys: List[str] = field(default_factory=list)
     media_refs: List[FeishuPostMediaRef] = field(default_factory=list)
-    mentioned_ids: List[str] = field(default_factory=list)
+    mentions: List[FeishuMentionRef] = field(default_factory=list)
     relation_kind: str = "plain"
     metadata: Dict[str, Any] = field(default_factory=dict)
 
 
 @dataclass(frozen=True)
 class FeishuAdapterSettings:
-    app_id: str
+    app_id: str  # Canonical bot/app identifier (credential, not from event payloads)
     app_secret: str
     domain_name: str
     connection_mode: str
@@ -307,7 +364,11 @@ class FeishuAdapterSettings:
     verification_token: str
     group_policy: str
     allowed_group_users: frozenset[str]
+    # Bot's own open_id (app-scoped) — returned by /bot/v3/info.  Used only for
+    # @mention matching: Feishu puts this value in mentions[].id.open_id when
+    # a user @-mentions the bot in a group chat.
     bot_open_id: str
+    # Bot's user_id (tenant-scoped) — optional, used as fallback mention match.
     bot_user_id: str
     bot_name: str
     dedup_cache_size: int
@@ -505,14 +566,17 @@ def _build_markdown_post_rows(content: str) -> List[List[Dict[str, str]]]:
     return rows or [[{"tag": "md", "text": content}]]
 
 
-def parse_feishu_post_payload(payload: Any) -> FeishuPostParseResult:
+def parse_feishu_post_payload(
+    payload: Any,
+    *,
+    mentions_map: Optional[Dict[str, FeishuMentionRef]] = None,
+) -> FeishuPostParseResult:
     resolved = _resolve_post_payload(payload)
     if not resolved:
         return FeishuPostParseResult(text_content=FALLBACK_POST_TEXT)
 
     image_keys: List[str] = []
     media_refs: List[FeishuPostMediaRef] = []
-    mentioned_ids: List[str] = []
     parts: List[str] = []
 
     title = _normalize_feishu_text(str(resolved.get("title", "")).strip())
@@ -523,7 +587,10 @@ def parse_feishu_post_payload(payload: Any) -> FeishuPostParseResult:
         if not isinstance(row, list):
             continue
         row_text = _normalize_feishu_text(
-            "".join(_render_post_element(item, image_keys, media_refs, mentioned_ids) for item in row)
+            "".join(
+                _render_post_element(item, image_keys, media_refs, mentions_map)
+                for item in row
+            )
         )
         if row_text:
             parts.append(row_text)
@@ -532,7 +599,6 @@ def parse_feishu_post_payload(payload: Any) -> FeishuPostParseResult:
         text_content="\n".join(parts).strip() or FALLBACK_POST_TEXT,
         image_keys=image_keys,
         media_refs=media_refs,
-        mentioned_ids=mentioned_ids,
     )
 
 
@@ -584,7 +650,7 @@ def _render_post_element(
     element: Any,
     image_keys: List[str],
     media_refs: List[FeishuPostMediaRef],
-    mentioned_ids: List[str],
+    mentions_map: Optional[Dict[str, FeishuMentionRef]] = None,
 ) -> str:
     if isinstance(element, str):
         return element
@@ -602,19 +668,21 @@ def _render_post_element(
         escaped_label = _escape_markdown_text(label)
         return f"[{escaped_label}]({href})" if href else escaped_label
     if tag == "at":
-        mentioned_id = (
-            str(element.get("open_id", "")).strip()
-            or str(element.get("user_id", "")).strip()
-        )
-        if mentioned_id and mentioned_id not in mentioned_ids:
-            mentioned_ids.append(mentioned_id)
-        display_name = (
-            str(element.get("user_name", "")).strip()
-            or str(element.get("name", "")).strip()
-            or str(element.get("text", "")).strip()
-            or mentioned_id
-        )
-        return f"@{_escape_markdown_text(display_name)}" if display_name else "@"
+        # Post <at>.user_id is a placeholder ("@_user_N" or "@_all"); look up
+        # the real ref in mentions_map for the display name.
+        placeholder = str(element.get("user_id", "")).strip()
+        if placeholder == "@_all":
+            # Feishu SDK sometimes omits @_all from the top-level mentions
+            # payload; record it here so the caller's mention list stays complete.
+            if mentions_map is not None and "@_all" not in mentions_map:
+                mentions_map["@_all"] = FeishuMentionRef(is_all=True)
+            return "@all"
+        ref = (mentions_map or {}).get(placeholder)
+        if ref is not None:
+            display_name = ref.name or ref.open_id or "user"
+        else:
+            display_name = str(element.get("user_name", "")).strip() or "user"
+        return f"@{_escape_markdown_text(display_name)}"
     if tag in {"img", "image"}:
         image_key = str(element.get("image_key", "")).strip()
         if image_key and image_key not in image_keys:
@@ -652,8 +720,7 @@ def _render_post_element(
 
     nested_parts: List[str] = []
     for key in ("text", "title", "content", "children", "elements"):
-        value = element.get(key)
-        extracted = _render_nested_post(value, image_keys, media_refs, mentioned_ids)
+        extracted = _render_nested_post(element.get(key), image_keys, media_refs, mentions_map)
         if extracted:
             nested_parts.append(extracted)
     return " ".join(part for part in nested_parts if part)
@@ -663,7 +730,7 @@ def _render_nested_post(
     value: Any,
     image_keys: List[str],
     media_refs: List[FeishuPostMediaRef],
-    mentioned_ids: List[str],
+    mentions_map: Optional[Dict[str, FeishuMentionRef]] = None,
 ) -> str:
     if isinstance(value, str):
         return _escape_markdown_text(value)
@@ -671,17 +738,17 @@ def _render_nested_post(
         return " ".join(
             part
             for item in value
-            for part in [_render_nested_post(item, image_keys, media_refs, mentioned_ids)]
+            for part in [_render_nested_post(item, image_keys, media_refs, mentions_map)]
             if part
         )
     if isinstance(value, dict):
-        direct = _render_post_element(value, image_keys, media_refs, mentioned_ids)
+        direct = _render_post_element(value, image_keys, media_refs, mentions_map)
         if direct:
             return direct
         return " ".join(
             part
             for item in value.values()
-            for part in [_render_nested_post(item, image_keys, media_refs, mentioned_ids)]
+            for part in [_render_nested_post(item, image_keys, media_refs, mentions_map)]
             if part
         )
     return ""
@@ -692,31 +759,48 @@ def _render_nested_post(
 # ---------------------------------------------------------------------------
 
 
-def normalize_feishu_message(*, message_type: str, raw_content: str) -> FeishuNormalizedMessage:
+def normalize_feishu_message(
+    *,
+    message_type: str,
+    raw_content: str,
+    mentions: Optional[Sequence[Any]] = None,
+    bot: _FeishuBotIdentity = _FeishuBotIdentity(),
+) -> FeishuNormalizedMessage:
     normalized_type = str(message_type or "").strip().lower()
     payload = _load_feishu_payload(raw_content)
+    mentions_map = _build_mentions_map(mentions, bot)
 
     if normalized_type == "text":
+        text = str(payload.get("text", "") or "")
+        # Feishu SDK sometimes omits @_all from the mentions payload even when
+        # the text literal contains it (confirmed via im.v1.message.get).
+        if "@_all" in text and "@_all" not in mentions_map:
+            mentions_map["@_all"] = FeishuMentionRef(is_all=True)
         return FeishuNormalizedMessage(
             raw_type=normalized_type,
-            text_content=_normalize_feishu_text(str(payload.get("text", "") or "")),
+            text_content=_normalize_feishu_text(text, mentions_map),
+            mentions=list(mentions_map.values()),
         )
     if normalized_type == "post":
-        parsed_post = parse_feishu_post_payload(payload)
+        # The walker writes back to mentions_map if it encounters
+        # <at user_id="@_all">, so reading .values() after parsing is enough.
+        parsed_post = parse_feishu_post_payload(payload, mentions_map=mentions_map)
         return FeishuNormalizedMessage(
             raw_type=normalized_type,
             text_content=parsed_post.text_content,
             image_keys=list(parsed_post.image_keys),
             media_refs=list(parsed_post.media_refs),
-            mentioned_ids=list(parsed_post.mentioned_ids),
+            mentions=list(mentions_map.values()),
             relation_kind="post",
         )
+    mention_refs = list(mentions_map.values())
     if normalized_type == "image":
         image_key = str(payload.get("image_key", "") or "").strip()
         alt_text = _normalize_feishu_text(
             str(payload.get("text", "") or "")
             or str(payload.get("alt", "") or "")
-            or FALLBACK_IMAGE_TEXT
+            or FALLBACK_IMAGE_TEXT,
+            mentions_map,
         )
         return FeishuNormalizedMessage(
             raw_type=normalized_type,
@@ -724,6 +808,7 @@ def normalize_feishu_message(*, message_type: str, raw_content: str) -> FeishuNo
             preferred_message_type="photo",
             image_keys=[image_key] if image_key else [],
             relation_kind="image",
+            mentions=mention_refs,
         )
     if normalized_type in {"file", "audio", "media"}:
         media_ref = _build_media_ref_from_payload(payload, resource_type=normalized_type)
@@ -735,6 +820,7 @@ def normalize_feishu_message(*, message_type: str, raw_content: str) -> FeishuNo
             media_refs=[media_ref] if media_ref.file_key else [],
             relation_kind=normalized_type,
             metadata={"placeholder_text": placeholder},
+            mentions=mention_refs,
         )
     if normalized_type == "merge_forward":
         return _normalize_merge_forward_message(payload)
@@ -1009,8 +1095,20 @@ def _first_non_empty_text(*values: Any) -> str:
 # ---------------------------------------------------------------------------
 
 
-def _normalize_feishu_text(text: str) -> str:
-    cleaned = _MENTION_PLACEHOLDER_RE.sub(" ", text or "")
+def _normalize_feishu_text(
+    text: str,
+    mentions_map: Optional[Dict[str, FeishuMentionRef]] = None,
+) -> str:
+    def _sub(match: "re.Match[str]") -> str:
+        key = match.group(0)
+        ref = (mentions_map or {}).get(key)
+        if ref is None:
+            return " "
+        name = ref.name or ref.open_id or "user"
+        return f"@{name}"
+
+    cleaned = _MENTION_PLACEHOLDER_RE.sub(_sub, text or "")
+    cleaned = cleaned.replace("@_all", "@all")
     cleaned = cleaned.replace("\r\n", "\n").replace("\r", "\n")
     cleaned = "\n".join(_WHITESPACE_RE.sub(" ", line).strip() for line in cleaned.split("\n"))
     cleaned = "\n".join(line for line in cleaned.split("\n") if line)
@@ -1029,6 +1127,117 @@ def _unique_lines(lines: List[str]) -> List[str]:
     return unique
 
 
+# ---------------------------------------------------------------------------
+# Mention helpers
+# ---------------------------------------------------------------------------
+
+
+def _extract_mention_ids(mention: Any) -> tuple[str, str]:
+    # Returns (open_id, user_id). im.v1.message.get hands back id as a string
+    # plus id_type discriminator; event payloads hand back a nested UserId
+    # object carrying both fields.
+    mention_id = getattr(mention, "id", None)
+    if isinstance(mention_id, str):
+        id_type = str(getattr(mention, "id_type", "") or "").lower()
+        if id_type == "open_id":
+            return mention_id, ""
+        if id_type == "user_id":
+            return "", mention_id
+        return "", ""
+    if mention_id is None:
+        return "", ""
+    return (
+        str(getattr(mention_id, "open_id", "") or ""),
+        str(getattr(mention_id, "user_id", "") or ""),
+    )
+
+
+def _build_mentions_map(
+    mentions: Optional[Sequence[Any]],
+    bot: _FeishuBotIdentity,
+) -> Dict[str, FeishuMentionRef]:
+    result: Dict[str, FeishuMentionRef] = {}
+    for mention in mentions or []:
+        key = str(getattr(mention, "key", "") or "")
+        if not key:
+            continue
+        if key == "@_all":
+            result[key] = FeishuMentionRef(is_all=True)
+            continue
+        open_id, user_id = _extract_mention_ids(mention)
+        name = str(getattr(mention, "name", "") or "").strip()
+        result[key] = FeishuMentionRef(
+            name=name,
+            open_id=open_id,
+            is_self=bot.matches(open_id=open_id, user_id=user_id, name=name),
+        )
+    return result
+
+
+def _build_mention_hint(mentions: Sequence[FeishuMentionRef]) -> str:
+    parts: List[str] = []
+    seen: set = set()
+    for ref in mentions:
+        if ref.is_self:
+            continue
+        signature = (ref.is_all, ref.open_id, ref.name)
+        if signature in seen:
+            continue
+        seen.add(signature)
+        if ref.is_all:
+            parts.append("@all")
+        elif ref.open_id:
+            parts.append(f"{ref.name or 'unknown'} (open_id={ref.open_id})")
+        else:
+            parts.append(ref.name or "unknown")
+    return f"[Mentioned: {', '.join(parts)}]" if parts else ""
+
+
+def _strip_edge_self_mentions(
+    text: str,
+    mentions: Sequence[FeishuMentionRef],
+) -> str:
+    # Leading: strip consecutive self-mentions unconditionally.
+    # Trailing: strip only when followed by whitespace/terminal punct, so
+    # mid-sentence references ("don't @Bot again") stay intact.
+    # Leading word-boundary prevents @Al from eating @Alice.
+    if not text:
+        return text
+    self_names = [
+        f"@{ref.name or ref.open_id or 'user'}"
+        for ref in mentions
+        if ref.is_self
+    ]
+    if not self_names:
+        return text
+
+    remaining = text.lstrip()
+    while True:
+        for nm in self_names:
+            if not remaining.startswith(nm):
+                continue
+            after = remaining[len(nm):]
+            if after and after[0] not in _MENTION_BOUNDARY_CHARS:
+                continue
+            remaining = after.lstrip()
+            break
+        else:
+            break
+
+    while True:
+        i = len(remaining)
+        while i > 0 and remaining[i - 1] in _TRAILING_TERMINAL_PUNCT:
+            i -= 1
+        body = remaining[:i]
+        tail = remaining[i:]
+        for nm in self_names:
+            if body.endswith(nm):
+                remaining = body[: -len(nm)].rstrip() + tail
+                break
+        else:
+            return remaining
+
+
 def _run_official_feishu_ws_client(ws_client: Any, adapter: Any) -> None:
     """Run the official Lark WS client in its own thread-local event loop."""
     import lark_oapi.ws.client as ws_client_module
@@ -2470,13 +2679,22 @@ class FeishuAdapter(BasePlatformAdapter):
         chat_type: str,
         message_id: str,
     ) -> None:
-        text, inbound_type, media_urls, media_types = await self._extract_message_content(message)
+        text, inbound_type, media_urls, media_types, mentions = await self._extract_message_content(message)
+
+        if inbound_type == MessageType.TEXT:
+            text = _strip_edge_self_mentions(text, mentions)
+            if text.startswith("/"):
+                inbound_type = MessageType.COMMAND
+
+        # Guard runs post-strip so a pure "@Bot" message (stripped to "") is dropped.
         if inbound_type == MessageType.TEXT and not text and not media_urls:
-            logger.debug("[Feishu] Ignoring unsupported or empty message type: %s", getattr(message, "message_type", ""))
+            logger.debug("[Feishu] Ignoring empty text message id=%s", message_id)
             return
 
-        if inbound_type == MessageType.TEXT and text.startswith("/"):
-            inbound_type = MessageType.COMMAND
+        if inbound_type != MessageType.COMMAND:
+            hint = _build_mention_hint(mentions)
+            if hint:
+                text = f"{hint}\n\n{text}" if text else hint
 
         reply_to_message_id = (
             getattr(message, "parent_id", None)
@@ -2935,14 +3153,20 @@ class FeishuAdapter(BasePlatformAdapter):
     # Message content extraction and resource download
     # =========================================================================
 
-    async def _extract_message_content(self, message: Any) -> tuple[str, MessageType, List[str], List[str]]:
-        """Extract text and cached media from a normalized Feishu message."""
+    async def _extract_message_content(
+        self, message: Any
+    ) -> tuple[str, MessageType, List[str], List[str], List[FeishuMentionRef]]:
         raw_content = getattr(message, "content", "") or ""
         raw_type = getattr(message, "message_type", "") or ""
         message_id = str(getattr(message, "message_id", "") or "")
         logger.info("[Feishu] Received raw message type=%s message_id=%s", raw_type, message_id)
 
-        normalized = normalize_feishu_message(message_type=raw_type, raw_content=raw_content)
+        normalized = normalize_feishu_message(
+            message_type=raw_type,
+            raw_content=raw_content,
+            mentions=getattr(message, "mentions", None),
+            bot=self._bot_identity(),
+        )
         media_urls, media_types = await self._download_feishu_message_resources(
             message_id=message_id,
             normalized=normalized,
@@ -2959,7 +3183,7 @@ class FeishuAdapter(BasePlatformAdapter):
             if injected:
                 text = injected
 
-        return text, inbound_type, media_urls, media_types
+        return text, inbound_type, media_urls, media_types, list(normalized.mentions)
 
     async def _download_feishu_message_resources(
         self,
@@ -3223,10 +3447,22 @@ class FeishuAdapter(BasePlatformAdapter):
         return "group"
 
     async def _resolve_sender_profile(self, sender_id: Any) -> Dict[str, Optional[str]]:
+        """Map Feishu's three-tier user IDs onto Hermes' SessionSource fields.
+
+        Preference order for the primary ``user_id`` field:
+          1. user_id  (tenant-scoped, most stable — requires permission scope)
+          2. open_id  (app-scoped, always available — different per bot app)
+
+        ``user_id_alt`` carries the union_id (developer-scoped, stable across
+        all apps by the same developer).  Session-key generation prefers
+        user_id_alt when present, so participant isolation stays stable even
+        if the primary ID is the app-scoped open_id.
+        """
         open_id = getattr(sender_id, "open_id", None) or None
         user_id = getattr(sender_id, "user_id", None) or None
         union_id = getattr(sender_id, "union_id", None) or None
-        primary_id = open_id or user_id
+        # Prefer tenant-scoped user_id; fall back to app-scoped open_id.
+        primary_id = user_id or open_id
         display_name = await self._resolve_sender_name_from_api(primary_id or union_id)
         return {
             "user_id": primary_id,
@@ -3308,15 +3544,31 @@ class FeishuAdapter(BasePlatformAdapter):
             body = getattr(parent, "body", None)
             msg_type = getattr(parent, "msg_type", "") or ""
             raw_content = getattr(body, "content", "") or ""
-            text = self._extract_text_from_raw_content(msg_type=msg_type, raw_content=raw_content)
+            parent_mentions = getattr(parent, "mentions", None) if parent else None
+            text = self._extract_text_from_raw_content(
+                msg_type=msg_type,
+                raw_content=raw_content,
+                mentions=parent_mentions,
+            )
             self._message_text_cache[message_id] = text
             return text
         except Exception:
             logger.warning("[Feishu] Failed to fetch parent message %s", message_id, exc_info=True)
             return None
 
-    def _extract_text_from_raw_content(self, *, msg_type: str, raw_content: str) -> Optional[str]:
-        normalized = normalize_feishu_message(message_type=msg_type, raw_content=raw_content)
+    def _extract_text_from_raw_content(
+        self,
+        *,
+        msg_type: str,
+        raw_content: str,
+        mentions: Optional[Sequence[Any]] = None,
+    ) -> Optional[str]:
+        normalized = normalize_feishu_message(
+            message_type=msg_type,
+            raw_content=raw_content,
+            mentions=mentions,
+            bot=self._bot_identity(),
+        )
         if normalized.text_content:
             return normalized.text_content
         placeholder = normalized.metadata.get("placeholder_text") if isinstance(normalized.metadata, dict) else None
@@ -3386,10 +3638,10 @@ class FeishuAdapter(BasePlatformAdapter):
         normalized = normalize_feishu_message(
             message_type=getattr(message, "message_type", "") or "",
             raw_content=raw_content,
+            mentions=getattr(message, "mentions", None),
+            bot=self._bot_identity(),
         )
-        if normalized.mentioned_ids:
-            return self._post_mentions_bot(normalized.mentioned_ids)
-        return False
+        return self._post_mentions_bot(normalized.mentions)
 
     def _is_self_sent_bot_message(self, event: Any) -> bool:
         """Return True only for Feishu events emitted by this Hermes bot."""
@@ -3409,30 +3661,37 @@ class FeishuAdapter(BasePlatformAdapter):
         return False
 
     def _message_mentions_bot(self, mentions: List[Any]) -> bool:
-        """Check whether any mention targets the configured or inferred bot identity."""
+        # IDs trump names: when both sides have open_id (or both user_id),
+        # match requires equal IDs. Name fallback only when either side
+        # lacks an ID.
         for mention in mentions:
             mention_id = getattr(mention, "id", None)
-            mention_open_id = getattr(mention_id, "open_id", None)
-            mention_user_id = getattr(mention_id, "user_id", None)
+            mention_open_id = (getattr(mention_id, "open_id", None) or "").strip()
+            mention_user_id = (getattr(mention_id, "user_id", None) or "").strip()
             mention_name = (getattr(mention, "name", None) or "").strip()
 
-            if self._bot_open_id and mention_open_id == self._bot_open_id:
-                return True
-            if self._bot_user_id and mention_user_id == self._bot_user_id:
-                return True
+            if mention_open_id and self._bot_open_id:
+                if mention_open_id == self._bot_open_id:
+                    return True
+                continue  # IDs differ — not the bot; skip name fallback.
+            if mention_user_id and self._bot_user_id:
+                if mention_user_id == self._bot_user_id:
+                    return True
+                continue
             if self._bot_name and mention_name == self._bot_name:
                 return True
 
         return False
 
-    def _post_mentions_bot(self, mentioned_ids: List[str]) -> bool:
-        if not mentioned_ids:
-            return False
-        if self._bot_open_id and self._bot_open_id in mentioned_ids:
-            return True
-        if self._bot_user_id and self._bot_user_id in mentioned_ids:
-            return True
-        return False
+    def _post_mentions_bot(self, mentions: List[FeishuMentionRef]) -> bool:
+        return any(m.is_self for m in mentions)
+
+    def _bot_identity(self) -> _FeishuBotIdentity:
+        return _FeishuBotIdentity(
+            open_id=self._bot_open_id,
+            user_id=self._bot_user_id,
+            name=self._bot_name,
+        )
 
     async def _hydrate_bot_identity(self) -> None:
         """Best-effort discovery of bot identity for precise group mention gating
@@ -3457,14 +3716,15 @@ class FeishuAdapter(BasePlatformAdapter):
         # uses via probe_bot().
         if not self._bot_open_id or not self._bot_name:
             try:
-                resp = await asyncio.to_thread(
-                    self._client.request,
-                    method="GET",
-                    url="/open-apis/bot/v3/info",
-                    body=None,
-                    raw_response=True,
+                req = (
+                    BaseRequest.builder()
+                    .http_method(HttpMethod.GET)
+                    .uri("/open-apis/bot/v3/info")
+                    .token_types({AccessTokenType.TENANT})
+                    .build()
                 )
-                content = getattr(resp, "content", None)
+                resp = await asyncio.to_thread(self._client.request, req)
+                content = getattr(getattr(resp, "raw", None), "content", None)
                 if content:
                     payload = json.loads(content)
                     parsed = _parse_bot_response(payload) or {}
@@ -4212,6 +4472,9 @@ def probe_bot(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
 
     Uses lark_oapi SDK when available, falls back to raw HTTP otherwise.
     Returns {"bot_name": ..., "bot_open_id": ...} on success, None on failure.
+
+    Note: ``bot_open_id`` here is the bot's app-scoped open_id — the same ID
+    that Feishu puts in @mention payloads.  It is NOT the app_id.
     """
     if FEISHU_AVAILABLE:
         return _probe_bot_sdk(app_id, app_secret, domain)
@@ -4232,12 +4495,12 @@ def _build_onboard_client(app_id: str, app_secret: str, domain: str) -> Any:
 
 
 def _parse_bot_response(data: dict) -> Optional[dict]:
-    """Extract bot_name and bot_open_id from a /bot/v3/info response."""
+    # /bot/v3/info returns bot.app_name; legacy paths used bot_name — accept both.
     if data.get("code") != 0:
         return None
     bot = data.get("bot") or data.get("data", {}).get("bot") or {}
     return {
-        "bot_name": bot.get("bot_name"),
+        "bot_name": bot.get("app_name") or bot.get("bot_name"),
         "bot_open_id": bot.get("open_id"),
     }
 
@@ -4246,13 +4509,18 @@ def _probe_bot_sdk(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
     """Probe bot info using lark_oapi SDK."""
     try:
         client = _build_onboard_client(app_id, app_secret, domain)
-        resp = client.request(
-            method="GET",
-            url="/open-apis/bot/v3/info",
-            body=None,
-            raw_response=True,
+        req = (
+            BaseRequest.builder()
+            .http_method(HttpMethod.GET)
+            .uri("/open-apis/bot/v3/info")
+            .token_types({AccessTokenType.TENANT})
+            .build()
         )
-        return _parse_bot_response(json.loads(resp.content))
+        resp = client.request(req)
+        content = getattr(getattr(resp, "raw", None), "content", None)
+        if content is None:
+            return None
+        return _parse_bot_response(json.loads(content))
     except Exception as exc:
         logger.debug("[Feishu onboard] SDK probe failed: %s", exc)
         return None

gateway/platforms/qqbot/__init__.py

@@ -26,9 +26,8 @@ from .adapter import (  # noqa: F401
 # -- Onboard (QR-code scan-to-configure) -----------------------------------
 from .onboard import (  # noqa: F401
     BindStatus,
-    create_bind_task,
-    poll_bind_result,
     build_connect_url,
+    qr_register,
 )
 from .crypto import decrypt_secret, generate_bind_key  # noqa: F401
 
@@ -44,9 +43,8 @@ __all__ = [
     "_ssrf_redirect_guard",
     # onboard
     "BindStatus",
-    "create_bind_task",
-    "poll_bind_result",
     "build_connect_url",
+    "qr_register",
     # crypto
     "decrypt_secret",
     "generate_bind_key",

gateway/platforms/qqbot/onboard.py

@@ -1,6 +1,10 @@
 """
 QQBot scan-to-configure (QR code onboard) module.
 
+Mirrors the Feishu onboarding pattern: synchronous HTTP + a single public
+entry-point ``qr_register()`` that handles the full flow (create task →
+display QR code → poll → decrypt credentials).
+
 Calls the ``q.qq.com`` ``create_bind_task`` / ``poll_bind_result`` APIs to
 generate a QR-code URL and poll for scan completion.  On success the caller
 receives the bot's *app_id*, *client_secret* (decrypted locally), and the
@@ -12,18 +16,20 @@ Reference: https://bot.q.qq.com/wiki/develop/api-v2/
 from __future__ import annotations
 
 import logging
+import time
 from enum import IntEnum
-from typing import Tuple
+from typing import Optional, Tuple
 from urllib.parse import quote
 
 from .constants import (
     ONBOARD_API_TIMEOUT,
     ONBOARD_CREATE_PATH,
+    ONBOARD_POLL_INTERVAL,
     ONBOARD_POLL_PATH,
     PORTAL_HOST,
     QR_URL_TEMPLATE,
 )
-from .crypto import generate_bind_key
+from .crypto import decrypt_secret, generate_bind_key
 from .utils import get_api_headers
 
 logger = logging.getLogger(__name__)
@@ -35,7 +41,7 @@ logger = logging.getLogger(__name__)
 
 
 class BindStatus(IntEnum):
-    """Status codes returned by ``poll_bind_result``."""
+    """Status codes returned by ``_poll_bind_result``."""
 
     NONE = 0
     PENDING = 1
@@ -44,18 +50,40 @@ class BindStatus(IntEnum):
 
 
 # ---------------------------------------------------------------------------
-# Public API
+# QR rendering
+# ---------------------------------------------------------------------------
+
+try:
+    import qrcode as _qrcode_mod
+except (ImportError, TypeError):
+    _qrcode_mod = None  # type: ignore[assignment]
+
+
+def _render_qr(url: str) -> bool:
+    """Try to render a QR code in the terminal. Returns True if successful."""
+    if _qrcode_mod is None:
+        return False
+    try:
+        qr = _qrcode_mod.QRCode(
+            error_correction=_qrcode_mod.constants.ERROR_CORRECT_M,
+            border=2,
+        )
+        qr.add_data(url)
+        qr.make(fit=True)
+        qr.print_ascii(invert=True)
+        return True
+    except Exception:
+        return False
+
+
+# ---------------------------------------------------------------------------
+# Synchronous HTTP helpers (mirrors Feishu _post_registration pattern)
 # ---------------------------------------------------------------------------
 
 
-async def create_bind_task(
-    timeout: float = ONBOARD_API_TIMEOUT,
-) -> Tuple[str, str]:
+def _create_bind_task(timeout: float = ONBOARD_API_TIMEOUT) -> Tuple[str, str]:
     """Create a bind task and return *(task_id, aes_key_base64)*.
 
-    The AES key is generated locally and sent to the server so it can
-    encrypt the bot credentials before returning them.
-
     Raises:
         RuntimeError: If the API returns a non-zero ``retcode``.
     """
@@ -64,8 +92,8 @@ async def create_bind_task(
     url = f"https://{PORTAL_HOST}{ONBOARD_CREATE_PATH}"
     key = generate_bind_key()
 
-    async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
-        resp = await client.post(url, json={"key": key}, headers=get_api_headers())
+    with httpx.Client(timeout=timeout, follow_redirects=True) as client:
+        resp = client.post(url, json={"key": key}, headers=get_api_headers())
         resp.raise_for_status()
         data = resp.json()
 
@@ -80,7 +108,7 @@ async def create_bind_task(
     return task_id, key
 
 
-async def poll_bind_result(
+def _poll_bind_result(
     task_id: str,
     timeout: float = ONBOARD_API_TIMEOUT,
 ) -> Tuple[BindStatus, str, str, str]:
@@ -89,12 +117,6 @@ async def poll_bind_result(
     Returns:
         A 4-tuple of ``(status, bot_appid, bot_encrypt_secret, user_openid)``.
 
-        * ``bot_encrypt_secret`` is AES-256-GCM encrypted — decrypt it with
-          :func:`~gateway.platforms.qqbot.crypto.decrypt_secret` using the
-          key from :func:`create_bind_task`.
-        * ``user_openid`` is the OpenID of the person who scanned the code
-          (available when ``status == COMPLETED``).
-
     Raises:
         RuntimeError: If the API returns a non-zero ``retcode``.
     """
@@ -102,8 +124,8 @@ async def poll_bind_result(
 
     url = f"https://{PORTAL_HOST}{ONBOARD_POLL_PATH}"
 
-    async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
-        resp = await client.post(url, json={"task_id": task_id}, headers=get_api_headers())
+    with httpx.Client(timeout=timeout, follow_redirects=True) as client:
+        resp = client.post(url, json={"task_id": task_id}, headers=get_api_headers())
         resp.raise_for_status()
         data = resp.json()
 
@@ -122,3 +144,77 @@ async def poll_bind_result(
 def build_connect_url(task_id: str) -> str:
     """Build the QR-code target URL for a given *task_id*."""
     return QR_URL_TEMPLATE.format(task_id=quote(task_id))
+
+
+# ---------------------------------------------------------------------------
+# Public entry-point
+# ---------------------------------------------------------------------------
+
+_MAX_REFRESHES = 3
+
+
+def qr_register(timeout_seconds: int = 600) -> Optional[dict]:
+    """Run the QQBot scan-to-configure QR registration flow.
+
+    Mirrors ``feishu.qr_register()``: handles create → display → poll →
+    decrypt in one call.  Unexpected errors propagate to the caller.
+
+    :returns:
+        ``{"app_id": ..., "client_secret": ..., "user_openid": ...}`` on
+        success, or ``None`` on failure / expiry / cancellation.
+    """
+    deadline = time.monotonic() + timeout_seconds
+
+    for refresh_count in range(_MAX_REFRESHES + 1):
+        # ── Create bind task ──
+        try:
+            task_id, aes_key = _create_bind_task()
+        except Exception as exc:
+            logger.warning("[QQBot onboard] Failed to create bind task: %s", exc)
+            return None
+
+        url = build_connect_url(task_id)
+
+        # ── Display QR code + URL ──
+        print()
+        if _render_qr(url):
+            print(f"  Scan the QR code above, or open this URL directly:\n  {url}")
+        else:
+            print(f"  Open this URL in QQ on your phone:\n  {url}")
+            print("  Tip: pip install qrcode  to display a scannable QR code here")
+        print()
+
+        # ── Poll loop ──
+        while time.monotonic() < deadline:
+            try:
+                status, app_id, encrypted_secret, user_openid = _poll_bind_result(task_id)
+            except Exception:
+                time.sleep(ONBOARD_POLL_INTERVAL)
+                continue
+
+            if status == BindStatus.COMPLETED:
+                client_secret = decrypt_secret(encrypted_secret, aes_key)
+                print()
+                print(f"  QR scan complete! (App ID: {app_id})")
+                if user_openid:
+                    print(f"  Scanner's OpenID: {user_openid}")
+                return {
+                    "app_id": app_id,
+                    "client_secret": client_secret,
+                    "user_openid": user_openid,
+                }
+
+            if status == BindStatus.EXPIRED:
+                if refresh_count >= _MAX_REFRESHES:
+                    logger.warning("[QQBot onboard] QR code expired %d times — giving up", _MAX_REFRESHES)
+                    return None
+                print(f"\n  QR code expired, refreshing... ({refresh_count + 1}/{_MAX_REFRESHES})")
+                break  # next for-loop iteration creates a new task
+
+            time.sleep(ONBOARD_POLL_INTERVAL)
+        else:
+            # deadline reached without completing
+            logger.warning("[QQBot onboard] Poll timed out after %ds", timeout_seconds)
+            return None
+
+    return None

gateway/platforms/slack.py

@@ -38,6 +38,7 @@ from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
+    ProcessingOutcome,
     SendResult,
     SUPPORTED_DOCUMENT_TYPES,
     safe_url_for_log,
@@ -113,6 +114,11 @@ class SlackAdapter(BasePlatformAdapter):
         # Cache for _fetch_thread_context results: cache_key → _ThreadContextCache
         self._thread_context_cache: Dict[str, _ThreadContextCache] = {}
         self._THREAD_CACHE_TTL = 60.0
+        # Track message IDs that should get reaction lifecycle (DMs / @mentions).
+        self._reacting_message_ids: set = set()
+        # Track active assistant thread status indicators so stop_typing can
+        # clear them (chat_id → thread_ts).
+        self._active_status_threads: Dict[str, str] = {}
 
     async def connect(self) -> bool:
         """Connect to Slack via Socket Mode."""
@@ -362,6 +368,7 @@ class SlackAdapter(BasePlatformAdapter):
         if not thread_ts:
             return  # Can only set status in a thread context
 
+        self._active_status_threads[chat_id] = thread_ts
         try:
             await self._get_client(chat_id).assistant_threads_setStatus(
                 channel_id=chat_id,
@@ -373,6 +380,22 @@ class SlackAdapter(BasePlatformAdapter):
             # in an assistant-enabled context. Falls back to reactions.
             logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
 
+    async def stop_typing(self, chat_id: str) -> None:
+        """Clear the assistant thread status indicator."""
+        if not self._app:
+            return
+        thread_ts = self._active_status_threads.pop(chat_id, None)
+        if not thread_ts:
+            return
+        try:
+            await self._get_client(chat_id).assistant_threads_setStatus(
+                channel_id=chat_id,
+                thread_ts=thread_ts,
+                status="",
+            )
+        except Exception as e:
+            logger.debug("[Slack] assistant.threads.setStatus clear failed: %s", e)
+
     def _dm_top_level_threads_as_sessions(self) -> bool:
         """Whether top-level Slack DMs get per-message session threads.
 
@@ -584,6 +607,38 @@ class SlackAdapter(BasePlatformAdapter):
             logger.debug("[Slack] reactions.remove failed (%s): %s", emoji, e)
             return False
 
+    def _reactions_enabled(self) -> bool:
+        """Check if message reactions are enabled via config/env."""
+        return os.getenv("SLACK_REACTIONS", "true").lower() not in ("false", "0", "no")
+
+    async def on_processing_start(self, event: MessageEvent) -> None:
+        """Add an in-progress reaction when message processing begins."""
+        if not self._reactions_enabled():
+            return
+        ts = getattr(event, "message_id", None)
+        if not ts or ts not in self._reacting_message_ids:
+            return
+        channel_id = getattr(event.source, "chat_id", None)
+        if channel_id:
+            await self._add_reaction(channel_id, ts, "eyes")
+
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
+        """Swap the in-progress reaction for a final success/failure reaction."""
+        if not self._reactions_enabled():
+            return
+        ts = getattr(event, "message_id", None)
+        if not ts or ts not in self._reacting_message_ids:
+            return
+        self._reacting_message_ids.discard(ts)
+        channel_id = getattr(event.source, "chat_id", None)
+        if not channel_id:
+            return
+        await self._remove_reaction(channel_id, ts, "eyes")
+        if outcome == ProcessingOutcome.SUCCESS:
+            await self._add_reaction(channel_id, ts, "white_check_mark")
+        elif outcome == ProcessingOutcome.FAILURE:
+            await self._add_reaction(channel_id, ts, "x")
+
     # ----- User identity resolution -----
 
     async def _resolve_user_name(self, user_id: str, chat_id: str = "") -> str:
@@ -1213,17 +1268,12 @@ class SlackAdapter(BasePlatformAdapter):
         # Only react when bot is directly addressed (DM or @mention).
         # In listen-all channels (require_mention=false), reacting to every
         # casual message would be noisy.
-        _should_react = is_dm or is_mentioned
-
+        _should_react = (is_dm or is_mentioned) and self._reactions_enabled()
         if _should_react:
-            await self._add_reaction(channel_id, ts, "eyes")
+            self._reacting_message_ids.add(ts)
 
         await self.handle_message(msg_event)
 
-        if _should_react:
-            await self._remove_reaction(channel_id, ts, "eyes")
-            await self._add_reaction(channel_id, ts, "white_check_mark")
-
     # ----- Approval button support (Block Kit) -----
 
     async def send_exec_approval(

gateway/platforms/wecom.py

@@ -1464,3 +1464,134 @@ class WeComAdapter(BasePlatformAdapter):
             "name": chat_id,
             "type": "group" if chat_id and chat_id.lower().startswith("group") else "dm",
         }
+
+
+# ------------------------------------------------------------------
+# QR code scan flow for obtaining bot credentials
+# ------------------------------------------------------------------
+
+_QR_GENERATE_URL = "https://work.weixin.qq.com/ai/qc/generate"
+_QR_QUERY_URL = "https://work.weixin.qq.com/ai/qc/query_result"
+_QR_CODE_PAGE = "https://work.weixin.qq.com/ai/qc/gen?source=hermes&scode="
+_QR_POLL_INTERVAL = 3  # seconds
+_QR_POLL_TIMEOUT = 300  # 5 minutes
+
+
+def qr_scan_for_bot_info(
+    *,
+    timeout_seconds: int = _QR_POLL_TIMEOUT,
+) -> Optional[Dict[str, str]]:
+    """Run the WeCom QR scan flow to obtain bot_id and secret.
+
+    Fetches a QR code from WeCom, renders it in the terminal, and polls
+    until the user scans it or the timeout expires.
+
+    Returns ``{"bot_id": ..., "secret": ...}`` on success, ``None`` on
+    failure or timeout.
+
+    Note: the ``work.weixin.qq.com/ai/qc/{generate,query_result}`` endpoints
+    used here are not part of WeCom's public developer API — they back the
+    admin-console web UI's bot-creation flow and may change without notice.
+    The same pattern is used by the feishu/dingtalk QR setup wizards.
+    """
+    try:
+        import urllib.request
+        import urllib.parse
+    except ImportError:  # pragma: no cover
+        logger.error("urllib is required for WeCom QR scan")
+        return None
+
+    generate_url = f"{_QR_GENERATE_URL}?source=hermes"
+
+    # ── Step 1: Fetch QR code ──
+    print("  Connecting to WeCom...", end="", flush=True)
+    try:
+        req = urllib.request.Request(generate_url, headers={"User-Agent": "HermesAgent/1.0"})
+        with urllib.request.urlopen(req, timeout=15) as resp:
+            raw = json.loads(resp.read().decode("utf-8"))
+    except Exception as exc:
+        logger.error("WeCom QR: failed to fetch QR code: %s", exc)
+        print(f" failed: {exc}")
+        return None
+
+    data = raw.get("data") or {}
+    scode = str(data.get("scode") or "").strip()
+    auth_url = str(data.get("auth_url") or "").strip()
+
+    if not scode or not auth_url:
+        logger.error("WeCom QR: unexpected response format: %s", raw)
+        print(" failed: unexpected response format")
+        return None
+
+    print(" done.")
+
+    # ── Step 2: Render QR code in terminal ──
+    print()
+    qr_rendered = False
+    try:
+        import qrcode as _qrcode
+        qr = _qrcode.QRCode()
+        qr.add_data(auth_url)
+        qr.make(fit=True)
+        qr.print_ascii(invert=True)
+        qr_rendered = True
+    except ImportError:
+        pass
+    except Exception:
+        pass
+
+    page_url = f"{_QR_CODE_PAGE}{urllib.parse.quote(scode)}"
+    if qr_rendered:
+        print(f"\n  Scan the QR code above, or open this URL directly:\n  {page_url}")
+    else:
+        print(f"  Open this URL in WeCom on your phone:\n\n  {page_url}\n")
+        print("  Tip: pip install qrcode  to display a scannable QR code here next time")
+    print()
+    print("  Fetching configuration results...", end="", flush=True)
+
+    # ── Step 3: Poll for result ──
+    import time
+    deadline = time.time() + timeout_seconds
+    query_url = f"{_QR_QUERY_URL}?scode={urllib.parse.quote(scode)}"
+    poll_count = 0
+
+    while time.time() < deadline:
+        try:
+            req = urllib.request.Request(query_url, headers={"User-Agent": "HermesAgent/1.0"})
+            with urllib.request.urlopen(req, timeout=10) as resp:
+                result = json.loads(resp.read().decode("utf-8"))
+        except Exception as exc:
+            logger.debug("WeCom QR poll error: %s", exc)
+            time.sleep(_QR_POLL_INTERVAL)
+            continue
+
+        poll_count += 1
+        # Print a dot on every poll so progress is visible within 3s.
+        print(".", end="", flush=True)
+
+        result_data = result.get("data") or {}
+        status = str(result_data.get("status") or "").lower()
+
+        if status == "success":
+            print()  # newline after "Fetching configuration results..." dots
+            bot_info = result_data.get("bot_info") or {}
+            bot_id = str(bot_info.get("botid") or bot_info.get("bot_id") or "").strip()
+            secret = str(bot_info.get("secret") or "").strip()
+            if bot_id and secret:
+                return {"bot_id": bot_id, "secret": secret}
+            logger.warning(
+                "WeCom QR: scan reported success but bot_info missing or incomplete: %s",
+                result_data,
+            )
+            print(
+                "  QR scan reported success but no bot credentials were returned.\n"
+                "  This usually means the bot was not actually created on the WeCom side.\n"
+                "  Falling back to manual credential entry."
+            )
+            return None
+
+        time.sleep(_QR_POLL_INTERVAL)
+
+    print()  # newline after dots
+    print(f"  QR scan timed out ({timeout_seconds // 60} minutes). Please try again.")
+    return None

gateway/run.py

@@ -710,7 +710,26 @@ class GatewayRunner:
             self._session_db = SessionDB()
         except Exception as e:
             logger.debug("SQLite session store not available: %s", e)
-        
+
+        # Opportunistic state.db maintenance: prune ended sessions older
+        # than sessions.retention_days + optional VACUUM. Tracks last-run
+        # in state_meta so it only actually executes once per
+        # sessions.min_interval_hours.  Gateway is long-lived so blocking
+        # a few seconds once per day is acceptable; failures are logged
+        # but never raised.
+        if self._session_db is not None:
+            try:
+                from hermes_cli.config import load_config as _load_full_config
+                _sess_cfg = (_load_full_config().get("sessions") or {})
+                if _sess_cfg.get("auto_prune", False):
+                    self._session_db.maybe_auto_prune_and_vacuum(
+                        retention_days=int(_sess_cfg.get("retention_days", 90)),
+                        min_interval_hours=int(_sess_cfg.get("min_interval_hours", 24)),
+                        vacuum=bool(_sess_cfg.get("vacuum_after_prune", True)),
+                    )
+            except Exception as exc:
+                logger.debug("state.db auto-maintenance skipped: %s", exc)
+
         # DM pairing store for code-based user authorization
         from gateway.pairing import PairingStore
         self.pairing_store = PairingStore()
@@ -2668,8 +2687,9 @@ class GatewayRunner:
                 except Exception as _e:
                     logger.debug("SessionDB close error: %s", _e)
 
-            from gateway.status import remove_pid_file
+            from gateway.status import remove_pid_file, release_gateway_runtime_lock
             remove_pid_file()
+            release_gateway_runtime_lock()
 
             # Write a clean-shutdown marker so the next startup knows this
             # wasn't a crash.  suspend_recently_active() only needs to run
@@ -3466,23 +3486,73 @@ class GatewayRunner:
 
         # Check for commands
         command = event.get_command()
-        
-        # Emit command:* hook for any recognized slash command.
-        # GATEWAY_KNOWN_COMMANDS is derived from the central COMMAND_REGISTRY
-        # in hermes_cli/commands.py — no hardcoded set to maintain here.
-        from hermes_cli.commands import GATEWAY_KNOWN_COMMANDS, resolve_command as _resolve_cmd
-        if command and command in GATEWAY_KNOWN_COMMANDS:
-            await self.hooks.emit(f"command:{command}", {
-                "platform": source.platform.value if source.platform else "",
-                "user_id": source.user_id,
-                "command": command,
-                "args": event.get_command_args().strip(),
-            })
 
-        # Resolve aliases to canonical name so dispatch only checks canonicals.
+        from hermes_cli.commands import (
+            GATEWAY_KNOWN_COMMANDS,
+            is_gateway_known_command,
+            resolve_command as _resolve_cmd,
+        )
+
+        # Resolve aliases to canonical name so dispatch and hook names
+        # don't depend on the exact alias the user typed.
         _cmd_def = _resolve_cmd(command) if command else None
         canonical = _cmd_def.name if _cmd_def else command
 
+        # Fire the ``command:<canonical>`` hook for any recognized slash
+        # command — built-in OR plugin-registered. Handlers can return a
+        # dict with ``{"decision": "deny" | "handled" | "rewrite", ...}``
+        # to intercept dispatch before core handling runs. This replaces
+        # the previous fire-and-forget emit(): return values are now
+        # honored, but handlers that return nothing behave exactly as
+        # before (telemetry-style hooks keep working).
+        if command and is_gateway_known_command(canonical):
+            raw_args = event.get_command_args().strip()
+            hook_ctx = {
+                "platform": source.platform.value if source.platform else "",
+                "user_id": source.user_id,
+                "command": canonical,
+                "raw_command": command,
+                "args": raw_args,
+                "raw_args": raw_args,
+            }
+            try:
+                hook_results = await self.hooks.emit_collect(
+                    f"command:{canonical}", hook_ctx
+                )
+            except Exception as _hook_err:
+                logger.debug(
+                    "command:%s hook dispatch failed (non-fatal): %s",
+                    canonical, _hook_err,
+                )
+                hook_results = []
+
+            for hook_result in hook_results:
+                if not isinstance(hook_result, dict):
+                    continue
+                decision = str(hook_result.get("decision", "")).strip().lower()
+                if not decision or decision == "allow":
+                    continue
+                if decision == "deny":
+                    message = hook_result.get("message")
+                    if isinstance(message, str) and message:
+                        return message
+                    return f"Command `/{command}` was blocked by a hook."
+                if decision == "handled":
+                    message = hook_result.get("message")
+                    return message if isinstance(message, str) and message else None
+                if decision == "rewrite":
+                    new_command = str(
+                        hook_result.get("command_name", "")
+                    ).strip().lstrip("/")
+                    if not new_command:
+                        continue
+                    new_args = str(hook_result.get("raw_args", "")).strip()
+                    event.text = f"/{new_command} {new_args}".strip()
+                    command = event.get_command()
+                    _cmd_def = _resolve_cmd(command) if command else None
+                    canonical = _cmd_def.name if _cmd_def else command
+                    break
+
         if canonical == "new":
             return await self._handle_reset_command(event)
         
@@ -4901,6 +4971,11 @@ class GatewayRunner:
         # the configured default instead of the previously switched model.
         self._session_model_overrides.pop(session_key, None)
 
+        # Clear session-scoped dangerous-command approvals and /yolo state.
+        # /new is a conversation-boundary operation — approval state from the
+        # previous conversation must not survive the reset.
+        self._clear_session_boundary_security_state(session_key)
+
         # Fire plugin on_session_finalize hook (session boundary)
         try:
             from hermes_cli.plugins import invoke_hook as _invoke_hook
@@ -6456,6 +6531,11 @@ class GatewayRunner:
                     session_id=task_id,
                     platform=platform_key,
                     user_id=source.user_id,
+                    user_name=source.user_name,
+                    chat_id=source.chat_id,
+                    chat_name=source.chat_name,
+                    chat_type=source.chat_type,
+                    thread_id=source.thread_id,
                     session_db=self._session_db,
                     fallback_model=self._fallback_model,
                 )
@@ -7142,6 +7222,7 @@ class GatewayRunner:
         new_entry = self.session_store.switch_session(session_key, target_id)
         if not new_entry:
             return "Failed to switch session."
+        self._clear_session_boundary_security_state(session_key)
 
         # Get the title for confirmation
         title = self._session_db.get_session_title(target_id) or name
@@ -7216,6 +7297,7 @@ class GatewayRunner:
                     tool_calls=msg.get("tool_calls"),
                     tool_call_id=msg.get("tool_call_id"),
                     reasoning=msg.get("reasoning"),
+                    reasoning_content=msg.get("reasoning_content"),
                 )
             except Exception:
                 pass  # Best-effort copy
@@ -7230,6 +7312,7 @@ class GatewayRunner:
         new_entry = self.session_store.switch_session(session_key, new_session_id)
         if not new_entry:
             return "Branch created but failed to switch to it."
+        self._clear_session_boundary_security_state(session_key)
 
         # Evict any cached agent for this session
         self._evict_cached_agent(session_key)
@@ -7620,13 +7703,14 @@ class GatewayRunner:
         from hermes_cli.debug import (
             _capture_dump, collect_debug_report,
             upload_to_pastebin, _schedule_auto_delete,
-            _GATEWAY_PRIVACY_NOTICE,
+            _GATEWAY_PRIVACY_NOTICE, _best_effort_sweep_expired_pastes,
         )
 
         loop = asyncio.get_running_loop()
 
         # Run blocking I/O (dump capture, log reads, uploads) in a thread.
         def _collect_and_upload():
+            _best_effort_sweep_expired_pastes()
             dump_text = _capture_dump()
             report = collect_debug_report(log_lines=200, dump_text=dump_text)
 
@@ -8603,6 +8687,29 @@ class GatewayRunner:
         if hasattr(self, "_busy_ack_ts"):
             self._busy_ack_ts.pop(session_key, None)
 
+    def _clear_session_boundary_security_state(self, session_key: str) -> None:
+        """Clear approval state that must not survive a real conversation switch."""
+        if not session_key:
+            return
+
+        pending_approvals = getattr(self, "_pending_approvals", None)
+        if isinstance(pending_approvals, dict):
+            pending_approvals.pop(session_key, None)
+
+        try:
+            from tools.approval import clear_session as _clear_approval_session
+        except Exception:
+            return
+
+        try:
+            _clear_approval_session(session_key)
+        except Exception as e:
+            logger.debug(
+                "Failed to clear approval state for session boundary %s: %s",
+                session_key,
+                e,
+            )
+
     def _begin_session_run_generation(self, session_key: str) -> int:
         """Claim a fresh run generation token for ``session_key``.
 
@@ -9698,6 +9805,11 @@ class GatewayRunner:
                     session_id=session_id,
                     platform=platform_key,
                     user_id=source.user_id,
+                    user_name=source.user_name,
+                    chat_id=source.chat_id,
+                    chat_name=source.chat_name,
+                    chat_type=source.chat_type,
+                    thread_id=source.thread_id,
                     gateway_session_key=session_key,
                     session_db=self._session_db,
                     fallback_model=self._fallback_model,
@@ -10764,7 +10876,13 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
     # The PID file is scoped to HERMES_HOME, so future multi-profile
     # setups (each profile using a distinct HERMES_HOME) will naturally
     # allow concurrent instances without tripping this guard.
-    from gateway.status import get_running_pid, remove_pid_file, terminate_pid
+    from gateway.status import (
+        acquire_gateway_runtime_lock,
+        get_running_pid,
+        release_gateway_runtime_lock,
+        remove_pid_file,
+        terminate_pid,
+    )
     existing_pid = get_running_pid()
     if existing_pid is not None and existing_pid != os.getpid():
         if replace:
@@ -10977,14 +11095,21 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
             "Exiting to avoid double-running.", _current_pid
         )
         return False
+    if not acquire_gateway_runtime_lock():
+        logger.error(
+            "Gateway runtime lock is already held by another instance. Exiting."
+        )
+        return False
     try:
         write_pid_file()
     except FileExistsError:
+        release_gateway_runtime_lock()
         logger.error(
             "PID file race lost to another gateway instance. Exiting."
         )
         return False
     atexit.register(remove_pid_file)
+    atexit.register(release_gateway_runtime_lock)
 
     # Start the gateway
     success = await runner.start()

gateway/session.py

@@ -80,7 +80,7 @@ class SessionSource:
     user_name: Optional[str] = None
     thread_id: Optional[str] = None  # For forum topics, Discord threads, etc.
     chat_topic: Optional[str] = None  # Channel topic/description (Discord, Slack)
-    user_id_alt: Optional[str] = None  # Signal UUID (alternative to phone number)
+    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)
     
@@ -1147,6 +1147,10 @@ class SessionStore:
                     tool_name=message.get("tool_name"),
                     tool_calls=message.get("tool_calls"),
                     tool_call_id=message.get("tool_call_id"),
+                    reasoning=message.get("reasoning") if message.get("role") == "assistant" else None,
+                    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,
                 )
             except Exception as e:
                 logger.debug("Session DB operation failed: %s", e)
@@ -1176,6 +1180,7 @@ class SessionStore:
                         tool_calls=msg.get("tool_calls"),
                         tool_call_id=msg.get("tool_call_id"),
                         reasoning=msg.get("reasoning") if role == "assistant" else None,
+                        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,
                     )

gateway/status.py

@@ -22,11 +22,18 @@ from pathlib import Path
 from hermes_constants import get_hermes_home
 from typing import Any, Optional
 
+if sys.platform == "win32":
+    import msvcrt
+else:
+    import fcntl
+
 _GATEWAY_KIND = "hermes-gateway"
 _RUNTIME_STATUS_FILE = "gateway_state.json"
 _LOCKS_DIRNAME = "gateway-locks"
 _IS_WINDOWS = sys.platform == "win32"
 _UNSET = object()
+_GATEWAY_LOCK_FILENAME = "gateway.lock"
+_gateway_lock_handle = None
 
 
 def _get_pid_path() -> Path:
@@ -35,6 +42,14 @@ def _get_pid_path() -> Path:
     return home / "gateway.pid"
 
 
+def _get_gateway_lock_path(pid_path: Optional[Path] = None) -> Path:
+    """Return the path to the runtime gateway lock file."""
+    if pid_path is not None:
+        return pid_path.with_name(_GATEWAY_LOCK_FILENAME)
+    home = get_hermes_home()
+    return home / _GATEWAY_LOCK_FILENAME
+
+
 def _get_runtime_status_path() -> Path:
     """Return the persisted runtime health/status file path."""
     return _get_pid_path().with_name(_RUNTIME_STATUS_FILE)
@@ -121,6 +136,7 @@ def _looks_like_gateway_process(pid: int) -> bool:
         "hermes_cli.main gateway",
         "hermes_cli/main.py gateway",
         "hermes gateway",
+        "hermes-gateway",
         "gateway/run.py",
     )
     return any(pattern in cmdline for pattern in patterns)
@@ -212,16 +228,135 @@ def _read_pid_record(pid_path: Optional[Path] = None) -> Optional[dict]:
     return None
 
 
+def _read_gateway_lock_record(lock_path: Optional[Path] = None) -> Optional[dict[str, Any]]:
+    return _read_pid_record(lock_path or _get_gateway_lock_path())
+
+
+def _pid_from_record(record: Optional[dict[str, Any]]) -> Optional[int]:
+    if not record:
+        return None
+    try:
+        return int(record["pid"])
+    except (KeyError, TypeError, ValueError):
+        return None
+
+
 def _cleanup_invalid_pid_path(pid_path: Path, *, cleanup_stale: bool) -> None:
+    """Delete a stale gateway PID file (and its sibling lock metadata).
+
+    Called from ``get_running_pid()`` after the runtime lock has already been
+    confirmed inactive, so the on-disk metadata is known to belong to a dead
+    process.  Unlike ``remove_pid_file()`` (which defensively refuses to delete
+    a PID file whose ``pid`` field differs from ``os.getpid()`` to protect
+    ``--replace`` handoffs), this path force-unlinks both files so the next
+    startup sees a clean slate.
+    """
     if not cleanup_stale:
         return
     try:
-        if pid_path == _get_pid_path():
-            remove_pid_file()
-        else:
-            pid_path.unlink(missing_ok=True)
+        pid_path.unlink(missing_ok=True)
     except Exception:
         pass
+    try:
+        _get_gateway_lock_path(pid_path).unlink(missing_ok=True)
+    except Exception:
+        pass
+
+
+def _write_gateway_lock_record(handle) -> None:
+    handle.seek(0)
+    handle.truncate()
+    json.dump(_build_pid_record(), handle)
+    handle.flush()
+    try:
+        os.fsync(handle.fileno())
+    except OSError:
+        pass
+
+
+def _try_acquire_file_lock(handle) -> bool:
+    try:
+        if _IS_WINDOWS:
+            handle.seek(0, os.SEEK_END)
+            if handle.tell() == 0:
+                handle.write("\n")
+                handle.flush()
+            handle.seek(0)
+            msvcrt.locking(handle.fileno(), msvcrt.LK_NBLCK, 1)
+        else:
+            fcntl.flock(handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
+        return True
+    except (BlockingIOError, OSError):
+        return False
+
+
+def _release_file_lock(handle) -> None:
+    try:
+        if _IS_WINDOWS:
+            handle.seek(0)
+            msvcrt.locking(handle.fileno(), msvcrt.LK_UNLCK, 1)
+        else:
+            fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
+    except OSError:
+        pass
+
+
+def acquire_gateway_runtime_lock() -> bool:
+    """Claim the cross-process runtime lock for the gateway.
+
+    Unlike the PID file, the lock is owned by the live process itself. If the
+    process dies abruptly, the OS releases the lock automatically.
+    """
+    global _gateway_lock_handle
+    if _gateway_lock_handle is not None:
+        return True
+
+    path = _get_gateway_lock_path()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    handle = open(path, "a+", encoding="utf-8")
+    if not _try_acquire_file_lock(handle):
+        handle.close()
+        return False
+    _write_gateway_lock_record(handle)
+    _gateway_lock_handle = handle
+    return True
+
+
+def release_gateway_runtime_lock() -> None:
+    """Release the gateway runtime lock when owned by this process."""
+    global _gateway_lock_handle
+    handle = _gateway_lock_handle
+    if handle is None:
+        return
+    _gateway_lock_handle = None
+    _release_file_lock(handle)
+    try:
+        handle.close()
+    except OSError:
+        pass
+
+
+def is_gateway_runtime_lock_active(lock_path: Optional[Path] = None) -> bool:
+    """Return True when some process currently owns the gateway runtime lock."""
+    global _gateway_lock_handle
+    resolved_lock_path = lock_path or _get_gateway_lock_path()
+    if _gateway_lock_handle is not None and resolved_lock_path == _get_gateway_lock_path():
+        return True
+
+    if not resolved_lock_path.exists():
+        return False
+
+    handle = open(resolved_lock_path, "a+", encoding="utf-8")
+    try:
+        if _try_acquire_file_lock(handle):
+            _release_file_lock(handle)
+            return False
+        return True
+    finally:
+        try:
+            handle.close()
+        except OSError:
+            pass
 
 
 def write_pid_file() -> None:
@@ -583,35 +718,42 @@ def get_running_pid(
     Cleans up stale PID files automatically.
     """
     resolved_pid_path = pid_path or _get_pid_path()
-    record = _read_pid_record(resolved_pid_path)
-    if not record:
+    resolved_lock_path = _get_gateway_lock_path(resolved_pid_path)
+    lock_active = is_gateway_runtime_lock_active(resolved_lock_path)
+    if not lock_active:
         _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
         return None
 
-    try:
-        pid = int(record["pid"])
-    except (KeyError, TypeError, ValueError):
-        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
-        return None
+    primary_record = _read_pid_record(resolved_pid_path)
+    fallback_record = _read_gateway_lock_record(resolved_lock_path)
 
-    try:
-        os.kill(pid, 0)  # signal 0 = existence check, no actual signal sent
-    except (ProcessLookupError, PermissionError):
-        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
-        return None
+    for record in (primary_record, fallback_record):
+        pid = _pid_from_record(record)
+        if pid is None:
+            continue
 
-    recorded_start = record.get("start_time")
-    current_start = _get_process_start_time(pid)
-    if recorded_start is not None and current_start is not None and current_start != recorded_start:
-        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
-        return None
+        try:
+            os.kill(pid, 0)  # signal 0 = existence check, no actual signal sent
+        except ProcessLookupError:
+            continue
+        except PermissionError:
+            # The process exists but belongs to another user/service scope.
+            # With the runtime lock still held, prefer keeping it visible
+            # rather than deleting the PID file as "stale".
+            if _record_looks_like_gateway(record):
+                return pid
+            continue
 
-    if not _looks_like_gateway_process(pid):
-        if not _record_looks_like_gateway(record):
-            _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
-            return None
+        recorded_start = record.get("start_time")
+        current_start = _get_process_start_time(pid)
+        if recorded_start is not None and current_start is not None and current_start != recorded_start:
+            continue
 
-    return pid
+        if _looks_like_gateway_process(pid) or _record_looks_like_gateway(record):
+            return pid
+
+    _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
+    return None
 
 
 def is_gateway_running(

hermes_cli/auth.py

@@ -72,6 +72,8 @@ DEFAULT_QWEN_BASE_URL = "https://portal.qwen.ai/v1"
 DEFAULT_GITHUB_MODELS_BASE_URL = "https://api.githubcopilot.com"
 DEFAULT_COPILOT_ACP_BASE_URL = "acp://copilot"
 DEFAULT_OLLAMA_CLOUD_BASE_URL = "https://ollama.com/v1"
+STEPFUN_STEP_PLAN_INTL_BASE_URL = "https://api.stepfun.ai/step_plan/v1"
+STEPFUN_STEP_PLAN_CN_BASE_URL = "https://api.stepfun.com/step_plan/v1"
 CODEX_OAUTH_CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann"
 CODEX_OAUTH_TOKEN_URL = "https://auth.openai.com/oauth/token"
 CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120
@@ -182,6 +184,14 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         inference_base_url="https://api.moonshot.cn/v1",
         api_key_env_vars=("KIMI_CN_API_KEY",),
     ),
+    "stepfun": ProviderConfig(
+        id="stepfun",
+        name="StepFun Step Plan",
+        auth_type="api_key",
+        inference_base_url=STEPFUN_STEP_PLAN_INTL_BASE_URL,
+        api_key_env_vars=("STEPFUN_API_KEY",),
+        base_url_env_var="STEPFUN_BASE_URL",
+    ),
     "arcee": ProviderConfig(
         id="arcee",
         name="Arcee AI",
@@ -204,6 +214,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         auth_type="api_key",
         inference_base_url="https://api.anthropic.com",
         api_key_env_vars=("ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN", "CLAUDE_CODE_OAUTH_TOKEN"),
+        base_url_env_var="ANTHROPIC_BASE_URL",
     ),
     "alibaba": ProviderConfig(
         id="alibaba",
@@ -992,6 +1003,7 @@ def resolve_provider(
         "x-ai": "xai", "x.ai": "xai", "grok": "xai",
         "kimi": "kimi-coding", "kimi-for-coding": "kimi-coding", "moonshot": "kimi-coding",
         "kimi-cn": "kimi-coding-cn", "moonshot-cn": "kimi-coding-cn",
+        "step": "stepfun", "stepfun-coding-plan": "stepfun",
         "arcee-ai": "arcee", "arceeai": "arcee",
         "minimax-china": "minimax-cn", "minimax_cn": "minimax-cn",
         "claude": "anthropic", "claude-code": "anthropic",

hermes_cli/claw.py

@@ -249,7 +249,7 @@ def _scan_workspace_state(source_dir: Path) -> list[tuple[Path, str]]:
             state_path = child / state_name
             if state_path.exists():
                 kind = "directory" if state_path.is_dir() else "file"
-                rel = state_path.relative_to(source_dir)
+                rel = state_path.relative_to(source_dir).as_posix()
                 findings.append((state_path, f"Workspace {kind}: {rel}"))
 
     return findings

hermes_cli/commands.py

@@ -260,6 +260,26 @@ GATEWAY_KNOWN_COMMANDS: frozenset[str] = frozenset(
 )
 
 
+def is_gateway_known_command(name: str | None) -> bool:
+    """Return True if ``name`` resolves to a gateway-dispatchable slash command.
+
+    This covers both built-in commands (``GATEWAY_KNOWN_COMMANDS`` derived
+    from ``COMMAND_REGISTRY``) and plugin-registered commands, which are
+    looked up lazily so importing this module never forces plugin
+    discovery. Gateway code uses this to decide whether to emit
+    ``command:<name>`` hooks — plugin commands get the same lifecycle
+    events as built-ins.
+    """
+    if not name:
+        return False
+    if name in GATEWAY_KNOWN_COMMANDS:
+        return True
+    for plugin_name, _description, _args_hint in _iter_plugin_command_entries():
+        if plugin_name == name:
+            return True
+    return False
+
+
 # Commands with explicit Level-2 running-agent handlers in gateway/run.py.
 # Listed here for introspection / tests; semantically a subset of
 # "all resolvable commands" — which is the real bypass set (see
@@ -371,12 +391,47 @@ def gateway_help_lines() -> list[str]:
     return lines
 
 
+def _iter_plugin_command_entries() -> list[tuple[str, str, str]]:
+    """Yield (name, description, args_hint) tuples for all plugin slash commands.
+
+    Plugin commands are registered via
+    :func:`hermes_cli.plugins.PluginContext.register_command`. They behave
+    like ``CommandDef`` entries for gateway surfacing: they appear in the
+    Telegram command menu, in Slack's ``/hermes`` subcommand mapping, and
+    (via :func:`gateway.platforms.discord._register_slash_commands`) in
+    Discord's native slash command picker.
+
+    Lookup is lazy so importing this module never forces plugin discovery
+    (which can trigger filesystem scans and environment-dependent
+    behavior).
+    """
+    try:
+        from hermes_cli.plugins import get_plugin_commands
+    except Exception:
+        return []
+    try:
+        commands = get_plugin_commands() or {}
+    except Exception:
+        return []
+    entries: list[tuple[str, str, str]] = []
+    for name, meta in commands.items():
+        if not isinstance(name, str) or not isinstance(meta, dict):
+            continue
+        description = str(meta.get("description") or f"Run /{name}")
+        args_hint = str(meta.get("args_hint") or "").strip()
+        entries.append((name, description, args_hint))
+    return entries
+
+
 def telegram_bot_commands() -> list[tuple[str, str]]:
     """Return (command_name, description) pairs for Telegram setMyCommands.
 
     Telegram command names cannot contain hyphens, so they are replaced with
     underscores.  Aliases are skipped -- Telegram shows one menu entry per
     canonical command.
+
+    Plugin-registered slash commands are included so plugins get native
+    autocomplete in Telegram without touching core code.
     """
     overrides = _resolve_config_gates()
     result: list[tuple[str, str]] = []
@@ -386,6 +441,10 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
         tg_name = _sanitize_telegram_name(cmd.name)
         if tg_name:
             result.append((tg_name, cmd.description))
+    for name, description, _args_hint in _iter_plugin_command_entries():
+        tg_name = _sanitize_telegram_name(name)
+        if tg_name:
+            result.append((tg_name, description))
     return result
 
 
@@ -750,6 +809,9 @@ def slack_subcommand_map() -> dict[str, str]:
 
     Maps both canonical names and aliases so /hermes bg do stuff works
     the same as /hermes background do stuff.
+
+    Plugin-registered slash commands are included so ``/hermes <plugin-cmd>``
+    routes through the plugin handler.
     """
     overrides = _resolve_config_gates()
     mapping: dict[str, str] = {}
@@ -759,6 +821,9 @@ def slack_subcommand_map() -> dict[str, str]:
         mapping[cmd.name] = f"/{cmd.name}"
         for alias in cmd.aliases:
             mapping[alias] = f"/{alias}"
+    for name, _description, _args_hint in _iter_plugin_command_entries():
+        if name not in mapping:
+            mapping[name] = f"/{name}"
     return mapping
 
 

hermes_cli/config.py

@@ -712,6 +712,12 @@ DEFAULT_CONFIG = {
         "provider": "",    # e.g. "openrouter" (empty = inherit parent provider + credentials)
         "base_url": "",    # direct OpenAI-compatible endpoint for subagents
         "api_key": "",     # API key for delegation.base_url (falls back to OPENAI_API_KEY)
+        # When delegate_task narrows child toolsets explicitly, preserve any
+        # MCP toolsets the parent already has enabled. On by default so
+        # narrowing (e.g. toolsets=["web","browser"]) expresses "I want these
+        # extras" without silently stripping MCP tools the parent already has.
+        # Set to false for strict intersection.
+        "inherit_mcp_toolsets": True,
         "max_iterations": 50,  # per-subagent iteration cap (each subagent gets its own budget,
                                # independent of the parent's max_iterations)
         "reasoning_effort": "",  # reasoning effort for subagents: "xhigh", "high", "medium",
@@ -840,6 +846,7 @@ DEFAULT_CONFIG = {
 
     # Pre-exec security scanning via tirith
     "security": {
+        "allow_private_urls": False,  # Allow requests to private/internal IPs (for OpenWrt, proxies, VPNs)
         "redact_secrets": True,
         "tirith_enabled": True,
         "tirith_path": "tirith",
@@ -893,6 +900,34 @@ DEFAULT_CONFIG = {
         "force_ipv4": False,
     },
 
+    # Session storage — controls automatic cleanup of ~/.hermes/state.db.
+    # state.db accumulates every session, message, tool call, and FTS5 index
+    # entry forever.  Without auto-pruning, a heavy user (gateway + cron)
+    # reports 384MB+ databases with 68K+ messages, which slows down FTS5
+    # inserts, /resume listing, and insights queries.
+    "sessions": {
+        # When true, prune ended sessions older than retention_days once
+        # per (roughly) min_interval_hours at CLI/gateway/cron startup.
+        # Only touches ended sessions — active sessions are always preserved.
+        # Default false: session history is valuable for search recall, and
+        # silently deleting it could surprise users.  Opt in explicitly.
+        "auto_prune": False,
+        # How many days of ended-session history to keep.  Matches the
+        # default of ``hermes sessions prune``.
+        "retention_days": 90,
+        # VACUUM after a prune that actually deleted rows.  SQLite does not
+        # reclaim disk space on DELETE — freed pages are just reused on
+        # subsequent INSERTs — so without VACUUM the file stays bloated
+        # even after pruning.  VACUUM blocks writes for a few seconds per
+        # 100MB, so it only runs at startup, and only when prune deleted
+        # ≥1 session.
+        "vacuum_after_prune": True,
+        # Minimum hours between auto-maintenance runs (avoids repeating
+        # the sweep on every CLI invocation).  Tracked via state_meta in
+        # state.db itself, so it's shared across all processes.
+        "min_interval_hours": 24,
+    },
+
     # Config schema version - bump this when adding new required fields
     "_config_version": 22,
 }
@@ -1050,6 +1085,22 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
+    "STEPFUN_API_KEY": {
+        "description": "StepFun Step Plan API key",
+        "prompt": "StepFun Step Plan API key",
+        "url": "https://platform.stepfun.com/",
+        "password": True,
+        "category": "provider",
+        "advanced": True,
+    },
+    "STEPFUN_BASE_URL": {
+        "description": "StepFun Step Plan base URL override",
+        "prompt": "StepFun Step Plan base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
     "ARCEEAI_API_KEY": {
         "description": "Arcee AI API key",
         "prompt": "Arcee AI API key",
@@ -2102,6 +2153,7 @@ _KNOWN_ROOT_KEYS = {
     "fallback_providers", "credential_pool_strategies", "toolsets",
     "agent", "terminal", "display", "compression", "delegation",
     "auxiliary", "custom_providers", "context", "memory", "gateway",
+    "sessions",
 }
 
 # Valid fields inside a custom_providers list entry
@@ -3117,7 +3169,7 @@ def save_config(config: Dict[str, Any]):
     if not sec or sec.get("redact_secrets") is None:
         parts.append(_SECURITY_COMMENT)
     fb = normalized.get("fallback_model", {})
-    if not fb or not (fb.get("provider") and fb.get("model")):
+    if not fb or not isinstance(fb, dict) or not (fb.get("provider") and fb.get("model")):
         parts.append(_FALLBACK_COMMENT)
 
     atomic_yaml_write(

hermes_cli/debug.py

@@ -13,6 +13,7 @@ import time
 import urllib.error
 import urllib.parse
 import urllib.request
+from dataclasses import dataclass
 from pathlib import Path
 from typing import Optional
 
@@ -147,6 +148,14 @@ def _sweep_expired_pastes(now: Optional[float] = None) -> tuple[int, int]:
     return (deleted, len(remaining))
 
 
+def _best_effort_sweep_expired_pastes() -> None:
+    """Attempt pending-paste cleanup without letting /debug fail offline."""
+    try:
+        _sweep_expired_pastes()
+    except Exception:
+        pass
+
+
 # ---------------------------------------------------------------------------
 # Privacy / delete helpers
 # ---------------------------------------------------------------------------
@@ -314,72 +323,128 @@ def upload_to_pastebin(content: str, expiry_days: int = 7) -> str:
 # Log file reading
 # ---------------------------------------------------------------------------
 
-def _resolve_log_path(log_name: str) -> Optional[Path]:
-    """Find the log file for *log_name*, falling back to the .1 rotation.
 
-    Returns the path if found, or None.
-    """
+@dataclass
+class LogSnapshot:
+    """Single-read snapshot of a log file used by debug-share."""
+
+    path: Optional[Path]
+    tail_text: str
+    full_text: Optional[str]
+
+
+def _primary_log_path(log_name: str) -> Optional[Path]:
+    """Where *log_name* would live if present. Doesn't check existence."""
     from hermes_cli.logs import LOG_FILES
 
     filename = LOG_FILES.get(log_name)
-    if not filename:
+    return (get_hermes_home() / "logs" / filename) if filename else None
+
+
+def _resolve_log_path(log_name: str) -> Optional[Path]:
+    """Find the log file for *log_name*, falling back to the .1 rotation.
+
+    Returns the first non-empty candidate (primary, then .1), or None.
+    Callers distinguish 'empty primary' from 'truly missing' via
+    :func:`_primary_log_path`.
+    """
+    primary = _primary_log_path(log_name)
+    if primary is None:
         return None
 
-    log_dir = get_hermes_home() / "logs"
-    primary = log_dir / filename
     if primary.exists() and primary.stat().st_size > 0:
         return primary
 
-    # Fall back to the most recent rotated file (.1).
-    rotated = log_dir / f"{filename}.1"
+    rotated = primary.parent / f"{primary.name}.1"
     if rotated.exists() and rotated.stat().st_size > 0:
         return rotated
 
     return None
 
 
-def _read_log_tail(log_name: str, num_lines: int) -> str:
-    """Read the last *num_lines* from a log file, or return a placeholder."""
-    from hermes_cli.logs import _read_last_n_lines
+def _capture_log_snapshot(
+    log_name: str,
+    *,
+    tail_lines: int,
+    max_bytes: int = _MAX_LOG_BYTES,
+) -> LogSnapshot:
+    """Capture a log once and derive summary/full-log views from it.
 
-    log_path = _resolve_log_path(log_name)
-    if log_path is None:
-        return "(file not found)"
-
-    try:
-        lines = _read_last_n_lines(log_path, num_lines)
-        return "".join(lines).rstrip("\n")
-    except Exception as exc:
-        return f"(error reading: {exc})"
-
-
-def _read_full_log(log_name: str, max_bytes: int = _MAX_LOG_BYTES) -> Optional[str]:
-    """Read a log file for standalone upload.
-
-    Returns the file content (last *max_bytes* if truncated), or None if the
-    file doesn't exist or is empty.
+    The report tail and standalone log upload must come from the same file
+    snapshot. Otherwise a rotation/truncate between reads can make the report
+    look newer than the uploaded ``agent.log`` paste.
     """
     log_path = _resolve_log_path(log_name)
     if log_path is None:
-        return None
+        primary = _primary_log_path(log_name)
+        tail = "(file empty)" if primary and primary.exists() else "(file not found)"
+        return LogSnapshot(path=None, tail_text=tail, full_text=None)
 
     try:
         size = log_path.stat().st_size
         if size == 0:
-            return None
+            # race: file was truncated between _resolve_log_path and stat
+            return LogSnapshot(path=log_path, tail_text="(file empty)", full_text=None)
 
-        if size <= max_bytes:
-            return log_path.read_text(encoding="utf-8", errors="replace")
-
-        # File is larger than max_bytes — read the tail.
         with open(log_path, "rb") as f:
-            f.seek(size - max_bytes)
-            # Skip partial line at the seek point.
-            f.readline()
-            content = f.read().decode("utf-8", errors="replace")
-        return f"[... truncated — showing last ~{max_bytes // 1024}KB ...]\n{content}"
-    except Exception:
-        return None
+            if size <= max_bytes:
+                raw = f.read()
+                truncated = False
+            else:
+                # Read from the end until we have enough bytes for the
+                # standalone upload and enough newline context to render the
+                # summary tail from the same snapshot.
+                chunk_size = 8192
+                pos = size
+                chunks: list[bytes] = []
+                total = 0
+                newline_count = 0
+
+                while pos > 0 and (total < max_bytes or newline_count <= tail_lines + 1) and total < max_bytes * 2:
+                    read_size = min(chunk_size, pos)
+                    pos -= read_size
+                    f.seek(pos)
+                    chunk = f.read(read_size)
+                    chunks.insert(0, chunk)
+                    total += len(chunk)
+                    newline_count += chunk.count(b"\n")
+                    chunk_size = min(chunk_size * 2, 65536)
+
+                raw = b"".join(chunks)
+                truncated = pos > 0
+
+        full_raw = raw
+        if truncated and len(full_raw) > max_bytes:
+            cut = len(full_raw) - max_bytes
+            # Check whether the cut lands exactly on a line boundary.  If the
+            # byte just before the cut position is a newline the first retained
+            # byte starts a complete line and we should keep it.  Only drop a
+            # partial first line when we're genuinely mid-line.
+            on_boundary = cut > 0 and full_raw[cut - 1 : cut] == b"\n"
+            full_raw = full_raw[cut:]
+            if not on_boundary and b"\n" in full_raw:
+                full_raw = full_raw.split(b"\n", 1)[1]
+
+        all_text = raw.decode("utf-8", errors="replace")
+        tail_text = "".join(all_text.splitlines(keepends=True)[-tail_lines:]).rstrip("\n")
+
+        full_text = full_raw.decode("utf-8", errors="replace")
+        if truncated:
+            full_text = f"[... truncated — showing last ~{max_bytes // 1024}KB ...]\n{full_text}"
+
+        return LogSnapshot(path=log_path, tail_text=tail_text, full_text=full_text)
+    except Exception as exc:
+        return LogSnapshot(path=log_path, tail_text=f"(error reading: {exc})", full_text=None)
+
+
+def _capture_default_log_snapshots(log_lines: int) -> dict[str, LogSnapshot]:
+    """Capture all logs used by debug-share exactly once."""
+    errors_lines = min(log_lines, 100)
+    return {
+        "agent": _capture_log_snapshot("agent", tail_lines=log_lines),
+        "errors": _capture_log_snapshot("errors", tail_lines=errors_lines),
+        "gateway": _capture_log_snapshot("gateway", tail_lines=errors_lines),
+    }
 
 
 # ---------------------------------------------------------------------------
@@ -405,7 +470,12 @@ def _capture_dump() -> str:
     return capture.getvalue()
 
 
-def collect_debug_report(*, log_lines: int = 200, dump_text: str = "") -> str:
+def collect_debug_report(
+    *,
+    log_lines: int = 200,
+    dump_text: str = "",
+    log_snapshots: Optional[dict[str, LogSnapshot]] = None,
+) -> str:
     """Build the summary debug report: system dump + log tails.
 
     Parameters
@@ -424,19 +494,22 @@ def collect_debug_report(*, log_lines: int = 200, dump_text: str = "") -> str:
         dump_text = _capture_dump()
     buf.write(dump_text)
 
+    if log_snapshots is None:
+        log_snapshots = _capture_default_log_snapshots(log_lines)
+
     # ── Recent log tails (summary only) ──────────────────────────────────
     buf.write("\n\n")
     buf.write(f"--- agent.log (last {log_lines} lines) ---\n")
-    buf.write(_read_log_tail("agent", log_lines))
+    buf.write(log_snapshots["agent"].tail_text)
     buf.write("\n\n")
 
     errors_lines = min(log_lines, 100)
     buf.write(f"--- errors.log (last {errors_lines} lines) ---\n")
-    buf.write(_read_log_tail("errors", errors_lines))
+    buf.write(log_snapshots["errors"].tail_text)
     buf.write("\n\n")
 
     buf.write(f"--- gateway.log (last {errors_lines} lines) ---\n")
-    buf.write(_read_log_tail("gateway", errors_lines))
+    buf.write(log_snapshots["gateway"].tail_text)
     buf.write("\n")
 
     return buf.getvalue()
@@ -448,6 +521,8 @@ def collect_debug_report(*, log_lines: int = 200, dump_text: str = "") -> str:
 
 def run_debug_share(args):
     """Collect debug report + full logs, upload each, print URLs."""
+    _best_effort_sweep_expired_pastes()
+
     log_lines = getattr(args, "lines", 200)
     expiry = getattr(args, "expire", 7)
     local_only = getattr(args, "local", False)
@@ -459,10 +534,15 @@ def run_debug_share(args):
 
     # Capture dump once — prepended to every paste for context.
     dump_text = _capture_dump()
+    log_snapshots = _capture_default_log_snapshots(log_lines)
 
-    report = collect_debug_report(log_lines=log_lines, dump_text=dump_text)
-    agent_log = _read_full_log("agent")
-    gateway_log = _read_full_log("gateway")
+    report = collect_debug_report(
+        log_lines=log_lines,
+        dump_text=dump_text,
+        log_snapshots=log_snapshots,
+    )
+    agent_log = log_snapshots["agent"].full_text
+    gateway_log = log_snapshots["gateway"].full_text
 
     # Prepend dump header to each full log so every paste is self-contained.
     if agent_log:

hermes_cli/doctor.py

@@ -912,6 +912,7 @@ def run_doctor(args):
     _apikey_providers = [
         ("Z.AI / GLM",      ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"), "https://api.z.ai/api/paas/v4/models", "GLM_BASE_URL", True),
         ("Kimi / Moonshot",  ("KIMI_API_KEY",),                              "https://api.moonshot.ai/v1/models",   "KIMI_BASE_URL", True),
+        ("StepFun Step Plan",   ("STEPFUN_API_KEY",),                           "https://api.stepfun.ai/step_plan/v1/models", "STEPFUN_BASE_URL", True),
         ("Kimi / Moonshot (China)", ("KIMI_CN_API_KEY",),                    "https://api.moonshot.cn/v1/models",   None, True),
         ("Arcee AI",         ("ARCEEAI_API_KEY",),                            "https://api.arcee.ai/api/v1/models",  "ARCEE_BASE_URL", True),
         ("DeepSeek",         ("DEEPSEEK_API_KEY",),                           "https://api.deepseek.com/v1/models",  "DEEPSEEK_BASE_URL", True),

hermes_cli/env_loader.py

@@ -160,6 +160,8 @@ def load_hermes_dotenv(
     # Fix corrupted .env files before python-dotenv parses them (#8908).
     if user_env.exists():
         _sanitize_env_file_if_needed(user_env)
+    if project_env_path and project_env_path.exists():
+        _sanitize_env_file_if_needed(project_env_path)
 
     if user_env.exists():
         _load_dotenv_with_fallback(user_env, override=True)

hermes_cli/gateway.py

@@ -333,6 +333,147 @@ def _probe_systemd_service_running(system: bool = False) -> tuple[bool, bool]:
     return selected_system, result.stdout.strip() == "active"
 
 
+def _read_systemd_unit_properties(
+    system: bool = False,
+    properties: tuple[str, ...] = (
+        "ActiveState",
+        "SubState",
+        "Result",
+        "ExecMainStatus",
+    ),
+) -> dict[str, str]:
+    """Return selected ``systemctl show`` properties for the gateway unit."""
+    selected_system = _select_systemd_scope(system)
+    try:
+        result = _run_systemctl(
+            [
+                "show",
+                get_service_name(),
+                "--no-pager",
+                "--property",
+                ",".join(properties),
+            ],
+            system=selected_system,
+            capture_output=True,
+            text=True,
+            timeout=10,
+        )
+    except (RuntimeError, subprocess.TimeoutExpired, OSError):
+        return {}
+
+    if result.returncode != 0:
+        return {}
+
+    parsed: dict[str, str] = {}
+    for line in result.stdout.splitlines():
+        if "=" not in line:
+            continue
+        key, value = line.split("=", 1)
+        parsed[key] = value.strip()
+    return parsed
+
+
+def _wait_for_systemd_service_restart(
+    *,
+    system: bool = False,
+    previous_pid: int | None = None,
+    timeout: float = 60.0,
+) -> bool:
+    """Wait for the gateway service to become active after a restart handoff."""
+    import time
+
+    svc = get_service_name()
+    scope_label = _service_scope_label(system).capitalize()
+    deadline = time.time() + timeout
+
+    while time.time() < deadline:
+        props = _read_systemd_unit_properties(system=system)
+        active_state = props.get("ActiveState", "")
+        sub_state = props.get("SubState", "")
+        new_pid = None
+        try:
+            from gateway.status import get_running_pid
+
+            new_pid = get_running_pid()
+        except Exception:
+            new_pid = None
+
+        if active_state == "active":
+            if new_pid and (previous_pid is None or new_pid != previous_pid):
+                print(f"✓ {scope_label} service restarted (PID {new_pid})")
+                return True
+            if previous_pid is None:
+                print(f"✓ {scope_label} service restarted")
+                return True
+
+        if active_state == "activating" and sub_state == "auto-restart":
+            time.sleep(1)
+            continue
+
+        time.sleep(2)
+
+    print(
+        f"⚠ {scope_label} service did not become active within {int(timeout)}s.\n"
+        f"  Check status: {'sudo ' if system else ''}hermes gateway status\n"
+        f"  Check logs:   journalctl {'--user ' if not system else ''}-u {svc} -l --since '2 min ago'"
+    )
+    return False
+
+
+def _recover_pending_systemd_restart(system: bool = False, previous_pid: int | None = None) -> bool:
+    """Recover a planned service restart that is stuck in systemd state."""
+    props = _read_systemd_unit_properties(system=system)
+    if not props:
+        return False
+
+    try:
+        from gateway.status import read_runtime_status
+    except Exception:
+        return False
+
+    runtime_state = read_runtime_status() or {}
+    if not runtime_state.get("restart_requested"):
+        return False
+
+    active_state = props.get("ActiveState", "")
+    sub_state = props.get("SubState", "")
+    exec_main_status = props.get("ExecMainStatus", "")
+    result = props.get("Result", "")
+
+    if active_state == "activating" and sub_state == "auto-restart":
+        print("⏳ Service restart already pending — waiting for systemd relaunch...")
+        return _wait_for_systemd_service_restart(
+            system=system,
+            previous_pid=previous_pid,
+        )
+
+    if active_state == "failed" and (
+        exec_main_status == str(GATEWAY_SERVICE_RESTART_EXIT_CODE)
+        or result == "exit-code"
+    ):
+        svc = get_service_name()
+        scope_label = _service_scope_label(system).capitalize()
+        print(f"↻ Clearing failed state for pending {scope_label.lower()} service restart...")
+        _run_systemctl(
+            ["reset-failed", svc],
+            system=system,
+            check=False,
+            timeout=30,
+        )
+        _run_systemctl(
+            ["start", svc],
+            system=system,
+            check=False,
+            timeout=90,
+        )
+        return _wait_for_systemd_service_restart(
+            system=system,
+            previous_pid=previous_pid,
+        )
+
+    return False
+
+
 def _probe_launchd_service_running() -> bool:
     if not get_launchd_plist_path().exists():
         return False
@@ -470,7 +611,8 @@ def stop_profile_gateway() -> bool:
         except (ProcessLookupError, PermissionError):
             break
 
-    remove_pid_file()
+    if get_running_pid() is None:
+        remove_pid_file()
     return True
 
 
@@ -1505,14 +1647,9 @@ def systemd_restart(system: bool = False):
 
     pid = get_running_pid()
     if pid is not None and _request_gateway_self_restart(pid):
-        # SIGUSR1 sent — the gateway will drain active agents, exit with
-        # code 75, and systemd will restart it after RestartSec (30s).
-        # Wait for the old process to die and the new one to become active
-        # so the CLI doesn't return while the service is still restarting.
         import time
         scope_label = _service_scope_label(system).capitalize()
         svc = get_service_name()
-        scope_cmd = _systemctl_cmd(system)
 
         # Phase 1: wait for old process to exit (drain + shutdown)
         print(f"⏳ {scope_label} service draining active work...")
@@ -1526,48 +1663,41 @@ def systemd_restart(system: bool = False):
         else:
             print(f"⚠ Old process (PID {pid}) still alive after 90s")
 
-        # Phase 2: wait for systemd to start the new process
-        print(f"⏳ Waiting for {svc} to restart...")
-        deadline = time.time() + 60
-        while time.time() < deadline:
-            try:
-                result = subprocess.run(
-                    scope_cmd + ["is-active", svc],
-                    capture_output=True, text=True, timeout=5,
-                )
-                if result.stdout.strip() == "active":
-                    # Verify it's a NEW process, not the old one somehow
-                    new_pid = get_running_pid()
-                    if new_pid and new_pid != pid:
-                        print(f"✓ {scope_label} service restarted (PID {new_pid})")
-                        return
-            except (subprocess.TimeoutExpired, FileNotFoundError):
-                pass
-            time.sleep(2)
-
-        # Timed out — check final state
-        try:
-            result = subprocess.run(
-                scope_cmd + ["is-active", svc],
-                capture_output=True, text=True, timeout=5,
-            )
-            if result.stdout.strip() == "active":
-                print(f"✓ {scope_label} service restarted")
-                return
-        except Exception:
-            pass
-        print(
-            f"⚠ {scope_label} service did not become active within 60s.\n"
-            f"  Check status: {'sudo ' if system else ''}hermes gateway status\n"
-            f"  Check logs:   journalctl {'--user ' if not system else ''}-u {svc} --since '2 min ago'"
+        # The gateway exits with code 75 for a planned service restart.
+        # systemd can sit in the RestartSec window or even wedge itself into a
+        # failed/rate-limited state if the operator asks for another restart in
+        # the middle of that handoff. Clear any stale failed state and kick the
+        # unit immediately so `hermes gateway restart` behaves idempotently.
+        _run_systemctl(
+            ["reset-failed", svc],
+            system=system,
+            check=False,
+            timeout=30,
         )
+        _run_systemctl(
+            ["start", svc],
+            system=system,
+            check=False,
+            timeout=90,
+        )
+        _wait_for_systemd_service_restart(system=system, previous_pid=pid)
         return
+
+    if _recover_pending_systemd_restart(system=system, previous_pid=pid):
+        return
+
+    _run_systemctl(
+        ["reset-failed", get_service_name()],
+        system=system,
+        check=False,
+        timeout=30,
+    )
     _run_systemctl(["reload-or-restart", get_service_name()], system=system, check=True, timeout=90)
     print(f"✓ {_service_scope_label(system).capitalize()} service restarted")
 
 
 
-def systemd_status(deep: bool = False, system: bool = False):
+def systemd_status(deep: bool = False, system: bool = False, full: bool = False):
     system = _select_systemd_scope(system)
     unit_path = get_systemd_unit_path(system=system)
     scope_flag = " --system" if system else ""
@@ -1590,8 +1720,12 @@ def systemd_status(deep: bool = False, system: bool = False):
         print(f"  Run: {'sudo ' if system else ''}hermes gateway restart{scope_flag}  # auto-refreshes the unit")
         print()
 
+    status_cmd = ["status", get_service_name(), "--no-pager"]
+    if full:
+        status_cmd.append("-l")
+
     _run_systemctl(
-        ["status", get_service_name(), "--no-pager"],
+        status_cmd,
         system=system,
         capture_output=False,
         timeout=10,
@@ -1624,6 +1758,19 @@ def systemd_status(deep: bool = False, system: bool = False):
         for line in runtime_lines:
             print(f"  {line}")
 
+    unit_props = _read_systemd_unit_properties(system=system)
+    active_state = unit_props.get("ActiveState", "")
+    sub_state = unit_props.get("SubState", "")
+    exec_main_status = unit_props.get("ExecMainStatus", "")
+    result_code = unit_props.get("Result", "")
+    if active_state == "activating" and sub_state == "auto-restart":
+        print("  ⏳ Restart pending: systemd is waiting to relaunch the gateway")
+    elif active_state == "failed" and exec_main_status == str(GATEWAY_SERVICE_RESTART_EXIT_CODE):
+        print("  ⚠ Planned restart is stuck in systemd failed state (exit 75)")
+        print(f"  Run: systemctl {'--user ' if not system else ''}reset-failed {get_service_name()} && {'sudo ' if system else ''}hermes gateway start{scope_flag}")
+    elif active_state == "failed" and result_code:
+        print(f"  ⚠ Systemd unit result: {result_code}")
+
     if system:
         print("✓ System service starts at boot without requiring systemd linger")
     elif deep:
@@ -1639,7 +1786,10 @@ def systemd_status(deep: bool = False, system: bool = False):
     if deep:
         print()
         print("Recent logs:")
-        subprocess.run(_journalctl_cmd(system) + ["-u", get_service_name(), "-n", "20", "--no-pager"], timeout=10)
+        log_cmd = _journalctl_cmd(system) + ["-u", get_service_name(), "-n", "20", "--no-pager"]
+        if full:
+            log_cmd.append("-l")
+        subprocess.run(log_cmd, timeout=10)
 
 
 # =============================================================================
@@ -2639,9 +2789,120 @@ def _setup_dingtalk():
 
 
 def _setup_wecom():
-    """Configure WeCom (Enterprise WeChat) via the standard platform setup."""
-    wecom_platform = next(p for p in _PLATFORMS if p["key"] == "wecom")
-    _setup_standard_platform(wecom_platform)
+    """Interactive setup for WeCom — scan QR code or manual credential input."""
+    print()
+    print(color("  ─── 💬 WeCom (Enterprise WeChat) Setup ───", Colors.CYAN))
+
+    existing_bot_id = get_env_value("WECOM_BOT_ID")
+    existing_secret = get_env_value("WECOM_SECRET")
+    if existing_bot_id and existing_secret:
+        print()
+        print_success("WeCom is already configured.")
+        if not prompt_yes_no("  Reconfigure WeCom?", False):
+            return
+
+    # ── Choose setup method ──
+    print()
+    method_choices = [
+        "Scan QR code to obtain Bot ID and Secret automatically (recommended)",
+        "Enter existing Bot ID and Secret manually",
+    ]
+    method_idx = prompt_choice("  How would you like to set up WeCom?", method_choices, 0)
+
+    bot_id = None
+    secret = None
+
+    if method_idx == 0:
+        # ── QR scan flow ──
+        try:
+            from gateway.platforms.wecom import qr_scan_for_bot_info
+        except Exception as exc:
+            print_error(f"  WeCom QR scan import failed: {exc}")
+            qr_scan_for_bot_info = None
+
+        if qr_scan_for_bot_info is not None:
+            try:
+                credentials = qr_scan_for_bot_info()
+            except KeyboardInterrupt:
+                print()
+                print_warning("  WeCom setup cancelled.")
+                return
+            except Exception as exc:
+                print_warning(f"  QR scan failed: {exc}")
+                credentials = None
+            if credentials:
+                bot_id = credentials.get("bot_id", "")
+                secret = credentials.get("secret", "")
+                print_success("  ✔ QR scan successful! Bot ID and Secret obtained.")
+
+        if not bot_id or not secret:
+            print_info("  QR scan did not complete. Continuing with manual input.")
+            bot_id = None
+            secret = None
+
+    # ── Manual credential input ──
+    if not bot_id or not secret:
+        print()
+        print_info("  1. Go to WeCom Application → Workspace → Smart Robot -> Create smart robots")
+        print_info("  2. Select API Mode")
+        print_info("  3. Copy the Bot ID and Secret from the bot's credentials info")
+        print_info("  4. The bot connects via WebSocket — no public endpoint needed")
+        print()
+        bot_id = prompt("  Bot ID", password=False)
+        if not bot_id:
+            print_warning("  Skipped — WeCom won't work without a Bot ID.")
+            return
+        secret = prompt("  Secret", password=True)
+        if not secret:
+            print_warning("  Skipped — WeCom won't work without a Secret.")
+            return
+
+    # ── Save core credentials ──
+    save_env_value("WECOM_BOT_ID", bot_id)
+    save_env_value("WECOM_SECRET", secret)
+
+    # ── Allowed users (deny-by-default security) ──
+    print()
+    print_info("  The gateway DENIES all users by default for security.")
+    print_info("  Enter user IDs to create an allowlist, or leave empty.")
+    allowed = prompt("  Allowed user IDs (comma-separated, or empty)", password=False)
+    if allowed:
+        cleaned = allowed.replace(" ", "")
+        save_env_value("WECOM_ALLOWED_USERS", cleaned)
+        print_success("  Saved — only these users can interact with the bot.")
+    else:
+        print()
+        access_choices = [
+            "Enable open access (anyone can message the bot)",
+            "Use DM pairing (unknown users request access, you approve with 'hermes pairing approve')",
+            "Disable direct messages",
+            "Skip for now (bot will deny all users until configured)",
+        ]
+        access_idx = prompt_choice("  How should unauthorized users be handled?", access_choices, 1)
+        if access_idx == 0:
+            save_env_value("WECOM_DM_POLICY", "open")
+            save_env_value("GATEWAY_ALLOW_ALL_USERS", "true")
+            print_warning("  Open access enabled — anyone can use your bot!")
+        elif access_idx == 1:
+            save_env_value("WECOM_DM_POLICY", "pairing")
+            print_success("  DM pairing mode — users will receive a code to request access.")
+            print_info("  Approve with: hermes pairing approve <platform> <code>")
+        elif access_idx == 2:
+            save_env_value("WECOM_DM_POLICY", "disabled")
+            print_warning("  Direct messages disabled.")
+        else:
+            print_info("  Skipped — configure later with 'hermes gateway setup'")
+
+    # ── Home channel (optional) ──
+    print()
+    print_info("  Chat ID for scheduled results and notifications.")
+    home = prompt("  Home chat ID (optional, for cron/notifications)", password=False)
+    if home:
+        save_env_value("WECOM_HOME_CHANNEL", home)
+        print_success(f"  Home channel set to {home}")
+
+    print()
+    print_success("💬 WeCom configured!")
 
 
 def _is_service_installed() -> bool:
@@ -3021,7 +3282,8 @@ def _setup_qqbot():
     if method_idx == 0:
         # ── QR scan-to-configure ──
         try:
-            credentials = _qqbot_qr_flow()
+            from gateway.platforms.qqbot import qr_register
+            credentials = qr_register()
         except KeyboardInterrupt:
             print()
             print_warning("  QQ Bot setup cancelled.")
@@ -3103,106 +3365,6 @@ def _setup_qqbot():
     print_info(f"  App ID: {credentials['app_id']}")
 
 
-def _qqbot_render_qr(url: str) -> bool:
-    """Try to render a QR code in the terminal. Returns True if successful."""
-    try:
-        import qrcode as _qr
-        qr = _qr.QRCode(border=1,error_correction=_qr.constants.ERROR_CORRECT_L)
-        qr.add_data(url)
-        qr.make(fit=True)
-        qr.print_ascii(invert=True)
-        return True
-    except Exception:
-        return False
-
-
-def _qqbot_qr_flow():
-    """Run the QR-code scan-to-configure flow.
-
-    Returns a dict with app_id, client_secret, user_openid on success,
-    or None on failure/cancel.
-    """
-    try:
-        from gateway.platforms.qqbot import (
-            create_bind_task, poll_bind_result, build_connect_url,
-            decrypt_secret, BindStatus,
-        )
-        from gateway.platforms.qqbot.constants import ONBOARD_POLL_INTERVAL
-    except Exception as exc:
-        print_error(f"  QQBot onboard import failed: {exc}")
-        return None
-
-    import asyncio
-    import time
-
-    MAX_REFRESHES = 3
-    refresh_count = 0
-
-    while refresh_count <= MAX_REFRESHES:
-        loop = asyncio.new_event_loop()
-
-        # ── Create bind task ──
-        try:
-            task_id, aes_key = loop.run_until_complete(create_bind_task())
-        except Exception as e:
-            print_warning(f"  Failed to create bind task: {e}")
-            loop.close()
-            return None
-
-        url = build_connect_url(task_id)
-
-        # ── Display QR code + URL ──
-        print()
-        if _qqbot_render_qr(url):
-            print(f"  Scan the QR code above, or open this URL directly:\n  {url}")
-        else:
-            print(f"  Open this URL in QQ on your phone:\n  {url}")
-            print_info("  Tip: pip install qrcode  to show a scannable QR code here")
-
-        # ── Poll loop (silent — keep QR visible at bottom) ──
-        try:
-            while True:
-                try:
-                    status, app_id, encrypted_secret, user_openid = loop.run_until_complete(
-                        poll_bind_result(task_id)
-                    )
-                except Exception:
-                    time.sleep(ONBOARD_POLL_INTERVAL)
-                    continue
-
-                if status == BindStatus.COMPLETED:
-                    client_secret = decrypt_secret(encrypted_secret, aes_key)
-                    print()
-                    print_success(f"  QR scan complete! (App ID: {app_id})")
-                    if user_openid:
-                        print_info(f"  Scanner's OpenID: {user_openid}")
-                    return {
-                        "app_id": app_id,
-                        "client_secret": client_secret,
-                        "user_openid": user_openid,
-                    }
-
-                if status == BindStatus.EXPIRED:
-                    refresh_count += 1
-                    if refresh_count > MAX_REFRESHES:
-                        print()
-                        print_warning(f"  QR code expired {MAX_REFRESHES} times — giving up.")
-                        return None
-                    print()
-                    print_warning(f"  QR code expired, refreshing... ({refresh_count}/{MAX_REFRESHES})")
-                    loop.close()
-                    break  # outer while creates a new task
-
-                time.sleep(ONBOARD_POLL_INTERVAL)
-        except KeyboardInterrupt:
-            loop.close()
-            raise
-        finally:
-            loop.close()
-
-    return None
-
-
 def _setup_signal():
     """Interactive setup for Signal messenger."""
     import shutil
@@ -3390,6 +3552,8 @@ def gateway_setup():
             _setup_feishu()
         elif platform["key"] == "qqbot":
             _setup_qqbot()
+        elif platform["key"] == "wecom":
+            _setup_wecom()
         else:
             _setup_standard_platform(platform)
 
@@ -3748,12 +3912,13 @@ def gateway_command(args):
     
     elif subcmd == "status":
         deep = getattr(args, 'deep', False)
+        full = getattr(args, 'full', False)
         system = getattr(args, 'system', False)
         snapshot = get_gateway_runtime_snapshot(system=system)
         
         # Check for service first
         if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
-            systemd_status(deep, system=system)
+            systemd_status(deep, system=system, full=full)
             _print_gateway_process_mismatch(snapshot)
         elif is_macos() and get_launchd_plist_path().exists():
             launchd_status(deep)

hermes_cli/main.py

@@ -1566,6 +1566,8 @@ def select_provider_and_model(args=None):
         _model_flow_anthropic(config, current_model)
     elif selected_provider == "kimi-coding":
         _model_flow_kimi(config, current_model)
+    elif selected_provider == "stepfun":
+        _model_flow_stepfun(config, current_model)
     elif selected_provider == "bedrock":
         _model_flow_bedrock(config, current_model)
     elif selected_provider in (
@@ -3462,6 +3464,140 @@ def _model_flow_kimi(config, current_model=""):
         print("No change.")
 
 
+def _infer_stepfun_region(base_url: str) -> str:
+    """Infer the current StepFun region from the configured endpoint."""
+    normalized = (base_url or "").strip().lower()
+    if "api.stepfun.com" in normalized:
+        return "china"
+    return "international"
+
+
+def _stepfun_base_url_for_region(region: str) -> str:
+    from hermes_cli.auth import (
+        STEPFUN_STEP_PLAN_CN_BASE_URL,
+        STEPFUN_STEP_PLAN_INTL_BASE_URL,
+    )
+
+    return (
+        STEPFUN_STEP_PLAN_CN_BASE_URL
+        if region == "china"
+        else STEPFUN_STEP_PLAN_INTL_BASE_URL
+    )
+
+
+def _model_flow_stepfun(config, current_model=""):
+    """StepFun Step Plan flow with region-specific endpoints."""
+    from hermes_cli.auth import (
+        PROVIDER_REGISTRY,
+        _prompt_model_selection,
+        _save_model_choice,
+        deactivate_provider,
+    )
+    from hermes_cli.config import get_env_value, save_env_value, load_config, save_config
+    from hermes_cli.models import fetch_api_models
+
+    provider_id = "stepfun"
+    pconfig = PROVIDER_REGISTRY[provider_id]
+    key_env = pconfig.api_key_env_vars[0] if pconfig.api_key_env_vars else ""
+    base_url_env = pconfig.base_url_env_var or ""
+
+    existing_key = ""
+    for ev in pconfig.api_key_env_vars:
+        existing_key = get_env_value(ev) or os.getenv(ev, "")
+        if existing_key:
+            break
+
+    if not existing_key:
+        print(f"No {pconfig.name} API key configured.")
+        if key_env:
+            try:
+                import getpass
+                new_key = getpass.getpass(f"{key_env} (or Enter to cancel): ").strip()
+            except (KeyboardInterrupt, EOFError):
+                print()
+                return
+            if not new_key:
+                print("Cancelled.")
+                return
+            save_env_value(key_env, new_key)
+            existing_key = new_key
+            print("API key saved.")
+            print()
+    else:
+        print(f"  {pconfig.name} API key: {existing_key[:8]}... ✓")
+        print()
+
+    current_base = ""
+    if base_url_env:
+        current_base = get_env_value(base_url_env) or os.getenv(base_url_env, "")
+    if not current_base:
+        model_cfg = config.get("model")
+        if isinstance(model_cfg, dict):
+            current_base = str(model_cfg.get("base_url") or "").strip()
+    current_region = _infer_stepfun_region(current_base or pconfig.inference_base_url)
+
+    region_choices = [
+        ("international", f"International ({_stepfun_base_url_for_region('international')})"),
+        ("china", f"China ({_stepfun_base_url_for_region('china')})"),
+    ]
+    ordered_regions = []
+    for region_key, label in region_choices:
+        if region_key == current_region:
+            ordered_regions.insert(0, (region_key, f"{label}  ← currently active"))
+        else:
+            ordered_regions.append((region_key, label))
+    ordered_regions.append(("cancel", "Cancel"))
+
+    region_idx = _prompt_provider_choice([label for _, label in ordered_regions])
+    if region_idx is None or ordered_regions[region_idx][0] == "cancel":
+        print("No change.")
+        return
+
+    selected_region = ordered_regions[region_idx][0]
+    effective_base = _stepfun_base_url_for_region(selected_region)
+    if base_url_env:
+        save_env_value(base_url_env, effective_base)
+
+    live_models = fetch_api_models(existing_key, effective_base)
+    if live_models:
+        model_list = live_models
+        print(f"  Found {len(model_list)} model(s) from {pconfig.name} API")
+    else:
+        model_list = _PROVIDER_MODELS.get(provider_id, [])
+        if model_list:
+            print(
+                f"  Could not auto-detect models from {pconfig.name} API — "
+                "showing Step Plan fallback catalog."
+            )
+
+    if model_list:
+        selected = _prompt_model_selection(model_list, current_model=current_model)
+    else:
+        try:
+            selected = input("Model name: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            selected = None
+
+    if selected:
+        _save_model_choice(selected)
+
+        cfg = load_config()
+        model = cfg.get("model")
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = provider_id
+        model["base_url"] = effective_base
+        model.pop("api_mode", None)
+        save_config(cfg)
+        deactivate_provider()
+
+        config["model"] = dict(model)
+        print(f"Default model set to: {selected} (via {pconfig.name})")
+    else:
+        print("No change.")
+
+
 def _model_flow_bedrock_api_key(config, region, current_model=""):
     """Bedrock API Key mode — uses the OpenAI-compatible bedrock-mantle endpoint.
 
@@ -6530,6 +6666,7 @@ For more help on a command:
             "zai",
             "kimi-coding",
             "kimi-coding-cn",
+            "stepfun",
             "minimax",
             "minimax-cn",
             "kilocode",
@@ -6751,6 +6888,12 @@ For more help on a command:
     # gateway status
     gateway_status = gateway_subparsers.add_parser("status", help="Show gateway status")
     gateway_status.add_argument("--deep", action="store_true", help="Deep status check")
+    gateway_status.add_argument(
+        "-l",
+        "--full",
+        action="store_true",
+        help="Show full, untruncated service/log output where supported",
+    )
     gateway_status.add_argument(
         "--system",
         action="store_true",

hermes_cli/model_switch.py

@@ -143,7 +143,7 @@ MODEL_ALIASES: dict[str, ModelIdentity] = {
     # Z.AI / GLM
     "glm":       ModelIdentity("z-ai", "glm"),
 
-    # StepFun
+    # Step Plan (StepFun)
     "step":      ModelIdentity("stepfun", "step"),
 
     # Xiaomi
@@ -810,7 +810,10 @@ def list_authenticated_providers(
         get_provider_info as _mdev_pinfo,
     )
     from hermes_cli.auth import PROVIDER_REGISTRY
-    from hermes_cli.models import OPENROUTER_MODELS, _PROVIDER_MODELS
+    from hermes_cli.models import (
+        OPENROUTER_MODELS, _PROVIDER_MODELS,
+        _MODELS_DEV_PREFERRED, _merge_with_models_dev,
+    )
 
     results: List[dict] = []
     seen_slugs: set = set()  # lowercase-normalized to catch case variants (#9545)
@@ -856,8 +859,13 @@ def list_authenticated_providers(
         if not has_creds:
             continue
 
-        # Use curated list, falling back to models.dev if no curated list
+        # Use curated list, falling back to models.dev if no curated list.
+        # For preferred providers, merge models.dev entries into the curated
+        # catalog so newly released models (e.g. mimo-v2.5-pro on opencode-go)
+        # show up in the picker without requiring a Hermes release.
         model_ids = curated.get(hermes_id, [])
+        if hermes_id in _MODELS_DEV_PREFERRED:
+            model_ids = _merge_with_models_dev(hermes_id, model_ids)
         total = len(model_ids)
         top = model_ids[:max_models]
 
@@ -961,6 +969,9 @@ def list_authenticated_providers(
 
         # 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]
 

hermes_cli/models.py

@@ -42,7 +42,8 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("openrouter/elephant-alpha",       "free"),
     ("openai/gpt-5.4",                  ""),
     ("openai/gpt-5.4-mini",             ""),
-    ("xiaomi/mimo-v2-pro",               ""),
+    ("xiaomi/mimo-v2.5-pro",             ""),
+    ("xiaomi/mimo-v2.5",                 ""),
     ("openai/gpt-5.3-codex",            ""),
     ("google/gemini-3-pro-image-preview", ""),
     ("google/gemini-3-flash-preview",   ""),
@@ -108,7 +109,8 @@ def _codex_curated_models() -> list[str]:
 _PROVIDER_MODELS: dict[str, list[str]] = {
     "nous": [
         "moonshotai/kimi-k2.6",
-        "xiaomi/mimo-v2-pro",
+        "xiaomi/mimo-v2.5-pro",
+        "xiaomi/mimo-v2.5",
         "anthropic/claude-opus-4.7",
         "anthropic/claude-opus-4.6",
         "anthropic/claude-sonnet-4.6",
@@ -210,6 +212,10 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-turbo-preview",
         "kimi-k2-0905-preview",
     ],
+    "stepfun": [
+        "step-3.5-flash",
+        "step-3.5-flash-2603",
+    ],
     "moonshot": [
         "kimi-k2.6",
         "kimi-k2.5",
@@ -699,6 +705,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("zai",            "Z.AI / GLM",               "Z.AI / GLM (Zhipu AI direct API)"),
     ProviderEntry("kimi-coding",    "Kimi / Kimi Coding Plan",  "Kimi Coding Plan (api.kimi.com) & Moonshot API"),
     ProviderEntry("kimi-coding-cn", "Kimi / Moonshot (China)",  "Kimi / Moonshot China (Moonshot CN direct API)"),
+    ProviderEntry("stepfun",        "StepFun Step Plan",       "StepFun Step Plan (agent/coding models via Step Plan API)"),
     ProviderEntry("minimax",        "MiniMax",                  "MiniMax (global direct API)"),
     ProviderEntry("minimax-cn",     "MiniMax (China)",          "MiniMax China (domestic direct API)"),
     ProviderEntry("alibaba",        "Alibaba Cloud (DashScope)","Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
@@ -733,6 +740,8 @@ _PROVIDER_ALIASES = {
     "moonshot": "kimi-coding",
     "kimi-cn": "kimi-coding-cn",
     "moonshot-cn": "kimi-coding-cn",
+    "step": "stepfun",
+    "stepfun-coding-plan": "stepfun",
     "arcee-ai": "arcee",
     "arceeai": "arcee",
     "minimax-china": "minimax-cn",
@@ -1580,11 +1589,84 @@ def _resolve_copilot_catalog_api_key() -> str:
         return ""
 
 
+# Providers where models.dev is treated as authoritative: curated static
+# lists are kept only as an offline fallback and to capture custom additions
+# the registry doesn't publish yet. Adding a provider here causes its
+# curated list to be merged with fresh models.dev entries (fresh first, any
+# curated-only names appended) for both the CLI and the gateway /model picker.
+#
+# DELIBERATELY EXCLUDED:
+#   - "openrouter": curated list is already a hand-picked agentic subset of
+#     OpenRouter's 400+ catalog. Blindly merging would dump everything.
+#   - "nous": curated list and Portal /models endpoint are the source of
+#     truth for the subscription tier.
+# Also excluded: providers that already have dedicated live-endpoint
+# branches below (copilot, anthropic, ai-gateway, ollama-cloud, custom,
+# stepfun, openai-codex) — those paths handle freshness themselves.
+_MODELS_DEV_PREFERRED: frozenset[str] = frozenset({
+    "opencode-go",
+    "opencode-zen",
+    "deepseek",
+    "kilocode",
+    "fireworks",
+    "mistral",
+    "togetherai",
+    "cohere",
+    "perplexity",
+    "groq",
+    "nvidia",
+    "huggingface",
+    "zai",
+    "gemini",
+    "google",
+})
+
+
+def _merge_with_models_dev(provider: str, curated: list[str]) -> list[str]:
+    """Merge curated list with fresh models.dev entries for a preferred provider.
+
+    Returns models.dev entries first (in models.dev order), then any
+    curated-only entries appended. Preserves case for curated fallbacks
+    (e.g. ``MiniMax-M2.7``) while trusting models.dev for newer variants.
+
+    If models.dev is unreachable or returns nothing, the curated list is
+    returned unchanged — this is the offline/CI fallback path.
+    """
+    try:
+        from agent.models_dev import list_agentic_models
+        mdev = list_agentic_models(provider)
+    except Exception:
+        mdev = []
+
+    if not mdev:
+        return list(curated)
+
+    # Case-insensitive dedup while preserving order and curated casing.
+    seen_lower: set[str] = set()
+    merged: list[str] = []
+    for mid in mdev:
+        key = str(mid).lower()
+        if key in seen_lower:
+            continue
+        seen_lower.add(key)
+        merged.append(mid)
+    for mid in curated:
+        key = str(mid).lower()
+        if key in seen_lower:
+            continue
+        seen_lower.add(key)
+        merged.append(mid)
+    return merged
+
+
 def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False) -> list[str]:
     """Return the best known model catalog for a provider.
 
     Tries live API endpoints for providers that support them (Codex, Nous),
-    falling back to static lists.
+    falling back to static lists. For providers in ``_MODELS_DEV_PREFERRED``
+    (opencode-go/zen, xiaomi, deepseek, smaller inference providers, etc.),
+    models.dev entries are merged on top of curated so new models released
+    on the platform appear in ``/model`` without a Hermes release.
     """
     normalized = normalize_provider(provider)
     if normalized == "openrouter":
@@ -1613,6 +1695,19 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
                     return live
         except Exception:
             pass
+    if normalized == "stepfun":
+        try:
+            from hermes_cli.auth import resolve_api_key_provider_credentials
+
+            creds = resolve_api_key_provider_credentials("stepfun")
+            api_key = str(creds.get("api_key") or "").strip()
+            base_url = str(creds.get("base_url") or "").strip()
+            if api_key and base_url:
+                live = fetch_api_models(api_key, base_url)
+                if live:
+                    return live
+        except Exception:
+            pass
     if normalized == "anthropic":
         live = _fetch_anthropic_models()
         if live:
@@ -1637,7 +1732,10 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
             live = fetch_api_models(api_key, base_url)
             if live:
                 return live
-    return list(_PROVIDER_MODELS.get(normalized, []))
+    curated_static = list(_PROVIDER_MODELS.get(normalized, []))
+    if normalized in _MODELS_DEV_PREFERRED:
+        return _merge_with_models_dev(normalized, curated_static)
+    return curated_static
 
 
 def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:

hermes_cli/plugins.py

@@ -283,6 +283,7 @@ class PluginContext:
         name: str,
         handler: Callable,
         description: str = "",
+        args_hint: str = "",
     ) -> None:
         """Register a slash command (e.g. ``/lcm``) available in CLI and gateway sessions.
 
@@ -293,6 +294,13 @@ class PluginContext:
         terminal commands), this registers in-session slash commands that users
         invoke during a conversation.
 
+        ``args_hint`` is an optional short string (e.g. ``"<file>"`` or
+        ``"dias:7 formato:json"``) used by gateway adapters to surface the
+        command with an argument field — for example Discord's native slash
+        command picker. Plugin commands without ``args_hint`` register as
+        parameterless in Discord and still accept trailing text when invoked
+        as free-form chat.
+
         Names conflicting with built-in commands are rejected with a warning.
         """
         clean = name.lower().strip().lstrip("/").replace(" ", "-")
@@ -320,6 +328,7 @@ class PluginContext:
             "handler": handler,
             "description": description or "Plugin command",
             "plugin": self.manifest.name,
+            "args_hint": (args_hint or "").strip(),
         }
         logger.debug("Plugin %s registered command: /%s", self.manifest.name, clean)
 
@@ -734,6 +743,30 @@ class PluginManager:
                 )
                 kind = "standalone"
 
+            # Auto-coerce user-installed memory providers to kind="exclusive"
+            # so they're routed to plugins/memory discovery instead of being
+            # loaded by the general PluginManager (which has no
+            # register_memory_provider on PluginContext). Mirrors the
+            # heuristic in plugins/memory/__init__.py:_is_memory_provider_dir.
+            # Bundled memory providers are already skipped via skip_names.
+            if kind == "standalone" and "kind" not in data:
+                init_file = plugin_dir / "__init__.py"
+                if init_file.exists():
+                    try:
+                        source_text = init_file.read_text(errors="replace")[:8192]
+                        if (
+                            "register_memory_provider" in source_text
+                            or "MemoryProvider" in source_text
+                        ):
+                            kind = "exclusive"
+                            logger.debug(
+                                "Plugin %s: detected memory provider, "
+                                "treating as kind='exclusive'",
+                                key,
+                            )
+                    except Exception:
+                        pass
+
             return PluginManifest(
                 name=name,
                 version=str(data.get("version", "")),

hermes_cli/providers.py

@@ -94,6 +94,12 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         transport="openai_chat",
         base_url_env_var="KIMI_BASE_URL",
     ),
+    "stepfun": HermesOverlay(
+        transport="openai_chat",
+        extra_env_vars=("STEPFUN_API_KEY",),
+        base_url_override="https://api.stepfun.ai/step_plan/v1",
+        base_url_env_var="STEPFUN_BASE_URL",
+    ),
     "minimax": HermesOverlay(
         transport="anthropic_messages",
         base_url_env_var="MINIMAX_BASE_URL",
@@ -210,6 +216,10 @@ ALIASES: Dict[str, str] = {
     "kimi-coding-cn": "kimi-for-coding",
     "moonshot": "kimi-for-coding",
 
+    # stepfun
+    "step": "stepfun",
+    "stepfun-coding-plan": "stepfun",
+
     # minimax-cn
     "minimax-china": "minimax-cn",
     "minimax_cn": "minimax-cn",
@@ -294,6 +304,7 @@ _LABEL_OVERRIDES: Dict[str, str] = {
     "nous": "Nous Portal",
     "openai-codex": "OpenAI Codex",
     "copilot-acp": "GitHub Copilot ACP",
+    "stepfun": "StepFun Step Plan",
     "xiaomi": "Xiaomi MiMo",
     "local": "Local endpoint",
     "bedrock": "AWS Bedrock",

hermes_cli/pty_bridge.py

@@ -0,0 +1,221 @@
+"""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:
+            raise PtyUnavailableError(
+                "Pseudo-terminals are unavailable on this platform. "
+                "Hermes Agent supports Windows only via WSL."
+            )
+        # 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/setup.py

@@ -96,6 +96,7 @@ _DEFAULT_PROVIDER_MODELS = {
     "zai": ["glm-5.1", "glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"],
     "kimi-coding": ["kimi-k2.6", "kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
     "kimi-coding-cn": ["kimi-k2.6", "kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
+    "stepfun": ["step-3.5-flash", "step-3.5-flash-2603"],
     "arcee": ["trinity-large-thinking", "trinity-large-preview", "trinity-mini"],
     "minimax": ["MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"],
     "minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.5", "MiniMax-M2.1", "MiniMax-M2"],
@@ -804,6 +805,7 @@ def setup_model_provider(config: dict, *, quick: bool = False):
             "zai": "Z.AI / GLM",
             "kimi-coding": "Kimi / Moonshot",
             "kimi-coding-cn": "Kimi / Moonshot (China)",
+            "stepfun": "StepFun Step Plan",
             "minimax": "MiniMax",
             "minimax-cn": "MiniMax CN",
             "anthropic": "Anthropic",

hermes_cli/skin_engine.py

@@ -30,6 +30,14 @@ All fields are optional. Missing values inherit from the ``default`` skin.
       prompt: "#FFF8DC"                  # Prompt text color
       input_rule: "#CD7F32"              # Input area horizontal rule
       response_border: "#FFD700"         # Response box border (ANSI)
+      status_bar_bg: "#1a1a2e"           # Status bar background
+      status_bar_text: "#C0C0C0"         # Status bar default text
+      status_bar_strong: "#FFD700"       # Status bar highlighted text
+      status_bar_dim: "#8B8682"          # Status bar separators/muted text
+      status_bar_good: "#8FBC8F"         # Healthy context usage
+      status_bar_warn: "#FFD700"         # Warning context usage
+      status_bar_bad: "#FF8C00"          # High context usage
+      status_bar_critical: "#FF6B6B"     # Critical context usage
       session_label: "#DAA520"           # Session label color
       session_border: "#8B8682"          # Session ID dim color
       status_bar_bg: "#1a1a2e"          # TUI status/usage bar background
@@ -170,6 +178,7 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#FFF8DC",
             "input_rule": "#CD7F32",
             "response_border": "#FFD700",
+            "status_bar_bg": "#1a1a2e",
             "session_label": "#DAA520",
             "session_border": "#8B8682",
         },
@@ -203,6 +212,14 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#F1E6CF",
             "input_rule": "#9F1C1C",
             "response_border": "#C7A96B",
+            "status_bar_bg": "#2A1212",
+            "status_bar_text": "#F1E6CF",
+            "status_bar_strong": "#C7A96B",
+            "status_bar_dim": "#6E584B",
+            "status_bar_good": "#7BC96F",
+            "status_bar_warn": "#C7A96B",
+            "status_bar_bad": "#DD4A3A",
+            "status_bar_critical": "#EF5350",
             "session_label": "#C7A96B",
             "session_border": "#6E584B",
         },
@@ -267,6 +284,14 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#c9d1d9",
             "input_rule": "#444444",
             "response_border": "#aaaaaa",
+            "status_bar_bg": "#1F1F1F",
+            "status_bar_text": "#C9D1D9",
+            "status_bar_strong": "#E6EDF3",
+            "status_bar_dim": "#777777",
+            "status_bar_good": "#B5B5B5",
+            "status_bar_warn": "#AAAAAA",
+            "status_bar_bad": "#D0D0D0",
+            "status_bar_critical": "#F0F0F0",
             "session_label": "#888888",
             "session_border": "#555555",
         },
@@ -298,6 +323,14 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#c9d1d9",
             "input_rule": "#4169e1",
             "response_border": "#7eb8f6",
+            "status_bar_bg": "#151C2F",
+            "status_bar_text": "#C9D1D9",
+            "status_bar_strong": "#7EB8F6",
+            "status_bar_dim": "#4B5563",
+            "status_bar_good": "#63D0A6",
+            "status_bar_warn": "#E6A855",
+            "status_bar_bad": "#F7A072",
+            "status_bar_critical": "#FF7A7A",
             "session_label": "#7eb8f6",
             "session_border": "#4b5563",
         },
@@ -403,6 +436,14 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#EAF7FF",
             "input_rule": "#2A6FB9",
             "response_border": "#5DB8F5",
+            "status_bar_bg": "#0F2440",
+            "status_bar_text": "#EAF7FF",
+            "status_bar_strong": "#A9DFFF",
+            "status_bar_dim": "#496884",
+            "status_bar_good": "#6ED7B0",
+            "status_bar_warn": "#5DB8F5",
+            "status_bar_bad": "#2A6FB9",
+            "status_bar_critical": "#D94F4F",
             "session_label": "#A9DFFF",
             "session_border": "#496884",
         },
@@ -467,6 +508,14 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#F5F5F5",
             "input_rule": "#656565",
             "response_border": "#B7B7B7",
+            "status_bar_bg": "#202020",
+            "status_bar_text": "#D3D3D3",
+            "status_bar_strong": "#F5F5F5",
+            "status_bar_dim": "#656565",
+            "status_bar_good": "#B7B7B7",
+            "status_bar_warn": "#D3D3D3",
+            "status_bar_bad": "#E7E7E7",
+            "status_bar_critical": "#F5F5F5",
             "session_label": "#919191",
             "session_border": "#656565",
         },
@@ -532,6 +581,14 @@ _BUILTIN_SKINS: Dict[str, Dict[str, Any]] = {
             "prompt": "#FFF0D4",
             "input_rule": "#C75B1D",
             "response_border": "#F29C38",
+            "status_bar_bg": "#2B160E",
+            "status_bar_text": "#FFF0D4",
+            "status_bar_strong": "#FFD39A",
+            "status_bar_dim": "#6C4724",
+            "status_bar_good": "#6BCB77",
+            "status_bar_warn": "#F29C38",
+            "status_bar_bad": "#E2832B",
+            "status_bar_critical": "#EF5350",
             "session_label": "#FFD39A",
             "session_border": "#6C4724",
         },
@@ -770,6 +827,13 @@ def get_prompt_toolkit_style_overrides() -> Dict[str, str]:
     warn = skin.get_color("ui_warn", "#FF8C00")
     error = skin.get_color("ui_error", "#FF6B6B")
     status_bg = skin.get_color("status_bar_bg", "#1a1a2e")
+    status_text = skin.get_color("status_bar_text", text)
+    status_strong = skin.get_color("status_bar_strong", title)
+    status_dim = skin.get_color("status_bar_dim", dim)
+    status_good = skin.get_color("status_bar_good", skin.get_color("ui_ok", "#8FBC8F"))
+    status_warn = skin.get_color("status_bar_warn", warn)
+    status_bad = skin.get_color("status_bar_bad", skin.get_color("banner_accent", warn))
+    status_critical = skin.get_color("status_bar_critical", error)
     voice_bg = skin.get_color("voice_status_bg", status_bg)
     menu_bg = skin.get_color("completion_menu_bg", "#1a1a2e")
     menu_current_bg = skin.get_color("completion_menu_current_bg", "#333355")
@@ -782,13 +846,13 @@ def get_prompt_toolkit_style_overrides() -> Dict[str, str]:
         "prompt": prompt,
         "prompt-working": f"{dim} italic",
         "hint": f"{dim} italic",
-        "status-bar": f"bg:{status_bg} {text}",
-        "status-bar-strong": f"bg:{status_bg} {title} bold",
-        "status-bar-dim": f"bg:{status_bg} {dim}",
-        "status-bar-good": f"bg:{status_bg} {skin.get_color('ui_ok', '#8FBC8F')} bold",
-        "status-bar-warn": f"bg:{status_bg} {warn} bold",
-        "status-bar-bad": f"bg:{status_bg} {skin.get_color('banner_accent', warn)} bold",
-        "status-bar-critical": f"bg:{status_bg} {error} bold",
+        "status-bar": f"bg:{status_bg} {status_text}",
+        "status-bar-strong": f"bg:{status_bg} {status_strong} bold",
+        "status-bar-dim": f"bg:{status_bg} {status_dim}",
+        "status-bar-good": f"bg:{status_bg} {status_good} bold",
+        "status-bar-warn": f"bg:{status_bg} {status_warn} bold",
+        "status-bar-bad": f"bg:{status_bg} {status_bad} bold",
+        "status-bar-critical": f"bg:{status_bg} {status_critical} bold",
         "input-rule": input_rule,
         "image-badge": f"{label} bold",
         "completion-menu": f"bg:{menu_bg} {text}",

hermes_cli/status.py

@@ -122,6 +122,7 @@ def show_status(args):
         "OpenAI": "OPENAI_API_KEY",
         "Z.AI/GLM": "GLM_API_KEY",
         "Kimi": "KIMI_API_KEY",
+        "StepFun Step Plan": "STEPFUN_API_KEY",
         "MiniMax": "MINIMAX_API_KEY",
         "MiniMax-CN": "MINIMAX_CN_API_KEY",
         "Firecrawl": "FIRECRAWL_API_KEY",
@@ -252,6 +253,7 @@ def show_status(args):
     apikey_providers = {
         "Z.AI / GLM":       ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"),
         "Kimi / Moonshot":  ("KIMI_API_KEY",),
+        "StepFun Step Plan": ("STEPFUN_API_KEY",),
         "MiniMax":          ("MINIMAX_API_KEY",),
         "MiniMax (China)":  ("MINIMAX_CN_API_KEY",),
     }

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
@@ -2189,7 +2189,8 @@ async def get_usage_analytics(days: int = 30):
                    SUM(reasoning_tokens) as reasoning_tokens,
                    COALESCE(SUM(estimated_cost_usd), 0) as estimated_cost,
                    COALESCE(SUM(actual_cost_usd), 0) as actual_cost,
-                   COUNT(*) as sessions
+                   COUNT(*) as sessions,
+                   SUM(COALESCE(api_call_count, 0)) as api_calls
             FROM sessions WHERE started_at > ?
             GROUP BY day ORDER BY day
         """, (cutoff,))
@@ -2200,7 +2201,8 @@ async def get_usage_analytics(days: int = 30):
                    SUM(input_tokens) as input_tokens,
                    SUM(output_tokens) as output_tokens,
                    COALESCE(SUM(estimated_cost_usd), 0) as estimated_cost,
-                   COUNT(*) as sessions
+                   COUNT(*) as sessions,
+                   SUM(COALESCE(api_call_count, 0)) as api_calls
             FROM sessions WHERE started_at > ? AND model IS NOT NULL
             GROUP BY model ORDER BY SUM(input_tokens) + SUM(output_tokens) DESC
         """, (cutoff,))
@@ -2213,7 +2215,8 @@ async def get_usage_analytics(days: int = 30):
                    SUM(reasoning_tokens) as total_reasoning,
                    COALESCE(SUM(estimated_cost_usd), 0) as total_estimated_cost,
                    COALESCE(SUM(actual_cost_usd), 0) as total_actual_cost,
-                   COUNT(*) as total_sessions
+                   COUNT(*) as total_sessions,
+                   SUM(COALESCE(api_call_count, 0)) as total_api_calls
             FROM sessions WHERE started_at > ?
         """, (cutoff,))
         totals = dict(cur3.fetchone())
@@ -2239,6 +2242,148 @@ 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
+# 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"})
+
+
+def _resolve_chat_argv(
+    resume: 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.
+    """
+    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:
+        env = os.environ.copy()
+        env["HERMES_TUI_RESUME"] = resume
+    return list(argv), str(cwd) if cwd else None, env
+
+
+@app.websocket("/api/pty")
+async def pty_ws(ws: WebSocket) -> None:
+    # --- 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
+    try:
+        argv, cwd, env = _resolve_chat_argv(resume=resume)
+    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()
+
+
 def mount_spa(application: FastAPI):
     """Mount the built SPA. Falls back to index.html for client-side routing.
 

hermes_state.py

@@ -31,7 +31,7 @@ T = TypeVar("T")
 
 DEFAULT_DB_PATH = get_hermes_home() / "state.db"
 
-SCHEMA_VERSION = 6
+SCHEMA_VERSION = 8
 
 SCHEMA_SQL = """
 CREATE TABLE IF NOT EXISTS schema_version (
@@ -65,6 +65,7 @@ CREATE TABLE IF NOT EXISTS sessions (
     cost_source TEXT,
     pricing_version TEXT,
     title TEXT,
+    api_call_count INTEGER DEFAULT 0,
     FOREIGN KEY (parent_session_id) REFERENCES sessions(id)
 );
 
@@ -80,10 +81,16 @@ CREATE TABLE IF NOT EXISTS messages (
     token_count INTEGER,
     finish_reason TEXT,
     reasoning TEXT,
+    reasoning_content TEXT,
     reasoning_details TEXT,
     codex_reasoning_items TEXT
 );
 
+CREATE TABLE IF NOT EXISTS state_meta (
+    key TEXT PRIMARY KEY,
+    value TEXT
+);
+
 CREATE INDEX IF NOT EXISTS idx_sessions_source ON sessions(source);
 CREATE INDEX IF NOT EXISTS idx_sessions_parent ON sessions(parent_session_id);
 CREATE INDEX IF NOT EXISTS idx_sessions_started ON sessions(started_at DESC);
@@ -329,6 +336,26 @@ class SessionDB:
                     except sqlite3.OperationalError:
                         pass  # Column already exists
                 cursor.execute("UPDATE schema_version SET version = 6")
+            if current_version < 7:
+                # v7: preserve provider-native reasoning_content separately from
+                # normalized reasoning text. Kimi/Moonshot replay can require
+                # this field on assistant tool-call messages when thinking is on.
+                try:
+                    cursor.execute('ALTER TABLE messages ADD COLUMN "reasoning_content" TEXT')
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 7")
+            if current_version < 8:
+                # v8: add api_call_count column to sessions — tracks the number
+                # of individual LLM API calls made within a session (as opposed
+                # to the session count itself).
+                try:
+                    cursor.execute(
+                        'ALTER TABLE sessions ADD COLUMN "api_call_count" INTEGER DEFAULT 0'
+                    )
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 8")
 
         # Unique title index — always ensure it exists (safe to run after migrations
         # since the title column is guaranteed to exist at this point)
@@ -435,6 +462,7 @@ class SessionDB:
         billing_provider: Optional[str] = None,
         billing_base_url: Optional[str] = None,
         billing_mode: Optional[str] = None,
+        api_call_count: int = 0,
         absolute: bool = False,
     ) -> None:
         """Update token counters and backfill model if not already set.
@@ -464,7 +492,8 @@ class SessionDB:
                    billing_provider = COALESCE(billing_provider, ?),
                    billing_base_url = COALESCE(billing_base_url, ?),
                    billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
+                   model = COALESCE(model, ?),
+                   api_call_count = ?
                    WHERE id = ?"""
         else:
             sql = """UPDATE sessions SET
@@ -484,7 +513,8 @@ class SessionDB:
                    billing_provider = COALESCE(billing_provider, ?),
                    billing_base_url = COALESCE(billing_base_url, ?),
                    billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
+                   model = COALESCE(model, ?),
+                   api_call_count = COALESCE(api_call_count, 0) + ?
                    WHERE id = ?"""
         params = (
             input_tokens,
@@ -502,6 +532,7 @@ class SessionDB:
             billing_base_url,
             billing_mode,
             model,
+            api_call_count,
             session_id,
         )
         def _do(conn):
@@ -922,6 +953,7 @@ class SessionDB:
         token_count: int = None,
         finish_reason: str = None,
         reasoning: str = None,
+        reasoning_content: str = None,
         reasoning_details: Any = None,
         codex_reasoning_items: Any = None,
     ) -> int:
@@ -951,8 +983,8 @@ 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_details, codex_reasoning_items)
-                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
+                   reasoning, reasoning_content, reasoning_details, codex_reasoning_items)
+                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
                 (
                     session_id,
                     role,
@@ -964,6 +996,7 @@ class SessionDB:
                     token_count,
                     finish_reason,
                     reasoning,
+                    reasoning_content,
                     reasoning_details_json,
                     codex_items_json,
                 ),
@@ -1014,7 +1047,7 @@ class SessionDB:
         with self._lock:
             cursor = self._conn.execute(
                 "SELECT role, content, tool_call_id, tool_calls, tool_name, "
-                "reasoning, reasoning_details, codex_reasoning_items "
+                "reasoning, reasoning_content, reasoning_details, codex_reasoning_items "
                 "FROM messages WHERE session_id = ? ORDER BY timestamp, id",
                 (session_id,),
             )
@@ -1038,6 +1071,8 @@ class SessionDB:
             if row["role"] == "assistant":
                 if row["reasoning"]:
                     msg["reasoning"] = row["reasoning"]
+                if row["reasoning_content"] is not None:
+                    msg["reasoning_content"] = row["reasoning_content"]
                 if row["reasoning_details"]:
                     try:
                         msg["reasoning_details"] = json.loads(row["reasoning_details"])
@@ -1441,3 +1476,116 @@ class SessionDB:
             return len(session_ids)
 
         return self._execute_write(_do)
+
+    # ── Meta key/value (for scheduler bookkeeping) ──
+
+    def get_meta(self, key: str) -> Optional[str]:
+        """Read a value from the state_meta key/value store."""
+        with self._lock:
+            row = self._conn.execute(
+                "SELECT value FROM state_meta WHERE key = ?", (key,)
+            ).fetchone()
+        if row is None:
+            return None
+        return row["value"] if isinstance(row, sqlite3.Row) else row[0]
+
+    def set_meta(self, key: str, value: str) -> None:
+        """Write a value to the state_meta key/value store."""
+        def _do(conn):
+            conn.execute(
+                "INSERT INTO state_meta (key, value) VALUES (?, ?) "
+                "ON CONFLICT(key) DO UPDATE SET value = excluded.value",
+                (key, value),
+            )
+        self._execute_write(_do)
+
+    # ── Space reclamation ──
+
+    def vacuum(self) -> None:
+        """Run VACUUM to reclaim disk space after large deletes.
+
+        SQLite does not shrink the database file when rows are deleted —
+        freed pages just get reused on the next insert. After a prune that
+        removed hundreds of sessions, the file stays bloated unless we
+        explicitly VACUUM.
+
+        VACUUM rewrites the entire DB, so it's expensive (seconds per
+        100MB) and cannot run inside a transaction. It also acquires an
+        exclusive lock, so callers must ensure no other writers are
+        active. Safe to call at startup before the gateway/CLI starts
+        serving traffic.
+        """
+        # VACUUM cannot be executed inside a transaction.
+        with self._lock:
+            # Best-effort WAL checkpoint first, then VACUUM.
+            try:
+                self._conn.execute("PRAGMA wal_checkpoint(TRUNCATE)")
+            except Exception:
+                pass
+            self._conn.execute("VACUUM")
+
+    def maybe_auto_prune_and_vacuum(
+        self,
+        retention_days: int = 90,
+        min_interval_hours: int = 24,
+        vacuum: bool = True,
+    ) -> Dict[str, Any]:
+        """Idempotent auto-maintenance: prune old sessions + optional VACUUM.
+
+        Records the last run timestamp in state_meta so subsequent calls
+        within ``min_interval_hours`` no-op. Designed to be called once at
+        startup from long-lived entrypoints (CLI, gateway, cron scheduler).
+
+        Never raises. On any failure, logs a warning and returns a dict
+        with ``"error"`` set.
+
+        Returns a dict with keys:
+          - ``"skipped"`` (bool) — true if within min_interval_hours of last run
+          - ``"pruned"`` (int)   — number of sessions deleted
+          - ``"vacuumed"`` (bool) — true if VACUUM ran
+          - ``"error"`` (str, optional) — present only on failure
+        """
+        result: Dict[str, Any] = {"skipped": False, "pruned": 0, "vacuumed": False}
+        try:
+            # Skip if another process/call did maintenance recently.
+            last_raw = self.get_meta("last_auto_prune")
+            now = time.time()
+            if last_raw:
+                try:
+                    last_ts = float(last_raw)
+                    if now - last_ts < min_interval_hours * 3600:
+                        result["skipped"] = True
+                        return result
+                except (TypeError, ValueError):
+                    pass  # corrupt meta; treat as no prior run
+
+            pruned = self.prune_sessions(older_than_days=retention_days)
+            result["pruned"] = pruned
+
+            # Only VACUUM if we actually freed rows — VACUUM on a tight DB
+            # is wasted I/O. Threshold keeps small DBs from paying the cost.
+            if vacuum and pruned > 0:
+                try:
+                    self.vacuum()
+                    result["vacuumed"] = True
+                except Exception as exc:
+                    logger.warning("state.db VACUUM failed: %s", exc)
+
+            # Record the attempt even if pruned == 0, so we don't retry
+            # every startup within the min_interval_hours window.
+            self.set_meta("last_auto_prune", str(now))
+
+            if pruned > 0:
+                logger.info(
+                    "state.db auto-maintenance: pruned %d session(s) older than %d days%s",
+                    pruned,
+                    retention_days,
+                    " + VACUUM" if result["vacuumed"] else "",
+                )
+        except Exception as exc:
+            # Maintenance must never block startup. Log and return error marker.
+            logger.warning("state.db auto-maintenance failed: %s", exc)
+            result["error"] = str(exc)
+
+        return result
+

model_tools.py

@@ -108,9 +108,15 @@ def _run_async(coro):
     if loop and loop.is_running():
         # Inside an async context (gateway, RL env) — run in a fresh thread.
         import concurrent.futures
-        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-            future = pool.submit(asyncio.run, coro)
+        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
+        future = pool.submit(asyncio.run, coro)
+        try:
             return future.result(timeout=300)
+        except concurrent.futures.TimeoutError:
+            future.cancel()
+            raise
+        finally:
+            pool.shutdown(wait=False, cancel_futures=True)
 
     # If we're on a worker thread (e.g., parallel tool execution in
     # delegate_task), use a per-thread persistent loop.  This avoids

nix/nixosModules.nix

@@ -28,7 +28,7 @@
 
   let
     cfg = config.services.hermes-agent;
-    hermes-agent = inputs.self.packages.${pkgs.system}.default;
+    hermes-agent = inputs.self.packages.${pkgs.stdenv.hostPlatform.system}.default;
 
     # Deep-merge config type (from 0xrsydn/nix-hermes-agent)
     deepConfigType = lib.types.mkOptionType {

optional-skills/web-development/DESCRIPTION.md

@@ -0,0 +1,5 @@
+# Web Development
+
+Optional skills for client-side web development workflows — embedding agents, copilots, and AI-native UX patterns into user-facing web apps.
+
+These are distinct from Hermes' own browser automation (Browserbase, Camofox), which operate *on* websites from outside. Web-development skills here help users build *into* their own websites.

optional-skills/web-development/page-agent/SKILL.md

@@ -0,0 +1,189 @@
+---
+name: page-agent
+description: Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script> tag or npm package and lets end-users of your site drive the UI with natural language ("click login, fill username as John"). No Python, no headless browser, no extension required. Use this skill when the user is a web developer who wants to add an AI copilot to their SaaS / admin panel / B2B tool, make a legacy web app accessible via natural language, or evaluate page-agent against a local (Ollama) or cloud (Qwen / OpenAI / OpenRouter) LLM. NOT for server-side browser automation — point those users to Hermes' built-in browser tool instead.
+version: 1.0.0
+author: Hermes Agent
+license: MIT
+metadata:
+  hermes:
+    tags: [web, javascript, agent, browser, gui, alibaba, embed, copilot, saas]
+    category: web-development
+---
+
+# page-agent
+
+alibaba/page-agent (https://github.com/alibaba/page-agent, 17k+ stars, MIT) is an in-page GUI agent written in TypeScript. It lives inside a webpage, reads the DOM as text (no screenshots, no multi-modal LLM), and executes natural-language instructions like "click the login button, then fill username as John" against the current page. Pure client-side — the host site just includes a script and passes an OpenAI-compatible LLM endpoint.
+
+## When to use this skill
+
+Load this skill when a user wants to:
+
+- **Ship an AI copilot inside their own web app** (SaaS, admin panel, B2B tool, ERP, CRM) — "users on my dashboard should be able to type 'create invoice for Acme Corp and email it' instead of clicking through five screens"
+- **Modernize a legacy web app** without rewriting the frontend — page-agent drops on top of existing DOM
+- **Add accessibility via natural language** — voice / screen-reader users drive the UI by describing what they want
+- **Demo or evaluate page-agent** against a local (Ollama) or hosted (Qwen, OpenAI, OpenRouter) LLM
+- **Build interactive training / product demos** — let an AI walk a user through "how to submit an expense report" live in the real UI
+
+## When NOT to use this skill
+
+- User wants **Hermes itself to drive a browser** → use Hermes' built-in browser tool (Browserbase / Camofox). page-agent is the *opposite* direction.
+- User wants **cross-tab automation without embedding** → use Playwright, browser-use, or the page-agent Chrome extension
+- User needs **visual grounding / screenshots** → page-agent is text-DOM only; use a multimodal browser agent instead
+
+## Prerequisites
+
+- Node 22.13+ or 24+, npm 10+ (docs claim 11+ but 10.9 works fine)
+- An OpenAI-compatible LLM endpoint: Qwen (DashScope), OpenAI, Ollama, OpenRouter, or anything speaking `/v1/chat/completions`
+- Browser with devtools (for debugging)
+
+## Path 1 — 30-second demo via CDN (no install)
+
+Fastest way to see it work. Uses alibaba's free testing LLM proxy — **for evaluation only**, subject to their terms.
+
+Add to any HTML page (or paste into the devtools console as a bookmarklet):
+
+```html
+<script src="https://cdn.jsdelivr.net/npm/page-agent@1.8.0/dist/iife/page-agent.demo.js" crossorigin="true"></script>
+```
+
+A panel appears. Type an instruction. Done.
+
+Bookmarklet form (drop into bookmarks bar, click on any page):
+
+```javascript
+javascript:(function(){var s=document.createElement('script');s.src='https://cdn.jsdelivr.net/npm/page-agent@1.8.0/dist/iife/page-agent.demo.js';document.head.appendChild(s);})();
+```
+
+## Path 2 — npm install into your own web app (production use)
+
+Inside an existing web project (React / Vue / Svelte / plain):
+
+```bash
+npm install page-agent
+```
+
+Wire it up with your own LLM endpoint — **never ship the demo CDN to real users**:
+
+```javascript
+import { PageAgent } from 'page-agent'
+
+const agent = new PageAgent({
+    model: 'qwen3.5-plus',
+    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+    apiKey: process.env.LLM_API_KEY,   // never hardcode
+    language: 'en-US',
+})
+
+// Show the panel for end users:
+agent.panel.show()
+
+// Or drive it programmatically:
+await agent.execute('Click submit button, then fill username as John')
+```
+
+Provider examples (any OpenAI-compatible endpoint works):
+
+| Provider | `baseURL` | `model` |
+|----------|-----------|---------|
+| Qwen / DashScope | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `qwen3.5-plus` |
+| OpenAI | `https://api.openai.com/v1` | `gpt-4o-mini` |
+| Ollama (local) | `http://localhost:11434/v1` | `qwen3:14b` |
+| OpenRouter | `https://openrouter.ai/api/v1` | `anthropic/claude-sonnet-4.6` |
+
+**Key config fields** (passed to `new PageAgent({...})`):
+
+- `model`, `baseURL`, `apiKey` — LLM connection
+- `language` — UI language (`en-US`, `zh-CN`, etc.)
+- Allowlist and data-masking hooks exist for locking down what the agent can touch — see https://alibaba.github.io/page-agent/ for the full option list
+
+**Security.** Don't put your `apiKey` in client-side code for a real deployment — proxy LLM calls through your backend and point `baseURL` at your proxy. The demo CDN exists because alibaba runs that proxy for evaluation.
+
+## Path 3 — clone the source repo (contributing, or hacking on it)
+
+Use this when the user wants to modify page-agent itself, test it against arbitrary sites via a local IIFE bundle, or develop the browser extension.
+
+```bash
+git clone https://github.com/alibaba/page-agent.git
+cd page-agent
+npm ci              # exact lockfile install (or `npm i` to allow updates)
+```
+
+Create `.env` in the repo root with an LLM endpoint. Example:
+
+```
+LLM_MODEL_NAME=gpt-4o-mini
+LLM_API_KEY=sk-...
+LLM_BASE_URL=https://api.openai.com/v1
+```
+
+Ollama flavor:
+
+```
+LLM_BASE_URL=http://localhost:11434/v1
+LLM_API_KEY=NA
+LLM_MODEL_NAME=qwen3:14b
+```
+
+Common commands:
+
+```bash
+npm start           # docs/website dev server
+npm run build       # build every package
+npm run dev:demo    # serve IIFE bundle at http://localhost:5174/page-agent.demo.js
+npm run dev:ext     # develop the browser extension (WXT + React)
+npm run build:ext   # build the extension
+```
+
+**Test on any website** using the local IIFE bundle. Add this bookmarklet:
+
+```javascript
+javascript:(function(){var s=document.createElement('script');s.src=`http://localhost:5174/page-agent.demo.js?t=${Math.random()}`;s.onload=()=>console.log('PageAgent ready!');document.head.appendChild(s);})();
+```
+
+Then: `npm run dev:demo`, click the bookmarklet on any page, and the local build injects. Auto-rebuilds on save.
+
+**Warning:** your `.env` `LLM_API_KEY` is inlined into the IIFE bundle during dev builds. Don't share the bundle. Don't commit it. Don't paste the URL into Slack. (Verified: grepping the public dev bundle returns the literal values from `.env`.)
+
+## Repo layout (Path 3)
+
+Monorepo with npm workspaces. Key packages:
+
+| Package | Path | Purpose |
+|---------|------|---------|
+| `page-agent` | `packages/page-agent/` | Main entry with UI panel |
+| `@page-agent/core` | `packages/core/` | Core agent logic, no UI |
+| `@page-agent/mcp` | `packages/mcp/` | MCP server (beta) |
+| — | `packages/llms/` | LLM client |
+| — | `packages/page-controller/` | DOM ops + visual feedback |
+| — | `packages/ui/` | Panel + i18n |
+| — | `packages/extension/` | Chrome/Firefox extension |
+| — | `packages/website/` | Docs + landing site |
+
+## Verifying it works
+
+After Path 1 or Path 2:
+1. Open the page in a browser with devtools open
+2. You should see a floating panel. If not, check the console for errors (most common: CORS on the LLM endpoint, wrong `baseURL`, or a bad API key)
+3. Type a simple instruction matching something visible on the page ("click the Login link")
+4. Watch the Network tab — you should see a request to your `baseURL`
+
+After Path 3:
+1. `npm run dev:demo` prints `Accepting connections at http://localhost:5174`
+2. `curl -I http://localhost:5174/page-agent.demo.js` returns `HTTP/1.1 200 OK` with `Content-Type: application/javascript`
+3. Click the bookmarklet on any site; panel appears
+
+## Pitfalls
+
+- **Demo CDN in production** — don't. It's rate-limited, uses alibaba's free proxy, and their terms forbid production use.
+- **API key exposure** — any key passed to `new PageAgent({apiKey: ...})` ships in your JS bundle. Always proxy through your own backend for real deployments.
+- **Non-OpenAI-compatible endpoints** fail silently or with cryptic errors. If your provider needs native Anthropic/Gemini formatting, use an OpenAI-compatibility proxy (LiteLLM, OpenRouter) in front.
+- **CSP blocks** — sites with strict Content-Security-Policy may refuse to load the CDN script or disallow inline eval. In that case, self-host from your origin.
+- **Restart dev server** after editing `.env` in Path 3 — Vite only reads env at startup.
+- **Node version** — the repo declares `^22.13.0 || >=24`. Node 20 will fail `npm ci` with engine errors.
+- **npm 10 vs 11** — docs say npm 11+; npm 10.9 actually works fine.
+
+## Reference
+
+- Repo: https://github.com/alibaba/page-agent
+- Docs: https://alibaba.github.io/page-agent/
+- License: MIT (built on browser-use's DOM processing internals, Copyright 2024 Gregor Zunic)

package.json

@@ -16,8 +16,8 @@
   },
   "homepage": "https://github.com/NousResearch/Hermes-Agent#readme",
   "dependencies": {
-    "agent-browser": "^0.13.0",
-    "@askjo/camofox-browser": "^1.5.2"
+    "@askjo/camofox-browser": "^1.5.2",
+    "agent-browser": "^0.26.0"
   },
   "overrides": {
     "lodash": "4.18.1"

plugins/memory/hindsight/README.md

@@ -84,7 +84,10 @@ Config file: `~/.hermes/hindsight/config.json`
 | `retain_async` | `true` | Process retain asynchronously on the Hindsight server |
 | `retain_every_n_turns` | `1` | Retain every N turns (1 = every turn) |
 | `retain_context` | `conversation between Hermes Agent and the User` | Context label for retained memories |
-| `tags` | — | Tags applied when storing memories |
+| `retain_tags` | — | Default tags applied to retained memories; merged with per-call tool tags |
+| `retain_source` | — | Optional `metadata.source` attached to retained memories |
+| `retain_user_prefix` | `User` | Label used before user turns in auto-retained transcripts |
+| `retain_assistant_prefix` | `Assistant` | Label used before assistant turns in auto-retained transcripts |
 
 ### Integration
 
@@ -113,7 +116,7 @@ Available in `hybrid` and `tools` memory modes:
 
 | Tool | Description |
 |------|-------------|
-| `hindsight_retain` | Store information with auto entity extraction |
+| `hindsight_retain` | Store information with auto entity extraction; supports optional per-call `tags` |
 | `hindsight_recall` | Multi-strategy search (semantic + entity graph) |
 | `hindsight_reflect` | Cross-memory synthesis (LLM-powered) |
 

plugins/memory/hindsight/__init__.py

@@ -6,11 +6,15 @@ retrieval. Supports cloud (API key) and local modes.
 Original PR #1811 by benfrank241, adapted to MemoryProvider ABC.
 
 Config via environment variables:
-  HINDSIGHT_API_KEY   — API key for Hindsight Cloud
-  HINDSIGHT_BANK_ID   — memory bank identifier (default: hermes)
-  HINDSIGHT_BUDGET    — recall budget: low/mid/high (default: mid)
-  HINDSIGHT_API_URL   — API endpoint
-  HINDSIGHT_MODE      — cloud or local (default: cloud)
+  HINDSIGHT_API_KEY                — API key for Hindsight Cloud
+  HINDSIGHT_BANK_ID                — memory bank identifier (default: hermes)
+  HINDSIGHT_BUDGET                 — recall budget: low/mid/high (default: mid)
+  HINDSIGHT_API_URL                — API endpoint
+  HINDSIGHT_MODE                   — cloud or local (default: cloud)
+  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
+  HINDSIGHT_RETAIN_ASSISTANT_PREFIX — label used before assistant turns in retained transcripts
 
 Or via $HERMES_HOME/hindsight/config.json (profile-scoped), falling back to
 ~/.hindsight/config.json (legacy, shared) for backward compatibility.
@@ -24,7 +28,7 @@ import logging
 import os
 import threading
 
-from hermes_constants import get_hermes_home
+from datetime import datetime, timezone
 from typing import Any, Dict, List
 
 from agent.memory_provider import MemoryProvider
@@ -99,6 +103,11 @@ RETAIN_SCHEMA = {
         "properties": {
             "content": {"type": "string", "description": "The information to store."},
             "context": {"type": "string", "description": "Short label (e.g. 'user preference', 'project decision')."},
+            "tags": {
+                "type": "array",
+                "items": {"type": "string"},
+                "description": "Optional per-call tags to merge with configured default retain tags.",
+            },
         },
         "required": ["content"],
     },
@@ -168,6 +177,10 @@ def _load_config() -> dict:
     return {
         "mode": os.environ.get("HINDSIGHT_MODE", "cloud"),
         "apiKey": os.environ.get("HINDSIGHT_API_KEY", ""),
+        "retain_tags": os.environ.get("HINDSIGHT_RETAIN_TAGS", ""),
+        "retain_source": os.environ.get("HINDSIGHT_RETAIN_SOURCE", ""),
+        "retain_user_prefix": os.environ.get("HINDSIGHT_RETAIN_USER_PREFIX", "User"),
+        "retain_assistant_prefix": os.environ.get("HINDSIGHT_RETAIN_ASSISTANT_PREFIX", "Assistant"),
         "banks": {
             "hermes": {
                 "bankId": os.environ.get("HINDSIGHT_BANK_ID", "hermes"),
@@ -178,6 +191,48 @@ def _load_config() -> dict:
     }
 
 
+def _normalize_retain_tags(value: Any) -> List[str]:
+    """Normalize tag config/tool values to a deduplicated list of strings."""
+    if value is None:
+        return []
+
+    raw_items: list[Any]
+    if isinstance(value, list):
+        raw_items = value
+    elif isinstance(value, str):
+        text = value.strip()
+        if not text:
+            return []
+        if text.startswith("["):
+            try:
+                parsed = json.loads(text)
+            except Exception:
+                parsed = None
+            if isinstance(parsed, list):
+                raw_items = parsed
+            else:
+                raw_items = text.split(",")
+        else:
+            raw_items = text.split(",")
+    else:
+        raw_items = [value]
+
+    normalized = []
+    seen = set()
+    for item in raw_items:
+        tag = str(item).strip()
+        if not tag or tag in seen:
+            continue
+        seen.add(tag)
+        normalized.append(tag)
+    return normalized
+
+
+def _utc_timestamp() -> str:
+    """Return current UTC timestamp in ISO-8601 with milliseconds and Z suffix."""
+    return datetime.now(timezone.utc).isoformat(timespec="milliseconds").replace("+00:00", "Z")
+
+
 # ---------------------------------------------------------------------------
 # MemoryProvider implementation
 # ---------------------------------------------------------------------------
@@ -195,6 +250,19 @@ class HindsightMemoryProvider(MemoryProvider):
         self._llm_base_url = ""
         self._memory_mode = "hybrid"  # "context", "tools", or "hybrid"
         self._prefetch_method = "recall"  # "recall" or "reflect"
+        self._retain_tags: List[str] = []
+        self._retain_source = ""
+        self._retain_user_prefix = "User"
+        self._retain_assistant_prefix = "Assistant"
+        self._platform = ""
+        self._user_id = ""
+        self._user_name = ""
+        self._chat_id = ""
+        self._chat_name = ""
+        self._chat_type = ""
+        self._thread_id = ""
+        self._agent_identity = ""
+        self._turn_index = 0
         self._client = None
         self._prefetch_result = ""
         self._prefetch_lock = threading.Lock()
@@ -210,6 +278,7 @@ class HindsightMemoryProvider(MemoryProvider):
         # Retain controls
         self._auto_retain = True
         self._retain_every_n_turns = 1
+        self._retain_async = True
         self._retain_context = "conversation between Hermes Agent and the User"
         self._turn_counter = 0
         self._session_turns: list[str] = []  # accumulates ALL turns for the session
@@ -224,7 +293,6 @@ class HindsightMemoryProvider(MemoryProvider):
         # Bank
         self._bank_mission = ""
         self._bank_retain_mission: str | None = None
-        self._retain_async = True
 
     @property
     def name(self) -> str:
@@ -423,7 +491,10 @@ class HindsightMemoryProvider(MemoryProvider):
             {"key": "recall_budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
             {"key": "memory_mode", "description": "Memory integration mode", "default": "hybrid", "choices": ["hybrid", "context", "tools"]},
             {"key": "recall_prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
-            {"key": "tags", "description": "Tags applied when storing memories (comma-separated)", "default": ""},
+            {"key": "retain_tags", "description": "Default tags applied to retained memories (comma-separated)", "default": ""},
+            {"key": "retain_source", "description": "Metadata source value attached to retained memories", "default": ""},
+            {"key": "retain_user_prefix", "description": "Label used before user turns in retained transcripts", "default": "User"},
+            {"key": "retain_assistant_prefix", "description": "Label used before assistant turns in retained transcripts", "default": "Assistant"},
             {"key": "recall_tags", "description": "Tags to filter when searching memories (comma-separated)", "default": ""},
             {"key": "recall_tags_match", "description": "Tag matching mode for recall", "default": "any", "choices": ["any", "all", "any_strict", "all_strict"]},
             {"key": "auto_recall", "description": "Automatically recall memories before each turn", "default": True},
@@ -467,7 +538,7 @@ class HindsightMemoryProvider(MemoryProvider):
         return self._client
 
     def initialize(self, session_id: str, **kwargs) -> None:
-        self._session_id = session_id
+        self._session_id = str(session_id or "").strip()
 
         # Check client version and auto-upgrade if needed
         try:
@@ -496,6 +567,16 @@ class HindsightMemoryProvider(MemoryProvider):
             pass  # packaging not available or other issue — proceed anyway
 
         self._config = _load_config()
+        self._platform = str(kwargs.get("platform") or "").strip()
+        self._user_id = str(kwargs.get("user_id") or "").strip()
+        self._user_name = str(kwargs.get("user_name") or "").strip()
+        self._chat_id = str(kwargs.get("chat_id") or "").strip()
+        self._chat_name = str(kwargs.get("chat_name") or "").strip()
+        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._turn_index = 0
+        self._session_turns = []
         self._mode = self._config.get("mode", "cloud")
         # "local" is a legacy alias for "local_embedded"
         if self._mode == "local":
@@ -513,7 +594,7 @@ class HindsightMemoryProvider(MemoryProvider):
         memory_mode = self._config.get("memory_mode", "hybrid")
         self._memory_mode = memory_mode if memory_mode in ("context", "tools", "hybrid") else "hybrid"
 
-        prefetch_method = self._config.get("recall_prefetch_method", "recall")
+        prefetch_method = self._config.get("recall_prefetch_method") or self._config.get("prefetch_method", "recall")
         self._prefetch_method = prefetch_method if prefetch_method in ("recall", "reflect") else "recall"
 
         # Bank options
@@ -521,9 +602,22 @@ class HindsightMemoryProvider(MemoryProvider):
         self._bank_retain_mission = self._config.get("bank_retain_mission") or None
 
         # Tags
-        self._tags = self._config.get("tags") or None
+        self._retain_tags = _normalize_retain_tags(
+            self._config.get("retain_tags")
+            or os.environ.get("HINDSIGHT_RETAIN_TAGS", "")
+        )
+        self._tags = self._retain_tags or None
         self._recall_tags = self._config.get("recall_tags") or None
         self._recall_tags_match = self._config.get("recall_tags_match", "any")
+        self._retain_source = str(
+            self._config.get("retain_source") or os.environ.get("HINDSIGHT_RETAIN_SOURCE", "")
+        ).strip()
+        self._retain_user_prefix = str(
+            self._config.get("retain_user_prefix") or os.environ.get("HINDSIGHT_RETAIN_USER_PREFIX", "User")
+        ).strip() or "User"
+        self._retain_assistant_prefix = str(
+            self._config.get("retain_assistant_prefix") or os.environ.get("HINDSIGHT_RETAIN_ASSISTANT_PREFIX", "Assistant")
+        ).strip() or "Assistant"
 
         # Retain controls
         self._auto_retain = self._config.get("auto_retain", True)
@@ -547,11 +641,9 @@ class HindsightMemoryProvider(MemoryProvider):
         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)
         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",
+                     "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,
-                     self._retain_async, self._retain_context,
-                     self._recall_max_tokens, self._recall_max_input_chars,
+                     self._retain_async, self._retain_context, self._recall_max_tokens, self._recall_max_input_chars,
                      self._tags, self._recall_tags)
 
         # For local mode, start the embedded daemon in the background so it
@@ -712,6 +804,78 @@ class HindsightMemoryProvider(MemoryProvider):
         self._prefetch_thread = threading.Thread(target=_run, daemon=True, name="hindsight-prefetch")
         self._prefetch_thread.start()
 
+    def _build_turn_messages(self, user_content: str, assistant_content: str) -> List[Dict[str, str]]:
+        now = datetime.now(timezone.utc).isoformat()
+        return [
+            {
+                "role": "user",
+                "content": f"{self._retain_user_prefix}: {user_content}",
+                "timestamp": now,
+            },
+            {
+                "role": "assistant",
+                "content": f"{self._retain_assistant_prefix}: {assistant_content}",
+                "timestamp": now,
+            },
+        ]
+
+    def _build_metadata(self, *, message_count: int, turn_index: int) -> Dict[str, str]:
+        metadata: Dict[str, str] = {
+            "retained_at": _utc_timestamp(),
+            "message_count": str(message_count),
+            "turn_index": str(turn_index),
+        }
+        if self._retain_source:
+            metadata["source"] = self._retain_source
+        if self._session_id:
+            metadata["session_id"] = self._session_id
+        if self._platform:
+            metadata["platform"] = self._platform
+        if self._user_id:
+            metadata["user_id"] = self._user_id
+        if self._user_name:
+            metadata["user_name"] = self._user_name
+        if self._chat_id:
+            metadata["chat_id"] = self._chat_id
+        if self._chat_name:
+            metadata["chat_name"] = self._chat_name
+        if self._chat_type:
+            metadata["chat_type"] = self._chat_type
+        if self._thread_id:
+            metadata["thread_id"] = self._thread_id
+        if self._agent_identity:
+            metadata["agent_identity"] = self._agent_identity
+        return metadata
+
+    def _build_retain_kwargs(
+        self,
+        content: str,
+        *,
+        context: str | None = None,
+        document_id: str | None = None,
+        metadata: Dict[str, str] | None = None,
+        tags: List[str] | None = None,
+        retain_async: bool | None = None,
+    ) -> Dict[str, Any]:
+        kwargs: Dict[str, Any] = {
+            "bank_id": self._bank_id,
+            "content": content,
+            "metadata": metadata or self._build_metadata(message_count=1, turn_index=self._turn_index),
+        }
+        if context is not None:
+            kwargs["context"] = context
+        if document_id:
+            kwargs["document_id"] = document_id
+        if retain_async is not None:
+            kwargs["retain_async"] = retain_async
+        merged_tags = _normalize_retain_tags(self._retain_tags)
+        for tag in _normalize_retain_tags(tags):
+            if tag not in merged_tags:
+                merged_tags.append(tag)
+        if merged_tags:
+            kwargs["tags"] = merged_tags
+        return kwargs
+
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
         """Retain conversation turn in background (non-blocking).
 
@@ -721,19 +885,14 @@ class HindsightMemoryProvider(MemoryProvider):
             logger.debug("sync_turn: skipped (auto_retain disabled)")
             return
 
-        from datetime import datetime, timezone
-        now = datetime.now(timezone.utc).isoformat()
+        if session_id:
+            self._session_id = str(session_id).strip()
 
-        messages = [
-            {"role": "user", "content": user_content, "timestamp": now},
-            {"role": "assistant", "content": assistant_content, "timestamp": now},
-        ]
-
-        turn = json.dumps(messages)
+        turn = json.dumps(self._build_turn_messages(user_content, assistant_content))
         self._session_turns.append(turn)
         self._turn_counter += 1
+        self._turn_index = self._turn_counter
 
-        # Only retain every N turns
         if self._turn_counter % self._retain_every_n_turns != 0:
             logger.debug("sync_turn: buffered turn %d (will retain at turn %d)",
                          self._turn_counter, self._turn_counter + (self._retain_every_n_turns - self._turn_counter % self._retain_every_n_turns))
@@ -741,19 +900,21 @@ class HindsightMemoryProvider(MemoryProvider):
 
         logger.debug("sync_turn: retaining %d turns, total session content %d chars",
                      len(self._session_turns), sum(len(t) for t in self._session_turns))
-        # Send the ENTIRE session as a single JSON array (document_id deduplicates).
-        # Each element in _session_turns is a JSON string of that turn's messages.
         content = "[" + ",".join(self._session_turns) + "]"
 
         def _sync():
             try:
                 client = self._get_client()
-                item: dict = {
-                    "content": content,
-                    "context": self._retain_context,
-                }
-                if self._tags:
-                    item["tags"] = self._tags
+                item = self._build_retain_kwargs(
+                    content,
+                    context=self._retain_context,
+                    metadata=self._build_metadata(
+                        message_count=len(self._session_turns) * 2,
+                        turn_index=self._turn_index,
+                    ),
+                )
+                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(
@@ -789,11 +950,11 @@ class HindsightMemoryProvider(MemoryProvider):
                 return tool_error("Missing required parameter: content")
             context = args.get("context")
             try:
-                retain_kwargs: dict = {
-                    "bank_id": self._bank_id, "content": content, "context": context,
-                }
-                if self._tags:
-                    retain_kwargs["tags"] = self._tags
+                retain_kwargs = self._build_retain_kwargs(
+                    content,
+                    context=context,
+                    tags=args.get("tags"),
+                )
                 logger.debug("Tool hindsight_retain: bank=%s, content_len=%d, context=%s",
                              self._bank_id, len(content), context)
                 _run_sync(client.aretain(**retain_kwargs))

pyproject.toml

@@ -126,7 +126,7 @@ py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajector
 hermes_cli = ["web_dist/**/*"]
 
 [tool.setuptools.packages.find]
-include = ["agent", "tools", "tools.*", "hermes_cli", "gateway", "gateway.*", "tui_gateway", "tui_gateway.*", "cron", "acp_adapter", "plugins", "plugins.*"]
+include = ["agent", "agent.*", "tools", "tools.*", "hermes_cli", "gateway", "gateway.*", "tui_gateway", "tui_gateway.*", "cron", "acp_adapter", "plugins", "plugins.*"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

run_agent.py

@@ -76,8 +76,6 @@ from tools.interrupt import set_interrupt as _set_interrupt
 from tools.browser_tool import cleanup_browser
 
 
-from hermes_constants import OPENROUTER_BASE_URL
-
 # Agent internals extracted to agent/ package for modularity
 from agent.memory_manager import build_memory_context_block, sanitize_context
 from agent.retry_utils import jittered_backoff
@@ -98,19 +96,11 @@ from agent.model_metadata import (
 from agent.context_compressor import ContextCompressor
 from agent.subdirectory_hints import SubdirectoryHintTracker
 from agent.prompt_caching import apply_anthropic_cache_control
-from agent.prompt_builder import build_skills_system_prompt, build_context_files_prompt, build_environment_hints, load_soul_md, TOOL_USE_ENFORCEMENT_GUIDANCE, TOOL_USE_ENFORCEMENT_MODELS, DEVELOPER_ROLE_MODELS, GOOGLE_MODEL_OPERATIONAL_GUIDANCE, OPENAI_MODEL_EXECUTION_GUIDANCE
+from agent.prompt_builder import build_skills_system_prompt, build_context_files_prompt, build_environment_hints, load_soul_md, TOOL_USE_ENFORCEMENT_GUIDANCE, TOOL_USE_ENFORCEMENT_MODELS, GOOGLE_MODEL_OPERATIONAL_GUIDANCE, OPENAI_MODEL_EXECUTION_GUIDANCE
 from agent.usage_pricing import estimate_usage_cost, normalize_usage
 from agent.codex_responses_adapter import (
-    _chat_content_to_responses_parts,
-    _chat_messages_to_responses_input as _codex_chat_messages_to_responses_input,
     _derive_responses_function_call_id as _codex_derive_responses_function_call_id,
     _deterministic_call_id as _codex_deterministic_call_id,
-    _extract_responses_message_text as _codex_extract_responses_message_text,
-    _extract_responses_reasoning_text as _codex_extract_responses_reasoning_text,
-    _normalize_codex_response as _codex_normalize_codex_response,
-    _preflight_codex_api_kwargs as _codex_preflight_codex_api_kwargs,
-    _preflight_codex_input_items as _codex_preflight_codex_input_items,
-    _responses_tools as _codex_responses_tools,
     _split_responses_tool_id as _codex_split_responses_tool_id,
     _summarize_user_message_for_log,
 )
@@ -385,9 +375,8 @@ def _sanitize_surrogates(text: str) -> str:
     return text
 
 
-# _chat_content_to_responses_parts and _summarize_user_message_for_log are
-# imported from agent.codex_responses_adapter (see import block above).
-# They remain importable from run_agent for backward compatibility.
+# _summarize_user_message_for_log is imported from agent.codex_responses_adapter
+# (see import block above). Remains importable from run_agent for backward compat.
 
 
 def _sanitize_structure_surrogates(payload: Any) -> bool:
@@ -751,6 +740,11 @@ class AIAgent:
         prefill_messages: List[Dict[str, Any]] = None,
         platform: str = None,
         user_id: str = None,
+        user_name: str = None,
+        chat_id: str = None,
+        chat_name: str = None,
+        chat_type: str = None,
+        thread_id: str = None,
         gateway_session_key: str = None,
         skip_context_files: bool = False,
         skip_memory: bool = False,
@@ -820,6 +814,11 @@ class AIAgent:
         self.ephemeral_system_prompt = ephemeral_system_prompt
         self.platform = platform  # "cli", "telegram", "discord", "whatsapp", etc.
         self._user_id = user_id  # Platform user identifier (gateway sessions)
+        self._user_name = user_name
+        self._chat_id = chat_id
+        self._chat_name = chat_name
+        self._chat_type = chat_type
+        self._thread_id = thread_id
         self._gateway_session_key = gateway_session_key  # Stable per-chat key (e.g. agent:main:telegram:dm:123)
         # Pluggable print function — CLI replaces this with _cprint so that
         # raw ANSI status lines are routed through prompt_toolkit's renderer
@@ -872,6 +871,13 @@ class AIAgent:
         else:
             self.api_mode = "chat_completions"
 
+        # Eagerly warm the transport cache so import errors surface at init,
+        # not mid-conversation.  Also validates the api_mode is registered.
+        try:
+            self._get_transport()
+        except Exception:
+            pass  # Non-fatal — transport may not exist for all modes yet
+
         try:
             from hermes_cli.model_normalize import (
                 _AGGREGATOR_PROVIDERS,
@@ -907,6 +913,10 @@ class AIAgent:
             )
         ):
             self.api_mode = "codex_responses"
+            # Invalidate the eager-warmed transport cache — api_mode changed
+            # from chat_completions to codex_responses after the warm at __init__.
+            if hasattr(self, "_transport_cache"):
+                self._transport_cache.clear()
 
         # Pre-warm OpenRouter model metadata cache in a background thread.
         # fetch_model_metadata() is cached for 1 hour; this avoids a blocking
@@ -1471,6 +1481,16 @@ class AIAgent:
                         # Thread gateway user identity for per-user memory scoping
                         if self._user_id:
                             _init_kwargs["user_id"] = self._user_id
+                        if self._user_name:
+                            _init_kwargs["user_name"] = self._user_name
+                        if self._chat_id:
+                            _init_kwargs["chat_id"] = self._chat_id
+                        if self._chat_name:
+                            _init_kwargs["chat_name"] = self._chat_name
+                        if self._chat_type:
+                            _init_kwargs["chat_type"] = self._chat_type
+                        if self._thread_id:
+                            _init_kwargs["thread_id"] = self._thread_id
                         # Thread gateway session key for stable per-chat Honcho session isolation
                         if self._gateway_session_key:
                             _init_kwargs["gateway_session_key"] = self._gateway_session_key
@@ -1903,6 +1923,9 @@ class AIAgent:
         self.provider = new_provider
         self.base_url = base_url or self.base_url
         self.api_mode = api_mode
+        # Invalidate transport cache — new api_mode may need a different transport
+        if hasattr(self, "_transport_cache"):
+            self._transport_cache.clear()
         if api_key:
             self.api_key = api_key
 
@@ -2503,6 +2526,20 @@ class AIAgent:
           4. Tag variants: ``<think>``, ``<thinking>``, ``<reasoning>``,
              ``<REASONING_SCRATCHPAD>``, ``<thought>`` (Gemma 4), all
              case-insensitive.
+
+        Additionally strips standalone tool-call XML blocks that some open
+        models (notably Gemma variants on OpenRouter) emit inside assistant
+        content instead of via the structured ``tool_calls`` field:
+          * ``<tool_call>…</tool_call>``
+          * ``<tool_calls>…</tool_calls>``
+          * ``<tool_result>…</tool_result>``
+          * ``<function_call>…</function_call>``
+          * ``<function_calls>…</function_calls>``
+          * ``<function name="…">…</function>`` (Gemma style)
+        Ported from openclaw/openclaw#67318. The ``<function>`` variant is
+        boundary-gated (only strips when the tag sits at start-of-line or
+        after punctuation and carries a ``name="..."`` attribute) so prose
+        mentions like "Use <function> in JavaScript" are preserved.
         """
         if not content:
             return ""
@@ -2514,6 +2551,30 @@ class AIAgent:
         content = re.sub(r'<reasoning>.*?</reasoning>', '', content, flags=re.DOTALL | re.IGNORECASE)
         content = re.sub(r'<REASONING_SCRATCHPAD>.*?</REASONING_SCRATCHPAD>', '', content, flags=re.DOTALL | re.IGNORECASE)
         content = re.sub(r'<thought>.*?</thought>', '', content, flags=re.DOTALL | re.IGNORECASE)
+        # 1b. Tool-call XML blocks (openclaw/openclaw#67318). Handle the
+        #     generic tag names first — they have no attribute gating since
+        #     a literal <tool_call> in prose is already vanishingly rare.
+        for _tc_name in ("tool_call", "tool_calls", "tool_result",
+                          "function_call", "function_calls"):
+            content = re.sub(
+                rf'<{_tc_name}\b[^>]*>.*?</{_tc_name}>',
+                '',
+                content,
+                flags=re.DOTALL | re.IGNORECASE,
+            )
+        # 1c. <function name="...">...</function> — Gemma-style standalone
+        #     tool call. Only strip when the tag sits at a block boundary
+        #     (start of text, after a newline, or after sentence-ending
+        #     punctuation) AND carries a name="..." attribute. This keeps
+        #     prose mentions like "Use <function> to declare" safe.
+        content = re.sub(
+            r'(?:(?<=^)|(?<=[\n\r.!?:]))[ \t]*'
+            r'<function\b[^>]*\bname\s*=[^>]*>'
+            r'(?:(?:(?!</function>).)*)</function>',
+            '',
+            content,
+            flags=re.DOTALL | re.IGNORECASE,
+        )
         # 2. Unterminated reasoning block — open tag at a block boundary
         #    (start of text, or after a newline) with no matching close.
         #    Strip from the tag to end of string.  Fixes #8878 / #9568
@@ -2531,6 +2592,16 @@ class AIAgent:
             content,
             flags=re.IGNORECASE,
         )
+        # 3b. Stray tool-call closers. (We do NOT strip bare <function> or
+        #     unterminated <function name="..."> because a truncated tail
+        #     during streaming may still be valuable to the user; matches
+        #     OpenClaw's intentional asymmetry.)
+        content = re.sub(
+            r'</(?:tool_call|tool_calls|tool_result|function_call|function_calls|function)>\s*',
+            '',
+            content,
+            flags=re.IGNORECASE,
+        )
         return content
 
     @staticmethod
@@ -2966,6 +3037,7 @@ class AIAgent:
                     tool_call_id=msg.get("tool_call_id"),
                     finish_reason=msg.get("finish_reason"),
                     reasoning=msg.get("reasoning") if role == "assistant" else None,
+                    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,
                 )
@@ -4823,7 +4895,7 @@ class AIAgent:
         active_client = client or self._ensure_primary_openai_client(reason="codex_create_stream_fallback")
         fallback_kwargs = dict(api_kwargs)
         fallback_kwargs["stream"] = True
-        fallback_kwargs = self._get_codex_transport().preflight_kwargs(fallback_kwargs, allow_stream=True)
+        fallback_kwargs = self._get_transport().preflight_kwargs(fallback_kwargs, allow_stream=True)
         stream_or_response = active_client.responses.create(**fallback_kwargs)
 
         # Compatibility shim for mocks or providers that still return a concrete response.
@@ -5178,6 +5250,9 @@ class AIAgent:
                     result["response"] = self._anthropic_messages_create(api_kwargs)
                 elif self.api_mode == "bedrock_converse":
                     # Bedrock uses boto3 directly — no OpenAI client needed.
+                    # normalize_converse_response produces an OpenAI-compatible
+                    # SimpleNamespace so the rest of the agent loop can treat
+                    # bedrock responses like chat_completions responses.
                     from agent.bedrock_adapter import (
                         _get_bedrock_runtime_client,
                         normalize_converse_response,
@@ -5805,16 +5880,6 @@ class AIAgent:
                             result["response"] = _call_chat_completions()
                         return  # success
                     except Exception as e:
-                        if deltas_were_sent["yes"]:
-                            # Streaming failed AFTER some tokens were already
-                            # delivered.  Don't retry or fall back — partial
-                            # content already reached the user.
-                            logger.warning(
-                                "Streaming failed after partial delivery, not retrying: %s", e
-                            )
-                            result["error"] = e
-                            return
-
                         _is_timeout = isinstance(
                             e, (_httpx.ReadTimeout, _httpx.ConnectTimeout, _httpx.PoolTimeout)
                         )
@@ -5822,6 +5887,123 @@ class AIAgent:
                             e, (_httpx.ConnectError, _httpx.RemoteProtocolError, ConnectionError)
                         )
 
+                        # If the stream died AFTER some tokens were delivered:
+                        # normally we don't retry (the user already saw text,
+                        # retrying would duplicate it).  BUT: if a tool call
+                        # was in-flight when the stream died, silently aborting
+                        # discards the tool call entirely.  In that case we
+                        # prefer to retry — the user sees a brief
+                        # "reconnecting" marker + duplicated preamble text,
+                        # which is strictly better than a failed action with
+                        # a "retry manually" message.  Limit this to transient
+                        # connection errors (Clawdbot-style narrow gate): no
+                        # tool has executed yet within this API call, so
+                        # silent retry is safe wrt side-effects.
+                        if deltas_were_sent["yes"]:
+                            _partial_tool_in_flight = bool(
+                                result.get("partial_tool_names")
+                            )
+                            _is_sse_conn_err_preview = False
+                            if not _is_timeout and not _is_conn_err:
+                                from openai import APIError as _APIError
+                                if isinstance(e, _APIError) and not getattr(e, "status_code", None):
+                                    _err_lower_preview = str(e).lower()
+                                    _SSE_PREVIEW_PHRASES = (
+                                        "connection lost",
+                                        "connection reset",
+                                        "connection closed",
+                                        "connection terminated",
+                                        "network error",
+                                        "network connection",
+                                        "terminated",
+                                        "peer closed",
+                                        "broken pipe",
+                                        "upstream connect error",
+                                    )
+                                    _is_sse_conn_err_preview = any(
+                                        phrase in _err_lower_preview
+                                        for phrase in _SSE_PREVIEW_PHRASES
+                                    )
+                            _is_transient = (
+                                _is_timeout or _is_conn_err or _is_sse_conn_err_preview
+                            )
+                            _can_silent_retry = (
+                                _partial_tool_in_flight
+                                and _is_transient
+                                and _stream_attempt < _max_stream_retries
+                            )
+                            if not _can_silent_retry:
+                                # Either no tool call was in-flight (so the
+                                # turn was a pure text response — current
+                                # stub-with-recovered-text behaviour is
+                                # correct), or retries are exhausted, or the
+                                # error isn't transient.  Fall through to the
+                                # stub path.
+                                logger.warning(
+                                    "Streaming failed after partial delivery, not retrying: %s", e
+                                )
+                                result["error"] = e
+                                return
+                            # Tool call was in-flight AND error is transient:
+                            # retry silently.  Clear per-attempt state so the
+                            # next stream starts clean.  Fire a "reconnecting"
+                            # marker so the user sees why the preamble is
+                            # about to be re-streamed.
+                            logger.info(
+                                "Streaming attempt %s/%s died mid tool-call "
+                                "(%s: %s) after user-visible text; retrying "
+                                "silently to avoid losing the action. "
+                                "Preamble will re-stream.",
+                                _stream_attempt + 1,
+                                _max_stream_retries + 1,
+                                type(e).__name__,
+                                e,
+                            )
+                            try:
+                                self._fire_stream_delta(
+                                    "\n\n⚠ Connection dropped mid tool-call; "
+                                    "reconnecting…\n\n"
+                                )
+                            except Exception:
+                                pass
+                            # Reset the streamed-text buffer so the retry's
+                            # fresh preamble doesn't get double-recorded in
+                            # _current_streamed_assistant_text (which would
+                            # pollute the interim-visible-text comparison).
+                            try:
+                                self._reset_stream_delivery_tracking()
+                            except Exception:
+                                pass
+                            # Reset in-memory accumulators so the next
+                            # attempt's chunks don't concat onto the dead
+                            # stream's partial JSON.
+                            result["partial_tool_names"] = []
+                            deltas_were_sent["yes"] = False
+                            first_delta_fired["done"] = False
+                            self._emit_status(
+                                f"⚠️ Connection dropped mid tool-call "
+                                f"({type(e).__name__}). Reconnecting… "
+                                f"(attempt {_stream_attempt + 2}/{_max_stream_retries + 1})"
+                            )
+                            self._touch_activity(
+                                f"stream retry {_stream_attempt + 2}/{_max_stream_retries + 1} "
+                                f"mid tool-call after {type(e).__name__}"
+                            )
+                            stale = request_client_holder.get("client")
+                            if stale is not None:
+                                self._close_request_openai_client(
+                                    stale, reason="stream_mid_tool_retry_cleanup"
+                                )
+                                request_client_holder["client"] = None
+                            try:
+                                self._replace_primary_openai_client(
+                                    reason="stream_mid_tool_retry_pool_cleanup"
+                                )
+                            except Exception:
+                                pass
+                            self._emit_status("🔄 Reconnected — resuming…")
+                            continue
+
                         # SSE error events from proxies (e.g. OpenRouter sends
                         # {"error":{"message":"Network connection lost."}}) are
                         # raised as APIError by the OpenAI SDK.  These are
@@ -6132,6 +6314,10 @@ class AIAgent:
             # falling through to OpenRouter defaults.
             fb_base_url_hint = (fb.get("base_url") or "").strip() or None
             fb_api_key_hint = (fb.get("api_key") or "").strip() or None
+            if not fb_api_key_hint:
+                fb_key_env = (fb.get("key_env") or "").strip()
+                if fb_key_env:
+                    fb_api_key_hint = os.getenv(fb_key_env, "").strip() or None
             # For Ollama Cloud endpoints, pull OLLAMA_API_KEY from env
             # when no explicit key is in the fallback config. Host match
             # (not substring) — see GHSA-76xc-57q6-vm5m.
@@ -6181,6 +6367,8 @@ class AIAgent:
             self.provider = fb_provider
             self.base_url = fb_base_url
             self.api_mode = fb_api_mode
+            if hasattr(self, "_transport_cache"):
+                self._transport_cache.clear()
             self._fallback_activated = True
 
             # Honor per-provider / per-model request_timeout_seconds for the
@@ -6292,6 +6480,8 @@ class AIAgent:
             self.provider = rt["provider"]
             self.base_url = rt["base_url"]           # setter updates _base_url_lower
             self.api_mode = rt["api_mode"]
+            if hasattr(self, "_transport_cache"):
+                self._transport_cache.clear()
             self.api_key = rt["api_key"]
             self._client_kwargs = dict(rt["client_kwargs"])
             self._use_prompt_caching = rt["use_prompt_caching"]
@@ -6398,6 +6588,8 @@ class AIAgent:
             self.provider = rt["provider"]
             self.base_url = rt["base_url"]
             self.api_mode = rt["api_mode"]
+            if hasattr(self, "_transport_cache"):
+                self._transport_cache.clear()
             self.api_key = rt["api_key"]
 
             if self.api_mode == "anthropic_messages":
@@ -6556,41 +6748,59 @@ class AIAgent:
             return suffix
         return "[A multimodal message was converted to text for Anthropic compatibility.]"
 
-    def _get_anthropic_transport(self):
-        """Return the cached AnthropicTransport instance (lazy singleton)."""
-        t = getattr(self, "_anthropic_transport", None)
+    def _get_transport(self, api_mode: str = None):
+        """Return the cached transport for the given (or current) api_mode.
+
+        Lazy-initializes on first call per api_mode. Returns None if no
+        transport is registered for the mode.
+        """
+        mode = api_mode or self.api_mode
+        cache = getattr(self, "_transport_cache", None)
+        if cache is None:
+            cache = {}
+            self._transport_cache = cache
+        t = cache.get(mode)
         if t is None:
             from agent.transports import get_transport
-            t = get_transport("anthropic_messages")
-            self._anthropic_transport = t
+            t = get_transport(mode)
+            cache[mode] = t
         return t
 
-    def _get_codex_transport(self):
-        """Return the cached ResponsesApiTransport instance (lazy singleton)."""
-        t = getattr(self, "_codex_transport", None)
-        if t is None:
-            from agent.transports import get_transport
-            t = get_transport("codex_responses")
-            self._codex_transport = t
-        return t
+    @staticmethod
+    def _nr_to_assistant_message(nr):
+        """Convert a NormalizedResponse to the SimpleNamespace shape downstream expects.
 
-    def _get_chat_completions_transport(self):
-        """Return the cached ChatCompletionsTransport instance (lazy singleton)."""
-        t = getattr(self, "_chat_completions_transport", None)
-        if t is None:
-            from agent.transports import get_transport
-            t = get_transport("chat_completions")
-            self._chat_completions_transport = t
-        return t
+        This is the single back-compat shim between the transport layer
+        (NormalizedResponse) and the agent loop (SimpleNamespace with
+        .content, .tool_calls, .reasoning, .reasoning_content,
+        .reasoning_details, .codex_reasoning_items, and per-tool-call
+        .call_id / .response_item_id).
 
-    def _get_bedrock_transport(self):
-        """Return the cached BedrockTransport instance (lazy singleton)."""
-        t = getattr(self, "_bedrock_transport", None)
-        if t is None:
-            from agent.transports import get_transport
-            t = get_transport("bedrock_converse")
-            self._bedrock_transport = t
-        return t
+        TODO: Remove when downstream code reads NormalizedResponse directly.
+        """
+        tc_list = None
+        if nr.tool_calls:
+            tc_list = []
+            for tc in nr.tool_calls:
+                tc_ns = SimpleNamespace(
+                    id=tc.id,
+                    type="function",
+                    function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
+                )
+                if tc.provider_data:
+                    for key in ("call_id", "response_item_id"):
+                        if tc.provider_data.get(key):
+                            setattr(tc_ns, key, tc.provider_data[key])
+                tc_list.append(tc_ns)
+        pd = nr.provider_data or {}
+        return SimpleNamespace(
+            content=nr.content,
+            tool_calls=tc_list or None,
+            reasoning=nr.reasoning,
+            reasoning_content=pd.get("reasoning_content"),
+            reasoning_details=pd.get("reasoning_details"),
+            codex_reasoning_items=pd.get("codex_reasoning_items"),
+        )
 
     def _prepare_anthropic_messages_for_api(self, api_messages: list) -> list:
         if not any(
@@ -6708,7 +6918,7 @@ class AIAgent:
     def _build_api_kwargs(self, api_messages: list) -> dict:
         """Build the keyword arguments dict for the active API mode."""
         if self.api_mode == "anthropic_messages":
-            _transport = self._get_anthropic_transport()
+            _transport = self._get_transport()
             anthropic_messages = self._prepare_anthropic_messages_for_api(api_messages)
             ctx_len = getattr(self, "context_compressor", None)
             ctx_len = ctx_len.context_length if ctx_len else None
@@ -6731,7 +6941,7 @@ class AIAgent:
         # AWS Bedrock native Converse API — bypasses the OpenAI client entirely.
         # The adapter handles message/tool conversion and boto3 calls directly.
         if self.api_mode == "bedrock_converse":
-            _bt = self._get_bedrock_transport()
+            _bt = self._get_transport()
             region = getattr(self, "_bedrock_region", None) or "us-east-1"
             guardrail = getattr(self, "_bedrock_guardrail_config", None)
             return _bt.build_kwargs(
@@ -6744,7 +6954,7 @@ class AIAgent:
             )
 
         if self.api_mode == "codex_responses":
-            _ct = self._get_codex_transport()
+            _ct = self._get_transport()
             is_github_responses = (
                 base_url_host_matches(self.base_url, "models.github.ai")
                 or base_url_host_matches(self.base_url, "api.githubcopilot.com")
@@ -6772,7 +6982,7 @@ class AIAgent:
             )
 
         # ── chat_completions (default) ─────────────────────────────────────
-        _ct = self._get_chat_completions_transport()
+        _ct = self._get_transport()
 
         # Provider detection flags
         _is_qwen = self._is_qwen_portal()
@@ -7003,6 +7213,11 @@ class AIAgent:
             "finish_reason": finish_reason,
         }
 
+        if hasattr(assistant_message, "reasoning_content"):
+            raw_reasoning_content = getattr(assistant_message, "reasoning_content", None)
+            if raw_reasoning_content is not None:
+                msg["reasoning_content"] = _sanitize_surrogates(raw_reasoning_content)
+
         if hasattr(assistant_message, 'reasoning_details') and assistant_message.reasoning_details:
             # Pass reasoning_details back unmodified so providers (OpenRouter,
             # Anthropic, OpenAI) can maintain reasoning continuity across turns.
@@ -7077,6 +7292,30 @@ class AIAgent:
 
         return msg
 
+    def _copy_reasoning_content_for_api(self, source_msg: dict, api_msg: dict) -> None:
+        """Copy provider-facing reasoning fields onto an API replay message."""
+        if source_msg.get("role") != "assistant":
+            return
+
+        explicit_reasoning = source_msg.get("reasoning_content")
+        if isinstance(explicit_reasoning, str):
+            api_msg["reasoning_content"] = explicit_reasoning
+            return
+
+        normalized_reasoning = source_msg.get("reasoning")
+        if isinstance(normalized_reasoning, str) and normalized_reasoning:
+            api_msg["reasoning_content"] = normalized_reasoning
+            return
+
+        kimi_requires_reasoning = (
+            self.provider in {"kimi-coding", "kimi-coding-cn"}
+            or base_url_host_matches(self.base_url, "api.kimi.com")
+            or base_url_host_matches(self.base_url, "moonshot.ai")
+            or base_url_host_matches(self.base_url, "moonshot.cn")
+        )
+        if kimi_requires_reasoning and source_msg.get("tool_calls"):
+            api_msg["reasoning_content"] = ""
+
     @staticmethod
     def _sanitize_tool_calls_for_strict_api(api_msg: dict) -> dict:
         """Strip Codex Responses API fields from tool_calls for strict providers.
@@ -7160,10 +7399,7 @@ class AIAgent:
             api_messages = []
             for msg in messages:
                 api_msg = msg.copy()
-                if msg.get("role") == "assistant":
-                    reasoning = msg.get("reasoning")
-                    if reasoning:
-                        api_msg["reasoning_content"] = reasoning
+                self._copy_reasoning_content_for_api(msg, api_msg)
                 api_msg.pop("reasoning", None)
                 api_msg.pop("finish_reason", None)
                 api_msg.pop("_flush_sentinel", None)
@@ -7221,7 +7457,7 @@ class AIAgent:
             if not _aux_available and self.api_mode == "codex_responses":
                 # No auxiliary client -- use the Codex Responses path directly
                 codex_kwargs = self._build_api_kwargs(api_messages)
-                codex_kwargs["tools"] = self._get_codex_transport().convert_tools([memory_tool_def])
+                codex_kwargs["tools"] = self._get_transport().convert_tools([memory_tool_def])
                 if _flush_temperature is not None:
                     codex_kwargs["temperature"] = _flush_temperature
                 else:
@@ -7231,7 +7467,7 @@ class AIAgent:
                 response = self._run_codex_stream(codex_kwargs)
             elif not _aux_available and self.api_mode == "anthropic_messages":
                 # Native Anthropic — use the transport for kwargs
-                _tflush = self._get_anthropic_transport()
+                _tflush = self._get_transport()
                 ant_kwargs = _tflush.build_kwargs(
                     model=self.model, messages=api_messages,
                     tools=[memory_tool_def], max_tokens=5120,
@@ -7256,7 +7492,7 @@ class AIAgent:
             # Extract tool calls from the response, handling all API formats
             tool_calls = []
             if self.api_mode == "codex_responses" and not _aux_available:
-                _ct_flush = self._get_codex_transport()
+                _ct_flush = self._get_transport()
                 _cnr_flush = _ct_flush.normalize_response(response)
                 if _cnr_flush and _cnr_flush.tool_calls:
                     tool_calls = [
@@ -7266,7 +7502,7 @@ class AIAgent:
                         ) for tc in _cnr_flush.tool_calls
                     ]
             elif self.api_mode == "anthropic_messages" and not _aux_available:
-                _tfn = self._get_anthropic_transport()
+                _tfn = self._get_transport()
                 _flush_nr = _tfn.normalize_response(response, strip_tool_prefix=self._is_anthropic_oauth)
                 if _flush_nr and _flush_nr.tool_calls:
                     tool_calls = [
@@ -7276,9 +7512,11 @@ class AIAgent:
                         ) for tc in _flush_nr.tool_calls
                     ]
             elif hasattr(response, "choices") and response.choices:
-                assistant_message = response.choices[0].message
-                if assistant_message.tool_calls:
-                    tool_calls = assistant_message.tool_calls
+                # chat_completions / bedrock — normalize through transport
+                _flush_cc_nr = self._get_transport().normalize_response(response)
+                _flush_msg = self._nr_to_assistant_message(_flush_cc_nr)
+                if _flush_msg.tool_calls:
+                    tool_calls = _flush_msg.tool_calls
 
             for tc in tool_calls:
                 if tc.function.name == "memory":
@@ -8308,7 +8546,7 @@ class AIAgent:
                 codex_kwargs = self._build_api_kwargs(api_messages)
                 codex_kwargs.pop("tools", None)
                 summary_response = self._run_codex_stream(codex_kwargs)
-                _ct_sum = self._get_codex_transport()
+                _ct_sum = self._get_transport()
                 _cnr_sum = _ct_sum.normalize_response(summary_response)
                 final_response = (_cnr_sum.content or "").strip()
             else:
@@ -8338,7 +8576,7 @@ class AIAgent:
                     summary_kwargs["extra_body"] = summary_extra_body
 
                 if self.api_mode == "anthropic_messages":
-                    _tsum = self._get_anthropic_transport()
+                    _tsum = self._get_transport()
                     _ant_kw = _tsum.build_kwargs(model=self.model, messages=api_messages, tools=None,
                                    max_tokens=self.max_tokens, reasoning_config=self.reasoning_config,
                                    is_oauth=self._is_anthropic_oauth,
@@ -8348,11 +8586,8 @@ class AIAgent:
                     final_response = (_sum_nr.content or "").strip()
                 else:
                     summary_response = self._ensure_primary_openai_client(reason="iteration_limit_summary").chat.completions.create(**summary_kwargs)
-
-                    if summary_response.choices and summary_response.choices[0].message.content:
-                        final_response = summary_response.choices[0].message.content
-                    else:
-                        final_response = ""
+                    _sum_cc_nr = self._get_transport().normalize_response(summary_response)
+                    final_response = (_sum_cc_nr.content or "").strip()
 
             if final_response:
                 if "<think>" in final_response:
@@ -8367,11 +8602,11 @@ class AIAgent:
                     codex_kwargs = self._build_api_kwargs(api_messages)
                     codex_kwargs.pop("tools", None)
                     retry_response = self._run_codex_stream(codex_kwargs)
-                    _ct_retry = self._get_codex_transport()
+                    _ct_retry = self._get_transport()
                     _cnr_retry = _ct_retry.normalize_response(retry_response)
                     final_response = (_cnr_retry.content or "").strip()
                 elif self.api_mode == "anthropic_messages":
-                    _tretry = self._get_anthropic_transport()
+                    _tretry = self._get_transport()
                     _ant_kw2 = _tretry.build_kwargs(model=self.model, messages=api_messages, tools=None,
                                     is_oauth=self._is_anthropic_oauth,
                                     max_tokens=self.max_tokens, reasoning_config=self.reasoning_config,
@@ -8392,11 +8627,8 @@ class AIAgent:
                         summary_kwargs["extra_body"] = summary_extra_body
 
                     summary_response = self._ensure_primary_openai_client(reason="iteration_limit_summary_retry").chat.completions.create(**summary_kwargs)
-
-                    if summary_response.choices and summary_response.choices[0].message.content:
-                        final_response = summary_response.choices[0].message.content
-                    else:
-                        final_response = ""
+                    _retry_cc_nr = self._get_transport().normalize_response(summary_response)
+                    final_response = (_retry_cc_nr.content or "").strip()
 
                 if final_response:
                     if "<think>" in final_response:
@@ -8923,11 +9155,7 @@ class AIAgent:
 
                 # For ALL assistant messages, pass reasoning back to the API
                 # This ensures multi-turn reasoning context is preserved
-                if msg.get("role") == "assistant":
-                    reasoning_text = msg.get("reasoning")
-                    if reasoning_text:
-                        # Add reasoning_content for API compatibility (Moonshot AI, Novita, OpenRouter)
-                        api_msg["reasoning_content"] = reasoning_text
+                self._copy_reasoning_content_for_api(msg, api_msg)
 
                 # Remove 'reasoning' field - it's for trajectory storage only
                 # We've copied it to 'reasoning_content' for the API above
@@ -9131,7 +9359,7 @@ class AIAgent:
                     if self._force_ascii_payload:
                         _sanitize_structure_non_ascii(api_kwargs)
                     if self.api_mode == "codex_responses":
-                        api_kwargs = self._get_codex_transport().preflight_kwargs(api_kwargs, allow_stream=False)
+                        api_kwargs = self._get_transport().preflight_kwargs(api_kwargs, allow_stream=False)
 
                     try:
                         from hermes_cli.plugins import invoke_hook as _invoke_hook
@@ -9219,7 +9447,7 @@ class AIAgent:
                     response_invalid = False
                     error_details = []
                     if self.api_mode == "codex_responses":
-                        _ct_v = self._get_codex_transport()
+                        _ct_v = self._get_transport()
                         if not _ct_v.validate_response(response):
                             if response is None:
                                 response_invalid = True
@@ -9248,7 +9476,7 @@ class AIAgent:
                                     response_invalid = True
                                     error_details.append("response.output is empty")
                     elif self.api_mode == "anthropic_messages":
-                        _tv = self._get_anthropic_transport()
+                        _tv = self._get_transport()
                         if not _tv.validate_response(response):
                             response_invalid = True
                             if response is None:
@@ -9256,7 +9484,7 @@ class AIAgent:
                             else:
                                 error_details.append("response.content invalid (not a non-empty list)")
                     elif self.api_mode == "bedrock_converse":
-                        _btv = self._get_bedrock_transport()
+                        _btv = self._get_transport()
                         if not _btv.validate_response(response):
                             response_invalid = True
                             if response is None:
@@ -9264,7 +9492,7 @@ class AIAgent:
                             else:
                                 error_details.append("Bedrock response invalid (no output or choices)")
                     else:
-                        _ctv = self._get_chat_completions_transport()
+                        _ctv = self._get_transport()
                         if not _ctv.validate_response(response):
                             response_invalid = True
                             if response is None:
@@ -9424,15 +9652,18 @@ class AIAgent:
                         else:
                             finish_reason = "stop"
                     elif self.api_mode == "anthropic_messages":
-                        _tfr = self._get_anthropic_transport()
+                        _tfr = self._get_transport()
                         finish_reason = _tfr.map_finish_reason(response.stop_reason)
                     elif self.api_mode == "bedrock_converse":
-                        # Bedrock response is already normalized at dispatch — finish_reason
-                        # is already in OpenAI format via normalize_converse_response()
-                        finish_reason = response.choices[0].finish_reason if hasattr(response, "choices") and response.choices else "stop"
+                        # Bedrock response already normalized at dispatch — use transport
+                        _bt_fr = self._get_transport()
+                        _bt_fr_nr = _bt_fr.normalize_response(response)
+                        finish_reason = _bt_fr_nr.finish_reason
                     else:
-                        finish_reason = response.choices[0].finish_reason
-                        assistant_message = response.choices[0].message
+                        _cc_fr = self._get_transport()
+                        _cc_fr_nr = _cc_fr.normalize_response(response)
+                        finish_reason = _cc_fr_nr.finish_reason
+                        assistant_message = self._nr_to_assistant_message(_cc_fr_nr)
                         if self._should_treat_stop_as_truncated(
                             finish_reason,
                             assistant_message,
@@ -9455,27 +9686,14 @@ class AIAgent:
                         # interim assistant message is byte-identical to what
                         # would have been appended in the non-truncated path.
                         _trunc_msg = None
-                        if self.api_mode in ("chat_completions", "bedrock_converse"):
-                            _trunc_msg = response.choices[0].message if (hasattr(response, "choices") and response.choices) else None
-                        elif self.api_mode == "anthropic_messages":
-                            _trunc_nr = self._get_anthropic_transport().normalize_response(
+                        _trunc_transport = self._get_transport()
+                        if self.api_mode == "anthropic_messages":
+                            _trunc_nr = _trunc_transport.normalize_response(
                                 response, strip_tool_prefix=self._is_anthropic_oauth
                             )
-                            _trunc_msg = SimpleNamespace(
-                                content=_trunc_nr.content,
-                                tool_calls=[
-                                    SimpleNamespace(
-                                        id=tc.id, type="function",
-                                        function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
-                                    ) for tc in (_trunc_nr.tool_calls or [])
-                                ] or None,
-                                reasoning=_trunc_nr.reasoning,
-                                reasoning_content=None,
-                                reasoning_details=(
-                                    _trunc_nr.provider_data.get("reasoning_details")
-                                    if _trunc_nr.provider_data else None
-                                ),
-                            )
+                        else:
+                            _trunc_nr = _trunc_transport.normalize_response(response)
+                        _trunc_msg = self._nr_to_assistant_message(_trunc_nr)
 
                         _trunc_content = getattr(_trunc_msg, "content", None) if _trunc_msg else None
                         _trunc_has_tool_calls = bool(getattr(_trunc_msg, "tool_calls", None)) if _trunc_msg else False
@@ -9724,6 +9942,7 @@ class AIAgent:
                                     billing_mode="subscription_included"
                                     if cost_result.status == "included" else None,
                                     model=self.model,
+                                    api_call_count=1,
                                 )
                             except Exception:
                                 pass  # never block the agent loop
@@ -10000,6 +10219,27 @@ class AIAgent:
                         if self._try_refresh_nous_client_credentials(force=True):
                             print(f"{self.log_prefix}🔐 Nous agent key refreshed after 401. Retrying request...")
                             continue
+                        # Credential refresh didn't help — show diagnostic info.
+                        # Most common causes: Portal OAuth expired/revoked,
+                        # account out of credits, or agent key blocked.
+                        from hermes_constants import display_hermes_home as _dhh_fn
+                        _dhh = _dhh_fn()
+                        _body_text = ""
+                        try:
+                            _body = getattr(api_error, "body", None) or getattr(api_error, "response", None)
+                            if _body is not None:
+                                _body_text = str(_body)[:200]
+                        except Exception:
+                            pass
+                        print(f"{self.log_prefix}🔐 Nous 401 — Portal authentication failed.")
+                        if _body_text:
+                            print(f"{self.log_prefix}   Response: {_body_text}")
+                        print(f"{self.log_prefix}   Most likely: Portal OAuth expired, account out of credits, or agent key revoked.")
+                        print(f"{self.log_prefix}   Troubleshooting:")
+                        print(f"{self.log_prefix}     • Re-authenticate: hermes login --provider nous")
+                        print(f"{self.log_prefix}     • Check credits / billing: https://portal.nousresearch.com")
+                        print(f"{self.log_prefix}     • Verify stored credentials: {_dhh}/auth.json")
+                        print(f"{self.log_prefix}     • Switch providers temporarily: /model <model> --provider openrouter")
                     if (
                         self.api_mode == "anthropic_messages"
                         and status_code == 401
@@ -10684,69 +10924,13 @@ class AIAgent:
                 break
 
             try:
-                if self.api_mode == "codex_responses":
-                    _ct = self._get_codex_transport()
-                    _cnr = _ct.normalize_response(response)
-                    # Back-compat shim: downstream expects SimpleNamespace with
-                    # codex-specific fields (.codex_reasoning_items, .reasoning_details,
-                    # and .call_id/.response_item_id on tool calls).
-                    _tc_list = None
-                    if _cnr.tool_calls:
-                        _tc_list = []
-                        for tc in _cnr.tool_calls:
-                            _tc_ns = SimpleNamespace(
-                                id=tc.id, type="function",
-                                function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
-                            )
-                            if tc.provider_data:
-                                if tc.provider_data.get("call_id"):
-                                    _tc_ns.call_id = tc.provider_data["call_id"]
-                                if tc.provider_data.get("response_item_id"):
-                                    _tc_ns.response_item_id = tc.provider_data["response_item_id"]
-                            _tc_list.append(_tc_ns)
-                    assistant_message = SimpleNamespace(
-                        content=_cnr.content,
-                        tool_calls=_tc_list or None,
-                        reasoning=_cnr.reasoning,
-                        reasoning_content=None,
-                        codex_reasoning_items=(
-                            _cnr.provider_data.get("codex_reasoning_items")
-                            if _cnr.provider_data else None
-                        ),
-                        reasoning_details=(
-                            _cnr.provider_data.get("reasoning_details")
-                            if _cnr.provider_data else None
-                        ),
-                    )
-                    finish_reason = _cnr.finish_reason
-                elif self.api_mode == "anthropic_messages":
-                    _transport = self._get_anthropic_transport()
-                    _nr = _transport.normalize_response(
-                        response, strip_tool_prefix=self._is_anthropic_oauth
-                    )
-                    # Back-compat shim: downstream code expects SimpleNamespace with
-                    # .content, .tool_calls, .reasoning, .reasoning_content,
-                    # .reasoning_details attributes.
-                    assistant_message = SimpleNamespace(
-                        content=_nr.content,
-                        tool_calls=[
-                            SimpleNamespace(
-                                id=tc.id,
-                                type="function",
-                                function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
-                            )
-                            for tc in (_nr.tool_calls or [])
-                        ] or None,
-                        reasoning=_nr.reasoning,
-                        reasoning_content=None,
-                        reasoning_details=(
-                            _nr.provider_data.get("reasoning_details")
-                            if _nr.provider_data else None
-                        ),
-                    )
-                    finish_reason = _nr.finish_reason
-                else:
-                    assistant_message = response.choices[0].message
+                _transport = self._get_transport()
+                _normalize_kwargs = {}
+                if self.api_mode == "anthropic_messages":
+                    _normalize_kwargs["strip_tool_prefix"] = self._is_anthropic_oauth
+                _nr = _transport.normalize_response(response, **_normalize_kwargs)
+                assistant_message = self._nr_to_assistant_message(_nr)
+                finish_reason = _nr.finish_reason
                 
                 # Normalize content to string — some OpenAI-compatible servers
                 # (llama-server, etc.) return content as a dict or list instead

scripts/discord-voice-doctor.py

@@ -265,7 +265,7 @@ def check_config(groq_key, eleven_key):
     if voice_mode_path.exists():
         try:
             import json
-            modes = json.loads(voice_mode_path.read_text())
+            modes = json.loads(voice_mode_path.read_text(encoding="utf-8"))
             off_count = sum(1 for v in modes.values() if v == "off")
             all_count = sum(1 for v in modes.values() if v == "all")
             check("Voice mode state", True, f"{all_count} on, {off_count} off, {len(modes)} total")

scripts/release.py

@@ -50,11 +50,15 @@ AUTHOR_MAP = {
     "71184274+MassiveMassimo@users.noreply.github.com": "MassiveMassimo",
     "massivemassimo@users.noreply.github.com": "MassiveMassimo",
     "82637225+kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
+    "keifergu@tencent.com": "keifergu",
     "kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
+    "abner.the.foreman@agentmail.to": "Abnertheforeman",
+    "harryykyle1@gmail.com": "hharry11",
     "kshitijk4poor@gmail.com": "kshitijk4poor",
     "16443023+stablegenius49@users.noreply.github.com": "stablegenius49",
     "185121704+stablegenius49@users.noreply.github.com": "stablegenius49",
     "101283333+batuhankocyigit@users.noreply.github.com": "batuhankocyigit",
+    "255305877+ismell0992-afk@users.noreply.github.com": "ismell0992-afk",
     "valdi.jorge@gmail.com": "jvcl",
     "francip@gmail.com": "francip",
     "omni@comelse.com": "omnissiah-comelse",
@@ -92,6 +96,8 @@ AUTHOR_MAP = {
     "135070653+sgaofen@users.noreply.github.com": "sgaofen",
     "nocoo@users.noreply.github.com": "nocoo",
     "30841158+n-WN@users.noreply.github.com": "n-WN",
+    "tsuijinglei@gmail.com": "hiddenpuppy",
+    "jerome@clawwork.ai": "HiddenPuppy",
     "leoyuan0099@gmail.com": "keyuyuan",
     "bxzt2006@163.com": "Only-Code-A",
     "i@troy-y.org": "TroyMitchell911",
@@ -99,6 +105,7 @@ AUTHOR_MAP = {
     "hansnow@users.noreply.github.com": "hansnow",
     "134848055+UNLINEARITY@users.noreply.github.com": "UNLINEARITY",
     "ben.burtenshaw@gmail.com": "burtenshaw",
+    "roopaknijhara@gmail.com": "rnijhara",
     # contributors (manual mapping from git names)
     "ahmedsherif95@gmail.com": "asheriif",
     "liujinkun@bytedance.com": "liujinkun2025",
@@ -134,6 +141,7 @@ AUTHOR_MAP = {
     "331214+counterposition@users.noreply.github.com": "counterposition",
     "blspear@gmail.com": "BrennerSpear",
     "akhater@gmail.com": "akhater",
+    "Cos_Admin@PTG-COS.lodluvup4uaudnm3ycd14giyug.xx.internal.cloudapp.net": "akhater",
     "239876380+handsdiff@users.noreply.github.com": "handsdiff",
     "hesapacicam112@gmail.com": "etherman-os",
     "mark.ramsell@rivermounts.com": "mark-ramsell",
@@ -175,6 +183,7 @@ AUTHOR_MAP = {
     "adavyasharma@gmail.com": "adavyas",
     "acaayush1111@gmail.com": "aayushchaudhary",
     "jason@outland.art": "jasonoutland",
+    "73175452+Magaav@users.noreply.github.com": "Magaav",
     "mrflu1918@proton.me": "SPANISHFLU",
     "morganemoss@gmai.com": "mormio",
     "kopjop926@gmail.com": "cesareth",
@@ -279,6 +288,7 @@ AUTHOR_MAP = {
     "srhtsrht17@gmail.com": "Sertug17",
     "stephenschoettler@gmail.com": "stephenschoettler",
     "tanishq231003@gmail.com": "yyovil",
+    "taosiyuan163@153.com": "taosiyuan163",
     "tesseracttars@gmail.com": "tesseracttars-creator",
     "tianliangjay@gmail.com": "xingkongliang",
     "tranquil_flow@protonmail.com": "Tranquil-Flow",
@@ -335,6 +345,32 @@ AUTHOR_MAP = {
     "shalompmc0505@naver.com": "pinion05",
     "105142614+VTRiot@users.noreply.github.com": "VTRiot",
     "vivien000812@gmail.com": "iamagenius00",
+    "89228157+Feranmi10@users.noreply.github.com": "Feranmi10",
+    "simon@gtcl.us": "simon-gtcl",
+    "suzukaze.haduki@gmail.com": "houko",
+    "cliff@cigii.com": "cgarwood82",
+    "anna@oa.ke": "anna-oake",
+    "jaffarkeikei@gmail.com": "jaffarkeikei",
+    "hxp@hxp.plus": "hxp-plus",
+    "3580442280@qq.com": "Tianworld",
+    "wujianxu91@gmail.com": "wujhsu",
+    "zhrh120@gmail.com": "niyoh120",
+    "vrinek@hey.com": "vrinek",
+    "268198004+xandersbell@users.noreply.github.com": "xandersbell",
+    "somme4096@gmail.com": "Somme4096",
+    "brian@tiuxo.com": "brianclemens",
+    "25944632+yudaiyan@users.noreply.github.com": "yudaiyan",
+    "chayton@sina.com": "ycbai",
+    "longsizhuo@gmail.com": "longsizhuo",
+    "chenb19870707@gmail.com": "ms-alan",
+    "276886827+WuTianyi123@users.noreply.github.com": "WuTianyi123",
+    "22549957+li0near@users.noreply.github.com": "li0near",
+    "23434080+sicnuyudidi@users.noreply.github.com": "sicnuyudidi",
+    "haimu0x0@proton.me": "haimu0x",
+    "abdelmajidnidnasser1@gmail.com": "NIDNASSER-Abdelmajid",
+    "projectadmin@wit.id": "projectadmin-dev",
+    "mrigankamondal10@gmail.com": "Dev-Mriganka",
+    "132275809+shushuzn@users.noreply.github.com": "shushuzn",
 }
 
 

scripts/whatsapp-bridge/package-lock.json

@@ -8,7 +8,7 @@
       "name": "hermes-whatsapp-bridge",
       "version": "1.0.0",
       "dependencies": {
-        "@whiskeysockets/baileys": "WhiskeySockets/Baileys#fix/abprops-abt-fetch",
+        "@whiskeysockets/baileys": "WhiskeySockets/Baileys#01047debd81beb20da7b7779b08edcb06aa03770",
         "express": "^4.21.0",
         "pino": "^9.0.0",
         "qrcode-terminal": "^0.12.0"

tests/agent/test_anthropic_adapter.py

@@ -1659,3 +1659,91 @@ class TestToolChoice:
             tool_choice="search",
         )
         assert kwargs["tool_choice"] == {"type": "tool", "name": "search"}
+
+
+
+# ---------------------------------------------------------------------------
+# max_tokens resolver — openclaw/openclaw#66664 port
+# ---------------------------------------------------------------------------
+
+from agent.anthropic_adapter import (
+    _resolve_positive_anthropic_max_tokens,
+    _resolve_anthropic_messages_max_tokens,
+)
+
+
+class TestResolvePositiveMaxTokens:
+    """Unit tests for the positive-int resolver helper."""
+
+    def test_positive_int_passes_through(self):
+        assert _resolve_positive_anthropic_max_tokens(8192) == 8192
+
+    def test_zero_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens(0) is None
+
+    def test_negative_int_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens(-1) is None
+        assert _resolve_positive_anthropic_max_tokens(-500) is None
+
+    def test_fractional_float_floored_and_kept_if_positive(self):
+        # 8192.7 -> 8192, still positive
+        assert _resolve_positive_anthropic_max_tokens(8192.7) == 8192
+
+    def test_small_positive_float_below_one_returns_none(self):
+        # 0.5 floors to 0, which is not positive
+        assert _resolve_positive_anthropic_max_tokens(0.5) is None
+
+    def test_negative_float_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens(-1.5) is None
+
+    def test_nan_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens(float("nan")) is None
+
+    def test_infinity_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens(float("inf")) is None
+        assert _resolve_positive_anthropic_max_tokens(float("-inf")) is None
+
+    def test_bool_true_returns_none(self):
+        # True is an int subclass but semantically never a real max_tokens value
+        assert _resolve_positive_anthropic_max_tokens(True) is None
+        assert _resolve_positive_anthropic_max_tokens(False) is None
+
+    def test_string_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens("8192") is None
+
+    def test_none_returns_none(self):
+        assert _resolve_positive_anthropic_max_tokens(None) is None
+
+
+class TestResolveMessagesMaxTokens:
+    """Integration tests for the full Messages resolver."""
+
+    def test_positive_requested_wins(self):
+        assert _resolve_anthropic_messages_max_tokens(
+            8192, "claude-opus-4-6"
+        ) == 8192
+
+    def test_zero_falls_back_to_model_default(self):
+        # Should use _get_anthropic_max_output(model), not crash
+        result = _resolve_anthropic_messages_max_tokens(0, "claude-opus-4-6")
+        assert result > 0
+
+    def test_none_falls_back_to_model_default(self):
+        result = _resolve_anthropic_messages_max_tokens(None, "claude-opus-4-6")
+        assert result > 0
+
+    def test_negative_falls_back_to_model_default(self):
+        # Previously leaked -1 to the API; now falls back safely
+        result = _resolve_anthropic_messages_max_tokens(-1, "claude-opus-4-6")
+        assert result > 0
+
+    def test_fractional_positive_floored(self):
+        assert _resolve_anthropic_messages_max_tokens(
+            8192.5, "claude-opus-4-6"
+        ) == 8192
+
+    def test_sub_one_float_falls_back(self):
+        # 0.5 floors to 0 -> not positive -> falls back to model ceiling
+        result = _resolve_anthropic_messages_max_tokens(0.5, "claude-opus-4-6")
+        assert result > 0
+        assert result != 0

tests/agent/test_anthropic_normalize_v2.py

@@ -1,238 +0,0 @@
-"""Regression tests: normalize_anthropic_response_v2 vs v1.
-
-Constructs mock Anthropic responses and asserts that the v2 function
-(returning NormalizedResponse) produces identical field values to the
-original v1 function (returning SimpleNamespace + finish_reason).
-"""
-
-import json
-import pytest
-from types import SimpleNamespace
-
-from agent.anthropic_adapter import (
-    normalize_anthropic_response,
-    normalize_anthropic_response_v2,
-)
-from agent.transports.types import NormalizedResponse, ToolCall
-
-
-# ---------------------------------------------------------------------------
-# Helpers to build mock Anthropic SDK responses
-# ---------------------------------------------------------------------------
-
-def _text_block(text: str):
-    return SimpleNamespace(type="text", text=text)
-
-
-def _thinking_block(thinking: str, signature: str = "sig_abc"):
-    return SimpleNamespace(type="thinking", thinking=thinking, signature=signature)
-
-
-def _tool_use_block(id: str, name: str, input: dict):
-    return SimpleNamespace(type="tool_use", id=id, name=name, input=input)
-
-
-def _response(content_blocks, stop_reason="end_turn"):
-    return SimpleNamespace(
-        content=content_blocks,
-        stop_reason=stop_reason,
-        usage=SimpleNamespace(
-            input_tokens=10,
-            output_tokens=5,
-        ),
-    )
-
-
-# ---------------------------------------------------------------------------
-# Tests
-# ---------------------------------------------------------------------------
-
-class TestTextOnly:
-    """Text-only response — no tools, no thinking."""
-
-    def setup_method(self):
-        self.resp = _response([_text_block("Hello world")])
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_type(self):
-        assert isinstance(self.v2, NormalizedResponse)
-
-    def test_content_matches(self):
-        assert self.v2.content == self.v1_msg.content
-
-    def test_finish_reason_matches(self):
-        assert self.v2.finish_reason == self.v1_finish
-
-    def test_no_tool_calls(self):
-        assert self.v2.tool_calls is None
-        assert self.v1_msg.tool_calls is None
-
-    def test_no_reasoning(self):
-        assert self.v2.reasoning is None
-        assert self.v1_msg.reasoning is None
-
-
-class TestWithToolCalls:
-    """Response with tool calls."""
-
-    def setup_method(self):
-        self.resp = _response(
-            [
-                _text_block("I'll check that"),
-                _tool_use_block("toolu_abc", "terminal", {"command": "ls"}),
-                _tool_use_block("toolu_def", "read_file", {"path": "/tmp"}),
-            ],
-            stop_reason="tool_use",
-        )
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_finish_reason(self):
-        assert self.v2.finish_reason == "tool_calls"
-        assert self.v1_finish == "tool_calls"
-
-    def test_tool_call_count(self):
-        assert len(self.v2.tool_calls) == 2
-        assert len(self.v1_msg.tool_calls) == 2
-
-    def test_tool_call_ids_match(self):
-        for i in range(2):
-            assert self.v2.tool_calls[i].id == self.v1_msg.tool_calls[i].id
-
-    def test_tool_call_names_match(self):
-        assert self.v2.tool_calls[0].name == "terminal"
-        assert self.v2.tool_calls[1].name == "read_file"
-        for i in range(2):
-            assert self.v2.tool_calls[i].name == self.v1_msg.tool_calls[i].function.name
-
-    def test_tool_call_arguments_match(self):
-        for i in range(2):
-            assert self.v2.tool_calls[i].arguments == self.v1_msg.tool_calls[i].function.arguments
-
-    def test_content_preserved(self):
-        assert self.v2.content == self.v1_msg.content
-        assert "check that" in self.v2.content
-
-
-class TestWithThinking:
-    """Response with thinking blocks (Claude 3.5+ extended thinking)."""
-
-    def setup_method(self):
-        self.resp = _response([
-            _thinking_block("Let me think about this carefully..."),
-            _text_block("The answer is 42."),
-        ])
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_reasoning_matches(self):
-        assert self.v2.reasoning == self.v1_msg.reasoning
-        assert "think about this" in self.v2.reasoning
-
-    def test_reasoning_details_in_provider_data(self):
-        v1_details = self.v1_msg.reasoning_details
-        v2_details = self.v2.provider_data.get("reasoning_details") if self.v2.provider_data else None
-        assert v1_details is not None
-        assert v2_details is not None
-        assert len(v2_details) == len(v1_details)
-
-    def test_content_excludes_thinking(self):
-        assert self.v2.content == "The answer is 42."
-
-
-class TestMixed:
-    """Response with thinking + text + tool calls."""
-
-    def setup_method(self):
-        self.resp = _response(
-            [
-                _thinking_block("Planning my approach..."),
-                _text_block("I'll run the command"),
-                _tool_use_block("toolu_xyz", "terminal", {"command": "pwd"}),
-            ],
-            stop_reason="tool_use",
-        )
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_all_fields_present(self):
-        assert self.v2.content is not None
-        assert self.v2.tool_calls is not None
-        assert self.v2.reasoning is not None
-        assert self.v2.finish_reason == "tool_calls"
-
-    def test_content_matches(self):
-        assert self.v2.content == self.v1_msg.content
-
-    def test_reasoning_matches(self):
-        assert self.v2.reasoning == self.v1_msg.reasoning
-
-    def test_tool_call_matches(self):
-        assert self.v2.tool_calls[0].id == self.v1_msg.tool_calls[0].id
-        assert self.v2.tool_calls[0].name == self.v1_msg.tool_calls[0].function.name
-
-
-class TestStopReasons:
-    """Verify finish_reason mapping matches between v1 and v2."""
-
-    @pytest.mark.parametrize("stop_reason,expected", [
-        ("end_turn", "stop"),
-        ("tool_use", "tool_calls"),
-        ("max_tokens", "length"),
-        ("stop_sequence", "stop"),
-        ("refusal", "content_filter"),
-        ("model_context_window_exceeded", "length"),
-        ("unknown_future_reason", "stop"),
-    ])
-    def test_stop_reason_mapping(self, stop_reason, expected):
-        resp = _response([_text_block("x")], stop_reason=stop_reason)
-        v1_msg, v1_finish = normalize_anthropic_response(resp)
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.finish_reason == v1_finish == expected
-
-
-class TestStripToolPrefix:
-    """Verify mcp_ prefix stripping works identically."""
-
-    def test_prefix_stripped(self):
-        resp = _response(
-            [_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
-            stop_reason="tool_use",
-        )
-        v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=True)
-        v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=True)
-        assert v1_msg.tool_calls[0].function.name == "terminal"
-        assert v2.tool_calls[0].name == "terminal"
-
-    def test_prefix_kept(self):
-        resp = _response(
-            [_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
-            stop_reason="tool_use",
-        )
-        v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=False)
-        v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=False)
-        assert v1_msg.tool_calls[0].function.name == "mcp_terminal"
-        assert v2.tool_calls[0].name == "mcp_terminal"
-
-
-class TestEdgeCases:
-    """Edge cases: empty content, no blocks, etc."""
-
-    def test_empty_content_blocks(self):
-        resp = _response([])
-        v1_msg, v1_finish = normalize_anthropic_response(resp)
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.content == v1_msg.content
-        assert v2.content is None
-
-    def test_no_reasoning_details_means_none_provider_data(self):
-        resp = _response([_text_block("hi")])
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.provider_data is None
-
-    def test_v2_returns_dataclass_not_namespace(self):
-        resp = _response([_text_block("hi")])
-        v2 = normalize_anthropic_response_v2(resp)
-        assert isinstance(v2, NormalizedResponse)
-        assert not isinstance(v2, SimpleNamespace)

tests/agent/test_context_compressor.py

@@ -253,6 +253,35 @@ class TestSummaryPrefixNormalization:
 
 
 class TestCompressWithClient:
+    def test_system_content_list_gets_compression_note_without_crashing(self):
+        mock_response = MagicMock()
+        mock_response.choices = [MagicMock()]
+        mock_response.choices[0].message.content = "summary text"
+
+        with patch("agent.context_compressor.get_model_context_length", return_value=100000):
+            c = ContextCompressor(model="test", quiet_mode=True, protect_first_n=2, protect_last_n=2)
+
+        msgs = [
+            {"role": "system", "content": [{"type": "text", "text": "system prompt"}]},
+            {"role": "user", "content": "msg 1"},
+            {"role": "assistant", "content": "msg 2"},
+            {"role": "user", "content": "msg 3"},
+            {"role": "assistant", "content": "msg 4"},
+            {"role": "user", "content": "msg 5"},
+            {"role": "assistant", "content": "msg 6"},
+            {"role": "user", "content": "msg 7"},
+        ]
+
+        with patch("agent.context_compressor.call_llm", return_value=mock_response):
+            result = c.compress(msgs)
+
+        assert isinstance(result[0]["content"], list)
+        assert any(
+            isinstance(block, dict)
+            and "compacted into a handoff summary" in block.get("text", "")
+            for block in result[0]["content"]
+        )
+
     def test_summarization_path(self):
         mock_client = MagicMock()
         mock_response = MagicMock()
@@ -460,6 +489,41 @@ class TestCompressWithClient:
         assert len(first_tail) == 1
         assert "summary text" in first_tail[0]["content"]
 
+    def test_double_collision_merges_summary_into_list_tail_content(self):
+        """Structured tail content should accept a merged summary without TypeError."""
+        mock_response = MagicMock()
+        mock_response.choices = [MagicMock()]
+        mock_response.choices[0].message.content = "summary text"
+
+        with patch("agent.context_compressor.get_model_context_length", return_value=100000):
+            c = ContextCompressor(model="test", quiet_mode=True, protect_first_n=3, protect_last_n=3)
+
+        msgs = [
+            {"role": "system", "content": "system prompt"},
+            {"role": "user", "content": "msg 1"},
+            {"role": "assistant", "content": "msg 2"},
+            {"role": "user", "content": "msg 3"},
+            {"role": "assistant", "content": "msg 4"},
+            {"role": "user", "content": "msg 5"},
+            {"role": "user", "content": [{"type": "text", "text": "msg 6"}]},
+            {"role": "assistant", "content": "msg 7"},
+            {"role": "user", "content": "msg 8"},
+        ]
+
+        with patch("agent.context_compressor.call_llm", return_value=mock_response):
+            result = c.compress(msgs)
+
+        merged_tail = next(
+            m for m in result
+            if m.get("role") == "user" and isinstance(m.get("content"), list)
+        )
+        assert isinstance(merged_tail["content"], list)
+        assert "summary text" in merged_tail["content"][0]["text"]
+        assert any(
+            isinstance(block, dict) and block.get("text") == "msg 6"
+            for block in merged_tail["content"]
+        )
+
     def test_double_collision_user_head_assistant_tail(self):
         """Reverse double collision: head ends with 'user', tail starts with 'assistant'.
         summary='assistant' collides with tail, 'user' collides with head → merge."""

tests/agent/test_error_classifier.py

@@ -298,9 +298,15 @@ class TestClassifyApiError:
         assert result.retryable is False
 
     def test_404_generic(self):
+        # Generic 404 with no "model not found" signal — common for local
+        # llama.cpp/Ollama/vLLM endpoints with slightly wrong paths.  Treat
+        # as unknown (retryable) so the real error surfaces, rather than
+        # claiming the model is missing and silently falling back.
         e = MockAPIError("Not Found", status_code=404)
         result = classify_api_error(e)
-        assert result.reason == FailoverReason.model_not_found
+        assert result.reason == FailoverReason.unknown
+        assert result.retryable is True
+        assert result.should_fallback is False
 
     # ── Payload too large ──
 
@@ -943,3 +949,94 @@ class TestAdversarialEdgeCases:
         e = MockAPIError("server error", status_code=500, body={"message": None})
         result = classify_api_error(e)
         assert result is not None
+
+
+# ── Test: SSL/TLS transient errors ─────────────────────────────────────
+
+class TestSSLTransientPatterns:
+    """SSL/TLS alerts mid-stream should retry as timeout, not unknown, and
+    should NOT trigger context compression even on a large session.
+
+    Motivation: OpenSSL 3.x changed TLS alert error code format
+    (`SSLV3_ALERT_BAD_RECORD_MAC` → `SSL/TLS_ALERT_BAD_RECORD_MAC`),
+    breaking string-exact matching in downstream retry logic.  We match
+    stable substrings instead.
+    """
+
+    def test_bad_record_mac_classifies_as_timeout(self):
+        """OpenSSL 3.x mid-stream bad record mac alert."""
+        e = Exception("[SSL: BAD_RECORD_MAC] sslv3 alert bad record mac (_ssl.c:2580)")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+        assert result.should_compress is False
+
+    def test_openssl_3x_format_classifies_as_timeout(self):
+        """New format `ERR_SSL_SSL/TLS_ALERT_BAD_RECORD_MAC` still matches
+        because we key on both space- and underscore-separated forms of
+        the stable `bad_record_mac` token."""
+        e = Exception("ERR_SSL_SSL/TLS_ALERT_BAD_RECORD_MAC during streaming")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+        assert result.should_compress is False
+
+    def test_tls_alert_internal_error_classifies_as_timeout(self):
+        e = Exception("[SSL: TLSV1_ALERT_INTERNAL_ERROR] tlsv1 alert internal error")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+        assert result.should_compress is False
+
+    def test_ssl_handshake_failure_classifies_as_timeout(self):
+        e = Exception("ssl handshake failure during mid-stream")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+
+    def test_ssl_prefix_classifies_as_timeout(self):
+        """Python's generic '[SSL: XYZ]' prefix from the ssl module."""
+        e = Exception("[SSL: UNEXPECTED_EOF_WHILE_READING] EOF occurred in violation of protocol")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+
+    def test_ssl_alert_on_large_session_does_not_compress(self):
+        """Critical: SSL alerts on big contexts must NOT trigger context
+        compression — compression is expensive and won't fix a transport
+        hiccup.  This is why _SSL_TRANSIENT_PATTERNS is separate from
+        _SERVER_DISCONNECT_PATTERNS.
+        """
+        e = Exception("[SSL: BAD_RECORD_MAC] sslv3 alert bad record mac")
+        result = classify_api_error(
+            e,
+            approx_tokens=180000,      # 90% of a 200k-context window
+            context_length=200000,
+            num_messages=300,
+        )
+        assert result.reason == FailoverReason.timeout
+        assert result.should_compress is False
+
+    def test_plain_disconnect_on_large_session_still_compresses(self):
+        """Regression guard: the context-overflow-via-disconnect path
+        (non-SSL disconnects on large sessions) must still trigger
+        compression.  Only SSL-specific disconnects skip it.
+        """
+        e = Exception("Server disconnected without sending a response")
+        result = classify_api_error(
+            e,
+            approx_tokens=180000,
+            context_length=200000,
+            num_messages=300,
+        )
+        assert result.reason == FailoverReason.context_overflow
+        assert result.should_compress is True
+
+    def test_real_ssl_error_type_classifies_as_timeout(self):
+        """Real ssl.SSLError instance — the type name alone (not message)
+        should route to the transport bucket."""
+        import ssl
+        e = ssl.SSLError("arbitrary ssl error")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True

tests/agent/test_local_stream_timeout.py

@@ -106,3 +106,25 @@ class TestIsLocalEndpoint:
     ])
     def test_remote_endpoints(self, url):
         assert is_local_endpoint(url) is False
+
+    @pytest.mark.parametrize("url", [
+        "http://100.64.0.0:11434",            # lower bound of CGNAT block
+        "http://100.64.0.1:11434/v1",         # lower bound +1
+        "http://100.77.243.5:11434",          # representative Tailscale host
+        "https://100.100.100.100:443",        # Tailscale MagicDNS anchor
+        "https://100.127.255.254:443",        # upper bound -1
+        "http://100.127.255.255:11434",       # upper bound of CGNAT block
+    ])
+    def test_tailscale_cgnat_is_local(self, url):
+        """Tailscale 100.64.0.0/10 should be treated as local for timeout bumps."""
+        assert is_local_endpoint(url) is True
+
+    @pytest.mark.parametrize("url", [
+        "http://100.63.255.255:11434",        # just below CGNAT block
+        "http://100.128.0.1:11434",           # just above CGNAT block
+        "http://100.200.0.1:11434",           # well outside CGNAT
+        "http://99.64.0.1:11434",             # first octet wrong
+    ])
+    def test_near_but_not_cgnat_is_remote(self, url):
+        """Hosts adjacent to but outside 100.64.0.0/10 must not match."""
+        assert is_local_endpoint(url) is False

tests/agent/test_memory_user_id.py

@@ -79,6 +79,28 @@ class TestMemoryManagerUserIdThreading:
         assert p._init_kwargs.get("platform") == "telegram"
         assert p._init_session_id == "sess-123"
 
+    def test_chat_context_forwarded_to_provider(self):
+        mgr = MemoryManager()
+        p = RecordingProvider()
+        mgr.add_provider(p)
+
+        mgr.initialize_all(
+            session_id="sess-chat",
+            platform="discord",
+            user_id="discord_u_7",
+            user_name="fakeusername",
+            chat_id="1485316232612941897",
+            chat_name="fakeassistantname-forums",
+            chat_type="thread",
+            thread_id="1491249007475949698",
+        )
+
+        assert p._init_kwargs.get("user_name") == "fakeusername"
+        assert p._init_kwargs.get("chat_id") == "1485316232612941897"
+        assert p._init_kwargs.get("chat_name") == "fakeassistantname-forums"
+        assert p._init_kwargs.get("chat_type") == "thread"
+        assert p._init_kwargs.get("thread_id") == "1491249007475949698"
+
     def test_no_user_id_when_cli(self):
         """CLI sessions should not have user_id in kwargs."""
         mgr = MemoryManager()
@@ -334,3 +356,4 @@ class TestAIAgentUserIdPropagation:
             agent = object.__new__(AIAgent)
             agent._user_id = None
             assert agent._user_id is None
+

tests/agent/test_model_metadata.py

@@ -385,6 +385,7 @@ class TestStripProviderPrefix:
         assert _strip_provider_prefix("local:my-model") == "my-model"
         assert _strip_provider_prefix("openrouter:anthropic/claude-sonnet-4") == "anthropic/claude-sonnet-4"
         assert _strip_provider_prefix("anthropic:claude-sonnet-4") == "claude-sonnet-4"
+        assert _strip_provider_prefix("stepfun:step-3.5-flash") == "step-3.5-flash"
 
     def test_ollama_model_tag_preserved(self):
         """Ollama model:tag format must NOT be stripped."""

tests/agent/test_models_dev.py

@@ -82,6 +82,7 @@ class TestProviderMapping:
     def test_known_providers_mapped(self):
         assert PROVIDER_TO_MODELS_DEV["anthropic"] == "anthropic"
         assert PROVIDER_TO_MODELS_DEV["copilot"] == "github-copilot"
+        assert PROVIDER_TO_MODELS_DEV["stepfun"] == "stepfun"
         assert PROVIDER_TO_MODELS_DEV["kilocode"] == "kilo"
         assert PROVIDER_TO_MODELS_DEV["ai-gateway"] == "vercel"
 

tests/agent/test_usage_pricing.py

@@ -39,6 +39,73 @@ def test_normalize_usage_openai_subtracts_cached_prompt_tokens():
     assert normalized.output_tokens == 700
 
 
+def test_normalize_usage_openai_reads_top_level_anthropic_cache_fields():
+    """Some OpenAI-compatible proxies (OpenRouter, Vercel AI Gateway, Cline) expose
+    Anthropic-style cache token counts at the top level of the usage object when
+    routing Claude models, instead of nesting them in prompt_tokens_details.
+
+    Regression guard for the bug fixed in cline/cline#10266 — before this fix,
+    the chat-completions branch of normalize_usage() only read
+    prompt_tokens_details.cache_write_tokens and completely missed the
+    cache_creation_input_tokens case, so cache writes showed as 0 and reflected
+    inputTokens were overstated by the cache-write amount.
+    """
+    usage = SimpleNamespace(
+        prompt_tokens=1000,
+        completion_tokens=200,
+        prompt_tokens_details=SimpleNamespace(cached_tokens=500),
+        cache_creation_input_tokens=300,
+    )
+
+    normalized = normalize_usage(usage, provider="openrouter", api_mode="chat_completions")
+
+    # Expected: cache read from prompt_tokens_details.cached_tokens (preferred),
+    # cache write from top-level cache_creation_input_tokens (fallback).
+    assert normalized.cache_read_tokens == 500
+    assert normalized.cache_write_tokens == 300
+    # input_tokens = prompt_total - cache_read - cache_write = 1000 - 500 - 300 = 200
+    assert normalized.input_tokens == 200
+    assert normalized.output_tokens == 200
+
+
+def test_normalize_usage_openai_reads_top_level_cache_read_when_details_missing():
+    """Some proxies expose only top-level Anthropic-style fields with no
+    prompt_tokens_details object. Regression guard for cline/cline#10266.
+    """
+    usage = SimpleNamespace(
+        prompt_tokens=1000,
+        completion_tokens=200,
+        cache_read_input_tokens=500,
+        cache_creation_input_tokens=300,
+    )
+
+    normalized = normalize_usage(usage, provider="openrouter", api_mode="chat_completions")
+
+    assert normalized.cache_read_tokens == 500
+    assert normalized.cache_write_tokens == 300
+    assert normalized.input_tokens == 200
+
+
+def test_normalize_usage_openai_prefers_prompt_tokens_details_over_top_level():
+    """When both prompt_tokens_details and top-level Anthropic fields are
+    present, we prefer the OpenAI-standard nested fields. Top-level Anthropic
+    fields are only a fallback when the nested ones are absent/zero.
+    """
+    usage = SimpleNamespace(
+        prompt_tokens=1000,
+        completion_tokens=200,
+        prompt_tokens_details=SimpleNamespace(cached_tokens=600, cache_write_tokens=150),
+        # Intentionally different values — proving we ignore these when details exist.
+        cache_read_input_tokens=999,
+        cache_creation_input_tokens=999,
+    )
+
+    normalized = normalize_usage(usage, provider="openrouter", api_mode="chat_completions")
+
+    assert normalized.cache_read_tokens == 600
+    assert normalized.cache_write_tokens == 150
+
+
 def test_openrouter_models_api_pricing_is_converted_from_per_token_to_per_million(monkeypatch):
     monkeypatch.setattr(
         "agent.usage_pricing.fetch_model_metadata",

tests/agent/transports/test_transport.py

@@ -114,6 +114,14 @@ class TestAnthropicTransport:
         r = SimpleNamespace(content=[])
         assert transport.validate_response(r) is False
 
+    def test_validate_response_empty_content_with_end_turn_is_valid(self, transport):
+        r = SimpleNamespace(content=[], stop_reason="end_turn")
+        assert transport.validate_response(r) is True
+
+    def test_validate_response_empty_content_with_tool_use_is_invalid(self, transport):
+        r = SimpleNamespace(content=[], stop_reason="tool_use")
+        assert transport.validate_response(r) is False
+
     def test_validate_response_valid(self, transport):
         r = SimpleNamespace(content=[SimpleNamespace(type="text", text="hello")])
         assert transport.validate_response(r) is True

tests/gateway/test_debug_command.py

@@ -0,0 +1,60 @@
+"""Tests for the gateway /debug command."""
+
+from unittest.mock import patch
+
+import pytest
+
+from gateway.config import GatewayConfig, Platform
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionSource
+
+
+def _make_event(text="/debug", platform=Platform.TELEGRAM,
+                user_id="12345", chat_id="67890"):
+    source = SessionSource(
+        platform=platform,
+        user_id=user_id,
+        chat_id=chat_id,
+        user_name="testuser",
+    )
+    return MessageEvent(text=text, source=source)
+
+
+def _make_runner():
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    runner.config = GatewayConfig()
+    runner.adapters = {}
+    return runner
+
+
+class TestHandleDebugCommand:
+    @pytest.mark.asyncio
+    async def test_debug_sweeps_expired_pastes_before_upload(self):
+        runner = _make_runner()
+        event = _make_event()
+
+        with patch("hermes_cli.debug._sweep_expired_pastes", return_value=(0, 0)) as mock_sweep, \
+             patch("hermes_cli.debug._capture_dump", return_value="dump"), \
+             patch("hermes_cli.debug.collect_debug_report", return_value="report"), \
+             patch("hermes_cli.debug.upload_to_pastebin", return_value="https://paste.rs/report"), \
+             patch("hermes_cli.debug._schedule_auto_delete"):
+            result = await runner._handle_debug_command(event)
+
+        mock_sweep.assert_called_once()
+        assert "https://paste.rs/report" in result
+
+    @pytest.mark.asyncio
+    async def test_debug_survives_sweep_failure(self):
+        runner = _make_runner()
+        event = _make_event()
+
+        with patch("hermes_cli.debug._sweep_expired_pastes", side_effect=RuntimeError("offline")), \
+             patch("hermes_cli.debug._capture_dump", return_value="dump"), \
+             patch("hermes_cli.debug.collect_debug_report", return_value="report"), \
+             patch("hermes_cli.debug.upload_to_pastebin", return_value="https://paste.rs/report"), \
+             patch("hermes_cli.debug._schedule_auto_delete"):
+            result = await runner._handle_debug_command(event)
+
+        assert "https://paste.rs/report" in result

tests/gateway/test_discord_slash_commands.py

@@ -199,6 +199,89 @@ async def test_auto_registered_command_with_args(adapter):
     )
 
 
+@pytest.mark.asyncio
+async def test_auto_registers_plugin_commands_for_discord(adapter):
+    """Plugin slash commands should appear as native Discord app commands."""
+    adapter._run_simple_slash = AsyncMock()
+
+    with patch(
+        "hermes_cli.plugins.get_plugin_commands",
+        return_value={
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics dashboard",
+                "args_hint": "dias:7 formato:json",
+                "plugin": "metrics-plugin",
+            }
+        },
+    ):
+        adapter._register_slash_commands()
+
+    tree_names = set(adapter._client.tree.commands.keys())
+    assert "metricas" in tree_names
+
+    metricas_cmd = adapter._client.tree.commands["metricas"]
+    interaction = SimpleNamespace()
+    await metricas_cmd.callback(interaction, args="dias:7 formato:json")
+    adapter._run_simple_slash.assert_awaited_once_with(
+        interaction, "/metricas dias:7 formato:json"
+    )
+
+
+@pytest.mark.asyncio
+async def test_auto_registered_plugin_command_without_args_hint(adapter):
+    """Plugin commands without args_hint should register as parameterless."""
+    adapter._run_simple_slash = AsyncMock()
+
+    with patch(
+        "hermes_cli.plugins.get_plugin_commands",
+        return_value={
+            "ping": {
+                "handler": lambda _a: "pong",
+                "description": "Ping the plugin",
+                "args_hint": "",
+                "plugin": "ping-plugin",
+            }
+        },
+    ):
+        adapter._register_slash_commands()
+
+    assert "ping" in adapter._client.tree.commands
+    ping_cmd = adapter._client.tree.commands["ping"]
+    interaction = SimpleNamespace()
+    await ping_cmd.callback(interaction)
+    adapter._run_simple_slash.assert_awaited_once_with(interaction, "/ping")
+
+
+@pytest.mark.asyncio
+async def test_plugin_command_name_conflict_skipped(adapter):
+    """A plugin command that collides with a built-in must not override it."""
+    adapter._run_simple_slash = AsyncMock()
+
+    with patch(
+        "hermes_cli.plugins.get_plugin_commands",
+        return_value={
+            "status": {
+                "handler": lambda _a: "plugin-status",
+                "description": "Plugin status",
+                "args_hint": "",
+                "plugin": "shadow-plugin",
+            }
+        },
+    ):
+        adapter._register_slash_commands()
+
+    # Built-ins are registered via @tree.command as plain functions. A
+    # plugin-registered override would install a _FakeCommand instance
+    # (has .callback) via tree.add_command. If the conflict-skip logic
+    # fires, the slot remains a bare function.
+    status_entry = adapter._client.tree.commands["status"]
+    assert callable(status_entry) and not hasattr(status_entry, "callback"), (
+        "plugin registration overrode the built-in /status command — "
+        "the already_registered skip must prevent this"
+    )
+
+
 # ------------------------------------------------------------------
 # _handle_thread_create_slash — success, session dispatch, failure
 # ------------------------------------------------------------------

tests/gateway/test_hooks.py

@@ -220,3 +220,99 @@ class TestEmit:
 
         await reg.emit("agent:start")  # no context arg
         assert captured[0] == {}
+
+
+class TestEmitCollect:
+    """Tests for emit_collect() — returns handler return values for decision-style hooks."""
+
+    @pytest.mark.asyncio
+    async def test_collects_sync_return_values(self):
+        reg = HookRegistry()
+        reg._handlers["command:status"] = [
+            lambda _e, _c: {"decision": "allow"},
+            lambda _e, _c: {"decision": "deny", "message": "nope"},
+        ]
+
+        results = await reg.emit_collect("command:status", {})
+
+        assert results == [
+            {"decision": "allow"},
+            {"decision": "deny", "message": "nope"},
+        ]
+
+    @pytest.mark.asyncio
+    async def test_collects_async_return_values(self):
+        reg = HookRegistry()
+
+        async def _async_handler(_event_type, _ctx):
+            return {"decision": "handled", "message": "done"}
+
+        reg._handlers["command:ping"] = [_async_handler]
+
+        results = await reg.emit_collect("command:ping", {})
+
+        assert results == [{"decision": "handled", "message": "done"}]
+
+    @pytest.mark.asyncio
+    async def test_drops_none_return_values(self):
+        reg = HookRegistry()
+        reg._handlers["command:x"] = [
+            lambda _e, _c: None,  # fire-and-forget, returns nothing
+            lambda _e, _c: {"decision": "deny"},
+            lambda _e, _c: None,
+        ]
+
+        results = await reg.emit_collect("command:x", {})
+
+        assert results == [{"decision": "deny"}]
+
+    @pytest.mark.asyncio
+    async def test_handler_exception_does_not_abort_chain(self):
+        reg = HookRegistry()
+
+        def _raises(_e, _c):
+            raise ValueError("boom")
+
+        reg._handlers["command:x"] = [
+            _raises,
+            lambda _e, _c: {"decision": "allow"},
+        ]
+
+        results = await reg.emit_collect("command:x", {})
+
+        # First handler's exception is swallowed; second handler's value still collected.
+        assert results == [{"decision": "allow"}]
+
+    @pytest.mark.asyncio
+    async def test_wildcard_match_also_collected(self):
+        reg = HookRegistry()
+        reg._handlers["command:*"] = [lambda _e, _c: {"decision": "allow"}]
+        reg._handlers["command:reset"] = [lambda _e, _c: {"decision": "deny"}]
+
+        results = await reg.emit_collect("command:reset", {})
+
+        # Exact match fires first, then wildcard.
+        assert results == [{"decision": "deny"}, {"decision": "allow"}]
+
+    @pytest.mark.asyncio
+    async def test_no_handlers_returns_empty_list(self):
+        reg = HookRegistry()
+
+        results = await reg.emit_collect("unknown:event", {})
+
+        assert results == []
+
+    @pytest.mark.asyncio
+    async def test_default_context(self):
+        reg = HookRegistry()
+        captured = []
+
+        def _handler(event_type, context):
+            captured.append((event_type, context))
+            return None
+
+        reg._handlers["agent:start"] = [_handler]
+
+        await reg.emit_collect("agent:start")  # no context arg
+
+        assert captured == [("agent:start", {})]

tests/gateway/test_session.py

@@ -1059,6 +1059,7 @@ class TestRewriteTranscriptPreservesReasoning:
             role="assistant",
             content="The answer is 42.",
             reasoning="I need to think step by step.",
+            reasoning_content="provider scratchpad",
             reasoning_details=[{"type": "summary", "text": "step by step"}],
             codex_reasoning_items=[{"id": "r1", "type": "reasoning"}],
         )
@@ -1066,6 +1067,7 @@ class TestRewriteTranscriptPreservesReasoning:
         # Verify all three were stored
         before = db.get_messages_as_conversation(session_id)
         assert before[0].get("reasoning") == "I need to think step by step."
+        assert before[0].get("reasoning_content") == "provider scratchpad"
         assert before[0].get("reasoning_details") == [{"type": "summary", "text": "step by step"}]
         assert before[0].get("codex_reasoning_items") == [{"id": "r1", "type": "reasoning"}]
 
@@ -1082,5 +1084,6 @@ class TestRewriteTranscriptPreservesReasoning:
         # Load again — all three reasoning fields must survive
         after = db.get_messages_as_conversation(session_id)
         assert after[0].get("reasoning") == "I need to think step by step."
+        assert after[0].get("reasoning_content") == "provider scratchpad"
         assert after[0].get("reasoning_details") == [{"type": "summary", "text": "step by step"}]
         assert after[0].get("codex_reasoning_items") == [{"id": "r1", "type": "reasoning"}]

tests/gateway/test_session_boundary_security_state.py

@@ -0,0 +1,201 @@
+"""Regression tests for approval-state cleanup on session boundaries."""
+
+from datetime import datetime
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from gateway.config import Platform
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionEntry, SessionSource, build_session_key
+from tools import approval as approval_mod
+from tools.approval import (
+    approve_session,
+    enable_session_yolo,
+    is_approved,
+    is_session_yolo_enabled,
+)
+
+
+@pytest.fixture(autouse=True)
+def _clear_approval_state():
+    approval_mod._gateway_queues.clear()
+    approval_mod._gateway_notify_cbs.clear()
+    approval_mod._session_approved.clear()
+    approval_mod._session_yolo.clear()
+    approval_mod._permanent_approved.clear()
+    approval_mod._pending.clear()
+    yield
+    approval_mod._gateway_queues.clear()
+    approval_mod._gateway_notify_cbs.clear()
+    approval_mod._session_approved.clear()
+    approval_mod._session_yolo.clear()
+    approval_mod._permanent_approved.clear()
+    approval_mod._pending.clear()
+
+
+def _make_source() -> SessionSource:
+    return SessionSource(
+        platform=Platform.TELEGRAM,
+        user_id="u1",
+        chat_id="c1",
+        user_name="tester",
+        chat_type="dm",
+    )
+
+
+def _make_event(text: str) -> MessageEvent:
+    return MessageEvent(text=text, source=_make_source(), message_id="m1")
+
+
+def _make_entry(session_id: str, source: SessionSource | None = None) -> SessionEntry:
+    source = source or _make_source()
+    return SessionEntry(
+        session_key=build_session_key(source),
+        session_id=session_id,
+        created_at=datetime.now(),
+        updated_at=datetime.now(),
+        origin=source,
+        platform=source.platform,
+        chat_type=source.chat_type,
+    )
+
+
+def _make_resume_runner():
+    from gateway.run import GatewayRunner
+
+    source = _make_source()
+    session_key = build_session_key(source)
+    current_entry = _make_entry("current-session", source)
+    resumed_entry = _make_entry("resumed-session", source)
+
+    runner = object.__new__(GatewayRunner)
+    runner.adapters = {}
+    runner._background_tasks = set()
+    runner._async_flush_memories = AsyncMock()
+    runner._running_agents = {}
+    runner._running_agents_ts = {}
+    runner._busy_ack_ts = {}
+    runner._pending_approvals = {}
+    runner._agent_cache_lock = None
+    runner.session_store = MagicMock()
+    runner.session_store.get_or_create_session.return_value = current_entry
+    runner.session_store.switch_session.return_value = resumed_entry
+    runner.session_store.load_transcript.return_value = []
+    runner._session_db = MagicMock()
+    runner._session_db.resolve_session_by_title.return_value = "resumed-session"
+    runner._session_db.get_session_title.return_value = "Resumed Work"
+    return runner, session_key
+
+
+def _make_branch_runner():
+    from gateway.run import GatewayRunner
+
+    source = _make_source()
+    session_key = build_session_key(source)
+    current_entry = _make_entry("current-session", source)
+    branched_entry = _make_entry("branched-session", source)
+
+    runner = object.__new__(GatewayRunner)
+    runner.adapters = {}
+    runner.config = {}
+    runner._running_agents = {}
+    runner._running_agents_ts = {}
+    runner._busy_ack_ts = {}
+    runner._pending_approvals = {}
+    runner._agent_cache_lock = None
+    runner.session_store = MagicMock()
+    runner.session_store.get_or_create_session.return_value = current_entry
+    runner.session_store.load_transcript.return_value = [
+        {"role": "user", "content": "hello"},
+        {"role": "assistant", "content": "world"},
+    ]
+    runner.session_store.switch_session.return_value = branched_entry
+    runner._session_db = MagicMock()
+    runner._session_db.get_session_title.return_value = "Current Work"
+    runner._session_db.get_next_title_in_lineage.return_value = "Current Work #2"
+    return runner, session_key
+
+
+@pytest.mark.asyncio
+async def test_resume_clears_session_scoped_approval_and_yolo_state():
+    runner, session_key = _make_resume_runner()
+    other_key = "agent:main:telegram:dm:other-chat"
+
+    approve_session(session_key, "recursive delete")
+    approve_session(other_key, "recursive delete")
+    enable_session_yolo(session_key)
+    enable_session_yolo(other_key)
+    runner._pending_approvals[session_key] = {"command": "rm -rf /tmp/demo"}
+    runner._pending_approvals[other_key] = {"command": "rm -rf /tmp/other"}
+
+    result = await runner._handle_resume_command(_make_event("/resume Resumed Work"))
+
+    assert "Resumed session" in result
+    assert is_approved(session_key, "recursive delete") is False
+    assert is_session_yolo_enabled(session_key) is False
+    assert session_key not in runner._pending_approvals
+    assert is_approved(other_key, "recursive delete") is True
+    assert is_session_yolo_enabled(other_key) is True
+    assert other_key in runner._pending_approvals
+
+
+@pytest.mark.asyncio
+async def test_branch_clears_session_scoped_approval_and_yolo_state():
+    runner, session_key = _make_branch_runner()
+    other_key = "agent:main:telegram:dm:other-chat"
+
+    approve_session(session_key, "recursive delete")
+    approve_session(other_key, "recursive delete")
+    enable_session_yolo(session_key)
+    enable_session_yolo(other_key)
+    runner._pending_approvals[session_key] = {"command": "rm -rf /tmp/demo"}
+    runner._pending_approvals[other_key] = {"command": "rm -rf /tmp/other"}
+
+    result = await runner._handle_branch_command(_make_event("/branch"))
+
+    assert "Branched to" in result
+    assert is_approved(session_key, "recursive delete") is False
+    assert is_session_yolo_enabled(session_key) is False
+    assert session_key not in runner._pending_approvals
+    assert is_approved(other_key, "recursive delete") is True
+    assert is_session_yolo_enabled(other_key) is True
+    assert other_key in runner._pending_approvals
+
+
+def test_clear_session_boundary_security_state_is_scoped():
+    """The helper must wipe only the target session's approval/yolo state.
+
+    Also exercises the /new reset path indirectly: /new calls this helper,
+    so if the helper is scoped correctly, /new's clearing is correct too.
+    """
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    runner._pending_approvals = {}
+
+    source = _make_source()
+    session_key = build_session_key(source)
+    other_key = "agent:main:telegram:dm:other-chat"
+
+    approve_session(session_key, "recursive delete")
+    approve_session(other_key, "recursive delete")
+    enable_session_yolo(session_key)
+    enable_session_yolo(other_key)
+    runner._pending_approvals[session_key] = {"command": "rm -rf /tmp/demo"}
+    runner._pending_approvals[other_key] = {"command": "rm -rf /tmp/other"}
+
+    runner._clear_session_boundary_security_state(session_key)
+
+    # Target session cleared
+    assert is_approved(session_key, "recursive delete") is False
+    assert is_session_yolo_enabled(session_key) is False
+    assert session_key not in runner._pending_approvals
+    # Other session untouched
+    assert is_approved(other_key, "recursive delete") is True
+    assert is_session_yolo_enabled(other_key) is True
+    assert other_key in runner._pending_approvals
+
+    # Empty session_key is a no-op
+    runner._clear_session_boundary_security_state("")
+    assert is_approved(other_key, "recursive delete") is True

tests/gateway/test_slack.py

@@ -1031,7 +1031,7 @@ class TestReactions:
 
     @pytest.mark.asyncio
     async def test_reactions_in_message_flow(self, adapter):
-        """Reactions should be added on receipt and swapped on completion."""
+        """Reactions should be bracketed around actual processing via hooks."""
         adapter._app.client.reactions_add = AsyncMock()
         adapter._app.client.reactions_remove = AsyncMock()
         adapter._app.client.users_info = AsyncMock(return_value={
@@ -1047,15 +1047,147 @@ class TestReactions:
         }
         await adapter._handle_slack_message(event)
 
-        # Should have added 👀, then removed 👀, then added ✅
+        # _handle_slack_message should register the message for reactions
+        assert "1234567890.000001" in adapter._reacting_message_ids
+
+        # Simulate the base class calling on_processing_start
+        from gateway.platforms.base import MessageEvent, MessageType, SessionSource
+        from gateway.config import Platform
+        source = SessionSource(
+            platform=Platform.SLACK,
+            chat_id="C123",
+            chat_type="dm",
+            user_id="U_USER",
+        )
+        msg_event = MessageEvent(
+            text="hello",
+            message_type=MessageType.TEXT,
+            source=source,
+            message_id="1234567890.000001",
+        )
+        await adapter.on_processing_start(msg_event)
+
+        add_calls = adapter._app.client.reactions_add.call_args_list
+        assert len(add_calls) == 1
+        assert add_calls[0].kwargs["name"] == "eyes"
+
+        # Simulate the base class calling on_processing_complete
+        from gateway.platforms.base import ProcessingOutcome
+        await adapter.on_processing_complete(msg_event, ProcessingOutcome.SUCCESS)
+
         add_calls = adapter._app.client.reactions_add.call_args_list
         remove_calls = adapter._app.client.reactions_remove.call_args_list
         assert len(add_calls) == 2
-        assert add_calls[0].kwargs["name"] == "eyes"
         assert add_calls[1].kwargs["name"] == "white_check_mark"
         assert len(remove_calls) == 1
         assert remove_calls[0].kwargs["name"] == "eyes"
 
+        # Message ID should be cleaned up
+        assert "1234567890.000001" not in adapter._reacting_message_ids
+
+    @pytest.mark.asyncio
+    async def test_reactions_failure_outcome(self, adapter):
+        """Failed processing should add :x: instead of :white_check_mark:."""
+        adapter._app.client.reactions_add = AsyncMock()
+        adapter._app.client.reactions_remove = AsyncMock()
+
+        from gateway.platforms.base import MessageEvent, MessageType, SessionSource, ProcessingOutcome
+        from gateway.config import Platform
+        source = SessionSource(
+            platform=Platform.SLACK,
+            chat_id="C123",
+            chat_type="dm",
+            user_id="U_USER",
+        )
+        adapter._reacting_message_ids.add("1234567890.000002")
+        msg_event = MessageEvent(
+            text="hello",
+            message_type=MessageType.TEXT,
+            source=source,
+            message_id="1234567890.000002",
+        )
+        await adapter.on_processing_complete(msg_event, ProcessingOutcome.FAILURE)
+
+        add_calls = adapter._app.client.reactions_add.call_args_list
+        remove_calls = adapter._app.client.reactions_remove.call_args_list
+        assert len(add_calls) == 1
+        assert add_calls[0].kwargs["name"] == "x"
+        assert len(remove_calls) == 1
+        assert remove_calls[0].kwargs["name"] == "eyes"
+
+    @pytest.mark.asyncio
+    async def test_reactions_skipped_for_non_dm_non_mention(self, adapter):
+        """Non-DM, non-mention messages should not get reactions."""
+        adapter._app.client.reactions_add = AsyncMock()
+        adapter._app.client.reactions_remove = AsyncMock()
+        adapter._app.client.users_info = AsyncMock(return_value={
+            "user": {"profile": {"display_name": "Tyler"}}
+        })
+
+        event = {
+            "text": "hello",
+            "user": "U_USER",
+            "channel": "C123",
+            "channel_type": "channel",
+            "ts": "1234567890.000003",
+        }
+        await adapter._handle_slack_message(event)
+
+        # Should NOT register for reactions when not mentioned in a channel
+        assert "1234567890.000003" not in adapter._reacting_message_ids
+        adapter._app.client.reactions_add.assert_not_called()
+        adapter._app.client.reactions_remove.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_reactions_disabled_via_env(self, adapter, monkeypatch):
+        """SLACK_REACTIONS=false should suppress all reaction lifecycle."""
+        monkeypatch.setenv("SLACK_REACTIONS", "false")
+        adapter._app.client.reactions_add = AsyncMock()
+        adapter._app.client.reactions_remove = AsyncMock()
+        adapter._app.client.users_info = AsyncMock(return_value={
+            "user": {"profile": {"display_name": "Tyler"}}
+        })
+
+        event = {
+            "text": "hello",
+            "user": "U_USER",
+            "channel": "C123",
+            "channel_type": "im",
+            "ts": "1234567890.000004",
+        }
+        await adapter._handle_slack_message(event)
+
+        # Should NOT register for reactions when toggle is off
+        assert "1234567890.000004" not in adapter._reacting_message_ids
+
+        # Hooks should also be no-ops when disabled
+        from gateway.platforms.base import MessageEvent, MessageType, SessionSource, ProcessingOutcome
+        from gateway.config import Platform
+        source = SessionSource(
+            platform=Platform.SLACK,
+            chat_id="C123",
+            chat_type="dm",
+            user_id="U_USER",
+        )
+        msg_event = MessageEvent(
+            text="hello",
+            message_type=MessageType.TEXT,
+            source=source,
+            message_id="1234567890.000004",
+        )
+        # Force-add to verify hooks respect the toggle independently
+        adapter._reacting_message_ids.add("1234567890.000004")
+        await adapter.on_processing_start(msg_event)
+        await adapter.on_processing_complete(msg_event, ProcessingOutcome.SUCCESS)
+
+        adapter._app.client.reactions_add.assert_not_called()
+        adapter._app.client.reactions_remove.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_reactions_enabled_by_default(self, adapter):
+        """SLACK_REACTIONS defaults to true (matches existing behavior)."""
+        assert adapter._reactions_enabled() is True
+
 
 # ---------------------------------------------------------------------------
 # TestThreadReplyHandling

tests/gateway/test_status.py

@@ -65,7 +65,11 @@ class TestGatewayPidState:
         monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
         monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
 
-        assert status.get_running_pid() == os.getpid()
+        assert status.acquire_gateway_runtime_lock() is True
+        try:
+            assert status.get_running_pid() == os.getpid()
+        finally:
+            status.release_gateway_runtime_lock()
 
     def test_get_running_pid_accepts_script_style_gateway_cmdline(self, tmp_path, monkeypatch):
         monkeypatch.setenv("HERMES_HOME", str(tmp_path))
@@ -85,7 +89,11 @@ class TestGatewayPidState:
             lambda pid: "/venv/bin/python /repo/hermes_cli/main.py gateway run --replace",
         )
 
-        assert status.get_running_pid() == os.getpid()
+        assert status.acquire_gateway_runtime_lock() is True
+        try:
+            assert status.get_running_pid() == os.getpid()
+        finally:
+            status.release_gateway_runtime_lock()
 
     def test_get_running_pid_accepts_explicit_pid_path_without_cleanup(self, tmp_path, monkeypatch):
         other_home = tmp_path / "profile-home"
@@ -102,9 +110,116 @@ class TestGatewayPidState:
         monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
         monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
 
+        lock_path = other_home / "gateway.lock"
+        lock_path.write_text(json.dumps({
+            "pid": os.getpid(),
+            "kind": "hermes-gateway",
+            "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+            "start_time": 123,
+        }))
+        monkeypatch.setattr(status, "is_gateway_runtime_lock_active", lambda lock_path=None: True)
+
         assert status.get_running_pid(pid_path, cleanup_stale=False) == os.getpid()
         assert pid_path.exists()
 
+    def test_runtime_lock_claims_and_releases_liveness(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+
+        assert status.is_gateway_runtime_lock_active() is False
+        assert status.acquire_gateway_runtime_lock() is True
+        assert status.is_gateway_runtime_lock_active() is True
+
+        status.release_gateway_runtime_lock()
+
+        assert status.is_gateway_runtime_lock_active() is False
+
+    def test_get_running_pid_treats_pid_file_as_stale_without_runtime_lock(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        pid_path = tmp_path / "gateway.pid"
+        pid_path.write_text(json.dumps({
+            "pid": os.getpid(),
+            "kind": "hermes-gateway",
+            "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+            "start_time": 123,
+        }))
+
+        monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
+        monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
+        monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
+
+        assert status.get_running_pid() is None
+        assert not pid_path.exists()
+
+    def test_get_running_pid_cleans_stale_metadata_from_dead_foreign_pid(self, tmp_path, monkeypatch):
+        """Stale PID file from a *different* PID (crashed process) must still be cleaned.
+
+        Regression for: ``remove_pid_file()`` defensively refuses to delete a
+        PID file whose pid != ``os.getpid()`` to protect ``--replace``
+        handoffs.  Stale-cleanup must not go through that path or real
+        crashed-process PID files never get removed.
+        """
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        pid_path = tmp_path / "gateway.pid"
+        lock_path = tmp_path / "gateway.lock"
+
+        # PID that is guaranteed not alive and not our own.
+        dead_foreign_pid = 999999
+        assert dead_foreign_pid != os.getpid()
+
+        pid_path.write_text(json.dumps({
+            "pid": dead_foreign_pid,
+            "kind": "hermes-gateway",
+            "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+            "start_time": 123,
+        }))
+        lock_path.write_text(json.dumps({
+            "pid": dead_foreign_pid,
+            "kind": "hermes-gateway",
+            "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+            "start_time": 123,
+        }))
+
+        # No live lock holder → get_running_pid should clean both files.
+        assert status.get_running_pid() is None
+        assert not pid_path.exists()
+        assert not lock_path.exists()
+
+    def test_get_running_pid_falls_back_to_live_lock_record(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        pid_path = tmp_path / "gateway.pid"
+        pid_path.write_text(json.dumps({
+            "pid": 99999,
+            "kind": "hermes-gateway",
+            "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+            "start_time": 123,
+        }))
+
+        monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
+        monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
+        monkeypatch.setattr(
+            status,
+            "_build_pid_record",
+            lambda: {
+                "pid": os.getpid(),
+                "kind": "hermes-gateway",
+                "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+                "start_time": 123,
+            },
+        )
+        assert status.acquire_gateway_runtime_lock() is True
+
+        def fake_kill(pid, sig):
+            if pid == 99999:
+                raise ProcessLookupError
+            return None
+
+        monkeypatch.setattr(status.os, "kill", fake_kill)
+
+        try:
+            assert status.get_running_pid() == os.getpid()
+        finally:
+            status.release_gateway_runtime_lock()
+
 
 class TestGatewayRuntimeStatus:
     def test_write_runtime_status_overwrites_stale_pid_on_restart(self, tmp_path, monkeypatch):

tests/gateway/test_unknown_command.py

@@ -41,7 +41,11 @@ def _make_runner():
     adapter.send = AsyncMock()
     runner.adapters = {Platform.TELEGRAM: adapter}
     runner._voice_mode = {}
-    runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
+    runner.hooks = SimpleNamespace(
+        emit=AsyncMock(),
+        emit_collect=AsyncMock(return_value=[]),
+        loaded_hooks=False,
+    )
 
     session_entry = SessionEntry(
         session_key=build_session_key(_make_source()),
@@ -164,3 +168,206 @@ async def test_underscored_alias_for_hyphenated_builtin_not_flagged(monkeypatch)
     # Whatever /reload_mcp returns, it must not be the unknown-command guard.
     if result is not None:
         assert "Unknown command" not in result
+
+
+# ------------------------------------------------------------------
+# command:<name> decision hook — deny / handled / rewrite
+# ------------------------------------------------------------------
+
+@pytest.mark.asyncio
+async def test_command_hook_can_deny_before_dispatch(monkeypatch):
+    """A handler returning {"decision": "deny"} blocks a slash command early."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._run_agent = AsyncMock(
+        side_effect=AssertionError("denied slash command leaked to the agent")
+    )
+    runner._handle_status_command = AsyncMock(
+        side_effect=AssertionError("denied slash command reached its handler")
+    )
+    runner.hooks.emit_collect = AsyncMock(
+        return_value=[{"decision": "deny", "message": "Blocked by ACL"}]
+    )
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert result == "Blocked by ACL"
+    runner._run_agent.assert_not_called()
+    # The emit_collect call should use the canonical command name.
+    call_args = runner.hooks.emit_collect.await_args
+    assert call_args.args[0] == "command:status"
+
+
+@pytest.mark.asyncio
+async def test_command_hook_deny_without_message_uses_default(monkeypatch):
+    """A deny decision with no message falls back to a generic blocked string."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._handle_status_command = AsyncMock(
+        side_effect=AssertionError("denied slash command reached its handler")
+    )
+    runner.hooks.emit_collect = AsyncMock(return_value=[{"decision": "deny"}])
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert result is not None
+    assert "blocked" in result.lower()
+
+
+@pytest.mark.asyncio
+async def test_command_hook_can_mark_command_as_handled(monkeypatch):
+    """A handled decision short-circuits dispatch cleanly with a custom reply."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._handle_status_command = AsyncMock(
+        side_effect=AssertionError("handled slash command reached its handler")
+    )
+    runner.hooks.emit_collect = AsyncMock(
+        return_value=[{"decision": "handled", "message": "Already handled upstream"}]
+    )
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert result == "Already handled upstream"
+
+
+@pytest.mark.asyncio
+async def test_command_hook_allow_decision_is_passthrough(monkeypatch):
+    """A handler returning {"decision": "allow"} must NOT prevent normal dispatch."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._handle_status_command = AsyncMock(return_value="status: ok")
+    runner.hooks.emit_collect = AsyncMock(
+        return_value=[{"decision": "allow"}]
+    )
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert result == "status: ok"
+    runner._handle_status_command.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_command_hook_non_dict_return_values_ignored(monkeypatch):
+    """Hook return values that aren't dicts must not break dispatch."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._handle_status_command = AsyncMock(return_value="status: ok")
+    runner.hooks.emit_collect = AsyncMock(
+        return_value=["some string", 42, None, {}]
+    )
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert result == "status: ok"
+
+
+@pytest.mark.asyncio
+async def test_command_hook_fires_for_plugin_registered_command(monkeypatch):
+    """Plugin-registered slash commands should also trigger command:<name> hooks."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._run_agent = AsyncMock(
+        side_effect=AssertionError("plugin command leaked to the agent")
+    )
+    runner.hooks.emit_collect = AsyncMock(
+        return_value=[{"decision": "handled", "message": "intercepted"}]
+    )
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+    # Stub plugin command lookup so is_gateway_known_command() recognizes /metricas.
+    from hermes_cli import plugins as _plugins_mod
+
+    monkeypatch.setattr(
+        _plugins_mod,
+        "get_plugin_commands",
+        lambda: {"metricas": {"description": "Metrics", "args_hint": "dias:7"}},
+    )
+
+    result = await runner._handle_message(_make_event("/metricas dias:7"))
+
+    assert result == "intercepted"
+    # Hook event name uses the plugin command as canonical.
+    call_args = runner.hooks.emit_collect.await_args
+    assert call_args.args[0] == "command:metricas"
+    # Args are passed through in both "args" and "raw_args" keys.
+    ctx = call_args.args[1]
+    assert ctx["raw_args"] == "dias:7"
+
+
+@pytest.mark.asyncio
+async def test_command_hook_rewrite_routes_to_plugin(monkeypatch):
+    """A rewrite decision should re-resolve the command and route to the new one."""
+    import gateway.run as gateway_run
+
+    runner = _make_runner()
+    runner._run_agent = AsyncMock(
+        side_effect=AssertionError("rewritten command leaked to the agent")
+    )
+
+    call_log = []
+
+    async def _emit_collect(event_type, ctx):
+        call_log.append(event_type)
+        if event_type == "command:status":
+            return [
+                {
+                    "decision": "rewrite",
+                    "command_name": "metricas",
+                    "raw_args": "dias:7",
+                }
+            ]
+        return []
+
+    runner.hooks.emit_collect = AsyncMock(side_effect=_emit_collect)
+
+    monkeypatch.setattr(
+        gateway_run, "_resolve_runtime_agent_kwargs", lambda: {"api_key": "***"}
+    )
+    from hermes_cli import plugins as _plugins_mod
+
+    monkeypatch.setattr(
+        _plugins_mod,
+        "get_plugin_commands",
+        lambda: {"metricas": {"description": "Metrics", "args_hint": "dias:7"}},
+    )
+    monkeypatch.setattr(
+        _plugins_mod,
+        "get_plugin_command_handler",
+        lambda name: (lambda args: f"metrics {args}") if name == "metricas" else None,
+    )
+
+    result = await runner._handle_message(_make_event("/status"))
+
+    assert result == "metrics dias:7"
+    # First emit_collect fires on the original command; after rewrite the
+    # dispatcher does NOT re-fire for the new command (one decision per turn).
+    assert call_log == ["command:status"]

tests/hermes_cli/test_api_key_providers.py

@@ -15,6 +15,8 @@ from hermes_cli.auth import (
     get_auth_status,
     AuthError,
     KIMI_CODE_BASE_URL,
+    STEPFUN_STEP_PLAN_INTL_BASE_URL,
+    STEPFUN_STEP_PLAN_CN_BASE_URL,
     _resolve_kimi_base_url,
 )
 from hermes_cli.copilot_auth import _try_gh_cli_token
@@ -35,6 +37,7 @@ class TestProviderRegistry:
         ("xai", "xAI", "api_key"),
         ("nvidia", "NVIDIA NIM", "api_key"),
         ("kimi-coding", "Kimi / Moonshot", "api_key"),
+        ("stepfun", "StepFun Step Plan", "api_key"),
         ("minimax", "MiniMax", "api_key"),
         ("minimax-cn", "MiniMax (China)", "api_key"),
         ("ai-gateway", "Vercel AI Gateway", "api_key"),
@@ -83,6 +86,11 @@ class TestProviderRegistry:
         assert pconfig.api_key_env_vars == ("MINIMAX_API_KEY",)
         assert pconfig.base_url_env_var == "MINIMAX_BASE_URL"
 
+    def test_stepfun_env_vars(self):
+        pconfig = PROVIDER_REGISTRY["stepfun"]
+        assert pconfig.api_key_env_vars == ("STEPFUN_API_KEY",)
+        assert pconfig.base_url_env_var == "STEPFUN_BASE_URL"
+
     def test_minimax_cn_env_vars(self):
         pconfig = PROVIDER_REGISTRY["minimax-cn"]
         assert pconfig.api_key_env_vars == ("MINIMAX_CN_API_KEY",)
@@ -108,6 +116,7 @@ class TestProviderRegistry:
         assert PROVIDER_REGISTRY["copilot-acp"].inference_base_url == "acp://copilot"
         assert PROVIDER_REGISTRY["zai"].inference_base_url == "https://api.z.ai/api/paas/v4"
         assert PROVIDER_REGISTRY["kimi-coding"].inference_base_url == "https://api.moonshot.ai/v1"
+        assert PROVIDER_REGISTRY["stepfun"].inference_base_url == STEPFUN_STEP_PLAN_INTL_BASE_URL
         assert PROVIDER_REGISTRY["minimax"].inference_base_url == "https://api.minimax.io/anthropic"
         assert PROVIDER_REGISTRY["minimax-cn"].inference_base_url == "https://api.minimaxi.com/anthropic"
         assert PROVIDER_REGISTRY["ai-gateway"].inference_base_url == "https://ai-gateway.vercel.sh/v1"
@@ -130,7 +139,8 @@ PROVIDER_ENV_VARS = (
     "OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
     "CLAUDE_CODE_OAUTH_TOKEN",
     "GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY",
-    "KIMI_API_KEY", "KIMI_BASE_URL", "MINIMAX_API_KEY", "MINIMAX_CN_API_KEY",
+    "KIMI_API_KEY", "KIMI_BASE_URL", "STEPFUN_API_KEY", "STEPFUN_BASE_URL",
+    "MINIMAX_API_KEY", "MINIMAX_CN_API_KEY",
     "AI_GATEWAY_API_KEY", "AI_GATEWAY_BASE_URL",
     "KILOCODE_API_KEY", "KILOCODE_BASE_URL",
     "DASHSCOPE_API_KEY", "OPENCODE_ZEN_API_KEY", "OPENCODE_GO_API_KEY",
@@ -156,6 +166,9 @@ class TestResolveProvider:
     def test_explicit_kimi_coding(self):
         assert resolve_provider("kimi-coding") == "kimi-coding"
 
+    def test_explicit_stepfun(self):
+        assert resolve_provider("stepfun") == "stepfun"
+
     def test_explicit_minimax(self):
         assert resolve_provider("minimax") == "minimax"
 
@@ -180,6 +193,9 @@ class TestResolveProvider:
     def test_alias_moonshot(self):
         assert resolve_provider("moonshot") == "kimi-coding"
 
+    def test_alias_step(self):
+        assert resolve_provider("step") == "stepfun"
+
     def test_alias_minimax_underscore(self):
         assert resolve_provider("minimax_cn") == "minimax-cn"
 
@@ -248,6 +264,10 @@ class TestResolveProvider:
         monkeypatch.setenv("KIMI_API_KEY", "test-kimi-key")
         assert resolve_provider("auto") == "kimi-coding"
 
+    def test_auto_detects_stepfun_key(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "test-stepfun-key")
+        assert resolve_provider("auto") == "stepfun"
+
     def test_auto_detects_minimax_key(self, monkeypatch):
         monkeypatch.setenv("MINIMAX_API_KEY", "test-mm-key")
         assert resolve_provider("auto") == "minimax"
@@ -312,6 +332,13 @@ class TestApiKeyProviderStatus:
         status = get_api_key_provider_status("kimi-coding")
         assert status["base_url"] == "https://custom.kimi.example/v1"
 
+    def test_stepfun_status_uses_configured_base_url(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-key")
+        monkeypatch.setenv("STEPFUN_BASE_URL", STEPFUN_STEP_PLAN_CN_BASE_URL)
+        status = get_api_key_provider_status("stepfun")
+        assert status["configured"] is True
+        assert status["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
+
     def test_copilot_status_uses_gh_cli_token(self, monkeypatch):
         monkeypatch.setattr("hermes_cli.copilot_auth._try_gh_cli_token", lambda: "gho_gh_cli_token")
         status = get_api_key_provider_status("copilot")
@@ -429,6 +456,19 @@ class TestResolveApiKeyProviderCredentials:
         assert creds["api_key"] == "kimi-secret-key"
         assert creds["base_url"] == "https://api.moonshot.ai/v1"
 
+    def test_resolve_stepfun_with_key(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-secret-key")
+        creds = resolve_api_key_provider_credentials("stepfun")
+        assert creds["provider"] == "stepfun"
+        assert creds["api_key"] == "stepfun-secret-key"
+        assert creds["base_url"] == STEPFUN_STEP_PLAN_INTL_BASE_URL
+
+    def test_resolve_stepfun_custom_base_url(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-secret-key")
+        monkeypatch.setenv("STEPFUN_BASE_URL", STEPFUN_STEP_PLAN_CN_BASE_URL)
+        creds = resolve_api_key_provider_credentials("stepfun")
+        assert creds["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
+
     def test_resolve_minimax_with_key(self, monkeypatch):
         monkeypatch.setenv("MINIMAX_API_KEY", "mm-secret-key")
         creds = resolve_api_key_provider_credentials("minimax")
@@ -519,6 +559,16 @@ class TestRuntimeProviderResolution:
         assert result["api_mode"] == "chat_completions"
         assert result["api_key"] == "kimi-key"
 
+    def test_runtime_stepfun(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-key")
+        monkeypatch.setenv("STEPFUN_BASE_URL", STEPFUN_STEP_PLAN_CN_BASE_URL)
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+        result = resolve_runtime_provider(requested="stepfun")
+        assert result["provider"] == "stepfun"
+        assert result["api_mode"] == "chat_completions"
+        assert result["api_key"] == "stepfun-key"
+        assert result["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
+
     def test_runtime_minimax(self, monkeypatch):
         monkeypatch.setenv("MINIMAX_API_KEY", "mm-key")
         from hermes_cli.runtime_provider import resolve_runtime_provider

tests/hermes_cli/test_commands.py

@@ -1208,3 +1208,119 @@ class TestDiscordSkillCommandsByCategory:
         assert "axolotl" in names
         assert "vllm" in names
         assert len(uncategorized) == 0
+
+
+# ---------------------------------------------------------------------------
+# Plugin slash command integration
+# ---------------------------------------------------------------------------
+
+class TestPluginCommandEnumeration:
+    """Plugin commands registered via ctx.register_command() must be surfaced
+    by every gateway enumerator (Telegram menu, Slack subcommand map, etc.).
+    """
+
+    def _patch_plugin_commands(self, monkeypatch, commands):
+        """Monkeypatch hermes_cli.plugins.get_plugin_commands() to a fixed dict."""
+        from hermes_cli import plugins as _plugins_mod
+
+        monkeypatch.setattr(
+            _plugins_mod, "get_plugin_commands", lambda: dict(commands)
+        )
+
+    def test_plugin_command_appears_in_telegram_menu(self, monkeypatch):
+        """/metricas registered by a plugin must appear in Telegram BotCommand menu."""
+        self._patch_plugin_commands(monkeypatch, {
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics dashboard",
+                "args_hint": "dias:7",
+                "plugin": "metrics-plugin",
+            }
+        })
+        names = {name for name, _desc in telegram_bot_commands()}
+        assert "metricas" in names
+
+    def test_plugin_command_appears_in_slack_subcommand_map(self, monkeypatch):
+        """/hermes metricas must route through the Slack subcommand map."""
+        self._patch_plugin_commands(monkeypatch, {
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics",
+                "args_hint": "",
+                "plugin": "metrics-plugin",
+            }
+        })
+        mapping = slack_subcommand_map()
+        assert mapping.get("metricas") == "/metricas"
+
+    def test_plugin_command_does_not_shadow_builtin_in_slack(self, monkeypatch):
+        """If a plugin registers a name that collides with a built-in, the built-in mapping wins."""
+        self._patch_plugin_commands(monkeypatch, {
+            "status": {
+                "handler": lambda _a: "plugin-status",
+                "description": "Plugin status",
+                "args_hint": "",
+                "plugin": "shadow-plugin",
+            }
+        })
+        mapping = slack_subcommand_map()
+        # Built-in /status must still be present and not overwritten.
+        assert mapping.get("status") == "/status"
+
+    def test_plugin_command_with_hyphens_sanitized_for_telegram(self, monkeypatch):
+        """Plugin names containing hyphens must be underscore-normalized for Telegram."""
+        self._patch_plugin_commands(monkeypatch, {
+            "my-plugin-cmd": {
+                "handler": lambda _a: "ok",
+                "description": "desc",
+                "args_hint": "",
+                "plugin": "p",
+            }
+        })
+        names = {name for name, _desc in telegram_bot_commands()}
+        assert "my_plugin_cmd" in names
+        assert "my-plugin-cmd" not in names
+
+    def test_is_gateway_known_command_recognizes_plugin_commands(self, monkeypatch):
+        """is_gateway_known_command() must return True for plugin commands."""
+        from hermes_cli.commands import is_gateway_known_command
+
+        self._patch_plugin_commands(monkeypatch, {
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics",
+                "args_hint": "",
+                "plugin": "p",
+            }
+        })
+        assert is_gateway_known_command("metricas") is True
+        assert is_gateway_known_command("definitely-not-registered") is False
+
+    def test_is_gateway_known_command_still_recognizes_builtins(self, monkeypatch):
+        """Built-in commands must remain known even when plugin discovery fails."""
+        from hermes_cli import plugins as _plugins_mod
+        from hermes_cli.commands import is_gateway_known_command
+
+        def _boom():
+            raise RuntimeError("plugin system down")
+
+        monkeypatch.setattr(_plugins_mod, "get_plugin_commands", _boom)
+
+        assert is_gateway_known_command("status") is True
+        assert is_gateway_known_command(None) is False
+        assert is_gateway_known_command("") is False
+
+    def test_plugin_enumerator_handles_missing_plugin_manager(self, monkeypatch):
+        """Enumerators must never raise when plugin discovery raises."""
+        from hermes_cli import plugins as _plugins_mod
+
+        def _boom():
+            raise RuntimeError("plugin system down")
+
+        monkeypatch.setattr(_plugins_mod, "get_plugin_commands", _boom)
+
+        # Both calls should succeed and just return the built-in set.
+        tg_names = {name for name, _desc in telegram_bot_commands()}
+        slack_names = set(slack_subcommand_map())
+        assert "status" in tg_names
+        assert "status" in slack_names

tests/hermes_cli/test_debug.py

@@ -137,50 +137,105 @@ class TestUploadToPastebin:
 # Log reading
 # ---------------------------------------------------------------------------
 
-class TestReadFullLog:
-    """Test _read_full_log for standalone log uploads."""
+class TestCaptureLogSnapshot:
+    """Test _capture_log_snapshot for log reading and truncation."""
 
     def test_reads_small_file(self, hermes_home):
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
-        content = _read_full_log("agent")
-        assert content is not None
-        assert "session started" in content
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is not None
+        assert "session started" in snap.full_text
+        assert "session started" in snap.tail_text
 
     def test_returns_none_for_missing(self, tmp_path, monkeypatch):
         home = tmp_path / ".hermes"
         home.mkdir()
         monkeypatch.setenv("HERMES_HOME", str(home))
 
-        from hermes_cli.debug import _read_full_log
-        assert _read_full_log("agent") is None
+        from hermes_cli.debug import _capture_log_snapshot
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is None
+        assert snap.tail_text == "(file not found)"
 
-    def test_returns_none_for_empty(self, hermes_home):
-        # Truncate agent.log to empty
+    def test_empty_primary_reports_file_empty(self, hermes_home):
+        """Empty primary (no .1 fallback) surfaces as '(file empty)', not missing."""
         (hermes_home / "logs" / "agent.log").write_text("")
 
-        from hermes_cli.debug import _read_full_log
-        assert _read_full_log("agent") is None
+        from hermes_cli.debug import _capture_log_snapshot
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is None
+        assert snap.tail_text == "(file empty)"
+
+    def test_race_truncate_after_resolve_reports_empty(self, hermes_home, monkeypatch):
+        """If the log is truncated between resolve and stat, say 'empty', not 'missing'."""
+        log_path = hermes_home / "logs" / "agent.log"
+        from hermes_cli import debug
+
+        monkeypatch.setattr(debug, "_resolve_log_path", lambda _name: log_path)
+        log_path.write_text("")
+
+        snap = debug._capture_log_snapshot("agent", tail_lines=10)
+        assert snap.path == log_path
+        assert snap.full_text is None
+        assert snap.tail_text == "(file empty)"
 
     def test_truncates_large_file(self, hermes_home):
         """Files larger than max_bytes get tail-truncated."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         # Write a file larger than 1KB
         big_content = "x" * 100 + "\n"
         (hermes_home / "logs" / "agent.log").write_text(big_content * 200)
 
-        content = _read_full_log("agent", max_bytes=1024)
-        assert content is not None
-        assert "truncated" in content
+        snap = _capture_log_snapshot("agent", tail_lines=10, max_bytes=1024)
+        assert snap.full_text is not None
+        assert "truncated" in snap.full_text
+
+    def test_keeps_first_line_when_truncation_on_boundary(self, hermes_home):
+        """When truncation lands on a line boundary, keep the first full line."""
+        from hermes_cli.debug import _capture_log_snapshot
+
+        # File must exceed the initial chunk_size (8192) used by the
+        # backward-reading loop so the truncation path actually fires.
+        line = "A" * 99 + "\n"  # 100 bytes per line
+        num_lines = 200  # 20000 bytes
+        (hermes_home / "logs" / "agent.log").write_text(line * num_lines)
+
+        # max_bytes = 1000 = 100 * 10 → cut at byte 20000 - 1000 = 19000,
+        # and byte 19000 - 1 is '\n'.  Boundary hit → keep all 10 lines.
+        snap = _capture_log_snapshot("agent", tail_lines=5, max_bytes=1000)
+        assert snap.full_text is not None
+        assert "truncated" in snap.full_text
+        raw = snap.full_text.split("\n", 1)[1]
+        kept = [l for l in raw.strip().splitlines() if l.startswith("A")]
+        assert len(kept) == 10
+
+    def test_drops_partial_when_truncation_mid_line(self, hermes_home):
+        """When truncation lands mid-line, drop the partial fragment."""
+        from hermes_cli.debug import _capture_log_snapshot
+
+        line = "A" * 99 + "\n"  # 100 bytes per line
+        num_lines = 200  # 20000 bytes
+        (hermes_home / "logs" / "agent.log").write_text(line * num_lines)
+
+        # max_bytes = 950 doesn't divide evenly into 100 → mid-line cut.
+        snap = _capture_log_snapshot("agent", tail_lines=5, max_bytes=950)
+        assert snap.full_text is not None
+        assert "truncated" in snap.full_text
+        raw = snap.full_text.split("\n", 1)[1]
+        kept = [l for l in raw.strip().splitlines() if l.startswith("A")]
+        # 950 / 100 = 9.5 → 9 complete lines after dropping partial
+        assert len(kept) == 9
 
     def test_unknown_log_returns_none(self, hermes_home):
-        from hermes_cli.debug import _read_full_log
-        assert _read_full_log("nonexistent") is None
+        from hermes_cli.debug import _capture_log_snapshot
+        snap = _capture_log_snapshot("nonexistent", tail_lines=10)
+        assert snap.full_text is None
 
     def test_falls_back_to_rotated_file(self, hermes_home):
         """When gateway.log doesn't exist, falls back to gateway.log.1."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         logs_dir = hermes_home / "logs"
         # Remove the primary (if any) and create a .1 rotation
@@ -189,33 +244,33 @@ class TestReadFullLog:
             "2026-04-12 10:00:00 INFO gateway.run: rotated content\n"
         )
 
-        content = _read_full_log("gateway")
-        assert content is not None
-        assert "rotated content" in content
+        snap = _capture_log_snapshot("gateway", tail_lines=10)
+        assert snap.full_text is not None
+        assert "rotated content" in snap.full_text
 
     def test_prefers_primary_over_rotated(self, hermes_home):
         """Primary log is used when it exists, even if .1 also exists."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         logs_dir = hermes_home / "logs"
         (logs_dir / "gateway.log").write_text("primary content\n")
         (logs_dir / "gateway.log.1").write_text("rotated content\n")
 
-        content = _read_full_log("gateway")
-        assert "primary content" in content
-        assert "rotated" not in content
+        snap = _capture_log_snapshot("gateway", tail_lines=10)
+        assert "primary content" in snap.full_text
+        assert "rotated" not in snap.full_text
 
     def test_falls_back_when_primary_empty(self, hermes_home):
         """Empty primary log falls back to .1 rotation."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         logs_dir = hermes_home / "logs"
         (logs_dir / "agent.log").write_text("")
         (logs_dir / "agent.log.1").write_text("rotated agent data\n")
 
-        content = _read_full_log("agent")
-        assert content is not None
-        assert "rotated agent data" in content
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is not None
+        assert "rotated agent data" in snap.full_text
 
 
 # ---------------------------------------------------------------------------
@@ -283,6 +338,44 @@ class TestCollectDebugReport:
 class TestRunDebugShare:
     """Test the run_debug_share CLI handler."""
 
+    def test_share_sweeps_expired_pastes(self, hermes_home, capsys):
+        """Slash-command path should sweep old pending deletes before uploading."""
+        from hermes_cli.debug import run_debug_share
+
+        args = MagicMock()
+        args.lines = 50
+        args.expire = 7
+        args.local = False
+
+        with patch("hermes_cli.dump.run_dump"), \
+             patch("hermes_cli.debug._sweep_expired_pastes", return_value=(0, 0)) as mock_sweep, \
+             patch("hermes_cli.debug.upload_to_pastebin",
+                    return_value="https://paste.rs/test"):
+            run_debug_share(args)
+
+        mock_sweep.assert_called_once()
+        assert "Debug report uploaded" in capsys.readouterr().out
+
+    def test_share_survives_sweep_failure(self, hermes_home, capsys):
+        """Expired-paste cleanup is best-effort and must not block sharing."""
+        from hermes_cli.debug import run_debug_share
+
+        args = MagicMock()
+        args.lines = 50
+        args.expire = 7
+        args.local = False
+
+        with patch("hermes_cli.dump.run_dump"), \
+             patch(
+                 "hermes_cli.debug._sweep_expired_pastes",
+                 side_effect=RuntimeError("offline"),
+             ), \
+             patch("hermes_cli.debug.upload_to_pastebin",
+                    return_value="https://paste.rs/test"):
+            run_debug_share(args)
+
+        assert "https://paste.rs/test" in capsys.readouterr().out
+
     def test_local_flag_prints_full_logs(self, hermes_home, capsys):
         """--local prints the report plus full log contents."""
         from hermes_cli.debug import run_debug_share
@@ -340,6 +433,55 @@ class TestRunDebugShare:
         assert "--- hermes dump ---" in gateway_paste
         assert "--- full gateway.log ---" in gateway_paste
 
+    def test_share_keeps_report_and_full_log_on_same_snapshot(self, hermes_home, capsys):
+        """A mid-run rotation must not make full agent.log older than the report."""
+        from hermes_cli.debug import run_debug_share, collect_debug_report as real_collect_debug_report
+
+        logs_dir = hermes_home / "logs"
+        (logs_dir / "agent.log").write_text(
+            "2026-04-22 12:00:00 INFO agent: newest line\n"
+        )
+        (logs_dir / "agent.log.1").write_text(
+            "2026-04-10 12:00:00 INFO agent: old rotated line\n"
+        )
+
+        args = MagicMock()
+        args.lines = 50
+        args.expire = 7
+        args.local = False
+
+        uploaded_content = []
+
+        def _mock_upload(content, expiry_days=7):
+            uploaded_content.append(content)
+            return f"https://paste.rs/paste{len(uploaded_content)}"
+
+        def _wrapped_collect_debug_report(*, log_lines=200, dump_text="", log_snapshots=None):
+            report = real_collect_debug_report(
+                log_lines=log_lines,
+                dump_text=dump_text,
+                log_snapshots=log_snapshots,
+            )
+            # Simulate the live log rotating after the report is built but
+            # before the old implementation would have re-read agent.log for
+            # standalone upload.
+            (logs_dir / "agent.log").write_text("")
+            (logs_dir / "agent.log.1").write_text(
+                "2026-04-10 12:00:00 INFO agent: old rotated line\n"
+            )
+            return report
+
+        with patch("hermes_cli.dump.run_dump"), \
+             patch("hermes_cli.debug.collect_debug_report", side_effect=_wrapped_collect_debug_report), \
+             patch("hermes_cli.debug.upload_to_pastebin", side_effect=_mock_upload):
+            run_debug_share(args)
+
+        report_paste = uploaded_content[0]
+        agent_paste = uploaded_content[1]
+        assert "2026-04-22 12:00:00 INFO agent: newest line" in report_paste
+        assert "2026-04-22 12:00:00 INFO agent: newest line" in agent_paste
+        assert "old rotated line" not in agent_paste
+
     def test_share_skips_missing_logs(self, tmp_path, monkeypatch, capsys):
         """Only uploads logs that exist."""
         home = tmp_path / ".hermes"

tests/hermes_cli/test_env_loader.py

@@ -33,6 +33,25 @@ def test_project_env_overrides_stale_shell_values_when_user_env_missing(tmp_path
     assert os.getenv("OPENAI_BASE_URL") == "https://project.example/v1"
 
 
+def test_project_env_is_sanitized_before_loading(tmp_path, monkeypatch):
+    home = tmp_path / "hermes"
+    project_env = tmp_path / ".env"
+    project_env.write_text(
+        "TELEGRAM_BOT_TOKEN=8356550917:AAGGEkzg06Hrc3Hjb3Sa1jkGVDOdU_lYy2Q"
+        "ANTHROPIC_API_KEY=sk-ant-test123\n",
+        encoding="utf-8",
+    )
+
+    monkeypatch.delenv("TELEGRAM_BOT_TOKEN", raising=False)
+    monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)
+
+    loaded = load_hermes_dotenv(hermes_home=home, project_env=project_env)
+
+    assert loaded == [project_env]
+    assert os.getenv("TELEGRAM_BOT_TOKEN") == "8356550917:AAGGEkzg06Hrc3Hjb3Sa1jkGVDOdU_lYy2Q"
+    assert os.getenv("ANTHROPIC_API_KEY") == "sk-ant-test123"
+
+
 def test_user_env_takes_precedence_over_project_env(tmp_path, monkeypatch):
     home = tmp_path / "hermes"
     home.mkdir()

tests/hermes_cli/test_gateway.py

@@ -121,6 +121,12 @@ def test_systemd_status_warns_when_linger_disabled(monkeypatch, tmp_path, capsys
             return SimpleNamespace(returncode=0, stdout="", stderr="")
         if cmd[:3] == ["systemctl", "--user", "is-active"]:
             return SimpleNamespace(returncode=0, stdout="active\n", stderr="")
+        if cmd[:3] == ["systemctl", "--user", "show"]:
+            return SimpleNamespace(
+                returncode=0,
+                stdout="ActiveState=active\nSubState=running\nResult=success\nExecMainStatus=0\n",
+                stderr="",
+            )
         raise AssertionError(f"Unexpected command: {cmd}")
 
     monkeypatch.setattr(gateway.subprocess, "run", fake_run)
@@ -352,3 +358,24 @@ class TestWaitForGatewayExit:
 
         assert killed == 2
         assert calls == [(11, True), (22, True)]
+
+
+class TestStopProfileGateway:
+    def test_stop_profile_gateway_keeps_pid_file_when_process_still_running(self, monkeypatch):
+        calls = {"kill": 0, "remove": 0}
+
+        monkeypatch.setattr("gateway.status.get_running_pid", lambda: 12345)
+        monkeypatch.setattr(
+            gateway.os,
+            "kill",
+            lambda pid, sig: calls.__setitem__("kill", calls["kill"] + 1),
+        )
+        monkeypatch.setattr("time.sleep", lambda _: None)
+        monkeypatch.setattr(
+            "gateway.status.remove_pid_file",
+            lambda: calls.__setitem__("remove", calls["remove"] + 1),
+        )
+
+        assert gateway.stop_profile_gateway() is True
+        assert calls["kill"] == 21
+        assert calls["remove"] == 0

tests/hermes_cli/test_gateway_service.py

@@ -77,8 +77,10 @@ class TestSystemdServiceRefresh:
         gateway_cli.systemd_restart()
 
         assert unit_path.read_text(encoding="utf-8") == "new unit\n"
-        assert calls[:2] == [
+        assert calls[:4] == [
             ["systemctl", "--user", "daemon-reload"],
+            ["systemctl", "--user", "show", gateway_cli.get_service_name(), "--no-pager", "--property", "ActiveState,SubState,Result,ExecMainStatus"],
+            ["systemctl", "--user", "reset-failed", gateway_cli.get_service_name()],
             ["systemctl", "--user", "reload-or-restart", gateway_cli.get_service_name()],
         ]
 
@@ -474,13 +476,21 @@ class TestGatewaySystemServiceRouting:
                 raise ProcessLookupError()
         monkeypatch.setattr(os, "kill", fake_kill)
 
-        # Simulate systemctl is-active returning "active" with a new PID
+        # Simulate systemctl reset-failed/start followed by an active unit
         new_pid = [None]
         def fake_subprocess_run(cmd, **kwargs):
-            if "is-active" in cmd:
-                result = SimpleNamespace(stdout="active\n", returncode=0)
-                new_pid[0] = 999  # new PID
-                return result
+            if "reset-failed" in cmd:
+                calls.append(("reset-failed", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            if "start" in cmd:
+                calls.append(("start", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            if "show" in cmd:
+                new_pid[0] = 999
+                return SimpleNamespace(
+                    stdout="ActiveState=active\nSubState=running\nResult=success\nExecMainStatus=0\n",
+                    returncode=0,
+                )
             raise AssertionError(f"Unexpected systemctl call: {cmd}")
 
         monkeypatch.setattr(gateway_cli.subprocess, "run", fake_subprocess_run)
@@ -494,9 +504,131 @@ class TestGatewaySystemServiceRouting:
         gateway_cli.systemd_restart()
 
         assert ("self", 654) in calls
+        assert any(call[0] == "reset-failed" for call in calls)
+        assert any(call[0] == "start" for call in calls)
         out = capsys.readouterr().out.lower()
         assert "restarted" in out
 
+    def test_systemd_restart_recovers_failed_planned_restart(self, monkeypatch, capsys):
+        monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        monkeypatch.setattr(gateway_cli, "refresh_systemd_unit_if_needed", lambda system=False: None)
+        monkeypatch.setattr(
+            "gateway.status.read_runtime_status",
+            lambda: {"restart_requested": True, "gateway_state": "stopped"},
+        )
+        monkeypatch.setattr(gateway_cli, "_request_gateway_self_restart", lambda pid: False)
+
+        calls = []
+        started = {"value": False}
+
+        def fake_subprocess_run(cmd, **kwargs):
+            if "show" in cmd:
+                if not started["value"]:
+                    return SimpleNamespace(
+                        stdout=(
+                            "ActiveState=failed\n"
+                            "SubState=failed\n"
+                            "Result=exit-code\n"
+                            f"ExecMainStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}\n"
+                        ),
+                        returncode=0,
+                    )
+                return SimpleNamespace(
+                    stdout="ActiveState=active\nSubState=running\nResult=success\nExecMainStatus=0\n",
+                    returncode=0,
+                )
+            if "reset-failed" in cmd:
+                calls.append(("reset-failed", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            if "start" in cmd:
+                started["value"] = True
+                calls.append(("start", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            raise AssertionError(f"Unexpected command: {cmd}")
+
+        monkeypatch.setattr(gateway_cli.subprocess, "run", fake_subprocess_run)
+        monkeypatch.setattr(
+            "gateway.status.get_running_pid",
+            lambda: 999 if started["value"] else None,
+        )
+
+        gateway_cli.systemd_restart()
+
+        assert any(call[0] == "reset-failed" for call in calls)
+        assert any(call[0] == "start" for call in calls)
+        out = capsys.readouterr().out.lower()
+        assert "restarted" in out
+
+    def test_systemd_status_surfaces_planned_restart_failure(self, monkeypatch, capsys):
+        unit = SimpleNamespace(exists=lambda: True)
+        monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit)
+        monkeypatch.setattr(gateway_cli, "has_conflicting_systemd_units", lambda: False)
+        monkeypatch.setattr(gateway_cli, "has_legacy_hermes_units", lambda: False)
+        monkeypatch.setattr(gateway_cli, "systemd_unit_is_current", lambda system=False: True)
+        monkeypatch.setattr(gateway_cli, "_runtime_health_lines", lambda: ["⚠ Last shutdown reason: Gateway restart requested"])
+        monkeypatch.setattr(gateway_cli, "get_systemd_linger_status", lambda: (True, ""))
+        monkeypatch.setattr(gateway_cli, "_read_systemd_unit_properties", lambda system=False: {
+            "ActiveState": "failed",
+            "SubState": "failed",
+            "Result": "exit-code",
+            "ExecMainStatus": str(GATEWAY_SERVICE_RESTART_EXIT_CODE),
+        })
+
+        calls = []
+
+        def fake_run_systemctl(args, **kwargs):
+            calls.append(args)
+            if args[:2] == ["status", gateway_cli.get_service_name()]:
+                return SimpleNamespace(returncode=0, stdout="", stderr="")
+            if args[:2] == ["is-active", gateway_cli.get_service_name()]:
+                return SimpleNamespace(returncode=3, stdout="failed\n", stderr="")
+            raise AssertionError(f"Unexpected args: {args}")
+
+        monkeypatch.setattr(gateway_cli, "_run_systemctl", fake_run_systemctl)
+
+        gateway_cli.systemd_status()
+
+        out = capsys.readouterr().out
+        assert "Planned restart is stuck in systemd failed state" in out
+
+    def test_gateway_status_dispatches_full_flag(self, monkeypatch):
+        user_unit = SimpleNamespace(exists=lambda: True)
+        system_unit = SimpleNamespace(exists=lambda: False)
+
+        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
+        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
+        monkeypatch.setattr(
+            gateway_cli,
+            "get_systemd_unit_path",
+            lambda system=False: system_unit if system else user_unit,
+        )
+        monkeypatch.setattr(
+            gateway_cli,
+            "get_gateway_runtime_snapshot",
+            lambda system=False: gateway_cli.GatewayRuntimeSnapshot(
+                manager="systemd (user)",
+                service_installed=True,
+                service_running=False,
+                gateway_pids=(),
+                service_scope="user",
+            ),
+        )
+
+        calls = []
+        monkeypatch.setattr(
+            gateway_cli,
+            "systemd_status",
+            lambda deep=False, system=False, full=False: calls.append((deep, system, full)),
+        )
+
+        gateway_cli.gateway_command(
+            SimpleNamespace(gateway_command="status", deep=False, system=False, full=True)
+        )
+
+        assert calls == [(False, False, True)]
+
     def test_gateway_install_passes_system_flags(self, monkeypatch):
         monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
@@ -547,11 +679,15 @@ class TestGatewaySystemServiceRouting:
         )
 
         calls = []
-        monkeypatch.setattr(gateway_cli, "systemd_status", lambda deep=False, system=False: calls.append((deep, system)))
+        monkeypatch.setattr(
+            gateway_cli,
+            "systemd_status",
+            lambda deep=False, system=False, full=False: calls.append((deep, system, full)),
+        )
 
         gateway_cli.gateway_command(SimpleNamespace(gateway_command="status", deep=False, system=False))
 
-        assert calls == [(False, False)]
+        assert calls == [(False, False, False)]
 
     def test_gateway_status_reports_manual_process_when_service_is_stopped(self, monkeypatch, capsys):
         user_unit = SimpleNamespace(exists=lambda: True)
@@ -565,7 +701,11 @@ class TestGatewaySystemServiceRouting:
             "get_systemd_unit_path",
             lambda system=False: system_unit if system else user_unit,
         )
-        monkeypatch.setattr(gateway_cli, "systemd_status", lambda deep=False, system=False: print("service stopped"))
+        monkeypatch.setattr(
+            gateway_cli,
+            "systemd_status",
+            lambda deep=False, system=False, full=False: print("service stopped"),
+        )
         monkeypatch.setattr(
             gateway_cli,
             "get_gateway_runtime_snapshot",
@@ -1570,6 +1710,23 @@ class TestMigrateLegacyCommand:
 
         assert called == {"interactive": False, "dry_run": False}
 
+
+class TestGatewayStatusParser:
+    def test_gateway_status_subparser_accepts_full_flag(self):
+        import subprocess
+        import sys
+
+        result = subprocess.run(
+            [sys.executable, "-m", "hermes_cli.main", "gateway", "status", "-l", "--help"],
+            cwd=str(gateway_cli.PROJECT_ROOT),
+            capture_output=True,
+            text=True,
+            timeout=15,
+        )
+
+        assert result.returncode == 0
+        assert "unrecognized arguments" not in result.stderr
+
     def test_gateway_command_migrate_legacy_dry_run_passes_through(
         self, monkeypatch
     ):

tests/hermes_cli/test_model_provider_persistence.py

@@ -32,6 +32,8 @@ def config_home(tmp_path, monkeypatch):
     monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
     monkeypatch.delenv("OPENAI_API_KEY", raising=False)
     monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
+    monkeypatch.delenv("STEPFUN_API_KEY", raising=False)
+    monkeypatch.delenv("STEPFUN_BASE_URL", raising=False)
     return home
 
 
@@ -330,3 +332,33 @@ class TestBaseUrlValidation:
 
         saved = get_env_value("GLM_BASE_URL") or ""
         assert saved == "", "Empty input should not save a base URL"
+
+    def test_stepfun_provider_saved_with_selected_region(self, config_home, monkeypatch):
+        from hermes_cli.main import _model_flow_stepfun
+        from hermes_cli.config import load_config, get_env_value
+
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-test-key")
+
+        with patch(
+            "hermes_cli.main._prompt_provider_choice",
+            return_value=1,
+        ), patch(
+            "hermes_cli.models.fetch_api_models",
+            return_value=["step-3.5-flash", "step-3-agent-lite"],
+        ), patch(
+            "hermes_cli.auth._prompt_model_selection",
+            return_value="step-3-agent-lite",
+        ), patch(
+            "hermes_cli.auth.deactivate_provider",
+        ):
+            _model_flow_stepfun(load_config(), "old-model")
+
+        import yaml
+
+        config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+        model = config.get("model")
+        assert isinstance(model, dict)
+        assert model.get("provider") == "stepfun"
+        assert model.get("default") == "step-3-agent-lite"
+        assert model.get("base_url") == "https://api.stepfun.com/step_plan/v1"
+        assert get_env_value("STEPFUN_BASE_URL") == "https://api.stepfun.com/step_plan/v1"

tests/hermes_cli/test_model_validation.py

@@ -63,6 +63,11 @@ class TestParseModelInput:
         assert provider == "zai"
         assert model == "glm-5"
 
+    def test_stepfun_alias_resolved(self):
+        provider, model = parse_model_input("step:step-3.5-flash", "openrouter")
+        assert provider == "stepfun"
+        assert model == "step-3.5-flash"
+
     def test_no_slash_no_colon_keeps_provider(self):
         provider, model = parse_model_input("gpt-5.4", "openrouter")
         assert provider == "openrouter"
@@ -154,6 +159,7 @@ class TestNormalizeProvider:
         assert normalize_provider("glm") == "zai"
         assert normalize_provider("kimi") == "kimi-coding"
         assert normalize_provider("moonshot") == "kimi-coding"
+        assert normalize_provider("step") == "stepfun"
         assert normalize_provider("github-copilot") == "copilot"
 
     def test_case_insensitive(self):
@@ -164,6 +170,7 @@ class TestProviderLabel:
     def test_known_labels_and_auto(self):
         assert provider_label("anthropic") == "Anthropic"
         assert provider_label("kimi") == "Kimi / Kimi Coding Plan"
+        assert provider_label("stepfun") == "StepFun Step Plan"
         assert provider_label("copilot") == "GitHub Copilot"
         assert provider_label("copilot-acp") == "GitHub Copilot ACP"
         assert provider_label("auto") == "Auto"
@@ -193,6 +200,16 @@ class TestProviderModelIds:
     def test_zai_returns_glm_models(self):
         assert "glm-5" in provider_model_ids("zai")
 
+    def test_stepfun_prefers_live_catalog(self):
+        with patch(
+            "hermes_cli.auth.resolve_api_key_provider_credentials",
+            return_value={"api_key": "***", "base_url": "https://api.stepfun.com/step_plan/v1"},
+        ), patch(
+            "hermes_cli.models.fetch_api_models",
+            return_value=["step-3.5-flash", "step-3-agent-lite"],
+        ):
+            assert provider_model_ids("stepfun") == ["step-3.5-flash", "step-3-agent-lite"]
+
     def test_copilot_prefers_live_catalog(self):
         with patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={"api_key": "gh-token"}), \
              patch("hermes_cli.models._fetch_github_models", return_value=["gpt-5.4", "claude-sonnet-4.6"]):

tests/hermes_cli/test_models_dev_preferred_merge.py

@@ -0,0 +1,124 @@
+"""Tests for the models.dev-preferred merge behavior in provider_model_ids
+and list_authenticated_providers.
+
+These guard the contract:
+
+  * For providers in ``_MODELS_DEV_PREFERRED`` (opencode-go, opencode-zen,
+    xiaomi, deepseek, smaller inference providers), both the CLI model
+    picker path (``provider_model_ids``) and the gateway ``/model`` picker
+    path (``list_authenticated_providers``) merge fresh models.dev entries
+    on top of the curated static list.
+  * OpenRouter and Nous Portal are NEVER merged — they keep their curated
+    (OpenRouter) or live-Portal (Nous) semantics.
+  * If models.dev is unreachable (offline / CI), the curated list is the
+    fallback — no crash, no empty list.
+
+Merging is what lets new models (e.g. ``mimo-v2.5-pro`` on opencode-go)
+appear in ``/model`` without a Hermes release.
+"""
+
+import os
+from unittest.mock import patch
+
+import pytest
+
+from hermes_cli.models import (
+    _MODELS_DEV_PREFERRED,
+    _merge_with_models_dev,
+    provider_model_ids,
+)
+
+
+class TestMergeHelper:
+    def test_merge_empty_mdev_returns_curated(self):
+        """When models.dev returns nothing, curated list is preserved verbatim."""
+        with patch("agent.models_dev.list_agentic_models", return_value=[]):
+            out = _merge_with_models_dev("opencode-go", ["mimo-v2-pro", "kimi-k2.6"])
+        assert out == ["mimo-v2-pro", "kimi-k2.6"]
+
+    def test_merge_mdev_raises_returns_curated(self):
+        """Offline / broken models.dev must not break the catalog path."""
+        def boom(_provider):
+            raise RuntimeError("network down")
+
+        with patch("agent.models_dev.list_agentic_models", side_effect=boom):
+            out = _merge_with_models_dev("opencode-go", ["mimo-v2-pro"])
+        assert out == ["mimo-v2-pro"]
+
+    def test_merge_mdev_first_then_curated_extras(self):
+        """models.dev entries come first; curated-only entries are appended."""
+        mdev = ["mimo-v2.5-pro", "mimo-v2-pro", "kimi-k2.6"]
+        curated = ["kimi-k2.6", "kimi-k2.5", "mimo-v2-pro"]  # kimi-k2.5 is curated-only
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = _merge_with_models_dev("opencode-go", curated)
+        # models.dev entries first (in order), then curated-only entries
+        assert out == ["mimo-v2.5-pro", "mimo-v2-pro", "kimi-k2.6", "kimi-k2.5"]
+
+    def test_merge_case_insensitive_dedup(self):
+        """Dedup is case-insensitive but preserves the first occurrence's casing."""
+        mdev = ["MiniMax-M2.7"]
+        curated = ["minimax-m2.7", "minimax-m2.5"]
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = _merge_with_models_dev("minimax", curated)
+        # models.dev casing wins since it came first
+        assert out == ["MiniMax-M2.7", "minimax-m2.5"]
+
+
+class TestProviderModelIdsPreferred:
+    def test_opencode_go_is_preferred(self):
+        assert "opencode-go" in _MODELS_DEV_PREFERRED
+
+    def test_opencode_go_includes_fresh_models_dev_entries(self):
+        """provider_model_ids('opencode-go') adds models.dev entries on top."""
+        mdev = ["mimo-v2.5-pro", "mimo-v2.5", "mimo-v2-pro", "kimi-k2.6"]
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = provider_model_ids("opencode-go")
+        # Fresh models must surface (this is exactly the reported bug fix:
+        # mimo-v2.5-pro should be pickable on opencode-go).
+        assert "mimo-v2.5-pro" in out
+        assert "mimo-v2.5" in out
+        # Curated entries are still present.
+        assert "mimo-v2-pro" in out
+        assert "kimi-k2.6" in out
+
+    def test_opencode_go_offline_falls_back_to_curated(self):
+        """Offline models.dev → curated-only list, no crash."""
+        with patch("agent.models_dev.list_agentic_models", return_value=[]):
+            out = provider_model_ids("opencode-go")
+        # Curated floor (see hermes_cli/models.py _PROVIDER_MODELS["opencode-go"])
+        assert "mimo-v2-pro" in out
+        assert "kimi-k2.6" in out
+
+    def test_opencode_zen_includes_fresh_models(self):
+        """opencode-zen follows the same pattern as opencode-go."""
+        assert "opencode-zen" in _MODELS_DEV_PREFERRED
+        mdev = ["claude-opus-4-7", "kimi-k2.6", "glm-5.1"]
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = provider_model_ids("opencode-zen")
+        assert "claude-opus-4-7" in out
+        assert "kimi-k2.6" in out
+
+
+class TestOpenRouterAndNousUnchanged:
+    """Per Teknium: openrouter and nous are NEVER merged with models.dev."""
+
+    def test_openrouter_not_in_preferred_set(self):
+        assert "openrouter" not in _MODELS_DEV_PREFERRED
+
+    def test_nous_not_in_preferred_set(self):
+        assert "nous" not in _MODELS_DEV_PREFERRED
+
+    def test_openrouter_does_not_call_merge(self):
+        """openrouter takes its own live path — merge helper must NOT run."""
+        with patch(
+            "hermes_cli.models._merge_with_models_dev",
+            side_effect=AssertionError("merge should not be called for openrouter"),
+        ):
+            # Even if model_ids() fails for some other reason, we just care
+            # that the merge path isn't invoked.
+            try:
+                provider_model_ids("openrouter")
+            except AssertionError:
+                raise
+            except Exception:
+                pass  # model_ids() may fail in the hermetic test env — that's fine.

tests/hermes_cli/test_opencode_go_in_model_list.py

@@ -6,16 +6,41 @@ from unittest.mock import patch
 from hermes_cli.model_switch import list_authenticated_providers
 
 
+# Minimum set of models that must be present for opencode-go no matter
+# whether the picker sourced its list from curated-only or curated+models.dev.
+# The curated list in hermes_cli/models.py defines the floor; models.dev only
+# ever adds names on top of it via _merge_with_models_dev.
+_OPENCODE_GO_REQUIRED = {
+    "kimi-k2.6",
+    "kimi-k2.5",
+    "glm-5.1",
+    "glm-5",
+    "mimo-v2-pro",
+    "mimo-v2-omni",
+    "minimax-m2.7",
+    "minimax-m2.5",
+}
+
+
 @patch.dict(os.environ, {"OPENCODE_GO_API_KEY": "test-key"}, clear=False)
 def test_opencode_go_appears_when_api_key_set():
     """opencode-go should appear in list_authenticated_providers when OPENCODE_GO_API_KEY is set."""
-    providers = list_authenticated_providers(current_provider="openrouter")
-    
+    providers = list_authenticated_providers(current_provider="openrouter", max_models=50)
+
     # Find opencode-go in results
     opencode_go = next((p for p in providers if p["slug"] == "opencode-go"), None)
-    
+
     assert opencode_go is not None, "opencode-go should appear when OPENCODE_GO_API_KEY is set"
-    assert opencode_go["models"] == ["kimi-k2.6", "kimi-k2.5", "glm-5.1", "glm-5", "mimo-v2-pro", "mimo-v2-omni", "minimax-m2.7", "minimax-m2.5"]
+    # Behavior check: the curated floor must be present. The list may also
+    # include extra models.dev entries (e.g. mimo-v2.5-pro) when the registry
+    # is reachable — that's the whole point of the models.dev-preferred merge
+    # introduced for opencode-go, so don't pin to an exact list here.
+    present = set(opencode_go["models"])
+    missing = _OPENCODE_GO_REQUIRED - present
+    assert not missing, (
+        f"opencode-go picker should include the curated floor; missing: {sorted(missing)}. "
+        f"Got: {opencode_go['models']}"
+    )
     # opencode-go can appear as "built-in" (from PROVIDER_TO_MODELS_DEV when
     # models.dev is reachable) or "hermes" (from HERMES_OVERLAYS fallback when
     # the API is unavailable, e.g. in CI).
@@ -26,10 +51,10 @@ def test_opencode_go_not_appears_when_no_creds():
     """opencode-go should NOT appear when no credentials are set."""
     # Ensure OPENCODE_GO_API_KEY is not set
     env_without_key = {k: v for k, v in os.environ.items() if k != "OPENCODE_GO_API_KEY"}
-    
+
     with patch.dict(os.environ, env_without_key, clear=True):
         providers = list_authenticated_providers(current_provider="openrouter")
-        
+
         # opencode-go should not be in results
         opencode_go = next((p for p in providers if p["slug"] == "opencode-go"), None)
         assert opencode_go is None, "opencode-go should not appear without credentials"

tests/hermes_cli/test_plugins.py

@@ -250,6 +250,73 @@ class TestPluginLoading:
 
         assert "hermes_plugins.ns_plugin" in sys.modules
 
+    def test_user_memory_plugin_auto_coerced_to_exclusive(self, tmp_path, monkeypatch):
+        """User-installed memory plugins must NOT be loaded by the general
+        PluginManager — they belong to plugins/memory discovery.
+
+        Regression test for the mempalace crash:
+            'PluginContext' object has no attribute 'register_memory_provider'
+
+        A plugin that calls ``ctx.register_memory_provider`` in its
+        ``__init__.py`` should be auto-detected and treated as
+        ``kind: exclusive`` so the general loader records the manifest but
+        does not import/register() it. The real activation happens through
+        ``plugins/memory/__init__.py`` via ``memory.provider`` config.
+        """
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        plugin_dir = plugins_dir / "mempalace"
+        plugin_dir.mkdir(parents=True)
+        # No explicit `kind:` — the heuristic should kick in.
+        (plugin_dir / "plugin.yaml").write_text(yaml.dump({"name": "mempalace"}))
+        (plugin_dir / "__init__.py").write_text(
+            "class MemPalaceProvider:\n"
+            "    pass\n"
+            "def register(ctx):\n"
+            "    ctx.register_memory_provider('mempalace', MemPalaceProvider)\n"
+        )
+        # Even if the user explicitly enables it in config, the loader
+        # should still treat it as exclusive and skip general loading.
+        hermes_home = tmp_path / "hermes_test"
+        (hermes_home / "config.yaml").write_text(
+            yaml.safe_dump({"plugins": {"enabled": ["mempalace"]}})
+        )
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "mempalace" in mgr._plugins
+        entry = mgr._plugins["mempalace"]
+        assert entry.manifest.kind == "exclusive", (
+            f"Expected auto-coerced kind='exclusive', got {entry.manifest.kind}"
+        )
+        # Not loaded by general manager (no register() call, no AttributeError).
+        assert not entry.enabled
+        assert entry.module is None
+        assert "exclusive" in (entry.error or "").lower()
+
+    def test_explicit_standalone_kind_not_coerced(self, tmp_path, monkeypatch):
+        """If a plugin explicitly declares ``kind: standalone`` in its
+        manifest, the memory-provider heuristic must NOT override it —
+        even if the source happens to mention ``MemoryProvider``.
+        """
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        plugin_dir = plugins_dir / "not_memory"
+        plugin_dir.mkdir(parents=True)
+        (plugin_dir / "plugin.yaml").write_text(
+            yaml.dump({"name": "not_memory", "kind": "standalone"})
+        )
+        (plugin_dir / "__init__.py").write_text(
+            "# This plugin inspects MemoryProvider docs but isn't one.\n"
+            "def register(ctx):\n    pass\n"
+        )
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes_test"))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert mgr._plugins["not_memory"].manifest.kind == "standalone"
+
 
 # ── TestPluginHooks ────────────────────────────────────────────────────────
 
@@ -720,6 +787,33 @@ class TestPluginCommands:
         assert entry["handler"] is handler
         assert entry["description"] == "My custom command"
         assert entry["plugin"] == "test-plugin"
+        # args_hint defaults to empty string when not passed.
+        assert entry["args_hint"] == ""
+
+    def test_register_command_with_args_hint(self):
+        """args_hint is stored and surfaced for gateway-native UI registration."""
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-plugin", source="user")
+        ctx = PluginContext(manifest, mgr)
+
+        ctx.register_command(
+            "metricas",
+            lambda a: a,
+            description="Metrics dashboard",
+            args_hint="dias:7 formato:json",
+        )
+
+        entry = mgr._plugin_commands["metricas"]
+        assert entry["args_hint"] == "dias:7 formato:json"
+
+    def test_register_command_args_hint_whitespace_trimmed(self):
+        """args_hint leading/trailing whitespace is stripped."""
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-plugin", source="user")
+        ctx = PluginContext(manifest, mgr)
+
+        ctx.register_command("foo", lambda a: a, args_hint="  <file>  ")
+        assert mgr._plugin_commands["foo"]["args_hint"] == "<file>"
 
     def test_register_command_normalizes_name(self):
         """Names are lowercased, stripped, and leading slashes removed."""

tests/hermes_cli/test_pty_bridge.py

@@ -0,0 +1,172 @@
+"""Unit tests for hermes_cli.pty_bridge — PTY spawning + byte forwarding.
+
+These tests drive the bridge with minimal POSIX processes (echo, env, sleep,
+printf) to verify it behaves like a PTY you can read/write/resize/close.
+"""
+
+from __future__ import annotations
+
+import os
+import sys
+import time
+
+import pytest
+
+pytest.importorskip("ptyprocess", reason="ptyprocess not installed")
+
+from hermes_cli.pty_bridge import PtyBridge, PtyUnavailableError
+
+
+skip_on_windows = pytest.mark.skipif(
+    sys.platform.startswith("win"), reason="PTY bridge is POSIX-only"
+)
+
+
+def _read_until(bridge: PtyBridge, needle: bytes, timeout: float = 5.0) -> bytes:
+    """Accumulate PTY output until we see `needle` or time out."""
+    deadline = time.monotonic() + timeout
+    buf = bytearray()
+    while time.monotonic() < deadline:
+        chunk = bridge.read(timeout=0.2)
+        if chunk is None:
+            break
+        buf.extend(chunk)
+        if needle in buf:
+            return bytes(buf)
+    return bytes(buf)
+
+
+@skip_on_windows
+class TestPtyBridgeSpawn:
+    def test_is_available_on_posix(self):
+        assert PtyBridge.is_available() is True
+
+    def test_spawn_returns_bridge_with_pid(self):
+        bridge = PtyBridge.spawn(["true"])
+        try:
+            assert bridge.pid > 0
+        finally:
+            bridge.close()
+
+    def test_spawn_raises_on_missing_argv0(self, tmp_path):
+        with pytest.raises((FileNotFoundError, OSError)):
+            PtyBridge.spawn([str(tmp_path / "definitely-not-a-real-binary")])
+
+
+@skip_on_windows
+class TestPtyBridgeIO:
+    def test_reads_child_stdout(self):
+        bridge = PtyBridge.spawn(["/bin/sh", "-c", "printf hermes-ok"])
+        try:
+            output = _read_until(bridge, b"hermes-ok")
+            assert b"hermes-ok" in output
+        finally:
+            bridge.close()
+
+    def test_write_sends_to_child_stdin(self):
+        # `cat` with no args echoes stdin back to stdout.  We write a line,
+        # read it back, then signal EOF to let cat exit cleanly.
+        bridge = PtyBridge.spawn(["/bin/cat"])
+        try:
+            bridge.write(b"hello-pty\n")
+            output = _read_until(bridge, b"hello-pty")
+            assert b"hello-pty" in output
+        finally:
+            bridge.close()
+
+    def test_read_returns_none_after_child_exits(self):
+        bridge = PtyBridge.spawn(["/bin/sh", "-c", "printf done"])
+        try:
+            _read_until(bridge, b"done")
+            # Give the child a beat to exit cleanly, then drain until EOF.
+            deadline = time.monotonic() + 3.0
+            while bridge.is_alive() and time.monotonic() < deadline:
+                bridge.read(timeout=0.1)
+            # Next reads after exit should return None (EOF), not raise.
+            got_none = False
+            for _ in range(10):
+                if bridge.read(timeout=0.1) is None:
+                    got_none = True
+                    break
+            assert got_none, "PtyBridge.read did not return None after child EOF"
+        finally:
+            bridge.close()
+
+
+@skip_on_windows
+class TestPtyBridgeResize:
+    def test_resize_updates_child_winsize(self):
+        # tput reads COLUMNS/LINES from the TTY ioctl (TIOCGWINSZ).
+        # Spawn a shell, resize, then ask tput for the dimensions.
+        bridge = PtyBridge.spawn(
+            ["/bin/sh", "-c", "sleep 0.1; tput cols; tput lines"],
+            cols=80,
+            rows=24,
+        )
+        try:
+            bridge.resize(cols=123, rows=45)
+            output = _read_until(bridge, b"45", timeout=5.0)
+            # tput prints just the numbers, one per line
+            assert b"123" in output
+            assert b"45" in output
+        finally:
+            bridge.close()
+
+
+@skip_on_windows
+class TestPtyBridgeClose:
+    def test_close_is_idempotent(self):
+        bridge = PtyBridge.spawn(["/bin/sh", "-c", "sleep 30"])
+        bridge.close()
+        bridge.close()  # must not raise
+        assert not bridge.is_alive()
+
+    def test_close_terminates_long_running_child(self):
+        bridge = PtyBridge.spawn(["/bin/sh", "-c", "sleep 30"])
+        pid = bridge.pid
+        bridge.close()
+        # Give the kernel a moment to reap
+        deadline = time.monotonic() + 3.0
+        reaped = False
+        while time.monotonic() < deadline:
+            try:
+                os.kill(pid, 0)
+                time.sleep(0.05)
+            except ProcessLookupError:
+                reaped = True
+                break
+        assert reaped, f"pid {pid} still running after close()"
+
+
+@skip_on_windows
+class TestPtyBridgeEnv:
+    def test_cwd_is_respected(self, tmp_path):
+        bridge = PtyBridge.spawn(
+            ["/bin/sh", "-c", "pwd"],
+            cwd=str(tmp_path),
+        )
+        try:
+            output = _read_until(bridge, str(tmp_path).encode())
+            assert str(tmp_path).encode() in output
+        finally:
+            bridge.close()
+
+    def test_env_is_forwarded(self):
+        bridge = PtyBridge.spawn(
+            ["/bin/sh", "-c", "printf %s \"$HERMES_PTY_TEST\""],
+            env={**os.environ, "HERMES_PTY_TEST": "pty-env-works"},
+        )
+        try:
+            output = _read_until(bridge, b"pty-env-works")
+            assert b"pty-env-works" in output
+        finally:
+            bridge.close()
+
+
+class TestPtyBridgeUnavailable:
+    """Platform fallback semantics — PtyUnavailableError is importable and
+    carries a user-readable message."""
+
+    def test_error_carries_user_message(self):
+        err = PtyUnavailableError("platform not supported")
+        assert "platform" in str(err)

tests/hermes_cli/test_skin_engine.py

@@ -268,7 +268,6 @@ class TestCliBrandingHelpers:
 
     def test_prompt_toolkit_style_overrides_cover_tui_classes(self):
         from hermes_cli.skin_engine import set_active_skin, get_prompt_toolkit_style_overrides
-
         set_active_skin("ares")
         overrides = get_prompt_toolkit_style_overrides()
         required = {
@@ -277,6 +276,13 @@ class TestCliBrandingHelpers:
             "prompt",
             "prompt-working",
             "hint",
+            "status-bar",
+            "status-bar-strong",
+            "status-bar-dim",
+            "status-bar-good",
+            "status-bar-warn",
+            "status-bar-bad",
+            "status-bar-critical",
             "input-rule",
             "image-badge",
             "completion-menu",
@@ -325,6 +331,15 @@ class TestCliBrandingHelpers:
         overrides = get_prompt_toolkit_style_overrides()
         assert overrides["prompt"] == skin.get_color("prompt")
         assert overrides["input-rule"] == skin.get_color("input_rule")
+        assert overrides["status-bar"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_text')}"
+        )
+        assert overrides["status-bar-strong"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_strong')} bold"
+        )
+        assert overrides["status-bar-critical"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_critical')} bold"
+        )
         assert overrides["clarify-title"] == f"{skin.get_color('banner_title')} bold"
         assert overrides["sudo-prompt"] == f"{skin.get_color('ui_error')} bold"
         assert overrides["approval-title"] == f"{skin.get_color('ui_warn')} bold"

tests/hermes_cli/test_web_server.py

@@ -706,6 +706,7 @@ class TestNewEndpoints:
         assert "skills" in data
         assert isinstance(data["daily"], list)
         assert "total_sessions" in data["totals"]
+        assert "total_api_calls" in data["totals"]
         assert data["skills"] == {
             "summary": {
                 "total_skill_loads": 0,
@@ -1255,3 +1256,186 @@ class TestStatusRemoteGateway:
         assert data["gateway_running"] is True
         assert data["gateway_pid"] is None
         assert data["gateway_state"] == "running"
+
+
+# ---------------------------------------------------------------------------
+# /api/pty WebSocket — terminal bridge for the dashboard "Chat" tab.
+#
+# These tests drive the endpoint with a tiny fake command (typically ``cat``
+# or ``sh -c 'printf …'``) instead of the real ``hermes --tui`` binary.  The
+# endpoint resolves its argv through ``_resolve_chat_argv``, so tests
+# monkeypatch that hook.
+# ---------------------------------------------------------------------------
+
+import sys
+
+
+skip_on_windows = pytest.mark.skipif(
+    sys.platform.startswith("win"), reason="PTY bridge is POSIX-only"
+)
+
+
+@skip_on_windows
+class TestPtyWebSocket:
+    @pytest.fixture(autouse=True)
+    def _setup(self, monkeypatch, _isolate_hermes_home):
+        from starlette.testclient import TestClient
+
+        import hermes_cli.web_server as ws
+
+        # Avoid exec'ing the actual TUI in tests: every test below installs
+        # its own fake argv via ``ws._resolve_chat_argv``.
+        self.ws_module = ws
+        self.token = ws._SESSION_TOKEN
+        self.client = TestClient(ws.app)
+
+    def _url(self, token: str | None = None, **params: str) -> str:
+        tok = token if token is not None else self.token
+        # TestClient.websocket_connect takes the path; it reconstructs the
+        # query string, so we pass it inline.
+        from urllib.parse import urlencode
+
+        q = {"token": tok, **params}
+        return f"/api/pty?{urlencode(q)}"
+
+    def test_rejects_missing_token(self, monkeypatch):
+        monkeypatch.setattr(
+            self.ws_module,
+            "_resolve_chat_argv",
+            lambda resume=None: (["/bin/cat"], None, None),
+        )
+        from starlette.websockets import WebSocketDisconnect
+
+        with pytest.raises(WebSocketDisconnect) as exc:
+            with self.client.websocket_connect("/api/pty"):
+                pass
+        assert exc.value.code == 4401
+
+    def test_rejects_bad_token(self, monkeypatch):
+        monkeypatch.setattr(
+            self.ws_module,
+            "_resolve_chat_argv",
+            lambda resume=None: (["/bin/cat"], None, None),
+        )
+        from starlette.websockets import WebSocketDisconnect
+
+        with pytest.raises(WebSocketDisconnect) as exc:
+            with self.client.websocket_connect(self._url(token="wrong")):
+                pass
+        assert exc.value.code == 4401
+
+    def test_streams_child_stdout_to_client(self, monkeypatch):
+        monkeypatch.setattr(
+            self.ws_module,
+            "_resolve_chat_argv",
+            lambda resume=None: (
+                ["/bin/sh", "-c", "printf hermes-ws-ok"],
+                None,
+                None,
+            ),
+        )
+        with self.client.websocket_connect(self._url()) as conn:
+            # Drain frames until we see the needle or time out.  TestClient's
+            # recv_bytes blocks; loop until we have the signal byte string.
+            buf = b""
+            import time
+
+            deadline = time.monotonic() + 5.0
+            while time.monotonic() < deadline:
+                try:
+                    frame = conn.receive_bytes()
+                except Exception:
+                    break
+                if frame:
+                    buf += frame
+                if b"hermes-ws-ok" in buf:
+                    break
+            assert b"hermes-ws-ok" in buf
+
+    def test_client_input_reaches_child_stdin(self, monkeypatch):
+        # ``cat`` echoes stdin back, so a write → read round-trip proves
+        # the full duplex path.
+        monkeypatch.setattr(
+            self.ws_module,
+            "_resolve_chat_argv",
+            lambda resume=None: (["/bin/cat"], None, None),
+        )
+        with self.client.websocket_connect(self._url()) as conn:
+            conn.send_bytes(b"round-trip-payload\n")
+            buf = b""
+            import time
+
+            deadline = time.monotonic() + 5.0
+            while time.monotonic() < deadline:
+                frame = conn.receive_bytes()
+                if frame:
+                    buf += frame
+                if b"round-trip-payload" in buf:
+                    break
+            assert b"round-trip-payload" in buf
+
+    def test_resize_escape_is_forwarded(self, monkeypatch):
+        # Resize escape gets intercepted and applied via TIOCSWINSZ,
+        # then ``tput cols/lines`` reports the new dimensions back.
+        monkeypatch.setattr(
+            self.ws_module,
+            "_resolve_chat_argv",
+            # sleep gives the test time to push the resize before tput runs
+            lambda resume=None: (
+                ["/bin/sh", "-c", "sleep 0.15; tput cols; tput lines"],
+                None,
+                None,
+            ),
+        )
+        with self.client.websocket_connect(self._url()) as conn:
+            conn.send_text("\x1b[RESIZE:99;41]")
+            buf = b""
+            import time
+
+            deadline = time.monotonic() + 5.0
+            while time.monotonic() < deadline:
+                frame = conn.receive_bytes()
+                if frame:
+                    buf += frame
+                if b"99" in buf and b"41" in buf:
+                    break
+            assert b"99" in buf and b"41" in buf
+
+    def test_unavailable_platform_closes_with_message(self, monkeypatch):
+        from hermes_cli.pty_bridge import PtyUnavailableError
+
+        def _raise(argv, **kwargs):
+            raise PtyUnavailableError("pty missing for tests")
+
+        monkeypatch.setattr(
+            self.ws_module,
+            "_resolve_chat_argv",
+            lambda resume=None: (["/bin/cat"], None, None),
+        )
+        # Patch PtyBridge.spawn at the web_server module's binding.
+        import hermes_cli.web_server as ws_mod
+
+        monkeypatch.setattr(ws_mod.PtyBridge, "spawn", classmethod(lambda cls, *a, **k: _raise(*a, **k)))
+
+        with self.client.websocket_connect(self._url()) as conn:
+            # Expect a final text frame with the error message, then close.
+            msg = conn.receive_text()
+            assert "pty missing" in msg or "unavailable" in msg.lower() or "pty" in msg.lower()
+
+    def test_resume_parameter_is_forwarded_to_argv(self, monkeypatch):
+        captured: dict = {}
+
+        def fake_resolve(resume=None):
+            captured["resume"] = resume
+            return (["/bin/sh", "-c", "printf resume-arg-ok"], None, None)
+
+        monkeypatch.setattr(self.ws_module, "_resolve_chat_argv", fake_resolve)
+
+        with self.client.websocket_connect(self._url(resume="sess-42")) as conn:
+            # Drain briefly so the handler actually invokes the resolver.
+            try:
+                conn.receive_bytes()
+            except Exception:
+                pass
+        assert captured.get("resume") == "sess-42"
+

tests/plugins/memory/test_hindsight_provider.py

@@ -6,6 +6,7 @@ turn counting, tags), and schema completeness.
 """
 
 import json
+import re
 import threading
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, MagicMock, patch
@@ -18,6 +19,7 @@ from plugins.memory.hindsight import (
     REFLECT_SCHEMA,
     RETAIN_SCHEMA,
     _load_config,
+    _normalize_retain_tags,
 )
 
 
@@ -32,14 +34,30 @@ def _clean_env(monkeypatch):
     for key in (
         "HINDSIGHT_API_KEY", "HINDSIGHT_API_URL", "HINDSIGHT_BANK_ID",
         "HINDSIGHT_BUDGET", "HINDSIGHT_MODE", "HINDSIGHT_LLM_API_KEY",
+        "HINDSIGHT_RETAIN_TAGS", "HINDSIGHT_RETAIN_SOURCE",
+        "HINDSIGHT_RETAIN_USER_PREFIX", "HINDSIGHT_RETAIN_ASSISTANT_PREFIX",
     ):
         monkeypatch.delenv(key, raising=False)
 
 
 def _make_mock_client():
     """Create a mock Hindsight client with async methods."""
+    async def _aretain(
+        bank_id,
+        content,
+        timestamp=None,
+        context=None,
+        document_id=None,
+        metadata=None,
+        entities=None,
+        tags=None,
+        update_mode=None,
+        retain_async=None,
+    ):
+        return SimpleNamespace(ok=True)
+
     client = MagicMock()
-    client.aretain = AsyncMock()
+    client.aretain = AsyncMock(side_effect=_aretain)
     client.arecall = AsyncMock(
         return_value=SimpleNamespace(
             results=[
@@ -56,6 +74,14 @@ def _make_mock_client():
     return client
 
 
+class _FakeSessionDB:
+    def __init__(self, messages=None):
+        self._messages = list(messages or [])
+
+    def get_messages_as_conversation(self, session_id):
+        return list(self._messages)
+
+
 @pytest.fixture()
 def provider(tmp_path, monkeypatch):
     """Create an initialized HindsightMemoryProvider with a mock client."""
@@ -109,6 +135,18 @@ def provider_with_config(tmp_path, monkeypatch):
     return _make
 
 
+def test_normalize_retain_tags_accepts_csv_and_dedupes():
+    assert _normalize_retain_tags("agent:fakeassistantname, source_system:hermes-agent, agent:fakeassistantname") == [
+        "agent:fakeassistantname",
+        "source_system:hermes-agent",
+    ]
+
+
+def test_normalize_retain_tags_accepts_json_array_string():
+    value = json.dumps(["agent:fakeassistantname", "source_system:hermes-agent"])
+    assert _normalize_retain_tags(value) == ["agent:fakeassistantname", "source_system:hermes-agent"]
+
+
 # ---------------------------------------------------------------------------
 # Schema tests
 # ---------------------------------------------------------------------------
@@ -118,6 +156,7 @@ class TestSchemas:
     def test_retain_schema_has_content(self):
         assert RETAIN_SCHEMA["name"] == "hindsight_retain"
         assert "content" in RETAIN_SCHEMA["parameters"]["properties"]
+        assert "tags" in RETAIN_SCHEMA["parameters"]["properties"]
         assert "content" in RETAIN_SCHEMA["parameters"]["required"]
 
     def test_recall_schema_has_query(self):
@@ -160,7 +199,10 @@ class TestConfig:
 
     def test_custom_config_values(self, provider_with_config):
         p = provider_with_config(
-            tags=["tag1", "tag2"],
+            retain_tags=["tag1", "tag2"],
+            retain_source="hermes",
+            retain_user_prefix="User (fakeusername)",
+            retain_assistant_prefix="Assistant (fakeassistantname)",
             recall_tags=["recall-tag"],
             recall_tags_match="all",
             auto_retain=False,
@@ -175,6 +217,10 @@ class TestConfig:
             bank_mission="Test agent mission",
         )
         assert p._tags == ["tag1", "tag2"]
+        assert p._retain_tags == ["tag1", "tag2"]
+        assert p._retain_source == "hermes"
+        assert p._retain_user_prefix == "User (fakeusername)"
+        assert p._retain_assistant_prefix == "Assistant (fakeassistantname)"
         assert p._recall_tags == ["recall-tag"]
         assert p._recall_tags_match == "all"
         assert p._auto_retain is False
@@ -222,11 +268,20 @@ class TestToolHandlers:
         assert call_kwargs["content"] == "user likes dark mode"
 
     def test_retain_with_tags(self, provider_with_config):
-        p = provider_with_config(tags=["pref", "ui"])
+        p = provider_with_config(retain_tags=["pref", "ui"])
         p.handle_tool_call("hindsight_retain", {"content": "likes dark mode"})
         call_kwargs = p._client.aretain.call_args.kwargs
         assert call_kwargs["tags"] == ["pref", "ui"]
 
+    def test_retain_merges_per_call_tags_with_config_tags(self, provider_with_config):
+        p = provider_with_config(retain_tags=["pref", "ui"])
+        p.handle_tool_call(
+            "hindsight_retain",
+            {"content": "likes dark mode", "tags": ["client:x", "ui"]},
+        )
+        call_kwargs = p._client.aretain.call_args.kwargs
+        assert call_kwargs["tags"] == ["pref", "ui", "client:x"]
+
     def test_retain_without_tags(self, provider):
         provider.handle_tool_call("hindsight_retain", {"content": "hello"})
         call_kwargs = provider._client.aretain.call_args.kwargs
@@ -389,38 +444,58 @@ class TestPrefetch:
 
 
 class TestSyncTurn:
-    def _get_retain_kwargs(self, provider):
-        """Helper to get the kwargs from the aretain_batch call."""
-        return provider._client.aretain_batch.call_args.kwargs
+    def test_sync_turn_retains_metadata_rich_turn(self, provider_with_config):
+        p = provider_with_config(
+            retain_tags=["conv", "session1"],
+            retain_source="hermes",
+            retain_user_prefix="User (fakeusername)",
+            retain_assistant_prefix="Assistant (fakeassistantname)",
+        )
+        p.initialize(
+            session_id="session-1",
+            platform="discord",
+            user_id="fakeusername-123",
+            user_name="fakeusername",
+            chat_id="1485316232612941897",
+            chat_name="fakeassistantname-forums",
+            chat_type="thread",
+            thread_id="1491249007475949698",
+            agent_identity="fakeassistantname",
+        )
+        p._client = _make_mock_client()
 
-    def _get_retain_content(self, provider):
-        """Helper to get the raw content string from the first item."""
-        kwargs = self._get_retain_kwargs(provider)
-        return kwargs["items"][0]["content"]
+        p.sync_turn("hello", "hi there")
+        p._sync_thread.join(timeout=5.0)
 
-    def _get_retain_messages(self, provider):
-        """Helper to parse the first turn's messages from retained content.
-
-        Content is a JSON array of turns: [[msgs...], [msgs...], ...]
-        For single-turn tests, returns the first turn's messages.
-        """
-        content = self._get_retain_content(provider)
-        turns = json.loads(content)
-        return turns[0] if len(turns) == 1 else turns
-
-    def test_sync_turn_retains(self, provider):
-        provider.sync_turn("hello", "hi there")
-        if provider._sync_thread:
-            provider._sync_thread.join(timeout=5.0)
-        provider._client.aretain_batch.assert_called_once()
-        messages = self._get_retain_messages(provider)
-        assert len(messages) == 2
-        assert messages[0]["role"] == "user"
-        assert messages[0]["content"] == "hello"
-        assert "timestamp" in messages[0]
-        assert messages[1]["role"] == "assistant"
-        assert messages[1]["content"] == "hi there"
-        assert "timestamp" in messages[1]
+        p._client.aretain_batch.assert_called_once()
+        call_kwargs = p._client.aretain_batch.call_args.kwargs
+        assert call_kwargs["bank_id"] == "test-bank"
+        assert call_kwargs["document_id"] == "session-1"
+        assert call_kwargs["retain_async"] is True
+        assert len(call_kwargs["items"]) == 1
+        item = call_kwargs["items"][0]
+        assert item["context"] == "conversation between Hermes Agent and the User"
+        assert item["tags"] == ["conv", "session1"]
+        content = json.loads(item["content"])
+        assert len(content) == 1
+        assert content[0][0]["role"] == "user"
+        assert content[0][0]["content"] == "User (fakeusername): hello"
+        assert content[0][1]["role"] == "assistant"
+        assert content[0][1]["content"] == "Assistant (fakeassistantname): hi there"
+        assert item["metadata"]["source"] == "hermes"
+        assert item["metadata"]["session_id"] == "session-1"
+        assert item["metadata"]["platform"] == "discord"
+        assert item["metadata"]["user_id"] == "fakeusername-123"
+        assert item["metadata"]["user_name"] == "fakeusername"
+        assert item["metadata"]["chat_id"] == "1485316232612941897"
+        assert item["metadata"]["chat_name"] == "fakeassistantname-forums"
+        assert item["metadata"]["chat_type"] == "thread"
+        assert item["metadata"]["thread_id"] == "1491249007475949698"
+        assert item["metadata"]["agent_identity"] == "fakeassistantname"
+        assert item["metadata"]["turn_index"] == "1"
+        assert item["metadata"]["message_count"] == "2"
+        assert re.fullmatch(r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?\+00:00", content[0][0]["timestamp"])
+        assert re.fullmatch(r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\.\d{3}Z", item["metadata"]["retained_at"])
 
     def test_sync_turn_skipped_when_auto_retain_off(self, provider_with_config):
         p = provider_with_config(auto_retain=False)
@@ -428,93 +503,33 @@ class TestSyncTurn:
         assert p._sync_thread is None
         p._client.aretain_batch.assert_not_called()
 
-    def test_sync_turn_with_tags(self, provider_with_config):
-        p = provider_with_config(tags=["conv", "session1"])
-        p.sync_turn("hello", "hi")
-        if p._sync_thread:
-            p._sync_thread.join(timeout=5.0)
-        item = p._client.aretain_batch.call_args.kwargs["items"][0]
-        assert item["tags"] == ["conv", "session1"]
-
-    def test_sync_turn_uses_aretain_batch(self, provider):
-        """sync_turn should use aretain_batch with retain_async."""
-        provider.sync_turn("hello", "hi")
-        if provider._sync_thread:
-            provider._sync_thread.join(timeout=5.0)
-        provider._client.aretain_batch.assert_called_once()
-        call_kwargs = provider._client.aretain_batch.call_args.kwargs
-        assert call_kwargs["document_id"] == "test-session"
-        assert call_kwargs["retain_async"] is True
-        assert len(call_kwargs["items"]) == 1
-        assert call_kwargs["items"][0]["context"] == "conversation between Hermes Agent and the User"
-
-    def test_sync_turn_custom_context(self, provider_with_config):
-        p = provider_with_config(retain_context="my-agent")
-        p.sync_turn("hello", "hi")
-        if p._sync_thread:
-            p._sync_thread.join(timeout=5.0)
-        item = p._client.aretain_batch.call_args.kwargs["items"][0]
-        assert item["context"] == "my-agent"
-
     def test_sync_turn_every_n_turns(self, provider_with_config):
-        """With retain_every_n_turns=3, only retains on every 3rd turn."""
-        p = provider_with_config(retain_every_n_turns=3)
-
+        p = provider_with_config(retain_every_n_turns=3, retain_async=False)
         p.sync_turn("turn1-user", "turn1-asst")
-        assert p._sync_thread is None  # not retained yet
-
+        assert p._sync_thread is None
         p.sync_turn("turn2-user", "turn2-asst")
-        assert p._sync_thread is None  # not retained yet
-
+        assert p._sync_thread is None
         p.sync_turn("turn3-user", "turn3-asst")
-        assert p._sync_thread is not None  # retained!
         p._sync_thread.join(timeout=5.0)
-
         p._client.aretain_batch.assert_called_once()
-        content = p._client.aretain_batch.call_args.kwargs["items"][0]["content"]
-        # Should contain all 3 turns
-        assert "turn1-user" in content
-        assert "turn2-user" in content
-        assert "turn3-user" in content
-
-    def test_sync_turn_accumulates_full_session(self, provider_with_config):
-        """Each retain sends the ENTIRE session, not just the latest batch."""
-        p = provider_with_config(retain_every_n_turns=2)
-
-        p.sync_turn("turn1-user", "turn1-asst")
-        p.sync_turn("turn2-user", "turn2-asst")
-        if p._sync_thread:
-            p._sync_thread.join(timeout=5.0)
-
-        p._client.aretain_batch.reset_mock()
-
-        p.sync_turn("turn3-user", "turn3-asst")
-        p.sync_turn("turn4-user", "turn4-asst")
-        if p._sync_thread:
-            p._sync_thread.join(timeout=5.0)
-
-        content = p._client.aretain_batch.call_args.kwargs["items"][0]["content"]
-        # Should contain ALL turns from the session
-        assert "turn1-user" in content
-        assert "turn2-user" in content
-        assert "turn3-user" in content
-        assert "turn4-user" in content
-
-    def test_sync_turn_passes_document_id(self, provider):
-        """sync_turn should pass session_id as document_id for dedup."""
-        provider.sync_turn("hello", "hi")
-        if provider._sync_thread:
-            provider._sync_thread.join(timeout=5.0)
-        call_kwargs = provider._client.aretain_batch.call_args.kwargs
+        call_kwargs = p._client.aretain_batch.call_args.kwargs
         assert call_kwargs["document_id"] == "test-session"
+        assert call_kwargs["retain_async"] is False
+        item = call_kwargs["items"][0]
+        content = json.loads(item["content"])
+        assert len(content) == 3
+        assert content[-1][0]["role"] == "user"
+        assert content[-1][0]["content"] == "User: turn3-user"
+        assert content[-1][1]["role"] == "assistant"
+        assert content[-1][1]["content"] == "Assistant: turn3-asst"
+        assert item["metadata"]["turn_index"] == "3"
+        assert item["metadata"]["message_count"] == "6"
 
     def test_sync_turn_error_does_not_raise(self, provider):
-        """Errors in sync_turn should be swallowed (non-blocking)."""
         provider._client.aretain_batch.side_effect = RuntimeError("network error")
         provider.sync_turn("hello", "hi")
         if provider._sync_thread:
             provider._sync_thread.join(timeout=5.0)
-        # Should not raise
 
 
 # ---------------------------------------------------------------------------
@@ -555,10 +570,11 @@ class TestConfigSchema:
             "mode", "api_url", "api_key", "llm_provider", "llm_api_key",
             "llm_model", "bank_id", "bank_mission", "bank_retain_mission",
             "recall_budget", "memory_mode", "recall_prefetch_method",
-            "tags", "recall_tags", "recall_tags_match",
+            "retain_tags", "retain_source",
+            "retain_user_prefix", "retain_assistant_prefix",
+            "recall_tags", "recall_tags_match",
             "auto_recall", "auto_retain",
-            "retain_every_n_turns", "retain_async",
-            "retain_context",
+            "retain_every_n_turns", "retain_async", "retain_context",
             "recall_max_tokens", "recall_max_input_chars",
             "recall_prompt_preamble",
         }

tests/run_agent/test_provider_fallback.py

@@ -155,3 +155,29 @@ class TestFallbackChainAdvancement:
             ]
             assert agent._try_activate_fallback() is True
             assert agent.model == "gpt-4o"
+
+    def test_resolves_key_env_for_fallback_provider(self):
+        fbs = [
+            {
+                "provider": "custom",
+                "model": "fallback-model",
+                "base_url": "https://fallback.example/v1",
+                "key_env": "MY_FALLBACK_KEY",
+            }
+        ]
+        agent = _make_agent(fallback_model=fbs)
+        with (
+            patch.dict("os.environ", {"MY_FALLBACK_KEY": "env-secret"}, clear=False),
+            patch(
+                "agent.auxiliary_client.resolve_provider_client",
+                return_value=(
+                    _mock_client(
+                        base_url="https://fallback.example/v1",
+                        api_key="env-secret",
+                    ),
+                    "fallback-model",
+                ),
+            ) as mock_rpc,
+        ):
+            assert agent._try_activate_fallback() is True
+            assert mock_rpc.call_args.kwargs["explicit_api_key"] == "env-secret"

tests/run_agent/test_run_agent.py

@@ -372,6 +372,91 @@ class TestStripThinkBlocks:
         assert "mixed" not in result
         assert "final" in result
 
+    # ─── Tool-call XML block stripping (openclaw/openclaw#67318) ─────────
+    # Some open models (notably Gemma variants via OpenRouter) emit
+    # standalone tool-call XML inside assistant content instead of via the
+    # structured `tool_calls` field. Left unstripped, raw XML leaks to
+    # gateway users (Discord/Telegram/Matrix) and the CLI.
+
+    def test_tool_call_block_stripped(self, agent):
+        text = '<tool_call>{"name": "read_file", "arguments": {"path": "/tmp/x"}}</tool_call> done'
+        result = agent._strip_think_blocks(text)
+        assert "<tool_call>" not in result
+        assert "read_file" not in result
+        assert "done" in result
+
+    def test_function_calls_block_stripped(self, agent):
+        text = '<function_calls>[{"name":"x"}]</function_calls>after'
+        result = agent._strip_think_blocks(text)
+        assert "<function_calls>" not in result
+        assert "after" in result
+
+    def test_gemma_function_name_block_stripped(self, agent):
+        """Gemma-style: <function name="read"><parameter>...</parameter></function>."""
+        text = (
+            'Let me check the file.\n'
+            '<function name="read_file"><parameter name="path">/tmp/x.md</parameter></function>\n'
+            'Here is the result.'
+        )
+        result = agent._strip_think_blocks(text)
+        assert '<function name="read_file">' not in result
+        assert "/tmp/x.md" not in result
+        assert "Let me check the file." in result
+        assert "Here is the result." in result
+
+    def test_gemma_function_multiline_payload_stripped(self, agent):
+        text = (
+            'Reading now.\n'
+            '<function name="read_file">\n'
+            '  <parameter name="path">/etc/passwd</parameter>\n'
+            '</function>\n'
+            'Done.'
+        )
+        result = agent._strip_think_blocks(text)
+        assert "/etc/passwd" not in result
+        assert "Reading now." in result
+        assert "Done." in result
+
+    def test_function_mention_in_prose_preserved(self, agent):
+        """'Use <function> in JavaScript.' — no name attr, not at block boundary
+        in a way that suggests tool call. Must survive."""
+        text = "In JS you can use <function> declarations for hoisting."
+        result = agent._strip_think_blocks(text)
+        # Prose mention has no name="..." attribute -> not stripped
+        assert "declarations for hoisting" in result
+
+    def test_function_with_attr_in_middle_of_sentence_preserved(self, agent):
+        """Docs example: 'Use <function name="x">...</function> in docs.'
+        The sentence-middle position without a preceding punctuation block
+        boundary means it is NOT stripped. Prose context remains."""
+        text = 'You can write <function name="x">y</function> inline.'
+        result = agent._strip_think_blocks(text)
+        # Without a leading block boundary (no punctuation before), leaves intact
+        assert "You can write" in result
+        assert "inline" in result
+
+    def test_stray_function_close_tag_removed(self, agent):
+        text = "answer</function> trailing"
+        result = agent._strip_think_blocks(text)
+        assert "</function>" not in result
+        assert "answer" in result
+        assert "trailing" in result
+
+    def test_dangling_function_open_tag_preserved(self, agent):
+        """A streamed-but-truncated <function name="..."> block with no close
+        is intentionally NOT stripped (OpenClaw's asymmetry). The tail of a
+        streaming reply may still be valuable to the user."""
+        text = 'Checking: <function name="read">'
+        result = agent._strip_think_blocks(text)
+        assert "Checking:" in result
+
+    def test_mixed_reasoning_and_tool_call_both_stripped(self, agent):
+        text = '<think>let me plan</think><tool_call>{"name":"x"}</tool_call>final answer'
+        result = agent._strip_think_blocks(text)
+        assert "let me plan" not in result
+        assert "<tool_call>" not in result
+        assert "final answer" in result
+
 
 class TestExtractReasoning:
     def test_reasoning_field(self, agent):
@@ -1216,6 +1301,15 @@ class TestBuildAssistantMessage:
         result = agent._build_assistant_message(msg, "stop")
         assert result["reasoning"] == "thinking"
 
+    def test_reasoning_content_preserved_separately(self, agent):
+        msg = _mock_assistant_msg(
+            content="answer",
+            reasoning="summary",
+            reasoning_content="provider scratchpad",
+        )
+        result = agent._build_assistant_message(msg, "stop")
+        assert result["reasoning_content"] == "provider scratchpad"
+
     def test_with_tool_calls(self, agent):
         tc = _mock_tool_call(name="web_search", arguments='{"q":"test"}', call_id="c1")
         msg = _mock_assistant_msg(content="", tool_calls=[tc])
@@ -4188,6 +4282,90 @@ class TestPersistUserMessageOverride:
         assert first_db_write["content"] == "Hello there"
 
 
+class TestReasoningReplayForStrictProviders:
+    """Assistant replay must preserve provider-native reasoning fields."""
+
+    def _setup_agent(self, agent):
+        agent._cached_system_prompt = "You are helpful."
+        agent._use_prompt_caching = False
+        agent.tool_delay = 0
+        agent.compression_enabled = False
+        agent.save_trajectories = False
+
+    def test_kimi_tool_replay_includes_empty_reasoning_content(self, agent):
+        self._setup_agent(agent)
+        agent.base_url = "https://api.kimi.com/coding/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.provider = "kimi-coding"
+
+        prior_assistant = {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "c1",
+                    "type": "function",
+                    "function": {"name": "terminal", "arguments": "{\"command\":\"date\"}"},
+                }
+            ],
+        }
+        tool_result = {"role": "tool", "tool_call_id": "c1", "content": "Tue Apr 21"}
+        final_resp = _mock_response(content="done", finish_reason="stop")
+        agent.client.chat.completions.create.return_value = final_resp
+
+        with (
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+        ):
+            result = agent.run_conversation(
+                "next step",
+                conversation_history=[prior_assistant, tool_result],
+            )
+
+        assert result["completed"] is True
+        sent_messages = agent.client.chat.completions.create.call_args.kwargs["messages"]
+        replayed_assistant = next(msg for msg in sent_messages if msg.get("role") == "assistant")
+        assert replayed_assistant["role"] == "assistant"
+        assert replayed_assistant["tool_calls"][0]["function"]["name"] == "terminal"
+        assert "reasoning_content" in replayed_assistant
+        assert replayed_assistant["reasoning_content"] == ""
+
+    def test_explicit_reasoning_content_beats_normalized_reasoning_on_replay(self, agent):
+        self._setup_agent(agent)
+        prior_assistant = {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "c1",
+                    "type": "function",
+                    "function": {"name": "web_search", "arguments": "{\"q\":\"test\"}"},
+                }
+            ],
+            "reasoning": "summary reasoning",
+            "reasoning_content": "provider-native scratchpad",
+        }
+        tool_result = {"role": "tool", "tool_call_id": "c1", "content": "ok"}
+        final_resp = _mock_response(content="done", finish_reason="stop")
+        agent.client.chat.completions.create.return_value = final_resp
+
+        with (
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+        ):
+            result = agent.run_conversation(
+                "next step",
+                conversation_history=[prior_assistant, tool_result],
+            )
+
+        assert result["completed"] is True
+        sent_messages = agent.client.chat.completions.create.call_args.kwargs["messages"]
+        replayed_assistant = next(msg for msg in sent_messages if msg.get("role") == "assistant")
+        assert replayed_assistant["reasoning_content"] == "provider-native scratchpad"
+
+
 # ---------------------------------------------------------------------------
 # Bugfix: _vprint force=True on error messages during TTS
 # ---------------------------------------------------------------------------

tests/run_agent/test_run_agent_multimodal_prologue.py

@@ -13,7 +13,8 @@ They do NOT boot the full AIAgent — the prologue-fix guarantees are pure
 function contracts at module scope.
 """
 
-from run_agent import _chat_content_to_responses_parts, _summarize_user_message_for_log
+from run_agent import _summarize_user_message_for_log
+from agent.codex_responses_adapter import _chat_content_to_responses_parts
 
 
 class TestSummarizeUserMessageForLog:

tests/run_agent/test_streaming.py

@@ -1133,3 +1133,225 @@ class TestPartialToolCallWarning:
             f"Unexpected warning on text-only partial stream: {content!r}"
         )
 
+
+class TestSilentRetryMidToolCall:
+    """Regression: when the stream dies mid tool-call JSON after text was
+    already delivered, we previously stubbed the turn with a "retry manually"
+    warning.  Now: if the error is a transient connection error AND a tool
+    call was in flight, silently retry the stream (the user sees a brief
+    reconnect marker + duplicated preamble, which is strictly better than
+    a lost action).  If no tool call was in flight, or the error isn't
+    transient, the existing stub-with-warning behaviour is preserved.
+    """
+
+    @patch("run_agent.AIAgent._replace_primary_openai_client")
+    @patch("run_agent.AIAgent._create_request_openai_client")
+    @patch("run_agent.AIAgent._close_request_openai_client")
+    def test_silent_retry_recovers_tool_call(
+        self, mock_close, mock_create, mock_replace,
+    ):
+        """First attempt: text + partial tool-call + connection drop.
+        Second attempt: text + complete tool-call.  Response should contain
+        the recovered tool call; no warning stub should be returned."""
+        from run_agent import AIAgent
+        import httpx as _httpx
+
+        attempts = {"n": 0}
+
+        def _first_stream():
+            yield _make_stream_chunk(content="Let me write the audit: ")
+            yield _make_stream_chunk(tool_calls=[
+                _make_tool_call_delta(index=0, tc_id="call_1", name="write_file"),
+            ])
+            yield _make_stream_chunk(tool_calls=[
+                _make_tool_call_delta(index=0, arguments='{"path": "/tmp/x", '),
+            ])
+            raise _httpx.RemoteProtocolError("peer closed connection")
+
+        def _second_stream():
+            yield _make_stream_chunk(content="Let me write the audit: ")
+            yield _make_stream_chunk(tool_calls=[
+                _make_tool_call_delta(index=0, tc_id="call_1", name="write_file"),
+            ])
+            yield _make_stream_chunk(tool_calls=[
+                _make_tool_call_delta(
+                    index=0, arguments='{"path": "/tmp/x", "content": "hi"}',
+                ),
+            ])
+            yield _make_stream_chunk(finish_reason="tool_calls")
+
+        def _pick_stream(*a, **kw):
+            attempts["n"] += 1
+            return _first_stream() if attempts["n"] == 1 else _second_stream()
+
+        mock_client = MagicMock()
+        mock_client.chat.completions.create.side_effect = _pick_stream
+        mock_create.return_value = mock_client
+
+        agent = AIAgent(
+            api_key="test-key",
+            base_url="https://openrouter.ai/api/v1",
+            model="test/model",
+            quiet_mode=True,
+            skip_context_files=True,
+            skip_memory=True,
+        )
+        agent.api_mode = "chat_completions"
+        agent._interrupt_requested = False
+
+        fired_deltas: list = []
+        agent._fire_stream_delta = lambda text: fired_deltas.append(text)
+
+        import os as _os
+        _prev = _os.environ.get("HERMES_STREAM_RETRIES")
+        _os.environ["HERMES_STREAM_RETRIES"] = "2"
+        try:
+            response = agent._interruptible_streaming_api_call({})
+        finally:
+            if _prev is None:
+                _os.environ.pop("HERMES_STREAM_RETRIES", None)
+            else:
+                _os.environ["HERMES_STREAM_RETRIES"] = _prev
+
+        assert attempts["n"] == 2, (
+            f"Expected silent retry (2 attempts), got {attempts['n']}"
+        )
+        # Response should carry the recovered tool call, not a warning stub.
+        msg = response.choices[0].message
+        tool_calls = getattr(msg, "tool_calls", None)
+        assert tool_calls, (
+            f"Silent retry should recover the tool call, got tool_calls={tool_calls!r} "
+            f"content={getattr(msg, 'content', None)!r}"
+        )
+        _tc0 = tool_calls[0]
+        _name = (
+            _tc0["function"]["name"] if isinstance(_tc0, dict)
+            else _tc0.function.name
+        )
+        assert _name == "write_file"
+        # User saw a reconnect marker between attempts.
+        assert any("reconnecting" in d.lower() for d in fired_deltas), (
+            f"Expected a reconnect marker delta, fired_deltas={fired_deltas}"
+        )
+        # Stub-path warning must NOT appear (this was the whole point).
+        joined = "".join(fired_deltas)
+        assert "Stream stalled" not in joined, (
+            f"Stub-path warning leaked into silent-retry path: {joined!r}"
+        )
+
+    @patch("run_agent.AIAgent._replace_primary_openai_client")
+    @patch("run_agent.AIAgent._create_request_openai_client")
+    @patch("run_agent.AIAgent._close_request_openai_client")
+    def test_silent_retry_exhausted_falls_back_to_stub(
+        self, mock_close, mock_create, mock_replace,
+    ):
+        """When all retry attempts fail with connection errors, fall back
+        to the original stub-with-warning behaviour so the user isn't left
+        with zero signal."""
+        from run_agent import AIAgent
+        import httpx as _httpx
+
+        def _always_fails():
+            yield _make_stream_chunk(content="Let me write the audit: ")
+            yield _make_stream_chunk(tool_calls=[
+                _make_tool_call_delta(index=0, tc_id="call_1", name="write_file"),
+            ])
+            raise _httpx.RemoteProtocolError("peer closed connection")
+
+        mock_client = MagicMock()
+        mock_client.chat.completions.create.side_effect = lambda *a, **kw: _always_fails()
+        mock_create.return_value = mock_client
+
+        agent = AIAgent(
+            api_key="test-key",
+            base_url="https://openrouter.ai/api/v1",
+            model="test/model",
+            quiet_mode=True,
+            skip_context_files=True,
+            skip_memory=True,
+        )
+        agent.api_mode = "chat_completions"
+        agent._interrupt_requested = False
+
+        fired_deltas: list = []
+        agent._fire_stream_delta = lambda text: fired_deltas.append(text)
+
+        import os as _os
+        _prev = _os.environ.get("HERMES_STREAM_RETRIES")
+        _os.environ["HERMES_STREAM_RETRIES"] = "1"
+        try:
+            response = agent._interruptible_streaming_api_call({})
+        finally:
+            if _prev is None:
+                _os.environ.pop("HERMES_STREAM_RETRIES", None)
+            else:
+                _os.environ["HERMES_STREAM_RETRIES"] = _prev
+
+        # After retries exhaust, the stub-with-warning path must engage.
+        content = response.choices[0].message.content or ""
+        assert "Stream stalled mid tool-call" in content, (
+            f"Exhausted-retry fallback dropped the user-visible warning: {content!r}"
+        )
+        assert response.choices[0].message.tool_calls is None
+
+    @patch("run_agent.AIAgent._replace_primary_openai_client")
+    @patch("run_agent.AIAgent._create_request_openai_client")
+    @patch("run_agent.AIAgent._close_request_openai_client")
+    def test_no_silent_retry_for_text_only_stall(
+        self, mock_close, mock_create, mock_replace,
+    ):
+        """Text-only stall (no tool call in flight) must NOT trigger silent
+        retry — that's the case where the user saw the model's text reply
+        and retrying would duplicate it with no benefit."""
+        from run_agent import AIAgent
+        import httpx as _httpx
+
+        attempts = {"n": 0}
+
+        def _text_stall(*a, **kw):
+            attempts["n"] += 1
+
+            def _gen():
+                yield _make_stream_chunk(content="Here's my answer so far")
+                raise _httpx.RemoteProtocolError("peer closed connection")
+            return _gen()
+
+        mock_client = MagicMock()
+        mock_client.chat.completions.create.side_effect = _text_stall
+        mock_create.return_value = mock_client
+
+        agent = AIAgent(
+            api_key="test-key",
+            base_url="https://openrouter.ai/api/v1",
+            model="test/model",
+            quiet_mode=True,
+            skip_context_files=True,
+            skip_memory=True,
+        )
+        agent.api_mode = "chat_completions"
+        agent._interrupt_requested = False
+        agent._current_streamed_assistant_text = "Here's my answer so far"
+
+        import os as _os
+        _prev = _os.environ.get("HERMES_STREAM_RETRIES")
+        _os.environ["HERMES_STREAM_RETRIES"] = "2"
+        try:
+            response = agent._interruptible_streaming_api_call({})
+        finally:
+            if _prev is None:
+                _os.environ.pop("HERMES_STREAM_RETRIES", None)
+            else:
+                _os.environ["HERMES_STREAM_RETRIES"] = _prev
+
+        # Only one attempt: text-only stall short-circuits retry.
+        assert attempts["n"] == 1, (
+            f"Text-only stall should not silent-retry, got {attempts['n']} attempts"
+        )
+        content = response.choices[0].message.content or ""
+        assert content == "Here's my answer so far", (
+            f"Text-only stall regressed: {content!r}"
+        )
+        assert "Stream stalled" not in content, (
+            f"Text-only stall should not emit tool-call warning: {content!r}"
+        )
+

tests/run_agent/test_strip_reasoning_tags_cli.py

@@ -0,0 +1,69 @@
+"""Tests for cli.py::_strip_reasoning_tags — specifically the tool-call
+XML stripping added in openclaw/openclaw#67318 port.
+
+The CLI has its own copy of the stripper because it needs to run on the
+final displayed assistant text (after streaming) without depending on the
+AIAgent instance. It must stay in sync with run_agent.py::_strip_think_blocks
+for tool-call tag coverage."""
+
+import pytest
+
+from cli import _strip_reasoning_tags
+
+
+class TestToolCallStripping:
+    def test_tool_call_block_stripped(self):
+        text = '<tool_call>{"name": "x"}</tool_call>result'
+        result = _strip_reasoning_tags(text)
+        assert "<tool_call>" not in result
+        assert "result" in result
+
+    def test_function_calls_block_stripped(self):
+        text = '<function_calls>[{}]</function_calls>\nanswer'
+        result = _strip_reasoning_tags(text)
+        assert "<function_calls>" not in result
+        assert "answer" in result
+
+    def test_gemma_function_name_block_stripped(self):
+        text = (
+            'Reading.\n'
+            '<function name="r"><parameter name="p">/tmp/x</parameter></function>\n'
+            'Done.'
+        )
+        result = _strip_reasoning_tags(text)
+        assert '<function name="r">' not in result
+        assert "/tmp/x" not in result
+        assert "Reading." in result
+        assert "Done." in result
+
+    def test_prose_mention_of_function_preserved(self):
+        text = "Use <function> declarations in JavaScript."
+        result = _strip_reasoning_tags(text)
+        assert "JavaScript" in result
+
+    def test_reasoning_still_stripped(self):
+        """Regression: make sure existing think-tag stripping still works."""
+        text = "<think>reasoning</think> answer"
+        result = _strip_reasoning_tags(text)
+        assert "reasoning" not in result
+        assert "answer" in result
+
+    def test_mixed_reasoning_and_tool_call(self):
+        text = '<think>plan</think><tool_call>{"x":1}</tool_call>final'
+        result = _strip_reasoning_tags(text)
+        assert "plan" not in result
+        assert "<tool_call>" not in result
+        assert "final" in result
+
+    def test_stray_function_close(self):
+        text = "visible</function> tail"
+        result = _strip_reasoning_tags(text)
+        assert "</function>" not in result
+        assert "visible" in result
+        assert "tail" in result
+
+    def test_empty_string(self):
+        assert _strip_reasoning_tags("") == ""
+
+    def test_plain_text_unchanged(self):
+        assert _strip_reasoning_tags("just text") == "just text"

tests/test_cli_skin_integration.py

@@ -66,6 +66,9 @@ class TestCliSkinPromptIntegration:
         assert style_dict["prompt"] == skin.get_color("prompt")
         assert style_dict["input-rule"] == skin.get_color("input_rule")
         assert style_dict["prompt-working"] == f"{skin.get_color('banner_dim')} italic"
+        assert style_dict["status-bar"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_text')}"
+        )
         assert style_dict["approval-title"] == f"{skin.get_color('ui_warn')} bold"
 
     def test_apply_tui_skin_style_updates_running_app(self):