Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

.dockerignore

@@ -25,3 +25,7 @@ ui-tui/packages/hermes-ink/dist/
 
 # Runtime data (bind-mounted at /opt/data; must not leak into build context)
 data/
+
+# Compose/profile runtime state (bind-mounted; avoid ownership/secret issues)
+hermes-config/
+runtime/

AGENTS.md

@@ -282,7 +282,16 @@ The dashboard embeds the real `hermes --tui` — **not** a rewrite.  See `hermes
 
 ## Adding New Tools
 
-Requires changes in **2 files**:
+For most custom or local-only tools, do **not** edit Hermes core. Use the plugin
+route instead: create `~/.hermes/plugins/<name>/plugin.yaml` and
+`~/.hermes/plugins/<name>/__init__.py`, then register tools with
+`ctx.register_tool(...)`. Plugin toolsets are discovered automatically and can be
+enabled or disabled without touching `tools/` or `toolsets.py`.
+
+Use the built-in route below only when the user is explicitly contributing a new
+core Hermes tool that should ship in the base system.
+
+Built-in/core tools require changes in **2 files**:
 
 **1. Create `tools/your_tool.py`:**
 ```python

agent/anthropic_adapter.py

@@ -76,6 +76,7 @@ _ADAPTIVE_THINKING_SUBSTRINGS = ("4-6", "4.6", "4-7", "4.7")
 # Models where temperature/top_p/top_k return 400 if set to non-default values.
 # This is the Opus 4.7 contract; future 4.x+ models are expected to follow it.
 _NO_SAMPLING_PARAMS_SUBSTRINGS = ("4-7", "4.7")
+_FAST_MODE_SUPPORTED_SUBSTRINGS = ("opus-4-6", "opus-4.6")
 
 # ── Max output token limits per Anthropic model ───────────────────────
 # Source: Anthropic docs + Cline model catalog.  Anthropic's API requires
@@ -105,6 +106,9 @@ _ANTHROPIC_OUTPUT_LIMITS = {
     "claude-3-haiku":      4_096,
     # Third-party Anthropic-compatible providers
     "minimax":            131_072,
+    # Qwen models via DashScope Anthropic-compatible endpoint
+    # DashScope enforces max_tokens ∈ [1, 65536]
+    "qwen3":               65_536,
 }
 
 # For any model not in the table, assume the highest current limit.
@@ -216,6 +220,17 @@ def _forbids_sampling_params(model: str) -> bool:
     return any(v in model for v in _NO_SAMPLING_PARAMS_SUBSTRINGS)
 
 
+def _supports_fast_mode(model: str) -> bool:
+    """Return True for models that support Anthropic Fast Mode (speed=fast).
+
+    Per Anthropic docs, fast mode is currently supported on Opus 4.6 only.
+    Sending ``speed: "fast"`` to any other Claude model (including Opus 4.7)
+    returns HTTP 400. This guard prevents silently 400'ing when stale config
+    or older callers leave fast mode enabled across a model upgrade.
+    """
+    return any(v in model for v in _FAST_MODE_SUPPORTED_SUBSTRINGS)
+
+
 # Beta headers for enhanced features (sent with ALL auth types).
 # As of Opus 4.7 (2026-04-16), the first two are GA on Claude 4.6+ — the
 # beta headers are still accepted (harmless no-op) but not required. Kept
@@ -1222,6 +1237,14 @@ def _normalize_tool_input_schema(schema: Any) -> Dict[str, Any]:
     ``keep_nullable_hint=False`` because the Anthropic validator does not
     recognize the OpenAPI-style ``nullable: true`` extension and strict
     schema-to-grammar converters may reject unknown keywords.
+
+    Top-level ``oneOf``/``allOf``/``anyOf`` are also stripped here: the
+    Anthropic API rejects union keywords at the schema root with a generic
+    HTTP 400. Several upstream and plugin tools ship schemas with one of
+    these keywords at the top level (commonly for Pydantic discriminated
+    unions). If we land here with those keywords still present after
+    nullable-union stripping, drop them and fall back to a plain object
+    schema so the tool still validates at the Anthropic boundary.
     """
     if not schema:
         return {"type": "object", "properties": {}}
@@ -1231,6 +1254,12 @@ def _normalize_tool_input_schema(schema: Any) -> Dict[str, Any]:
     normalized = strip_nullable_unions(schema, keep_nullable_hint=False)
     if not isinstance(normalized, dict):
         return {"type": "object", "properties": {}}
+    # Strip top-level union keywords that Anthropic's validator rejects.
+    banned = {"oneOf", "allOf", "anyOf"}
+    if banned & normalized.keys():
+        normalized = {k: v for k, v in normalized.items() if k not in banned}
+        if "type" not in normalized:
+            normalized["type"] = "object"
     if normalized.get("type") == "object" and not isinstance(normalized.get("properties"), dict):
         normalized = {**normalized, "properties": {}}
     return normalized
@@ -1915,9 +1944,15 @@ def build_anthropic_kwargs(
 
     # ── Fast mode (Opus 4.6 only) ────────────────────────────────────
     # Adds extra_body.speed="fast" + the fast-mode beta header for ~2.5x
-    # output speed. Only for native Anthropic endpoints — third-party
-    # providers would reject the unknown beta header and speed parameter.
-    if fast_mode and not _is_third_party_anthropic_endpoint(base_url):
+    # output speed. Per Anthropic docs, fast mode is only supported on
+    # Opus 4.6 — Opus 4.7 and other models 400 on the speed parameter.
+    # Only for native Anthropic endpoints — third-party providers would
+    # reject the unknown beta header and speed parameter.
+    if (
+        fast_mode
+        and not _is_third_party_anthropic_endpoint(base_url)
+        and _supports_fast_mode(model)
+    ):
         kwargs.setdefault("extra_body", {})["speed"] = "fast"
         # Build extra_headers with ALL applicable betas (the per-request
         # extra_headers override the client-level anthropic-beta header).

agent/auxiliary_client.py

@@ -1529,7 +1529,7 @@ def _build_codex_client(model: str) -> Tuple[Optional[Any], Optional[str]]:
     return CodexAuxiliaryClient(real_client, model), model
 
 
-def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
+def _try_anthropic(explicit_api_key: str = None) -> Tuple[Optional[Any], Optional[str]]:
     try:
         from agent.anthropic_adapter import build_anthropic_client, resolve_anthropic_token
     except ImportError:
@@ -1539,10 +1539,10 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
     if pool_present:
         if entry is None:
             return None, None
-        token = _pool_runtime_api_key(entry)
+        token = explicit_api_key or _pool_runtime_api_key(entry)
     else:
         entry = None
-        token = resolve_anthropic_token()
+        token = explicit_api_key or resolve_anthropic_token()
     if not token:
         return None, None
 
@@ -2336,7 +2336,7 @@ def resolve_provider_client(
 
     if pconfig.auth_type == "api_key":
         if provider == "anthropic":
-            client, default_model = _try_anthropic()
+            client, default_model = _try_anthropic(explicit_api_key=explicit_api_key)
             if client is None:
                 logger.warning("resolve_provider_client: anthropic requested but no Anthropic credentials found")
                 return None, None
@@ -2648,8 +2648,11 @@ def resolve_vision_provider_client(
         return resolved_provider, sync_client, final_model
 
     if resolved_base_url:
+        provider_for_base_override = (
+            requested if requested and requested not in ("", "auto") else "custom"
+        )
         client, final_model = resolve_provider_client(
-            "custom",
+            provider_for_base_override,
             model=resolved_model,
             async_mode=async_mode,
             explicit_base_url=resolved_base_url,
@@ -2657,8 +2660,8 @@ def resolve_vision_provider_client(
             api_mode=resolved_api_mode,
         )
         if client is None:
-            return "custom", None, None
-        return "custom", client, final_model
+            return provider_for_base_override, None, None
+        return provider_for_base_override, client, final_model
 
     if requested == "auto":
         # Vision auto-detection order:

agent/context_compressor.py

@@ -344,6 +344,7 @@ class ContextCompressor(ContextEngine):
         self._last_aux_model_failure_model = None
         self._last_compression_savings_pct = 100.0
         self._ineffective_compression_count = 0
+        self._summary_failure_cooldown_until = 0.0  # transient errors must not block a fresh session
 
     def update_model(
         self,
@@ -553,7 +554,16 @@ class ContextCompressor(ContextEngine):
                     break
                 accumulated += msg_tokens
                 boundary = i
-            prune_boundary = max(boundary, len(result) - min_protect)
+            # Translate the budget walk into a "protected count", apply the
+            # floor in count-space (where `max` reads naturally: protect at
+            # least `min_protect` messages or whatever the budget reserved,
+            # whichever is more), then convert back to a prune boundary.
+            # Doing this in index-space with `max` would invert the direction
+            # (smaller index = MORE protected), so a generous budget would
+            # silently get truncated back down to `min_protect`.
+            budget_protect_count = len(result) - boundary
+            protected_count = max(budget_protect_count, min_protect)
+            prune_boundary = len(result) - protected_count
         else:
             prune_boundary = len(result) - protect_tail_count
 
@@ -569,6 +579,8 @@ class ContextCompressor(ContextEngine):
             # Skip multimodal content (list of content blocks)
             if isinstance(content, list):
                 continue
+            if not isinstance(content, str):
+                continue
             if len(content) < 200:
                 continue
             h = hashlib.md5(content.encode("utf-8", errors="replace")).hexdigest()[:12]
@@ -588,6 +600,8 @@ class ContextCompressor(ContextEngine):
             # Skip multimodal content (list of content blocks)
             if isinstance(content, list):
                 continue
+            if not isinstance(content, str):
+                continue
             if not content or content == _PRUNED_TOOL_PLACEHOLDER:
                 continue
             # Skip already-deduplicated or previously-summarized results
@@ -903,15 +917,19 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                 or "does not exist" in _err_str
                 or "no available channel" in _err_str
             )
+            _is_timeout = (
+                _status in (408, 429, 502, 504)
+                or "timeout" in _err_str
+            )
             if (
-                _is_model_not_found
+                (_is_model_not_found or _is_timeout)
                 and self.summary_model
                 and self.summary_model != self.model
                 and not getattr(self, "_summary_model_fallen_back", False)
             ):
                 self._summary_model_fallen_back = True
                 logging.warning(
-                    "Summary model '%s' not available (%s). "
+                    "Summary model '%s' unavailable (%s). "
                     "Falling back to main model '%s' for compression.",
                     self.summary_model, e, self.model,
                 )

agent/curator.py

@@ -24,11 +24,12 @@ from __future__ import annotations
 import json
 import logging
 import os
+import re
 import tempfile
 import threading
 from datetime import datetime, timedelta, timezone
 from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional, Set
+from typing import Any, Callable, Dict, List, NamedTuple, Optional, Set
 
 from hermes_constants import get_hermes_home
 from tools import skill_usage
@@ -36,6 +37,22 @@ from tools import skill_usage
 logger = logging.getLogger(__name__)
 
 
+def _strip_aux_credential(value: Any) -> Optional[str]:
+    if value is None:
+        return None
+    text = str(value).strip()
+    return text or None
+
+
+class _ReviewRuntimeBinding(NamedTuple):
+    """Provider/model for the curator review fork plus optional per-slot overrides."""
+
+    provider: str
+    model: str
+    explicit_api_key: Optional[str]
+    explicit_base_url: Optional[str]
+
+
 DEFAULT_INTERVAL_HOURS = 24 * 7  # 7 days
 DEFAULT_MIN_IDLE_HOURS = 2
 DEFAULT_STALE_AFTER_DAYS = 30
@@ -453,6 +470,24 @@ def _reports_root() -> Path:
     return root
 
 
+def _needle_in_path_component(needle: str, path: str) -> bool:
+    """Check if *needle* is a complete filename stem or directory name in *path*.
+
+    Unlike simple substring matching, this avoids false positives where short
+    skill names are embedded in longer filenames (e.g. "api" matching
+    "references/api-design.md").  Hyphens and underscores are normalised so
+    "open-webui-setup" matches "open_webui_setup.md".
+    """
+    norm_needle = needle.replace("-", "_")
+    for part in path.replace("\\", "/").split("/"):
+        if not part:
+            continue
+        stem = part.rsplit(".", 1)[0] if "." in part else part
+        if stem.replace("-", "_") == norm_needle:
+            return True
+    return False
+
+
 def _classify_removed_skills(
     removed: List[str],
     added: List[str],
@@ -531,15 +566,29 @@ def _classify_removed_skills(
                 continue
 
             # Look for the removed skill's name in file_path / content / raw.
-            haystacks: List[str] = []
+            # Matching strategy differs by field type:
+            #   file_path — needle must be a complete path component
+            #     (filename stem or directory name), so "api" does NOT
+            #     falsely match "references/api-design.md".
+            #   content fields — word-boundary regex so "test" does NOT
+            #     falsely match "latest" or "testing".
+            haystacks: List[tuple[str, str]] = []
             for key in ("file_path", "file_content", "content", "new_string", "_raw"):
                 v = args.get(key)
                 if isinstance(v, str):
-                    haystacks.append(v)
+                    haystacks.append((key, v))
             hit = False
-            for hay in haystacks:
+            for key, hay in haystacks:
                 for needle in needles:
-                    if needle and needle in hay:
+                    if not needle:
+                        continue
+                    if key == "file_path":
+                        matched = _needle_in_path_component(needle, hay)
+                    else:
+                        matched = bool(
+                            re.search(rf'\b{re.escape(needle)}\b', hay)
+                        )
+                    if matched:
                         hit = True
                         evidence = (
                             f"skill_manage action={args.get('action', '?')} "
@@ -1398,6 +1447,52 @@ def run_curator_review(
     }
 
 
+def _resolve_review_runtime(cfg: Dict[str, Any]) -> _ReviewRuntimeBinding:
+    """Resolve provider/model and per-slot credentials for the curator review fork.
+
+    Same precedence as `_resolve_review_model()`. Non-empty ``api_key`` /
+    ``base_url`` from the active slot are returned as explicit overrides so
+    ``resolve_runtime_provider`` does not silently reuse the main chat
+    credential chain for a routed auxiliary model.
+    """
+    _main = cfg.get("model", {}) if isinstance(cfg.get("model"), dict) else {}
+    _main_provider = _main.get("provider") or "auto"
+    _main_model = _main.get("default") or _main.get("model") or ""
+
+    # 1. Canonical aux task slot
+    _aux = cfg.get("auxiliary", {}) if isinstance(cfg.get("auxiliary"), dict) else {}
+    _cur_task = _aux.get("curator", {}) if isinstance(_aux.get("curator"), dict) else {}
+    _task_provider = (_cur_task.get("provider") or "").strip() or None
+    _task_model = (_cur_task.get("model") or "").strip() or None
+    if _task_provider and _task_provider != "auto" and _task_model:
+        return _ReviewRuntimeBinding(
+            _task_provider,
+            _task_model,
+            _strip_aux_credential(_cur_task.get("api_key")),
+            _strip_aux_credential(_cur_task.get("base_url")),
+        )
+
+    # 2. Legacy curator.auxiliary.{provider,model} (deprecated, pre-unification)
+    _cur = cfg.get("curator", {}) if isinstance(cfg.get("curator"), dict) else {}
+    _legacy = _cur.get("auxiliary", {}) if isinstance(_cur.get("auxiliary"), dict) else {}
+    _legacy_provider = _legacy.get("provider") or None
+    _legacy_model = _legacy.get("model") or None
+    if _legacy_provider and _legacy_model:
+        logger.info(
+            "curator: using deprecated curator.auxiliary.{provider,model} "
+            "config — please migrate to auxiliary.curator.{provider,model}"
+        )
+        return _ReviewRuntimeBinding(
+            str(_legacy_provider),
+            str(_legacy_model),
+            _strip_aux_credential(_legacy.get("api_key")),
+            _strip_aux_credential(_legacy.get("base_url")),
+        )
+
+    # 3. Fall through to the main chat model
+    return _ReviewRuntimeBinding(_main_provider, _main_model, None, None)
+
+
 def _resolve_review_model(cfg: Dict[str, Any]) -> tuple[str, str]:
     """Pick (provider, model) for the curator review fork.
 
@@ -1413,32 +1508,8 @@ def _resolve_review_model(cfg: Dict[str, Any]) -> tuple[str, str]:
       2. Legacy ``curator.auxiliary.{provider,model}`` when both are set
       3. Main ``model.{provider,default/model}`` pair
     """
-    _main = cfg.get("model", {}) if isinstance(cfg.get("model"), dict) else {}
-    _main_provider = _main.get("provider") or "auto"
-    _main_model = _main.get("default") or _main.get("model") or ""
-
-    # 1. Canonical aux task slot
-    _aux = cfg.get("auxiliary", {}) if isinstance(cfg.get("auxiliary"), dict) else {}
-    _cur_task = _aux.get("curator", {}) if isinstance(_aux.get("curator"), dict) else {}
-    _task_provider = (_cur_task.get("provider") or "").strip() or None
-    _task_model = (_cur_task.get("model") or "").strip() or None
-    if _task_provider and _task_provider != "auto" and _task_model:
-        return _task_provider, _task_model
-
-    # 2. Legacy curator.auxiliary.{provider,model} (deprecated, pre-unification)
-    _cur = cfg.get("curator", {}) if isinstance(cfg.get("curator"), dict) else {}
-    _legacy = _cur.get("auxiliary", {}) if isinstance(_cur.get("auxiliary"), dict) else {}
-    _legacy_provider = _legacy.get("provider") or None
-    _legacy_model = _legacy.get("model") or None
-    if _legacy_provider and _legacy_model:
-        logger.info(
-            "curator: using deprecated curator.auxiliary.{provider,model} "
-            "config — please migrate to auxiliary.curator.{provider,model}"
-        )
-        return _legacy_provider, _legacy_model
-
-    # 3. Fall through to the main chat model
-    return _main_provider, _main_model
+    b = _resolve_review_runtime(cfg)
+    return b.provider, b.model
 
 
 def _run_llm_review(prompt: str) -> Dict[str, Any]:
@@ -1477,10 +1548,10 @@ def _run_llm_review(prompt: str) -> Dict[str, Any]:
     # arguments hits an auto-resolution path that fails for OAuth-only
     # providers and for pool-backed credentials.
     #
-    # `_resolve_review_model()` honors `auxiliary.curator.{provider,model}`
+    # `_resolve_review_runtime()` honors `auxiliary.curator.{provider,model,...}`
     # (canonical aux-task slot, wired through `hermes model` → auxiliary
     # picker and the dashboard Models tab), with a legacy fallback to
-    # `curator.auxiliary.{provider,model}`. See docs/user-guide/features/curator.md.
+    # `curator.auxiliary.{provider,model,...}`. See docs/user-guide/features/curator.md.
     _api_key = None
     _base_url = None
     _api_mode = None
@@ -1490,9 +1561,13 @@ def _run_llm_review(prompt: str) -> Dict[str, Any]:
         from hermes_cli.config import load_config
         from hermes_cli.runtime_provider import resolve_runtime_provider
         _cfg = load_config()
-        _provider, _model_name = _resolve_review_model(_cfg)
+        _binding = _resolve_review_runtime(_cfg)
+        _provider, _model_name = _binding.provider, _binding.model
         _rp = resolve_runtime_provider(
-            requested=_provider, target_model=_model_name
+            requested=_provider,
+            target_model=_model_name,
+            explicit_api_key=_binding.explicit_api_key,
+            explicit_base_url=_binding.explicit_base_url,
         )
         _api_key = _rp.get("api_key")
         _base_url = _rp.get("base_url")

agent/error_classifier.py

@@ -520,7 +520,12 @@ def classify_api_error(
 
     is_disconnect = any(p in error_msg for p in _SERVER_DISCONNECT_PATTERNS)
     if is_disconnect and not status_code:
-        is_large = approx_tokens > context_length * 0.6 or approx_tokens > 120000 or num_messages > 200
+        # Absolute token/message-count thresholds are only a proxy for smaller
+        # context windows.  Large-context sessions can have hundreds of
+        # messages while still being far below their actual token budget.
+        is_large = approx_tokens > context_length * 0.6 or (
+            context_length <= 256000 and (approx_tokens > 120000 or num_messages > 200)
+        )
         if is_large:
             return _result(
                 FailoverReason.context_overflow,
@@ -766,7 +771,12 @@ def _classify_400(
         if not err_body_msg:
             err_body_msg = str(body.get("message") or "").strip().lower()
     is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
-    is_large = approx_tokens > context_length * 0.4 or approx_tokens > 80000 or num_messages > 80
+    # Absolute token/message-count thresholds are only a proxy for smaller
+    # context windows.  Large-context sessions can have many messages while
+    # still being far below their actual token budget.
+    is_large = approx_tokens > context_length * 0.4 or (
+        context_length <= 256000 and (approx_tokens > 80000 or num_messages > 80)
+    )
 
     if is_generic and is_large:
         return result_fn(

agent/gemini_native_adapter.py

@@ -679,7 +679,21 @@ def translate_stream_event(event: Dict[str, Any], model: str, tool_call_indices:
     finish_reason_raw = str(cand.get("finishReason") or "")
     if finish_reason_raw:
         mapped = "tool_calls" if tool_call_indices else _map_gemini_finish_reason(finish_reason_raw)
-        chunks.append(_make_stream_chunk(model=model, finish_reason=mapped))
+        finish_chunk = _make_stream_chunk(model=model, finish_reason=mapped)
+        # Attach usage from this event's usageMetadata so the streaming
+        # loop in run_agent.py can record token counts (mirrors the
+        # non-streaming path in translate_gemini_response).
+        usage_meta = event.get("usageMetadata") or {}
+        if usage_meta:
+            finish_chunk.usage = SimpleNamespace(
+                prompt_tokens=int(usage_meta.get("promptTokenCount") or 0),
+                completion_tokens=int(usage_meta.get("candidatesTokenCount") or 0),
+                total_tokens=int(usage_meta.get("totalTokenCount") or 0),
+                prompt_tokens_details=SimpleNamespace(
+                    cached_tokens=int(usage_meta.get("cachedContentTokenCount") or 0),
+                ),
+            )
+        chunks.append(finish_chunk)
     return chunks
 
 

agent/google_oauth.py

@@ -489,16 +489,29 @@ def save_credentials(creds: GoogleCredentials) -> Path:
     """Atomically write creds to disk with 0o600 permissions."""
     path = _credentials_path()
     path.parent.mkdir(parents=True, exist_ok=True)
+    # Tighten parent dir to 0o700 so siblings can't traverse to the creds file.
+    # On Windows this is a no-op (POSIX mode bits aren't enforced); ignore failures.
+    try:
+        os.chmod(path.parent, 0o700)
+    except OSError:
+        pass
     payload = json.dumps(creds.to_dict(), indent=2, sort_keys=True) + "\n"
 
     with _credentials_lock():
         tmp_path = path.with_suffix(f".tmp.{os.getpid()}.{secrets.token_hex(4)}")
         try:
-            with open(tmp_path, "w", encoding="utf-8") as fh:
+            # Create with 0o600 atomically to close the TOCTOU window where the
+            # default umask (often 0o644) would briefly expose tokens to other
+            # local users between open() and chmod().
+            fd = os.open(
+                str(tmp_path),
+                os.O_WRONLY | os.O_CREAT | os.O_EXCL,
+                stat.S_IRUSR | stat.S_IWUSR,
+            )
+            with os.fdopen(fd, "w", encoding="utf-8") as fh:
                 fh.write(payload)
                 fh.flush()
                 os.fsync(fh.fileno())
-            os.chmod(tmp_path, stat.S_IRUSR | stat.S_IWUSR)
             atomic_replace(tmp_path, path)
         finally:
             try:

agent/prompt_builder.py

@@ -183,8 +183,8 @@ SKILLS_GUIDANCE = (
 )
 
 KANBAN_GUIDANCE = (
-    "# You are a Kanban worker\n"
-    "You were spawned by the Hermes Kanban dispatcher to execute ONE task from "
+    "# Kanban task execution protocol\n"
+    "You have been assigned ONE task from "
     "the shared board at `~/.hermes/kanban.db`. Your task id is in "
     "`$HERMES_KANBAN_TASK`; your workspace is `$HERMES_KANBAN_WORKSPACE`. "
     "The `kanban_*` tools in your schema are your primary coordination surface — "

agent/redact.py

@@ -305,13 +305,18 @@ def _redact_form_body(text: str) -> str:
     return _redact_query_string(text.strip())
 
 
-def redact_sensitive_text(text: str, *, force: bool = False) -> str:
+def redact_sensitive_text(text: str, *, force: bool = False, code_file: bool = False) -> str:
     """Apply all redaction patterns to a block of text.
 
     Safe to call on any string -- non-matching text passes through unchanged.
     Disabled by default — enable via security.redact_secrets: true in config.yaml.
     Set force=True for safety boundaries that must never return raw secrets
     regardless of the user's global logging redaction preference.
+
+    Set code_file=True to skip the ENV-assignment and JSON-field regex
+    patterns when the text is known to be source code (e.g. MAX_TOKENS=***
+    constants, "apiKey": "test" fixtures). Prefix patterns, auth headers,
+    private keys, DB connstrings, JWTs, and URL secrets are still redacted.
     """
     if text is None:
         return None
@@ -325,17 +330,18 @@ def redact_sensitive_text(text: str, *, force: bool = False) -> str:
     # Known prefixes (sk-, ghp_, etc.)
     text = _PREFIX_RE.sub(lambda m: _mask_token(m.group(1)), text)
 
-    # ENV assignments: OPENAI_API_KEY=sk-abc...
-    def _redact_env(m):
-        name, quote, value = m.group(1), m.group(2), m.group(3)
-        return f"{name}={quote}{_mask_token(value)}{quote}"
-    text = _ENV_ASSIGN_RE.sub(_redact_env, text)
+    # ENV assignments: OPENAI_API_KEY=***  (skip for code files — false positives)
+    if not code_file:
+        def _redact_env(m):
+            name, quote, value = m.group(1), m.group(2), m.group(3)
+            return f"{name}={quote}{_mask_token(value)}{quote}"
+        text = _ENV_ASSIGN_RE.sub(_redact_env, text)
 
-    # JSON fields: "apiKey": "value"
-    def _redact_json(m):
-        key, value = m.group(1), m.group(2)
-        return f'{key}: "{_mask_token(value)}"'
-    text = _JSON_FIELD_RE.sub(_redact_json, text)
+        # JSON fields: "apiKey": "***"  (skip for code files — false positives)
+        def _redact_json(m):
+            key, value = m.group(1), m.group(2)
+            return f'{key}: "{_mask_token(value)}"'
+        text = _JSON_FIELD_RE.sub(_redact_json, text)
 
     # Authorization headers
     text = _AUTH_HEADER_RE.sub(

agent/transports/codex.py

@@ -143,7 +143,18 @@ class ResponsesApiTransport(ProviderTransport):
             kwargs["max_output_tokens"] = max_tokens
 
         if is_xai_responses and session_id:
-            kwargs["extra_headers"] = {"x-grok-conv-id": session_id}
+            existing_extra_headers = kwargs.get("extra_headers")
+            merged_extra_headers: Dict[str, str] = {}
+            if isinstance(existing_extra_headers, dict):
+                merged_extra_headers.update(
+                    {
+                        str(key): str(value)
+                        for key, value in existing_extra_headers.items()
+                        if key and value is not None
+                    }
+                )
+            merged_extra_headers["x-grok-conv-id"] = session_id
+            kwargs["extra_headers"] = merged_extra_headers
 
         return kwargs
 

apps/dashboard/src/App.tsx

@@ -80,6 +80,14 @@ function RootRedirect() {
   return <Navigate to="/sessions" replace />;
 }
 
+function UnknownRouteFallback({ pluginsLoading }: { pluginsLoading: boolean }) {
+  if (pluginsLoading) {
+    // Render nothing during the plugin-load window — a spinner here would just flash.
+    return null;
+  }
+  return <Navigate to="/sessions" replace />;
+}
+
 const CHAT_NAV_ITEM: NavItem = {
   path: "/chat",
   labelKey: "chat",
@@ -582,7 +590,9 @@ export default function App() {
                   ))}
                   <Route
                     path="*"
-                    element={<Navigate to="/sessions" replace />}
+                    element={
+                      <UnknownRouteFallback pluginsLoading={pluginsLoading} />
+                    }
                   />
                 </Routes>
 

apps/dashboard/src/components/ThemeSwitcher.tsx

@@ -4,6 +4,7 @@ import { Button } from "@nous-research/ui/ui/components/button";
 import { ListItem } from "@nous-research/ui/ui/components/list-item";
 import { Typography } from "@/components/NouiTypography";
 import { BUILTIN_THEMES, useTheme } from "@/themes";
+import type { DashboardTheme } from "@/themes";
 import { useI18n } from "@/i18n";
 import { cn } from "@/lib/utils";
 
@@ -11,8 +12,8 @@ import { cn } from "@/lib/utils";
  * Compact theme picker mounted next to the language switcher in the header.
  * Each dropdown row shows a 3-stop swatch (background / midground / warm
  * glow) so users can preview the palette before committing. User-defined
- * themes from `~/.hermes/dashboard-themes/*.yaml` that aren't in
- * `BUILTIN_THEMES` render without swatches and apply the default palette.
+ * themes from `~/.hermes/dashboard-themes/*.yaml` use their API-provided
+ * definitions so they show real palette swatches just like built-ins.
  *
  * When placed at the bottom of a container (e.g. the sidebar rail), pass
  * `dropUp` so the menu opens above the trigger instead of clipping below
@@ -95,7 +96,7 @@ export function ThemeSwitcher({ dropUp = false }: ThemeSwitcherProps) {
 
           {availableThemes.map((th) => {
             const isActive = th.name === themeName;
-            const preset = BUILTIN_THEMES[th.name];
+            const paletteTheme = BUILTIN_THEMES[th.name] ?? th.definition;
 
             return (
               <ListItem
@@ -109,8 +110,8 @@ export function ThemeSwitcher({ dropUp = false }: ThemeSwitcherProps) {
                 }}
                 className="gap-3"
               >
-                {preset ? (
-                  <ThemeSwatch theme={preset.name} />
+                {paletteTheme ? (
+                  <ThemeSwatch theme={paletteTheme} />
                 ) : (
                   <PlaceholderSwatch />
                 )}
@@ -144,10 +145,8 @@ export function ThemeSwitcher({ dropUp = false }: ThemeSwitcherProps) {
   );
 }
 
-function ThemeSwatch({ theme }: { theme: string }) {
-  const preset = BUILTIN_THEMES[theme];
-  if (!preset) return <PlaceholderSwatch />;
-  const { background, midground, warmGlow } = preset.palette;
+function ThemeSwatch({ theme }: { theme: DashboardTheme }) {
+  const { background, midground, warmGlow } = theme.palette;
   return (
     <div
       aria-hidden

apps/dashboard/src/pages/ConfigPage.tsx

@@ -27,6 +27,15 @@ import {
   Wrench,
   FileQuestion,
   Filter,
+  Cloud,
+  Sparkles,
+  LayoutDashboard,
+  BookOpen,
+  Route,
+  History,
+  Shield,
+  FileOutput,
+  RefreshCw,
 } from "lucide-react";
 import { api } from "@/lib/api";
 import { getNestedValue, setNestedValue } from "@/lib/nested";
@@ -66,6 +75,15 @@ const CATEGORY_ICONS: Record<
   logging: ClipboardList,
   discord: MessageCircle,
   auxiliary: Wrench,
+  bedrock: Cloud,
+  curator: Sparkles,
+  kanban: LayoutDashboard,
+  model_catalog: BookOpen,
+  openrouter: Route,
+  sessions: History,
+  tool_loop_guardrails: Shield,
+  tool_output: FileOutput,
+  updates: RefreshCw,
 };
 
 function CategoryIcon({

apps/dashboard/src/themes/context.tsx

@@ -311,9 +311,7 @@ export function ThemeProvider({ children }: { children: ReactNode }) {
 
   /** All selectable themes (shown in the picker). Starts with just the
    *  built-ins; the API call below merges in user themes. */
-  const [availableThemes, setAvailableThemes] = useState<
-    Array<{ description: string; label: string; name: string }>
-  >(() =>
+  const [availableThemes, setAvailableThemes] = useState<ThemeSummary[]>(() =>
     Object.values(BUILTIN_THEMES).map((t) => ({
       name: t.name,
       label: t.label,
@@ -360,6 +358,7 @@ export function ThemeProvider({ children }: { children: ReactNode }) {
               name: t.name,
               label: t.label,
               description: t.description,
+              definition: t.definition,
             })),
           );
           // Index any definitions the server shipped (user themes).
@@ -430,8 +429,15 @@ const ThemeContext = createContext<ThemeContextValue>({
 });
 
 interface ThemeContextValue {
-  availableThemes: Array<{ description: string; label: string; name: string }>;
+  availableThemes: ThemeSummary[];
   setTheme: (name: string) => void;
   theme: DashboardTheme;
   themeName: string;
 }
+
+interface ThemeSummary {
+  description: string;
+  label: string;
+  name: string;
+  definition?: DashboardTheme;
+}

cli.py

@@ -459,32 +459,19 @@ def load_cli_config() -> Dict[str, Any]:
     if "backend" in terminal_config:
         terminal_config["env_type"] = terminal_config["backend"]
     
-    # Handle special cwd values: "." or "auto" means use current working directory.
-    # Only resolve to the host's CWD for the local backend where the host
-    # filesystem is directly accessible.  For ALL remote/container backends
-    # (ssh, docker, modal, singularity), the host path doesn't exist on the
-    # target -- remove the key so terminal_tool.py uses its per-backend default.
-    #
-    # GUARD: If TERMINAL_CWD is already set to a real absolute path (by the
-    # gateway's config bridge earlier in the process), don't clobber it.
-    # This prevents a lazy import of cli.py during gateway runtime from
-    # rewriting TERMINAL_CWD to the service's working directory.
-    # See issue #10817.
+    # CWD resolution for CLI/TUI. The gateway has its own config bridge in
+    # gateway/run.py but may lazily import cli.py (triggering this code).
+    # Local backend: always os.getcwd(). Use `cd /dir && hermes` to control it.
+    # Non-local with placeholder: pop so terminal_tool uses its per-backend default.
+    # Non-local with explicit path: keep as-is.
     _CWD_PLACEHOLDERS = (".", "auto", "cwd")
-    if terminal_config.get("cwd") in _CWD_PLACEHOLDERS:
-        _existing_cwd = os.environ.get("TERMINAL_CWD", "")
-        if _existing_cwd and _existing_cwd not in _CWD_PLACEHOLDERS and os.path.isabs(_existing_cwd):
-            # Gateway (or earlier startup) already resolved a real path — keep it
-            terminal_config["cwd"] = _existing_cwd
-            defaults["terminal"]["cwd"] = _existing_cwd
-        else:
-            effective_backend = terminal_config.get("env_type", "local")
-            if effective_backend == "local":
-                terminal_config["cwd"] = os.getcwd()
-                defaults["terminal"]["cwd"] = terminal_config["cwd"]
-            else:
-                # Remove so TERMINAL_CWD stays unset → tool picks backend default
-                terminal_config.pop("cwd", None)
+    effective_backend = terminal_config.get("env_type", "local")
+
+    if effective_backend == "local":
+        terminal_config["cwd"] = os.getcwd()
+        defaults["terminal"]["cwd"] = terminal_config["cwd"]
+    elif terminal_config.get("cwd") in _CWD_PLACEHOLDERS:
+        terminal_config.pop("cwd", None)
     
     env_mappings = {
         "env_type": "TERMINAL_ENV",
@@ -517,13 +504,18 @@ def load_cli_config() -> Dict[str, Any]:
         "sudo_password": "SUDO_PASSWORD",
     }
     
-    # Apply config values to env vars so terminal_tool picks them up.
-    # If the config file explicitly has a [terminal] section, those values are
-    # authoritative and override any .env settings.  When using defaults only
-    # (no config file or no terminal section), don't overwrite env vars that
-    # were already set by .env -- the user's .env is the fallback source.
+    # Bridge config → env vars for terminal_tool. TERMINAL_CWD is force-exported
+    # UNLESS we're inside a gateway process (detected by _HERMES_GATEWAY marker)
+    # where it was already set correctly by gateway/run.py's config bridge.
+    _is_gateway = os.environ.get("_HERMES_GATEWAY") == "1"
     for config_key, env_var in env_mappings.items():
         if config_key in terminal_config:
+            if env_var == "TERMINAL_CWD":
+                if _is_gateway:
+                    continue
+                # CLI: always export (overrides stale .env or inherited values)
+                os.environ[env_var] = str(terminal_config[config_key])
+                continue
             if _file_has_terminal_config or env_var not in os.environ:
                 val = terminal_config[config_key]
                 if isinstance(val, list):
@@ -1234,6 +1226,28 @@ def _strip_markdown_syntax(text: str) -> str:
     return plain.strip("\n")
 
 
+_WINDOWS_PATH_WITH_DOT_SEGMENT_RE = re.compile(
+    r"(?i)(?:\b[a-z]:\\|\\\\)[^\s`]*\\\.[^\s`]*"
+)
+
+
+def _preserve_windows_dot_segments_for_markdown(text: str) -> str:
+    r"""Keep Windows path separators before hidden directories in Markdown.
+
+    CommonMark treats ``\.`` as an escaped literal dot, so Rich Markdown would
+    render ``D:\repo\.ai`` as ``D:\repo.ai``.  Doubling only that separator
+    inside Windows path-looking tokens preserves the path without changing
+    ordinary markdown escapes like ``1\. not a list``.
+    """
+    if "\\." not in text:
+        return text
+
+    def _protect(match: re.Match[str]) -> str:
+        return re.sub(r"(?<!\\)\\(?=\.)", r"\\\\", match.group(0))
+
+    return _WINDOWS_PATH_WITH_DOT_SEGMENT_RE.sub(_protect, text)
+
+
 def _render_final_assistant_content(text: str, mode: str = "render"):
     """Render final assistant content as markdown, stripped text, or raw text."""
     from rich.markdown import Markdown
@@ -1245,6 +1259,7 @@ def _render_final_assistant_content(text: str, mode: str = "render"):
         return _rich_text_from_ansi(text or "")
 
     plain = _rich_text_from_ansi(text or "").plain
+    plain = _preserve_windows_dot_segments_for_markdown(plain)
     return Markdown(plain)
 
 
@@ -1513,6 +1528,10 @@ def _detect_file_drop(user_input: str) -> "dict | None":
         or stripped.startswith('"~')
         or stripped.startswith("'/")
         or stripped.startswith("'~")
+        or stripped.startswith('"./')
+        or stripped.startswith('"../')
+        or stripped.startswith("'./")
+        or stripped.startswith("'../")
         or (len(stripped) >= 4 and stripped[0] in ("'", '"') and stripped[2] == ":" and stripped[3] in ("\\", "/") and stripped[1].isalpha())
     )
     if not starts_like_path:
@@ -4936,7 +4955,7 @@ class HermesCLI:
         except Exception:
             pass
 
-    def new_session(self, silent=False):
+    def new_session(self, silent=False, title=None):
         """Start a fresh session with a new session ID and cleared agent state."""
         if self.agent and self.conversation_history:
             # Trigger memory extraction on the old session before session_id rotates.
@@ -4991,6 +5010,28 @@ class HermesCLI:
                     self.agent._session_db_created = True
                 except Exception:
                     pass
+                if title and self._session_db:
+                    from hermes_state import SessionDB
+                    try:
+                        sanitized = SessionDB.sanitize_title(title)
+                    except ValueError as e:
+                        _cprint(f"  Title rejected: {e}")
+                        sanitized = None
+                        title = None
+                    if sanitized:
+                        try:
+                            self._session_db.set_session_title(self.session_id, sanitized)
+                            self._pending_title = None
+                            title = sanitized
+                        except ValueError as e:
+                            _cprint(f"  {e} — session started untitled.")
+                            title = None
+                        except Exception:
+                            title = None
+                    elif title is not None:
+                        # sanitize_title returned empty (whitespace-only / unprintable)
+                        _cprint("  Title is empty after cleanup — session started untitled.")
+                        title = None
             # Notify memory providers that session_id rotated to a fresh
             # conversation. reset=True signals providers to flush accumulated
             # per-session state (_session_turns, _turn_counter, _document_id).
@@ -5010,7 +5051,10 @@ class HermesCLI:
             self._notify_session_boundary("on_session_reset")
 
         if not silent:
-            print("(^_^)v New session started!")
+            if title:
+                print(f"(^_^)v New session started: {title}")
+            else:
+                print("(^_^)v New session started!")
 
     def _handle_resume_command(self, cmd_original: str) -> None:
         """Handle /resume <session_id_or_title> — switch to a previous session mid-conversation."""
@@ -6286,7 +6330,7 @@ class HermesCLI:
         _cmd_def = _resolve_cmd(_base_word)
         canonical = _cmd_def.name if _cmd_def else _base_word
         
-        if canonical in ("quit", "exit", "q"):
+        if canonical in ("quit", "exit"):
             return False
         elif canonical == "help":
             self.show_help()
@@ -6422,7 +6466,9 @@ class HermesCLI:
                 else:
                     _cprint("  Session database not available.")
         elif canonical == "new":
-            self.new_session()
+            parts = cmd_original.split(maxsplit=1)
+            title = parts[1].strip() if len(parts) > 1 else None
+            self.new_session(title=title)
         elif canonical == "resume":
             self._handle_resume_command(cmd_original)
         elif canonical == "model":
@@ -8383,6 +8429,17 @@ class HermesCLI:
                         _cprint(f"{_DIM}Voice auto-restart failed: {e}{_RST}")
                 threading.Thread(target=_restart_recording, daemon=True).start()
 
+    def _voice_speak_response_async(self, text: str) -> None:
+        """Schedule TTS and mark it pending before continuous recording can restart."""
+        if not self._voice_tts or not text:
+            return
+        self._voice_tts_done.clear()
+        threading.Thread(
+            target=self._voice_speak_response,
+            args=(text,),
+            daemon=True,
+        ).start()
+
     def _voice_speak_response(self, text: str):
         """Speak the agent's response aloud using TTS (runs in background thread)."""
         if not self._voice_tts:
@@ -9543,11 +9600,7 @@ class HermesCLI:
             # Speak response aloud if voice TTS is enabled
             # Skip batch TTS when streaming TTS already handled it
             if self._voice_tts and response and not use_streaming_tts:
-                threading.Thread(
-                    target=self._voice_speak_response,
-                    args=(response,),
-                    daemon=True,
-                ).start()
+                self._voice_speak_response_async(response)
 
 
             # Re-queue the interrupt message (and any that arrived while we were

cron/jobs.py

@@ -797,19 +797,36 @@ def get_due_jobs() -> List[Dict[str, Any]]:
 
         next_run = job.get("next_run_at")
         if not next_run:
+            schedule = job.get("schedule", {})
+            kind = schedule.get("kind")
+
+            # One-shot jobs use a small grace window via the dedicated helper.
             recovered_next = _recoverable_oneshot_run_at(
-                job.get("schedule", {}),
+                schedule,
                 now,
                 last_run_at=job.get("last_run_at"),
             )
+            recovery_kind = "one-shot" if recovered_next else None
+
+            # Recurring jobs reach here only when something — typically a
+            # direct jobs.json edit that bypassed add_job() — left
+            # next_run_at unset.  Without this branch, such jobs are
+            # silently skipped forever; recompute next_run_at from the
+            # schedule so they pick up at their next scheduled tick.
+            if not recovered_next and kind in ("cron", "interval"):
+                recovered_next = compute_next_run(schedule, now.isoformat())
+                if recovered_next:
+                    recovery_kind = kind
+
             if not recovered_next:
                 continue
 
             job["next_run_at"] = recovered_next
             next_run = recovered_next
             logger.info(
-                "Job '%s' had no next_run_at; recovering one-shot run at %s",
+                "Job '%s' had no next_run_at; recovering %s run at %s",
                 job.get("name", job["id"]),
+                recovery_kind,
                 recovered_next,
             )
             for rj in raw_jobs:

cron/scheduler.py

@@ -417,7 +417,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
         thread_id = target.get("thread_id")
 
         # Diagnostic: log thread_id for topic-aware delivery debugging
-        origin = job.get("origin") or {}
+        origin = _resolve_origin(job) or {}
         origin_thread = origin.get("thread_id")
         if origin_thread and not thread_id:
             logger.warning(
@@ -706,10 +706,8 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
                     f"{prompt}"
                 )
             else:
-                prompt = (
-                    "[Script ran successfully but produced no output.]\n\n"
-                    f"{prompt}"
-                )
+                # Script produced no output — nothing to report, skip AI call.
+                return None
         else:
             prompt = (
                 "## Script Error\n"
@@ -782,6 +780,7 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
         return prompt
 
     from tools.skills_tool import skill_view
+    from tools.skill_usage import bump_use
 
     parts = []
     skipped: list[str] = []
@@ -793,6 +792,12 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
             skipped.append(skill_name)
             continue
 
+        # Bump usage so the curator sees this skill as actively used.
+        try:
+            bump_use(skill_name)
+        except Exception:
+            logger.debug("Cron job: failed to bump skill usage for '%s'", skill_name, exc_info=True)
+
         content = str(loaded.get("content") or "").strip()
         if parts:
             parts.append("")
@@ -862,6 +867,9 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             return True, silent_doc, SILENT_MARKER, None
 
     prompt = _build_job_prompt(job, prerun_script=prerun_script)
+    if prompt is None:
+        logger.info("Job '%s': script produced no output, skipping AI call.", job_name)
+        return True, "", SILENT_MARKER, None
     origin = _resolve_origin(job)
     _cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
 
@@ -997,8 +1005,13 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         )
         from hermes_cli.auth import AuthError
         try:
+            # Do not inject HERMES_INFERENCE_PROVIDER here. resolve_runtime_provider()
+            # already prefers persisted config over stale shell/env overrides when
+            # no explicit provider is requested. Passing the env var here short-
+            # circuits that precedence and can resurrect old providers (for
+            # example DeepSeek) for cron jobs that do not pin provider/model.
             runtime_kwargs = {
-                "requested": job.get("provider") or os.getenv("HERMES_INFERENCE_PROVIDER"),
+                "requested": job.get("provider"),
             }
             if job.get("base_url"):
                 runtime_kwargs["explicit_base_url"] = job.get("base_url")

docker/entrypoint.sh

@@ -86,6 +86,41 @@ if [ -d "$INSTALL_DIR/skills" ]; then
     python3 "$INSTALL_DIR/tools/skills_sync.py"
 fi
 
+# Optionally start `hermes dashboard` as a side-process.
+#
+# Toggled by HERMES_DASHBOARD=1 (also accepts "true"/"yes", case-insensitive).
+# Host/port/TUI can be overridden via:
+#   HERMES_DASHBOARD_HOST  (default 0.0.0.0 — exposed outside the container)
+#   HERMES_DASHBOARD_PORT  (default 9119, matches `hermes dashboard` default)
+#   HERMES_DASHBOARD_TUI   (already honored by `hermes dashboard` itself)
+#
+# The dashboard is a long-lived server.  We background it *before* the final
+# `exec hermes "$@"` so the user's chosen foreground command (chat, gateway,
+# sleep infinity, …) remains PID-of-interest for the container runtime.  When
+# the container stops the whole process tree is torn down, so no explicit
+# cleanup is needed.
+case "${HERMES_DASHBOARD:-}" in
+    1|true|TRUE|True|yes|YES|Yes)
+        dash_host="${HERMES_DASHBOARD_HOST:-0.0.0.0}"
+        dash_port="${HERMES_DASHBOARD_PORT:-9119}"
+        dash_args=(--host "$dash_host" --port "$dash_port" --no-open)
+        # Binding to anything other than localhost requires --insecure — the
+        # dashboard refuses otherwise because it exposes API keys.  Inside a
+        # container this is the expected deployment (host reaches it via
+        # published port), so opt in automatically.
+        if [ "$dash_host" != "127.0.0.1" ] && [ "$dash_host" != "localhost" ]; then
+            dash_args+=(--insecure)
+        fi
+        echo "Starting hermes dashboard on ${dash_host}:${dash_port} (background)"
+        # Prefix dashboard output so it's distinguishable from the main
+        # process in `docker logs`.  stdbuf keeps the pipe line-buffered.
+        (
+            stdbuf -oL -eL hermes dashboard "${dash_args[@]}" 2>&1 \
+                | sed -u 's/^/[dashboard] /'
+        ) &
+        ;;
+esac
+
 # Final exec: two supported invocation patterns.
 #
 #   docker run <image>                 -> exec `hermes` with no args (legacy default)

gateway/config.py

@@ -846,11 +846,25 @@ def load_gateway_config() -> GatewayConfig:
                         if yaml_key in allow_mentions_cfg and not os.getenv(env_key):
                             os.environ[env_key] = str(allow_mentions_cfg[yaml_key]).lower()
 
+            # Bridge top-level require_mention to Telegram when the telegram: section
+            # does not already provide one.  Users often write "require_mention: true"
+            # at the top level alongside group_sessions_per_user, expecting it to work
+            # the same way (#3979).
+            _tl_require_mention = yaml_cfg.get("require_mention")
+            if _tl_require_mention is not None:
+                _tg_section = yaml_cfg.get("telegram") or {}
+                if "require_mention" not in _tg_section:
+                    _tg_plat = platforms_data.setdefault(Platform.TELEGRAM.value, {})
+                    _tg_extra = _tg_plat.setdefault("extra", {})
+                    _tg_extra.setdefault("require_mention", _tl_require_mention)
+
             # Telegram settings → env vars (env vars take precedence)
             telegram_cfg = yaml_cfg.get("telegram", {})
             if isinstance(telegram_cfg, dict):
-                if "require_mention" in telegram_cfg and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
-                    os.environ["TELEGRAM_REQUIRE_MENTION"] = str(telegram_cfg["require_mention"]).lower()
+                # Prefer telegram.require_mention; fall back to the top-level shorthand.
+                _effective_rm = telegram_cfg.get("require_mention", yaml_cfg.get("require_mention"))
+                if _effective_rm is not None and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
+                    os.environ["TELEGRAM_REQUIRE_MENTION"] = str(_effective_rm).lower()
                 if "mention_patterns" in telegram_cfg and not os.getenv("TELEGRAM_MENTION_PATTERNS"):
                     os.environ["TELEGRAM_MENTION_PATTERNS"] = json.dumps(telegram_cfg["mention_patterns"])
                 frc = telegram_cfg.get("free_response_chats")

gateway/platforms/api_server.py

@@ -62,6 +62,14 @@ MAX_NORMALIZED_TEXT_LENGTH = 65_536  # 64 KB cap for normalized content parts
 MAX_CONTENT_LIST_SIZE = 1_000  # Max items when content is an array
 
 
+def _coerce_port(value: Any, default: int = DEFAULT_PORT) -> int:
+    """Parse a listen port without letting malformed env/config values crash startup."""
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
 def _normalize_chat_content(
     content: Any, *, _max_depth: int = 10, _depth: int = 0,
 ) -> str:
@@ -573,7 +581,10 @@ class APIServerAdapter(BasePlatformAdapter):
         super().__init__(config, Platform.API_SERVER)
         extra = config.extra or {}
         self._host: str = extra.get("host", os.getenv("API_SERVER_HOST", DEFAULT_HOST))
-        self._port: int = int(extra.get("port", os.getenv("API_SERVER_PORT", str(DEFAULT_PORT))))
+        raw_port = extra.get("port")
+        if raw_port is None:
+            raw_port = os.getenv("API_SERVER_PORT", str(DEFAULT_PORT))
+        self._port: int = _coerce_port(raw_port, DEFAULT_PORT)
         self._api_key: str = extra.get("key", os.getenv("API_SERVER_KEY", ""))
         self._cors_origins: tuple[str, ...] = self._parse_cors_origins(
             extra.get("cors_origins", os.getenv("API_SERVER_CORS_ORIGINS", "")),
@@ -727,10 +738,11 @@ class APIServerAdapter(BasePlatformAdapter):
         gateway platforms), falling back to the hermes-api-server default.
         """
         from run_agent import AIAgent
-        from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config
+        from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config, GatewayRunner
         from hermes_cli.tools_config import _get_platform_tools
 
         runtime_kwargs = _resolve_runtime_agent_kwargs()
+        reasoning_config = GatewayRunner._load_reasoning_config()
         model = _resolve_gateway_model()
 
         user_config = _load_gateway_config()
@@ -740,7 +752,6 @@ class APIServerAdapter(BasePlatformAdapter):
 
         # Load fallback provider chain so the API server platform has the
         # same fallback behaviour as Telegram/Discord/Slack (fixes #4954).
-        from gateway.run import GatewayRunner
         fallback_model = GatewayRunner._load_fallback_model()
 
         agent = AIAgent(
@@ -759,6 +770,7 @@ class APIServerAdapter(BasePlatformAdapter):
             tool_complete_callback=tool_complete_callback,
             session_db=self._ensure_session_db(),
             fallback_model=fallback_model,
+            reasoning_config=reasoning_config,
         )
         return agent
 
@@ -2566,21 +2578,39 @@ class APIServerAdapter(BasePlatformAdapter):
                     return r, u
 
                 result, usage = await asyncio.get_running_loop().run_in_executor(None, _run_sync)
-                final_response = result.get("final_response", "") if isinstance(result, dict) else ""
-                q.put_nowait({
-                    "event": "run.completed",
-                    "run_id": run_id,
-                    "timestamp": time.time(),
-                    "output": final_response,
-                    "usage": usage,
-                })
-                self._set_run_status(
-                    run_id,
-                    "completed",
-                    output=final_response,
-                    usage=usage,
-                    last_event="run.completed",
-                )
+                # Check for structured failure (non-retryable client errors like
+                # 401/400 return failed=True instead of raising, so the except
+                # block below never fires — issue #15561).
+                if isinstance(result, dict) and result.get("failed"):
+                    error_msg = result.get("error") or "agent run failed"
+                    q.put_nowait({
+                        "event": "run.failed",
+                        "run_id": run_id,
+                        "timestamp": time.time(),
+                        "error": error_msg,
+                    })
+                    self._set_run_status(
+                        run_id,
+                        "failed",
+                        error=error_msg,
+                        last_event="run.failed",
+                    )
+                else:
+                    final_response = result.get("final_response", "") if isinstance(result, dict) else ""
+                    q.put_nowait({
+                        "event": "run.completed",
+                        "run_id": run_id,
+                        "timestamp": time.time(),
+                        "output": final_response,
+                        "usage": usage,
+                    })
+                    self._set_run_status(
+                        run_id,
+                        "completed",
+                        output=final_response,
+                        usage=usage,
+                        last_event="run.completed",
+                    )
             except asyncio.CancelledError:
                 self._set_run_status(
                     run_id,

gateway/platforms/base.py

@@ -2506,7 +2506,13 @@ class BasePlatformAdapter(ABC):
                 _r = await self._send_with_retry(
                     chat_id=event.source.chat_id,
                     content=_text,
-                    reply_to=event.message_id,
+                    reply_to=(
+                        event.reply_to_message_id
+                        if event.source.platform == Platform.FEISHU
+                        and event.source.thread_id
+                        and event.reply_to_message_id
+                        else event.message_id
+                    ),
                     metadata=thread_meta,
                 )
                 if _eph_ttl > 0 and _r.success and _r.message_id:
@@ -2606,7 +2612,13 @@ class BasePlatformAdapter(ABC):
                         _r = await self._send_with_retry(
                             chat_id=event.source.chat_id,
                             content=_text,
-                            reply_to=event.message_id,
+                            reply_to=(
+                                event.reply_to_message_id
+                                if event.source.platform == Platform.FEISHU
+                                and event.source.thread_id
+                                and event.reply_to_message_id
+                                else event.message_id
+                            ),
                             metadata=_thread_meta,
                         )
                         if _eph_ttl > 0 and _r.success and _r.message_id:
@@ -2810,10 +2822,15 @@ class BasePlatformAdapter(ABC):
                 # Send the text portion
                 if text_content:
                     logger.info("[%s] Sending response (%d chars) to %s", self.name, len(text_content), event.source.chat_id)
+                    _reply_anchor = (
+                        event.reply_to_message_id
+                        if event.source.platform == Platform.FEISHU and event.source.thread_id and event.reply_to_message_id
+                        else event.message_id
+                    )
                     result = await self._send_with_retry(
                         chat_id=event.source.chat_id,
                         content=text_content,
-                        reply_to=event.message_id,
+                        reply_to=_reply_anchor,
                         metadata=_thread_metadata,
                     )
                     _record_delivery(result)

gateway/platforms/discord.py

@@ -720,11 +720,22 @@ class DiscordAdapter(BasePlatformAdapter):
                         return
                     # If humans are mentioned but we're not → not for us
                     # (preserves old DISCORD_IGNORE_NO_MENTION=true behavior)
+                    # EXCEPT in free-response channels where the bot should
+                    # answer regardless of who is mentioned.
                     _ignore_no_mention = os.getenv(
                         "DISCORD_IGNORE_NO_MENTION", "true"
                     ).lower() in ("true", "1", "yes")
                     if _ignore_no_mention and not _self_mentioned and not _other_bots_mentioned:
-                        return
+                        _channel_id = str(message.channel.id)
+                        _parent_id = None
+                        if hasattr(message.channel, "parent_id") and message.channel.parent_id:
+                            _parent_id = str(message.channel.parent_id)
+                        _free_channels = adapter_self._discord_free_response_channels()
+                        _channel_ids = {_channel_id}
+                        if _parent_id:
+                            _channel_ids.add(_parent_id)
+                        if "*" not in _free_channels and not (_channel_ids & _free_channels):
+                            return
 
                 await self._handle_message(message)
 
@@ -3797,7 +3808,7 @@ class DiscordAdapter(BasePlatformAdapter):
         if not is_thread and not isinstance(message.channel, discord.DMChannel):
             no_thread_channels_raw = os.getenv("DISCORD_NO_THREAD_CHANNELS", "")
             no_thread_channels = {ch.strip() for ch in no_thread_channels_raw.split(",") if ch.strip()}
-            skip_thread = bool(channel_ids & no_thread_channels) or is_free_channel
+            skip_thread = bool(channel_ids & no_thread_channels)
             auto_thread = os.getenv("DISCORD_AUTO_THREAD", "true").lower() in ("true", "1", "yes")
             is_reply_message = getattr(message, "type", None) == discord.MessageType.reply
             if auto_thread and not skip_thread and not is_voice_linked_channel and not is_reply_message:

gateway/platforms/feishu.py

@@ -2757,9 +2757,11 @@ class FeishuAdapter(BasePlatformAdapter):
             if hint:
                 text = f"{hint}\n\n{text}" if text else hint
 
+        thread_id = getattr(message, "thread_id", None) or getattr(message, "root_id", None) or None
         reply_to_message_id = (
             getattr(message, "parent_id", None)
             or getattr(message, "upper_message_id", None)
+            or getattr(message, "root_id", None)
             or None
         )
         reply_to_text = await self._fetch_message_text(reply_to_message_id) if reply_to_message_id else None
@@ -2791,7 +2793,7 @@ class FeishuAdapter(BasePlatformAdapter):
             chat_type=self._resolve_source_chat_type(chat_info=chat_info, event_chat_type=chat_type),
             user_id=sender_profile["user_id"],
             user_name=sender_profile["user_name"],
-            thread_id=getattr(message, "thread_id", None) or None,
+            thread_id=thread_id,
             user_id_alt=sender_profile["user_id_alt"],
             is_bot=is_bot,
         )
@@ -4227,6 +4229,15 @@ class FeishuAdapter(BasePlatformAdapter):
                 if active_reply_to and not self._response_succeeded(response):
                     code = getattr(response, "code", None)
                     if code in _FEISHU_REPLY_FALLBACK_CODES:
+                        if (metadata or {}).get("thread_id"):
+                            logger.warning(
+                                "[Feishu] Reply to %s failed in thread %s (code %s — message withdrawn/missing); "
+                                "skipping top-level fallback to avoid creating a new topic",
+                                active_reply_to,
+                                (metadata or {}).get("thread_id"),
+                                code,
+                            )
+                            return response
                         logger.warning(
                             "[Feishu] Reply to %s failed (code %s — message withdrawn/missing); "
                             "falling back to new message in chat %s",

gateway/platforms/qqbot/adapter.py

@@ -397,13 +397,24 @@ class QQAdapter(BasePlatformAdapter):
             await self._session.close()
         self._session = None
 
-        self._session = aiohttp.ClientSession()
+        # Honor WSL proxy env for QQ WebSocket. Hermes upgrades overwrite this
+        # local patch, so QQ can regress to direct-connect timeouts after update.
+        self._session = aiohttp.ClientSession(trust_env=True)
+        ws_proxy = (
+            os.getenv("WSS_PROXY")
+            or os.getenv("wss_proxy")
+            or os.getenv("HTTPS_PROXY")
+            or os.getenv("https_proxy")
+            or os.getenv("ALL_PROXY")
+            or os.getenv("all_proxy")
+        )
         self._ws = await self._session.ws_connect(
             gateway_url,
             headers={
                 "User-Agent": build_user_agent(),
             },
             timeout=CONNECT_TIMEOUT_SECONDS,
+            proxy=ws_proxy,
         )
         logger.info("[%s] WebSocket connected to %s", self._log_tag, gateway_url)
 

gateway/platforms/signal.py

@@ -192,6 +192,15 @@ class SignalAdapter(BasePlatformAdapter):
         group_allowed_str = os.getenv("SIGNAL_GROUP_ALLOWED_USERS", "")
         self.group_allow_from = set(_parse_comma_list(group_allowed_str))
 
+        # DM allowlist — mirrors SIGNAL_ALLOWED_USERS checked by run.py.
+        # Stored here so the reaction hooks can skip unauthorized senders
+        # (reactions fire before run.py's auth gate, so without this check
+        # every inbound DM from any contact gets a 👀 reaction).
+        # "*" means all users allowed (open mode); empty means no restriction
+        # recorded at adapter level (run.py still enforces auth separately).
+        dm_allowed_str = os.getenv("SIGNAL_ALLOWED_USERS", "*")
+        self.dm_allow_from = set(_parse_comma_list(dm_allowed_str))
+
         # HTTP client
         self.client: Optional[httpx.AsyncClient] = None
 
@@ -1430,8 +1439,28 @@ class SignalAdapter(BasePlatformAdapter):
             return None
         return (author, ts)
 
+    def _reactions_enabled(self, event: "MessageEvent" = None) -> bool:
+        """Check if message reactions are enabled for this event.
+
+        Two gates:
+        1. SIGNAL_REACTIONS env var — set to false/0/no to disable globally.
+        2. DM allowlist — if SIGNAL_ALLOWED_USERS is set, only react to
+           messages from senders in that list.  This prevents unauthorized
+           contacts from seeing the 👀 reaction (which fires before run.py's
+           auth gate and would otherwise reveal that a bot is listening).
+        """
+        if os.getenv("SIGNAL_REACTIONS", "true").lower() in ("false", "0", "no"):
+            return False
+        if event is not None:
+            sender = getattr(getattr(event, "source", None), "user_id", None)
+            if sender and "*" not in self.dm_allow_from and sender not in self.dm_allow_from:
+                return False
+        return True
+
     async def on_processing_start(self, event: MessageEvent) -> None:
         """React with 👀 when processing begins."""
+        if not self._reactions_enabled(event):
+            return
         target = self._extract_reaction_target(event)
         if target:
             await self.send_reaction(event.source.chat_id, "👀", *target)
@@ -1442,6 +1471,8 @@ class SignalAdapter(BasePlatformAdapter):
         On CANCELLED we leave the 👀 in place — no terminal outcome means
         the reaction should keep reflecting "in progress" (matches Telegram).
         """
+        if not self._reactions_enabled(event):
+            return
         if outcome == ProcessingOutcome.CANCELLED:
             return
         target = self._extract_reaction_target(event)

gateway/platforms/sms.py

@@ -10,7 +10,7 @@ Shares credentials with the optional telephony skill — same env vars:
 
 Gateway-specific env vars:
   - SMS_WEBHOOK_PORT     (default 8080)
-  - SMS_WEBHOOK_HOST     (default 0.0.0.0)
+  - SMS_WEBHOOK_HOST     (default 127.0.0.1)
   - SMS_WEBHOOK_URL      (public URL for Twilio signature validation — required)
   - SMS_INSECURE_NO_SIGNATURE  (true to disable signature validation — dev only)
   - SMS_ALLOWED_USERS    (comma-separated E.164 phone numbers)
@@ -41,7 +41,7 @@ logger = logging.getLogger(__name__)
 TWILIO_API_BASE = "https://api.twilio.com/2010-04-01/Accounts"
 MAX_SMS_LENGTH = 1600  # ~10 SMS segments
 DEFAULT_WEBHOOK_PORT = 8080
-DEFAULT_WEBHOOK_HOST = "0.0.0.0"
+DEFAULT_WEBHOOK_HOST = "127.0.0.1"
 
 
 def check_sms_requirements() -> bool:
@@ -91,19 +91,23 @@ class SmsAdapter(BasePlatformAdapter):
         from aiohttp import web
 
         if not self._from_number:
-            logger.error("[sms] TWILIO_PHONE_NUMBER not set — cannot send replies")
+            msg = "[sms] TWILIO_PHONE_NUMBER not set — cannot send replies"
+            logger.error(msg)
+            self._set_fatal_error("sms_missing_phone_number", msg, retryable=False)
             return False
 
         insecure_no_sig = os.getenv("SMS_INSECURE_NO_SIGNATURE", "").lower() == "true"
 
         if not self._webhook_url and not insecure_no_sig:
-            logger.error(
+            msg = (
                 "[sms] Refusing to start: SMS_WEBHOOK_URL is required for Twilio "
                 "signature validation. Set it to the public URL configured in your "
                 "Twilio console (e.g. https://example.com/webhooks/twilio). "
                 "For local development without validation, set "
-                "SMS_INSECURE_NO_SIGNATURE=true (NOT recommended for production).",
+                "SMS_INSECURE_NO_SIGNATURE=true (NOT recommended for production)."
             )
+            logger.error(msg)
+            self._set_fatal_error("sms_missing_webhook_url", msg, retryable=False)
             return False
 
         if insecure_no_sig and not self._webhook_url:

gateway/platforms/telegram.py

@@ -2267,13 +2267,54 @@ class TelegramAdapter(BasePlatformAdapter):
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
-            logger.error(
-                "[%s] Failed to send Telegram local image, falling back to base adapter: %s",
-                self.name,
-                e,
-                exc_info=True,
+            error_str = str(e)
+            # Dimension-related errors are the expected case for valid image
+            # files that Telegram just refuses as photos (screenshots, extreme
+            # aspect ratios). Log at INFO because the document fallback is
+            # the correct path. Any other send_photo failure also falls back
+            # to document (rate limits, corrupt file markers, format edge
+            # cases), but at WARNING because it's unexpected and worth
+            # surfacing in logs.
+            is_dim_error = (
+                "Photo_invalid_dimensions" in error_str
+                or "PHOTO_INVALID_DIMENSIONS" in error_str
             )
-            return await super().send_image_file(chat_id, image_path, caption, reply_to)
+            if is_dim_error:
+                logger.info(
+                    "[%s] Image dimensions exceed Telegram photo limits, "
+                    "sending as document: %s",
+                    self.name,
+                    image_path,
+                )
+            else:
+                logger.warning(
+                    "[%s] Failed to send Telegram local image as photo, "
+                    "trying document fallback: %s",
+                    self.name,
+                    e,
+                    exc_info=True,
+                )
+            # Fallback to sending as document (file) — no dimension limit,
+            # only 50MB size limit. If even that fails, fall back to the
+            # base adapter's text-only "Image: /path" rendering.
+            try:
+                return await self.send_document(
+                    chat_id=chat_id,
+                    file_path=image_path,
+                    caption=caption,
+                    file_name=os.path.basename(image_path),
+                    reply_to=reply_to,
+                    metadata=metadata,
+                )
+            except Exception as doc_err:
+                logger.error(
+                    "[%s] Failed to send Telegram local image as document, "
+                    "falling back to base adapter: %s",
+                    self.name,
+                    doc_err,
+                    exc_info=True,
+                )
+                return await super().send_image_file(chat_id, image_path, caption, reply_to)
 
     async def send_document(
         self,

gateway/platforms/wecom.py

@@ -142,6 +142,7 @@ class WeComAdapter(BasePlatformAdapter):
     """WeCom AI Bot adapter backed by a persistent WebSocket connection."""
 
     MAX_MESSAGE_LENGTH = MAX_MESSAGE_LENGTH
+    SUPPORTS_MESSAGE_EDITING = False
     # Threshold for detecting WeCom client-side message splits.
     # When a chunk is near the 4000-char limit, a continuation is almost certain.
     _SPLIT_THRESHOLD = 3900

gateway/platforms/weixin.py

@@ -1333,6 +1333,15 @@ class WeixinAdapter(BasePlatformAdapter):
         if message_id and self._dedup.is_duplicate(message_id):
             return
 
+        # Secondary content-fingerprint dedup for text messages
+        item_list = message.get("item_list") or []
+        text = _extract_text(item_list)
+        if text:
+            content_key = f"content:{sender_id}:{hashlib.md5(text.encode()).hexdigest()}"
+            if self._dedup.is_duplicate(content_key):
+                logger.debug("[%s] Content-dedup: skipping duplicate message from %s", self.name, sender_id)
+                return
+
         chat_type, effective_chat_id = _guess_chat_type(message, self._account_id)
         if chat_type == "group":
             if self._group_policy == "disabled":
@@ -1347,8 +1356,6 @@ class WeixinAdapter(BasePlatformAdapter):
             self._token_store.set(self._account_id, sender_id, context_token)
         asyncio.create_task(self._maybe_fetch_typing_ticket(sender_id, context_token or None))
 
-        item_list = message.get("item_list") or []
-        text = _extract_text(item_list)
         media_paths: List[str] = []
         media_types: List[str] = []
 

gateway/run.py

@@ -49,6 +49,29 @@ from hermes_cli.config import cfg_get
 _AGENT_CACHE_MAX_SIZE = 128
 _AGENT_CACHE_IDLE_TTL_SECS = 3600.0  # evict agents idle for >1h
 _PLATFORM_CONNECT_TIMEOUT_SECS_DEFAULT = 30.0
+_TELEGRAM_COMMAND_MENTION_RE = re.compile(r"(?<![\w:/])/([A-Za-z0-9][A-Za-z0-9_-]*)")
+
+
+def _telegramize_command_mentions(text: str, platform: Any) -> str:
+    """Rewrite slash-command mentions to Telegram-valid command names.
+
+    Telegram Bot API command names allow only lowercase letters, digits, and
+    underscores.  Keep other platform renderings unchanged, but normalize
+    Telegram help text so command mentions remain clickable/valid there.
+    """
+    platform_value = getattr(platform, "value", platform)
+    if platform_value != "telegram":
+        return text
+
+    from hermes_cli.commands import _sanitize_telegram_name
+
+    def _replace(match: re.Match[str]) -> str:
+        sanitized = _sanitize_telegram_name(match.group(1))
+        return f"/{sanitized}" if sanitized else match.group(0)
+
+    return _TELEGRAM_COMMAND_MENTION_RE.sub(_replace, text)
+
+
 # Only auto-continue interrupted gateway turns while the interruption is fresh.
 # Stale tool-tail/resume markers can otherwise revive an unrelated old task
 # after a gateway restart when the user's next message starts new work.
@@ -293,6 +316,10 @@ def _restart_notification_pending() -> bool:
     return (_hermes_home / ".restart_notify.json").exists()
 
 
+# Mark this process as a gateway so cli.py's module-level load_cli_config()
+# knows not to clobber TERMINAL_CWD if lazily imported.
+os.environ["_HERMES_GATEWAY"] = "1"
+
 _ensure_ssl_certs()
 
 # Add parent directory to path
@@ -1161,6 +1188,10 @@ class GatewayRunner:
 
         # Per-chat voice reply mode: "off" | "voice_only" | "all"
         self._voice_mode: Dict[str, str] = self._load_voice_modes()
+        # Recent voice transcripts per (guild,user) for duplicate suppression.
+        # Protects against the same utterance being emitted twice by the voice
+        # capture / STT pipeline, which otherwise produces a second delayed reply.
+        self._recent_voice_transcripts: Dict[tuple[int, int], List[tuple[float, str]]] = {}
 
         # Track background tasks to prevent garbage collection mid-execution
         self._background_tasks: set = set()
@@ -3246,6 +3277,11 @@ class GatewayRunner:
         Runs in the gateway event loop; all SQLite work is pushed to a
         thread via ``asyncio.to_thread`` so the loop never blocks on the
         WAL lock. Failures in one tick don't stop subsequent ticks.
+
+        **Multi-board:** iterates every board discovered on disk per
+        tick. Subscriptions live inside each board's own DB and cannot
+        cross boards, so delivery semantics are unchanged — this is
+        purely a fan-out of the single-DB poll.
         """
         from gateway.config import Platform as _Platform
         try:
@@ -3278,40 +3314,54 @@ class GatewayRunner:
         while self._running:
             try:
                 def _collect():
-                    conn = _kb.connect()
+                    deliveries: list[dict] = []
+                    # Enumerate every board on disk. Cheap: a few
+                    # directory stat calls per tick. Missing/empty
+                    # boards are silently skipped.
                     try:
-                        _kb.init_db()  # idempotent; handles first-run
+                        boards = _kb.list_boards(include_archived=False)
                     except Exception:
-                        pass
-                    try:
-                        subs = _kb.list_notify_subs(conn)
-                        deliveries: list[dict] = []
-                        for sub in subs:
-                            cursor, events = _kb.unseen_events_for_sub(
-                                conn,
-                                task_id=sub["task_id"],
-                                platform=sub["platform"],
-                                chat_id=sub["chat_id"],
-                                thread_id=sub.get("thread_id") or "",
-                                kinds=TERMINAL_KINDS,
-                            )
-                            if not events:
-                                continue
-                            task = _kb.get_task(conn, sub["task_id"])
-                            deliveries.append({
-                                "sub": sub,
-                                "cursor": cursor,
-                                "events": events,
-                                "task": task,
-                            })
-                        return deliveries
-                    finally:
-                        conn.close()
+                        boards = [_kb.read_board_metadata(_kb.DEFAULT_BOARD)]
+                    for board_meta in boards:
+                        slug = board_meta.get("slug") or _kb.DEFAULT_BOARD
+                        try:
+                            conn = _kb.connect(board=slug)
+                        except Exception:
+                            continue
+                        try:
+                            try:
+                                _kb.init_db(board=slug)  # idempotent; handles first-run
+                            except Exception:
+                                pass
+                            subs = _kb.list_notify_subs(conn)
+                            for sub in subs:
+                                cursor, events = _kb.unseen_events_for_sub(
+                                    conn,
+                                    task_id=sub["task_id"],
+                                    platform=sub["platform"],
+                                    chat_id=sub["chat_id"],
+                                    thread_id=sub.get("thread_id") or "",
+                                    kinds=TERMINAL_KINDS,
+                                )
+                                if not events:
+                                    continue
+                                task = _kb.get_task(conn, sub["task_id"])
+                                deliveries.append({
+                                    "sub": sub,
+                                    "cursor": cursor,
+                                    "events": events,
+                                    "task": task,
+                                    "board": slug,
+                                })
+                        finally:
+                            conn.close()
+                    return deliveries
 
                 deliveries = await asyncio.to_thread(_collect)
                 for d in deliveries:
                     sub = d["sub"]
                     task = d["task"]
+                    board_slug = d.get("board")
                     platform_str = (sub["platform"] or "").lower()
                     try:
                         plat = _Platform(platform_str)
@@ -3319,7 +3369,7 @@ class GatewayRunner:
                         # Unknown platform string; skip and advance cursor so
                         # we don't replay forever.
                         await asyncio.to_thread(
-                            self._kanban_advance, sub, d["cursor"],
+                            self._kanban_advance, sub, d["cursor"], board_slug,
                         )
                         continue
                     adapter = self.adapters.get(plat)
@@ -3409,14 +3459,14 @@ class GatewayRunner:
                                     "%s on %s after %d consecutive send failures",
                                     sub["task_id"], platform_str, fails,
                                 )
-                                await asyncio.to_thread(self._kanban_unsub, sub)
+                                await asyncio.to_thread(self._kanban_unsub, sub, board_slug)
                                 sub_fail_counts.pop(sub_key, None)
                             # Don't advance cursor on send failure — retry next tick.
                             break
                     else:
                         # All events delivered; advance cursor + maybe unsub.
                         await asyncio.to_thread(
-                            self._kanban_advance, sub, d["cursor"],
+                            self._kanban_advance, sub, d["cursor"], board_slug,
                         )
                         # Unsubscribe when the LAST delivered event is a
                         # terminal kind (the task hit a "no further updates"
@@ -3428,7 +3478,7 @@ class GatewayRunner:
                         event_terminal = last_kind in TERMINAL_EVENT_KINDS
                         if task_terminal or event_terminal:
                             await asyncio.to_thread(
-                                self._kanban_unsub, sub,
+                                self._kanban_unsub, sub, board_slug,
                             )
             except Exception as exc:
                 logger.warning("kanban notifier tick failed: %s", exc)
@@ -3438,10 +3488,16 @@ class GatewayRunner:
                     return
                 await asyncio.sleep(1)
 
-    def _kanban_advance(self, sub: dict, cursor: int) -> None:
-        """Sync helper: advance a subscription's cursor. Runs in to_thread."""
+    def _kanban_advance(
+        self, sub: dict, cursor: int, board: Optional[str] = None,
+    ) -> None:
+        """Sync helper: advance a subscription's cursor. Runs in to_thread.
+
+        ``board`` scopes the DB connection to the board that owns this
+        subscription. Unsub cursors in one board can't touch another's.
+        """
         from hermes_cli import kanban_db as _kb
-        conn = _kb.connect()
+        conn = _kb.connect(board=board)
         try:
             _kb.advance_notify_cursor(
                 conn,
@@ -3454,9 +3510,9 @@ class GatewayRunner:
         finally:
             conn.close()
 
-    def _kanban_unsub(self, sub: dict) -> None:
+    def _kanban_unsub(self, sub: dict, board: Optional[str] = None) -> None:
         from hermes_cli import kanban_db as _kb
-        conn = _kb.connect()
+        conn = _kb.connect(board=board)
         try:
             _kb.remove_notify_sub(
                 conn,
@@ -3534,20 +3590,25 @@ class GatewayRunner:
         bad_ticks = 0
         last_warn_at = 0
 
-        def _tick_once() -> "Optional[object]":
-            """Run one dispatch_once; return result or None on error.
+        def _tick_once_for_board(slug: str) -> "Optional[object]":
+            """Run one dispatch_once for a specific board.
 
-            Runs in a worker thread via `asyncio.to_thread`."""
+            Runs in a worker thread via `asyncio.to_thread`. `board=slug`
+            is passed through `dispatch_once` so `resolve_workspace` and
+            `_default_spawn` see the right paths. The per-board DB is
+            opened explicitly so concurrent boards never share a
+            connection handle or accidentally claim across each other.
+            """
             conn = None
             try:
-                conn = _kb.connect()
+                conn = _kb.connect(board=slug)
                 try:
-                    _kb.init_db()  # idempotent, handles first-run
+                    _kb.init_db(board=slug)  # idempotent, handles first-run
                 except Exception:
                     pass
-                return _kb.dispatch_once(conn)
+                return _kb.dispatch_once(conn, board=slug)
             except Exception:
-                logger.exception("kanban dispatcher: tick failed")
+                logger.exception("kanban dispatcher: tick failed on board %s", slug)
                 return None
             finally:
                 if conn is not None:
@@ -3556,49 +3617,77 @@ class GatewayRunner:
                     except Exception:
                         pass
 
-        def _ready_nonempty() -> bool:
-            """Cheap probe: is there at least one ready+assigned+unclaimed task?"""
-            conn = None
+        def _tick_once() -> "list[tuple[str, Optional[object]]]":
+            """Run one dispatch_once per board. Returns (slug, result) pairs.
+
+            Enumerating boards on every tick keeps the dispatcher honest
+            when users create a new board mid-run: no restart required,
+            the next tick picks it up automatically.
+            """
             try:
-                conn = _kb.connect()
-                row = conn.execute(
-                    "SELECT 1 FROM tasks "
-                    "WHERE status = 'ready' AND assignee IS NOT NULL "
-                    "    AND claim_lock IS NULL LIMIT 1"
-                ).fetchone()
-                return row is not None
+                boards = _kb.list_boards(include_archived=False)
             except Exception:
-                return False
-            finally:
-                if conn is not None:
-                    try:
-                        conn.close()
-                    except Exception:
-                        pass
+                boards = [_kb.read_board_metadata(_kb.DEFAULT_BOARD)]
+            out: list[tuple[str, "Optional[object]"]] = []
+            for b in boards:
+                slug = b.get("slug") or _kb.DEFAULT_BOARD
+                out.append((slug, _tick_once_for_board(slug)))
+            return out
+
+        def _ready_nonempty() -> bool:
+            """Cheap probe: is there a ready+assigned+unclaimed task on ANY board?"""
+            try:
+                boards = _kb.list_boards(include_archived=False)
+            except Exception:
+                boards = [_kb.read_board_metadata(_kb.DEFAULT_BOARD)]
+            for b in boards:
+                slug = b.get("slug") or _kb.DEFAULT_BOARD
+                conn = None
+                try:
+                    conn = _kb.connect(board=slug)
+                    row = conn.execute(
+                        "SELECT 1 FROM tasks "
+                        "WHERE status = 'ready' AND assignee IS NOT NULL "
+                        "    AND claim_lock IS NULL LIMIT 1"
+                    ).fetchone()
+                    if row is not None:
+                        return True
+                except Exception:
+                    continue
+                finally:
+                    if conn is not None:
+                        try:
+                            conn.close()
+                        except Exception:
+                            pass
+            return False
 
         logger.info(
             "kanban dispatcher: embedded in gateway (interval=%.1fs)", interval
         )
         while self._running:
             try:
-                res = await asyncio.to_thread(_tick_once)
-                if res is not None and getattr(res, "spawned", None):
-                    # Quiet by default — only log when something actually
-                    # happened, so an idle gateway stays silent.
-                    logger.info(
-                        "kanban dispatcher: tick spawned=%d reclaimed=%d "
-                        "crashed=%d timed_out=%d promoted=%d auto_blocked=%d",
-                        len(res.spawned),
-                        res.reclaimed,
-                        len(res.crashed) if hasattr(res.crashed, "__len__") else 0,
-                        len(res.timed_out) if hasattr(res.timed_out, "__len__") else 0,
-                        res.promoted,
-                        len(res.auto_blocked) if hasattr(res.auto_blocked, "__len__") else 0,
-                    )
-                # Health telemetry
+                results = await asyncio.to_thread(_tick_once)
+                any_spawned = False
+                for slug, res in (results or []):
+                    if res is not None and getattr(res, "spawned", None):
+                        any_spawned = True
+                        # Quiet by default — only log when something actually
+                        # happened, so an idle gateway stays silent.
+                        logger.info(
+                            "kanban dispatcher [%s]: spawned=%d reclaimed=%d "
+                            "crashed=%d timed_out=%d promoted=%d auto_blocked=%d",
+                            slug,
+                            len(res.spawned),
+                            res.reclaimed,
+                            len(res.crashed) if hasattr(res.crashed, "__len__") else 0,
+                            len(res.timed_out) if hasattr(res.timed_out, "__len__") else 0,
+                            res.promoted,
+                            len(res.auto_blocked) if hasattr(res.auto_blocked, "__len__") else 0,
+                        )
+                # Health telemetry (aggregate across boards)
                 ready_pending = await asyncio.to_thread(_ready_nonempty)
-                spawned_any = bool(res and getattr(res, "spawned", None))
-                if ready_pending and not spawned_any:
+                if ready_pending and not any_spawned:
                     bad_ticks += 1
                 else:
                     bad_ticks = 0
@@ -5107,6 +5196,28 @@ class GatewayRunner:
         _cmd_def = _resolve_cmd(command) if command else None
         canonical = _cmd_def.name if _cmd_def else command
 
+        # Expand alias quick commands before built-in dispatch so targets like
+        # /model openai/gpt-5.5 --provider openrouter reach the /model handler.
+        # Preserve built-in precedence; aliases only need early handling when
+        # the typed command is not already known.
+        if command and _cmd_def is None:
+            if isinstance(self.config, dict):
+                quick_commands = self.config.get("quick_commands", {}) or {}
+            else:
+                quick_commands = getattr(self.config, "quick_commands", {}) or {}
+            if isinstance(quick_commands, dict) and command in quick_commands:
+                qcmd = quick_commands[command]
+                if qcmd.get("type") == "alias":
+                    target = qcmd.get("target", "").strip()
+                    if target:
+                        target = target if target.startswith("/") else f"/{target}"
+                        target_command = target.lstrip("/")
+                        user_args = event.get_command_args().strip()
+                        event.text = f"{target} {user_args}".strip()
+                        command = target_command.split()[0] if target_command else target_command
+                        _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", ...}``
@@ -5320,7 +5431,7 @@ class GatewayRunner:
                         target_command = target.lstrip("/")
                         user_args = event.get_command_args().strip()
                         event.text = f"{target} {user_args}".strip()
-                        command = target_command
+                        command = target_command.split()[0] if target_command else target_command
                         # Fall through to normal command dispatch below
                     else:
                         return f"Quick command '/{command}' has no target defined."
@@ -6681,6 +6792,7 @@ class GatewayRunner:
         base_url = None
         api_key = None
         custom_provs = None
+        data = None
 
         try:
             data = _load_gateway_config()
@@ -6703,6 +6815,41 @@ class GatewayRunner:
         except Exception:
             pass
 
+        # Also check custom_providers for context_length when top-level model.context_length is not set
+        if config_context_length is None and data:
+            try:
+                custom_providers = data.get("custom_providers", [])
+                if custom_providers:
+                    for cp in custom_providers:
+                        if not isinstance(cp, dict):
+                            continue
+                        cp_model = cp.get("model") or ""
+                        cp_models = cp.get("models") or {}
+                        # Match provider model to current model
+                        if cp_model and cp_model == model:
+                            raw_cp_ctx = cp.get("context_length")
+                            if raw_cp_ctx is not None:
+                                try:
+                                    config_context_length = int(raw_cp_ctx)
+                                    break
+                                except (TypeError, ValueError):
+                                    pass
+                        # Also check per-model context_length
+                        if isinstance(cp_models, dict):
+                            model_entry = cp_models.get(model)
+                            if isinstance(model_entry, dict):
+                                model_ctx = model_entry.get("context_length")
+                            else:
+                                model_ctx = model_entry
+                            if model_ctx is not None and isinstance(model_ctx, (int, float)):
+                                try:
+                                    config_context_length = int(model_ctx)
+                                    break
+                                except (TypeError, ValueError):
+                                    pass
+            except Exception:
+                pass
+
         # Resolve runtime credentials for probing
         try:
             runtime = _resolve_runtime_agent_kwargs()
@@ -6843,6 +6990,29 @@ class GatewayRunner:
             new_entry = self.session_store.get_or_create_session(source, force_new=True)
             header = "✨ New session started!"
 
+        # Set session title if provided with /new <title>
+        _title_arg = event.get_command_args().strip()
+        _title_note = ""
+        if _title_arg and self._session_db and new_entry:
+            from hermes_state import SessionDB
+            try:
+                sanitized = SessionDB.sanitize_title(_title_arg)
+            except ValueError as e:
+                sanitized = None
+                _title_note = f"\n⚠️ Title rejected: {e}"
+            if sanitized:
+                try:
+                    self._session_db.set_session_title(new_entry.session_id, sanitized)
+                    header = f"✨ New session started: {sanitized}"
+                except ValueError as e:
+                    _title_note = f"\n⚠️ {e} — session started untitled."
+                except Exception:
+                    pass
+            elif not _title_note:
+                # sanitize_title returned empty (whitespace-only / unprintable)
+                _title_note = "\n⚠️ Title is empty after cleanup — session started untitled."
+        header = header + _title_note
+
         # Fire plugin on_session_reset hook (new session guaranteed to exist)
         try:
             from hermes_cli.plugins import invoke_hook as _invoke_hook
@@ -7298,7 +7468,10 @@ class GatewayRunner:
                     lines.append(f"\n... and {len(sorted_cmds) - 10} more. Use `/commands` for the full paginated list.")
         except Exception:
             pass
-        return "\n".join(lines)
+        return _telegramize_command_mentions(
+            "\n".join(lines),
+            getattr(getattr(event, "source", None), "platform", None),
+        )
 
     async def _handle_commands_command(self, event: MessageEvent) -> str:
         """Handle /commands [page] - paginated list of all commands and skills."""
@@ -7351,7 +7524,10 @@ class GatewayRunner:
             lines.extend(["", " | ".join(nav_parts)])
         if page != requested_page:
             lines.append(f"_(Requested page {requested_page} was out of range, showing page {page}.)_")
-        return "\n".join(lines)
+        return _telegramize_command_mentions(
+            "\n".join(lines),
+            getattr(getattr(event, "source", None), "platform", None),
+        )
 
     async def _handle_model_command(self, event: MessageEvent) -> Optional[str]:
         """Handle /model command — switch model for this session.
@@ -8261,6 +8437,47 @@ class GatewayRunner:
         adapter = self.adapters.get(Platform.DISCORD)
         self._set_adapter_auto_tts_disabled(adapter, chat_id, disabled=True)
 
+    def _is_duplicate_voice_transcript(self, guild_id: int, user_id: int, transcript: str) -> bool:
+        """Suppress repeated STT outputs for the same recent utterance.
+
+        Voice capture can occasionally emit the same utterance twice a few
+        seconds apart, which creates a second queued agent run and overlapping
+        spoken replies. Dedup exact and near-exact repeats per guild/user over a
+        short window while allowing genuinely new turns through.
+        """
+        from difflib import SequenceMatcher
+
+        normalized = re.sub(r"\s+", " ", transcript).strip().lower()
+        normalized = re.sub(r"[^\w\s]", "", normalized)
+        if not normalized:
+            return False
+
+        now = time.monotonic()
+        window_seconds = 12.0
+        key = (guild_id, user_id)
+        recent_store = getattr(self, "_recent_voice_transcripts", None)
+        if not isinstance(recent_store, dict):
+            recent_store = {}
+            self._recent_voice_transcripts = recent_store
+        recent = [
+            (ts, txt)
+            for ts, txt in recent_store.get(key, [])
+            if now - ts <= window_seconds
+        ]
+
+        for _, prior in recent:
+            if prior == normalized:
+                recent_store[key] = recent
+                return True
+            if len(prior) >= 16 and len(normalized) >= 16:
+                if SequenceMatcher(None, prior, normalized).ratio() >= 0.95:
+                    recent_store[key] = recent
+                    return True
+
+        recent.append((now, normalized))
+        recent_store[key] = recent[-5:]
+        return False
+
     async def _handle_voice_channel_input(
         self, guild_id: int, user_id: int, transcript: str
     ):
@@ -8298,6 +8515,15 @@ class GatewayRunner:
             logger.debug("Unauthorized voice input from user %d, ignoring", user_id)
             return
 
+        if self._is_duplicate_voice_transcript(guild_id, user_id, transcript):
+            logger.info(
+                "Suppressing duplicate voice transcript for guild=%s user=%s: %s",
+                guild_id,
+                user_id,
+                transcript[:100],
+            )
+            return
+
         # Show transcript in text channel (after auth, with mention sanitization)
         try:
             channel = adapter._client.get_channel(text_ch_id)
@@ -11311,6 +11537,12 @@ class GatewayRunner:
         if not session_key:
             return
 
+        pending_skills_reload_notes = getattr(
+            self, "_pending_skills_reload_notes", None
+        )
+        if isinstance(pending_skills_reload_notes, dict):
+            pending_skills_reload_notes.pop(session_key, None)
+
         pending_approvals = getattr(self, "_pending_approvals", None)
         if isinstance(pending_approvals, dict):
             pending_approvals.pop(session_key, None)

gateway/session.py

@@ -1121,7 +1121,7 @@ class SessionStore:
                 self._save()
         return count
 
-    def reset_session(self, session_key: str) -> Optional[SessionEntry]:
+    def reset_session(self, session_key: str, display_name: Optional[str] = None) -> Optional[SessionEntry]:
         """Force reset a session, creating a new session ID."""
         db_end_session_id = None
         db_create_kwargs = None
@@ -1145,7 +1145,7 @@ class SessionStore:
                 created_at=now,
                 updated_at=now,
                 origin=old_entry.origin,
-                display_name=old_entry.display_name,
+                display_name=display_name if display_name is not None else old_entry.display_name,
                 platform=old_entry.platform,
                 chat_type=old_entry.chat_type,
                 is_fresh_reset=True,

hermes_cli/__init__.py

@@ -5,11 +5,43 @@ Provides subcommands for:
 - hermes chat          - Interactive chat (same as ./hermes)
 - hermes gateway       - Run gateway in foreground
 - hermes gateway start - Start gateway service
-- hermes gateway stop  - Stop gateway service  
+- hermes gateway stop  - Stop gateway service
 - hermes setup         - Interactive setup wizard
 - hermes status        - Show status of all components
 - hermes cron          - Manage cron jobs
 """
 
+import os
+import sys
+
 __version__ = "0.12.0"
 __release_date__ = "2026.4.30"
+
+
+def _ensure_utf8():
+    """Force UTF-8 stdout/stderr on Windows to prevent UnicodeEncodeError.
+
+    Windows services and terminals default to cp1252, which cannot encode
+    box-drawing characters used in CLI output. This causes unhandled
+    UnicodeEncodeError crashes on gateway startup.
+    """
+    if sys.platform != "win32":
+        return
+    os.environ.setdefault("PYTHONUTF8", "1")
+    os.environ.setdefault("PYTHONIOENCODING", "utf-8")
+    for stream_name in ("stdout", "stderr"):
+        stream = getattr(sys, stream_name, None)
+        if stream is None:
+            continue
+        try:
+            if getattr(stream, "encoding", "").lower().replace("-", "") != "utf8":
+                new_stream = open(
+                    stream.fileno(), "w", encoding="utf-8",
+                    buffering=1, closefd=False,
+                )
+                setattr(sys, stream_name, new_stream)
+        except (AttributeError, OSError):
+            pass
+
+
+_ensure_utf8()

hermes_cli/auth.py

@@ -2589,6 +2589,208 @@ def _poll_for_token(
 # Nous Portal — token refresh, agent key minting, model discovery
 # =============================================================================
 
+# -----------------------------------------------------------------------------
+# Shared Nous token store — lets OAuth credentials persist across profiles
+# so a new `hermes --profile <name> auth add nous --type oauth` can one-tap
+# import instead of running the full device-code flow every time.
+#
+# File lives at ${HERMES_SHARED_AUTH_DIR}/nous_auth.json, defaulting to
+# ~/.hermes/shared/nous_auth.json. It is OUTSIDE any named profile's
+# HERMES_HOME so named profiles (which typically live under
+# ~/.hermes/profiles/<name>/) all see the same file.
+#
+# Written on successful login and on every runtime refresh so the stored
+# refresh_token stays current even if one profile refreshes and rotates it.
+# If ever the stored refresh_token does go stale server-side, import fails
+# gracefully and the user falls back to the normal device-code flow.
+# -----------------------------------------------------------------------------
+
+NOUS_SHARED_STORE_FILENAME = "nous_auth.json"
+
+
+def _nous_shared_auth_dir() -> Path:
+    """Resolve the directory that holds the shared Nous token store.
+
+    Honors ``HERMES_SHARED_AUTH_DIR`` so tests can redirect it to a tmp
+    path without touching the real user's home. Defaults to
+    ``~/.hermes/shared/``.
+    """
+    override = os.getenv("HERMES_SHARED_AUTH_DIR", "").strip()
+    if override:
+        return Path(override).expanduser()
+    return Path.home() / ".hermes" / "shared"
+
+
+def _nous_shared_store_path() -> Path:
+    path = _nous_shared_auth_dir() / NOUS_SHARED_STORE_FILENAME
+    # Seat belt: if pytest is running and this resolves to a path under the
+    # real user's home, refuse rather than silently corrupt cross-profile
+    # state. Tests must set HERMES_SHARED_AUTH_DIR to a tmp_path (conftest
+    # does not do this automatically — mirror the _auth_file_path() guard
+    # so forgetting to set it fails loudly instead of writing to the real
+    # shared store).
+    if os.environ.get("PYTEST_CURRENT_TEST"):
+        real_home_shared = (
+            Path.home() / ".hermes" / "shared" / NOUS_SHARED_STORE_FILENAME
+        ).resolve(strict=False)
+        try:
+            resolved = path.resolve(strict=False)
+        except Exception:
+            resolved = path
+        if resolved == real_home_shared:
+            raise RuntimeError(
+                f"Refusing to touch real user shared Nous auth store during test run: "
+                f"{path}. Set HERMES_SHARED_AUTH_DIR to a tmp_path in your test fixture."
+            )
+    return path
+
+
+def _write_shared_nous_state(state: Dict[str, Any]) -> None:
+    """Persist a minimal copy of the Nous OAuth state to the shared store.
+
+    Best-effort: any failure is swallowed after logging. The shared store
+    is a convenience layer; the per-profile auth.json remains the source
+    of truth.
+
+    We deliberately omit the short-lived ``agent_key`` (24h TTL, profile-
+    specific) — only the long-lived OAuth tokens are cross-profile useful.
+    """
+    refresh_token = state.get("refresh_token")
+    access_token = state.get("access_token")
+    if not (isinstance(refresh_token, str) and refresh_token.strip()):
+        # No refresh_token = nothing worth sharing across profiles
+        return
+    if not (isinstance(access_token, str) and access_token.strip()):
+        return
+
+    shared = {
+        "_schema": 1,
+        "access_token": access_token,
+        "refresh_token": refresh_token,
+        "token_type": state.get("token_type") or "Bearer",
+        "scope": state.get("scope") or DEFAULT_NOUS_SCOPE,
+        "client_id": state.get("client_id") or DEFAULT_NOUS_CLIENT_ID,
+        "portal_base_url": state.get("portal_base_url") or DEFAULT_NOUS_PORTAL_URL,
+        "inference_base_url": state.get("inference_base_url") or DEFAULT_NOUS_INFERENCE_URL,
+        "obtained_at": state.get("obtained_at"),
+        "expires_at": state.get("expires_at"),
+        "updated_at": datetime.now(timezone.utc).isoformat(),
+    }
+    try:
+        path = _nous_shared_store_path()
+        path.parent.mkdir(parents=True, exist_ok=True)
+        tmp = path.with_suffix(path.suffix + ".tmp")
+        tmp.write_text(json.dumps(shared, indent=2, sort_keys=True))
+        try:
+            os.chmod(tmp, 0o600)
+        except OSError:
+            pass
+        os.replace(tmp, path)
+        _oauth_trace(
+            "nous_shared_store_written",
+            path=str(path),
+            refresh_token_fp=_token_fingerprint(refresh_token),
+        )
+    except Exception as exc:
+        logger.debug("Failed to write shared Nous auth store: %s", exc)
+
+
+def _read_shared_nous_state() -> Optional[Dict[str, Any]]:
+    """Return the shared Nous OAuth state if present and well-formed.
+
+    Returns ``None`` when the file is missing, unreadable, malformed, or
+    lacks required fields. Callers should treat ``None`` as "no shared
+    credentials available — fall through to device-code".
+    """
+    try:
+        path = _nous_shared_store_path()
+    except RuntimeError:
+        # Test seat belt tripped — treat as missing
+        return None
+    if not path.is_file():
+        return None
+    try:
+        payload = json.loads(path.read_text())
+    except (OSError, ValueError) as exc:
+        logger.debug("Shared Nous auth store at %s is unreadable: %s", path, exc)
+        return None
+    if not isinstance(payload, dict):
+        return None
+    refresh_token = payload.get("refresh_token")
+    access_token = payload.get("access_token")
+    if not (isinstance(refresh_token, str) and refresh_token.strip()):
+        return None
+    if not (isinstance(access_token, str) and access_token.strip()):
+        return None
+    return payload
+
+
+def _try_import_shared_nous_state(
+    *,
+    timeout_seconds: float = 15.0,
+    min_key_ttl_seconds: int = 5 * 60,
+) -> Optional[Dict[str, Any]]:
+    """Attempt to rehydrate Nous OAuth state from the shared store.
+
+    Reads the shared file (if present), runs a forced refresh+mint using
+    the stored refresh_token to produce a fresh access_token + agent_key
+    scoped to this profile, and returns the full auth_state dict ready
+    for ``persist_nous_credentials()``.
+
+    Returns ``None`` when no shared state is available or the rehydrate
+    fails for any reason (expired refresh_token, portal unreachable,
+    etc.) — caller should then fall through to the normal device-code
+    flow.
+    """
+    shared = _read_shared_nous_state()
+    if not shared:
+        return None
+
+    # Build a full state dict so refresh_nous_oauth_from_state has every
+    # field it needs. force_refresh=True gets us a fresh access_token
+    # for this profile; force_mint=True gets us a fresh agent_key.
+    state: Dict[str, Any] = {
+        "access_token": shared.get("access_token"),
+        "refresh_token": shared.get("refresh_token"),
+        "client_id": shared.get("client_id") or DEFAULT_NOUS_CLIENT_ID,
+        "portal_base_url": shared.get("portal_base_url") or DEFAULT_NOUS_PORTAL_URL,
+        "inference_base_url": shared.get("inference_base_url") or DEFAULT_NOUS_INFERENCE_URL,
+        "token_type": shared.get("token_type") or "Bearer",
+        "scope": shared.get("scope") or DEFAULT_NOUS_SCOPE,
+        "obtained_at": shared.get("obtained_at"),
+        "expires_at": shared.get("expires_at"),
+        "agent_key": None,
+        "agent_key_expires_at": None,
+        "tls": {"insecure": False, "ca_bundle": None},
+    }
+
+    try:
+        refreshed = refresh_nous_oauth_from_state(
+            state,
+            min_key_ttl_seconds=min_key_ttl_seconds,
+            timeout_seconds=timeout_seconds,
+            force_refresh=True,
+            force_mint=True,
+        )
+    except AuthError as exc:
+        _oauth_trace(
+            "nous_shared_import_failed",
+            error_type=type(exc).__name__,
+            error_code=getattr(exc, "code", None),
+        )
+        logger.debug("Shared Nous import failed: %s", exc)
+        return None
+    except Exception as exc:
+        _oauth_trace(
+            "nous_shared_import_failed",
+            error_type=type(exc).__name__,
+        )
+        logger.debug("Shared Nous import failed: %s", exc)
+        return None
+
+    return refreshed
+
+
 def _refresh_access_token(
     *,
     client: httpx.Client,
@@ -2991,6 +3193,12 @@ def persist_nous_credentials(
         _save_provider_state(auth_store, "nous", state)
         _save_auth_store(auth_store)
 
+    # Mirror to the shared store so a new profile can one-tap import
+    # these credentials via `hermes auth add nous --type oauth`. Best-
+    # effort: any I/O failure is logged and swallowed (the per-profile
+    # auth.json is still the source of truth).
+    _write_shared_nous_state(state)
+
     pool = load_pool("nous")
     return next(
         (e for e in pool.entries() if e.source == NOUS_DEVICE_CODE_SOURCE),
@@ -3059,6 +3267,11 @@ def resolve_nous_runtime_credentials(
                 refresh_token_fp=_token_fingerprint(state.get("refresh_token")),
                 access_token_fp=_token_fingerprint(state.get("access_token")),
             )
+            # Mirror post-refresh state to the shared store so sibling
+            # profiles don't hold stale refresh_tokens after rotation.
+            # Best-effort — any failure is logged and swallowed inside
+            # _write_shared_nous_state.
+            _write_shared_nous_state(state)
 
         verify = _resolve_verify(insecure=insecure, ca_bundle=ca_bundle, auth_state=state)
         timeout = httpx.Timeout(timeout_seconds if timeout_seconds else 15.0)
@@ -4283,7 +4496,8 @@ def _minimax_oauth_login(
     print(f"Portal: {portal_base_url}")
 
     with httpx.Client(timeout=httpx.Timeout(timeout_seconds),
-                      headers={"Accept": "application/json"}) as client:
+                      headers={"Accept": "application/json"},
+                      follow_redirects=True) as client:
         code_data = _minimax_request_user_code(
             client, portal_base_url=portal_base_url,
             client_id=pconfig.client_id,
@@ -4360,7 +4574,8 @@ def _refresh_minimax_oauth_state(
         return state
 
     portal_base_url = state["portal_base_url"]
-    with httpx.Client(timeout=httpx.Timeout(timeout_seconds)) as client:
+    with httpx.Client(timeout=httpx.Timeout(timeout_seconds),
+                      follow_redirects=True) as client:
         response = client.post(
             f"{portal_base_url}/oauth/token",
             data={
@@ -4598,17 +4813,47 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
     )
 
     try:
-        auth_state = _nous_device_code_login(
-            portal_base_url=getattr(args, "portal_url", None),
-            inference_base_url=getattr(args, "inference_url", None),
-            client_id=getattr(args, "client_id", None) or pconfig.client_id,
-            scope=getattr(args, "scope", None) or pconfig.scope,
-            open_browser=not getattr(args, "no_browser", False),
-            timeout_seconds=timeout_seconds,
-            insecure=insecure,
-            ca_bundle=ca_bundle,
-            min_key_ttl_seconds=5 * 60,
-        )
+        auth_state = None
+
+        # Codex-style auto-import: before launching a fresh device-code
+        # flow, check the shared store for an existing Nous credential
+        # from any other profile. If present, offer to rehydrate it.
+        shared = _read_shared_nous_state()
+        if shared:
+            try:
+                shared_path = _nous_shared_store_path()
+            except RuntimeError:
+                shared_path = None
+            print()
+            if shared_path:
+                print(f"Found existing Nous OAuth credentials at {shared_path}")
+            else:
+                print("Found existing shared Nous OAuth credentials")
+            try:
+                do_import = input("Import these credentials? [Y/n]: ").strip().lower()
+            except (EOFError, KeyboardInterrupt):
+                do_import = "y"
+            if do_import in ("", "y", "yes"):
+                print("Rehydrating Nous session from shared credentials...")
+                auth_state = _try_import_shared_nous_state(
+                    timeout_seconds=timeout_seconds,
+                    min_key_ttl_seconds=5 * 60,
+                )
+                if auth_state is None:
+                    print("Could not refresh shared credentials — falling back to device-code login.")
+
+        if auth_state is None:
+            auth_state = _nous_device_code_login(
+                portal_base_url=getattr(args, "portal_url", None),
+                inference_base_url=getattr(args, "inference_url", None),
+                client_id=getattr(args, "client_id", None) or pconfig.client_id,
+                scope=getattr(args, "scope", None) or pconfig.scope,
+                open_browser=not getattr(args, "no_browser", False),
+                timeout_seconds=timeout_seconds,
+                insecure=insecure,
+                ca_bundle=ca_bundle,
+                min_key_ttl_seconds=5 * 60,
+            )
 
         inference_base_url = auth_state["inference_base_url"]
 
@@ -4625,6 +4870,11 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
             _save_provider_state(auth_store, "nous", auth_state)
             saved_to = _save_auth_store(auth_store)
 
+        # Mirror to the shared store so other profiles can one-tap import
+        # these credentials. Best-effort: any I/O failure is logged and
+        # swallowed inside the helper.
+        _write_shared_nous_state(auth_state)
+
         print()
         print("Login successful!")
         print(f"  Auth state: {saved_to}")

hermes_cli/auth_commands.py

@@ -245,6 +245,47 @@ def auth_add_command(args) -> None:
         return
 
     if provider == "nous":
+        # Codex-style auto-import: if a shared Nous credential lives at
+        # ~/.hermes/shared/nous_auth.json (written by any previous
+        # successful login), offer to import it instead of running the
+        # full device-code flow. This makes `hermes --profile <name>
+        # auth add nous --type oauth` a one-tap operation for users who
+        # run multiple profiles.
+        shared = auth_mod._read_shared_nous_state()
+        if shared:
+            try:
+                path = auth_mod._nous_shared_store_path()
+            except RuntimeError:
+                path = None
+            print()
+            if path:
+                print(f"Found existing Nous OAuth credentials at {path}")
+            else:
+                print("Found existing shared Nous OAuth credentials")
+            try:
+                do_import = input("Import these credentials? [Y/n]: ").strip().lower()
+            except (EOFError, KeyboardInterrupt):
+                do_import = "y"
+            if do_import in ("", "y", "yes"):
+                print("Rehydrating Nous session from shared credentials...")
+                rehydrated = auth_mod._try_import_shared_nous_state(
+                    timeout_seconds=getattr(args, "timeout", None) or 15.0,
+                    min_key_ttl_seconds=max(
+                        60, int(getattr(args, "min_key_ttl_seconds", 5 * 60))
+                    ),
+                )
+                if rehydrated is not None:
+                    custom_label = (getattr(args, "label", None) or "").strip() or None
+                    entry = auth_mod.persist_nous_credentials(rehydrated, label=custom_label)
+                    shown_label = entry.label if entry is not None else label_from_token(
+                        rehydrated.get("access_token", ""), _oauth_default_label(provider, 1),
+                    )
+                    print(f'Imported {provider} OAuth credentials: "{shown_label}"')
+                    return
+                # Rehydrate failed (expired refresh_token, portal down, etc.)
+                # — fall through to device-code flow.
+                print("Could not refresh shared credentials — falling back to device-code login.")
+
         creds = auth_mod._nous_device_code_login(
             portal_base_url=getattr(args, "portal_url", None),
             inference_base_url=getattr(args, "inference_url", None),

hermes_cli/backup.py

@@ -61,6 +61,9 @@ _EXCLUDED_NAMES = {
     "cron.pid",
 }
 
+# zipfile.open() drops Unix mode bits on extract; restore tightens these to 0600.
+_SECRET_FILE_NAMES = {".env", "auth.json", "state.db"}
+
 
 def _should_exclude(rel_path: Path) -> bool:
     """Return True if *rel_path* (relative to hermes root) should be skipped."""
@@ -381,6 +384,8 @@ def run_import(args) -> None:
                 target.parent.mkdir(parents=True, exist_ok=True)
                 with zf.open(member) as src, open(target, "wb") as dst:
                     dst.write(src.read())
+                if target.name in _SECRET_FILE_NAMES:
+                    os.chmod(target, 0o600)
                 restored += 1
             except (PermissionError, OSError) as exc:
                 errors.append(f"  {rel}: {exc}")
@@ -788,9 +793,17 @@ def _prune_pre_update_backups(backup_dir: Path, keep: int) -> int:
     Returns the number of files deleted.  Only touches files matching
     ``pre-update-*.zip`` so hand-made zips dropped in the same directory
     are never touched.
+
+    ``keep`` is floored to 1 because this helper is only called immediately
+    after a fresh backup is written: deleting that backup right after the
+    user paid the disk/CPU cost to create it would leave them worse off
+    than no backup at all (and the wrapper in ``main.py`` would still print
+    a misleading ``Saved: <path>`` line for a file that no longer exists).
+    Operators who genuinely don't want a backup should set
+    ``updates.pre_update_backup: false`` in config — that gates creation.
     """
-    if keep < 0:
-        keep = 0
+    if keep < 1:
+        keep = 1
     if not backup_dir.exists():
         return 0
 

hermes_cli/commands.py

@@ -64,7 +64,7 @@ class CommandDef:
 COMMAND_REGISTRY: list[CommandDef] = [
     # Session
     CommandDef("new", "Start a new session (fresh session ID + history)", "Session",
-               aliases=("reset",)),
+               aliases=("reset",), args_hint="[name]"),
     CommandDef("clear", "Clear screen and start a new session", "Session",
                cli_only=True),
     CommandDef("redraw", "Force a full UI repaint (recovers from terminal drift)", "Session",
@@ -399,6 +399,11 @@ def _is_gateway_available(cmd: CommandDef, config_overrides: set[str] | None = N
     return False
 
 
+def _requires_argument(args_hint: str) -> bool:
+    """Return True when selecting a command without text would be incomplete."""
+    return args_hint.strip().startswith("<")
+
+
 def gateway_help_lines() -> list[str]:
     """Generate gateway help text lines from the registry."""
     overrides = _resolve_config_gates()
@@ -455,7 +460,9 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
 
     Telegram command names cannot contain hyphens, so they are replaced with
     underscores.  Aliases are skipped -- Telegram shows one menu entry per
-    canonical command.
+    canonical command. Commands that require arguments are skipped because
+    selecting a Telegram BotCommand sends only ``/command`` and would execute
+    an incomplete command.
 
     Plugin-registered slash commands are included so plugins get native
     autocomplete in Telegram without touching core code.
@@ -465,10 +472,14 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
     for cmd in COMMAND_REGISTRY:
         if not _is_gateway_available(cmd, overrides):
             continue
+        if _requires_argument(cmd.args_hint):
+            continue
         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():
+    for name, description, args_hint in _iter_plugin_command_entries():
+        if _requires_argument(args_hint):
+            continue
         tg_name = _sanitize_telegram_name(name)
         if tg_name:
             result.append((tg_name, description))
@@ -1115,6 +1126,12 @@ class SlashCommandCompleter(Completer):
         except Exception:
             return {}
 
+    # Commands that open pickers when run without arguments.
+    # These should NOT receive a trailing space in completions because:
+    # - The TUI's submit handler applies completions on Enter if input differs
+    # - Adding space makes "/model" → "/model " which blocks picker execution
+    _PICKER_COMMANDS = frozenset({"model", "skin", "personality"})
+
     @staticmethod
     def _completion_text(cmd_name: str, word: str) -> str:
         """Return replacement text for a completion.
@@ -1123,8 +1140,17 @@ class SlashCommandCompleter(Completer):
         returning ``help`` would be a no-op and prompt_toolkit suppresses the
         menu. Appending a trailing space keeps the dropdown visible and makes
         backspacing retrigger it naturally.
+
+        However, commands that open pickers (model, skin, personality) should
+        NOT get a trailing space — the TUI would apply the completion on Enter
+        and block the picker from opening.
         """
-        return f"{cmd_name} " if cmd_name == word else cmd_name
+        if cmd_name != word:
+            return cmd_name
+        # Don't add space for picker commands — allows Enter to execute them
+        if cmd_name in SlashCommandCompleter._PICKER_COMMANDS:
+            return cmd_name
+        return f"{cmd_name} "
 
     @staticmethod
     def _extract_path_word(text: str) -> str | None:

hermes_cli/config.py

@@ -1292,7 +1292,10 @@ DEFAULT_CONFIG = {
         # for a single update run.
         "pre_update_backup": False,
         # How many pre-update backup zips to retain.  Older ones are pruned
-        # automatically after each successful backup.
+        # automatically after each successful backup.  Values below 1 are
+        # floored to 1 — the backup just created is always preserved.  To
+        # disable backups entirely, set ``pre_update_backup: false`` above
+        # rather than ``backup_keep: 0``.
         "backup_keep": 5,
     },
 
@@ -4682,7 +4685,9 @@ def set_config_value(key: str, value: str):
         "terminal.vercel_runtime": "TERMINAL_VERCEL_RUNTIME",
         "terminal.docker_mount_cwd_to_workspace": "TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE",
         "terminal.docker_run_as_host_user": "TERMINAL_DOCKER_RUN_AS_HOST_USER",
-        "terminal.cwd": "TERMINAL_CWD",
+        # terminal.cwd intentionally excluded — CLI resolves at runtime,
+        # gateway bridges it in gateway/run.py. Persisting to .env causes
+        # stale values to poison child processes.
         "terminal.timeout": "TERMINAL_TIMEOUT",
         "terminal.sandbox_dir": "TERMINAL_SANDBOX_DIR",
         "terminal.persistent_shell": "TERMINAL_PERSISTENT_SHELL",

hermes_cli/curses_ui.py

@@ -156,6 +156,8 @@ def curses_checklist(
         flush_stdin()
         return result_holder[0] if result_holder[0] is not None else cancel_returns
 
+    except KeyboardInterrupt:
+        return cancel_returns
     except Exception:
         return _numbered_fallback(title, items, selected, cancel_returns, status_fn)
 
@@ -278,6 +280,8 @@ def curses_radiolist(
         flush_stdin()
         return result_holder[0] if result_holder[0] is not None else cancel_returns
 
+    except KeyboardInterrupt:
+        return cancel_returns
     except Exception:
         return _radio_numbered_fallback(title, items, selected, cancel_returns)
 
@@ -401,6 +405,8 @@ def curses_single_select(
             return None
         return result_holder[0]
 
+    except KeyboardInterrupt:
+        return None
     except Exception:
         all_items = list(items) + [cancel_label]
         cancel_idx = len(items)

hermes_cli/debug.py

@@ -1,12 +1,19 @@
-"""``hermes debug`` — debug tools for Hermes Agent.
+"""``hermes debug`` debug tools for Hermes Agent.
 
 Currently supports:
     hermes debug share    Upload debug report (system info + logs) to a
                           paste service and print a shareable URL.
+                          By default, log content is run through
+                          ``agent.redact.redact_sensitive_text`` with
+                          ``force=True`` before upload so credentials in
+                          ``~/.hermes/logs/*.log`` are not leaked into
+                          the public paste service. Pass ``--no-redact``
+                          to disable.
 """
 
 import io
 import json
+import logging
 import sys
 import time
 import urllib.error
@@ -19,6 +26,16 @@ from typing import Optional
 from hermes_constants import get_hermes_home
 from utils import atomic_replace
 
+logger = logging.getLogger(__name__)
+
+# Banner prepended to upload-bound log content when redaction is enabled.
+# Visible in the public paste so reviewers know the content was sanitized.
+# Kept short; the trailing newline guarantees the banner sits on its own line.
+_REDACTION_BANNER = (
+    "[hermes debug share: log content redacted at upload time. "
+    "run with --no-redact to disable]\n"
+)
+
 
 # ---------------------------------------------------------------------------
 # Paste services — try paste.rs first, dpaste.com as fallback.
@@ -368,17 +385,40 @@ def _resolve_log_path(log_name: str) -> Optional[Path]:
     return None
 
 
+def _redact_log_text(text: str) -> str:
+    """Run ``redact_sensitive_text`` with ``force=True`` over upload-bound text.
+
+    Uses ``force=True`` so redaction fires regardless of the operator's
+    ``security.redact_secrets`` setting. The local on-disk log file is
+    not modified; only the in-memory copy headed for the public paste
+    service is sanitized. Returns the redacted text (or the original
+    when empty / non-string).
+    """
+    if not text:
+        return text
+    from agent.redact import redact_sensitive_text
+
+    return redact_sensitive_text(text, force=True)
+
+
 def _capture_log_snapshot(
     log_name: str,
     *,
     tail_lines: int,
     max_bytes: int = _MAX_LOG_BYTES,
+    redact: bool = True,
 ) -> LogSnapshot:
     """Capture a log once and derive summary/full-log views from it.
 
     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.
+
+    When ``redact`` is True (the default), both ``tail_text`` and
+    ``full_text`` are run through ``_redact_log_text`` so the snapshot
+    returned is upload-safe. The on-disk log file is never modified.
+    Pass ``redact=False`` to capture original log content (used by
+    ``hermes debug share --no-redact``).
     """
     log_path = _resolve_log_path(log_name)
     if log_path is None:
@@ -438,18 +478,34 @@ def _capture_log_snapshot(
         if truncated:
             full_text = f"[... truncated — showing last ~{max_bytes // 1024}KB ...]\n{full_text}"
 
+        if redact:
+            tail_text = _redact_log_text(tail_text)
+            full_text = _redact_log_text(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."""
+def _capture_default_log_snapshots(
+    log_lines: int, *, redact: bool = True
+) -> dict[str, LogSnapshot]:
+    """Capture all logs used by debug-share exactly once.
+
+    ``redact`` is forwarded to each ``_capture_log_snapshot`` call so all
+    captured logs share the same redaction policy for a given run.
+    """
     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),
+        "agent": _capture_log_snapshot(
+            "agent", tail_lines=log_lines, redact=redact
+        ),
+        "errors": _capture_log_snapshot(
+            "errors", tail_lines=errors_lines, redact=redact
+        ),
+        "gateway": _capture_log_snapshot(
+            "gateway", tail_lines=errors_lines, redact=redact
+        ),
     }
 
 
@@ -532,6 +588,7 @@ def run_debug_share(args):
     log_lines = getattr(args, "lines", 200)
     expiry = getattr(args, "expire", 7)
     local_only = getattr(args, "local", False)
+    redact = not getattr(args, "no_redact", False)
 
     if not local_only:
         print(_PRIVACY_NOTICE)
@@ -539,8 +596,16 @@ def run_debug_share(args):
     print("Collecting debug report...")
 
     # Capture dump once — prepended to every paste for context.
+    # The dump is already redacted at extract time via dump.py:_redact;
+    # log_snapshots are redacted by _capture_default_log_snapshots when
+    # redact=True so credentials never reach the public paste service.
     dump_text = _capture_dump()
-    log_snapshots = _capture_default_log_snapshots(log_lines)
+    log_snapshots = _capture_default_log_snapshots(log_lines, redact=redact)
+
+    if redact:
+        logger.info(
+            "hermes debug share: applied force-mode redaction to log snapshots before upload"
+        )
 
     report = collect_debug_report(
         log_lines=log_lines,
@@ -556,6 +621,15 @@ def run_debug_share(args):
     if gateway_log:
         gateway_log = dump_text + "\n\n--- full gateway.log ---\n" + gateway_log
 
+    # Visible banner so reviewers reading the public paste know redaction
+    # was applied at upload time. Banner is omitted under --no-redact.
+    if redact:
+        report = _REDACTION_BANNER + report
+        if agent_log:
+            agent_log = _REDACTION_BANNER + agent_log
+        if gateway_log:
+            gateway_log = _REDACTION_BANNER + gateway_log
+
     if local_only:
         print(report)
         if agent_log:
@@ -666,6 +740,7 @@ def run_debug(args):
         print("  --lines N    Number of log lines to include (default: 200)")
         print("  --expire N   Paste expiry in days (default: 7)")
         print("  --local      Print report locally instead of uploading")
+        print("  --no-redact  Disable upload-time secret redaction (default: redact)")
         print()
         print("Options (delete):")
         print("  <url> ...    One or more paste URLs to delete")

hermes_cli/doctor.py

@@ -935,6 +935,8 @@ def run_doctor(args):
         agent_browser_path = PROJECT_ROOT / "node_modules" / "agent-browser"
         if agent_browser_path.exists():
             check_ok("agent-browser (Node.js)", "(browser automation)")
+        elif shutil.which("agent-browser"):
+            check_ok("agent-browser", "(browser automation)")
         else:
             if _is_termux():
                 check_info("agent-browser is not installed (expected in the tested Termux path)")
@@ -1096,9 +1098,10 @@ def run_doctor(args):
         ("Hugging Face",     ("HF_TOKEN",),                                   "https://router.huggingface.co/v1/models", "HF_BASE_URL", True),
         ("NVIDIA NIM",       ("NVIDIA_API_KEY",),                             "https://integrate.api.nvidia.com/v1/models", "NVIDIA_BASE_URL", True),
         ("Alibaba/DashScope", ("DASHSCOPE_API_KEY",),                         "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models", "DASHSCOPE_BASE_URL", True),
-        # MiniMax: the /anthropic endpoint doesn't support /models, but the /v1 endpoint does.
+        # MiniMax global: /v1 endpoint supports /models.
         ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
-        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", True),
+        # MiniMax CN: /v1 endpoint does NOT support /models (returns 404).
+        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", False),
         ("Vercel AI Gateway",       ("AI_GATEWAY_API_KEY",),                          "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
         ("Kilo Code",        ("KILOCODE_API_KEY",),                            "https://api.kilo.ai/api/gateway/models",  "KILOCODE_BASE_URL", True),
         ("OpenCode Zen",     ("OPENCODE_ZEN_API_KEY",),                        "https://opencode.ai/zen/v1/models",  "OPENCODE_ZEN_BASE_URL", True),

hermes_cli/gateway.py

@@ -237,6 +237,26 @@ def _graceful_restart_via_sigusr1(pid: int, drain_timeout: float) -> bool:
     return False
 
 
+def _get_ancestor_pids() -> set[int]:
+    """Return the set of PIDs in the current process's ancestor chain.
+
+    Walks from the current PID up to PID 1 (init) so that process-table scans
+    never match the calling CLI process or any of its parents.  This prevents
+    ``hermes gateway status`` from falsely counting the ``hermes`` CLI that
+    invoked it as a running gateway instance (see #13242).
+    """
+    ancestors: set[int] = set()
+    pid = os.getpid()
+    # Cap iterations to avoid infinite loops on exotic platforms.
+    for _ in range(64):
+        ancestors.add(pid)
+        parent = _get_parent_pid(pid)
+        if parent is None or parent <= 0 or parent in ancestors:
+            break
+        pid = parent
+    return ancestors
+
+
 def _append_unique_pid(pids: list[int], pid: int | None, exclude_pids: set[int]) -> None:
     if pid is None or pid <= 0:
         return
@@ -252,6 +272,10 @@ def _scan_gateway_pids(exclude_pids: set[int], all_profiles: bool = False) -> li
     a live gateway when the PID file is stale/missing, and ``--all`` sweeps can
     discover gateways outside the current profile.
     """
+    # Exclude the entire ancestor chain so the CLI process that invoked this
+    # scan (e.g. ``hermes gateway status``) is never mistaken for a running
+    # gateway.  See #13242.
+    exclude_pids = exclude_pids | _get_ancestor_pids()
     pids: list[int] = []
     patterns = [
         "hermes_cli.main gateway",
@@ -690,6 +714,32 @@ def _print_gateway_process_mismatch(snapshot: GatewayRuntimeSnapshot) -> None:
     print("  can refuse to start another copy until this process stops.")
 
 
+def _print_other_profiles_gateway_status() -> None:
+    """Print a summary of gateway status across all profiles.
+
+    Shown at the bottom of ``hermes gateway status`` output so users with
+    multiple profiles can tell at a glance which gateways are running and
+    avoid confusing another profile's process with the current one.
+    """
+    try:
+        from hermes_cli.profiles import get_active_profile_name
+
+        current = get_active_profile_name()
+        other_processes = [
+            p for p in find_profile_gateway_processes()
+            if p.profile != current
+        ]
+        if not other_processes:
+            return
+
+        print()
+        print("Other profiles:")
+        for proc in other_processes:
+            print(f"  ✓ {proc.profile:<16s} — PID {proc.pid}")
+    except Exception:
+        pass
+
+
 def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None,
                            all_profiles: bool = False) -> int:
     """Kill any running gateway processes. Returns count killed.
@@ -1921,6 +1971,15 @@ def systemd_uninstall(system: bool = False):
     print(f"✓ {_service_scope_label(system).capitalize()} service uninstalled")
 
 
+def _require_service_installed(action: str, system: bool = False) -> None:
+    unit_path = get_systemd_unit_path(system=system)
+    if not unit_path.exists():
+        scope_flag = " --system" if system else ""
+        print(f"✗ Gateway service is not installed")
+        print(f"  Run: {'sudo ' if system else ''}hermes gateway install{scope_flag}")
+        sys.exit(1)
+
+
 def systemd_start(system: bool = False):
     system = _select_systemd_scope(system)
     if system:
@@ -1930,6 +1989,7 @@ def systemd_start(system: bool = False):
         # reachable (common on fresh RHEL/Debian SSH sessions without linger).
         # Raises UserSystemdUnavailableError with a remediation message.
         _preflight_user_systemd()
+    _require_service_installed("start", system=system)
     refresh_systemd_unit_if_needed(system=system)
     _run_systemctl(["start", get_service_name()], system=system, check=True, timeout=30)
     print(f"✓ {_service_scope_label(system).capitalize()} service started")
@@ -1940,6 +2000,7 @@ def systemd_stop(system: bool = False):
     system = _select_systemd_scope(system)
     if system:
         _require_root_for_system_service("stop")
+    _require_service_installed("stop", system=system)
     _run_systemctl(["stop", get_service_name()], system=system, check=True, timeout=90)
     print(f"✓ {_service_scope_label(system).capitalize()} service stopped")
 
@@ -1951,6 +2012,7 @@ def systemd_restart(system: bool = False):
         _require_root_for_system_service("restart")
     else:
         _preflight_user_systemd()
+    _require_service_installed("restart", system=system)
     refresh_systemd_unit_if_needed(system=system)
     from gateway.status import get_running_pid
 
@@ -2442,6 +2504,20 @@ def run_gateway(verbose: int = 0, quiet: bool = False, replace: bool = False):
                  hasn't fully exited yet.
     """
     sys.path.insert(0, str(PROJECT_ROOT))
+
+    # Refresh the systemd unit definition on every boot so that restart
+    # settings (RestartSec, StartLimitIntervalSec, etc.) stay current even
+    # when the process was respawned via exit-code-75 (stale-code or
+    # /restart) rather than through `hermes gateway restart` which already
+    # calls refresh_systemd_unit_if_needed().  Without this, a code update
+    # that ships new unit settings won't take effect until the next manual
+    # `hermes gateway start/restart` — leaving the gateway vulnerable to
+    # the exact failure mode the new settings were meant to prevent.
+    if supports_systemd_services():
+        try:
+            refresh_systemd_unit_if_needed(system=False)
+        except Exception:
+            pass  # best-effort; don't block gateway startup
     
     from gateway.run import start_gateway
     
@@ -4456,6 +4532,9 @@ def _gateway_command_inner(args):
                     print("  hermes gateway install  # Install as user service")
                     print("  sudo hermes gateway install --system  # Install as boot-time system service")
 
+        # Show other profiles' gateway status for multi-profile awareness
+        _print_other_profiles_gateway_status()
+
     elif subcmd == "migrate-legacy":
         # Stop, disable, and remove legacy Hermes gateway unit files from
         # pre-rename installs (e.g. hermes.service). Profile units and

hermes_cli/kanban.py

@@ -169,11 +169,93 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
             "or docs/hermes-kanban-v1-spec.pdf for the full design."
         ),
     )
+    # --- global --board flag ---
+    # Applies to every subcommand below. When set, scopes all reads and
+    # writes to that board's DB. When omitted, resolves via the
+    # HERMES_KANBAN_BOARD env var, then the persisted current-board
+    # file, then "default". See kanban_db.get_current_board().
+    kanban_parser.add_argument(
+        "--board",
+        default=None,
+        metavar="<slug>",
+        help=(
+            "Board slug to operate on. Defaults to the current board "
+            "(set via `hermes kanban boards switch <slug>` or the "
+            "HERMES_KANBAN_BOARD env var). Use `hermes kanban boards list` "
+            "to see all boards."
+        ),
+    )
     sub = kanban_parser.add_subparsers(dest="kanban_action")
 
     # --- init ---
     sub.add_parser("init", help="Create kanban.db if missing (idempotent)")
 
+    # --- boards (new in v2: multi-project support) ---
+    p_boards = sub.add_parser(
+        "boards",
+        help="Manage kanban boards (one board per project / workstream)",
+        description=(
+            "Boards let you separate unrelated streams of work "
+            "(projects, repos, domains) into isolated queues. Each "
+            "board has its own DB, workspaces directory, and dispatcher "
+            "loop — tasks on one board cannot collide with tasks on "
+            "another. The first board is 'default' and always exists."
+        ),
+    )
+    boards_sub = p_boards.add_subparsers(dest="boards_action")
+
+    b_list = boards_sub.add_parser(
+        "list", aliases=["ls"],
+        help="List all boards with task counts",
+    )
+    b_list.add_argument("--json", action="store_true")
+    b_list.add_argument("--all", action="store_true",
+                        help="Include archived boards too")
+
+    b_create = boards_sub.add_parser(
+        "create", aliases=["new"],
+        help="Create a new board",
+    )
+    b_create.add_argument("slug",
+                          help="Board slug (kebab-case, e.g. atm10-server)")
+    b_create.add_argument("--name", default=None,
+                          help="Human-readable display name (defaults to Title Case of slug)")
+    b_create.add_argument("--description", default=None,
+                          help="Optional description")
+    b_create.add_argument("--icon", default=None,
+                          help="Optional emoji or single-character icon for the dashboard")
+    b_create.add_argument("--color", default=None,
+                          help="Optional hex color (e.g. '#8b5cf6') for the dashboard")
+    b_create.add_argument("--switch", action="store_true",
+                          help="Switch to the new board after creating it")
+
+    b_rm = boards_sub.add_parser(
+        "rm", aliases=["remove", "delete"],
+        help="Archive (default) or delete a board",
+    )
+    b_rm.add_argument("slug")
+    b_rm.add_argument("--delete", action="store_true",
+                      help="Hard-delete the board directory instead of archiving it. "
+                           "Default is to move it to boards/_archived/ so it's recoverable.")
+
+    b_switch = boards_sub.add_parser(
+        "switch", aliases=["use"],
+        help="Set the active board for subsequent CLI calls",
+    )
+    b_switch.add_argument("slug")
+
+    boards_sub.add_parser(
+        "show", aliases=["current"],
+        help="Print the currently-active board slug",
+    )
+
+    b_rename = boards_sub.add_parser(
+        "rename",
+        help="Change a board's human-readable display name (slug is immutable)",
+    )
+    b_rename.add_argument("slug")
+    b_rename.add_argument("name", help="New display name")
+
     # --- create ---
     p_create = sub.add_parser("create", help="Create a new task")
     p_create.add_argument("title", help="Task title")
@@ -366,7 +448,7 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
     # --- log ---
     p_log = sub.add_parser(
         "log",
-        help="Print the worker log for a task (from $HERMES_HOME/kanban/logs/)",
+        help="Print the worker log for a task (from <kanban-root>/kanban/logs/)",
     )
     p_log.add_argument("task_id")
     p_log.add_argument("--tail", type=int, default=None,
@@ -442,6 +524,38 @@ def kanban_command(args: argparse.Namespace) -> int:
             )
         return 0
 
+    # `--board <slug>` applies to every subcommand below by way of an
+    # env-var pin for the duration of this call. Using HERMES_KANBAN_BOARD
+    # (rather than threading `board=` through 50+ kb.connect() sites)
+    # keeps the patch small and inherits the exact same resolution the
+    # dispatcher uses for workers — consistency is a feature here.
+    board_override = getattr(args, "board", None)
+    if board_override:
+        try:
+            normed = kb._normalize_board_slug(board_override)
+        except ValueError as exc:
+            print(f"kanban: {exc}", file=sys.stderr)
+            return 2
+        if not normed:
+            print("kanban: --board requires a slug", file=sys.stderr)
+            return 2
+        # Boards other than 'default' must already exist — typoed slugs
+        # would otherwise silently create an empty board.
+        if normed != kb.DEFAULT_BOARD and not kb.board_exists(normed):
+            print(
+                f"kanban: board {normed!r} does not exist. "
+                f"Create it with `hermes kanban boards create {normed}`.",
+                file=sys.stderr,
+            )
+            return 1
+        os.environ["HERMES_KANBAN_BOARD"] = normed
+
+    # Boards management doesn't touch the DB at all — dispatch early so
+    # fresh installs that haven't initialized any DB can still use
+    # `hermes kanban boards create …`.
+    if action == "boards":
+        return _dispatch_boards(args)
+
     # Auto-initialize the DB before dispatching any subcommand. init_db
     # is idempotent, so running it every invocation is cheap (one
     # SELECT against sqlite_master when tables already exist) and
@@ -513,6 +627,185 @@ def _profile_author() -> str:
         return "user"
 
 
+# ---------------------------------------------------------------------------
+# Boards management (hermes kanban boards …)
+# ---------------------------------------------------------------------------
+
+def _dispatch_boards(args: argparse.Namespace) -> int:
+    """Handle ``hermes kanban boards <action>``.
+
+    Boards management is deliberately separate from the task-level
+    commands: it operates on the filesystem (board directories,
+    ``current`` pointer, ``board.json``), not on the per-board SQLite
+    DB, so a fresh HERMES_HOME that has never called ``kanban init``
+    can still run ``boards create`` / ``boards list``.
+    """
+    sub = getattr(args, "boards_action", None) or "list"
+    if sub in ("list", "ls"):
+        return _cmd_boards_list(args)
+    if sub in ("create", "new"):
+        return _cmd_boards_create(args)
+    if sub in ("rm", "remove", "delete"):
+        return _cmd_boards_rm(args)
+    if sub in ("switch", "use"):
+        return _cmd_boards_switch(args)
+    if sub in ("show", "current"):
+        return _cmd_boards_show(args)
+    if sub == "rename":
+        return _cmd_boards_rename(args)
+    print(f"kanban boards: unknown action {sub!r}", file=sys.stderr)
+    return 2
+
+
+def _board_task_counts(slug: str) -> dict[str, int]:
+    """Return ``{status: count}`` for a board. Safe to call on an empty DB."""
+    try:
+        path = kb.kanban_db_path(board=slug)
+        if not path.exists():
+            return {}
+        with kb.connect(board=slug) as conn:
+            rows = conn.execute(
+                "SELECT status, COUNT(*) AS n FROM tasks GROUP BY status"
+            ).fetchall()
+        return {r["status"]: int(r["n"]) for r in rows}
+    except Exception:
+        return {}
+
+
+def _cmd_boards_list(args: argparse.Namespace) -> int:
+    include_archived = bool(getattr(args, "all", False))
+    boards = kb.list_boards(include_archived=include_archived)
+    # Enrich each entry with task counts + whether it's the current board.
+    current = kb.get_current_board()
+    for b in boards:
+        b["is_current"] = (b["slug"] == current)
+        b["counts"] = _board_task_counts(b["slug"])
+        b["total"] = sum(b["counts"].values())
+    if getattr(args, "json", False):
+        print(json.dumps(boards, indent=2, ensure_ascii=False))
+        return 0
+    # Human table: marker (•) for current, slug, display name, counts.
+    if not boards:
+        print("(no boards — create one with `hermes kanban boards create <slug>`)")
+        return 0
+    print(f"{'':2s}  {'SLUG':24s}  {'NAME':28s}  COUNTS")
+    for b in boards:
+        marker = "●" if b["is_current"] else " "
+        counts = b["counts"] or {}
+        counts_str = (
+            ", ".join(f"{k}={v}" for k, v in sorted(counts.items()))
+            or "(empty)"
+        )
+        name = b.get("name") or ""
+        if b.get("archived"):
+            name += " [archived]"
+        print(f"{marker:2s}  {b['slug']:24s}  {name:28s}  {counts_str}")
+    print()
+    print(f"Current board: {current}")
+    if len(boards) > 1:
+        print("Switch boards with `hermes kanban boards switch <slug>`.")
+    return 0
+
+
+def _cmd_boards_create(args: argparse.Namespace) -> int:
+    try:
+        normed = kb._normalize_board_slug(args.slug)
+    except ValueError as exc:
+        print(f"kanban boards create: {exc}", file=sys.stderr)
+        return 2
+    if not normed:
+        print("kanban boards create: slug is required", file=sys.stderr)
+        return 2
+    already = kb.board_exists(normed) and normed != kb.DEFAULT_BOARD
+    meta = kb.create_board(
+        normed,
+        name=args.name,
+        description=args.description,
+        icon=args.icon,
+        color=args.color,
+    )
+    verb = "already exists" if already else "created"
+    print(f"Board {meta['slug']!r} {verb}.")
+    print(f"  Display name: {meta.get('name', '')}")
+    print(f"  DB path:      {meta['db_path']}")
+    if getattr(args, "switch", False):
+        kb.set_current_board(meta["slug"])
+        print(f"  Switched to {meta['slug']!r}.")
+    else:
+        print(f"  Use `hermes kanban boards switch {meta['slug']}` to make it current.")
+    return 0
+
+
+def _cmd_boards_rm(args: argparse.Namespace) -> int:
+    try:
+        res = kb.remove_board(args.slug, archive=not getattr(args, "delete", False))
+    except ValueError as exc:
+        print(f"kanban boards rm: {exc}", file=sys.stderr)
+        return 1
+    if res["action"] == "archived":
+        print(f"Board {res['slug']!r} archived → {res['new_path']}")
+        print("Recover by moving the directory back to "
+              "<root>/kanban/boards/<slug>/.")
+    else:
+        print(f"Board {res['slug']!r} deleted.")
+    return 0
+
+
+def _cmd_boards_switch(args: argparse.Namespace) -> int:
+    try:
+        normed = kb._normalize_board_slug(args.slug)
+    except ValueError as exc:
+        print(f"kanban boards switch: {exc}", file=sys.stderr)
+        return 2
+    if not normed:
+        print("kanban boards switch: slug is required", file=sys.stderr)
+        return 2
+    if not kb.board_exists(normed):
+        print(
+            f"kanban boards switch: board {normed!r} does not exist. "
+            f"Create it with `hermes kanban boards create {normed}`.",
+            file=sys.stderr,
+        )
+        return 1
+    kb.set_current_board(normed)
+    print(f"Active board is now {normed!r}.")
+    return 0
+
+
+def _cmd_boards_show(args: argparse.Namespace) -> int:
+    current = kb.get_current_board()
+    meta = kb.read_board_metadata(current)
+    counts = _board_task_counts(current)
+    total = sum(counts.values())
+    print(f"Current board: {current}")
+    print(f"  Display name: {meta.get('name', '')}")
+    if meta.get("description"):
+        print(f"  Description:  {meta['description']}")
+    print(f"  DB path:      {meta['db_path']}")
+    print(f"  Tasks:        {total} total"
+          + (f" ({', '.join(f'{k}={v}' for k, v in sorted(counts.items()))})"
+             if counts else ""))
+    return 0
+
+
+def _cmd_boards_rename(args: argparse.Namespace) -> int:
+    try:
+        normed = kb._normalize_board_slug(args.slug)
+    except ValueError as exc:
+        print(f"kanban boards rename: {exc}", file=sys.stderr)
+        return 2
+    if not normed or not kb.board_exists(normed):
+        print(f"kanban boards rename: board {args.slug!r} does not exist",
+              file=sys.stderr)
+        return 1
+    meta = kb.write_board_metadata(normed, name=args.name)
+    print(f"Board {normed!r} renamed to {meta['name']!r}.")
+    return 0
+
+
+# ---------------------------------------------------------------------------
+
+
 def _parse_duration(val) -> Optional[int]:
     """Parse ``30s`` / ``5m`` / ``2h`` / ``1d`` or a raw integer → seconds.
 
@@ -662,6 +955,21 @@ def _cmd_list(args: argparse.Namespace) -> int:
     if getattr(args, "json", False):
         print(json.dumps([_task_to_dict(t) for t in tasks], indent=2, ensure_ascii=False))
         return 0
+    # Passive discoverability: when the user has multiple boards, surface
+    # which one they're looking at in the list header. Single-board users
+    # never see this — the feature stays invisible until you opt in.
+    try:
+        all_boards = kb.list_boards(include_archived=False)
+    except Exception:
+        all_boards = []
+    if len(all_boards) > 1:
+        current = kb.get_current_board()
+        other_count = len(all_boards) - 1
+        print(
+            f"Board: {current} "
+            f"({other_count} other board{'s' if other_count != 1 else ''} — "
+            f"`hermes kanban boards list`)\n"
+        )
     if not tasks:
         print("(no matching tasks)")
         return 0

hermes_cli/kanban_db.py

@@ -1,8 +1,56 @@
-"""SQLite-backed Kanban board for multi-profile collaboration.
+"""SQLite-backed Kanban board for multi-profile, multi-project collaboration.
 
-The board lives at ``$HERMES_HOME/kanban.db`` (profile-agnostic on purpose:
-multiple profiles on the same machine all see the same board, which IS the
-coordination primitive).
+In a fresh install the board lives at ``<root>/kanban.db`` where
+``<root>`` is the **shared Hermes root** (the parent of any active
+profile). Profiles intentionally collapse onto a shared board: it IS
+the cross-profile coordination primitive. A worker spawned with
+``hermes -p <profile>`` joins the same board as the dispatcher that
+claimed the task. The same applies to ``<root>/kanban/workspaces/`` and
+``<root>/kanban/logs/``.
+
+**Multiple boards (projects):** users can create additional boards to
+separate unrelated streams of work (e.g. one per project / repo / domain).
+Each board is a directory under ``<root>/kanban/boards/<slug>/`` with
+its own ``kanban.db``, ``workspaces/``, and ``logs/``. All boards share
+the profile's Hermes home but are otherwise isolated: a worker spawned
+for a task on board ``atm10-server`` sees only that board's tasks,
+cannot enumerate other boards, and its dispatcher ticks don't touch
+other boards' DBs.
+
+The first (and for single-project users, only) board is ``default``.
+For back-compat its on-disk DB is ``<root>/kanban.db`` (not
+``boards/default/kanban.db``), so installs that predate the boards
+feature keep working with zero migration. See :func:`kanban_db_path`.
+
+Board resolution order (highest precedence first, all optional):
+
+* ``board=`` argument passed directly to :func:`connect` / :func:`init_db`
+  (explicit — used by the CLI ``--board`` flag and the dashboard
+  ``?board=...`` query param).
+* ``HERMES_KANBAN_BOARD`` env var (used by the dispatcher to pin workers
+  to the board their task lives on — workers cannot see other boards).
+* ``HERMES_KANBAN_DB`` env var (pins the DB file path directly — legacy
+  override still honoured; highest precedence when the file path itself
+  is what the caller wants to force).
+* ``<root>/kanban/current`` — a one-line text file holding the slug of
+  the "currently selected" board. Written by ``hermes kanban boards
+  switch <slug>``. When absent, the active board is ``default``.
+
+In standard installs ``<root>`` is ``~/.hermes``. In Docker / custom
+deployments where ``HERMES_HOME`` points outside ``~/.hermes`` (e.g.
+``/opt/hermes``), ``<root>`` is ``HERMES_HOME``. Legacy env-var
+overrides still work:
+
+* ``HERMES_KANBAN_DB`` — pin the database file path directly.
+* ``HERMES_KANBAN_WORKSPACES_ROOT`` — pin the workspaces root directly.
+* ``HERMES_KANBAN_HOME`` — pin the umbrella root that anchors kanban
+  paths. Useful for tests and unusual deployments.
+
+The dispatcher injects ``HERMES_KANBAN_DB``,
+``HERMES_KANBAN_WORKSPACES_ROOT``, and ``HERMES_KANBAN_BOARD`` into
+worker subprocess env so workers converge on the exact DB the
+dispatcher used to claim their task — even under unusual symlink or
+Docker layouts.
 
 Schema is intentionally small: tasks, task_links, task_comments,
 task_events.  The ``workspace_kind`` field decouples coordination from git
@@ -15,6 +63,9 @@ transactions + compare-and-swap (CAS) updates on ``tasks.status`` and
 ``tasks.claim_lock``.  SQLite serializes writers via its WAL lock, so at
 most one claimer can win any given task.  Losers observe zero affected
 rows and move on -- no retry loops, no distributed-lock machinery.
+The CAS coordination is **per-board** — each board is a separate DB,
+so multi-board installs get the same atomicity guarantees without any
+new locking.
 """
 
 from __future__ import annotations
@@ -22,6 +73,7 @@ from __future__ import annotations
 import contextlib
 import json
 import os
+import re
 import secrets
 import sqlite3
 import sys
@@ -61,16 +113,438 @@ _CTX_MAX_COMMENT_BYTES  = 2 * 1024   # 2 KB per comment
 # Paths
 # ---------------------------------------------------------------------------
 
-def kanban_db_path() -> Path:
-    """Return the path to ``kanban.db`` inside the active HERMES_HOME."""
-    from hermes_constants import get_hermes_home
-    return get_hermes_home() / "kanban.db"
+DEFAULT_BOARD = "default"
+
+# Slug validator: lowercase alphanumerics, digits, hyphens; 1–64 chars.
+# Strict enough to stop traversal (`..`) and embedded path separators, loose
+# enough that kebab-case names like ``atm10-server`` or ``hermes-agent``
+# pass without fuss. Board names with display formatting (spaces, emoji)
+# live in ``board.json``; the slug is just the directory name.
+_BOARD_SLUG_RE = re.compile(r"^[a-z0-9][a-z0-9\-_]{0,63}$")
 
 
-def workspaces_root() -> Path:
-    """Return the directory under which ``scratch`` workspaces are created."""
-    from hermes_constants import get_hermes_home
-    return get_hermes_home() / "kanban" / "workspaces"
+def _normalize_board_slug(slug: Optional[str]) -> Optional[str]:
+    """Lowercase + strip a slug; validate; return ``None`` for empty."""
+    if slug is None:
+        return None
+    s = str(slug).strip().lower()
+    if not s:
+        return None
+    if not _BOARD_SLUG_RE.match(s):
+        raise ValueError(
+            f"invalid board slug {slug!r}: must be 1-64 chars, lowercase "
+            f"alphanumerics / hyphens / underscores, not starting with '-' or '_'"
+        )
+    return s
+
+
+def kanban_home() -> Path:
+    """Return the shared Hermes root that anchors the kanban board.
+
+    Resolution order:
+
+    1. ``HERMES_KANBAN_HOME`` env var when set and non-empty (explicit
+       override for tests and unusual deployments).
+    2. ``get_default_hermes_root()``, which already returns ``<root>``
+       when ``HERMES_HOME`` is ``<root>/profiles/<name>``, and returns
+       ``HERMES_HOME`` directly for Docker / custom deployments.
+
+    The kanban board is shared across profiles **by design** (see the
+    module docstring). Resolving the kanban paths through the active
+    profile's ``HERMES_HOME`` would silently fork the board per profile,
+    which breaks the dispatcher / worker handoff.
+    """
+    override = os.environ.get("HERMES_KANBAN_HOME", "").strip()
+    if override:
+        return Path(override).expanduser()
+    from hermes_constants import get_default_hermes_root
+    return get_default_hermes_root()
+
+
+def boards_root() -> Path:
+    """Return ``<root>/kanban/boards`` — the parent of non-default board dirs.
+
+    ``default`` is intentionally NOT under this directory — its DB lives at
+    ``<root>/kanban.db`` for back-compat with pre-boards installs. This
+    function returns the directory where *additional* named boards live,
+    used by :func:`list_boards` to enumerate them.
+    """
+    return kanban_home() / "kanban" / "boards"
+
+
+def current_board_path() -> Path:
+    """Return the path to ``<root>/kanban/current``.
+
+    One-line text file written by ``hermes kanban boards switch <slug>``
+    to persist the user's board selection across CLI invocations. Absent
+    by default (meaning: active board is ``default``).
+    """
+    return kanban_home() / "kanban" / "current"
+
+
+def get_current_board() -> str:
+    """Return the active board slug, honouring the resolution chain.
+
+    Order (highest precedence first):
+
+    1. ``HERMES_KANBAN_BOARD`` env var (set by the dispatcher on worker
+       spawn, or manually for ad-hoc overrides).
+    2. ``<root>/kanban/current`` on disk (set by ``hermes kanban boards
+       switch``).
+    3. ``DEFAULT_BOARD`` (``"default"``).
+
+    A malformed slug at any step falls through to the next layer with a
+    best-effort warning — the dispatcher must never crash because a user
+    hand-edited a file.
+    """
+    env = os.environ.get("HERMES_KANBAN_BOARD", "").strip()
+    if env:
+        try:
+            normed = _normalize_board_slug(env)
+            if normed:
+                return normed
+        except ValueError:
+            pass
+    try:
+        f = current_board_path()
+        if f.exists():
+            val = f.read_text(encoding="utf-8").strip()
+            if val:
+                try:
+                    normed = _normalize_board_slug(val)
+                    if normed:
+                        return normed
+                except ValueError:
+                    pass
+    except OSError:
+        pass
+    return DEFAULT_BOARD
+
+
+def set_current_board(slug: str) -> Path:
+    """Persist ``slug`` as the active board. Returns the file written.
+
+    Writes ``<root>/kanban/current``. The caller should validate the slug
+    exists first (via :func:`board_exists`) — this function does not —
+    so that ``hermes kanban boards switch <typo>`` returns an error
+    instead of silently pointing at nothing.
+    """
+    normed = _normalize_board_slug(slug)
+    if not normed:
+        raise ValueError("board slug is required")
+    path = current_board_path()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(normed + "\n", encoding="utf-8")
+    return path
+
+
+def clear_current_board() -> None:
+    """Remove ``<root>/kanban/current`` so the active board reverts to ``default``."""
+    try:
+        current_board_path().unlink()
+    except FileNotFoundError:
+        pass
+
+
+def board_dir(board: Optional[str] = None) -> Path:
+    """Return the on-disk directory for ``board``.
+
+    ``default`` is ``<root>/kanban/boards/default/`` **for metadata only**
+    (board.json + workspaces/ + logs/). Its DB file stays at
+    ``<root>/kanban.db`` for back-compat — see :func:`kanban_db_path`.
+
+    All other boards live at ``<root>/kanban/boards/<slug>/`` with
+    everything inside that directory including the ``kanban.db``.
+    """
+    slug = _normalize_board_slug(board) or DEFAULT_BOARD
+    return boards_root() / slug
+
+
+def board_exists(board: Optional[str] = None) -> bool:
+    """Return True if the board has a DB or a metadata dir on disk.
+
+    ``default`` is considered to always exist — its DB is created
+    on first :func:`connect` and there's no way for it to be missing
+    in a configuration where the kanban feature is usable at all.
+    """
+    slug = _normalize_board_slug(board) or DEFAULT_BOARD
+    if slug == DEFAULT_BOARD:
+        return True
+    d = board_dir(slug)
+    return d.is_dir() or (d / "kanban.db").exists()
+
+
+def kanban_db_path(board: Optional[str] = None) -> Path:
+    """Return the path to the ``kanban.db`` for ``board``.
+
+    Resolution (highest precedence first):
+
+    1. ``HERMES_KANBAN_DB`` env var — pins the path directly. Honoured for
+       back-compat and for the dispatcher→worker handoff (defense in
+       depth: dispatcher injects this into worker env so workers are
+       immune to any path-resolution disagreement).
+    2. When ``board`` arg is None, the active board from
+       :func:`get_current_board` is used.
+    3. Board ``default`` → ``<root>/kanban.db`` (back-compat path).
+       Other boards → ``<root>/kanban/boards/<slug>/kanban.db``.
+    """
+    override = os.environ.get("HERMES_KANBAN_DB", "").strip()
+    if override:
+        return Path(override).expanduser()
+    slug = _normalize_board_slug(board)
+    if slug is None:
+        slug = get_current_board()
+    if slug == DEFAULT_BOARD:
+        return kanban_home() / "kanban.db"
+    return board_dir(slug) / "kanban.db"
+
+
+def workspaces_root(board: Optional[str] = None) -> Path:
+    """Return the directory under which ``scratch`` workspaces are created.
+
+    Anchored per-board so workspaces don't leak between projects.
+    ``HERMES_KANBAN_WORKSPACES_ROOT`` pins the path directly (highest
+    precedence) — the dispatcher injects this into worker env.
+
+    ``default`` keeps the legacy path ``<root>/kanban/workspaces/`` so
+    that existing scratch workspaces from before the boards feature are
+    preserved. Other boards use ``<root>/kanban/boards/<slug>/workspaces/``.
+    """
+    override = os.environ.get("HERMES_KANBAN_WORKSPACES_ROOT", "").strip()
+    if override:
+        return Path(override).expanduser()
+    slug = _normalize_board_slug(board)
+    if slug is None:
+        slug = get_current_board()
+    if slug == DEFAULT_BOARD:
+        return kanban_home() / "kanban" / "workspaces"
+    return board_dir(slug) / "workspaces"
+
+
+def worker_logs_dir(board: Optional[str] = None) -> Path:
+    """Return the directory under which per-task worker logs are written.
+
+    ``default`` keeps the legacy path ``<root>/kanban/logs/``. Other
+    boards use ``<root>/kanban/boards/<slug>/logs/``. Logs follow the
+    board — makes ``hermes kanban log`` unambiguous even when multiple
+    boards have tasks with the same id.
+    """
+    slug = _normalize_board_slug(board)
+    if slug is None:
+        slug = get_current_board()
+    if slug == DEFAULT_BOARD:
+        return kanban_home() / "kanban" / "logs"
+    return board_dir(slug) / "logs"
+
+
+def board_metadata_path(board: Optional[str] = None) -> Path:
+    """Return the path to ``board.json`` for ``board``.
+
+    Stores display metadata (display name, description, icon, color,
+    created_at). The on-disk slug is the canonical identity; this file
+    is purely for presentation in the CLI / dashboard.
+    """
+    slug = _normalize_board_slug(board) or DEFAULT_BOARD
+    return board_dir(slug) / "board.json"
+
+
+def _default_board_display_name(slug: str) -> str:
+    """Turn a slug into a reasonable default display name.
+
+    ``atm10-server`` → ``Atm10 Server``. Users can override via
+    ``board.json`` but the default should look presentable in the
+    dashboard without any follow-up editing.
+    """
+    return " ".join(part.capitalize() for part in slug.replace("_", "-").split("-") if part) or slug
+
+
+def read_board_metadata(board: Optional[str] = None) -> dict:
+    """Return ``board.json`` contents (or synthesized defaults).
+
+    Never raises — a missing / malformed ``board.json`` falls back to a
+    synthesised entry so the dashboard always has something to render.
+    Includes the canonical ``slug`` and ``db_path`` so the caller
+    doesn't need to reconstruct them.
+    """
+    slug = _normalize_board_slug(board) or DEFAULT_BOARD
+    meta: dict[str, Any] = {
+        "slug": slug,
+        "name": _default_board_display_name(slug),
+        "description": "",
+        "icon": "",
+        "color": "",
+        "created_at": None,
+        "archived": False,
+    }
+    try:
+        p = board_metadata_path(slug)
+        if p.exists():
+            raw = json.loads(p.read_text(encoding="utf-8"))
+            if isinstance(raw, dict):
+                # Never let the metadata file claim a different slug than
+                # its directory — trust the filesystem.
+                raw["slug"] = slug
+                meta.update(raw)
+    except (OSError, json.JSONDecodeError):
+        pass
+    meta["db_path"] = str(kanban_db_path(slug))
+    return meta
+
+
+def write_board_metadata(
+    board: Optional[str],
+    *,
+    name: Optional[str] = None,
+    description: Optional[str] = None,
+    icon: Optional[str] = None,
+    color: Optional[str] = None,
+    archived: Optional[bool] = None,
+) -> dict:
+    """Create / update ``board.json`` for ``board``.
+
+    Preserves any existing fields not mentioned in the call. Sets
+    ``created_at`` on first write. Returns the resulting metadata dict.
+    """
+    slug = _normalize_board_slug(board) or DEFAULT_BOARD
+    meta = read_board_metadata(slug)
+    # Preserve existing DB-derived fields — they get re-computed each
+    # read but shouldn't be written into board.json.
+    meta.pop("db_path", None)
+    if name is not None:
+        meta["name"] = str(name).strip() or _default_board_display_name(slug)
+    if description is not None:
+        meta["description"] = str(description)
+    if icon is not None:
+        meta["icon"] = str(icon)
+    if color is not None:
+        meta["color"] = str(color)
+    if archived is not None:
+        meta["archived"] = bool(archived)
+    if not meta.get("created_at"):
+        meta["created_at"] = int(time.time())
+    path = board_metadata_path(slug)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(
+        json.dumps(meta, indent=2, ensure_ascii=False) + "\n",
+        encoding="utf-8",
+    )
+    meta["db_path"] = str(kanban_db_path(slug))
+    return meta
+
+
+def create_board(
+    slug: str,
+    *,
+    name: Optional[str] = None,
+    description: Optional[str] = None,
+    icon: Optional[str] = None,
+    color: Optional[str] = None,
+) -> dict:
+    """Create a new board directory + DB + metadata. Idempotent.
+
+    Returns the resulting metadata. Raises :class:`ValueError` for a
+    malformed slug; returns the existing metadata (not an error) if the
+    board already exists — matching ``mkdir -p`` semantics.
+    """
+    normed = _normalize_board_slug(slug)
+    if not normed:
+        raise ValueError("board slug is required")
+    meta = write_board_metadata(
+        normed,
+        name=name,
+        description=description,
+        icon=icon,
+        color=color,
+    )
+    # Touch the DB so list_boards() sees it immediately.
+    init_db(board=normed)
+    return meta
+
+
+def list_boards(*, include_archived: bool = True) -> list[dict]:
+    """Enumerate all boards that exist on disk.
+
+    Always includes ``default`` (even when the ``boards/default/``
+    metadata dir doesn't exist, because its DB is at the legacy path).
+    Other boards are discovered by scanning ``boards/`` for subdirectories
+    that either contain a ``kanban.db`` or a ``board.json``.
+
+    Returns a list of metadata dicts, sorted with ``default`` first and
+    the rest alphabetically.
+    """
+    entries: list[dict] = []
+    seen: set[str] = set()
+
+    # Default board is always first.
+    entries.append(read_board_metadata(DEFAULT_BOARD))
+    seen.add(DEFAULT_BOARD)
+
+    root = boards_root()
+    if root.is_dir():
+        for child in sorted(root.iterdir(), key=lambda p: p.name.lower()):
+            if not child.is_dir():
+                continue
+            slug = child.name
+            # Keep slug normalisation soft for discovery — but skip dirs
+            # that don't parse as valid slugs so we don't surface junk.
+            try:
+                normed = _normalize_board_slug(slug)
+            except ValueError:
+                continue
+            if not normed or normed in seen:
+                continue
+            has_db = (child / "kanban.db").exists()
+            has_meta = (child / "board.json").exists()
+            if not (has_db or has_meta):
+                continue
+            meta = read_board_metadata(normed)
+            if meta.get("archived") and not include_archived:
+                continue
+            entries.append(meta)
+            seen.add(normed)
+    return entries
+
+
+def remove_board(slug: str, *, archive: bool = True) -> dict:
+    """Remove or archive a board.
+
+    ``archive=True`` (default) moves the board's directory to
+    ``<root>/kanban/boards/_archived/<slug>-<timestamp>/`` so the data
+    is recoverable. ``archive=False`` deletes the directory outright.
+
+    The ``default`` board cannot be removed — raises :class:`ValueError`.
+    Returns a summary dict describing what happened (``{"slug", "action",
+    "new_path"}``).
+    """
+    normed = _normalize_board_slug(slug)
+    if not normed:
+        raise ValueError("board slug is required")
+    if normed == DEFAULT_BOARD:
+        raise ValueError("the 'default' board cannot be removed")
+    d = board_dir(normed)
+    if not d.exists():
+        raise ValueError(f"board {normed!r} does not exist")
+
+    # If the user removed the currently-active board, revert to default.
+    if get_current_board() == normed:
+        clear_current_board()
+
+    if archive:
+        archive_root = boards_root() / "_archived"
+        archive_root.mkdir(parents=True, exist_ok=True)
+        ts = int(time.time())
+        target = archive_root / f"{normed}-{ts}"
+        # Avoid collision on rapid double-archives.
+        suffix = 1
+        while target.exists():
+            target = archive_root / f"{normed}-{ts}-{suffix}"
+            suffix += 1
+        d.rename(target)
+        return {"slug": normed, "action": "archived", "new_path": str(target)}
+    else:
+        import shutil
+        shutil.rmtree(d)
+        return {"slug": normed, "action": "deleted", "new_path": ""}
 
 
 # ---------------------------------------------------------------------------
@@ -368,7 +842,11 @@ CREATE INDEX IF NOT EXISTS idx_notify_task           ON kanban_notify_subs(task_
 _INITIALIZED_PATHS: set[str] = set()
 
 
-def connect(db_path: Optional[Path] = None) -> sqlite3.Connection:
+def connect(
+    db_path: Optional[Path] = None,
+    *,
+    board: Optional[str] = None,
+) -> sqlite3.Connection:
     """Open (and initialize if needed) the kanban DB.
 
     WAL mode is enabled on every connection; it's a no-op after the first
@@ -378,8 +856,19 @@ def connect(db_path: Optional[Path] = None) -> sqlite3.Connection:
     fresh installs and test harnesses that construct `connect()`
     directly don't have to remember a separate init step. Subsequent
     connections skip the schema check via a module-level path cache.
+
+    Path resolution:
+
+    * ``db_path`` explicit → used as-is (legacy callers, tests).
+    * ``board`` explicit → resolves to that board's DB.
+    * Neither → :func:`kanban_db_path` resolves via
+      ``HERMES_KANBAN_DB`` env → ``HERMES_KANBAN_BOARD`` env →
+      ``<root>/kanban/current`` → ``default``.
     """
-    path = db_path or kanban_db_path()
+    if db_path is not None:
+        path = db_path
+    else:
+        path = kanban_db_path(board=board)
     path.parent.mkdir(parents=True, exist_ok=True)
     resolved = str(path.resolve())
     needs_init = resolved not in _INITIALIZED_PATHS
@@ -398,7 +887,11 @@ def connect(db_path: Optional[Path] = None) -> sqlite3.Connection:
     return conn
 
 
-def init_db(db_path: Optional[Path] = None) -> Path:
+def init_db(
+    db_path: Optional[Path] = None,
+    *,
+    board: Optional[str] = None,
+) -> Path:
     """Create the schema if it doesn't exist; return the path used.
 
     Kept as a public entry point so CLI ``hermes kanban init`` and the
@@ -409,7 +902,10 @@ def init_db(db_path: Optional[Path] = None) -> Path:
     external tools that upgrade an old DB file — can call this to
     force re-migration.
     """
-    path = db_path or kanban_db_path()
+    if db_path is not None:
+        path = db_path
+    else:
+        path = kanban_db_path(board=board)
     path.parent.mkdir(parents=True, exist_ok=True)
     resolved = str(path.resolve())
     # Clear the cache entry so the underlying connect() re-runs the
@@ -590,6 +1086,15 @@ def _claimer_id() -> str:
 # Task creation / mutation
 # ---------------------------------------------------------------------------
 
+def _canonical_assignee(assignee: Optional[str]) -> Optional[str]:
+    """Lowercase-assignee normalization for Kanban rows (dashboard/CLI parity)."""
+    if assignee is None:
+        return None
+    from hermes_cli.profiles import normalize_profile_name
+
+    return normalize_profile_name(assignee)
+
+
 def create_task(
     conn: sqlite3.Connection,
     *,
@@ -631,6 +1136,7 @@ def create_task(
     (e.g. ``skills=["translation"]`` so the worker loads the
     translation skill regardless of the profile's default config).
     """
+    assignee = _canonical_assignee(assignee)
     if not title or not title.strip():
         raise ValueError("title is required")
     if workspace_kind not in VALID_WORKSPACE_KINDS:
@@ -795,7 +1301,7 @@ def list_tasks(
     params: list[Any] = []
     if assignee is not None:
         query += " AND assignee = ?"
-        params.append(assignee)
+        params.append(_canonical_assignee(assignee))
     if status is not None:
         if status not in VALID_STATUSES:
             raise ValueError(f"status must be one of {sorted(VALID_STATUSES)}")
@@ -819,6 +1325,7 @@ def assign_task(conn: sqlite3.Connection, task_id: str, profile: Optional[str])
     Refuses to reassign a task that's currently running (claim_lock set).
     Reassign after the current run completes if needed.
     """
+    profile = _canonical_assignee(profile)
     with write_txn(conn):
         row = conn.execute(
             "SELECT status, claim_lock FROM tasks WHERE id = ?", (task_id,)
@@ -1513,15 +2020,18 @@ def archive_task(conn: sqlite3.Connection, task_id: str) -> bool:
 # Workspace resolution
 # ---------------------------------------------------------------------------
 
-def resolve_workspace(task: Task) -> Path:
+def resolve_workspace(task: Task, *, board: Optional[str] = None) -> Path:
     """Resolve (and create if needed) the workspace for a task.
 
-    - ``scratch``: a fresh dir under ``$HERMES_HOME/kanban/workspaces/<id>/``.
+    - ``scratch``: a fresh dir under ``<board-root>/workspaces/<id>/``,
+      where ``<board-root>`` is the active board's root. The path is the
+      same for the dispatcher and every profile worker, so handoff is
+      path-stable.
     - ``dir:<path>``: the path stored in ``workspace_path``.  Created
       if missing.  MUST be absolute — relative paths are rejected to
       prevent confused-deputy traversal where ``../../../tmp/attacker``
       resolves against the dispatcher's CWD instead of a meaningful
-      root.  Users who want a HERMES_HOME-relative workspace should
+      root.  Users who want a kanban-root-relative workspace should
       compute the absolute path themselves.
     - ``worktree``: a git worktree at ``workspace_path``.  Not created
       automatically in v1 -- the kanban-worker skill documents
@@ -1543,7 +2053,7 @@ def resolve_workspace(task: Task) -> Path:
                     f"{task.workspace_path!r}; workspace paths must be absolute"
                 )
         else:
-            p = workspaces_root() / task.id
+            p = workspaces_root(board=board) / task.id
         p.mkdir(parents=True, exist_ok=True)
         return p
     if kind == "dir":
@@ -1957,6 +2467,7 @@ def dispatch_once(
     dry_run: bool = False,
     max_spawn: Optional[int] = None,
     failure_limit: int = DEFAULT_SPAWN_FAILURE_LIMIT,
+    board: Optional[str] = None,
 ) -> DispatchResult:
     """Run one dispatcher tick.
 
@@ -1965,15 +2476,17 @@ def dispatch_once(
       2. Reclaim crashed running tasks (host-local PID no longer alive).
       3. Promote todo -> ready where all parents are done.
       4. For each ready task with an assignee, atomically claim and call
-         ``spawn_fn(task, workspace_path) -> Optional[int]``. The return
-         value (if any) is recorded as ``worker_pid`` so subsequent ticks
-         can detect crashes before the TTL expires.
+         ``spawn_fn(task, workspace_path, board) -> Optional[int]``. The
+         return value (if any) is recorded as ``worker_pid`` so subsequent
+         ticks can detect crashes before the TTL expires.
 
     Spawn failures are counted per-task. After ``failure_limit`` consecutive
     failures the task is auto-blocked with the last error as its reason —
     prevents the dispatcher from thrashing forever on an unfixable task.
 
     ``spawn_fn`` defaults to ``_default_spawn``. Tests pass a stub.
+    ``board`` pins workspace/log/db resolution for this tick to a specific
+    board. When omitted, the current-board resolution chain is used.
     """
     result = DispatchResult()
     result.reclaimed = release_stale_claims(conn)
@@ -2000,7 +2513,7 @@ def dispatch_once(
         if claimed is None:
             continue
         try:
-            workspace = resolve_workspace(claimed)
+            workspace = resolve_workspace(claimed, board=board)
         except Exception as exc:
             auto = _record_spawn_failure(
                 conn, claimed.id, f"workspace: {exc}",
@@ -2013,7 +2526,18 @@ def dispatch_once(
         set_workspace_path(conn, claimed.id, str(workspace))
         _spawn = spawn_fn if spawn_fn is not None else _default_spawn
         try:
-            pid = _spawn(claimed, str(workspace))
+            # Back-compat: older spawn_fn signatures accept only
+            # (task, workspace). Test stubs in the suite rely on that.
+            # Introspect the callable and pass `board` only when supported.
+            import inspect
+            try:
+                sig = inspect.signature(_spawn)
+                if "board" in sig.parameters:
+                    pid = _spawn(claimed, str(workspace), board=board)
+                else:
+                    pid = _spawn(claimed, str(workspace))
+            except (TypeError, ValueError):
+                pid = _spawn(claimed, str(workspace))
             if pid:
                 _set_worker_pid(conn, claimed.id, int(pid))
             _clear_spawn_failures(conn, claimed.id)
@@ -2052,33 +2576,60 @@ def _rotate_worker_log(log_path: Path, max_bytes: int) -> None:
         pass
 
 
-def _default_spawn(task: Task, workspace: str) -> Optional[int]:
+def _default_spawn(
+    task: Task,
+    workspace: str,
+    *,
+    board: Optional[str] = None,
+) -> Optional[int]:
     """Fire-and-forget ``hermes -p <profile> chat -q ...`` subprocess.
 
     Returns the spawned child's PID so the dispatcher can detect crashes
     before the claim TTL expires. The child's completion is still observed
     via the ``complete`` / ``block`` transitions the worker writes itself;
     the PID check is a safety net for crashes, OOM kills, and Ctrl+C.
+
+    ``board`` pins the child's kanban context to that board: the child's
+    ``HERMES_KANBAN_DB`` / ``HERMES_KANBAN_BOARD`` / workspaces_root env
+    vars all resolve to the same board the dispatcher claimed the task
+    from. Workers cannot accidentally see other boards.
     """
     import subprocess
     if not task.assignee:
         raise ValueError(f"task {task.id} has no assignee")
 
+    from hermes_cli.profiles import normalize_profile_name
+
+    profile_arg = normalize_profile_name(task.assignee)
+
     prompt = f"work kanban task {task.id}"
     env = dict(os.environ)
     if task.tenant:
         env["HERMES_TENANT"] = task.tenant
     env["HERMES_KANBAN_TASK"] = task.id
     env["HERMES_KANBAN_WORKSPACE"] = workspace
+    # Pin the shared board + workspaces root the dispatcher resolved, so
+    # that even when the worker activates a profile (`hermes -p <name>`
+    # rewrites HERMES_HOME), its kanban paths still match the
+    # dispatcher's. Belt-and-braces with the `get_default_hermes_root()`
+    # resolution in `kanban_home()` — symmetric resolution is the norm,
+    # but unusual symlink / Docker layouts are caught here too.
+    env["HERMES_KANBAN_DB"] = str(kanban_db_path(board=board))
+    env["HERMES_KANBAN_WORKSPACES_ROOT"] = str(workspaces_root(board=board))
+    # Board slug — the final defense-in-depth pin. If the worker ever
+    # resolves kanban paths without the DB / workspaces env vars, the
+    # board slug still forces it to the right directory.
+    resolved_board = _normalize_board_slug(board) or get_current_board()
+    env["HERMES_KANBAN_BOARD"] = resolved_board
     # HERMES_PROFILE is the author the kanban_comment tool defaults to.
     # `hermes -p <assignee>` activates the profile, but the env var is
     # what the tool reads — set it explicitly here so comments are
     # attributed correctly regardless of how the child loads config.
-    env["HERMES_PROFILE"] = task.assignee
+    env["HERMES_PROFILE"] = profile_arg
 
     cmd = [
         "hermes",
-        "-p", task.assignee,
+        "-p", profile_arg,
         # Auto-load the kanban-worker skill so every dispatched worker
         # has the pattern library (good summary/metadata shapes, retry
         # diagnostics, block-reason examples) in its context, even if
@@ -2104,9 +2655,11 @@ def _default_spawn(task: Task, workspace: str) -> Optional[int]:
         "chat",
         "-q", prompt,
     ])
-    # Redirect output to a per-task log under HERMES_HOME/kanban/logs/.
-    from hermes_constants import get_hermes_home
-    log_dir = get_hermes_home() / "kanban" / "logs"
+    # Redirect output to a per-task log under <board-root>/logs/.
+    # Anchored at the board root (not the shared kanban root), so
+    # `hermes kanban log` on a specific board reads its own file and
+    # logs don't collide across boards that happen to share task ids.
+    log_dir = worker_logs_dir(board=board)
     log_dir.mkdir(parents=True, exist_ok=True)
     log_path = log_dir / f"{task.id}.log"
     _rotate_worker_log(log_path, DEFAULT_LOG_ROTATE_BYTES)
@@ -2587,12 +3140,14 @@ def gc_events(
 
 def gc_worker_logs(
     *, older_than_seconds: int = 30 * 24 * 3600,
+    board: Optional[str] = None,
 ) -> int:
     """Delete worker log files older than ``older_than_seconds``. Returns
     the number of files removed. Kept separate from ``gc_events`` because
-    log files live on disk, not in SQLite."""
-    from hermes_constants import get_hermes_home
-    log_dir = get_hermes_home() / "kanban" / "logs"
+    log files live on disk, not in SQLite. Scoped to ``board`` (defaults
+    to the active board) — per-board isolation means deleting logs from
+    board A cannot touch board B's logs."""
+    log_dir = worker_logs_dir(board=board)
     if not log_dir.exists():
         return 0
     cutoff = time.time() - older_than_seconds
@@ -2611,20 +3166,25 @@ def gc_worker_logs(
 # Worker log accessor
 # ---------------------------------------------------------------------------
 
-def worker_log_path(task_id: str) -> Path:
+def worker_log_path(task_id: str, *, board: Optional[str] = None) -> Path:
     """Return the path to a worker's log file. The file may not exist
-    (task never spawned, or log already GC'd)."""
-    from hermes_constants import get_hermes_home
-    return get_hermes_home() / "kanban" / "logs" / f"{task_id}.log"
+    (task never spawned, or log already GC'd).
+
+    When ``board`` is None, resolves via the active board (env var →
+    current-board file → default). The dispatcher always passes the
+    board explicitly to avoid any resolution ambiguity when multiple
+    boards exist."""
+    return worker_logs_dir(board=board) / f"{task_id}.log"
 
 
 def read_worker_log(
     task_id: str, *, tail_bytes: Optional[int] = None,
+    board: Optional[str] = None,
 ) -> Optional[str]:
     """Read the worker log for ``task_id``. Returns None if the file
     doesn't exist. If ``tail_bytes`` is set, only the last N bytes are
     returned (useful for the dashboard drawer which shouldn't page megabytes)."""
-    path = worker_log_path(task_id)
+    path = worker_log_path(task_id, board=board)
     if not path.exists():
         return None
     try:
@@ -2661,7 +3221,8 @@ def list_profiles_on_disk() -> list[str]:
     ``config.yaml`` — a bare dir without config isn't a real profile.
     """
     try:
-        home = Path.home() / ".hermes" / "profiles"
+        from hermes_constants import get_default_hermes_root
+        home = get_default_hermes_root() / "profiles"
     except Exception:
         return []
     if not home.is_dir():

hermes_cli/main.py

@@ -114,6 +114,16 @@ def _apply_profile_override() -> None:
             consume = 1
             break
 
+    # 1b. Reject values that can't be valid profile names (e.g. pytest's
+    # "-p no:xdist" would be misread as profile "no:xdist" otherwise).
+    # Mirrors hermes_cli.profiles._PROFILE_ID_RE so we never call
+    # resolve_profile_env() with a value it must reject + sys.exit on.
+    if profile_name is not None and consume == 2:
+        import re as _re
+        if not _re.match(r"^[a-z0-9][a-z0-9_-]{0,63}$", profile_name):
+            profile_name = None
+            consume = 0
+
     # 1.5 If HERMES_HOME is already set and no explicit flag was given, trust it.
     # This lets child processes (relaunch, subprocess) inherit the parent's
     # profile choice without having to pass --profile again.
@@ -837,7 +847,17 @@ def _print_tui_exit_summary(session_id: Optional[str], active_session_file: Opti
     )
 
 
-_NPM_LOCK_RUNTIME_KEYS = frozenset({"ideallyInert"})
+_NPM_LOCK_RUNTIME_KEYS = frozenset({"ideallyInert", "peer"})
+"""Lockfile fields npm writes non-deterministically at install time.
+
+``ideallyInert`` is npm's runtime annotation for packages it skipped installing
+(per-platform opt-outs).  ``peer`` is dropped from the hidden ``.package-lock.json``
+on dev-dependencies that are *also* declared as peers — the canonical
+``package-lock.json`` records the dual role, but npm 9's actualized tree strips
+it.  Neither key represents a real skew between what was declared and what was
+installed, so we exclude them from the comparison in :func:`_tui_need_npm_install`
+to avoid false-positive reinstalls on every launch.
+"""
 
 
 def _tui_need_npm_install(root: Path) -> bool:
@@ -1042,17 +1062,21 @@ def _make_tui_argv(tui_dir: Path, tui_dev: bool) -> tuple[list[str], Path]:
     if _tui_need_npm_install(tui_dir):
         if not os.environ.get("HERMES_QUIET"):
             print("Installing TUI dependencies…")
+        # Capture stdout as well as stderr — some npm errors (notably EACCES on a
+        # root-owned node_modules in containers) are emitted on stdout, and a
+        # bare "npm install failed." with no preview defeats debugging.  We keep
+        # the failure-only print path so a successful install stays silent.
         result = subprocess.run(
             [npm, "install", "--silent", "--no-fund", "--no-audit", "--progress=false"],
             cwd=str(tui_dir),
-            stdout=subprocess.DEVNULL,
+            stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,
             text=True,
             env={**os.environ, "CI": "1"},
         )
         if result.returncode != 0:
-            err = (result.stderr or "").strip()
-            preview = "\n".join(err.splitlines()[-30:])
+            combined = f"{result.stdout or ''}\n{result.stderr or ''}".strip()
+            preview = "\n".join(combined.splitlines()[-30:])
             print("npm install failed.")
             if preview:
                 print(preview)
@@ -3399,10 +3423,10 @@ def _model_flow_named_custom(config, provider_info):
     print()
 
     print("Fetching available models...")
-    models = fetch_api_models(
-        api_key, base_url, timeout=8.0,
-        api_mode=api_mode or None,
-    )
+    fetch_kwargs = {"timeout": 8.0}
+    if api_mode:
+        fetch_kwargs["api_mode"] = api_mode
+    models = fetch_api_models(api_key, base_url, **fetch_kwargs)
 
     if models:
         default_idx = 0
@@ -6477,13 +6501,29 @@ def _cmd_update_check():
     if sys.platform == "win32":
         git_cmd = ["git", "-c", "windows.appendAtomically=false"]
 
-    print("→ Fetching from origin...")
+    # Fetch both origin and upstream; prefer upstream as the canonical reference
+    print("→ Fetching from upstream...")
     fetch_result = subprocess.run(
-        git_cmd + ["fetch", "origin"],
+        git_cmd + ["fetch", "upstream"],
         cwd=PROJECT_ROOT,
         capture_output=True,
         text=True,
     )
+    if fetch_result.returncode != 0:
+        # Fallback to origin if upstream doesn't exist
+        print("→ Fetching from origin...")
+        fetch_result = subprocess.run(
+            git_cmd + ["fetch", "origin"],
+            cwd=PROJECT_ROOT,
+            capture_output=True,
+            text=True,
+        )
+        upstream_exists = False
+        compare_branch = "origin/main"
+    else:
+        upstream_exists = True
+        compare_branch = "upstream/main"
+
     if fetch_result.returncode != 0:
         stderr = fetch_result.stderr.strip()
         if "Could not resolve host" in stderr or "unable to access" in stderr:
@@ -6491,13 +6531,13 @@ def _cmd_update_check():
         elif "Authentication failed" in stderr or "could not read Username" in stderr:
             print("✗ Authentication failed — check your git credentials or SSH key.")
         else:
-            print("✗ Failed to fetch from origin.")
+            print("✗ Failed to fetch.")
             if stderr:
                 print(f"  {stderr.splitlines()[0]}")
         sys.exit(1)
 
     rev_result = subprocess.run(
-        git_cmd + ["rev-list", "HEAD..origin/main", "--count"],
+        git_cmd + ["rev-list", f"HEAD..{compare_branch}", "--count"],
         cwd=PROJECT_ROOT,
         capture_output=True,
         text=True,
@@ -6509,7 +6549,7 @@ def _cmd_update_check():
         print("✓ Already up to date.")
     else:
         commits_word = "commit" if behind == 1 else "commits"
-        print(f"⚕ Update available: {behind} {commits_word} behind origin/main.")
+        print(f"⚕ Update available: {behind} {commits_word} behind {compare_branch}.")
         from hermes_cli.config import recommended_update_command
         print(f"  Run '{recommended_update_command()}' to install.")
 
@@ -8897,6 +8937,7 @@ Examples:
     hermes debug share --lines 500  Include more log lines
     hermes debug share --expire 30  Keep paste for 30 days
     hermes debug share --local      Print report locally (no upload)
+    hermes debug share --no-redact  Disable upload-time secret redaction
     hermes debug delete <url>       Delete a previously uploaded paste
 """,
     )
@@ -8922,6 +8963,16 @@ Examples:
         action="store_true",
         help="Print the report locally instead of uploading",
     )
+    share_parser.add_argument(
+        "--no-redact",
+        action="store_true",
+        help=(
+            "Disable upload-time secret redaction (default: redact). Logs "
+            "are normally run through agent.redact.redact_sensitive_text "
+            "with force=True before upload so credentials are not leaked "
+            "into the public paste service."
+        ),
+    )
     delete_parser = debug_sub.add_parser(
         "delete",
         help="Delete a paste uploaded by 'hermes debug share'",

hermes_cli/model_switch.py

@@ -904,6 +904,26 @@ def switch_model(
                         if any(m.get("name") == new_model for m in cfg_models if isinstance(m, dict)):
                             override = True
                             break
+        # Also check custom_providers list — models declared there should be accepted
+        # even if the remote /v1/models endpoint doesn't list them.
+        if not override and custom_providers and isinstance(custom_providers, list):
+            for entry in custom_providers:
+                if not isinstance(entry, dict):
+                    continue
+                # Match by provider slug (custom:<name>) or by base_url
+                entry_name = entry.get("name", "")
+                entry_slug = f"custom:{entry_name}" if entry_name else ""
+                entry_url = entry.get("base_url", "")
+                if entry_slug == target_provider or entry_url == base_url:
+                    # Check if the requested model matches the entry's model
+                    entry_model = entry.get("model", "")
+                    entry_models = entry.get("models", {})
+                    if new_model == entry_model:
+                        override = True
+                        break
+                    if isinstance(entry_models, dict) and new_model in entry_models:
+                        override = True
+                        break
         if override:
             validation = {"accepted": True, "persist": True, "recognized": False, "message": validation.get("message", "")}
         else:
@@ -1244,11 +1264,7 @@ def list_authenticated_providers(
                 from hermes_cli.auth import _load_auth_store
                 store = _load_auth_store()
                 providers_store = store.get("providers", {})
-                pool_store = store.get("credential_pool", {})
-                if store and (
-                    pid in providers_store or hermes_slug in providers_store
-                    or pid in pool_store or hermes_slug in pool_store
-                ):
+                if store and (pid in providers_store or hermes_slug in providers_store):
                     has_creds = True
             except Exception as exc:
                 logger.debug("Auth store check failed for %s: %s", pid, exc)
@@ -1344,11 +1360,7 @@ def list_authenticated_providers(
                 from hermes_cli.auth import _load_auth_store
                 _cp_store = _load_auth_store()
                 _cp_providers_store = _cp_store.get("providers", {})
-                _cp_pool_store = _cp_store.get("credential_pool", {})
-                if _cp_store and (
-                    _cp.slug in _cp_providers_store
-                    or _cp.slug in _cp_pool_store
-                ):
+                if _cp_store and _cp.slug in _cp_providers_store:
                     _cp_has_creds = True
             except Exception:
                 pass

hermes_cli/models.py

@@ -1740,10 +1740,20 @@ def model_supports_fast_mode(model_id: Optional[str]) -> bool:
 
 
 def _is_anthropic_fast_model(model_id: Optional[str]) -> bool:
-    """Return True if the model is a Claude model eligible for Anthropic Fast Mode."""
+    """Return True if the model is a Claude model eligible for Anthropic Fast Mode.
+
+    Fast mode is currently supported on Claude Opus 4.6 only. Per Anthropic's
+    docs (https://platform.claude.com/docs/en/build-with-claude/fast-mode):
+    "Fast mode is currently supported on Opus 4.6 only. Sending speed: fast
+    with an unsupported model returns an error." Opus 4.7 explicitly rejects
+    the ``speed`` parameter with HTTP 400.
+    """
     raw = _strip_vendor_prefix(str(model_id or ""))
     base = raw.split(":")[0]
-    return base.startswith("claude-")
+    if not base.startswith("claude-"):
+        return False
+    # Only Opus 4.6 supports fast mode at present.
+    return "opus-4-6" in base or "opus-4.6" in base
 
 
 def resolve_fast_mode_overrides(model_id: Optional[str]) -> dict[str, Any] | None:
@@ -3087,7 +3097,7 @@ def validate_requested_model(
             "message": f"Model `{requested}` was not found in LM Studio's model listing.",
         }
 
-    if normalized == "custom":
+    if normalized == "custom" or normalized.startswith("custom:"):
         # Try probing with correct auth for the api_mode.
         if api_mode == "anthropic_messages":
             probe = probe_api_models(api_key, base_url, api_mode=api_mode)
@@ -3185,11 +3195,12 @@ def validate_requested_model(
             if suggestions:
                 suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
             return {
-                "accepted": False,
-                "persist": False,
+                "accepted": True,
+                "persist": True,
                 "recognized": False,
                 "message": (
-                    f"Model `{requested}` was not found in the OpenAI Codex model listing."
+                    f"Note: `{requested}` was not found in the OpenAI Codex model listing. "
+                    "It may still work if your ChatGPT/Codex account has access to a newer or hidden model ID."
                     f"{suggestion_text}"
                 ),
             }

hermes_cli/profiles.py

@@ -179,8 +179,33 @@ def _get_wrapper_dir() -> Path:
 # Validation
 # ---------------------------------------------------------------------------
 
+def normalize_profile_name(name: str) -> str:
+    """Return the canonical profile id used on disk and in CLI ``-p`` argv.
+
+    Named profiles are stored lowercase under ``profiles/<id>/``. The special
+    alias ``default`` is matched case-insensitively (``Default`` → ``default``).
+    Dashboards and tools may pass title-cased display labels; normalize before
+    validation, assignment, and subprocess spawn (see issue #18498).
+    """
+    if not isinstance(name, str):
+        name = str(name)
+    stripped = name.strip()
+    if not stripped:
+        raise ValueError("profile name cannot be empty")
+    if stripped.casefold() == "default":
+        return "default"
+    return stripped.lower()
+
+
 def validate_profile_name(name: str) -> None:
-    """Raise ``ValueError`` if *name* is not a valid profile identifier."""
+    """Raise ``ValueError`` if *name* is not a valid profile identifier.
+
+    Validates the input as-given — strict lowercase match. Callers that accept
+    mixed-case or title-cased input from users (dashboard UI, CLI args) should
+    call :func:`normalize_profile_name` first. This separation keeps validate
+    honest about what the on-disk directory name must look like, while
+    ingress-point normalization handles UX flexibility (see #18498).
+    """
     if name == "default":
         return  # special alias for ~/.hermes
     if not _PROFILE_ID_RE.match(name):
@@ -192,16 +217,18 @@ def validate_profile_name(name: str) -> None:
 
 def get_profile_dir(name: str) -> Path:
     """Resolve a profile name to its HERMES_HOME directory."""
-    if name == "default":
+    canon = normalize_profile_name(name)
+    if canon == "default":
         return _get_default_hermes_home()
-    return _get_profiles_root() / name
+    return _get_profiles_root() / canon
 
 
 def profile_exists(name: str) -> bool:
     """Check whether a profile directory exists."""
-    if name == "default":
+    canon = normalize_profile_name(name)
+    if canon == "default":
         return True
-    return get_profile_dir(name).is_dir()
+    return get_profile_dir(canon).is_dir()
 
 
 # ---------------------------------------------------------------------------
@@ -213,28 +240,29 @@ def check_alias_collision(name: str) -> Optional[str]:
 
     Checks: reserved names, hermes subcommands, existing binaries in PATH.
     """
-    if name in _RESERVED_NAMES:
-        return f"'{name}' is a reserved name"
-    if name in _HERMES_SUBCOMMANDS:
-        return f"'{name}' conflicts with a hermes subcommand"
+    canon = normalize_profile_name(name)
+    if canon in _RESERVED_NAMES:
+        return f"'{canon}' is a reserved name"
+    if canon in _HERMES_SUBCOMMANDS:
+        return f"'{canon}' conflicts with a hermes subcommand"
 
     # Check existing commands in PATH
     wrapper_dir = _get_wrapper_dir()
     try:
         result = subprocess.run(
-            ["which", name], capture_output=True, text=True, timeout=5,
+            ["which", canon], capture_output=True, text=True, timeout=5,
         )
         if result.returncode == 0:
             existing_path = result.stdout.strip()
             # Allow overwriting our own wrappers
-            if existing_path == str(wrapper_dir / name):
+            if existing_path == str(wrapper_dir / canon):
                 try:
-                    content = (wrapper_dir / name).read_text()
+                    content = (wrapper_dir / canon).read_text()
                     if "hermes -p" in content:
                         return None  # it's our wrapper, safe to overwrite
                 except Exception:
                     pass
-            return f"'{name}' conflicts with an existing command ({existing_path})"
+            return f"'{canon}' conflicts with an existing command ({existing_path})"
     except (FileNotFoundError, subprocess.TimeoutExpired):
         pass
 
@@ -252,6 +280,7 @@ def create_wrapper_script(name: str) -> Optional[Path]:
 
     Returns the path to the created wrapper, or None if creation failed.
     """
+    canon = normalize_profile_name(name)
     wrapper_dir = _get_wrapper_dir()
     try:
         wrapper_dir.mkdir(parents=True, exist_ok=True)
@@ -259,9 +288,9 @@ def create_wrapper_script(name: str) -> Optional[Path]:
         print(f"⚠ Could not create {wrapper_dir}: {e}")
         return None
 
-    wrapper_path = wrapper_dir / name
+    wrapper_path = wrapper_dir / canon
     try:
-        wrapper_path.write_text(f'#!/bin/sh\nexec hermes -p {name} "$@"\n')
+        wrapper_path.write_text(f'#!/bin/sh\nexec hermes -p {canon} "$@"\n')
         wrapper_path.chmod(wrapper_path.stat().st_mode | stat.S_IEXEC | stat.S_IXGRP | stat.S_IXOTH)
         return wrapper_path
     except OSError as e:
@@ -271,7 +300,7 @@ def create_wrapper_script(name: str) -> Optional[Path]:
 
 def remove_wrapper_script(name: str) -> bool:
     """Remove the wrapper script for a profile. Returns True if removed."""
-    wrapper_path = _get_wrapper_dir() / name
+    wrapper_path = _get_wrapper_dir() / normalize_profile_name(name)
     if wrapper_path.exists():
         try:
             # Verify it's our wrapper before removing
@@ -421,16 +450,17 @@ def create_profile(
     Path
         The newly created profile directory.
     """
-    validate_profile_name(name)
+    canon = normalize_profile_name(name)
+    validate_profile_name(canon)
 
-    if name == "default":
+    if canon == "default":
         raise ValueError(
             "Cannot create a profile named 'default' — it is the built-in profile (~/.hermes)."
         )
 
-    profile_dir = get_profile_dir(name)
+    profile_dir = get_profile_dir(canon)
     if profile_dir.exists():
-        raise FileExistsError(f"Profile '{name}' already exists at {profile_dir}")
+        raise FileExistsError(f"Profile '{canon}' already exists at {profile_dir}")
 
     # Resolve clone source
     source_dir = None
@@ -440,6 +470,7 @@ def create_profile(
             from hermes_constants import get_hermes_home
             source_dir = get_hermes_home()
         else:
+            clone_from = normalize_profile_name(clone_from)
             validate_profile_name(clone_from)
             source_dir = get_profile_dir(clone_from)
         if not source_dir.is_dir():
@@ -540,24 +571,25 @@ def delete_profile(name: str, yes: bool = False) -> Path:
 
     Returns the path that was removed.
     """
-    validate_profile_name(name)
+    canon = normalize_profile_name(name)
+    validate_profile_name(canon)
 
-    if name == "default":
+    if canon == "default":
         raise ValueError(
             "Cannot delete the default profile (~/.hermes).\n"
             "To remove everything, use: hermes uninstall"
         )
 
-    profile_dir = get_profile_dir(name)
+    profile_dir = get_profile_dir(canon)
     if not profile_dir.is_dir():
-        raise FileNotFoundError(f"Profile '{name}' does not exist.")
+        raise FileNotFoundError(f"Profile '{canon}' does not exist.")
 
     # Show what will be deleted
     model, provider = _read_config_model(profile_dir)
     gw_running = _check_gateway_running(profile_dir)
     skill_count = _count_skills(profile_dir)
 
-    print(f"\nProfile: {name}")
+    print(f"\nProfile: {canon}")
     print(f"Path:    {profile_dir}")
     if model:
         print(f"Model:   {model}" + (f" ({provider})" if provider else ""))
@@ -569,7 +601,7 @@ def delete_profile(name: str, yes: bool = False) -> Path:
     ]
 
     # Check for service
-    wrapper_path = _get_wrapper_dir() / name
+    wrapper_path = _get_wrapper_dir() / canon
     has_wrapper = wrapper_path.exists()
     if has_wrapper:
         items.append(f"Command alias ({wrapper_path})")
@@ -584,16 +616,16 @@ def delete_profile(name: str, yes: bool = False) -> Path:
     if not yes:
         print()
         try:
-            confirm = input(f"Type '{name}' to confirm: ").strip()
+            confirm = input(f"Type '{canon}' to confirm: ").strip()
         except (KeyboardInterrupt, EOFError):
             print("\nCancelled.")
             return profile_dir
-        if confirm != name:
+        if confirm != canon:
             print("Cancelled.")
             return profile_dir
 
     # 1. Disable service (prevents auto-restart)
-    _cleanup_gateway_service(name, profile_dir)
+    _cleanup_gateway_service(canon, profile_dir)
 
     # 2. Stop running gateway
     if gw_running:
@@ -601,7 +633,7 @@ def delete_profile(name: str, yes: bool = False) -> Path:
 
     # 3. Remove wrapper script
     if has_wrapper:
-        if remove_wrapper_script(name):
+        if remove_wrapper_script(canon):
             print(f"✓ Removed {wrapper_path}")
 
     # 4. Remove profile directory
@@ -614,13 +646,13 @@ def delete_profile(name: str, yes: bool = False) -> Path:
     # 5. Clear active_profile if it pointed to this profile
     try:
         active = get_active_profile()
-        if active == name:
+        if active == canon:
             set_active_profile("default")
             print("✓ Active profile reset to default")
     except Exception:
         pass
 
-    print(f"\nProfile '{name}' deleted.")
+    print(f"\nProfile '{canon}' deleted.")
     return profile_dir
 
 
@@ -730,22 +762,23 @@ def set_active_profile(name: str) -> None:
 
     Writes to ``~/.hermes/active_profile``. Use ``"default"`` to clear.
     """
-    validate_profile_name(name)
-    if name != "default" and not profile_exists(name):
+    canon = normalize_profile_name(name)
+    validate_profile_name(canon)
+    if canon != "default" and not profile_exists(canon):
         raise FileNotFoundError(
-            f"Profile '{name}' does not exist. "
-            f"Create it with: hermes profile create {name}"
+            f"Profile '{canon}' does not exist. "
+            f"Create it with: hermes profile create {canon}"
         )
 
     path = _get_active_profile_path()
     path.parent.mkdir(parents=True, exist_ok=True)
-    if name == "default":
+    if canon == "default":
         # Remove the file to indicate default
         path.unlink(missing_ok=True)
     else:
         # Atomic write
         tmp = path.with_suffix(".tmp")
-        tmp.write_text(name + "\n")
+        tmp.write_text(canon + "\n")
         tmp.replace(path)
 
 
@@ -811,16 +844,17 @@ def export_profile(name: str, output_path: str) -> Path:
     """
     import tempfile
 
-    validate_profile_name(name)
-    profile_dir = get_profile_dir(name)
+    canon = normalize_profile_name(name)
+    validate_profile_name(canon)
+    profile_dir = get_profile_dir(canon)
     if not profile_dir.is_dir():
-        raise FileNotFoundError(f"Profile '{name}' does not exist.")
+        raise FileNotFoundError(f"Profile '{canon}' does not exist.")
 
     output = Path(output_path)
     # shutil.make_archive wants the base name without extension
     base = str(output).removesuffix(".tar.gz").removesuffix(".tgz")
 
-    if name == "default":
+    if canon == "default":
         # The default profile IS ~/.hermes itself — its parent is ~/ and its
         # directory name is ".hermes", not "default".  We stage a clean copy
         # under a temp dir so the archive contains ``default/...``.
@@ -836,14 +870,14 @@ def export_profile(name: str, output_path: str) -> Path:
 
     # Named profiles — stage a filtered copy to exclude credentials
     with tempfile.TemporaryDirectory() as tmpdir:
-        staged = Path(tmpdir) / name
+        staged = Path(tmpdir) / canon
         _CREDENTIAL_FILES = {"auth.json", ".env"}
         shutil.copytree(
             profile_dir,
             staged,
             ignore=lambda d, contents: _CREDENTIAL_FILES & set(contents),
         )
-        result = shutil.make_archive(base, "gztar", tmpdir, name)
+        result = shutil.make_archive(base, "gztar", tmpdir, canon)
         return Path(result)
 
 
@@ -952,16 +986,17 @@ def import_profile(archive_path: str, name: Optional[str] = None) -> Path:
     # Archives exported from the default profile have "default/" as top-level
     # dir.  Importing as "default" would target ~/.hermes itself — disallow
     # that and guide the user toward a named profile.
-    if inferred_name == "default":
+    canon = normalize_profile_name(inferred_name)
+    validate_profile_name(canon)
+    if canon == "default":
         raise ValueError(
             "Cannot import as 'default' — that is the built-in root profile (~/.hermes). "
             "Specify a different name: hermes profile import <archive> --name <name>"
         )
 
-    validate_profile_name(inferred_name)
-    profile_dir = get_profile_dir(inferred_name)
+    profile_dir = get_profile_dir(canon)
     if profile_dir.exists():
-        raise FileExistsError(f"Profile '{inferred_name}' already exists at {profile_dir}")
+        raise FileExistsError(f"Profile '{canon}' already exists at {profile_dir}")
 
     profiles_root = _get_profiles_root()
     profiles_root.mkdir(parents=True, exist_ok=True)
@@ -977,8 +1012,8 @@ def import_profile(archive_path: str, name: Optional[str] = None) -> Path:
             )
 
         final_source = extracted
-        if archive_root != inferred_name:
-            final_source = staging_root / inferred_name
+        if archive_root != canon:
+            final_source = staging_root / canon
             extracted.rename(final_source)
 
         shutil.move(str(final_source), str(profile_dir))
@@ -1048,25 +1083,27 @@ def rename_profile(old_name: str, new_name: str) -> Path:
 
     Returns the new profile directory.
     """
-    validate_profile_name(old_name)
-    validate_profile_name(new_name)
+    old_canon = normalize_profile_name(old_name)
+    new_canon = normalize_profile_name(new_name)
+    validate_profile_name(old_canon)
+    validate_profile_name(new_canon)
 
-    if old_name == "default":
+    if old_canon == "default":
         raise ValueError("Cannot rename the default profile.")
-    if new_name == "default":
+    if new_canon == "default":
         raise ValueError("Cannot rename to 'default' — it is reserved.")
 
-    old_dir = get_profile_dir(old_name)
-    new_dir = get_profile_dir(new_name)
+    old_dir = get_profile_dir(old_canon)
+    new_dir = get_profile_dir(new_canon)
 
     if not old_dir.is_dir():
-        raise FileNotFoundError(f"Profile '{old_name}' does not exist.")
+        raise FileNotFoundError(f"Profile '{old_canon}' does not exist.")
     if new_dir.exists():
-        raise FileExistsError(f"Profile '{new_name}' already exists.")
+        raise FileExistsError(f"Profile '{new_canon}' already exists.")
 
     # 1. Stop gateway if running
     if _check_gateway_running(old_dir):
-        _cleanup_gateway_service(old_name, old_dir)
+        _cleanup_gateway_service(old_canon, old_dir)
         _stop_gateway_process(old_dir)
 
     # 2. Rename directory
@@ -1074,22 +1111,22 @@ def rename_profile(old_name: str, new_name: str) -> Path:
     print(f"✓ Renamed {old_dir.name} → {new_dir.name}")
 
     # 3. Update profile-scoped Honcho host blocks, preserving aiPeer identity
-    _migrate_honcho_profile_host(old_name, new_name, new_dir)
+    _migrate_honcho_profile_host(old_canon, new_canon, new_dir)
 
     # 4. Update wrapper script
-    remove_wrapper_script(old_name)
-    collision = check_alias_collision(new_name)
+    remove_wrapper_script(old_canon)
+    collision = check_alias_collision(new_canon)
     if not collision:
-        create_wrapper_script(new_name)
-        print(f"✓ Alias updated: {new_name}")
+        create_wrapper_script(new_canon)
+        print(f"✓ Alias updated: {new_canon}")
     else:
-        print(f"⚠ Cannot create alias '{new_name}' — {collision}")
+        print(f"⚠ Cannot create alias '{new_canon}' — {collision}")
 
     # 5. Update active_profile if it pointed to old name
     try:
-        if get_active_profile() == old_name:
-            set_active_profile(new_name)
-            print(f"✓ Active profile updated: {new_name}")
+        if get_active_profile() == old_canon:
+            set_active_profile(new_canon)
+            print(f"✓ Active profile updated: {new_canon}")
     except Exception:
         pass
 
@@ -1191,13 +1228,14 @@ def resolve_profile_env(profile_name: str) -> str:
     Called early in the CLI entry point, before any hermes modules
     are imported, to set the HERMES_HOME environment variable.
     """
-    validate_profile_name(profile_name)
-    profile_dir = get_profile_dir(profile_name)
+    canon = normalize_profile_name(profile_name)
+    validate_profile_name(canon)
+    profile_dir = get_profile_dir(canon)
 
-    if profile_name != "default" and not profile_dir.is_dir():
+    if canon != "default" and not profile_dir.is_dir():
         raise FileNotFoundError(
-            f"Profile '{profile_name}' does not exist. "
-            f"Create it with: hermes profile create {profile_name}"
+            f"Profile '{canon}' does not exist. "
+            f"Create it with: hermes profile create {canon}"
         )
 
     return str(profile_dir)

hermes_cli/pty_bridge.py

@@ -108,9 +108,14 @@ class PtyBridge:
                     "(or pip install -e '.[pty]')."
                 )
             raise PtyUnavailableError("Pseudo-terminals are unavailable.")
-        # Let caller-supplied env fully override inheritance; if they pass
-        # None we inherit the server's env (same semantics as subprocess).
-        spawn_env = os.environ.copy() if env is None else env
+        # PTY-hosted programs expect TERM to describe the terminal type.
+        # CI often runs without TERM in the parent process, which makes
+        # simple terminal probes like `tput cols` fail before winsize reads.
+        # Preserve explicit caller overrides, but backfill a sensible default
+        # when TERM is missing or blank.
+        spawn_env = (os.environ.copy() if env is None else env.copy())
+        if not spawn_env.get("TERM"):
+            spawn_env["TERM"] = "xterm-256color"
         proc = ptyprocess.PtyProcess.spawn(  # type: ignore[union-attr]
             list(argv),
             cwd=cwd,

hermes_cli/setup.py

@@ -964,7 +964,8 @@ def setup_model_provider(config: dict, *, quick: bool = False):
                     )
                 else:
                     _selected_vision_model = prompt("  Vision model (blank = use main/custom default)").strip()
-                save_env_value("AUXILIARY_VISION_MODEL", _selected_vision_model)
+                if _selected_vision_model:
+                    save_env_value("AUXILIARY_VISION_MODEL", _selected_vision_model)
                 print_success(
                     f"Vision configured with {_base_url}"
                     + (f" ({_selected_vision_model})" if _selected_vision_model else "")
@@ -1328,15 +1329,13 @@ def setup_terminal_backend(config: dict):
         print_success("Terminal backend: Local")
         print_info("Commands run directly on this machine.")
 
-        # CWD for messaging
+        # Gateway/cron working directory
         print()
-        print_info("Working directory for messaging sessions:")
-        print_info("  When using Hermes via Telegram/Discord, this is where")
-        print_info(
-            "  the agent starts. CLI mode always starts in the current directory."
-        )
+        print_info("Gateway working directory:")
+        print_info("  Used by Telegram/Discord/cron sessions.")
+        print_info("  CLI/TUI always uses your launch directory instead.")
         current_cwd = cfg_get(config, "terminal", "cwd", default="")
-        cwd = prompt("  Messaging working directory", current_cwd or str(Path.home()))
+        cwd = prompt("  Gateway working directory", current_cwd or str(Path.home()))
         if cwd:
             config["terminal"]["cwd"] = cwd
 
@@ -2049,6 +2048,16 @@ def _setup_slack():
         print_warning("⚠️  No Slack allowlist set - unpaired users will be denied by default.")
         print_info("   Set SLACK_ALLOW_ALL_USERS=true or GATEWAY_ALLOW_ALL_USERS=true only if you intentionally want open workspace access.")
 
+    print()
+    print_info("📬 Home Channel: where Hermes delivers cron job results,")
+    print_info("   cross-platform messages, and notifications.")
+    print_info("   To get a channel ID: open the channel in Slack, then right-click")
+    print_info("   the channel name → Copy link — the ID starts with C (e.g. C01ABC2DE3F).")
+    print_info("   You can also set this later by typing /set-home in a Slack channel.")
+    home_channel = prompt("Home channel ID (leave empty to set later with /set-home)")
+    if home_channel:
+        save_env_value("SLACK_HOME_CHANNEL", home_channel.strip())
+
 
 def _write_slack_manifest_and_instruct():
     """Generate the Slack manifest, write it under HERMES_HOME, and print
@@ -2995,6 +3004,21 @@ def run_setup_wizard(args):
     config = load_config()
     hermes_home = get_hermes_home()
 
+    # Back up existing config before setup modifies it (#3522)
+    config_path = get_config_path()
+    if config_path.exists():
+        from datetime import datetime as _dt
+        _backup_path = config_path.with_suffix(
+            f".yaml.bak.{_dt.now().strftime('%Y%m%d_%H%M%S')}"
+        )
+        try:
+            import shutil
+            shutil.copy2(config_path, _backup_path)
+        except Exception:
+            _backup_path = None
+    else:
+        _backup_path = None
+
     # Detect non-interactive environments (headless SSH, Docker, CI/CD)
     non_interactive = getattr(args, 'non_interactive', False)
     if not non_interactive and not is_interactive_stdin():
@@ -3164,6 +3188,10 @@ def run_setup_wizard(args):
 
     # Save and show summary
     save_config(config)
+    if _backup_path and _backup_path.exists():
+        print_info(f"Previous config backed up to: {_backup_path}")
+        print_info("If setup changed a value you customized, restore it with:")
+        print_info(f"  cp {_backup_path} {config_path}")
     _print_setup_summary(config, hermes_home)
 
     _offer_launch_chat()

hermes_cli/status.py

@@ -122,11 +122,16 @@ def show_status(args):
     print()
     print(color("◆ API Keys", Colors.CYAN, Colors.BOLD))
 
-    keys = {
+    # Values may be a single env var name (str) or a tuple of alternates (first found wins).
+    keys: dict[str, str | tuple[str, ...]] = {
         "OpenRouter": "OPENROUTER_API_KEY",
         "OpenAI": "OPENAI_API_KEY",
-        "NVIDIA": "NVIDIA_API_KEY",
-        "Z.AI/GLM": "GLM_API_KEY",
+        "Anthropic": ("ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN"),
+        "Google / Gemini": ("GOOGLE_API_KEY", "GEMINI_API_KEY"),
+        "DeepSeek": "DEEPSEEK_API_KEY",
+        "xAI / Grok": "XAI_API_KEY",
+        "NVIDIA NIM": "NVIDIA_API_KEY",
+        "Z.AI / GLM": "GLM_API_KEY",
         "Kimi": "KIMI_API_KEY",
         "StepFun Step Plan": "STEPFUN_API_KEY",
         "MiniMax": "MINIMAX_API_KEY",
@@ -142,8 +147,23 @@ def show_status(args):
         "GitHub": "GITHUB_TOKEN",
     }
 
-    for name, env_var in keys.items():
-        value = get_env_value(env_var) or ""
+    def _resolve_env(env_ref) -> str:
+        """Return first non-empty env var value from a str or tuple of names."""
+        if isinstance(env_ref, tuple):
+            for candidate in env_ref:
+                v = get_env_value(candidate) or ""
+                if v:
+                    return v
+            return ""
+        return get_env_value(env_ref) or ""
+
+    for name, env_ref in keys.items():
+        # Anthropic already has a dedicated lookup below; keep that as the
+        # single source of truth (it also resolves OAuth tokens), skip here
+        # so we don't print two "Anthropic" rows.
+        if name == "Anthropic":
+            continue
+        value = _resolve_env(env_ref)
         has_key = bool(value)
         display = redact_key(value) if not show_all else value
         print(f"  {name:<12}  {check_mark(has_key)} {display}")

hermes_cli/tools_config.py

@@ -56,6 +56,7 @@ CONFIGURABLE_TOOLSETS = [
     ("file",            "📁 File Operations",           "read, write, patch, search"),
     ("code_execution",  "⚡ Code Execution",            "execute_code"),
     ("vision",          "👁️  Vision / Image Analysis",  "vision_analyze"),
+    ("video",           "🎬 Video Analysis",            "video_analyze (requires video-capable model)"),
     ("image_gen",       "🎨 Image Generation",          "image_generate"),
     ("moa",             "🧠 Mixture of Agents",         "mixture_of_agents"),
     ("tts",             "🔊 Text-to-Speech",            "text_to_speech"),
@@ -78,7 +79,7 @@ CONFIGURABLE_TOOLSETS = [
 # Toolsets that are OFF by default for new installs.
 # They're still in _HERMES_CORE_TOOLS (available at runtime if enabled),
 # but the setup checklist won't pre-select them for first-time users.
-_DEFAULT_OFF_TOOLSETS = {"moa", "homeassistant", "rl", "spotify", "discord", "discord_admin"}
+_DEFAULT_OFF_TOOLSETS = {"moa", "homeassistant", "rl", "spotify", "discord", "discord_admin", "video"}
 
 # Platform-scoped toolsets: only appear in the `hermes tools` checklist for
 # these platforms, and only resolve/save for these platforms.  A toolset
@@ -1919,21 +1920,27 @@ def _reconfigure_provider(provider: dict, config: dict):
             return
 
     if provider.get("tts_provider"):
-        config.setdefault("tts", {})["provider"] = provider["tts_provider"]
+        tts_cfg = config.setdefault("tts", {})
+        tts_cfg["provider"] = provider["tts_provider"]
+        tts_cfg["use_gateway"] = bool(managed_feature)
         _print_success(f"  TTS provider set to: {provider['tts_provider']}")
 
     if "browser_provider" in provider:
         bp = provider["browser_provider"]
+        browser_cfg = config.setdefault("browser", {})
         if bp == "local":
-            config.setdefault("browser", {})["cloud_provider"] = "local"
+            browser_cfg["cloud_provider"] = "local"
             _print_success("  Browser set to local mode")
         elif bp:
-            config.setdefault("browser", {})["cloud_provider"] = bp
+            browser_cfg["cloud_provider"] = bp
             _print_success(f"  Browser cloud provider set to: {bp}")
+        browser_cfg["use_gateway"] = bool(managed_feature)
 
     # Set web search backend in config if applicable
     if provider.get("web_backend"):
-        config.setdefault("web", {})["backend"] = provider["web_backend"]
+        web_cfg = config.setdefault("web", {})
+        web_cfg["backend"] = provider["web_backend"]
+        web_cfg["use_gateway"] = bool(managed_feature)
         _print_success(f"  Web backend set to: {provider['web_backend']}")
 
     if managed_feature and managed_feature not in ("web", "tts", "browser"):

hermes_cli/web_server.py

@@ -510,10 +510,23 @@ except (ValueError, TypeError):
     )
     _GATEWAY_HEALTH_TIMEOUT = 3.0
 
+# DEPRECATED (scheduled for removal): GATEWAY_HEALTH_URL / GATEWAY_HEALTH_TIMEOUT.
+# Cross-container / cross-host gateway liveness detection will be folded into a
+# first-class dashboard config key so it's no longer Docker-adjacent lore buried
+# in env vars.  The env vars still work for now so existing Compose deployments
+# don't break.  Do not add new callers — wire new uses through the planned
+# config surface.
+
 
 def _probe_gateway_health() -> tuple[bool, dict | None]:
     """Probe the gateway via its HTTP health endpoint (cross-container).
 
+    .. deprecated::
+        Driven by the deprecated ``GATEWAY_HEALTH_URL`` /
+        ``GATEWAY_HEALTH_TIMEOUT`` env vars.  Scheduled for removal alongside
+        a move to a first-class dashboard config key.  See
+        :data:`_GATEWAY_HEALTH_URL` for context.
+
     Uses ``/health/detailed`` first (returns full state), falling back to
     the simpler ``/health`` endpoint.  Returns ``(is_alive, body_dict)``.
 

model_tools.py

@@ -511,6 +511,12 @@ def coerce_tool_args(tool_name: str, args: Dict[str, Any]) -> Dict[str, Any]:
 
     Handles ``"type": "integer"``, ``"type": "number"``, ``"type": "boolean"``,
     and union types (``"type": ["integer", "string"]``).
+
+    Also wraps bare scalar values in a single-element list when the schema
+    declares ``"type": "array"``.  Open-weight models (DeepSeek, Qwen, GLM)
+    sometimes emit ``{"urls": "https://a.com"}`` when the tool expects
+    ``{"urls": ["https://a.com"]}``; wrapping here avoids a confusing tool
+    failure on what is otherwise a well-formed call.
     """
     if not args or not isinstance(args, dict):
         return args
@@ -523,13 +529,42 @@ def coerce_tool_args(tool_name: str, args: Dict[str, Any]) -> Dict[str, Any]:
     if not properties:
         return args
 
-    for key, value in args.items():
-        if not isinstance(value, str):
-            continue
+    for key, value in list(args.items()):
         prop_schema = properties.get(key)
         if not prop_schema:
             continue
         expected = prop_schema.get("type")
+
+        # Wrap bare non-list values when the schema declares ``array``.
+        # Strings still go through _coerce_value first so JSON-encoded
+        # arrays (``'["a","b"]'``) get parsed and nullable ``"null"``
+        # becomes ``None`` rather than ``["null"]``.
+        # ``None`` itself is preserved — we don't know whether the model
+        # meant "omit" or "empty list", and tools with sensible defaults
+        # (e.g. read_file's normalize_read_pagination) already handle it.
+        if expected == "array" and value is not None and not isinstance(value, (list, tuple)):
+            if isinstance(value, str):
+                coerced = _coerce_value(value, expected, schema=prop_schema)
+                if coerced is not value:
+                    # _coerce_value handled it (JSON-parsed list or
+                    # nullable "null" → None).
+                    args[key] = coerced
+                    continue
+                args[key] = [value]
+                logger.info(
+                    "coerce_tool_args: wrapped bare string in list for %s.%s",
+                    tool_name, key,
+                )
+                continue
+            args[key] = [value]
+            logger.info(
+                "coerce_tool_args: wrapped bare %s in list for %s.%s",
+                type(value).__name__, tool_name, key,
+            )
+            continue
+
+        if not isinstance(value, str):
+            continue
         if not expected and not _schema_allows_null(prop_schema):
             continue
         coerced = _coerce_value(value, expected, schema=prop_schema)

optional-skills/creative/kanban-video-orchestrator/references/role-archetypes.md

@@ -82,14 +82,14 @@ film and music video. Often pairs with a diagramming tool.
 Designs the visual language: framing, color, motion, transitions. Reviews
 generator output for visual consistency. Hands off per-scene `VISUAL_SPEC.md`.
 
-- **Toolsets:** kanban, terminal, file
+- **Toolsets:** kanban, terminal, file, video, vision
 - **Skills:** `kanban-worker` plus the visual skill that matches the project
   (e.g., `ascii-video` for ASCII work, `manim-video` for explainers,
   `touchdesigner-mcp` for real-time visuals, etc.)
 - **Outputs:** `scenes/scene-NN/VISUAL_SPEC.md`, review comments on renderer
   tasks
-- **Reviews via:** any media-analysis approach (Gemini multimodal, manual
-  inspection of clip thumbnails, ffprobe summaries)
+- **Reviews via:** `video_analyze` (sends full clip to multimodal LLM for
+  native review), `vision_analyze` for spot-checking frames, ffprobe summaries
 
 ## Production roles
 
@@ -247,10 +247,10 @@ specifically on what's off (pacing, sync, brand alignment, technical
 quality). Distinct from the cinematographer (who reviews visuals during
 production) and the editor (who reviews for assembly).
 
-- **Toolsets:** kanban, terminal, file
+- **Toolsets:** kanban, terminal, file, video, vision
 - **Skills:** `kanban-worker`
-- **External tools:** any media-analysis approach (Gemini multimodal,
-  ffprobe, manual frame extraction)
+- **Review tools:** `video_analyze` (native clip review via multimodal LLM),
+  `vision_analyze` (frame/thumbnail review), ffprobe
 - **Outputs:** `review-notes.md`, comments on tasks
 
 ### brand-cop

optional-skills/creative/kanban-video-orchestrator/references/tool-matrix.md

@@ -81,7 +81,16 @@ them directly.
 | Remotion CLI (`npx remotion render`) | React-based motion graphics | renderer-motion-graphics |
 | Manim CE (`manim`) | Math animation render (driven by `manim-video` skill's recipes) | renderer-manim |
 | Blender (`blender -b`) | 3D rendering (alternative to `blender-mcp`) | renderer-3d |
-| Gemini multimodal / Claude vision | AI review of clips | reviewer, cinematographer, editor |
+
+## Built-in Hermes tools for media review
+
+These are native Hermes tools — not invoked via terminal but through their own
+toolsets. Enable them per-profile by adding the toolset to the profile config.
+
+| Tool | Toolset | What it does | Profile that uses it |
+|------|---------|--------------|----------------------|
+| `video_analyze` | `video` (opt-in — `hermes tools enable video`) | Native video understanding — sends full clip to a multimodal LLM (Gemini via OpenRouter) for review without frame extraction. Supports mp4, webm, mov, avi, mkv. 50 MB cap. Model: `AUXILIARY_VIDEO_MODEL` env → `AUXILIARY_VISION_MODEL` fallback. | reviewer, cinematographer, editor |
+| `vision_analyze` | `vision` (core — enabled by default) | Image/frame analysis — review stills, thumbnails, exported frames. Already available to all profiles without opt-in. | reviewer, cinematographer, concept-artist |
 
 ## Standard toolset configurations per role
 
@@ -156,6 +165,8 @@ toolsets:
   - kanban
   - terminal
   - file
+  - video               # video_analyze — review full clips natively
+  - vision              # vision_analyze — review stills / exported frames
 skills:
   always_load:
     - kanban-worker
@@ -246,6 +257,8 @@ toolsets:
   - kanban
   - terminal
   - file
+  - video              # video_analyze — editor reviews assembled cuts natively
+  - vision             # vision_analyze — spot-check frames
 skills:
   always_load:
     - kanban-worker
@@ -259,14 +272,13 @@ For captioner add Whisper invocation patterns to the SOUL.md.
 ```yaml
 toolsets:
   - kanban
-  - terminal           # for media inspection
+  - terminal           # for media inspection (ffprobe, etc.)
   - file
+  - video              # video_analyze — review full clips natively
+  - vision             # vision_analyze — review stills / exported frames
 skills:
   always_load:
     - kanban-worker
-env_required:
-  - OPENROUTER_API_KEY    # if using Gemini multimodal review
-  # or ANTHROPIC_API_KEY if using Claude vision (already required globally)
 ```
 
 ## API key requirements
@@ -278,7 +290,7 @@ key is present in `~/.hermes/.env` (or macOS Keychain) before firing the kanban.
 |---------|---------|---------|
 | ElevenLabs | `ELEVENLABS_API_KEY` | voice-talent |
 | OpenAI | `OPENAI_API_KEY` | image-generator (DALL-E), voice-talent (TTS) |
-| OpenRouter | `OPENROUTER_API_KEY` | reviewer, cinematographer, editor (Gemini multimodal review) |
+| OpenRouter | `OPENROUTER_API_KEY` | reviewer, cinematographer, editor (`video_analyze` routes through `AUXILIARY_VIDEO_MODEL` → OpenRouter) |
 | FAL | `FAL_KEY` | image-generator (FAL flux models) |
 | Replicate | `REPLICATE_API_TOKEN` | image-generator (alternate provider) |
 | Runway | `RUNWAY_API_KEY` | image-to-video-generator |

plugins/google_meet/node/server.py

@@ -43,7 +43,7 @@ class NodeServer:
 
     def __init__(
         self,
-        host: str = "0.0.0.0",
+        host: str = "127.0.0.1",
         port: int = 18789,
         token_path: Optional[Path] = None,
         display_name: str = "hermes-meet-node",
@@ -76,6 +76,13 @@ class NodeServer:
             json.dumps({"token": tok, "generated_at": time.time()}, indent=2),
             encoding="utf-8",
         )
+        # Restrict to owner-read-write only — the token grants full RPC
+        # access to the meet bot (start, transcribe, speak in meetings).
+        try:
+            tmp.chmod(0o600)
+        except (OSError, NotImplementedError):
+            # Best-effort on non-POSIX filesystems; mode is set on POSIX.
+            pass
         tmp.replace(self.token_path)
         self._token = tok
         return tok

plugins/hermes-achievements/README.md

@@ -11,6 +11,8 @@ Achievement system for the Hermes Dashboard: collectible, tiered badges generate
 The screenshots use temporary demo tier data to show the full visual range. The plugin itself reads real local Hermes session history by default.
 
 > **Update notice (2026-04-29):** If you installed this plugin before today, update to the latest version. The achievements scan path was refactored for much faster warm loads (snapshot cache + incremental checkpoint scan).
+>
+> **Share cards (2026-05-04, vendored in hermes-agent v0.4.0):** Unlocked achievement cards now have a "Share" button that renders a 1200×630 PNG share card (client-side canvas, no backend, no network) with Download + Copy-to-clipboard actions. Fits X/Twitter, Discord, LinkedIn, Bluesky link-preview dimensions.
 
 ## What it does
 

plugins/hermes-achievements/dashboard/dist/index.js

@@ -66,6 +66,296 @@
     });
   }
 
+  const TIER_HEX = {
+    "Copper": "#b87333",
+    "Silver": "#c0c7d2",
+    "Gold": "#f2c94c",
+    "Diamond": "#67e8f9",
+    "Olympian": "#c084fc",
+  };
+
+  function tierHex(tier) {
+    return TIER_HEX[tier] || "#67e8f9";
+  }
+
+  // Render a LUCIDE icon path fragment into a standalone SVG string with an
+  // explicit stroke color so it can be rasterized onto a <canvas> via Image.
+  // The normal render path uses stroke="currentColor" which browsers honor in
+  // DOM but NOT when the SVG is drawn to a canvas from a data URL.
+  function iconSvgForCanvas(iconKey, strokeColor) {
+    const paths = LUCIDE[iconKey] || LUCIDE.secret;
+    return "<svg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 24 24\" fill=\"none\" " +
+      "stroke=\"" + strokeColor + "\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">" +
+      paths + "</svg>";
+  }
+
+  function loadSvgImage(svgString) {
+    return new Promise(function (resolve, reject) {
+      const blob = new Blob([svgString], { type: "image/svg+xml;charset=utf-8" });
+      const url = URL.createObjectURL(blob);
+      const img = new Image();
+      img.onload = function () { URL.revokeObjectURL(url); resolve(img); };
+      img.onerror = function (e) { URL.revokeObjectURL(url); reject(e); };
+      img.src = url;
+    });
+  }
+
+  function wrapText(ctx, text, maxWidth) {
+    const words = String(text || "").split(/\s+/).filter(Boolean);
+    const lines = [];
+    let current = "";
+    for (let i = 0; i < words.length; i++) {
+      const candidate = current ? current + " " + words[i] : words[i];
+      if (ctx.measureText(candidate).width <= maxWidth) {
+        current = candidate;
+      } else {
+        if (current) lines.push(current);
+        current = words[i];
+      }
+    }
+    if (current) lines.push(current);
+    return lines;
+  }
+
+  // Build a 1200x630 share card PNG for a single achievement. Returns a Blob.
+  // Pure client-side render via Canvas2D — no external deps, no network.
+  async function buildShareImage(achievement) {
+    const W = 1200;
+    const H = 630;
+    const canvas = document.createElement("canvas");
+    canvas.width = W;
+    canvas.height = H;
+    const ctx = canvas.getContext("2d");
+
+    const tier = achievement.tier || achievement.next_tier || "Copper";
+    const color = tierHex(tier);
+
+    // Background: dark charcoal with a tier-tinted radial highlight on the
+    // top-left, echoing the card visual language.
+    ctx.fillStyle = "#0b0d11";
+    ctx.fillRect(0, 0, W, H);
+    const bgGrad = ctx.createRadialGradient(260, 220, 60, 260, 220, 820);
+    bgGrad.addColorStop(0, color + "33");
+    bgGrad.addColorStop(0.55, color + "0a");
+    bgGrad.addColorStop(1, "#0b0d1100");
+    ctx.fillStyle = bgGrad;
+    ctx.fillRect(0, 0, W, H);
+
+    // Outer border
+    ctx.strokeStyle = color + "66";
+    ctx.lineWidth = 2;
+    ctx.strokeRect(1, 1, W - 2, H - 2);
+
+    // Icon block — 380x380 on the left
+    try {
+      const svg = iconSvgForCanvas(achievement.icon || "secret", color);
+      const iconImg = await loadSvgImage(svg);
+      const ix = 90;
+      const iy = 125;
+      const isize = 380;
+      // Icon glow
+      ctx.save();
+      ctx.shadowColor = color;
+      ctx.shadowBlur = 40;
+      ctx.drawImage(iconImg, ix, iy, isize, isize);
+      ctx.restore();
+    } catch (_) {
+      // Icon render failure is non-fatal; card still useful without it.
+    }
+
+    // Right column text layout
+    const rx = 520;
+    const rMaxWidth = W - rx - 70;
+
+    // Category label (kicker)
+    ctx.fillStyle = "#8b95a8";
+    ctx.font = "600 22px ui-monospace, 'SF Mono', Menlo, monospace";
+    ctx.textBaseline = "top";
+    ctx.fillText((achievement.category || "").toUpperCase(), rx, 112);
+
+    // Achievement name — wrap to 2 lines if needed
+    ctx.fillStyle = "#ffffff";
+    ctx.font = "780 68px system-ui, -apple-system, 'Segoe UI', sans-serif";
+    const nameLines = wrapText(ctx, achievement.name || "Achievement", rMaxWidth).slice(0, 2);
+    let cursorY = 150;
+    for (let i = 0; i < nameLines.length; i++) {
+      ctx.fillText(nameLines[i], rx, cursorY);
+      cursorY += 76;
+    }
+
+    // Tier badge pill
+    const badgeLabel = tier.toUpperCase() + " TIER";
+    ctx.font = "700 22px ui-monospace, 'SF Mono', Menlo, monospace";
+    const badgeWidth = ctx.measureText(badgeLabel).width + 32;
+    const badgeX = rx;
+    const badgeY = cursorY + 14;
+    const badgeH = 40;
+    ctx.fillStyle = color + "1f";
+    ctx.strokeStyle = color;
+    ctx.lineWidth = 1.5;
+    ctx.beginPath();
+    ctx.rect(badgeX, badgeY, badgeWidth, badgeH);
+    ctx.fill();
+    ctx.stroke();
+    ctx.fillStyle = color;
+    ctx.textBaseline = "middle";
+    ctx.fillText(badgeLabel, badgeX + 16, badgeY + badgeH / 2 + 1);
+    ctx.textBaseline = "top";
+
+    // Description — wrap up to 3 lines
+    ctx.fillStyle = "#c3cad6";
+    ctx.font = "400 26px system-ui, -apple-system, 'Segoe UI', sans-serif";
+    const descLines = wrapText(ctx, achievement.description || "", rMaxWidth).slice(0, 3);
+    let descY = badgeY + badgeH + 28;
+    for (let i = 0; i < descLines.length; i++) {
+      ctx.fillText(descLines[i], rx, descY);
+      descY += 34;
+    }
+
+    // Progress / stat line (if meaningful)
+    const progressValue = achievement.progress;
+    const threshold = achievement.next_threshold;
+    let statLine = null;
+    if (progressValue && threshold) {
+      statLine = progressValue.toLocaleString() + " / " + threshold.toLocaleString();
+    } else if (progressValue) {
+      statLine = progressValue.toLocaleString();
+    }
+    if (statLine) {
+      ctx.fillStyle = color;
+      ctx.font = "700 28px ui-monospace, 'SF Mono', Menlo, monospace";
+      ctx.fillText(statLine, rx, descY + 14);
+    }
+
+    // Footer watermark
+    ctx.fillStyle = "#8b95a8";
+    ctx.font = "600 20px ui-monospace, 'SF Mono', Menlo, monospace";
+    ctx.textBaseline = "bottom";
+    ctx.fillText("HERMES AGENT  ·  hermes-agent.nousresearch.com", 70, H - 40);
+
+    // "UNLOCKED" stamp upper-right
+    ctx.textBaseline = "top";
+    ctx.fillStyle = color;
+    ctx.font = "800 24px ui-monospace, 'SF Mono', Menlo, monospace";
+    const stamp = "◆ UNLOCKED";
+    const stampW = ctx.measureText(stamp).width;
+    ctx.fillText(stamp, W - 70 - stampW, 70);
+
+    return await new Promise(function (resolve, reject) {
+      canvas.toBlob(function (blob) {
+        if (blob) resolve(blob); else reject(new Error("canvas.toBlob returned null"));
+      }, "image/png");
+    });
+  }
+
+  function ShareDialog({ achievement, onClose }) {
+    const [status, setStatus] = hooks.useState("rendering"); // rendering | ready | copied | error
+    const [errorMsg, setErrorMsg] = hooks.useState(null);
+    const [previewUrl, setPreviewUrl] = hooks.useState(null);
+    const blobRef = React.useRef(null);
+
+    hooks.useEffect(function () {
+      let cancelled = false;
+      let createdUrl = null;
+      buildShareImage(achievement).then(function (blob) {
+        if (cancelled) return;
+        blobRef.current = blob;
+        createdUrl = URL.createObjectURL(blob);
+        setPreviewUrl(createdUrl);
+        setStatus("ready");
+      }).catch(function (err) {
+        if (cancelled) return;
+        setErrorMsg(String(err && err.message || err));
+        setStatus("error");
+      });
+      return function () {
+        cancelled = true;
+        if (createdUrl) URL.revokeObjectURL(createdUrl);
+      };
+    }, [achievement.id]);
+
+    function download() {
+      if (!blobRef.current) return;
+      const url = URL.createObjectURL(blobRef.current);
+      const a = document.createElement("a");
+      a.href = url;
+      a.download = "hermes-achievement-" + (achievement.id || "badge") + ".png";
+      document.body.appendChild(a);
+      a.click();
+      a.remove();
+      setTimeout(function () { URL.revokeObjectURL(url); }, 1000);
+    }
+
+    async function copyToClipboard() {
+      if (!blobRef.current) return;
+      try {
+        if (!navigator.clipboard || !window.ClipboardItem) {
+          throw new Error("Clipboard image copy not supported in this browser — use Download instead.");
+        }
+        await navigator.clipboard.write([
+          new window.ClipboardItem({ "image/png": blobRef.current }),
+        ]);
+        setStatus("copied");
+        setTimeout(function () { setStatus("ready"); }, 1800);
+      } catch (err) {
+        setErrorMsg(String(err && err.message || err));
+        setStatus("error");
+      }
+    }
+
+    // Build the pre-filled tweet text. Keep it short so X doesn't truncate
+    // when the user hasn't attached the PNG yet — they'll copy-image and
+    // paste in the same flow.
+    function tweetText() {
+      const tierPart = achievement.tier ? (achievement.tier + " tier ") : "";
+      return "Just unlocked " + tierPart + "\"" + achievement.name + "\" in Hermes Agent ☤\n\n" +
+        "@NousResearch · https://hermes-agent.nousresearch.com";
+    }
+
+    function shareOnX() {
+      const url = "https://x.com/intent/post?text=" + encodeURIComponent(tweetText());
+      window.open(url, "_blank", "noopener,noreferrer");
+    }
+
+    return React.createElement("div", {
+      className: "ha-share-backdrop",
+      onClick: function (e) { if (e.target === e.currentTarget) onClose(); },
+    },
+      React.createElement("div", { className: "ha-share-dialog", role: "dialog", "aria-label": "Share achievement" },
+        React.createElement("div", { className: "ha-share-head" },
+          React.createElement("strong", null, "Share: " + achievement.name),
+          React.createElement("button", { className: "ha-share-close", onClick: onClose, "aria-label": "Close" }, "×")
+        ),
+        React.createElement("div", { className: "ha-share-preview" },
+          status === "rendering" && React.createElement("div", { className: "ha-share-placeholder" }, "Rendering…"),
+          previewUrl && React.createElement("img", { src: previewUrl, alt: achievement.name + " share card" })
+        ),
+        status === "error" && React.createElement("div", { className: "ha-share-error" }, errorMsg || "Something went wrong."),
+        React.createElement("div", { className: "ha-share-actions" },
+          React.createElement("button", {
+            className: "ha-share-btn ha-share-btn-primary",
+            onClick: shareOnX,
+            title: "Opens X with a pre-filled post",
+          }, "Share on X"),
+          React.createElement("button", {
+            className: "ha-share-btn",
+            onClick: copyToClipboard,
+            disabled: status !== "ready" && status !== "copied",
+            title: "Copy the image to paste into your post",
+          }, status === "copied" ? "Copied ✓" : "Copy image"),
+          React.createElement("button", {
+            className: "ha-share-btn",
+            onClick: download,
+            disabled: status !== "ready" && status !== "copied",
+          }, "Download PNG")
+        ),
+        React.createElement("p", { className: "ha-share-hint" },
+          "Share on X opens a pre-filled post in a new tab. Click Copy image first if you want the 1200×630 badge attached — X lets you paste it right into the tweet composer. Download PNG saves the file for use anywhere."
+        )
+      )
+    );
+  }
+
   function StatCard(props) {
     return React.createElement(C.Card, { className: "ha-stat" },
       React.createElement(C.CardContent, { className: "ha-stat-content" },
@@ -170,6 +460,7 @@
     const targetTier = achievement.next_tier || achievement.tier;
     const tierLabel = achievement.tier ? achievement.tier : (targetTier ? "Target " + targetTier : (state === "secret" ? "Hidden" : (unlocked ? "Complete" : "Objective")));
     const progressText = state === "secret" ? "hidden" : (progress + (achievement.next_threshold ? " / " + achievement.next_threshold : ""));
+    const [shareOpen, setShareOpen] = hooks.useState(false);
     return React.createElement(C.Card, { className: cn("ha-card", "ha-state-" + state, tierClass(achievement.tier || achievement.next_tier)) },
       React.createElement(C.CardContent, { className: "ha-card-content" },
         React.createElement("div", { className: "ha-card-head" },
@@ -180,7 +471,13 @@
           ),
           React.createElement("div", { className: "ha-badges" },
             React.createElement("span", { className: "ha-state-badge" }, stateLabel),
-            React.createElement("span", { className: "ha-tier-badge" }, tierLabel)
+            React.createElement("span", { className: "ha-tier-badge" }, tierLabel),
+            state === "unlocked" && React.createElement("button", {
+              className: "ha-share-trigger",
+              onClick: function () { setShareOpen(true); },
+              title: "Share this achievement",
+              "aria-label": "Share " + achievement.name,
+            }, "Share")
           )
         ),
         React.createElement("p", { className: "ha-description" }, achievement.description),
@@ -200,7 +497,11 @@
           ),
           React.createElement("span", { className: "ha-progress-text" }, progressText)
         )
-      )
+      ),
+      shareOpen && React.createElement(ShareDialog, {
+        achievement: achievement,
+        onClose: function () { setShareOpen(false); },
+      })
     );
   }
 

plugins/hermes-achievements/dashboard/dist/style.css

@@ -118,3 +118,29 @@
 .ha-scan-banner-text p { margin: .25rem 0 0; font-size: .78rem; line-height: 1.35; color: var(--color-muted-foreground); text-transform: none; letter-spacing: normal; }
 .ha-scan-progress-track { height: .4rem; border: 1px solid color-mix(in srgb, #67e8f9 28%, var(--color-border)); background: rgba(0,0,0,.22); overflow: hidden; }
 .ha-scan-progress-fill { height: 100%; background: linear-gradient(90deg, #67e8f9, color-mix(in srgb, #67e8f9 48%, white)); transition: width .4s ease-out; }
+
+/* Share achievement — trigger button on unlocked cards + modal dialog.
+ * Added to the vendored bundle (on top of the upstream PCinkusz base).
+ * Canvas rendering is pure client-side, no backend, no network.
+ */
+.ha-share-trigger { border: 1px solid color-mix(in srgb, var(--ha-tier) 58%, var(--color-border)); color: var(--ha-tier); background: color-mix(in srgb, var(--ha-tier) 8%, transparent); padding: .18rem .42rem; font-size: .66rem; text-transform: uppercase; letter-spacing: .08em; font-family: var(--font-mono, ui-monospace, monospace); cursor: pointer; margin-top: .05rem; transition: background .12s ease, border-color .12s ease; }
+.ha-share-trigger:hover { background: color-mix(in srgb, var(--ha-tier) 20%, transparent); border-color: var(--ha-tier); }
+.ha-share-trigger:focus-visible { outline: 2px solid var(--ha-tier); outline-offset: 2px; }
+
+.ha-share-backdrop { position: fixed; inset: 0; z-index: 1000; background: rgba(4,6,10,.72); backdrop-filter: blur(6px); display: flex; align-items: center; justify-content: center; padding: 1.5rem; animation: ha-fade-in .14s ease-out; }
+.ha-share-dialog { width: min(760px, 100%); max-height: calc(100vh - 3rem); overflow: auto; border: 1px solid color-mix(in srgb, var(--color-border) 70%, var(--color-ring)); background: color-mix(in srgb, var(--color-card) 94%, #000); box-shadow: 0 24px 60px rgba(0,0,0,.55); display: flex; flex-direction: column; gap: .9rem; padding: 1rem 1.1rem 1.1rem; }
+.ha-share-head { display: flex; align-items: center; justify-content: space-between; gap: .75rem; }
+.ha-share-head strong { font-size: .82rem; text-transform: uppercase; letter-spacing: .1em; font-family: var(--font-mono, ui-monospace, monospace); color: var(--color-foreground); }
+.ha-share-close { width: 1.9rem; height: 1.9rem; display: grid; place-items: center; border: 1px solid var(--color-border); background: transparent; color: var(--color-muted-foreground); font-size: 1.1rem; cursor: pointer; line-height: 1; }
+.ha-share-close:hover { color: var(--color-foreground); border-color: var(--color-ring); }
+.ha-share-preview { position: relative; border: 1px solid var(--color-border); background: #0b0d11; overflow: hidden; aspect-ratio: 1200 / 630; }
+.ha-share-preview img { display: block; width: 100%; height: 100%; object-fit: contain; }
+.ha-share-placeholder { position: absolute; inset: 0; display: grid; place-items: center; color: var(--color-muted-foreground); font-family: var(--font-mono, ui-monospace, monospace); font-size: .82rem; text-transform: uppercase; letter-spacing: .1em; animation: ha-pulse 1.4s ease-in-out infinite; border-radius: 0; }
+.ha-share-error { border: 1px solid #ef4444; color: #fecaca; background: color-mix(in srgb, #ef4444 10%, transparent); padding: .55rem .7rem; font-size: .78rem; font-family: var(--font-mono, ui-monospace, monospace); }
+.ha-share-actions { display: flex; gap: .55rem; flex-wrap: wrap; }
+.ha-share-btn { border: 1px solid var(--color-border); background: color-mix(in srgb, var(--color-card) 72%, transparent); color: var(--color-foreground); padding: .5rem .85rem; font-size: .82rem; font-family: var(--font-mono, ui-monospace, monospace); text-transform: uppercase; letter-spacing: .08em; cursor: pointer; transition: border-color .12s ease, background .12s ease; }
+.ha-share-btn:hover:not(:disabled) { border-color: var(--color-ring); background: color-mix(in srgb, var(--color-primary) 16%, var(--color-card)); }
+.ha-share-btn:disabled { opacity: .5; cursor: not-allowed; }
+.ha-share-btn-primary { border-color: #ffffff; color: #ffffff; background: #000000; }
+.ha-share-btn-primary:hover:not(:disabled) { background: #1a1a1a; border-color: #67e8f9; color: #67e8f9; }
+.ha-share-hint { margin: 0; color: var(--color-muted-foreground); font-size: .76rem; line-height: 1.45; }

plugins/hermes-achievements/dashboard/manifest.json

@@ -3,7 +3,7 @@
   "label": "Achievements",
   "description": "Steam-style achievements for vibe coding and agentic Hermes workflows.",
   "icon": "Star",
-  "version": "0.3.1",
+  "version": "0.4.0",
   "tab": { "path": "/achievements", "position": "after:analytics" },
   "entry": "dist/index.js",
   "css": "dist/style.css",

plugins/image_gen/xai/__init__.py

@@ -203,11 +203,12 @@ class XAIImageGenProvider(ImageGenProvider):
             )
             response.raise_for_status()
         except requests.HTTPError as exc:
-            status = exc.response.status_code if exc.response else 0
+            response = exc.response
+            status = response.status_code if response is not None else 0
             try:
-                err_msg = exc.response.json().get("error", {}).get("message", exc.response.text[:300])
+                err_msg = response.json().get("error", {}).get("message", response.text[:300])
             except Exception:
-                err_msg = exc.response.text[:300] if exc.response else str(exc)
+                err_msg = response.text[:300] if response is not None else str(exc)
             logger.error("xAI image gen failed (%d): %s", status, err_msg)
             return error_response(
                 error=f"xAI image generation failed ({status}): {err_msg}",

plugins/kanban/dashboard/dist/index.js

@@ -63,6 +63,53 @@
   const API = "/api/plugins/kanban";
   const MIME_TASK = "text/x-hermes-task";
 
+  // localStorage key for the user's selected board. Independent of the
+  // CLI's on-disk ``<root>/kanban/current`` pointer so browser users
+  // can inspect any board without shifting the CLI's active board out
+  // from under a terminal they left open.
+  const LS_BOARD_KEY = "hermes.kanban.selectedBoard";
+
+  function readSelectedBoard() {
+    try {
+      const v = window.localStorage.getItem(LS_BOARD_KEY);
+      return (v || "").trim() || null;
+    } catch (_e) { return null; }
+  }
+
+  function writeSelectedBoard(slug) {
+    try {
+      if (slug && slug !== "default") window.localStorage.setItem(LS_BOARD_KEY, slug);
+      else window.localStorage.removeItem(LS_BOARD_KEY);
+    } catch (_e) { /* ignore quota / private mode */ }
+  }
+
+  function withBoard(url, board) {
+    // Append ?board=<slug> when a non-default board is active. Omitted
+    // for default so the URL stays clean and the backend falls through
+    // to its own resolution chain (env var → ``current`` file →
+    // default) which is already correct.
+    if (!board || board === "default") return url;
+    const sep = url.indexOf("?") >= 0 ? "&" : "?";
+    return `${url}${sep}board=${encodeURIComponent(board)}`;
+  }
+
+  // The SDK's Select component fires ``onValueChange(value)`` directly
+  // (it's a shadcn-style popup, not a native <select>). Older plugin
+  // code calls ``onChange({target: {value}})`` which silently never
+  // fires. This helper wires both signatures so a setter works with
+  // either API — use it as:
+  //
+  //   h(Select, {..., ...selectChangeHandler(setState), ...})
+  function selectChangeHandler(setter) {
+    return {
+      onValueChange: function (v) { setter(v == null ? "" : v); },
+      onChange: function (e) {
+        const v = e && e.target ? e.target.value : e;
+        setter(v == null ? "" : v);
+      },
+    };
+  }
+
   // -------------------------------------------------------------------------
   // Minimal safe markdown renderer.
   //
@@ -245,7 +292,19 @@
   // -------------------------------------------------------------------------
 
   function KanbanPage() {
-    const [board, setBoard] = useState(null);
+    const [board, setBoard] = useState(() => readSelectedBoard() || "default");
+    const [boardList, setBoardList] = useState([]);      // [{slug, name, counts, ...}]
+    const [showNewBoard, setShowNewBoard] = useState(false);
+
+    const [kanbanBoard, setKanbanBoard] = useState(null);  // the grid data
+    // Alias so the rest of the function can keep using `board` semantically
+    // for the grid data (card columns + tenants + assignees) without
+    // colliding with the selected-board slug above. History: the old
+    // component had `const [board, setBoard]` for the grid data. We
+    // renamed the grid data to `kanbanBoard` so the more useful name
+    // (`board`) belongs to the selected slug.
+    const boardData = kanbanBoard;
+    const setBoardData = setKanbanBoard;
     const [config, setConfig] = useState(null);
     const [loading, setLoading] = useState(true);
     const [error, setError] = useState(null);
@@ -292,9 +351,9 @@
       if (tenantFilter) qs.set("tenant", tenantFilter);
       if (includeArchived) qs.set("include_archived", "true");
       const url = qs.toString() ? `${API}/board?${qs}` : `${API}/board`;
-      return SDK.fetchJSON(url)
+      return SDK.fetchJSON(withBoard(url, board))
         .then(function (data) {
-          setBoard(data);
+          setBoardData(data);
           cursorRef.current = data.latest_event_id || 0;
           setError(null);
         })
@@ -302,7 +361,26 @@
           setError(String(err && err.message ? err.message : err));
         })
         .finally(function () { setLoading(false); });
-    }, [tenantFilter, includeArchived]);
+    }, [tenantFilter, includeArchived, board]);
+
+    // --- load list of boards for the switcher ------------------------------
+    const loadBoardList = useCallback(function () {
+      return SDK.fetchJSON(`${API}/boards`)
+        .then(function (data) {
+          const boards = (data && data.boards) || [];
+          setBoardList(boards);
+          // If the stored slug isn't in the list any longer (board was
+          // deleted in the CLI while dashboard was open), fall back to
+          // default so the UI doesn't hang on a 404.
+          if (board !== "default" && !boards.find(function (b) { return b.slug === board; })) {
+            setBoard("default");
+            writeSelectedBoard("default");
+          }
+        })
+        .catch(function () { /* non-fatal */ });
+    }, [board]);
+
+    useEffect(function () { loadBoardList(); }, [loadBoardList]);
 
     const scheduleReload = useCallback(function () {
       if (reloadTimerRef.current) return;
@@ -324,16 +402,21 @@
 
     // --- WebSocket ---------------------------------------------------------
     useEffect(function () {
-      if (!board) return undefined;
+      if (!boardData) return undefined;
       wsClosedRef.current = false;
       function openWs() {
         if (wsClosedRef.current) return;
         const token = window.__HERMES_SESSION_TOKEN__ || "";
         const proto = window.location.protocol === "https:" ? "wss:" : "ws:";
-        const qs = new URLSearchParams({
+        const qsParams = {
           since: String(cursorRef.current || 0),
           token: token,
-        });
+        };
+        // Pin the WS stream to the currently-selected board so events
+        // from other boards don't bleed in. Only set for non-default so
+        // single-board installs keep the cleaner URL.
+        if (board && board !== "default") qsParams.board = board;
+        const qs = new URLSearchParams(qsParams);
         const url = `${proto}//${window.location.host}${API}/events?${qs}`;
         let ws;
         try { ws = new WebSocket(url); } catch (_e) { return; }
@@ -372,11 +455,11 @@
         wsClosedRef.current = true;
         try { wsRef.current && wsRef.current.close(); } catch (_e) { /* noop */ }
       };
-    }, [!!board, scheduleReload]);
+    }, [!!boardData, board, scheduleReload]);
 
     // --- filtering ----------------------------------------------------------
     const filteredBoard = useMemo(function () {
-      if (!board) return null;
+      if (!boardData) return null;
       const q = search.trim().toLowerCase();
       const filterTask = function (t) {
         if (assigneeFilter && t.assignee !== assigneeFilter) return false;
@@ -386,18 +469,18 @@
         }
         return true;
       };
-      return Object.assign({}, board, {
-        columns: board.columns.map(function (col) {
+      return Object.assign({}, boardData, {
+        columns: boardData.columns.map(function (col) {
           return Object.assign({}, col, { tasks: col.tasks.filter(filterTask) });
         }),
       });
-    }, [board, assigneeFilter, search]);
+    }, [boardData, assigneeFilter, search]);
 
     // --- actions ------------------------------------------------------------
     const moveTask = useCallback(function (taskId, newStatus) {
       const confirmMsg = DESTRUCTIVE_TRANSITIONS[newStatus];
       if (confirmMsg && !window.confirm(confirmMsg)) return;
-      setBoard(function (b) {
+      setBoardData(function (b) {
         if (!b) return b;
         let moved = null;
         const columns = b.columns.map(function (col) {
@@ -413,7 +496,7 @@
         }
         return Object.assign({}, b, { columns });
       });
-      SDK.fetchJSON(`${API}/tasks/${encodeURIComponent(taskId)}`, {
+      SDK.fetchJSON(withBoard(`${API}/tasks/${encodeURIComponent(taskId)}`, board), {
         method: "PATCH",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify({ status: newStatus }),
@@ -421,10 +504,10 @@
         setError(`Move failed: ${err.message || err}`);
         loadBoard();
       });
-    }, [loadBoard]);
+    }, [loadBoard, board]);
 
     const createTask = useCallback(function (body) {
-      return SDK.fetchJSON(`${API}/tasks`, {
+      return SDK.fetchJSON(withBoard(`${API}/tasks`, board), {
         method: "POST",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify(body),
@@ -437,9 +520,10 @@
           setError("Task created, but: " + res.warning);
         }
         loadBoard();
+        loadBoardList();  // refresh counts in the switcher
         return res;
       });
-    }, [loadBoard]);
+    }, [loadBoard, loadBoardList, board]);
 
     const toggleSelected = useCallback(function (id, additive) {
       setSelectedIds(function (prev) {
@@ -455,7 +539,7 @@
       if (selectedIds.size === 0) return;
       if (confirmMsg && !window.confirm(confirmMsg)) return;
       const body = Object.assign({ ids: Array.from(selectedIds) }, patch);
-      SDK.fetchJSON(`${API}/tasks/bulk`, {
+      SDK.fetchJSON(withBoard(`${API}/tasks/bulk`, board), {
         method: "POST",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify(body),
@@ -470,14 +554,50 @@
           loadBoard();
         })
         .catch(function (e) { setError(String(e.message || e)); });
-    }, [selectedIds, loadBoard, clearSelected]);
+    }, [selectedIds, loadBoard, clearSelected, board]);
+
+    // --- board switching ----------------------------------------------------
+    const switchBoard = useCallback(function (nextSlug) {
+      if (!nextSlug || nextSlug === board) return;
+      // Optimistic UI: clear the current grid + show loading, reset the
+      // event cursor so the WS reopens aligned to the new board's
+      // latest_event_id on the next loadBoard.
+      setBoardData(null);
+      cursorRef.current = 0;
+      setLoading(true);
+      setBoard(nextSlug);
+      writeSelectedBoard(nextSlug);
+    }, [board]);
+
+    const createNewBoard = useCallback(function (payload) {
+      return SDK.fetchJSON(`${API}/boards`, {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify(payload),
+      }).then(function (res) {
+        loadBoardList();
+        const slug = res && res.board && res.board.slug;
+        if (slug && payload.switch) switchBoard(slug);
+        return res;
+      });
+    }, [loadBoardList, switchBoard]);
+
+    const deleteBoard = useCallback(function (slug) {
+      if (!slug || slug === "default") return Promise.resolve();
+      return SDK.fetchJSON(`${API}/boards/${encodeURIComponent(slug)}`, {
+        method: "DELETE",
+      }).then(function () {
+        loadBoardList();
+        if (board === slug) switchBoard("default");
+      });
+    }, [board, loadBoardList, switchBoard]);
 
     // --- render -------------------------------------------------------------
-    if (loading && !board) {
+    if (loading && !boardData) {
       return h("div", { className: "p-8 text-sm text-muted-foreground" },
         "Loading Kanban board…");
     }
-    if (error && !board) {
+    if (error && !boardData) {
       return h(Card, null,
         h(CardContent, { className: "p-6" },
           h("div", { className: "text-sm text-destructive" },
@@ -493,15 +613,28 @@
 
     return h(ErrorBoundary, null,
       h("div", { className: "hermes-kanban flex flex-col gap-4" },
-        h(BoardToolbar, {
+        h(BoardSwitcher, {
           board: board,
+          boardList: boardList,
+          onSwitch: switchBoard,
+          onNewClick: function () { setShowNewBoard(true); },
+          onDeleteBoard: deleteBoard,
+        }),
+        showNewBoard ? h(NewBoardDialog, {
+          onCancel: function () { setShowNewBoard(false); },
+          onCreate: function (payload) {
+            return createNewBoard(payload).then(function () { setShowNewBoard(false); });
+          },
+        }) : null,
+        h(BoardToolbar, {
+          board: boardData,
           tenantFilter, setTenantFilter,
           assigneeFilter, setAssigneeFilter,
           includeArchived, setIncludeArchived,
           laneByProfile, setLaneByProfile,
           search, setSearch,
           onNudgeDispatch: function () {
-            SDK.fetchJSON(`${API}/dispatch?max=8`, { method: "POST" })
+            SDK.fetchJSON(withBoard(`${API}/dispatch?max=8`, board), { method: "POST" })
               .then(loadBoard)
               .catch(function (e) { setError(String(e.message || e)); });
           },
@@ -509,7 +642,7 @@
         }),
         selectedIds.size > 0 ? h(BulkActionBar, {
           count: selectedIds.size,
-          assignees: (board && board.assignees) || [],
+          assignees: (boardData && boardData.assignees) || [],
           onApply: applyBulk,
           onClear: clearSelected,
         }) : null,
@@ -522,20 +655,215 @@
           onMove: moveTask,
           onOpen: setSelectedTaskId,
           onCreate: createTask,
-          allTasks: board.columns.reduce(function (acc, c) { return acc.concat(c.tasks); }, []),
+          allTasks: boardData.columns.reduce(function (acc, c) { return acc.concat(c.tasks); }, []),
         }),
         selectedTaskId ? h(TaskDrawer, {
           taskId: selectedTaskId,
+          boardSlug: board,
           onClose: function () { setSelectedTaskId(null); },
           onRefresh: loadBoard,
           renderMarkdown: renderMd,
-          allTasks: board.columns.reduce(function (acc, c) { return acc.concat(c.tasks); }, []),
+          allTasks: boardData.columns.reduce(function (acc, c) { return acc.concat(c.tasks); }, []),
           eventTick: taskEventTick[selectedTaskId] || 0,
         }) : null,
       ),
     );
   }
 
+  // -------------------------------------------------------------------------
+  // Board switcher (multi-project)
+  // -------------------------------------------------------------------------
+
+  function BoardSwitcher(props) {
+    const list = props.boardList || [];
+    const current = list.find(function (b) { return b.slug === props.board; });
+    const currentName = current && current.name ? current.name : props.board;
+    const currentTotal = current ? current.total : 0;
+    const hasMultipleBoards = list.length > 1;
+
+    // Hide entirely when only the default board exists AND it's empty —
+    // single-project users never see boards UI unless they ask for it.
+    // We show the [+ New board] affordance as soon as any board has a
+    // task (so the user can discover multi-project before they need it)
+    // OR when any non-default board exists.
+    const totalAcrossAllBoards = list.reduce(function (n, b) { return n + (b.total || 0); }, 0);
+    const shouldShow = hasMultipleBoards || totalAcrossAllBoards > 0;
+    if (!shouldShow) {
+      return h("div", {
+        className: "hermes-kanban-boardswitcher-compact",
+        title: "Boards let you separate unrelated streams of work",
+      },
+        h(Button, {
+          onClick: props.onNewClick,
+          size: "sm",
+          className: "h-7 text-xs",
+        }, "+ New board"),
+      );
+    }
+
+    return h("div", { className: "hermes-kanban-boardswitcher" },
+      h("div", { className: "hermes-kanban-boardswitcher-inner" },
+        h("div", { className: "flex flex-col gap-0.5" },
+          h("div", { className: "text-[11px] uppercase tracking-wider text-muted-foreground" },
+            "Board"),
+          h("div", { className: "flex items-center gap-2" },
+            h(Select, Object.assign({
+              value: props.board,
+              className: "h-8 min-w-[220px]",
+              "aria-label": "Switch kanban board",
+            }, selectChangeHandler(function (v) { if (v) props.onSwitch(v); })),
+              list.map(function (b) {
+                const label = b.total > 0
+                  ? `${b.name || b.slug} · ${b.total}`
+                  : (b.name || b.slug);
+                return h(SelectOption, { key: b.slug, value: b.slug }, label);
+              }),
+            ),
+            h("span", { className: "text-xs text-muted-foreground" },
+              `${currentTotal || 0} task${currentTotal === 1 ? "" : "s"}`),
+          ),
+        ),
+        h("div", { className: "flex-1" }),
+        h(Button, {
+          onClick: props.onNewClick,
+          size: "sm",
+          className: "h-8",
+        }, "+ New board"),
+        props.board !== "default"
+          ? h(Button, {
+            onClick: function () {
+              const msg =
+                `Archive board '${currentName}'? ` +
+                `It will be moved to boards/_archived/ so you can recover it later. ` +
+                `Tasks on this board will no longer appear anywhere in the UI.`;
+              if (window.confirm(msg)) props.onDeleteBoard(props.board);
+            },
+            size: "sm",
+            className: "h-8",
+            title: "Archive this board",
+          }, "Archive")
+          : null,
+      ),
+    );
+  }
+
+  function NewBoardDialog(props) {
+    const [slug, setSlug] = useState("");
+    const [name, setName] = useState("");
+    const [description, setDescription] = useState("");
+    const [icon, setIcon] = useState("");
+    const [switchTo, setSwitchTo] = useState(true);
+    const [submitting, setSubmitting] = useState(false);
+    const [err, setErr] = useState(null);
+
+    // Auto-derive a name from the slug if the user hasn't typed one.
+    const autoName = useMemo(function () {
+      if (!slug) return "";
+      return slug.replace(/[-_]+/g, " ")
+        .split(" ")
+        .filter(Boolean)
+        .map(function (w) { return w[0].toUpperCase() + w.slice(1); })
+        .join(" ");
+    }, [slug]);
+
+    function onSubmit(ev) {
+      if (ev) ev.preventDefault();
+      if (!slug.trim()) { setErr("slug is required"); return; }
+      setSubmitting(true);
+      setErr(null);
+      props.onCreate({
+        slug: slug.trim(),
+        name: name.trim() || autoName || undefined,
+        description: description.trim() || undefined,
+        icon: icon.trim() || undefined,
+        switch: switchTo,
+      }).catch(function (e) {
+        setErr(String(e && e.message ? e.message : e));
+        setSubmitting(false);
+      });
+    }
+
+    return h("div", {
+      className: "hermes-kanban-dialog-backdrop",
+      onClick: function (e) { if (e.target === e.currentTarget) props.onCancel(); },
+    },
+      h("form", {
+        className: "hermes-kanban-dialog",
+        onSubmit: onSubmit,
+      },
+        h("div", { className: "hermes-kanban-dialog-title" }, "New board"),
+        h("div", { className: "text-xs text-muted-foreground mb-2" },
+          "Boards let you separate unrelated streams of work — one per project, repo, or domain. Workers on one board never see another board's tasks."),
+        h("div", { className: "flex flex-col gap-3" },
+          h("div", { className: "flex flex-col gap-1" },
+            h(Label, { className: "text-xs" }, "Slug ",
+              h("span", { className: "text-muted-foreground" },
+                "— lowercase, hyphens, e.g. atm10-server")),
+            h(Input, {
+              value: slug,
+              onChange: function (e) { setSlug(e.target.value.toLowerCase().replace(/[^a-z0-9\-_]/g, "-")); },
+              placeholder: "atm10-server",
+              autoFocus: true,
+              className: "h-8",
+            }),
+          ),
+          h("div", { className: "flex flex-col gap-1" },
+            h(Label, { className: "text-xs" }, "Display name ",
+              h("span", { className: "text-muted-foreground" }, "(optional)")),
+            h(Input, {
+              value: name,
+              onChange: function (e) { setName(e.target.value); },
+              placeholder: autoName || "Display name",
+              className: "h-8",
+            }),
+          ),
+          h("div", { className: "flex flex-col gap-1" },
+            h(Label, { className: "text-xs" }, "Description ",
+              h("span", { className: "text-muted-foreground" }, "(optional)")),
+            h(Input, {
+              value: description,
+              onChange: function (e) { setDescription(e.target.value); },
+              placeholder: "What goes on this board?",
+              className: "h-8",
+            }),
+          ),
+          h("div", { className: "flex flex-col gap-1" },
+            h(Label, { className: "text-xs" }, "Icon ",
+              h("span", { className: "text-muted-foreground" }, "(single character or emoji)")),
+            h(Input, {
+              value: icon,
+              onChange: function (e) { setIcon(e.target.value.slice(0, 4)); },
+              placeholder: "📦",
+              className: "h-8 w-24",
+            }),
+          ),
+          h("label", { className: "flex items-center gap-2 text-xs" },
+            h("input", {
+              type: "checkbox",
+              checked: switchTo,
+              onChange: function (e) { setSwitchTo(e.target.checked); },
+            }),
+            "Switch to this board after creating it",
+          ),
+        ),
+        err ? h("div", { className: "text-xs text-destructive mt-2" }, err) : null,
+        h("div", { className: "hermes-kanban-dialog-actions" },
+          h(Button, {
+            type: "button",
+            onClick: props.onCancel,
+            size: "sm",
+            disabled: submitting,
+          }, "Cancel"),
+          h(Button, {
+            type: "submit",
+            size: "sm",
+            disabled: submitting || !slug.trim(),
+          }, submitting ? "Creating…" : "Create board"),
+        ),
+      ),
+    );
+  }
+
   // -------------------------------------------------------------------------
   // Toolbar
   // -------------------------------------------------------------------------
@@ -555,11 +883,10 @@
       ),
       h("div", { className: "flex flex-col gap-1" },
         h(Label, { className: "text-xs text-muted-foreground" }, "Tenant"),
-        h(Select, {
+        h(Select, Object.assign({
           value: props.tenantFilter,
-          onChange: function (e) { props.setTenantFilter(e.target.value); },
           className: "h-8",
-        },
+        }, selectChangeHandler(props.setTenantFilter)),
           h(SelectOption, { value: "" }, "All tenants"),
           tenants.map(function (t) {
             return h(SelectOption, { key: t, value: t }, t);
@@ -568,11 +895,10 @@
       ),
       h("div", { className: "flex flex-col gap-1" },
         h(Label, { className: "text-xs text-muted-foreground" }, "Assignee"),
-        h(Select, {
+        h(Select, Object.assign({
           value: props.assigneeFilter,
-          onChange: function (e) { props.setAssigneeFilter(e.target.value); },
           className: "h-8",
-        },
+        }, selectChangeHandler(props.setAssigneeFilter)),
           h(SelectOption, { value: "" }, "All profiles"),
           assignees.map(function (a) {
             return h(SelectOption, { key: a, value: a }, a);
@@ -919,6 +1245,12 @@
     const [priority, setPriority] = useState(0);
     const [parent, setParent] = useState("");
     const [skills, setSkills] = useState("");
+    // Workspace controls. `scratch` (default) ignores path; `worktree` optionally
+    // takes a path (dispatcher derives one from the assignee profile otherwise);
+    // `dir` requires a path. Backend enforces the rule — we only hide/show the
+    // input here to save vertical space in the common `scratch` case.
+    const [workspaceKind, setWorkspaceKind] = useState("scratch");
+    const [workspacePath, setWorkspacePath] = useState("");
 
     const submit = function () {
       const trimmed = title.trim();
@@ -938,10 +1270,23 @@
         .map(function (s) { return s.trim(); })
         .filter(function (s) { return s.length > 0; });
       if (skillList.length > 0) body.skills = skillList;
+      // Only send workspace_kind when it's non-default. Keeps the request
+      // shape small and interoperable with older dispatcher versions.
+      if (workspaceKind && workspaceKind !== "scratch") {
+        body.workspace_kind = workspaceKind;
+      }
+      const wpTrim = workspacePath.trim();
+      if (wpTrim) body.workspace_path = wpTrim;
       props.onSubmit(body);
       setTitle(""); setAssignee(""); setPriority(0); setParent(""); setSkills("");
+      setWorkspaceKind("scratch"); setWorkspacePath("");
     };
 
+    const showPathInput = workspaceKind !== "scratch";
+    const pathPlaceholder = workspaceKind === "dir"
+      ? "workspace path (required, e.g. ~/projects/my-app)"
+      : "workspace path (optional, derived from assignee if blank)";
+
     return h("div", { className: "hermes-kanban-inline-create" },
       h(Input, {
         value: title,
@@ -978,6 +1323,24 @@
         title: "Force-load these skills into the worker (in addition to the built-in kanban-worker).",
         className: "h-7 text-xs",
       }),
+      h("div", { className: "flex gap-2" },
+        h(Select, {
+          value: workspaceKind,
+          onChange: function (e) { setWorkspaceKind(e.target.value); },
+          title: "scratch: isolated temp dir (default). worktree: git worktree on the assignee profile. dir: exact path (required below).",
+          className: "h-7 text-xs w-28",
+        },
+          h(SelectOption, { value: "scratch" }, "scratch"),
+          h(SelectOption, { value: "worktree" }, "worktree"),
+          h(SelectOption, { value: "dir" }, "dir"),
+        ),
+        showPathInput ? h(Input, {
+          value: workspacePath,
+          onChange: function (e) { setWorkspacePath(e.target.value); },
+          placeholder: pathPlaceholder,
+          className: "h-7 text-xs flex-1",
+        }) : null,
+      ),
       h(Select, {
         value: parent,
         onChange: function (e) { setParent(e.target.value); },
@@ -1012,13 +1375,14 @@
     const [err, setErr] = useState(null);
     const [newComment, setNewComment] = useState("");
     const [editing, setEditing] = useState(false);
+    const boardSlug = props.boardSlug;
 
     const load = useCallback(function () {
-      return SDK.fetchJSON(`${API}/tasks/${encodeURIComponent(props.taskId)}`)
+      return SDK.fetchJSON(withBoard(`${API}/tasks/${encodeURIComponent(props.taskId)}`, boardSlug))
         .then(function (d) { setData(d); setErr(null); })
         .catch(function (e) { setErr(String(e.message || e)); })
         .finally(function () { setLoading(false); });
-    }, [props.taskId]);
+    }, [props.taskId, boardSlug]);
 
     // Reload when the WS stream reports new events for this task id
     // (completion, block, crash, etc. — anything that'd make the drawer
@@ -1033,7 +1397,7 @@
     const handleComment = function () {
       const body = newComment.trim();
       if (!body) return;
-      SDK.fetchJSON(`${API}/tasks/${encodeURIComponent(props.taskId)}/comments`, {
+      SDK.fetchJSON(withBoard(`${API}/tasks/${encodeURIComponent(props.taskId)}/comments`, boardSlug), {
         method: "POST",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify({ body }),
@@ -1048,7 +1412,7 @@
       if (opts && opts.confirm && !window.confirm(opts.confirm)) {
         return Promise.resolve();
       }
-      return SDK.fetchJSON(`${API}/tasks/${encodeURIComponent(props.taskId)}`, {
+      return SDK.fetchJSON(withBoard(`${API}/tasks/${encodeURIComponent(props.taskId)}`, boardSlug), {
         method: "PATCH",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify(patch),
@@ -1056,7 +1420,7 @@
     };
 
     const addLink = function (parentId) {
-      return SDK.fetchJSON(`${API}/links`, {
+      return SDK.fetchJSON(withBoard(`${API}/links`, boardSlug), {
         method: "POST",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify({ parent_id: parentId, child_id: props.taskId }),
@@ -1065,12 +1429,12 @@
     };
     const removeLink = function (parentId) {
       const qs = new URLSearchParams({ parent_id: parentId, child_id: props.taskId });
-      return SDK.fetchJSON(`${API}/links?${qs}`, { method: "DELETE" })
+      return SDK.fetchJSON(withBoard(`${API}/links?${qs}`, boardSlug), { method: "DELETE" })
         .then(function () { load(); props.onRefresh(); })
         .catch(function (e) { setErr(String(e.message || e)); });
     };
     const addChild = function (childId) {
-      return SDK.fetchJSON(`${API}/links`, {
+      return SDK.fetchJSON(withBoard(`${API}/links`, boardSlug), {
         method: "POST",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify({ parent_id: props.taskId, child_id: childId }),
@@ -1079,7 +1443,7 @@
     };
     const removeChild = function (childId) {
       const qs = new URLSearchParams({ parent_id: props.taskId, child_id: childId });
-      return SDK.fetchJSON(`${API}/links?${qs}`, { method: "DELETE" })
+      return SDK.fetchJSON(withBoard(`${API}/links?${qs}`, boardSlug), { method: "DELETE" })
         .then(function () { load(); props.onRefresh(); })
         .catch(function (e) { setErr(String(e.message || e)); });
     };
@@ -1104,6 +1468,7 @@
           data, editing, setEditing,
           renderMarkdown: props.renderMarkdown,
           allTasks: props.allTasks,
+          boardSlug: boardSlug,
           onPatch: doPatch,
           onAddParent: addLink,
           onRemoveParent: removeLink,
@@ -1216,7 +1581,7 @@
           );
         }),
       ),
-      h(WorkerLogSection, { taskId: t.id }),
+      h(WorkerLogSection, { taskId: t.id, boardSlug: props.boardSlug }),
       h(RunHistorySection, { runs: props.data.runs || [] }),
     );
   }
@@ -1287,10 +1652,10 @@
     const [state, setState] = useState({ loading: false, data: null, err: null });
     const load = useCallback(function () {
       setState({ loading: true, data: null, err: null });
-      SDK.fetchJSON(`${API}/tasks/${encodeURIComponent(props.taskId)}/log?tail=100000`)
+      SDK.fetchJSON(withBoard(`${API}/tasks/${encodeURIComponent(props.taskId)}/log?tail=100000`, props.boardSlug))
         .then(function (d) { setState({ loading: false, data: d, err: null }); })
         .catch(function (e) { setState({ loading: false, data: null, err: String(e.message || e) }); });
-    }, [props.taskId]);
+    }, [props.taskId, props.boardSlug]);
 
     // Auto-load when the section mounts; the user opened the drawer so the
     // cost is one small HTTP round-trip.

plugins/kanban/dashboard/dist/style.css

@@ -268,7 +268,7 @@
 }
 
 .hermes-kanban-drawer {
-  width: min(480px, 92vw);
+  width: min(var(--hermes-kanban-drawer-width, 640px), 92vw);
   height: 100vh;
   background: var(--color-card);
   border-left: 1px solid var(--color-border);
@@ -334,7 +334,7 @@
 .hermes-kanban-meta-row {
   display: flex;
   gap: 0.5rem;
-  font-size: 0.72rem;
+  font-size: 0.8rem;
 }
 .hermes-kanban-meta-label {
   width: 92px;
@@ -367,14 +367,15 @@
 
 .hermes-kanban-pre {
   margin: 0;
-  padding: 0.45rem 0.55rem;
+  padding: 0.5rem 0.6rem;
   white-space: pre-wrap;
   word-break: break-word;
   background: color-mix(in srgb, var(--color-foreground) 4%, transparent);
   border: 1px solid var(--color-border);
   border-radius: var(--radius-sm, 0.25rem);
   font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.72rem;
+  font-size: 0.8rem;
+  line-height: 1.5;
   color: var(--color-foreground);
 }
 
@@ -605,8 +606,8 @@
 /* ---- Markdown rendering -------------------------------------------- */
 
 .hermes-kanban-md {
-  font-size: 0.8rem;
-  line-height: 1.55;
+  font-size: 0.85rem;
+  line-height: 1.6;
   color: var(--color-foreground);
 }
 .hermes-kanban-md p  { margin: 0.25rem 0; }
@@ -632,15 +633,22 @@
 }
 .hermes-kanban-md code {
   font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.75rem;
+  font-size: 0.8rem;
   padding: 0.05rem 0.3rem;
   background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
   border-radius: 3px;
+  color: inherit;
 }
+/* Fenced code block. Set a visible background even when --color-foreground
+ * is empty (color-mix falls through to transparent in that case), and force
+ * color: inherit so the text tracks the drawer foreground rather than the
+ * UA default on <code> elements — otherwise themes that don't set
+ * --color-foreground leave code text rendering near-black on dark themes
+ * (see issue #18576). */
 .hermes-kanban-md-code {
   margin: 0.35rem 0;
   padding: 0.5rem 0.6rem;
-  background: color-mix(in srgb, var(--color-foreground) 5%, transparent);
+  background: color-mix(in srgb, currentColor 6%, transparent);
   border: 1px solid var(--color-border);
   border-radius: var(--radius-sm, 0.25rem);
   overflow-x: auto;
@@ -648,8 +656,9 @@
 .hermes-kanban-md-code code {
   background: transparent;
   padding: 0;
-  font-size: 0.75rem;
+  font-size: 0.8rem;
   white-space: pre;
+  color: inherit;
 }
 .hermes-kanban-md strong { font-weight: 600; }
 
@@ -684,11 +693,11 @@
 /* ---- Worker log pane ------------------------------------------------ */
 
 .hermes-kanban-log {
-  max-height: 340px;
+  max-height: 360px;
   overflow: auto;
   white-space: pre;
-  font-size: 0.7rem;
-  line-height: 1.45;
+  font-size: 0.78rem;
+  line-height: 1.5;
 }
 
 
@@ -739,7 +748,8 @@
   color: var(--color-muted-foreground);
 }
 .hermes-kanban-run-summary {
-  font-size: 0.75rem;
+  font-size: 0.82rem;
+  line-height: 1.5;
   padding: 0.2rem 0 0;
   color: var(--color-foreground);
 }
@@ -751,10 +761,65 @@
 }
 .hermes-kanban-run-meta {
   display: block;
-  font-size: 0.65rem;
+  font-size: 0.72rem;
+  line-height: 1.5;
   padding: 0.15rem 0 0;
   color: var(--color-muted-foreground);
   white-space: pre-wrap;
   word-break: break-word;
   font-family: var(--font-mono, ui-monospace, monospace);
 }
+
+/* -------------------------------------------------------------------------
+   Multi-project: board switcher + create-board dialog
+   ------------------------------------------------------------------------- */
+.hermes-kanban-boardswitcher {
+  border: 1px solid var(--color-border, rgba(120, 120, 140, 0.25));
+  border-radius: 0.5rem;
+  padding: 0.6rem 0.85rem;
+  background: var(--color-card-subtle, rgba(255, 255, 255, 0.02));
+}
+.hermes-kanban-boardswitcher-inner {
+  display: flex;
+  align-items: flex-end;
+  gap: 0.75rem;
+  flex-wrap: wrap;
+}
+.hermes-kanban-boardswitcher-compact {
+  display: flex;
+  justify-content: flex-end;
+  padding: 0 0.25rem;
+}
+.hermes-kanban-dialog-backdrop {
+  position: fixed;
+  inset: 0;
+  background: rgba(8, 10, 16, 0.55);
+  backdrop-filter: blur(2px);
+  z-index: 60;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+.hermes-kanban-dialog {
+  background: var(--color-card, #121421);
+  color: var(--color-foreground);
+  border: 1px solid var(--color-border, rgba(120, 120, 140, 0.25));
+  border-radius: 0.5rem;
+  padding: 1.1rem 1.2rem 1rem;
+  width: 28rem;
+  max-width: calc(100vw - 2rem);
+  max-height: calc(100vh - 3rem);
+  overflow: auto;
+  box-shadow: 0 18px 40px rgba(0, 0, 0, 0.5);
+}
+.hermes-kanban-dialog-title {
+  font-size: 1rem;
+  font-weight: 600;
+  margin-bottom: 0.25rem;
+}
+.hermes-kanban-dialog-actions {
+  display: flex;
+  justify-content: flex-end;
+  gap: 0.5rem;
+  margin-top: 1rem;
+}

plugins/kanban/dashboard/plugin_api.py

@@ -72,19 +72,45 @@ def _check_ws_token(provided: Optional[str]) -> bool:
     return hmac.compare_digest(str(provided), str(expected))
 
 
-def _conn():
+def _resolve_board(board: Optional[str]) -> Optional[str]:
+    """Validate and normalise a board slug from a query param.
+
+    Raises :class:`HTTPException` 400 on malformed slugs so the browser
+    sees a clean error instead of a 500. Returns the normalised slug,
+    or ``None`` when the caller omitted the param (which then falls
+    through to the active board inside ``kb.connect()``).
+    """
+    if board is None or board == "":
+        return None
+    try:
+        normed = kanban_db._normalize_board_slug(board)
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc))
+    if normed and normed != kanban_db.DEFAULT_BOARD and not kanban_db.board_exists(normed):
+        raise HTTPException(
+            status_code=404,
+            detail=f"board {normed!r} does not exist",
+        )
+    return normed
+
+
+def _conn(board: Optional[str] = None):
     """Open a kanban_db connection, creating the schema on first use.
 
     Every handler that mutates the DB goes through this so the plugin
     self-heals on a fresh install (no user-visible "no such table"
     error if somebody hits POST /tasks before GET /board).
     ``init_db`` is idempotent.
+
+    ``board`` is the query-param slug (already normalised by
+    :func:`_resolve_board`). When ``None`` the active board is used
+    via the resolution chain (env var → ``current`` file → ``default``).
     """
     try:
-        kanban_db.init_db()
+        kanban_db.init_db(board=board)
     except Exception as exc:
         log.warning("kanban init_db failed: %s", exc)
-    return kanban_db.connect()
+    return kanban_db.connect(board=board)
 
 
 # ---------------------------------------------------------------------------
@@ -177,13 +203,19 @@ def _links_for(conn: sqlite3.Connection, task_id: str) -> dict[str, list[str]]:
 def get_board(
     tenant: Optional[str] = Query(None, description="Filter to a single tenant"),
     include_archived: bool = Query(False),
+    board: Optional[str] = Query(None, description="Kanban board slug (omit for current)"),
 ):
     """Return the full board grouped by status column.
 
     ``_conn()`` auto-initializes ``kanban.db`` on first call so a fresh
     install doesn't surface a "failed to load" error on the plugin tab.
+
+    ``board`` selects which board to read from. Omitting it falls
+    through to the active board (``HERMES_KANBAN_BOARD`` env → on-disk
+    ``current`` pointer → ``default``).
     """
-    conn = _conn()
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         tasks = kanban_db.list_tasks(
             conn, tenant=tenant, include_archived=include_archived
@@ -274,8 +306,9 @@ def get_board(
 # ---------------------------------------------------------------------------
 
 @router.get("/tasks/{task_id}")
-def get_task(task_id: str):
-    conn = _conn()
+def get_task(task_id: str, board: Optional[str] = Query(None)):
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         task = kanban_db.get_task(conn, task_id)
         if task is None:
@@ -311,8 +344,9 @@ class CreateTaskBody(BaseModel):
 
 
 @router.post("/tasks")
-def create_task(payload: CreateTaskBody):
-    conn = _conn()
+def create_task(payload: CreateTaskBody, board: Optional[str] = Query(None)):
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         task_id = kanban_db.create_task(
             conn,
@@ -373,8 +407,9 @@ class UpdateTaskBody(BaseModel):
 
 
 @router.patch("/tasks/{task_id}")
-def update_task(task_id: str, payload: UpdateTaskBody):
-    conn = _conn()
+def update_task(task_id: str, payload: UpdateTaskBody, board: Optional[str] = Query(None)):
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         task = kanban_db.get_task(conn, task_id)
         if task is None:
@@ -414,7 +449,12 @@ def update_task(task_id: str, payload: UpdateTaskBody):
                     ok = _set_status_direct(conn, task_id, "ready")
             elif s == "archived":
                 ok = kanban_db.archive_task(conn, task_id)
-            elif s in ("todo", "running", "triage"):
+            elif s == "running":
+                raise HTTPException(
+                    status_code=400,
+                    detail="Cannot set status to 'running' directly; use the dispatcher/claim path",
+                )
+            elif s in ("todo", "triage"):
                 ok = _set_status_direct(conn, task_id, s)
             else:
                 raise HTTPException(status_code=400, detail=f"unknown status: {s}")
@@ -527,10 +567,11 @@ class CommentBody(BaseModel):
 
 
 @router.post("/tasks/{task_id}/comments")
-def add_comment(task_id: str, payload: CommentBody):
+def add_comment(task_id: str, payload: CommentBody, board: Optional[str] = Query(None)):
     if not payload.body.strip():
         raise HTTPException(status_code=400, detail="body is required")
-    conn = _conn()
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         if kanban_db.get_task(conn, task_id) is None:
             raise HTTPException(status_code=404, detail=f"task {task_id} not found")
@@ -552,8 +593,9 @@ class LinkBody(BaseModel):
 
 
 @router.post("/links")
-def add_link(payload: LinkBody):
-    conn = _conn()
+def add_link(payload: LinkBody, board: Optional[str] = Query(None)):
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         kanban_db.link_tasks(conn, payload.parent_id, payload.child_id)
         return {"ok": True}
@@ -564,8 +606,13 @@ def add_link(payload: LinkBody):
 
 
 @router.delete("/links")
-def delete_link(parent_id: str = Query(...), child_id: str = Query(...)):
-    conn = _conn()
+def delete_link(
+    parent_id: str = Query(...),
+    child_id: str = Query(...),
+    board: Optional[str] = Query(None),
+):
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         ok = kanban_db.unlink_tasks(conn, parent_id, child_id)
         return {"ok": bool(ok)}
@@ -586,7 +633,7 @@ class BulkTaskBody(BaseModel):
 
 
 @router.post("/tasks/bulk")
-def bulk_update(payload: BulkTaskBody):
+def bulk_update(payload: BulkTaskBody, board: Optional[str] = Query(None)):
     """Apply the same patch to every id in ``payload.ids``.
 
     This is an *independent* iteration — per-task failures don't abort
@@ -596,7 +643,8 @@ def bulk_update(payload: BulkTaskBody):
     if not ids:
         raise HTTPException(status_code=400, detail="ids is required")
     results: list[dict] = []
-    conn = _conn()
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         for tid in ids:
             entry: dict[str, Any] = {"id": tid, "ok": True}
@@ -690,14 +738,15 @@ def get_config():
 # ---------------------------------------------------------------------------
 
 @router.get("/stats")
-def get_stats():
+def get_stats(board: Optional[str] = Query(None)):
     """Per-status + per-assignee counts + oldest-ready age.
 
     Designed for the dashboard HUD and for router profiles that need to
     answer "is this specialist overloaded?" without scanning the whole
     board themselves.
     """
-    conn = _conn()
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         return kanban_db.board_stats(conn)
     finally:
@@ -705,7 +754,7 @@ def get_stats():
 
 
 @router.get("/assignees")
-def get_assignees():
+def get_assignees(board: Optional[str] = Query(None)):
     """Known profiles + per-profile task counts.
 
     Returns the union of ``~/.hermes/profiles/*`` on disk and every
@@ -713,7 +762,8 @@ def get_assignees():
     this to populate its assignee dropdown so a freshly-created profile
     appears in the picker before it's been given any task.
     """
-    conn = _conn()
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         return {"assignees": kanban_db.known_assignees(conn)}
     finally:
@@ -725,7 +775,11 @@ def get_assignees():
 # ---------------------------------------------------------------------------
 
 @router.get("/tasks/{task_id}/log")
-def get_task_log(task_id: str, tail: Optional[int] = Query(None, ge=1, le=2_000_000)):
+def get_task_log(
+    task_id: str,
+    tail: Optional[int] = Query(None, ge=1, le=2_000_000),
+    board: Optional[str] = Query(None),
+):
     """Return the worker's stdout/stderr log.
 
     ``tail`` caps the response size (bytes) so the dashboard drawer
@@ -734,15 +788,16 @@ def get_task_log(task_id: str, tail: Optional[int] = Query(None, ge=1, le=2_000_
     ``_rotate_worker_log`` — a single ``.log.1`` is kept, no further
     generations, so disk usage per task is bounded at ~4 MiB.
     """
-    conn = _conn()
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         task = kanban_db.get_task(conn, task_id)
     finally:
         conn.close()
     if task is None:
         raise HTTPException(status_code=404, detail=f"task {task_id} not found")
-    content = kanban_db.read_worker_log(task_id, tail_bytes=tail)
-    log_path = kanban_db.worker_log_path(task_id)
+    content = kanban_db.read_worker_log(task_id, tail_bytes=tail, board=board)
+    log_path = kanban_db.worker_log_path(task_id, board=board)
     size = log_path.stat().st_size if log_path.exists() else 0
     return {
         "task_id": task_id,
@@ -760,11 +815,16 @@ def get_task_log(task_id: str, tail: Optional[int] = Query(None, ge=1, le=2_000_
 # ---------------------------------------------------------------------------
 
 @router.post("/dispatch")
-def dispatch(dry_run: bool = Query(False), max_n: int = Query(8, alias="max")):
-    conn = _conn()
+def dispatch(
+    dry_run: bool = Query(False),
+    max_n: int = Query(8, alias="max"),
+    board: Optional[str] = Query(None),
+):
+    board = _resolve_board(board)
+    conn = _conn(board=board)
     try:
         result = kanban_db.dispatch_once(
-            conn, dry_run=dry_run, max_spawn=max_n,
+            conn, dry_run=dry_run, max_spawn=max_n, board=board,
         )
         # DispatchResult is a dataclass.
         try:
@@ -775,6 +835,124 @@ def dispatch(dry_run: bool = Query(False), max_n: int = Query(8, alias="max")):
         conn.close()
 
 
+# ---------------------------------------------------------------------------
+# Boards CRUD (multi-project support)
+# ---------------------------------------------------------------------------
+
+class CreateBoardBody(BaseModel):
+    slug: str
+    name: Optional[str] = None
+    description: Optional[str] = None
+    icon: Optional[str] = None
+    color: Optional[str] = None
+    switch: bool = False
+
+
+class RenameBoardBody(BaseModel):
+    name: Optional[str] = None
+    description: Optional[str] = None
+    icon: Optional[str] = None
+    color: Optional[str] = None
+
+
+def _board_counts(slug: str) -> dict[str, int]:
+    """Return ``{status: count}`` for a board. Safe on an empty DB."""
+    try:
+        path = kanban_db.kanban_db_path(board=slug)
+        if not path.exists():
+            return {}
+        conn = kanban_db.connect(board=slug)
+        try:
+            rows = conn.execute(
+                "SELECT status, COUNT(*) AS n FROM tasks GROUP BY status"
+            ).fetchall()
+            return {r["status"]: int(r["n"]) for r in rows}
+        finally:
+            conn.close()
+    except Exception:
+        return {}
+
+
+@router.get("/boards")
+def list_boards(include_archived: bool = Query(False)):
+    """Return every board on disk with task counts and the active slug."""
+    boards = kanban_db.list_boards(include_archived=include_archived)
+    current = kanban_db.get_current_board()
+    for b in boards:
+        b["is_current"] = (b["slug"] == current)
+        b["counts"] = _board_counts(b["slug"])
+        b["total"] = sum(b["counts"].values())
+    return {"boards": boards, "current": current}
+
+
+@router.post("/boards")
+def create_board_endpoint(payload: CreateBoardBody):
+    """Create a new board. Idempotent — ``slug`` collision returns existing."""
+    try:
+        meta = kanban_db.create_board(
+            payload.slug,
+            name=payload.name,
+            description=payload.description,
+            icon=payload.icon,
+            color=payload.color,
+        )
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc))
+    if payload.switch:
+        try:
+            kanban_db.set_current_board(meta["slug"])
+        except ValueError as exc:
+            raise HTTPException(status_code=400, detail=str(exc))
+    return {"board": meta, "current": kanban_db.get_current_board()}
+
+
+@router.patch("/boards/{slug}")
+def rename_board(slug: str, payload: RenameBoardBody):
+    """Update a board's display metadata (slug is immutable — create a new one to rename the directory)."""
+    try:
+        normed = kanban_db._normalize_board_slug(slug)
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc))
+    if not normed or not kanban_db.board_exists(normed):
+        raise HTTPException(status_code=404, detail=f"board {slug!r} does not exist")
+    meta = kanban_db.write_board_metadata(
+        normed,
+        name=payload.name,
+        description=payload.description,
+        icon=payload.icon,
+        color=payload.color,
+    )
+    return {"board": meta}
+
+
+@router.delete("/boards/{slug}")
+def delete_board(slug: str, delete: bool = Query(False, description="Hard-delete instead of archive")):
+    """Archive (default) or hard-delete a board."""
+    try:
+        res = kanban_db.remove_board(slug, archive=not delete)
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc))
+    return {"result": res, "current": kanban_db.get_current_board()}
+
+
+@router.post("/boards/{slug}/switch")
+def switch_board(slug: str):
+    """Persist ``slug`` as the active board for subsequent CLI / slash calls.
+
+    Dashboard users pick boards via a client-side ``localStorage`` — this
+    endpoint is for ``/kanban boards switch`` parity so gateway slash
+    commands and the CLI share the same current-board pointer.
+    """
+    try:
+        normed = kanban_db._normalize_board_slug(slug)
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc))
+    if not normed or not kanban_db.board_exists(normed):
+        raise HTTPException(status_code=404, detail=f"board {slug!r} does not exist")
+    kanban_db.set_current_board(normed)
+    return {"current": normed}
+
+
 # ---------------------------------------------------------------------------
 # WebSocket: /events?since=<event_id>
 # ---------------------------------------------------------------------------
@@ -802,8 +980,18 @@ async def stream_events(ws: WebSocket):
         except ValueError:
             cursor = 0
 
+        # Board selection — pinned at the WS handshake; re-subscribe to
+        # switch boards. Changing boards mid-stream would require
+        # reconciling two cursors, so the UI just opens a new WS on
+        # board change.
+        ws_board_raw = ws.query_params.get("board")
+        try:
+            ws_board = kanban_db._normalize_board_slug(ws_board_raw) if ws_board_raw else None
+        except ValueError:
+            ws_board = None
+
         def _fetch_new(cursor_val: int) -> tuple[int, list[dict]]:
-            conn = kanban_db.connect()
+            conn = kanban_db.connect(board=ws_board)
             try:
                 rows = conn.execute(
                     "SELECT id, task_id, run_id, kind, payload, created_at "

plugins/platforms/teams/adapter.py

@@ -592,6 +592,8 @@ def interactive_setup() -> None:
     from hermes_cli.config import (
         get_env_value,
         save_env_value,
+    )
+    from hermes_cli.cli_output import (
         prompt,
         prompt_yes_no,
         print_info,

run_agent.py

@@ -3611,7 +3611,7 @@ class AIAgent:
                     _parent_runtime = self._current_main_runtime()
                     review_agent = AIAgent(
                         model=self.model,
-                        max_iterations=8,
+                        max_iterations=16,
                         quiet_mode=True,
                         platform=self.platform,
                         provider=self.provider,
@@ -3629,6 +3629,14 @@ class AIAgent:
                     review_agent._user_profile_enabled = self._user_profile_enabled
                     review_agent._memory_nudge_interval = 0
                     review_agent._skill_nudge_interval = 0
+                    # Suppress all status/warning emits from the fork so the
+                    # user only sees the final successful-action summary.
+                    # Without this, mid-review "Iteration budget exhausted",
+                    # rate-limit retries, compression warnings, and other
+                    # lifecycle messages bubble up through _emit_status ->
+                    # _vprint and leak past the stdout redirect (they go via
+                    # _print_fn/status_callback, which bypass sys.stdout).
+                    review_agent.suppress_status_output = True
 
                     review_agent.run_conversation(
                         user_message=prompt,
@@ -5056,6 +5064,23 @@ class AIAgent:
             return tc.get("call_id", "") or tc.get("id", "") or ""
         return getattr(tc, "call_id", "") or getattr(tc, "id", "") or ""
 
+    @staticmethod
+    def _get_tool_call_name_static(tc) -> str:
+        """Extract function name from a tool_call entry (dict or object).
+
+        Gemini's OpenAI-compatibility endpoint requires every `role: tool`
+        message to carry the matching function name. OpenAI/Anthropic/ollama
+        tolerate its absence, so the field is best-effort: callers fall back
+        to "" and the message still works elsewhere.
+        """
+        if isinstance(tc, dict):
+            fn = tc.get("function")
+            if isinstance(fn, dict):
+                return fn.get("name", "") or ""
+            return ""
+        fn = getattr(tc, "function", None)
+        return getattr(fn, "name", "") or ""
+
     _VALID_API_ROLES = frozenset({"system", "user", "assistant", "tool", "function", "developer"})
 
     @staticmethod
@@ -5118,6 +5143,7 @@ class AIAgent:
                         if cid in missing_results:
                             patched.append({
                                 "role": "tool",
+                                "name": AIAgent._get_tool_call_name_static(tc),
                                 "content": "[Result unavailable — see context summary above]",
                                 "tool_call_id": cid,
                             })
@@ -5816,6 +5842,17 @@ class AIAgent:
             return primary_client
         with self._openai_client_lock():
             request_kwargs = dict(self._client_kwargs)
+        # Per-request OpenAI-wire clients (used by both the non-streaming
+        # chat-completions path and the streaming chat-completions path
+        # in `_interruptible_api_call`) should not run the SDK's built-in
+        # retry loop: the agent's outer loop owns retries with credential
+        # rotation, provider fallback, and backoff that the SDK can't
+        # see. Leaving SDK retries on (default 2) compounds with our outer
+        # retries and lets a single hung provider request stretch to ~3x
+        # the per-call timeout before our stale detector reports it.
+        # Shared/primary clients and Anthropic / Bedrock paths are
+        # unaffected (they don't go through here).
+        request_kwargs["max_retries"] = 0
         if (
             base_url_host_matches(str(request_kwargs.get("base_url", "")), "api.githubcopilot.com")
             and self._api_kwargs_have_image_parts(api_kwargs or {})
@@ -8192,6 +8229,7 @@ class AIAgent:
         """True when using an anthropic-compatible endpoint that preserves dots in model names.
         Alibaba/DashScope keeps dots (e.g. qwen3.5-plus).
         MiniMax keeps dots (e.g. MiniMax-M2.7).
+        Xiaomi MiMo keeps dots (e.g. mimo-v2.5, mimo-v2.5-pro).
         OpenCode Go/Zen keeps dots for non-Claude models (e.g. minimax-m2.5-free).
         ZAI/Zhipu keeps dots (e.g. glm-4.7, glm-5.1).
         AWS Bedrock uses dotted inference-profile IDs
@@ -8205,6 +8243,7 @@ class AIAgent:
             "alibaba", "minimax", "minimax-cn",
             "opencode-go", "opencode-zen",
             "zai", "bedrock",
+            "xiaomi",
         }:
             return True
         base = (getattr(self, "base_url", "") or "").lower()
@@ -8214,6 +8253,7 @@ class AIAgent:
             or "minimax" in base
             or "opencode.ai/zen/" in base
             or "bigmodel.cn" in base
+            or "xiaomimimo.com" in base
             # AWS Bedrock runtime endpoints — defense-in-depth when
             # ``provider`` is unset but ``base_url`` still names Bedrock.
             or "bedrock-runtime." in base
@@ -9008,6 +9048,7 @@ class AIAgent:
                             insert_at,
                             {
                                 "role": "tool",
+                                "name": function_name if function_name != "?" else "",
                                 "tool_call_id": tool_call_id,
                                 "content": marker,
                             },
@@ -9412,6 +9453,7 @@ class AIAgent:
             for tc in tool_calls:
                 messages.append({
                     "role": "tool",
+                    "name": tc.function.name,
                     "content": f"[Tool execution cancelled — {tc.function.name} was skipped due to user interrupt]",
                     "tool_call_id": tc.id,
                 })
@@ -9753,6 +9795,7 @@ class AIAgent:
 
             tool_msg = {
                 "role": "tool",
+                "name": name,
                 "content": function_result,
                 "tool_call_id": tc.id,
             }
@@ -9790,6 +9833,7 @@ class AIAgent:
                     skipped_name = skipped_tc.function.name
                     skip_msg = {
                         "role": "tool",
+                        "name": skipped_name,
                         "content": f"[Tool execution cancelled — {skipped_name} was skipped due to user interrupt]",
                         "tool_call_id": skipped_tc.id,
                     }
@@ -10140,6 +10184,7 @@ class AIAgent:
 
             tool_msg = {
                 "role": "tool",
+                "name": function_name,
                 "content": function_result,
                 "tool_call_id": tool_call.id
             }
@@ -10166,6 +10211,7 @@ class AIAgent:
                     skipped_name = skipped_tc.function.name
                     skip_msg = {
                         "role": "tool",
+                        "name": skipped_name,
                         "content": f"[Tool execution skipped — {skipped_name} was not started. User sent a new message]",
                         "tool_call_id": skipped_tc.id
                     }
@@ -10300,7 +10346,10 @@ class AIAgent:
                     provider_preferences["order"] = self.providers_order
                 if self.provider_sort:
                     provider_preferences["sort"] = self.provider_sort
-                if provider_preferences:
+                if provider_preferences and (
+                    (self.provider or "").strip().lower() == "openrouter"
+                    or self._is_openrouter_url()
+                ):
                     summary_extra_body["provider"] = provider_preferences
 
                 if summary_extra_body:
@@ -10418,6 +10467,15 @@ class AIAgent:
         from hermes_logging import set_session_context
         set_session_context(self.session_id)
 
+        # Bind the skill write-origin ContextVar for this thread so tool
+        # handlers (e.g. skill_manage create) can tell whether they are
+        # running inside the background self-improvement review fork vs.
+        # a foreground user-directed turn. Set at the top of each call;
+        # the review fork runs on its own thread with a fresh context,
+        # so the foreground value here does not leak into it.
+        from tools.skill_provenance import set_current_write_origin
+        set_current_write_origin(getattr(self, "_memory_write_origin", "assistant_tool"))
+
         # If the previous turn activated fallback, restore the primary
         # runtime so this turn gets a fresh attempt with the preferred model.
         # No-op when _fallback_activated is False (gateway, first turn, etc.).
@@ -10623,11 +10681,11 @@ class AIAgent:
                     self.model,
                     f"{self.context_compressor.context_length:,}",
                 )
-                if not self.quiet_mode:
-                    self._safe_print(
-                        f"📦 Preflight compression: ~{_preflight_tokens:,} tokens "
-                        f">= {self.context_compressor.threshold_tokens:,} threshold"
-                    )
+                self._emit_status(
+                    f"📦 Preflight compression: ~{_preflight_tokens:,} tokens "
+                    f">= {self.context_compressor.threshold_tokens:,} threshold. "
+                    "This may take a moment."
+                )
                 # May need multiple passes for very large sessions with small
                 # context windows (each pass summarises the middle N turns).
                 for _pass in range(3):
@@ -13076,6 +13134,7 @@ class AIAgent:
                                 content = "Skipped: another tool call in this turn used an invalid name. Please retry this tool call."
                             messages.append({
                                 "role": "tool",
+                                "name": tc.function.name,
                                 "tool_call_id": tc.id,
                                 "content": content,
                             })
@@ -13167,6 +13226,7 @@ class AIAgent:
                                     tool_result = "Skipped: other tool call in this response had invalid JSON."
                                 messages.append({
                                     "role": "tool",
+                                    "name": tc.function.name,
                                     "tool_call_id": tc.id,
                                     "content": tool_result,
                                 })
@@ -13415,9 +13475,22 @@ class AIAgent:
                             m.get("role") == "tool"
                             for m in messages[-5:]  # check recent messages
                         )
+                        # Detect Qwen3/Ollama-style in-content thinking blocks.
+                        # Ollama puts <think> in the content field (not in
+                        # reasoning_content), so _has_structured below would
+                        # miss it.  We check here so thinking-only responses
+                        # after tool calls route to prefill instead of nudge.
+                        _has_inline_thinking = bool(
+                            re.search(
+                                r'<think>|<thinking>|<reasoning>',
+                                final_response or "",
+                                re.IGNORECASE,
+                            )
+                        )
                         if (
                             _prior_was_tool
                             and not getattr(self, "_post_tool_empty_retried", False)
+                            and not _has_inline_thinking  # thinking model still working — let prefill handle
                         ):
                             self._post_tool_empty_retried = True
                             # Clear stale narration so it doesn't resurface
@@ -13457,10 +13530,13 @@ class AIAgent:
                         # continue — the model will see its own reasoning
                         # on the next turn and produce the text portion.
                         # Inspired by clawdbot's "incomplete-text" recovery.
+                        # Also covers Qwen3/Ollama in-content <think> blocks
+                        # (detected above as _has_inline_thinking).
                         _has_structured = bool(
                             getattr(assistant_message, "reasoning", None)
                             or getattr(assistant_message, "reasoning_content", None)
                             or getattr(assistant_message, "reasoning_details", None)
+                            or _has_inline_thinking
                         )
                         if _has_structured and self._thinking_prefill_retries < 2:
                             self._thinking_prefill_retries += 1
@@ -13667,6 +13743,7 @@ class AIAgent:
                             if tc["id"] not in answered_ids:
                                 err_msg = {
                                     "role": "tool",
+                                    "name": AIAgent._get_tool_call_name_static(tc),
                                     "tool_call_id": tc["id"],
                                     "content": f"Error executing tool: {error_msg}",
                                 }

scripts/release.py

@@ -48,6 +48,7 @@ AUTHOR_MAP = {
     "127238744+teknium1@users.noreply.github.com": "teknium1",
     "159539633+MottledShadow@users.noreply.github.com": "MottledShadow",
     "aludwin+gh@gmail.com": "adamludwin",
+    "ngusev@astralinux.ru": "NikolayGusev-astra",
     "2093036+exiao@users.noreply.github.com": "exiao",
     "rylen.anil@gmail.com": "rylena",
     "godnanijatin@gmail.com": "jatingodnani",
@@ -67,6 +68,8 @@ AUTHOR_MAP = {
     "nbot@liizfq.top": "liizfq",
     "274096618+hermes-agent-dhabibi@users.noreply.github.com": "dhabibi",
     "dejie.guo@gmail.com": "JayGwod",
+    "133716830+0xKingBack@users.noreply.github.com": "0xKingBack",
+    "daixin1204@gmail.com": "SimbaKingjoe",
     "maxence@groine.fr": "MaxyMoos",
     "61830395+leprincep35700@users.noreply.github.com": "leprincep35700",
     # OpenViking viking_read salvage (April 2026)
@@ -95,6 +98,7 @@ AUTHOR_MAP = {
     "252818347@qq.com": "hejuntt1014",
     "uzmpsk.dilekakbas@gmail.com": "dlkakbs",
     "beliefanx@gmail.com": "BeliefanX",
+    "changchun989@proton.me": "changchun989",
     "jefferson@heimdallstrategy.com": "Mind-Dragon",
     "44753291+Nanako0129@users.noreply.github.com": "Nanako0129",
     "steve.westerhouse@origami-analytics.com": "westers",
@@ -339,6 +343,8 @@ AUTHOR_MAP = {
     "haileymarshall005@gmail.com": "haileymarshall",
     "greer.guthrie@gmail.com": "g-guthrie",
     "kennyx102@gmail.com": "bobashopcashier",
+    "77253505+bobashopcashier@users.noreply.github.com": "bobashopcashier",
+    "25355950+megastary@users.noreply.github.com": "megastary",  # PR #18325
     "shokatalishaikh95@gmail.com": "areu01or00",
     "bryan@intertwinesys.com": "bryanyoung",
     "christo.mitov@gmail.com": "christomitov",
@@ -457,6 +463,7 @@ AUTHOR_MAP = {
     "centripetal-star@users.noreply.github.com": "centripetal-star",
     "LeonSGP43@users.noreply.github.com": "LeonSGP43",
     "154585401+LeonSGP43@users.noreply.github.com": "LeonSGP43",
+    "cine.dreamer.one@gmail.com": "LeonSGP43",
     "Lubrsy706@users.noreply.github.com": "Lubrsy706",
     "niyant@spicefi.xyz": "spniyant",
     "olafthiele@gmail.com": "olafthiele",
@@ -510,6 +517,7 @@ AUTHOR_MAP = {
     "nftpoetrist@gmail.com": "nftpoetrist",  # PR #18982
     "millerc79@users.noreply.github.com": "millerc79",  # PR #19033
     "hermes@example.com": "shellybotmoyer",  # PR #18915 (bot-committed)
+    "exx@example.com": "exxmen",  # PR #19555
     "hypnosis.mda@gmail.com": "Hypn0sis",
     "ywt000818@gmail.com": "OwenYWT",
     "dhandhalyabhavik@gmail.com": "v1k22",
@@ -621,6 +629,84 @@ AUTHOR_MAP = {
     "2114364329@qq.com": "cuyua9",
     "2557058999@qq.com": "Disaster-Terminator",
     "cine.dreamer.one@gmail.com": "LeonSGP43",
+    "zyprothh@gmail.com": "Zyproth",
+    "amitgaur@gmail.com": "amitgaur",
+    "albuquerque.abner@gmail.com": "mrbob-git",
+    "kiala@users.noreply.github.com": "kiala9",
+    "alanxchen@gmail.com": "alanxchen85",
+    "clawbot@clawbots-Mac-mini.local": "John-tip",
+    "der@konsi.org": "konsisumer",
+    "cirwel@The-CIRWEL-Group.local": "CIRWEL",
+    "molvikar8@gmail.com": "molvikar",
+    "nftpoetrist@gmail.com": "nftpoetrist",
+    "dodofun@126.com": "colorcross",
+    "1615063567@qq.com": "zhao0112",
+    "ethanguo.2003@gmail.com": "EthanGuo-coder",
+    "dev0jsh@gmail.com": "tmdgusya",
+    "leavr@163.com": "leavrcn",
+    "17683456+wanazhar@users.noreply.github.com": "wanazhar",
+    "26782336+cixuuz@users.noreply.github.com": "cixuuz",
+    "aleksandr.pasevin@openzeppelin.com": "pasevin",
+    "ubuntu@localhost.localdomain": "holynn-q",
+    "holynn@placeholder.local": "holynn-q",
+    "agent@hermes.local": "jacdevos",
+    "sunsky.lau@gmail.com": "liuhao1024",
+    "qiuqfang98@qq.com": "keepcalmqqf",
+    "261867348+ai-ag2026@users.noreply.github.com": "ai-ag2026",
+    "yanzh.su@gmail.com": "YanzhongSu",
+    "wanderwang@users.noreply.github.com": "WanderWang",
+    "yueheime@gmail.com": "yuehei",
+    "emidomh@gmail.com": "Emidomenge",
+    "2642448440@qq.com": "BlackJulySnow",
+    "4317663+helix4u@users.noreply.github.com": "helix4u",
+    "floptopbot33@gmail.com": "flobo3",
+    "dpaluy@users.noreply.github.com": "dpaluy",
+    "psikonetik@gmail.com": "el-analista",
+    "chenb19870707@gmail.com": "ms-alan",
+    "hex-clawd@users.noreply.github.com": "hex-clawd",
+    "154585401+LeonSGP43@users.noreply.github.com": "LeonSGP43",
+    "barteq@hacknotes.local": "barteqpl",
+    "pama0227@gmail.com": "pama0227",
+    "52785845+ee-blog@users.noreply.github.com": "ee-blog",
+    "simplenamebox@gmail.com": "simplenamebox-ops",
+    "balyan.sid@gmail.com": "alt-glitch",
+    "xdord@xdorddeMac-mini.local": "foreverxdord",
+    "k2767567815@gmail.com": "QifengKuang",
+    "88077783+jjjojoj@users.noreply.github.com": "jjjojoj",
+    "valda@underscore.jp": "valda",
+    "lling486@163.com": "M3RCUR2Y",
+    "buraysandro9@gmail.com": "ygd58",
+    "ideathinklab01-source@users.noreply.github.com": "ideathinklab01-source",
+    "27987889@qq.com": "zng8418",
+    "daniuxie88@proton.me": "DaniuXie",
+    "panchanler@gmail.com": "ChanlerDev",
+    "252620095+briandevans@users.noreply.github.com": "briandevans",
+    "141889580+h0tp-ftw@users.noreply.github.com": "h0tp-ftw",
+    "chinadbo@foxmail.com": "chinadbo",
+    "82637225+kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
+    "xyywtt@gmail.com": "xyiy001",
+    "charliekerfoot@gmail.com": "CharlieKerfoot",
+    "grey0202@users.noreply.github.com": "Grey0202",
+    "vominh1919@gmail.com": "vominh1919",
+    "giwavictor9@gmail.com": "giwaov",
+    "yoimexex@gmail.com": "Yoimex",
+    "76803960+atongrun@users.noreply.github.com": "atongrun",
+    "michaeldanko@icloud.com": "MichaelWDanko",
+    "xudavid429@gmail.com": "YX234",
+    "kathy@Kathy.local": "julysir",
+    "274902531@qq.com": "JanCong",
+    "225304168+e-shizz@users.noreply.github.com": "e-shizz",
+    "vincent_hh@users.noreply.github.com": "VinVC",
+    "1243352777@qq.com": "zons-zhaozhy",
+    "dejie.guo@gmail.com": "JayGwod",
+    "52840391+swithek@users.noreply.github.com": "swithek",
+    "raipratik0101@gmail.com": "PratikRai0101",
+    "code@sasha.id": "sasha-id",
+    "chen.yunbo@xydigit.com": "chenyunbo411",
+    "openclaw@local": "Asce66",
+    "59465365+0xsir0000@users.noreply.github.com": "0xsir0000",
+    "lisanhu2014@hotmail.com": "lisanhu",
+    "0668001438@zte.com.cn": "chenyunbo411",
     "leozeli@qq.com": "leozeli",
     "linlehao@cuhk.edu.cn": "LehaoLin",
     "liutong@isacas.ac.cn": "I3eg1nner",
@@ -679,6 +765,8 @@ AUTHOR_MAP = {
     "ztzheng@163.com": "chengoak",  # PR #17467
     "24110240104@m.fudan.edu.cn": "YuShu",  # co-author only
     "charliekerfoot@gmail.com": "CharlieKerfoot",  # PR #18951
+    # Debug share upload-time redaction (May 2026)
+    "dhuysamen@gmail.com": "GodsBoy",  # PR #19318
 }
 
 

tests/agent/test_anthropic_adapter.py

@@ -1113,6 +1113,45 @@ class TestBuildAnthropicKwargs:
         assert _forbids_sampling_params("claude-opus-4-6") is False
         assert _forbids_sampling_params("claude-sonnet-4-5") is False
 
+    def test_supports_fast_mode_predicate(self):
+        """Fast mode is Opus 4.6 only — Opus 4.7 and others must be excluded."""
+        from agent.anthropic_adapter import _supports_fast_mode
+        assert _supports_fast_mode("claude-opus-4-6") is True
+        assert _supports_fast_mode("anthropic/claude-opus-4-6") is True
+        assert _supports_fast_mode("claude-opus-4-7") is False
+        assert _supports_fast_mode("claude-sonnet-4-6") is False
+        assert _supports_fast_mode("claude-haiku-4-5") is False
+        assert _supports_fast_mode("") is False
+
+    def test_fast_mode_omitted_for_unsupported_model(self):
+        """fast_mode=True on Opus 4.7 must NOT inject speed=fast (API 400s)."""
+        kwargs = build_anthropic_kwargs(
+            model="claude-opus-4-7",
+            messages=[{"role": "user", "content": "hi"}],
+            tools=None,
+            max_tokens=1024,
+            reasoning_config=None,
+            fast_mode=True,
+        )
+        # extra_body either absent or doesn't carry "speed"
+        assert "speed" not in kwargs.get("extra_body", {})
+        # No fast-mode beta header should be added either
+        beta_header = (kwargs.get("extra_headers") or {}).get("anthropic-beta", "")
+        assert "fast-mode-2026-02-01" not in beta_header
+
+    def test_fast_mode_still_applied_on_opus_46(self):
+        """Regression guard — fast mode must still work on Opus 4.6."""
+        kwargs = build_anthropic_kwargs(
+            model="claude-opus-4-6",
+            messages=[{"role": "user", "content": "hi"}],
+            tools=None,
+            max_tokens=1024,
+            reasoning_config=None,
+            fast_mode=True,
+        )
+        assert kwargs.get("extra_body", {}).get("speed") == "fast"
+        assert "fast-mode-2026-02-01" in kwargs["extra_headers"]["anthropic-beta"]
+
     def test_reasoning_disabled(self):
         kwargs = build_anthropic_kwargs(
             model="claude-sonnet-4-20250514",

tests/agent/test_auxiliary_client.py

@@ -1893,3 +1893,53 @@ class TestOpenRouterExplicitApiKey:
             assert call_kwargs["api_key"] == "env-fallback-key", (
                 f"Expected env fallback key to be used when explicit_api_key is None, got: {call_kwargs['api_key']}"
             )
+
+
+class TestAnthropicExplicitApiKey:
+    """Test that explicit_api_key is correctly propagated to _try_anthropic().
+
+    Parity with the OpenRouter fix in #18768: resolve_provider_client() passes
+    explicit_api_key to _try_openrouter(), but the anthropic branch was not
+    updated — _try_anthropic() always fell back to resolve_anthropic_token()
+    even when an explicit key was supplied (e.g. from a fallback_model entry).
+    """
+
+    def test_try_anthropic_uses_explicit_api_key_over_env(self):
+        """_try_anthropic(explicit_api_key) must use the supplied key, not the env fallback."""
+        with patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="env-fallback-key"), \
+             patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
+             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
+            mock_build.return_value = MagicMock()
+            from agent.auxiliary_client import _try_anthropic
+            client, model = _try_anthropic("explicit-pool-key")
+        assert client is not None
+        assert mock_build.call_args.args[0] == "explicit-pool-key", (
+            f"Expected explicit_api_key to be passed, got: {mock_build.call_args.args[0]}"
+        )
+        assert mock_build.call_args.args[0] != "env-fallback-key"
+
+    def test_try_anthropic_without_explicit_key_falls_back_to_resolve(self):
+        """Without explicit_api_key, _try_anthropic falls back to resolve_anthropic_token."""
+        with patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="env-fallback-key"), \
+             patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
+             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
+            mock_build.return_value = MagicMock()
+            from agent.auxiliary_client import _try_anthropic
+            client, model = _try_anthropic()
+        assert client is not None
+        assert mock_build.call_args.args[0] == "env-fallback-key"
+
+    def test_resolve_provider_client_passes_explicit_api_key_to_anthropic(self):
+        """resolve_provider_client(provider='anthropic', explicit_api_key=...) must propagate the key."""
+        with patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="env-key"), \
+             patch("agent.anthropic_adapter.build_anthropic_client") as mock_build, \
+             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)):
+            mock_build.return_value = MagicMock()
+            client, model = resolve_provider_client(
+                provider="anthropic",
+                explicit_api_key="explicit-fallback-key",
+            )
+        assert client is not None
+        assert mock_build.call_args.args[0] == "explicit-fallback-key", (
+            "resolve_provider_client must forward explicit_api_key to _try_anthropic()"
+        )

tests/agent/test_bedrock_adapter.py

@@ -1283,18 +1283,21 @@ class TestIsStaleConnectionError:
     """Classifier that decides whether an exception warrants client eviction."""
 
     def test_detects_botocore_connection_closed_error(self):
+        pytest.importorskip("botocore", reason="botocore required for Bedrock exception tests")
         from agent.bedrock_adapter import is_stale_connection_error
         from botocore.exceptions import ConnectionClosedError
         exc = ConnectionClosedError(endpoint_url="https://bedrock.example")
         assert is_stale_connection_error(exc) is True
 
     def test_detects_botocore_endpoint_connection_error(self):
+        pytest.importorskip("botocore", reason="botocore required for Bedrock exception tests")
         from agent.bedrock_adapter import is_stale_connection_error
         from botocore.exceptions import EndpointConnectionError
         exc = EndpointConnectionError(endpoint_url="https://bedrock.example")
         assert is_stale_connection_error(exc) is True
 
     def test_detects_botocore_read_timeout(self):
+        pytest.importorskip("botocore", reason="botocore required for Bedrock exception tests")
         from agent.bedrock_adapter import is_stale_connection_error
         from botocore.exceptions import ReadTimeoutError
         exc = ReadTimeoutError(endpoint_url="https://bedrock.example")
@@ -1355,6 +1358,7 @@ class TestCallConverseInvalidatesOnStaleError:
     reconnects instead of reusing the dead socket."""
 
     def test_converse_evicts_client_on_stale_error(self):
+        pytest.importorskip("botocore", reason="botocore required for Bedrock exception tests")
         from agent.bedrock_adapter import (
             _bedrock_runtime_client_cache,
             call_converse,
@@ -1381,6 +1385,7 @@ class TestCallConverseInvalidatesOnStaleError:
         )
 
     def test_converse_stream_evicts_client_on_stale_error(self):
+        pytest.importorskip("botocore", reason="botocore required for Bedrock exception tests")
         from agent.bedrock_adapter import (
             _bedrock_runtime_client_cache,
             call_converse_stream,
@@ -1406,6 +1411,7 @@ class TestCallConverseInvalidatesOnStaleError:
 
     def test_converse_does_not_evict_on_non_stale_error(self):
         """Non-stale errors (e.g. ValidationException) leave the client cache alone."""
+        pytest.importorskip("botocore", reason="botocore required for Bedrock exception tests")
         from agent.bedrock_adapter import (
             _bedrock_runtime_client_cache,
             call_converse,

tests/agent/test_context_compressor.py

@@ -1281,6 +1281,47 @@ class TestTokenBudgetTailProtection:
         assert isinstance(cut, int)
         assert 0 <= cut <= len(messages)
 
+    def test_generous_budget_protects_everything_floor_does_not_override(
+        self, budget_compressor
+    ):
+        """A budget that covers the whole transcript must prune nothing —
+        ``protect_tail_count`` is a minimum floor, not a ceiling."""
+        c = budget_compressor
+
+        # 100 alternating assistant/tool messages.  Each tool result has
+        # *unique* content so the dedup pass (Pass 1, which is independent
+        # of prune_boundary) is a no-op and we isolate the boundary logic.
+        messages = []
+        for i in range(50):
+            messages.append({
+                "role": "assistant", "content": None,
+                "tool_calls": [{
+                    "id": f"c{i}",
+                    "type": "function",
+                    "function": {"name": "noop", "arguments": "{}"},
+                }],
+            })
+            messages.append({
+                "role": "tool",
+                "tool_call_id": f"c{i}",
+                "content": f"unique-tool-output-{i:03d}-" + ("x" * 250),
+            })
+
+        # Budget large enough to cover the whole transcript many times over,
+        # so the budget walk completes without hitting its break condition
+        # and the boundary lands at 0 ("protect everything").
+        _, pruned = c._prune_old_tool_results(
+            messages,
+            protect_tail_count=20,
+            protect_tail_tokens=10_000_000,
+        )
+
+        assert pruned == 0, (
+            "budget said protect everything, but the floor still pruned "
+            f"{pruned} messages — protect_tail_count is acting as a ceiling, "
+            "not a minimum floor"
+        )
+
 
 class TestUpdateModelBudgets:
     """Regression: update_model() must recalculate token budgets."""

tests/agent/test_curator.py

@@ -154,6 +154,7 @@ def test_unused_skill_transitions_to_stale(curator_env):
     long_ago = (datetime.now(timezone.utc) - timedelta(days=45)).isoformat()
     data = u.load_usage()
     data["old-skill"] = u._empty_record()
+    data["old-skill"]["created_by"] = "agent"
     data["old-skill"]["last_used_at"] = long_ago
     data["old-skill"]["created_at"] = long_ago
     u.save_usage(data)
@@ -172,6 +173,7 @@ def test_very_old_skill_gets_archived(curator_env):
     super_old = (datetime.now(timezone.utc) - timedelta(days=120)).isoformat()
     data = u.load_usage()
     data["ancient"] = u._empty_record()
+    data["ancient"]["created_by"] = "agent"
     data["ancient"]["last_used_at"] = super_old
     data["ancient"]["created_at"] = super_old
     u.save_usage(data)
@@ -192,6 +194,7 @@ def test_pinned_skill_is_never_touched(curator_env):
     super_old = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
     data = u.load_usage()
     data["precious"] = u._empty_record()
+    data["precious"]["created_by"] = "agent"
     data["precious"]["last_used_at"] = super_old
     data["precious"]["created_at"] = super_old
     data["precious"]["pinned"] = True
@@ -214,6 +217,7 @@ def test_stale_skill_reactivates_on_recent_use(curator_env):
     recent = datetime.now(timezone.utc).isoformat()
     data = u.load_usage()
     data["revived"] = u._empty_record()
+    data["revived"]["created_by"] = "agent"
     data["revived"]["state"] = "stale"
     data["revived"]["last_used_at"] = recent
     data["revived"]["created_at"] = recent
@@ -240,6 +244,27 @@ def test_new_skill_without_last_used_not_immediately_archived(curator_env):
     assert (skills_dir / "fresh").exists()
 
 
+def test_manual_skill_is_not_auto_archived(curator_env):
+    """Manual skills can have usage records, but without the agent-created
+    marker they must stay out of curator transitions."""
+    c = curator_env["curator"]
+    u = curator_env["usage"]
+    skills_dir = curator_env["home"] / "skills"
+    skill_dir = _write_skill(skills_dir, "manual")
+
+    super_old = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
+    data = u.load_usage()
+    data["manual"] = u._empty_record()
+    data["manual"]["last_used_at"] = super_old
+    data["manual"]["created_at"] = super_old
+    u.save_usage(data)
+
+    counts = c.apply_automatic_transitions()
+    assert counts["checked"] == 0
+    assert counts["archived"] == 0
+    assert skill_dir.exists()
+
+
 def test_bundled_skill_not_touched_by_transitions(curator_env):
     c = curator_env["curator"]
     u = curator_env["usage"]
@@ -267,8 +292,10 @@ def test_bundled_skill_not_touched_by_transitions(curator_env):
 
 def test_run_review_records_state(curator_env):
     c = curator_env["curator"]
+    u = curator_env["usage"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
+    u.mark_agent_created("a")
 
     result = c.run_curator_review(synchronous=True)
     assert "started_at" in result
@@ -284,8 +311,10 @@ def test_dry_run_does_not_advance_state(curator_env, monkeypatch):
     `hermes curator status`. Fixes #18373.
     """
     c = curator_env["curator"]
+    u = curator_env["usage"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
+    u.mark_agent_created("a")
 
     # Stub the LLM so the test doesn't need a provider.
     monkeypatch.setattr(
@@ -311,8 +340,10 @@ def test_dry_run_injects_report_only_banner(curator_env, monkeypatch):
     skips automatic transitions — but the LLM prompt is the only guard
     against the model calling skill_manage directly."""
     c = curator_env["curator"]
+    u = curator_env["usage"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
+    u.mark_agent_created("a")
 
     captured = {}
     def _stub(prompt):
@@ -331,8 +362,10 @@ def test_dry_run_skips_automatic_transitions(curator_env, monkeypatch):
     archives skills deterministically, and a preview must not touch the
     filesystem."""
     c = curator_env["curator"]
+    u = curator_env["usage"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
+    u.mark_agent_created("a")
 
     called = {"n": 0}
     def _explode(*_a, **_kw):
@@ -351,8 +384,10 @@ def test_dry_run_skips_automatic_transitions(curator_env, monkeypatch):
 
 def test_run_review_synchronous_invokes_llm_stub(curator_env, monkeypatch):
     c = curator_env["curator"]
+    u = curator_env["usage"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
+    u.mark_agent_created("a")
 
     calls = []
     def _stub(prompt):
@@ -409,8 +444,10 @@ def test_maybe_run_curator_enforces_idle_gate(curator_env, monkeypatch):
 
 def test_maybe_run_curator_runs_when_eligible(curator_env, monkeypatch):
     c = curator_env["curator"]
+    u = curator_env["usage"]
     skills_dir = curator_env["home"] / "skills"
     _write_skill(skills_dir, "a")
+    u.mark_agent_created("a")
     # Seed last_run_at far in the past so the interval gate opens — the
     # "no state" path intentionally defers the first run now (#18373).
     long_ago = datetime.now(timezone.utc) - timedelta(hours=c.get_interval_hours() * 2)
@@ -645,6 +682,86 @@ def test_review_model_honors_auxiliary_curator_slot(curator_env):
     )
 
 
+def test_review_runtime_passes_auxiliary_curator_credentials(curator_env):
+    """Per-slot api_key/base_url must ride into resolve_runtime_provider (not main-only creds)."""
+    curator = curator_env["curator"]
+    cfg = {
+        "model": {"provider": "openrouter", "default": "openai/gpt-5.5"},
+        "auxiliary": {
+            "curator": {
+                "provider": "custom",
+                "model": "local-mini",
+                "api_key": "sk-curator-only",
+                "base_url": "http://localhost:11434/v1",
+            },
+        },
+    }
+    binding = curator._resolve_review_runtime(cfg)
+    assert binding.provider == "custom"
+    assert binding.model == "local-mini"
+    assert binding.explicit_api_key == "sk-curator-only"
+    assert binding.explicit_base_url == "http://localhost:11434/v1"
+
+
+def test_review_runtime_strips_blank_aux_credentials(curator_env):
+    curator = curator_env["curator"]
+    cfg = {
+        "model": {"provider": "openrouter", "default": "openai/gpt-5.5"},
+        "auxiliary": {
+            "curator": {
+                "provider": "openrouter",
+                "model": "x/y",
+                "api_key": "   ",
+                "base_url": "",
+            },
+        },
+    }
+    binding = curator._resolve_review_runtime(cfg)
+    assert binding.explicit_api_key is None
+    assert binding.explicit_base_url is None
+
+
+def test_review_runtime_ignores_auxiliary_credentials_when_using_main(curator_env):
+    """Falling through to main model must not pick up stray auxiliary.curator secrets."""
+    curator = curator_env["curator"]
+    cfg = {
+        "model": {"provider": "openrouter", "default": "openai/gpt-5.5"},
+        "auxiliary": {
+            "curator": {
+                "provider": "auto",
+                "model": "",
+                "api_key": "must-not-leak",
+                "base_url": "http://curator-slot-ignored/",
+            },
+        },
+    }
+    binding = curator._resolve_review_runtime(cfg)
+    assert (binding.provider, binding.model) == ("openrouter", "openai/gpt-5.5")
+    assert binding.explicit_api_key is None
+    assert binding.explicit_base_url is None
+
+
+def test_review_runtime_legacy_auxiliary_carry_credentials(curator_env, caplog):
+    curator = curator_env["curator"]
+    cfg = {
+        "model": {"provider": "openrouter", "default": "openai/gpt-5.5"},
+        "curator": {
+            "auxiliary": {
+                "provider": "custom",
+                "model": "m",
+                "api_key": "legacy-key",
+                "base_url": "http://legacy/v1",
+            },
+        },
+    }
+    import logging
+    with caplog.at_level(logging.INFO, logger="agent.curator"):
+        binding = curator._resolve_review_runtime(cfg)
+    assert binding.explicit_api_key == "legacy-key"
+    assert binding.explicit_base_url == "http://legacy/v1"
+    assert any("deprecated curator.auxiliary" in rec.message for rec in caplog.records)
+
+
 def test_review_model_auxiliary_curator_partial_override_falls_back(curator_env):
     """Only one of slot provider/model set → fall back to the main pair.
 

tests/agent/test_curator_classification.py

@@ -220,6 +220,81 @@ def test_classify_handles_malformed_arguments_string(curator_env):
     assert len(result["pruned"]) == 1
 
 
+def test_classify_no_false_positive_short_name_in_file_path(curator_env):
+    """Short skill name that is a substring of another filename = pruned, not consolidated."""
+    # e.g. "api" should NOT match "references/api-design.md"
+    result = curator_env._classify_removed_skills(
+        removed=["api"],
+        added=[],
+        after_names={"conventions"},
+        tool_calls=[
+            {
+                "name": "skill_manage",
+                "arguments": json.dumps({
+                    "action": "write_file",
+                    "name": "conventions",
+                    "file_path": "references/api-design.md",
+                    "file_content": "# API Design\n...",
+                }),
+            },
+        ],
+    )
+    assert result["consolidated"] == [], (
+        f"Short name 'api' should NOT match file_path 'references/api-design.md'"
+    )
+    assert len(result["pruned"]) == 1
+    assert result["pruned"][0]["name"] == "api"
+
+
+def test_classify_no_false_positive_short_name_in_content(curator_env):
+    """Short skill name embedded in longer word in content = pruned, not consolidated."""
+    # e.g. "test" should NOT match content "running latest tests"
+    result = curator_env._classify_removed_skills(
+        removed=["test"],
+        added=[],
+        after_names={"umbrella"},
+        tool_calls=[
+            {
+                "name": "skill_manage",
+                "arguments": json.dumps({
+                    "action": "patch",
+                    "name": "umbrella",
+                    "old_string": "old",
+                    "new_string": "running latest tests with pytest",
+                }),
+            },
+        ],
+    )
+    assert result["consolidated"] == [], (
+        f"Short name 'test' should NOT match 'latest' via word boundary"
+    )
+    assert len(result["pruned"]) == 1
+
+
+def test_classify_still_matches_exact_word_in_content(curator_env):
+    """Word-boundary match still works for exact word occurrences."""
+    # "api" SHOULD match content "use the api gateway"
+    result = curator_env._classify_removed_skills(
+        removed=["api"],
+        added=[],
+        after_names={"gateway"},
+        tool_calls=[
+            {
+                "name": "skill_manage",
+                "arguments": json.dumps({
+                    "action": "edit",
+                    "name": "gateway",
+                    "content": "# Gateway\n\nUse the api gateway for all requests.\n",
+                }),
+            },
+        ],
+    )
+    assert len(result["consolidated"]) == 1, (
+        f"'api' should match as a standalone word in content"
+    )
+    assert result["consolidated"][0]["into"] == "gateway"
+
+
 def test_report_md_splits_consolidated_and_pruned_sections(curator_env):
     """End-to-end: REPORT.md shows both sections distinctly."""
     curator = curator_env

tests/agent/test_error_classifier.py

@@ -410,6 +410,24 @@ class TestClassifyApiError:
         result = classify_api_error(e, approx_tokens=1000, context_length=200000)
         assert result.reason == FailoverReason.format_error
 
+    def test_400_generic_many_messages_below_large_context_pressure_is_format_error(self):
+        """Large-context sessions should not overflow solely due to message count."""
+        e = MockAPIError(
+            "Error",
+            status_code=400,
+            body={"error": {"message": "Error"}},
+        )
+        result = classify_api_error(
+            e,
+            provider="openai-codex",
+            model="gpt-5.5",
+            approx_tokens=74320,
+            context_length=1_000_000,
+            num_messages=432,
+        )
+        assert result.reason == FailoverReason.format_error
+        assert result.should_compress is False
+
     # ── Server disconnect + large session ──
 
     def test_disconnect_large_session_context_overflow(self):
@@ -425,6 +443,20 @@ class TestClassifyApiError:
         result = classify_api_error(e, approx_tokens=5000, context_length=200000)
         assert result.reason == FailoverReason.timeout
 
+    def test_disconnect_many_messages_below_large_context_pressure_is_timeout(self):
+        """Large-context disconnects should not overflow solely due to message count."""
+        e = Exception("server disconnected without sending complete message")
+        result = classify_api_error(
+            e,
+            provider="openai-codex",
+            model="gpt-5.5",
+            approx_tokens=74320,
+            context_length=1_000_000,
+            num_messages=432,
+        )
+        assert result.reason == FailoverReason.timeout
+        assert result.should_compress is False
+
     # ── Provider-specific: Anthropic thinking signature ──
 
     def test_anthropic_thinking_signature(self):

tests/agent/test_vision_resolved_args.py

@@ -13,16 +13,13 @@ def test_vision_call_uses_resolved_provider_args():
         usage=MagicMock(prompt_tokens=10, completion_tokens=5),
     )
 
-    with (
-        patch(
-            "agent.auxiliary_client._resolve_task_provider_model",
-            return_value=("my-resolved-provider", "my-resolved-model", "http://resolved", "resolved-key", "chat_completions"),
-        ),
-        patch(
-            "agent.auxiliary_client.resolve_vision_provider_client",
-            return_value=("my-resolved-provider", fake_client, "my-resolved-model"),
-        ) as mock_vision,
-    ):
+    with patch(
+        "agent.auxiliary_client._resolve_task_provider_model",
+        return_value=("my-resolved-provider", "my-resolved-model", "http://resolved", "resolved-key", "chat_completions"),
+    ), patch(
+        "agent.auxiliary_client.resolve_vision_provider_client",
+        return_value=("my-resolved-provider", fake_client, "my-resolved-model"),
+    ) as mock_vision:
         call_llm(
             "vision",
             provider="raw-provider",
@@ -38,3 +35,30 @@ def test_vision_call_uses_resolved_provider_args():
     assert call_args.kwargs["model"] == "my-resolved-model"
     assert call_args.kwargs["base_url"] == "http://resolved"
     assert call_args.kwargs["api_key"] == "resolved-key"
+
+
+def test_vision_base_url_override_keeps_explicit_provider():
+    """Explicit provider should still drive credential resolution with custom base_url."""
+    from agent.auxiliary_client import resolve_vision_provider_client
+
+    fake_client = MagicMock()
+    with patch(
+        "agent.auxiliary_client._resolve_task_provider_model",
+        return_value=(
+            "zai",
+            "glm-4v",
+            "https://open.bigmodel.cn/api/paas/v4",
+            None,
+            "chat_completions",
+        ),
+    ), patch(
+        "agent.auxiliary_client.resolve_provider_client",
+        return_value=(fake_client, "glm-4v"),
+    ) as mock_resolve:
+        provider, client, model = resolve_vision_provider_client()
+
+    assert provider == "zai"
+    assert client is fake_client
+    assert model == "glm-4v"
+    assert mock_resolve.call_args.args[0] == "zai"
+    assert mock_resolve.call_args.kwargs["explicit_base_url"] == "https://open.bigmodel.cn/api/paas/v4"

tests/agent/transports/test_codex_transport.py

@@ -126,6 +126,20 @@ class TestCodexBuildKwargs:
         )
         assert kw.get("extra_headers", {}).get("x-grok-conv-id") == "conv-123"
 
+    def test_xai_headers_preserve_request_override_headers(self, transport):
+        messages = [{"role": "user", "content": "Hi"}]
+        kw = transport.build_kwargs(
+            model="grok-3", messages=messages, tools=[],
+            session_id="conv-123",
+            is_xai_responses=True,
+            request_overrides={"extra_headers": {"X-Test": "1", "X-Trace": "abc"}},
+        )
+        assert kw.get("extra_headers") == {
+            "X-Test": "1",
+            "X-Trace": "abc",
+            "x-grok-conv-id": "conv-123",
+        }
+
     def test_minimal_effort_clamped(self, transport):
         messages = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(

tests/cli/test_cli_init.py

@@ -123,6 +123,13 @@ class TestBusyInputMode:
         cli.process_command("/queue follow up")
         assert cli._pending_input.get_nowait() == "follow up"
 
+    def test_q_alias_queues_prompt(self):
+        """The /q alias should resolve to /queue, not /quit."""
+        cli = _make_cli()
+        cli._agent_running = False
+        assert cli.process_command("/q follow up") is True
+        assert cli._pending_input.get_nowait() == "follow up"
+
     def test_queue_mode_routes_busy_enter_to_pending(self):
         """In queue mode, Enter while busy should go to _pending_input, not _interrupt_queue."""
         cli = _make_cli(config_overrides={"display": {"busy_input_mode": "queue"}})

tests/cli/test_cli_markdown_rendering.py

@@ -22,6 +22,23 @@ def test_final_assistant_content_uses_markdown_renderable():
     assert "two" in output
 
 
+def test_final_assistant_content_preserves_windows_hidden_dir_paths():
+    renderable = _render_final_assistant_content(
+        r"D:\Projects\SourceCode\hermes-agent\.ai\skills" + "\\"
+    )
+
+    output = _render_to_text(renderable)
+    assert r"D:\Projects\SourceCode\hermes-agent\.ai\skills" + "\\" in output
+
+
+def test_final_assistant_content_keeps_non_path_markdown_escapes():
+    renderable = _render_final_assistant_content(r"1\. Not an ordered list")
+
+    output = _render_to_text(renderable)
+    assert "1. Not an ordered list" in output
+    assert r"1\." not in output
+
+
 def test_final_assistant_content_strips_ansi_before_markdown_rendering():
     renderable = _render_final_assistant_content("\x1b[31m# Title\x1b[0m")
 

tests/cli/test_cli_new_session.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 import importlib
 import os
 import sys
-from datetime import timedelta
+from datetime import datetime, timedelta
 from unittest.mock import MagicMock, patch
 
 from hermes_state import SessionDB
@@ -219,3 +219,59 @@ def test_new_session_resets_token_counters(tmp_path):
     assert comp.last_total_tokens == 0
     assert comp.compression_count == 0
     assert comp._context_probed is False
+
+
+def test_new_session_with_title(capsys):
+    """new_session(title=...) creates a session and sets the title."""
+    cli = _make_cli()
+    cli._session_db = MagicMock()
+    cli.agent = _FakeAgent("old_session_id", datetime.now())
+    cli.conversation_history = []
+
+    cli.new_session(title="My Test Session")
+
+    # Assert set_session_title was called with the new session ID and sanitized title
+    cli._session_db.set_session_title.assert_called_once()
+    call_args = cli._session_db.set_session_title.call_args
+    assert call_args[0][0] == cli.session_id
+    assert call_args[0][1] == "My Test Session"
+
+    captured = capsys.readouterr()
+    assert "My Test Session" in captured.out
+
+
+def test_new_session_with_duplicate_title_surfaces_error(capsys):
+    """new_session(title=...) handles ValueError from a duplicate-title conflict.
+
+    The session is still created; the title assignment fails; the success banner
+    must not claim the rejected title as the session name.
+    """
+    cli = _make_cli()
+    cli._session_db = MagicMock()
+    cli._session_db.set_session_title.side_effect = ValueError(
+        "Title 'Dup' is already in use by session abc-123"
+    )
+    cli.agent = _FakeAgent("old_session_id", datetime.now())
+    cli.conversation_history = []
+
+    # Capture warnings printed via cli._cprint. After importlib.reload(),
+    # the method's __globals__ dict is the one from the live module — patch
+    # the exact dict the method will read.
+    warnings: list[str] = []
+    method_globals = cli.new_session.__globals__
+    original = method_globals["_cprint"]
+    method_globals["_cprint"] = lambda msg: warnings.append(msg)
+    try:
+        cli.new_session(title="Dup")
+    finally:
+        method_globals["_cprint"] = original
+
+    cli._session_db.set_session_title.assert_called_once()
+    joined = "\n".join(warnings)
+    assert "already in use" in joined
+    assert "session started untitled" in joined
+
+    # The success banner must NOT claim the rejected title as the session name.
+    captured = capsys.readouterr()
+    assert "New session started: Dup" not in captured.out
+    assert "New session started!" in captured.out

tests/cli/test_cwd_env_respect.py

@@ -1,107 +1,101 @@
-"""Tests that load_cli_config() guards against lazy-import TERMINAL_CWD clobbering.
+"""Tests for CLI/TUI CWD resolution in load_cli_config().
 
-When the gateway resolves TERMINAL_CWD at startup and cli.py is later
-imported lazily (via delegate_tool → CLI_CONFIG), load_cli_config() must
-not overwrite the already-resolved value with os.getcwd().
-
-config.yaml terminal.cwd is the canonical source of truth.
-.env TERMINAL_CWD and MESSAGING_CWD are deprecated.
-See issue #10817.
+Rules:
+- Local backend CLI/TUI: always os.getcwd(), ignoring config and inherited env.
+- Non-local with placeholder: pop cwd for backend default.
+- Non-local with explicit path: keep as-is.
 """
 
 import os
 import pytest
 
-
-# The sentinel values that mean "resolve at runtime"
 _CWD_PLACEHOLDERS = (".", "auto", "cwd")
 
 
-def _resolve_terminal_cwd(terminal_config: dict, defaults: dict, env: dict):
-    """Simulate the CWD resolution logic from load_cli_config().
+def _resolve_cwd(terminal_config: dict, defaults: dict, env: dict):
+    """Mirror the CWD resolution logic from cli.py load_cli_config()."""
+    effective_backend = terminal_config.get("env_type", "local")
 
-    This mirrors the code in cli.py that checks for a pre-resolved
-    TERMINAL_CWD before falling back to os.getcwd().
-    """
-    if terminal_config.get("cwd") in _CWD_PLACEHOLDERS:
-        _existing_cwd = env.get("TERMINAL_CWD", "")
-        if _existing_cwd and _existing_cwd not in _CWD_PLACEHOLDERS and os.path.isabs(_existing_cwd):
-            terminal_config["cwd"] = _existing_cwd
-            defaults["terminal"]["cwd"] = _existing_cwd
-        else:
-            effective_backend = terminal_config.get("env_type", "local")
-            if effective_backend == "local":
-                terminal_config["cwd"] = "/fake/getcwd"  # stand-in for os.getcwd()
-                defaults["terminal"]["cwd"] = terminal_config["cwd"]
-            else:
-                terminal_config.pop("cwd", None)
+    if effective_backend == "local":
+        terminal_config["cwd"] = "/fake/getcwd"
+        defaults["terminal"]["cwd"] = terminal_config["cwd"]
+    elif terminal_config.get("cwd") in _CWD_PLACEHOLDERS:
+        terminal_config.pop("cwd", None)
 
-    # Simulate the bridging loop: write terminal_config["cwd"] to env
-    _file_has_terminal = defaults.get("_file_has_terminal", False)
+    # Bridge: TERMINAL_CWD always exported in CLI, skipped in gateway
+    _is_gateway = env.get("_HERMES_GATEWAY") == "1"
     if "cwd" in terminal_config:
-        if _file_has_terminal or "TERMINAL_CWD" not in env:
+        if _is_gateway:
+            pass  # don't touch env
+        else:
             env["TERMINAL_CWD"] = str(terminal_config["cwd"])
 
     return env.get("TERMINAL_CWD", "")
 
 
-class TestLazyImportGuard:
-    """TERMINAL_CWD resolved by gateway must survive a lazy cli.py import."""
+class TestLocalBackendCli:
+    """Local backend always uses os.getcwd()."""
 
-    def test_gateway_resolved_cwd_survives(self):
-        """Gateway set TERMINAL_CWD → lazy cli import must not clobber."""
-        env = {"TERMINAL_CWD": "/home/user/workspace"}
-        terminal_config = {"cwd": ".", "env_type": "local"}
-        defaults = {"terminal": {"cwd": "."}, "_file_has_terminal": False}
-
-        result = _resolve_terminal_cwd(terminal_config, defaults, env)
-        assert result == "/home/user/workspace"
-
-    def test_gateway_resolved_cwd_survives_with_file_terminal(self):
-        """Even when config.yaml has a terminal: section, resolved CWD survives."""
-        env = {"TERMINAL_CWD": "/home/user/workspace"}
-        terminal_config = {"cwd": ".", "env_type": "local"}
-        defaults = {"terminal": {"cwd": "."}, "_file_has_terminal": True}
-
-        result = _resolve_terminal_cwd(terminal_config, defaults, env)
-        assert result == "/home/user/workspace"
-
-
-class TestConfigCwdResolution:
-    """config.yaml terminal.cwd is the canonical source of truth."""
-
-    def test_explicit_config_cwd_wins(self):
-        """terminal.cwd: /explicit/path always wins."""
-        env = {"TERMINAL_CWD": "/old/gateway/value"}
-        terminal_config = {"cwd": "/explicit/path"}
-        defaults = {"terminal": {"cwd": "/explicit/path"}, "_file_has_terminal": True}
-
-        result = _resolve_terminal_cwd(terminal_config, defaults, env)
-        assert result == "/explicit/path"
-
-    def test_dot_cwd_resolves_to_getcwd_when_no_prior(self):
-        """With no pre-set TERMINAL_CWD, "." resolves to os.getcwd()."""
+    def test_explicit_config_ignored(self):
         env = {}
-        terminal_config = {"cwd": "."}
-        defaults = {"terminal": {"cwd": "."}, "_file_has_terminal": False}
+        tc = {"cwd": "/explicit/path", "env_type": "local"}
+        d = {"terminal": {"cwd": "/explicit/path"}}
+        assert _resolve_cwd(tc, d, env) == "/fake/getcwd"
 
-        result = _resolve_terminal_cwd(terminal_config, defaults, env)
+    def test_inherited_env_overwritten(self):
+        env = {"TERMINAL_CWD": "/parent/hermes"}
+        tc = {"cwd": "/home/user", "env_type": "local"}
+        d = {"terminal": {"cwd": "/home/user"}}
+        assert _resolve_cwd(tc, d, env) == "/fake/getcwd"
+
+    def test_placeholder_resolved(self):
+        env = {}
+        tc = {"cwd": "."}
+        d = {"terminal": {"cwd": "."}}
+        assert _resolve_cwd(tc, d, env) == "/fake/getcwd"
+
+    def test_env_and_no_config_file(self):
+        env = {"TERMINAL_CWD": "/stale/value"}
+        tc = {"cwd": ".", "env_type": "local"}
+        d = {"terminal": {"cwd": "."}}
+        assert _resolve_cwd(tc, d, env) == "/fake/getcwd"
+
+
+class TestNonLocalBackends:
+    """Non-local backends use config or per-backend defaults."""
+
+    def test_placeholder_popped(self):
+        env = {}
+        tc = {"cwd": ".", "env_type": "docker"}
+        d = {"terminal": {"cwd": "."}}
+        assert _resolve_cwd(tc, d, env) == ""
+
+    def test_explicit_path_kept(self):
+        env = {}
+        tc = {"cwd": "/srv/app", "env_type": "ssh"}
+        d = {"terminal": {"cwd": "/srv/app"}}
+        assert _resolve_cwd(tc, d, env) == "/srv/app"
+
+    def test_auto_placeholder_popped(self):
+        env = {}
+        tc = {"cwd": "auto", "env_type": "modal"}
+        d = {"terminal": {"cwd": "auto"}}
+        assert _resolve_cwd(tc, d, env) == ""
+
+
+class TestGatewayLazyImport:
+    """Gateway lazy import of cli.py must not clobber TERMINAL_CWD."""
+
+    def test_gateway_cwd_preserved(self):
+        env = {"_HERMES_GATEWAY": "1", "TERMINAL_CWD": "/home/user/project"}
+        tc = {"cwd": "/home/user", "env_type": "local"}
+        d = {"terminal": {"cwd": "/home/user"}}
+        result = _resolve_cwd(tc, d, env)
+        assert result == "/home/user/project"
+
+    def test_cli_overwrites_stale_env(self):
+        env = {"TERMINAL_CWD": "/stale/from/dotenv"}
+        tc = {"cwd": "/home/user", "env_type": "local"}
+        d = {"terminal": {"cwd": "/home/user"}}
+        result = _resolve_cwd(tc, d, env)
         assert result == "/fake/getcwd"
-
-    def test_remote_backend_pops_cwd(self):
-        """Remote backend + placeholder cwd → popped for backend default."""
-        env = {}
-        terminal_config = {"cwd": ".", "env_type": "docker"}
-        defaults = {"terminal": {"cwd": "."}, "_file_has_terminal": False}
-
-        result = _resolve_terminal_cwd(terminal_config, defaults, env)
-        assert result == ""  # cwd popped, no env var set
-
-    def test_remote_backend_with_prior_cwd_preserves(self):
-        """Remote backend + pre-resolved TERMINAL_CWD → adopted."""
-        env = {"TERMINAL_CWD": "/project"}
-        terminal_config = {"cwd": ".", "env_type": "docker"}
-        defaults = {"terminal": {"cwd": "."}, "_file_has_terminal": False}
-
-        result = _resolve_terminal_cwd(terminal_config, defaults, env)
-        assert result == "/project"

tests/cli/test_fast_command.py

@@ -128,17 +128,34 @@ class TestPriorityProcessingModels(unittest.TestCase):
             assert model_supports_fast_mode(model), f"{model} should support fast mode"
 
     def test_all_anthropic_models_supported(self):
+        """Per Anthropic docs, fast mode is currently Opus 4.6 only.
+
+        Sending speed=fast to Opus 4.7, Sonnet, or Haiku returns HTTP 400.
+        Pre-fix this test asserted all Claude variants supported fast mode,
+        which mirrored the bug rather than the API contract.
+        """
         from hermes_cli.models import model_supports_fast_mode
 
-        # All Claude models support Anthropic Fast Mode — Opus, Sonnet, Haiku.
+        # Supported: Opus 4.6 in any form
         supported = [
-            "claude-opus-4-7", "claude-opus-4-6", "claude-opus-4.6",
-            "claude-sonnet-4-6", "claude-sonnet-4.6", "claude-sonnet-4",
-            "claude-haiku-4-5", "claude-3-5-haiku",
+            "claude-opus-4-6", "claude-opus-4.6",
+            "anthropic/claude-opus-4-6", "anthropic/claude-opus-4.6",
         ]
         for model in supported:
             assert model_supports_fast_mode(model), f"{model} should support fast mode"
 
+        # Unsupported per Anthropic API: Opus 4.7, Sonnet, Haiku
+        unsupported = [
+            "claude-opus-4-7",
+            "claude-sonnet-4-6", "claude-sonnet-4.6", "claude-sonnet-4",
+            "claude-haiku-4-5", "claude-3-5-haiku",
+        ]
+        for model in unsupported:
+            assert not model_supports_fast_mode(model), (
+                f"{model} should NOT support fast mode — Anthropic restricts "
+                f"speed=fast to Opus 4.6"
+            )
+
     def test_codex_models_excluded(self):
         """Codex models route through Responses API and don't accept service_tier."""
         from hermes_cli.models import model_supports_fast_mode
@@ -257,18 +274,20 @@ class TestAnthropicFastMode(unittest.TestCase):
         assert model_supports_fast_mode("anthropic/claude-opus-4-6") is True
         assert model_supports_fast_mode("anthropic/claude-opus-4.6") is True
 
-    def test_anthropic_all_claude_models_supported(self):
+    def test_anthropic_non_opus46_models_excluded(self):
+        """Anthropic restricts fast mode to Opus 4.6 — others must be excluded.
+
+        Per https://platform.claude.com/docs/en/build-with-claude/fast-mode,
+        sending speed=fast to Opus 4.7, Sonnet, or Haiku returns HTTP 400.
+        """
         from hermes_cli.models import model_supports_fast_mode
 
-        # All Claude models support fast mode — Opus, Sonnet, Haiku.
-        # The anthropic adapter gates speed=fast on native Anthropic
-        # endpoints only, so third-party proxies that reject the beta
-        # are protected downstream (see _is_third_party_anthropic_endpoint).
-        assert model_supports_fast_mode("claude-sonnet-4-6") is True
-        assert model_supports_fast_mode("claude-sonnet-4.6") is True
-        assert model_supports_fast_mode("claude-haiku-4-5") is True
-        assert model_supports_fast_mode("claude-opus-4-7") is True
-        assert model_supports_fast_mode("anthropic/claude-sonnet-4.6") is True
+        assert model_supports_fast_mode("claude-sonnet-4-6") is False
+        assert model_supports_fast_mode("claude-sonnet-4.6") is False
+        assert model_supports_fast_mode("claude-haiku-4-5") is False
+        assert model_supports_fast_mode("claude-opus-4-7") is False
+        assert model_supports_fast_mode("anthropic/claude-sonnet-4.6") is False
+        assert model_supports_fast_mode("anthropic/claude-opus-4-7") is False
 
     def test_non_claude_models_not_anthropic_fast(self):
         """Non-Claude models should not be treated as Anthropic fast-mode."""
@@ -294,6 +313,17 @@ class TestAnthropicFastMode(unittest.TestCase):
         result = resolve_fast_mode_overrides("anthropic/claude-opus-4.6")
         assert result == {"speed": "fast"}
 
+    def test_resolve_overrides_returns_none_for_unsupported_claude(self):
+        """Opus 4.7 and other Claude models don't support fast mode (API 400s).
+
+        Per Anthropic docs, fast mode is currently Opus 4.6 only.
+        """
+        from hermes_cli.models import resolve_fast_mode_overrides
+
+        assert resolve_fast_mode_overrides("claude-opus-4-7") is None
+        assert resolve_fast_mode_overrides("claude-sonnet-4-6") is None
+        assert resolve_fast_mode_overrides("claude-haiku-4-5") is None
+
     def test_resolve_overrides_returns_service_tier_for_openai(self):
         """OpenAI models should still get service_tier, not speed."""
         from hermes_cli.models import resolve_fast_mode_overrides
@@ -302,13 +332,21 @@ class TestAnthropicFastMode(unittest.TestCase):
         assert result == {"service_tier": "priority"}
 
     def test_is_anthropic_fast_model(self):
+        """Fast mode is currently Opus 4.6 only — other Claude variants must be excluded."""
         from hermes_cli.models import _is_anthropic_fast_model
 
+        # Supported: Opus 4.6 in any form
         assert _is_anthropic_fast_model("claude-opus-4-6") is True
         assert _is_anthropic_fast_model("claude-opus-4.6") is True
-        assert _is_anthropic_fast_model("claude-sonnet-4-6") is True
-        assert _is_anthropic_fast_model("claude-haiku-4-5") is True
         assert _is_anthropic_fast_model("anthropic/claude-opus-4-6") is True
+        assert _is_anthropic_fast_model("claude-opus-4.6:fast") is True
+
+        # Unsupported per Anthropic API contract — would 400 if we sent speed=fast
+        assert _is_anthropic_fast_model("claude-opus-4-7") is False
+        assert _is_anthropic_fast_model("claude-sonnet-4-6") is False
+        assert _is_anthropic_fast_model("claude-haiku-4-5") is False
+
+        # Non-Claude
         assert _is_anthropic_fast_model("gpt-5.4") is False
         assert _is_anthropic_fast_model("") is False
 
@@ -320,14 +358,23 @@ class TestAnthropicFastMode(unittest.TestCase):
         )
         assert cli_mod.HermesCLI._fast_command_available(stub) is True
 
-    def test_fast_command_exposed_for_anthropic_sonnet(self):
-        """Sonnet now supports Anthropic Fast Mode — the adapter gates on base_url."""
+    def test_fast_command_hidden_for_anthropic_sonnet(self):
+        """Sonnet doesn't support fast mode (Opus 4.6 only) — /fast must be hidden."""
         cli_mod = _import_cli()
         stub = SimpleNamespace(
             provider="anthropic", requested_provider="anthropic",
             model="claude-sonnet-4-6", agent=None,
         )
-        assert cli_mod.HermesCLI._fast_command_available(stub) is True
+        assert cli_mod.HermesCLI._fast_command_available(stub) is False
+
+    def test_fast_command_hidden_for_anthropic_opus_47(self):
+        """Opus 4.7 doesn't support fast mode — /fast must be hidden."""
+        cli_mod = _import_cli()
+        stub = SimpleNamespace(
+            provider="anthropic", requested_provider="anthropic",
+            model="claude-opus-4-7", agent=None,
+        )
+        assert cli_mod.HermesCLI._fast_command_available(stub) is False
 
     def test_fast_command_hidden_for_non_claude_non_openai(self):
         """Non-Claude, non-OpenAI models should not expose /fast."""

tests/cron/test_jobs.py

@@ -647,6 +647,74 @@ class TestGetDueJobs:
         assert get_due_jobs() == []
         assert get_job("oneshot-stale")["next_run_at"] is None
 
+    def test_broken_cron_without_next_run_is_recovered(self, tmp_cron_dir, monkeypatch):
+        now = datetime(2026, 3, 18, 10, 0, 0, tzinfo=timezone.utc)
+        monkeypatch.setattr("cron.jobs._hermes_now", lambda: now)
+
+        save_jobs(
+            [{
+                "id": "cron-recover",
+                "name": "AI Daily Digest",
+                "prompt": "...",
+                "schedule": {"kind": "cron", "expr": "0 12 * * *", "display": "0 12 * * *"},
+                "schedule_display": "0 12 * * *",
+                "repeat": {"times": None, "completed": 0},
+                "enabled": True,
+                "state": "scheduled",
+                "paused_at": None,
+                "paused_reason": None,
+                "created_at": "2026-03-18T09:00:00+00:00",
+                "next_run_at": None,
+                "last_run_at": None,
+                "last_status": None,
+                "last_error": None,
+                "deliver": "local",
+                "origin": None,
+            }]
+        )
+
+        assert get_due_jobs() == []
+        recovered = get_job("cron-recover")["next_run_at"]
+        assert recovered is not None
+        recovered_dt = datetime.fromisoformat(recovered)
+        if recovered_dt.tzinfo is None:
+            recovered_dt = recovered_dt.replace(tzinfo=timezone.utc)
+        assert recovered_dt > now
+
+    def test_broken_interval_without_next_run_is_recovered(self, tmp_cron_dir, monkeypatch):
+        now = datetime(2026, 3, 18, 10, 0, 0, tzinfo=timezone.utc)
+        monkeypatch.setattr("cron.jobs._hermes_now", lambda: now)
+
+        save_jobs(
+            [{
+                "id": "interval-recover",
+                "name": "Hourly heartbeat",
+                "prompt": "...",
+                "schedule": {"kind": "interval", "minutes": 60, "display": "every 60m"},
+                "schedule_display": "every 1h",
+                "repeat": {"times": None, "completed": 0},
+                "enabled": True,
+                "state": "scheduled",
+                "paused_at": None,
+                "paused_reason": None,
+                "created_at": "2026-03-18T09:00:00+00:00",
+                "next_run_at": None,
+                "last_run_at": None,
+                "last_status": None,
+                "last_error": None,
+                "deliver": "local",
+                "origin": None,
+            }]
+        )
+
+        assert get_due_jobs() == []
+        recovered = get_job("interval-recover")["next_run_at"]
+        assert recovered is not None
+        recovered_dt = datetime.fromisoformat(recovered)
+        if recovered_dt.tzinfo is None:
+            recovered_dt = recovered_dt.replace(tzinfo=timezone.utc)
+        assert recovered_dt > now
+
 
 class TestEnabledToolsets:
     def test_enabled_toolsets_stored(self, tmp_cron_dir):

tests/cron/test_scheduler.py

@@ -1857,6 +1857,54 @@ class TestBuildJobPromptMissingSkill:
         assert "go" in result
 
 
+class TestBuildJobPromptBumpUse:
+    """Verify that cron jobs bump skill usage counters so the curator sees them as active."""
+
+    def test_bump_use_called_for_loaded_skill(self):
+        """bump_use is called for each successfully loaded skill."""
+
+        def _skill_view(name: str) -> str:
+            return json.dumps({"success": True, "content": f"Content for {name}."})
+
+        with patch("tools.skills_tool.skill_view", side_effect=_skill_view), \
+             patch("tools.skill_usage.bump_use") as mock_bump:
+            _build_job_prompt({"skills": ["alpha", "beta"], "prompt": "go"})
+
+        assert mock_bump.call_count == 2
+        calls = [c[0][0] for c in mock_bump.call_args_list]
+        assert "alpha" in calls
+        assert "beta" in calls
+
+    def test_bump_use_not_called_for_missing_skill(self):
+        """bump_use is NOT called when a skill fails to load."""
+
+        def _missing_view(name: str) -> str:
+            return json.dumps({"success": False, "error": "not found"})
+
+        with patch("tools.skills_tool.skill_view", side_effect=_missing_view), \
+             patch("tools.skill_usage.bump_use") as mock_bump:
+            _build_job_prompt({"skills": ["ghost"], "prompt": "go"})
+
+        assert mock_bump.call_count == 0
+
+    def test_bump_failure_does_not_break_prompt(self, caplog):
+        """If bump_use raises, the prompt still builds — error is logged at DEBUG."""
+
+        def _skill_view(name: str) -> str:
+            return json.dumps({"success": True, "content": "Works."})
+
+        with patch("tools.skills_tool.skill_view", side_effect=_skill_view), \
+             patch("tools.skill_usage.bump_use", side_effect=RuntimeError("boom")), \
+             caplog.at_level(logging.DEBUG, logger="cron.scheduler"):
+            result = _build_job_prompt({"skills": ["good-skill"], "prompt": "go"})
+
+        # Prompt should still contain the skill content and original instruction
+        assert "Works." in result
+        assert "go" in result
+        # The error should be logged at DEBUG level, not crash
+        assert any("failed to bump" in r.message for r in caplog.records)
+
+
 class TestSendMediaViaAdapter:
     """Unit tests for _send_media_via_adapter — routes files to typed adapter methods."""
 

tests/e2e/test_platform_commands.py

@@ -138,6 +138,29 @@ class TestSlashCommands:
         response_text = send.call_args[1].get("content") or send.call_args[0][1]
         assert "compress" in response_text.lower() or "context" in response_text.lower()
 
+    @pytest.mark.asyncio
+    async def test_quick_command_alias_targets_builtin_command_with_args(
+        self, adapter, runner, platform
+    ):
+        """Alias targets with args must reach the built-in command handler."""
+        runner.config.quick_commands = {
+            "s": {"type": "alias", "target": "/status extra-arg"}
+        }
+        async def _handle_status(event):
+            assert event.get_command_args() == "extra-arg"
+            return "status via alias"
+
+        runner._handle_status_command = AsyncMock(side_effect=_handle_status)
+
+        send = await send_and_capture(adapter, "/s", platform)
+
+        send.assert_called_once()
+        response_text = send.call_args[1].get("content") or send.call_args[0][1]
+        assert response_text == "status via alias"
+        runner._handle_status_command.assert_awaited_once()
+        runner._handle_message_with_agent.assert_not_awaited()
+
+
 
 class TestSessionLifecycle:
     """Verify session state changes across command sequences."""

tests/gateway/test_api_server.py

@@ -240,6 +240,48 @@ class TestAdapterInit:
             "http://127.0.0.1:3000",
         )
 
+    def test_invalid_port_from_env_falls_back_to_default(self, monkeypatch):
+        monkeypatch.setenv("API_SERVER_PORT", "not-a-port")
+        config = PlatformConfig(enabled=True)
+        adapter = APIServerAdapter(config)
+        assert adapter._port == 8642
+
+    def test_create_agent_forwards_config_reasoning_effort(self, monkeypatch):
+        captured = {}
+
+        class FakeAgent:
+            def __init__(self, **kwargs):
+                captured.update(kwargs)
+
+        monkeypatch.setattr("run_agent.AIAgent", FakeAgent)
+        monkeypatch.setattr(
+            "gateway.run._resolve_runtime_agent_kwargs",
+            lambda: {
+                "provider": "openai-codex",
+                "base_url": "https://example.test/v1",
+                "api_mode": "codex_responses",
+            },
+        )
+        monkeypatch.setattr("gateway.run._resolve_gateway_model", lambda: "gpt-5.5")
+        monkeypatch.setattr(
+            "gateway.run._load_gateway_config",
+            lambda: {"agent": {"reasoning_effort": "xhigh"}},
+        )
+        monkeypatch.setattr(
+            "gateway.run.GatewayRunner._load_reasoning_config",
+            staticmethod(lambda: {"enabled": True, "effort": "xhigh"}),
+        )
+        monkeypatch.setattr("gateway.run.GatewayRunner._load_fallback_model", staticmethod(lambda: None))
+        monkeypatch.setattr("hermes_cli.tools_config._get_platform_tools", lambda *_: set())
+
+        adapter = APIServerAdapter(PlatformConfig(enabled=True))
+        monkeypatch.setattr(adapter, "_ensure_session_db", lambda: None)
+
+        agent = adapter._create_agent(session_id="api-session")
+
+        assert isinstance(agent, FakeAgent)
+        assert captured["reasoning_config"] == {"enabled": True, "effort": "xhigh"}
+
 
 # ---------------------------------------------------------------------------
 # Auth checking

tests/gateway/test_gateway_command_help.py

@@ -0,0 +1,78 @@
+"""Gateway command help rendering tests."""
+
+import pytest
+
+from gateway.config import Platform
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionSource
+
+
+def _make_event(text: str, platform: Platform) -> MessageEvent:
+    return MessageEvent(
+        text=text,
+        source=SessionSource(
+            platform=platform,
+            chat_id="chat-1",
+            user_id="user-1",
+            user_name="tester",
+            chat_type="dm",
+        ),
+    )
+
+
+def _make_runner():
+    from gateway.run import GatewayRunner
+
+    return object.__new__(GatewayRunner)
+
+
+@pytest.mark.asyncio
+async def test_help_sanitizes_slash_command_mentions_for_telegram(monkeypatch):
+    """Telegram help output must not expose invalid uppercase/hyphenated slashes."""
+    monkeypatch.setattr(
+        "agent.skill_commands.get_skill_commands",
+        lambda: {
+            "/Linear": {"description": "Open Linear"},
+            "/Custom-Thing": {"description": "Run a custom thing"},
+        },
+    )
+
+    result = await _make_runner()._handle_help_command(
+        _make_event("/help", Platform.TELEGRAM)
+    )
+
+    assert "`/linear`" in result
+    assert "`/custom_thing`" in result
+    assert "`/Linear`" not in result
+    assert "`/Custom-Thing`" not in result
+
+
+@pytest.mark.asyncio
+async def test_commands_sanitizes_slash_command_mentions_for_telegram(monkeypatch):
+    """Paginated Telegram /commands output uses Telegram-valid slash mentions."""
+    monkeypatch.setattr(
+        "agent.skill_commands.get_skill_commands",
+        lambda: {"/Linear": {"description": "Open Linear"}},
+    )
+
+    result = await _make_runner()._handle_commands_command(
+        _make_event("/commands 999", Platform.TELEGRAM)
+    )
+
+    assert "`/linear`" in result
+    assert "`/Linear`" not in result
+
+
+@pytest.mark.asyncio
+async def test_help_keeps_non_telegram_slash_command_mentions_unchanged(monkeypatch):
+    """Only Telegram needs slash mentions rewritten to Telegram command names."""
+    monkeypatch.setattr(
+        "agent.skill_commands.get_skill_commands",
+        lambda: {"/Linear": {"description": "Open Linear"}},
+    )
+
+    result = await _make_runner()._handle_help_command(
+        _make_event("/help", Platform.DISCORD)
+    )
+
+    assert "`/Linear`" in result

tests/gateway/test_qqbot.py

@@ -191,6 +191,50 @@ class TestVoiceAttachmentSSRFProtection:
         assert kwargs.get("follow_redirects") is True
         assert kwargs.get("event_hooks", {}).get("response") == [_ssrf_redirect_guard]
 
+
+# ---------------------------------------------------------------------------
+# WebSocket proxy handling
+# ---------------------------------------------------------------------------
+
+class TestQQWebSocketProxy:
+    @pytest.mark.asyncio
+    async def test_open_ws_honors_proxy_env(self, monkeypatch):
+        from gateway.platforms.qqbot import QQAdapter
+
+        for key in (
+            "WSS_PROXY",
+            "wss_proxy",
+            "HTTPS_PROXY",
+            "https_proxy",
+            "ALL_PROXY",
+            "all_proxy",
+        ):
+            monkeypatch.delenv(key, raising=False)
+        monkeypatch.setenv("HTTPS_PROXY", "http://127.0.0.1:7897")
+
+        adapter = QQAdapter(_make_config(app_id="a", client_secret="b"))
+
+        seen_session_kwargs = {}
+        seen_ws_kwargs = {}
+
+        class FakeSession:
+            def __init__(self, **kwargs):
+                seen_session_kwargs.update(kwargs)
+                self.closed = False
+
+            async def close(self):
+                self.closed = True
+
+            async def ws_connect(self, *args, **kwargs):
+                seen_ws_kwargs.update(kwargs)
+                return mock.AsyncMock(closed=False)
+
+        with mock.patch("gateway.platforms.qqbot.adapter.aiohttp.ClientSession", side_effect=FakeSession):
+            await adapter._open_ws("wss://api.sgroup.qq.com/websocket")
+
+        assert seen_session_kwargs.get("trust_env") is True
+        assert seen_ws_kwargs.get("proxy") == "http://127.0.0.1:7897"
+
 # ---------------------------------------------------------------------------
 # _strip_at_mention
 # ---------------------------------------------------------------------------

tests/gateway/test_session_boundary_security_state.py

@@ -124,6 +124,10 @@ 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"
 
+    runner._pending_skills_reload_notes = {
+        session_key: "[USER INITIATED SKILLS RELOAD: target]",
+        other_key: "[USER INITIATED SKILLS RELOAD: other]",
+    }
     approve_session(session_key, "recursive delete")
     approve_session(other_key, "recursive delete")
     enable_session_yolo(session_key)
@@ -140,10 +144,12 @@ async def test_resume_clears_session_scoped_approval_and_yolo_state():
     assert is_session_yolo_enabled(session_key) is False
     assert session_key not in runner._pending_approvals
     assert session_key not in runner._update_prompt_pending
+    assert session_key not in runner._pending_skills_reload_notes
     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
     assert other_key in runner._update_prompt_pending
+    assert other_key in runner._pending_skills_reload_notes
 
 
 @pytest.mark.asyncio
@@ -151,6 +157,10 @@ 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"
 
+    runner._pending_skills_reload_notes = {
+        session_key: "[USER INITIATED SKILLS RELOAD: target]",
+        other_key: "[USER INITIATED SKILLS RELOAD: other]",
+    }
     approve_session(session_key, "recursive delete")
     approve_session(other_key, "recursive delete")
     enable_session_yolo(session_key)
@@ -167,10 +177,12 @@ async def test_branch_clears_session_scoped_approval_and_yolo_state():
     assert is_session_yolo_enabled(session_key) is False
     assert session_key not in runner._pending_approvals
     assert session_key not in runner._update_prompt_pending
+    assert session_key not in runner._pending_skills_reload_notes
     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
     assert other_key in runner._update_prompt_pending
+    assert other_key in runner._pending_skills_reload_notes
 
 
 @pytest.mark.asyncio
@@ -216,6 +228,7 @@ def test_clear_session_boundary_security_state_is_scoped():
     runner = object.__new__(GatewayRunner)
     runner._pending_approvals = {}
     runner._update_prompt_pending = {}
+    runner._pending_skills_reload_notes = {}
 
     source = _make_source()
     session_key = build_session_key(source)
@@ -229,6 +242,12 @@ def test_clear_session_boundary_security_state_is_scoped():
     runner._pending_approvals[other_key] = {"command": "rm -rf /tmp/other"}
     runner._update_prompt_pending[session_key] = True
     runner._update_prompt_pending[other_key] = True
+    runner._pending_skills_reload_notes[session_key] = (
+        "[USER INITIATED SKILLS RELOAD: target]"
+    )
+    runner._pending_skills_reload_notes[other_key] = (
+        "[USER INITIATED SKILLS RELOAD: other]"
+    )
 
     runner._clear_session_boundary_security_state(session_key)
 
@@ -237,16 +256,19 @@ def test_clear_session_boundary_security_state_is_scoped():
     assert is_session_yolo_enabled(session_key) is False
     assert session_key not in runner._pending_approvals
     assert session_key not in runner._update_prompt_pending
+    assert session_key not in runner._pending_skills_reload_notes
     # 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
     assert other_key in runner._update_prompt_pending
+    assert other_key in runner._pending_skills_reload_notes
 
     # Empty session_key is a no-op
     runner._clear_session_boundary_security_state("")
     assert is_approved(other_key, "recursive delete") is True
     assert other_key in runner._update_prompt_pending
+    assert other_key in runner._pending_skills_reload_notes
 
 
 def test_clear_session_boundary_security_state_wakes_blocked_approvals():

tests/gateway/test_sms.py

@@ -169,9 +169,9 @@ class TestSmsRequirements:
 class TestWebhookHostConfig:
     """Verify SMS_WEBHOOK_HOST env var and default."""
 
-    def test_default_host_is_all_interfaces(self):
+    def test_default_host_is_localhost(self):
         from gateway.platforms.sms import DEFAULT_WEBHOOK_HOST
-        assert DEFAULT_WEBHOOK_HOST == "0.0.0.0"
+        assert DEFAULT_WEBHOOK_HOST == "127.0.0.1"
 
     def test_host_from_env(self):
         from gateway.platforms.sms import SmsAdapter
@@ -242,6 +242,48 @@ class TestStartupGuard:
         result = await adapter.connect()
         assert result is False
 
+    @pytest.mark.asyncio
+    async def test_missing_webhook_url_is_non_retryable(self):
+        adapter = self._make_adapter()
+        await adapter.connect()
+        assert adapter.has_fatal_error is True
+        assert adapter.fatal_error_retryable is False
+        assert "sms_missing_webhook_url" == adapter.fatal_error_code
+
+    @pytest.mark.asyncio
+    async def test_missing_phone_number_is_non_retryable(self):
+        from gateway.platforms.sms import SmsAdapter
+
+        env = {
+            "TWILIO_ACCOUNT_SID": "ACtest",
+            "TWILIO_AUTH_TOKEN": "tok",
+            "TWILIO_PHONE_NUMBER": "",
+            "SMS_WEBHOOK_URL": "",
+        }
+        with patch.dict(os.environ, env, clear=True):
+            pc = PlatformConfig(enabled=True, api_key="tok")
+            adapter = SmsAdapter(pc)
+        await adapter.connect()
+        assert adapter.has_fatal_error is True
+        assert adapter.fatal_error_retryable is False
+        assert adapter.fatal_error_code == "sms_missing_phone_number"
+
+    @pytest.mark.asyncio
+    async def test_insecure_flag_does_not_set_fatal_error(self):
+        mock_session = AsyncMock()
+        with patch.dict(os.environ, {"SMS_INSECURE_NO_SIGNATURE": "true"}), \
+             patch("aiohttp.web.AppRunner") as mock_runner_cls, \
+             patch("aiohttp.web.TCPSite") as mock_site_cls, \
+             patch("aiohttp.ClientSession", return_value=mock_session):
+            mock_runner_cls.return_value.setup = AsyncMock()
+            mock_runner_cls.return_value.cleanup = AsyncMock()
+            mock_site_cls.return_value.start = AsyncMock()
+            adapter = self._make_adapter()
+            result = await adapter.connect()
+            assert result is True
+            assert adapter.has_fatal_error is False
+            await adapter.disconnect()
+
     @pytest.mark.asyncio
     async def test_insecure_flag_allows_start_without_url(self):
         mock_session = AsyncMock()

tests/gateway/test_teams.py

@@ -313,9 +313,33 @@ class TestTeamsPluginRegistration:
 
 
 # ---------------------------------------------------------------------------
-# Tests: Connect / Disconnect
+# Tests: Interactive setup (import fix regression — #18325 / #19173)
 # ---------------------------------------------------------------------------
 
+class TestTeamsInteractiveSetup:
+    def test_interactive_setup_persists_credentials(self, tmp_path, monkeypatch):
+        """Regression for #19173: interactive_setup must import prompt helpers
+        from hermes_cli.cli_output (not hermes_cli.config) and persist
+        credentials to .env without crashing.
+        """
+        hermes_home = tmp_path / "hermes"
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+        import hermes_cli.cli_output as cli_output_mod
+
+        answers = iter(["client-id", "client-secret", "tenant-id", "aad-1, aad-2"])
+        monkeypatch.setattr(cli_output_mod, "prompt", lambda *_a, **_kw: next(answers))
+        monkeypatch.setattr(cli_output_mod, "prompt_yes_no", lambda *_a, **_kw: True)
+        monkeypatch.setattr(cli_output_mod, "print_info", lambda *_a, **_kw: None)
+        monkeypatch.setattr(cli_output_mod, "print_success", lambda *_a, **_kw: None)
+        monkeypatch.setattr(cli_output_mod, "print_warning", lambda *_a, **_kw: None)
+
+        _teams_mod.interactive_setup()
+
+        env_text = (hermes_home / ".env").read_text(encoding="utf-8")
+        assert "TEAMS_CLIENT_ID=client-id" in env_text
+        assert "TEAMS_TENANT_ID=tenant-id" in env_text
+
 class TestTeamsConnect:
     @pytest.mark.asyncio
     async def test_connect_fails_without_sdk(self, monkeypatch):

tests/gateway/test_telegram_group_gating.py

@@ -261,6 +261,57 @@ def test_group_allow_from_is_enforced_by_gateway_authorization_not_trigger_gate(
     assert adapter._should_process_message(_group_message("hello", from_user_id=333)) is True
 
 
+def test_top_level_require_mention_bridges_to_telegram(monkeypatch, tmp_path):
+    """require_mention at the config.yaml top level (alongside group_sessions_per_user)
+    must behave identically to telegram.require_mention: true (#3979).
+    """
+    hermes_home = tmp_path / ".hermes"
+    hermes_home.mkdir()
+    # Intentionally no "telegram:" section — keys are at the top level.
+    (hermes_home / "config.yaml").write_text(
+        "require_mention: true\n"
+        "group_sessions_per_user: true\n",
+        encoding="utf-8",
+    )
+
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+    monkeypatch.delenv("TELEGRAM_REQUIRE_MENTION", raising=False)
+
+    config = load_gateway_config()
+
+    assert config is not None
+    assert __import__("os").environ.get("TELEGRAM_REQUIRE_MENTION") == "true"
+
+    # The adapter's extra dict must also carry the setting so that
+    # _telegram_require_mention() works even without the env var.
+    tg_cfg = config.platforms.get(__import__("gateway.config", fromlist=["Platform"]).Platform.TELEGRAM)
+    if tg_cfg is not None:
+        assert tg_cfg.extra.get("require_mention") is True
+
+
+def test_top_level_require_mention_does_not_override_telegram_section(monkeypatch, tmp_path):
+    """When telegram.require_mention is explicitly set, top-level require_mention
+    must not override it (platform-specific config takes precedence).
+    """
+    hermes_home = tmp_path / ".hermes"
+    hermes_home.mkdir()
+    (hermes_home / "config.yaml").write_text(
+        "require_mention: true\n"
+        "telegram:\n"
+        "  require_mention: false\n",
+        encoding="utf-8",
+    )
+
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+    monkeypatch.delenv("TELEGRAM_REQUIRE_MENTION", raising=False)
+
+    config = load_gateway_config()
+
+    assert config is not None
+    # The telegram-specific "false" must win over the top-level "true".
+    assert __import__("os").environ.get("TELEGRAM_REQUIRE_MENTION") == "false"
+
+
 def test_config_bridges_telegram_ignored_threads(monkeypatch, tmp_path):
     hermes_home = tmp_path / ".hermes"
     hermes_home.mkdir()

tests/gateway/test_title_command.py

@@ -5,11 +5,12 @@ across all gateway messenger platforms.
 """
 
 import os
-from unittest.mock import MagicMock, patch
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from gateway.config import Platform
+from gateway.config import GatewayConfig, Platform, PlatformConfig
 from gateway.platforms.base import MessageEvent
 from gateway.session import SessionSource
 
@@ -206,3 +207,152 @@ class TestTitleInHelp:
         import inspect
         source = inspect.getsource(GatewayRunner._handle_message)
         assert '"title"' in source
+
+
+# ---------------------------------------------------------------------------
+# /new with title
+# ---------------------------------------------------------------------------
+
+
+class TestResetCommandWithTitle:
+    """Tests for GatewayRunner._handle_reset_command with a title argument."""
+
+    @pytest.mark.asyncio
+    async def test_reset_command_with_title(self):
+        """Sending /new <title> resets session and sets the title."""
+        from datetime import datetime
+
+        from gateway.run import GatewayRunner
+        from gateway.session import SessionEntry, SessionSource, build_session_key
+
+        runner = object.__new__(GatewayRunner)
+        runner.config = GatewayConfig(
+            platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
+        )
+        adapter = MagicMock()
+        adapter.send = AsyncMock()
+        runner.adapters = {Platform.TELEGRAM: adapter}
+        runner._voice_mode = {}
+        runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
+        runner._session_model_overrides = {}
+        runner._pending_model_notes = {}
+        runner._background_tasks = set()
+
+        source = SessionSource(
+            platform=Platform.TELEGRAM,
+            user_id="12345",
+            chat_id="67890",
+            user_name="testuser",
+        )
+        session_key = build_session_key(source)
+        new_session_entry = SessionEntry(
+            session_key=session_key,
+            session_id="sess-new",
+            created_at=datetime.now(),
+            updated_at=datetime.now(),
+            platform=Platform.TELEGRAM,
+            chat_type="dm",
+        )
+        runner.session_store = MagicMock()
+        runner.session_store.get_or_create_session.return_value = new_session_entry
+        runner.session_store.reset_session.return_value = new_session_entry
+        runner.session_store._entries = {session_key: new_session_entry}
+        runner.session_store._generate_session_key.return_value = session_key
+        runner._running_agents = {}
+        runner._pending_messages = {}
+        runner._pending_approvals = {}
+        runner._session_db = MagicMock()
+        runner._agent_cache = {}
+        runner._agent_cache_lock = None
+        runner._is_user_authorized = lambda _source: True
+        runner._format_session_info = lambda: ""
+
+        event = _make_event(text="/new Custom Name")
+        result = await runner._handle_reset_command(event)
+
+        runner.session_store.reset_session.assert_called_once()
+        runner._session_db.set_session_title.assert_called_once_with(
+            "sess-new", "Custom Name"
+        )
+        # Header reflects the applied title
+        assert "Custom Name" in str(result)
+
+    @pytest.mark.asyncio
+    async def test_reset_command_duplicate_title_surfaces_warning(self):
+        """/new <title> with an already-in-use title returns a warning in the reply."""
+        from datetime import datetime
+
+        from gateway.run import GatewayRunner
+        from gateway.session import SessionEntry, SessionSource, build_session_key
+
+        runner = object.__new__(GatewayRunner)
+        runner.config = GatewayConfig(
+            platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
+        )
+        adapter = MagicMock()
+        adapter.send = AsyncMock()
+        runner.adapters = {Platform.TELEGRAM: adapter}
+        runner._voice_mode = {}
+        runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
+        runner._session_model_overrides = {}
+        runner._pending_model_notes = {}
+        runner._background_tasks = set()
+
+        source = SessionSource(
+            platform=Platform.TELEGRAM,
+            user_id="12345",
+            chat_id="67890",
+            user_name="testuser",
+        )
+        session_key = build_session_key(source)
+        new_session_entry = SessionEntry(
+            session_key=session_key,
+            session_id="sess-new",
+            created_at=datetime.now(),
+            updated_at=datetime.now(),
+            platform=Platform.TELEGRAM,
+            chat_type="dm",
+        )
+        runner.session_store = MagicMock()
+        runner.session_store.get_or_create_session.return_value = new_session_entry
+        runner.session_store.reset_session.return_value = new_session_entry
+        runner.session_store._entries = {session_key: new_session_entry}
+        runner.session_store._generate_session_key.return_value = session_key
+        runner._running_agents = {}
+        runner._pending_messages = {}
+        runner._pending_approvals = {}
+        runner._session_db = MagicMock()
+        runner._session_db.set_session_title.side_effect = ValueError(
+            "Title 'Dup' is already in use by session abc-123"
+        )
+        runner._agent_cache = {}
+        runner._agent_cache_lock = None
+        runner._is_user_authorized = lambda _source: True
+        runner._format_session_info = lambda: ""
+
+        event = _make_event(text="/new Dup")
+        result = await runner._handle_reset_command(event)
+
+        runner._session_db.set_session_title.assert_called_once()
+        reply = str(result)
+        assert "already in use" in reply
+        assert "session started untitled" in reply
+        # Header must NOT claim the rejected title as the session name
+        assert "New session started: Dup" not in reply
+
+
+# ---------------------------------------------------------------------------
+# /new in help output
+# ---------------------------------------------------------------------------
+
+
+class TestNewInHelp:
+    """Verify /new appears in help text with the [name] args hint."""
+
+    def test_new_command_in_help_output(self):
+        """The gateway help output includes /new with the [name] hint."""
+        from hermes_cli.commands import gateway_help_lines
+        lines = gateway_help_lines()
+        new_line = next((line for line in lines if line.startswith("`/new ")), None)
+        assert new_line is not None
+        assert "[name]" in new_line

tests/gateway/test_voice_command.py

@@ -954,6 +954,46 @@ class TestVoiceChannelCommands:
         assert "Test transcript" in msg
         assert "42" in msg  # user_id in mention
 
+    @pytest.mark.asyncio
+    async def test_input_suppresses_duplicate_transcript(self, runner):
+        """Near-immediate duplicate STT output should not dispatch twice."""
+        from gateway.config import Platform
+
+        mock_adapter = AsyncMock()
+        mock_adapter._voice_text_channels = {111: 123}
+        mock_adapter._voice_sources = {}
+        mock_channel = AsyncMock()
+        mock_adapter._client = MagicMock()
+        mock_adapter._client.get_channel = MagicMock(return_value=mock_channel)
+        mock_adapter.handle_message = AsyncMock()
+        runner.adapters[Platform.DISCORD] = mock_adapter
+
+        await runner._handle_voice_channel_input(111, 42, "Hello from VC")
+        await runner._handle_voice_channel_input(111, 42, "Hello from VC")
+
+        mock_adapter.handle_message.assert_called_once()
+        mock_channel.send.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_input_suppresses_near_duplicate_transcript(self, runner):
+        """Small STT wording drift should still be treated as the same utterance."""
+        from gateway.config import Platform
+
+        mock_adapter = AsyncMock()
+        mock_adapter._voice_text_channels = {111: 123}
+        mock_adapter._voice_sources = {}
+        mock_channel = AsyncMock()
+        mock_adapter._client = MagicMock()
+        mock_adapter._client.get_channel = MagicMock(return_value=mock_channel)
+        mock_adapter.handle_message = AsyncMock()
+        runner.adapters[Platform.DISCORD] = mock_adapter
+
+        await runner._handle_voice_channel_input(111, 42, "This is a test of the voice system")
+        await runner._handle_voice_channel_input(111, 42, "This is a test for the voice system")
+
+        mock_adapter.handle_message.assert_called_once()
+        mock_channel.send.assert_called_once()
+
     # -- _get_guild_id --
 
     def test_get_guild_id_from_guild(self, runner):

tests/gateway/test_wecom.py

@@ -36,6 +36,11 @@ class TestWeComRequirements:
 
 
 class TestWeComAdapterInit:
+    def test_declares_non_editable_message_capability(self):
+        from gateway.platforms.wecom import WeComAdapter
+
+        assert WeComAdapter.SUPPORTS_MESSAGE_EDITING is False
+
     def test_reads_config_from_extra(self):
         from gateway.platforms.wecom import WeComAdapter
 

tests/gateway/test_weixin.py

@@ -5,7 +5,7 @@ import base64
 import json
 import os
 from pathlib import Path
-from unittest.mock import AsyncMock, patch
+from unittest.mock import AsyncMock, Mock, patch
 
 from gateway.config import PlatformConfig
 from gateway.config import GatewayConfig, HomeChannel, Platform, _apply_env_overrides
@@ -788,3 +788,43 @@ class TestIsStaleSessionRet:
     def test_success_codes_are_not_stale(self):
         assert weixin._is_stale_session_ret(0, 0, "") is False
         assert weixin._is_stale_session_ret(None, None, "unknown error") is False
+
+
+class TestWeixinContentDedup:
+    """Regression tests for Issue #16182 — upstream API sends duplicate content
+    with different message_ids, bypassing message_id deduplication.
+    """
+
+    def test_duplicate_content_with_different_message_ids_is_dropped(self):
+        adapter = _make_adapter()
+        adapter._poll_session = object()
+        adapter.handle_message = AsyncMock()
+
+        base_msg = {
+            "from_user_id": "wxid_user1",
+            "item_list": [{"type": 1, "text_item": {"text": "hello world"}}],
+        }
+
+        asyncio.run(adapter._process_message({**base_msg, "message_id": "msg-1"}))
+        asyncio.run(adapter._process_message({**base_msg, "message_id": "msg-2"}))
+
+        assert adapter.handle_message.await_count == 1
+        event = adapter.handle_message.await_args[0][0]
+        assert event.text == "hello world"
+
+    def test_content_dedup_not_called_for_messages_without_text(self):
+        adapter = _make_adapter()
+        adapter._poll_session = object()
+        adapter.handle_message = AsyncMock()
+        adapter._dedup.is_duplicate = Mock(return_value=False)
+
+        empty_msg = {
+            "from_user_id": "wxid_user1",
+            "message_id": "msg-1",
+            "item_list": [],
+        }
+        asyncio.run(adapter._process_message(empty_msg))
+
+        assert adapter.handle_message.await_count == 0
+        # is_duplicate should only be called for message_id, never for content
+        assert all("content:" not in str(call) for call in adapter._dedup.is_duplicate.call_args_list)

tests/hermes_cli/test_auth_nous_provider.py

@@ -896,3 +896,286 @@ def test_refresh_non_reuse_error_keeps_original_description():
     assert "Refresh session has been revoked" in str(exc_info.value)
     # Must not have been rewritten with the reuse message.
     assert "external process" not in str(exc_info.value).lower()
+
+
+# =============================================================================
+# Shared Nous token store — cross-profile persistence (Codex-style auto-import)
+# =============================================================================
+
+
+@pytest.fixture
+def shared_store_env(tmp_path, monkeypatch):
+    """Redirect HERMES_SHARED_AUTH_DIR to a tmp_path.
+
+    Required for every test that exercises the shared Nous store — the
+    in-auth.py seat belt refuses to touch the real user's shared store
+    under pytest, so tests that forget this fixture fail loudly instead
+    of corrupting real state.
+    """
+    shared_dir = tmp_path / "shared"
+    monkeypatch.setenv("HERMES_SHARED_AUTH_DIR", str(shared_dir))
+    return shared_dir
+
+
+def test_shared_store_seat_belt_refuses_real_home_under_pytest(monkeypatch):
+    """Without HERMES_SHARED_AUTH_DIR override, the seat belt must trip.
+
+    Mirrors the existing ``_auth_file_path`` seat belt: forgetting to
+    redirect this store in a test must fail loudly instead of silently
+    writing to the user's real ``~/.hermes/shared/`` across CI runs.
+    """
+    from hermes_cli.auth import _nous_shared_store_path
+
+    monkeypatch.delenv("HERMES_SHARED_AUTH_DIR", raising=False)
+
+    with pytest.raises(RuntimeError, match="shared Nous auth store"):
+        _nous_shared_store_path()
+
+
+def test_shared_store_honors_env_override(tmp_path, monkeypatch):
+    """HERMES_SHARED_AUTH_DIR must redirect the path."""
+    from hermes_cli.auth import _nous_shared_store_path, NOUS_SHARED_STORE_FILENAME
+
+    custom_dir = tmp_path / "custom_shared"
+    monkeypatch.setenv("HERMES_SHARED_AUTH_DIR", str(custom_dir))
+
+    path = _nous_shared_store_path()
+    assert path == custom_dir / NOUS_SHARED_STORE_FILENAME
+
+
+def test_shared_store_read_missing_returns_none(shared_store_env):
+    """Missing file → ``_read_shared_nous_state()`` returns None."""
+    from hermes_cli.auth import _read_shared_nous_state
+
+    assert _read_shared_nous_state() is None
+
+
+def test_shared_store_read_malformed_returns_none(shared_store_env):
+    """Unreadable / non-JSON file → None, not an exception."""
+    from hermes_cli.auth import _nous_shared_store_path, _read_shared_nous_state
+
+    path = _nous_shared_store_path()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text("{ not json")
+
+    assert _read_shared_nous_state() is None
+
+
+def test_shared_store_read_missing_required_fields_returns_none(shared_store_env):
+    """Payload without refresh_token → None (nothing worth importing)."""
+    from hermes_cli.auth import _nous_shared_store_path, _read_shared_nous_state
+
+    path = _nous_shared_store_path()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps({"_schema": 1, "access_token": "abc"}))
+
+    assert _read_shared_nous_state() is None
+
+
+def test_shared_store_write_and_read_roundtrip(shared_store_env):
+    """Write → read must preserve refresh_token + OAuth URLs."""
+    from hermes_cli.auth import (
+        _nous_shared_store_path,
+        _read_shared_nous_state,
+        _write_shared_nous_state,
+    )
+
+    _write_shared_nous_state(_full_state_fixture())
+
+    path = _nous_shared_store_path()
+    assert path.is_file()
+
+    # Permissions should be 0600 where the platform supports it.
+    mode = path.stat().st_mode & 0o777
+    assert mode == 0o600 or mode == 0o644  # 0o644 on platforms without chmod
+
+    loaded = _read_shared_nous_state()
+    assert loaded is not None
+    assert loaded["refresh_token"] == "refresh-tok"
+    assert loaded["access_token"] == "access-tok"
+    assert loaded["portal_base_url"] == "https://portal.example.com"
+    assert loaded["inference_base_url"] == "https://inference.example.com/v1"
+    # Volatile agent_key MUST NOT be persisted to the shared store
+    # (24h TTL, profile-specific — only long-lived OAuth tokens are
+    # cross-profile useful).
+    assert "agent_key" not in loaded
+
+
+def test_shared_store_write_skips_when_refresh_token_missing(shared_store_env):
+    """Write is a no-op when refresh_token is absent (nothing to share)."""
+    from hermes_cli.auth import _nous_shared_store_path, _write_shared_nous_state
+
+    state = dict(_full_state_fixture())
+    state["refresh_token"] = ""
+
+    _write_shared_nous_state(state)
+
+    assert not _nous_shared_store_path().is_file()
+
+
+def test_persist_nous_credentials_mirrors_to_shared_store(
+    tmp_path, monkeypatch, shared_store_env,
+):
+    """persist_nous_credentials must populate BOTH per-profile auth.json
+    AND the shared store, so a future profile's `hermes auth add nous
+    --type oauth` can one-tap import instead of redoing device-code.
+    """
+    from hermes_cli.auth import (
+        _nous_shared_store_path,
+        _read_shared_nous_state,
+        persist_nous_credentials,
+    )
+
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    (hermes_home / "auth.json").write_text(
+        json.dumps({"version": 1, "providers": {}})
+    )
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    persist_nous_credentials(_full_state_fixture())
+
+    # Per-profile auth.json populated
+    payload = json.loads((hermes_home / "auth.json").read_text())
+    assert "nous" in payload.get("providers", {})
+
+    # Shared store populated with the same refresh_token
+    shared = _read_shared_nous_state()
+    assert shared is not None
+    assert shared["refresh_token"] == "refresh-tok"
+
+    # Shared file path lives under the tmp override, NOT the real home
+    assert str(_nous_shared_store_path()).startswith(str(shared_store_env))
+
+
+def test_try_import_shared_returns_none_when_store_missing(shared_store_env):
+    """No shared store → no rehydrate (fall through to device-code)."""
+    from hermes_cli.auth import _try_import_shared_nous_state
+
+    assert _try_import_shared_nous_state() is None
+
+
+def test_try_import_shared_returns_none_on_refresh_failure(
+    shared_store_env, monkeypatch,
+):
+    """If the portal rejects the stored refresh_token (revoked, expired,
+    portal down), _try_import_shared_nous_state must return None so the
+    login flow falls back to a fresh device-code run.
+    """
+    from hermes_cli import auth as auth_mod
+
+    # Seed the shared store
+    auth_mod._write_shared_nous_state(_full_state_fixture())
+
+    # Make refresh fail
+    def _boom(*_args, **_kwargs):
+        raise AuthError(
+            "Refresh session has been revoked",
+            provider="nous",
+            code="invalid_grant",
+            relogin_required=True,
+        )
+
+    monkeypatch.setattr(auth_mod, "refresh_nous_oauth_from_state", _boom)
+
+    assert auth_mod._try_import_shared_nous_state() is None
+
+
+def test_try_import_shared_rehydrates_on_success(shared_store_env, monkeypatch):
+    """Happy path: stored refresh_token is accepted, forced refresh+mint
+    returns a fresh access_token + agent_key, and the returned dict has
+    every field persist_nous_credentials() needs.
+    """
+    from hermes_cli import auth as auth_mod
+
+    auth_mod._write_shared_nous_state(_full_state_fixture())
+
+    def _fake_refresh(state, **kwargs):
+        # Simulate portal returning fresh tokens + a new agent_key
+        assert kwargs.get("force_refresh") is True
+        assert kwargs.get("force_mint") is True
+        return {
+            **state,
+            "access_token": "fresh-access-tok",
+            "refresh_token": "fresh-refresh-tok",  # rotated
+            "agent_key": "new-agent-key",
+            "agent_key_expires_at": "2026-04-19T22:00:00+00:00",
+        }
+
+    monkeypatch.setattr(auth_mod, "refresh_nous_oauth_from_state", _fake_refresh)
+
+    result = auth_mod._try_import_shared_nous_state()
+
+    assert result is not None
+    assert result["access_token"] == "fresh-access-tok"
+    assert result["refresh_token"] == "fresh-refresh-tok"
+    assert result["agent_key"] == "new-agent-key"
+    # Preserved from shared state
+    assert result["portal_base_url"] == "https://portal.example.com"
+    assert result["client_id"] == "hermes-cli"
+
+
+def test_shared_store_survives_across_profile_switch(
+    tmp_path, monkeypatch, shared_store_env,
+):
+    """End-to-end: profile A logs in → shared store populated → profile B
+    (different HERMES_HOME) sees the same shared state and can rehydrate
+    without re-running device-code.
+    """
+    from hermes_cli import auth as auth_mod
+
+    # Profile A: login, which mirrors to shared store
+    profile_a = tmp_path / "profile_a"
+    profile_a.mkdir(parents=True, exist_ok=True)
+    (profile_a / "auth.json").write_text(
+        json.dumps({"version": 1, "providers": {}})
+    )
+    monkeypatch.setenv("HERMES_HOME", str(profile_a))
+    auth_mod.persist_nous_credentials(_full_state_fixture())
+
+    # Profile A's auth.json has nous
+    a_payload = json.loads((profile_a / "auth.json").read_text())
+    assert "nous" in a_payload.get("providers", {})
+
+    # Profile B: fresh HERMES_HOME, no auth yet, but the shared store
+    # persists — _read_shared_nous_state() must still return the tokens.
+    profile_b = tmp_path / "profile_b"
+    profile_b.mkdir(parents=True, exist_ok=True)
+    (profile_b / "auth.json").write_text(
+        json.dumps({"version": 1, "providers": {}})
+    )
+    monkeypatch.setenv("HERMES_HOME", str(profile_b))
+
+    # B's own auth.json has no nous
+    b_payload = json.loads((profile_b / "auth.json").read_text())
+    assert "nous" not in b_payload.get("providers", {})
+
+    # But the shared store is visible
+    shared = auth_mod._read_shared_nous_state()
+    assert shared is not None
+    assert shared["refresh_token"] == "refresh-tok"
+
+    # And a successful rehydrate + persist lands nous into profile B
+    def _fake_refresh(state, **kwargs):
+        return {
+            **state,
+            "access_token": "b-access-tok",
+            "refresh_token": "b-refresh-tok",
+            "agent_key": "b-agent-key",
+            "agent_key_expires_at": "2026-04-19T22:00:00+00:00",
+        }
+
+    monkeypatch.setattr(auth_mod, "refresh_nous_oauth_from_state", _fake_refresh)
+    result = auth_mod._try_import_shared_nous_state()
+    assert result is not None
+
+    auth_mod.persist_nous_credentials(result)
+
+    b_payload = json.loads((profile_b / "auth.json").read_text())
+    assert "nous" in b_payload.get("providers", {})
+    assert b_payload["providers"]["nous"]["refresh_token"] == "b-refresh-tok"
+
+    # Shared store was updated with the rotated refresh_token too
+    shared_after = auth_mod._read_shared_nous_state()
+    assert shared_after is not None
+    assert shared_after["refresh_token"] == "b-refresh-tok"

tests/hermes_cli/test_backup.py

@@ -471,6 +471,32 @@ class TestImport:
         with pytest.raises(SystemExit):
             run_import(args)
 
+    @pytest.mark.skipif(os.name != "posix", reason="POSIX file permissions only")
+    def test_restores_secret_files_with_0600_perms(self, tmp_path, monkeypatch):
+        """Secret files must end up at 0600 after restore (zipfile drops mode bits)."""
+        hermes_home = tmp_path / ".hermes"
+        hermes_home.mkdir()
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+        monkeypatch.setattr(Path, "home", lambda: tmp_path)
+
+        zip_path = tmp_path / "backup.zip"
+        self._make_backup_zip(zip_path, {
+            "config.yaml": "model: openrouter\n",
+            ".env": "OPENROUTER_API_KEY=sk-secret\n",
+            "auth.json": '{"providers": {"nous": "token"}}',
+            "state.db": b"SQLite format 3\x00",
+            "profiles/coder/.env": "ANTHROPIC_API_KEY=sk-ant-secret\n",
+        })
+
+        args = Namespace(zipfile=str(zip_path), force=True)
+
+        from hermes_cli.backup import run_import
+        run_import(args)
+
+        for rel in (".env", "auth.json", "state.db", "profiles/coder/.env"):
+            mode = (hermes_home / rel).stat().st_mode & 0o777
+            assert mode == 0o600, f"{rel} restored with mode {oct(mode)}, expected 0o600"
+
 
 # ---------------------------------------------------------------------------
 # Round-trip test
@@ -1348,6 +1374,53 @@ class TestPreUpdateBackup:
         from hermes_cli.backup import create_pre_update_backup
         assert create_pre_update_backup(hermes_home=tmp_path / "does-not-exist") is None
 
+    def test_keep_zero_does_not_delete_freshly_created_backup(self, hermes_home):
+        """Regression: ``backup_keep: 0`` previously triggered ``backups[0:]``
+        in the pruner — wiping the just-created zip and leaving the user
+        with no recovery point.  The floor (keep>=1) preserves the new file
+        regardless of misconfiguration; users who don't want backups should
+        set ``pre_update_backup: false`` instead.
+        """
+        from hermes_cli.backup import create_pre_update_backup
+        out = create_pre_update_backup(hermes_home=hermes_home, keep=0)
+        assert out is not None
+        assert out.exists(), (
+            "keep=0 silently deleted the freshly-created backup; floor "
+            "should preserve the just-written file."
+        )
+
+    def test_keep_negative_does_not_delete_freshly_created_backup(self, hermes_home):
+        """Mirror coverage: any value <1 should be floored, not literally
+        applied as a slice index."""
+        from hermes_cli.backup import create_pre_update_backup
+        out = create_pre_update_backup(hermes_home=hermes_home, keep=-3)
+        assert out is not None
+        assert out.exists()
+
+    def test_keep_zero_still_prunes_older_backups(self, hermes_home):
+        """The floor preserves the new backup but should NOT regress the
+        rotation behaviour for older zips: a third call with keep=0 must
+        still remove pre-existing backups beyond the (floored) limit of 1.
+        """
+        import time as _t
+        from hermes_cli.backup import create_pre_update_backup
+
+        first = create_pre_update_backup(hermes_home=hermes_home, keep=5)
+        _t.sleep(1.05)
+        second = create_pre_update_backup(hermes_home=hermes_home, keep=5)
+        _t.sleep(1.05)
+        third = create_pre_update_backup(hermes_home=hermes_home, keep=0)
+
+        remaining = {
+            p.name for p in (hermes_home / "backups").iterdir()
+            if p.name.startswith("pre-update-")
+        }
+        assert third.name in remaining, "Floor must preserve the new backup"
+        assert first.name not in remaining and second.name not in remaining, (
+            f"keep=0 floor of 1 should still prune older backups; "
+            f"remaining={remaining}"
+        )
+
 
 class TestRunPreUpdateBackup:
     """Tests for the ``_run_pre_update_backup`` wrapper in main.py —

tests/hermes_cli/test_commands.py

@@ -236,6 +236,13 @@ class TestTelegramBotCommands:
                 tg_name = cmd.name.replace("-", "_")
                 assert tg_name not in names
 
+    def test_excludes_commands_with_required_args(self):
+        names = {name for name, _ in telegram_bot_commands()}
+        assert "background" not in names
+        assert "queue" not in names
+        assert "steer" not in names
+        assert "background" in GATEWAY_KNOWN_COMMANDS
+
 
 class TestSlackSubcommandMap:
     def test_returns_dict(self):
@@ -1661,6 +1668,19 @@ class TestPluginCommandEnumeration:
         names = {name for name, _desc in telegram_bot_commands()}
         assert "metricas" in names
 
+    def test_plugin_command_with_required_args_excluded_from_telegram_menu(self, monkeypatch):
+        """Telegram BotCommand selections cannot supply required arguments."""
+        self._patch_plugin_commands(monkeypatch, {
+            "background-job": {
+                "handler": lambda _a: "ok",
+                "description": "Run a background job",
+                "args_hint": "<prompt>",
+                "plugin": "jobs-plugin",
+            }
+        })
+        names = {name for name, _desc in telegram_bot_commands()}
+        assert "background_job" not 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, {