fix(auth): write rotated Codex/xAI pool grant through to global root (#48415)

CredentialPool._sync_device_code_entry_to_auth_store rotated single-use
OAuth refresh tokens but wrote the new chain only into the active profile
store. When a profile resolves a grant from the global-root fallback
(read_credential_pool, #18594) and the pool then refreshes it, root was
left holding a now-revoked refresh token — every other profile reading the
stale root grant subsequently died with refresh_token_reused / invalid_grant
once its access token expired.

This is the credential-pool analog of #43589 (which fixed the non-pool xAI
refresh path in _save_xai_oauth_tokens). Detect the read-from-root case
(profile lacks its own providers.<id> block) BEFORE the profile save and,
after it, write the rotated chain back to the global root via a best-effort,
seat-belted write-through. A profile that genuinely shadows root (owns the
block) is untouched; classic mode (profile == root) is a no-op; a failed root
write never breaks the profile's own save. Covers openai-codex (reported),
xai-oauth, and nous through the shared sync path.

.github/workflows/ci.yml

@@ -12,6 +12,7 @@ name: CI
 
 on:
   pull_request:
+    branches: [main]
   push:
     branches: [main]
 

.github/workflows/docker-publish.yml

@@ -16,6 +16,7 @@ on:
   # reports a status (path-gated workflows leave checks "pending" forever
   # when no matching files change, which blocks merge).
   pull_request:
+    branches: [main]
 
   release:
     types: [published]

Dockerfile

@@ -290,19 +290,6 @@ ENV HERMES_TUI_DIR=/opt/hermes/ui-tui
 ENV HERMES_HOME=/opt/data
 ENV HERMES_WRITE_SAFE_ROOT=/opt/data
 ENV HERMES_DISABLE_LAZY_INSTALLS=1
-# The published image seals /opt/hermes (root-owned, read-only) so a runtime
-# lazy install can't mutate the agent's own venv and brick it. But opt-in
-# backends (Firecrawl web search, Exa, Feishu, …) keep their SDKs in
-# tools/lazy_deps.py — deliberately NOT baked into [all] (see pyproject.toml
-# policy 2026-05-12: one quarantined release must not break every install).
-# Redirect those lazy installs to a writable dir on the durable data volume.
-# lazy_deps appends this dir to the END of sys.path, so a package installed
-# here can only ADD modules — it can never shadow or downgrade a core module,
-# so the sealed-venv guarantee holds even with installs re-enabled. The dir
-# is seeded + chowned to the hermes user by docker/stage2-hook.sh and lives
-# on the /opt/data volume, so it persists across container recreates / image
-# updates (an ABI stamp invalidates it if a rebuild bumps the interpreter).
-ENV HERMES_LAZY_INSTALL_TARGET=/opt/data/lazy-packages
 
 # `docker exec` privilege-drop shim. When operators run
 # `docker exec <c> hermes ...` they default to root, and any file the

acp_adapter/tools.py

@@ -74,7 +74,7 @@ _POLISHED_TOOLS = {
     "kanban_create", "kanban_show", "kanban_comment", "kanban_complete",
     "kanban_block", "kanban_link", "kanban_heartbeat",
     "yb_query_group_info", "yb_query_group_members", "yb_search_sticker",
-    "yb_send_dm", "yb_send_sticker",
+    "yb_send_dm", "yb_send_sticker", "mixture_of_agents",
 }
 
 

agent/agent_init.py

@@ -106,12 +106,7 @@ def _custom_provider_extra_body_for_agent(
     base_url: str,
     custom_providers: List[Dict[str, Any]],
 ) -> Optional[Dict[str, Any]]:
-    provider_norm = (provider or "").strip().lower()
-    if provider_norm == "custom":
-        provider_key_filter = ""
-    elif provider_norm.startswith("custom:"):
-        provider_key_filter = provider_norm.split(":", 1)[1].strip()
-    else:
+    if (provider or "").strip().lower() != "custom":
         return None
 
     target_url = _normalized_custom_base_url(base_url)
@@ -122,13 +117,6 @@ def _custom_provider_extra_body_for_agent(
     for entry in custom_providers or []:
         if not isinstance(entry, dict):
             continue
-        if provider_key_filter:
-            entry_keys = {
-                str(entry.get("provider_key", "") or "").strip().lower(),
-                str(entry.get("name", "") or "").strip().lower(),
-            }
-            if provider_key_filter not in entry_keys:
-                continue
         if _normalized_custom_base_url(entry.get("base_url")) != target_url:
             continue
         extra_body = entry.get("extra_body")
@@ -719,15 +707,6 @@ def init_agent(
                     print("🔑 Using credentials: Microsoft Entra ID")
                 elif isinstance(effective_key, str) and len(effective_key) > 12:
                     print(f"🔑 Using token: {effective_key[:8]}...{effective_key[-4:]}")
-    elif agent.provider == "moa":
-        from agent.moa_loop import MoAClient
-        agent.api_mode = "chat_completions"
-        agent.client = MoAClient(agent.model or "default")
-        agent._client_kwargs = {}
-        agent.api_key = api_key or "moa-virtual-provider"
-        agent.base_url = base_url or "moa://local"
-        if not agent.quiet_mode:
-            print(f"🤖 AI Agent initialized with MoA preset: {agent.model}")
     elif agent.api_mode == "bedrock_converse":
         # AWS Bedrock — uses boto3 directly, no OpenAI client needed.
         # Region is extracted from the base_url or defaults to us-east-1.
@@ -1527,7 +1506,6 @@ def init_agent(
     # 3. Check general plugin system (user-installed plugins)
     # 4. Fall back to built-in ContextCompressor
     _selected_engine = None
-    _copy_failed = False
     _engine_name = "compressor"  # default
     try:
         _ctx_cfg = _agent_cfg.get("context", {}) if isinstance(_agent_cfg, dict) else {}
@@ -1545,35 +1523,15 @@ def init_agent(
 
         # Try general plugin system as fallback
         if _selected_engine is None:
-            _candidate = None
             try:
                 from hermes_cli.plugins import get_plugin_context_engine
                 _candidate = get_plugin_context_engine()
+                if _candidate and _candidate.name == _engine_name:
+                    _selected_engine = _candidate
             except Exception:
-                _candidate = None
-            if _candidate is not None and _candidate.name == _engine_name:
-                # Deep-copy the shared plugin singleton so a child agent's
-                # update_model() can't mutate the parent's compressor (#42449).
-                # Copy can fail for engines holding uncopyable state (locks, DB
-                # connections, clients); in that case fall back to the built-in
-                # compressor with an ACCURATE message rather than silently
-                # mislabelling it "not found".
-                import copy
-                try:
-                    _selected_engine = copy.deepcopy(_candidate)
-                except Exception as _copy_err:
-                    _copy_failed = True
-                    _ra().logger.warning(
-                        "Context engine '%s' could not be safely copied for this "
-                        "agent (%s) — falling back to built-in compressor. Plugin "
-                        "engines that hold uncopyable state (locks, DB connections) "
-                        "should implement __deepcopy__ to copy only mutable budget "
-                        "state.",
-                        _engine_name, _copy_err,
-                    )
-                    _selected_engine = None
+                pass
 
-        if _selected_engine is None and not _copy_failed:
+        if _selected_engine is None:
             _ra().logger.warning(
                 "Context engine '%s' not found — falling back to built-in compressor",
                 _engine_name,
@@ -1663,27 +1621,16 @@ def init_agent(
             for t in agent.tools
             if isinstance(t, dict)
         }
-        from agent.memory_manager import normalize_tool_schema as _normalize_tool_schema
-        for _raw_schema in agent.context_compressor.get_tool_schemas():
-            _schema = _normalize_tool_schema(_raw_schema)
-            if _schema is None:
-                # A schema with no resolvable name (e.g. an already-wrapped
-                # entry) would append a nameless tool that strict providers
-                # 400 on, disabling the whole toolset (#47707). Skip it.
-                _ra().logger.warning(
-                    "Context engine returned a tool schema with no resolvable "
-                    "name; skipping to avoid poisoning the request (%r)",
-                    _raw_schema,
-                )
-                continue
-            _tname = _schema["name"]
-            if _tname in _existing_tool_names:
+        for _schema in agent.context_compressor.get_tool_schemas():
+            _tname = _schema.get("name", "")
+            if _tname and _tname in _existing_tool_names:
                 continue  # already registered via plugin/cache path
             _wrapped = {"type": "function", "function": _schema}
             agent.tools.append(_wrapped)
-            agent.valid_tool_names.add(_tname)
-            agent._context_engine_tool_names.add(_tname)
-            _existing_tool_names.add(_tname)
+            if _tname:
+                agent.valid_tool_names.add(_tname)
+                agent._context_engine_tool_names.add(_tname)
+                _existing_tool_names.add(_tname)
 
     # Notify context engine of session start
     if hasattr(agent, "context_compressor") and agent.context_compressor:

agent/agent_runtime_helpers.py

@@ -1697,27 +1697,6 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
         old_model, old_provider, new_model, new_provider,
     )
 
-    # ── Persist billing route to session DB ──
-    # The agent's _session_db / session_id may not be set in all contexts
-    # (tests, bare agents without a session DB, etc.).  This ensures the
-    # dashboard Model cards show the actual provider after a mid-session
-    # /model switch instead of the stale session-creation provider.
-    # See #48248 for the full bug description.
-    _session_db = getattr(agent, "_session_db", None)
-    _session_id = getattr(agent, "session_id", None)
-    if _session_db is not None and _session_id:
-        try:
-            _session_db.update_session_billing_route(
-                _session_id,
-                provider=agent.provider,
-                base_url=agent.base_url,
-                billing_mode=getattr(agent, "api_mode", None),
-            )
-        except Exception:
-            logger.warning(
-                "Failed to persist billing route after model switch",
-                exc_info=True,
-            )
 
 
 def invoke_tool(agent, function_name: str, function_args: dict, effective_task_id: str,

agent/auxiliary_client.py

@@ -101,7 +101,6 @@ class _OpenAIProxy:
 OpenAI = _OpenAIProxy()  # module-level name, resolves lazily on call/isinstance
 
 from agent.credential_pool import load_pool
-from agent.model_metadata import MINIMUM_CONTEXT_LENGTH, get_model_context_length
 from hermes_cli.config import get_hermes_home
 from hermes_constants import OPENROUTER_BASE_URL
 from utils import base_url_host_matches, base_url_hostname, env_float, model_forces_max_completion_tokens, normalize_proxy_env_vars
@@ -666,28 +665,6 @@ def _pool_runtime_base_url(entry: Any, fallback: str = "") -> str:
     return str(url or "").strip().rstrip("/")
 
 
-# Hostnames (lowercase, exact) that the auxiliary Anthropic path is allowed to
-# be pointed at via config.yaml model.base_url. Anything else falls back to the
-# Anthropic default — operators routing main-session traffic through a
-# non-Anthropic host (e.g. OpenRouter, OpenAI) with provider=anthropic in config
-# must NOT have that foreign host leak into the auxiliary client. See #52608.
-_ANTHROPIC_COMPATIBLE_HOSTS = frozenset({
-    "api.anthropic.com",
-})
-
-
-def _is_anthropic_compatible_host(url: str) -> bool:
-    """Return True if ``url``'s hostname is an Anthropic endpoint we trust for aux calls."""
-    if not url:
-        return False
-    try:
-        from urllib.parse import urlparse
-        host = (urlparse(url).hostname or "").strip().lower().rstrip(".")
-        return host in _ANTHROPIC_COMPATIBLE_HOSTS
-    except Exception:
-        return False
-
-
 def _nous_min_key_ttl_seconds() -> int:
     try:
         return max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800")))
@@ -2278,16 +2255,9 @@ def _try_anthropic(explicit_api_key: str = None) -> Tuple[Optional[Any], Optiona
     if not token:
         return None, None
 
-    # Allow base URL override from config.yaml model.base_url, but only when:
-    #   1. the configured provider is anthropic (otherwise a non-Anthropic
-    #      base_url, e.g. Codex endpoint, would leak into Anthropic requests), AND
-    #   2. the override URL actually points at an Anthropic-compatible endpoint.
-    # Without gate (2), operators who route main-session traffic through a
-    # non-Anthropic provider that accepts Anthropic-format requests (e.g.
-    # OpenRouter at openrouter.ai/api/v1, with provider=anthropic in config.yaml)
-    # would have every auxiliary side-channel call (memory extractors,
-    # reflection, vision, title generation) 401 from the foreign host —
-    # see issue #52608.
+    # Allow base URL override from config.yaml model.base_url, but only
+    # when the configured provider is anthropic — otherwise a non-Anthropic
+    # base_url (e.g. Codex endpoint) would leak into Anthropic requests.
     base_url = _pool_runtime_base_url(entry, _ANTHROPIC_DEFAULT_BASE_URL) if pool_present else _ANTHROPIC_DEFAULT_BASE_URL
     try:
         from hermes_cli.config import load_config
@@ -2297,7 +2267,7 @@ def _try_anthropic(explicit_api_key: str = None) -> Tuple[Optional[Any], Optiona
             cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
             if cfg_provider == "anthropic":
                 cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
-                if cfg_base_url and _is_anthropic_compatible_host(cfg_base_url):
+                if cfg_base_url:
                     base_url = cfg_base_url
     except Exception:
         pass
@@ -2500,7 +2470,7 @@ def _is_payment_error(exc: Exception) -> bool:
     # but sometimes wrap them in 429 or other codes.
     # Daily quota exhaustion from Bedrock, Vertex AI, and similar providers
     # uses different language but is semantically identical to credit exhaustion.
-    if status in {402, 403, 404, 429, None}:
+    if status in {402, 404, 429, None}:
         if any(kw in err_lower for kw in (
             "credits", "insufficient funds",
             "can only afford", "billing",
@@ -2509,8 +2479,6 @@ def _is_payment_error(exc: Exception) -> bool:
             "balance_depleted", "no usable credits",
             "model_not_supported_on_free_tier",
             "not available on the free tier",
-            "requires a subscription", "upgrade for access",
-            "upgrade for higher limits", "reached your session usage limit",
             # Daily / monthly / weekly quota exhaustion keywords
             "quota exceeded", "quota_exceeded",
             "too many tokens per day", "daily limit",
@@ -2729,60 +2697,6 @@ def _is_model_not_found_error(exc: Exception) -> bool:
     ))
 
 
-def _is_model_incompatible_error(exc: Exception) -> bool:
-    """Detect "this route cannot serve this model" 400s (capability mismatch).
-
-    Distinct from :func:`_is_model_not_found_error` (the model does not exist
-    anywhere): here the model name is valid but the *current provider/account*
-    is structurally unable to run it. The canonical case is a configured
-    fallback that cannot run the main model — e.g. an ``openai-codex`` /
-    ChatGPT-account fallback asked to compress a ``glm-5.2`` conversation::
-
-        Error code: 400 - {'detail': "The 'glm-5.2' model is not supported
-        when using Codex with a ChatGPT account."}
-
-    The candidate authenticates fine and builds a client, so the auth and
-    payment predicates don't fire and the call would otherwise raise and
-    abort the whole auxiliary task (commonly compression — which then drops
-    middle turns and churns the session, destroying the prompt cache).
-    Treating it as a fallback-worthy capability error lets the chain skip the
-    incapable route and continue to the next candidate, mirroring the
-    context-window feasibility screen (#52392).
-
-    Billing/quota 400s belong to :func:`_is_payment_error`; "model does not
-    exist" 400s belong to :func:`_is_model_not_found_error`. This predicate
-    explicitly excludes both so the three don't overlap.
-    """
-    status = getattr(exc, "status_code", None)
-    if status not in {400, None}:
-        return False
-    err_lower = str(exc).lower()
-    # Not-found 400s ("invalid model ID", "model does not exist") are owned by
-    # _is_model_not_found_error. Billing/free-tier 400s are owned by the
-    # payment path — key on the billing keywords directly here rather than
-    # calling _is_payment_error(), because that predicate is status-gated
-    # ({402,403,404,429,None}) and would not recognise a 400-coded billing
-    # body, letting it leak into this capability bucket.
-    if _is_model_not_found_error(exc):
-        return False
-    if any(kw in err_lower for kw in (
-        "credits", "insufficient funds", "billing", "out of funds",
-        "balance_depleted", "no usable credits", "payment required",
-        "free tier", "free-tier", "not available on the free tier",
-        "model_not_supported_on_free_tier", "quota",
-    )):
-        return False
-    return any(kw in err_lower for kw in (
-        "is not supported when using",   # codex/ChatGPT-account model gating
-        "model is not supported",
-        "not supported with this",
-        "not supported for this account",
-        "model_not_supported",
-        "does not support this model",
-        "unsupported model",
-    ))
-
-
 def _evict_cached_clients(provider: str) -> None:
     """Drop cached auxiliary clients for a provider so fresh creds are used."""
     normalized = _normalize_aux_provider(provider)
@@ -3233,88 +3147,6 @@ def _try_main_agent_model_fallback(
     return client, resolved_model or main_model, label
 
 
-# ── Context-window screening for runtime fallback chains (issue #52392) ──
-#
-# When the runtime auxiliary fallback chain selects a candidate that is
-# reachable but has a context window smaller than the compression task
-# requires, the call errors out instead of continuing to the next, viable
-# candidate. The startup feasibility check in
-# ``agent.conversation_compression.check_compression_model_feasibility``
-# already filters too-small auxiliary models at startup, but the runtime
-# fallback chain (``_try_configured_fallback_chain`` and
-# ``_try_main_fallback_chain``) does not apply the same filter, so
-# compression can stop at the first alive door even if the room behind it
-# is too small.
-#
-# The helpers below screen each candidate by its effective context window
-# before it is returned. ``None`` results from ``get_model_context_length``
-# are passed through (we cannot prove a model is too small, so we do not
-# block it). This preserves the existing fallback surface for
-# unrecognised/custom models while closing the gap on the well-known ones.
-
-def _task_minimum_context_length(task: Optional[str]) -> Optional[int]:
-    """Return the minimum context length required for an auxiliary task.
-
-    Only ``compression`` carries an explicit minimum today (the same
-    ``MINIMUM_CONTEXT_LENGTH`` (64K) floor that
-    ``check_compression_model_feasibility`` already enforces at startup).
-    Other tasks (``vision``, ``title_generation``, ``web_extract``,
-    ``skills_hub``, ``mcp``, ``session_search``) return ``None`` — they
-    have no per-task context floor and the runtime chain must remain
-    permissive for them.
-
-    Returns ``None`` for an empty/``None`` task name so the helper is a
-    safe no-op when called from generic sites.
-    """
-    if not task:
-        return None
-    if task == "compression":
-        return MINIMUM_CONTEXT_LENGTH
-    return None
-
-
-def _candidate_context_window(
-    provider: str,
-    model: str,
-    base_url: str = "",
-    api_key: str = "",
-) -> Optional[int]:
-    """Resolve the effective context window for a fallback candidate.
-
-    Thin wrapper around :func:`agent.model_metadata.get_model_context_length`
-    that swallows probe failures (returns ``None``). Callers treat
-    ``None`` as "unknown — pass through" so the existing fallback
-    surface is preserved when the context-length resolver chain cannot
-    determine a value (custom endpoints, models not in the registry,
-    offline endpoints).
-
-    Best-effort, never raises — the runtime fallback chain must keep
-    moving even if the resolver hits a probe error.
-    """
-    if not model:
-        return None
-    try:
-        ctx = get_model_context_length(
-            model,
-            base_url=base_url,
-            api_key=api_key,
-            provider=provider,
-        )
-    except Exception as exc:
-        logger.debug(
-            "Auxiliary fallback: could not resolve context window for %s/%s: %s",
-            provider, model, exc,
-        )
-        return None
-    # ``get_model_context_length`` returns an int (with a 256K default
-    # fallback when nothing else matches). We still propagate ``None`` if
-    # a future change returns ``Optional[int]`` — being explicit is
-    # cheap and the test suite covers both shapes.
-    if isinstance(ctx, int) and ctx > 0:
-        return ctx
-    return None
-
-
 def _try_configured_fallback_chain(
     task: str,
     failed_provider: str,
@@ -3339,7 +3171,6 @@ def _try_configured_fallback_chain(
 
     skip = failed_provider.lower().strip()
     tried = []
-    min_ctx = _task_minimum_context_length(task)
 
     for i, entry in enumerate(chain):
         if not isinstance(entry, dict):
@@ -3357,20 +3188,6 @@ def _try_configured_fallback_chain(
             fb_client, resolved_model = None, None
 
         if fb_client is not None:
-            if min_ctx is not None and resolved_model:
-                fb_ctx = _candidate_context_window(
-                    fb_provider,
-                    resolved_model,
-                    base_url=str(entry.get("base_url") or ""),
-                    api_key=_fallback_entry_api_key(entry) or "",
-                )
-                if fb_ctx is not None and fb_ctx < min_ctx:
-                    logger.info(
-                        "Auxiliary %s: skipping %s (%s context=%d < min=%d), continuing chain",
-                        task, label, resolved_model, fb_ctx, min_ctx,
-                    )
-                    tried.append(f"{label} (context too small: {fb_ctx}<{min_ctx})")
-                    continue
             logger.info(
                 "Auxiliary %s: %s on %s — configured fallback to %s (%s)",
                 task, reason, failed_provider, label, resolved_model or fb_model or "default",
@@ -3386,28 +3203,6 @@ def _try_configured_fallback_chain(
     return None, None, ""
 
 
-def _try_configured_fallback_for_unavailable_client(
-    task: Optional[str],
-    failed_provider: str,
-) -> Tuple[Optional[Any], Optional[str], str]:
-    """Try task fallback_chain when an explicit aux provider cannot build.
-
-    This covers the "no client" case before any request is sent: missing
-    raw env key, unavailable OAuth/pool credentials, or provider resolver
-    returning ``(None, None)``.  It deliberately stops at the configured
-    per-task fallback chain; the main-agent model remains the last-resort
-    runtime fallback for request-time capacity errors.
-    """
-    explicit = (failed_provider or "").strip().lower()
-    if not task or not explicit or explicit in {"auto"}:
-        return None, None, ""
-    return _try_configured_fallback_chain(
-        task,
-        explicit,
-        reason="provider unavailable",
-    )
-
-
 def _fallback_entry_api_key(entry: Dict[str, Any]) -> Optional[str]:
     """Resolve inline or env-backed API key from a fallback-chain entry."""
     explicit = str(entry.get("api_key") or "").strip()
@@ -3466,7 +3261,6 @@ def _try_main_fallback_chain(
     main_norm = (_read_main_provider() or "").strip().lower()
     skip = {p for p in (failed_norm, main_norm, "auto") if p}
     tried: List[str] = []
-    min_ctx = _task_minimum_context_length(task)
 
     for i, entry in enumerate(chain):
         if not isinstance(entry, dict):
@@ -3490,20 +3284,6 @@ def _try_main_fallback_chain(
             logger.debug("Auxiliary %s: main fallback %s failed to resolve: %s", task or "call", label, exc)
             fb_client, resolved_model = None, None
         if fb_client is not None:
-            if min_ctx is not None:
-                fb_ctx = _candidate_context_window(
-                    fb_provider,
-                    resolved_model or fb_model,
-                    base_url=str(entry.get("base_url") or ""),
-                    api_key=_fallback_entry_api_key(entry) or "",
-                )
-                if fb_ctx is not None and fb_ctx < min_ctx:
-                    logger.info(
-                        "Auxiliary %s: skipping %s (context=%d < min=%d), continuing chain",
-                        task or "call", label, fb_ctx, min_ctx,
-                    )
-                    tried.append(f"{label} (context too small: {fb_ctx}<{min_ctx})")
-                    continue
             logger.info(
                 "Auxiliary %s: %s on %s — main fallback chain to %s (%s)",
                 task or "call", reason, failed_provider or "auto", label,
@@ -5564,30 +5344,21 @@ def call_llm(
         )
         if client is None:
             # When the user explicitly chose a non-OpenRouter provider but no
-            # credentials were found, honor the task fallback_chain before
-            # raising.  Missing raw env keys are recoverable for auxiliary
-            # tasks because fallback entries may use OAuth / credential-pool
-            # auth (for example openai-codex).
+            # credentials were found, fail fast instead of silently routing
+            # through OpenRouter (which causes confusing 404s).
             _explicit = (resolved_provider or "").strip().lower()
             if _explicit and _explicit not in {"auto", "openrouter", "custom"}:
-                fb_client, fb_model, fb_label = _try_configured_fallback_for_unavailable_client(
-                    task, _explicit,
+                raise RuntimeError(
+                    f"Provider '{_explicit}' is set in config.yaml but no API key "
+                    f"was found. Set the {_explicit.upper()}_API_KEY environment "
+                    f"variable, or switch to a different provider with `hermes model`."
                 )
-                if fb_client is not None:
-                    client, final_model = fb_client, fb_model
-                    resolved_provider = fb_label or resolved_provider
-                else:
-                    raise RuntimeError(
-                        f"Provider '{_explicit}' is set in config.yaml but no API key "
-                        f"was found. Set the {_explicit.upper()}_API_KEY environment "
-                        f"variable, or switch to a different provider with `hermes model`."
-                    )
             # For auto/custom with no credentials, try the full auto chain
             # rather than hardcoding OpenRouter (which may be depleted).
             # Pass model=None so each provider uses its own default —
             # resolved_model may be an OpenRouter-format slug that doesn't
             # work on other providers.
-            if client is None and not resolved_base_url:
+            if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
                 client, final_model = _get_cached_client("auto", main_runtime=main_runtime, task=task)
@@ -5886,7 +5657,6 @@ def call_llm(
             _is_payment_error(first_err)
             or _is_connection_error(first_err)
             or _is_rate_limit_error(first_err)
-            or _is_model_incompatible_error(first_err)
         )
         # Respect explicit provider choice for transient errors (auth, request
         # validation, etc.) but allow fallback when the provider clearly cannot
@@ -5897,19 +5667,7 @@ def call_llm(
         is_auto = resolved_provider in {"auto", "", None}
         # Capacity errors bypass the explicit-provider gate: the provider
         # literally cannot serve this request regardless of user intent.
-        # Rate limits are included: after retries are exhausted, a 429 means
-        # the provider cannot serve this request — fall back. See #52228.
-        # Model-incompatibility 400s are also a hard capability mismatch (the
-        # route cannot run this model at all — e.g. a codex/ChatGPT-account
-        # fallback asked to compress a glm-5.2 conversation), so they bypass
-        # the explicit-provider gate and continue to the next candidate
-        # instead of aborting the auxiliary task and churning the session.
-        is_capacity_error = (
-            _is_payment_error(first_err)
-            or _is_connection_error(first_err)
-            or _is_rate_limit_error(first_err)
-            or _is_model_incompatible_error(first_err)
-        )
+        is_capacity_error = _is_payment_error(first_err) or _is_connection_error(first_err)
         if should_fallback and (is_auto or is_capacity_error):
             if _is_payment_error(first_err):
                 reason = "payment error"
@@ -5922,8 +5680,6 @@ def call_llm(
                 )
             elif _is_rate_limit_error(first_err):
                 reason = "rate limit"
-            elif _is_model_incompatible_error(first_err):
-                reason = "model incompatible with route"
             else:
                 reason = "connection error"
             logger.info("Auxiliary %s: %s on %s (%s), trying fallback",
@@ -6098,21 +5854,12 @@ async def async_call_llm(
         if client is None:
             _explicit = (resolved_provider or "").strip().lower()
             if _explicit and _explicit not in {"auto", "openrouter", "custom"}:
-                fb_client, fb_model, fb_label = _try_configured_fallback_for_unavailable_client(
-                    task, _explicit,
+                raise RuntimeError(
+                    f"Provider '{_explicit}' is set in config.yaml but no API key "
+                    f"was found. Set the {_explicit.upper()}_API_KEY environment "
+                    f"variable, or switch to a different provider with `hermes model`."
                 )
-                if fb_client is not None:
-                    client, final_model = _to_async_client(
-                        fb_client, fb_model or "", is_vision=(task == "vision")
-                    )
-                    resolved_provider = fb_label or resolved_provider
-                else:
-                    raise RuntimeError(
-                        f"Provider '{_explicit}' is set in config.yaml but no API key "
-                        f"was found. Set the {_explicit.upper()}_API_KEY environment "
-                        f"variable, or switch to a different provider with `hermes model`."
-                    )
-            if client is None and not resolved_base_url:
+            if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
                 client, final_model = _get_cached_client("auto", async_mode=True, main_runtime=main_runtime, task=task)
@@ -6362,22 +6109,12 @@ async def async_call_llm(
             _is_payment_error(first_err)
             or _is_connection_error(first_err)
             or _is_rate_limit_error(first_err)
-            or _is_model_incompatible_error(first_err)
         )
-        # Capacity errors (payment/quota/connection/rate-limit) bypass the
-        # explicit-provider gate — the provider cannot serve the request
-        # regardless of user intent. Rate limits are included: after retries
-        # are exhausted, a 429 means the provider is at capacity. See #52228.
+        # Capacity errors (payment/quota/connection) bypass the explicit-provider
+        # gate — the provider cannot serve the request regardless of user intent.
         # See #26803: daily token quota must fall back like a 402 credit error.
-        # Model-incompatibility 400s (route cannot run this model at all)
-        # bypass the gate too — see the sync call_llm() path for rationale.
         is_auto = resolved_provider in {"auto", "", None}
-        is_capacity_error = (
-            _is_payment_error(first_err)
-            or _is_connection_error(first_err)
-            or _is_rate_limit_error(first_err)
-            or _is_model_incompatible_error(first_err)
-        )
+        is_capacity_error = _is_payment_error(first_err) or _is_connection_error(first_err)
         if should_fallback and (is_auto or is_capacity_error):
             if _is_payment_error(first_err):
                 reason = "payment error"
@@ -6386,8 +6123,6 @@ async def async_call_llm(
                 )
             elif _is_rate_limit_error(first_err):
                 reason = "rate limit"
-            elif _is_model_incompatible_error(first_err):
-                reason = "model incompatible with route"
             else:
                 reason = "connection error"
             logger.info("Auxiliary %s (async): %s on %s (%s), trying fallback",

agent/chat_completion_helpers.py

@@ -2561,17 +2561,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
             _stream_stale_timeout = max(_stream_stale_timeout_base, 240.0)
         else:
             _stream_stale_timeout = _stream_stale_timeout_base
-        # Reasoning-model floor: known reasoning models (Nemotron 3 Ultra,
-        # OpenAI o1/o3, Anthropic Opus 4.x thinking, DeepSeek R1, Qwen QwQ,
-        # xAI Grok reasoning, etc.) routinely exceed the default 180s chat-
-        # model threshold during their thinking phase.  The cloud gateway
-        # upstream kills the socket first, surfacing as BrokenPipeError.
-        # Raises the floor only — never overrides explicit user config
-        # (handled by get_provider_stale_timeout above).
-        from agent.reasoning_timeouts import get_reasoning_stale_timeout_floor
-        _reasoning_floor = get_reasoning_stale_timeout_floor(api_kwargs.get("model"))
-        if _reasoning_floor is not None:
-            _stream_stale_timeout = max(_stream_stale_timeout, _reasoning_floor)
 
     t = threading.Thread(target=_call, daemon=True)
     t.start()

agent/coding_context.py

@@ -83,59 +83,6 @@ _PROJECT_MARKERS = (
 # Agent-instruction files surfaced separately from manifests in the snapshot.
 _CONTEXT_FILES = ("AGENTS.md", "CLAUDE.md", ".cursorrules")
 
-# Source-file extensions that make a git repo a *code* workspace even with no
-# manifest. Without this, `git init` on a notes/writing/research folder (a huge
-# non-coding use case) would flip the whole session into the coding posture just
-# for having a `.git`. A manifest still wins on its own (see `_PROJECT_MARKERS`).
-_CODE_EXTENSIONS = frozenset({
-    ".py", ".pyi", ".ipynb", ".js", ".jsx", ".ts", ".tsx", ".mjs", ".cjs",
-    ".go", ".rs", ".java", ".kt", ".kts", ".scala", ".rb", ".php", ".c", ".h",
-    ".cc", ".cpp", ".hpp", ".cs", ".swift", ".m", ".mm", ".dart", ".ex", ".exs",
-    ".lua", ".sh", ".bash", ".zsh", ".sql", ".vue", ".svelte", ".r", ".jl",
-    ".hs", ".clj", ".erl", ".pl",
-})
-
-# Dirs never worth scanning for the code check (deps/build/vcs/venv noise).
-_CODE_SCAN_SKIP_DIRS = frozenset({
-    ".git", "node_modules", "venv", ".venv", "__pycache__", "dist", "build",
-    "target", ".next", ".turbo", "vendor",
-})
-
-# Bounded sweep: a code workspace reveals itself in the first handful of entries.
-_CODE_SCAN_MAX_ENTRIES = 500
-
-
-def _has_code_files(root: Path) -> bool:
-    """Cheap, bounded check for source files in a repo's top two levels.
-
-    Lets a git repo of loose scripts (no manifest) still read as a code
-    workspace while a bare notes/writing repo does not. Scans the root and its
-    immediate subdirectories only, capped at ``_CODE_SCAN_MAX_ENTRIES`` stats —
-    a handful of readdirs at session start, not a full walk.
-    """
-    seen = 0
-    stack = [(root, True)]
-    while stack:
-        directory, is_root = stack.pop()
-        try:
-            with os.scandir(directory) as entries:
-                for entry in entries:
-                    seen += 1
-                    if seen > _CODE_SCAN_MAX_ENTRIES:
-                        return False
-                    name = entry.name
-                    try:
-                        if entry.is_file():
-                            if os.path.splitext(name)[1].lower() in _CODE_EXTENSIONS:
-                                return True
-                        elif is_root and entry.is_dir() and name not in _CODE_SCAN_SKIP_DIRS and not name.startswith("."):
-                            stack.append((Path(entry.path), False))
-                    except OSError:
-                        continue
-        except OSError:
-            continue
-    return False
-
 # Lockfile → package manager, checked in priority order.
 _PY_LOCKFILES = (("uv.lock", "uv"), ("poetry.lock", "poetry"), ("Pipfile.lock", "pipenv"))
 _JS_LOCKFILES = (
@@ -421,16 +368,10 @@ def _detect_profile_name(mode: str, platform: str, cwd_str: str) -> str:
     if platform and platform.strip().lower() not in INTERACTIVE_CODING_PLATFORMS:
         return GENERAL_PROFILE.name
     cwd = Path(cwd_str)
-    # A recognized project root (manifest / AGENTS.md / .cursorrules) is a code
-    # workspace on its own — cheap stat checks, no scan.
-    if _marker_root(cwd) is not None:
-        return CODING_PROFILE.name
     git_root = _git_root(cwd)
     if git_root is not None and git_root == _home():
         git_root = None  # dotfiles repo at $HOME — not a code workspace
-    # A bare git repo only counts when it actually holds code, so `git init` on a
-    # notes/writing/research folder stays in the general posture.
-    if git_root is not None and _has_code_files(git_root):
+    if git_root is not None or _marker_root(cwd) is not None:
         return CODING_PROFILE.name
     return GENERAL_PROFILE.name
 

agent/context_compressor.py

@@ -890,15 +890,7 @@ class ContextCompressor(ContextEngine):
         # This is independent of the abort_on_summary_failure config flag:
         # rotating on a broken credential is never the right behavior.
         self._last_summary_auth_failure: bool = False
-        # Set when summary generation ultimately fails due to a transient
-        # network/connection error (httpx/httpcore connection drop, premature
-        # stream close, etc.) — distinct from auth failures but treated the
-        # same way by compress(): ABORT and preserve the session unchanged
-        # rather than destroy the middle window for a deterministic
-        # "summary unavailable" marker. Retrying once the network recovers is
-        # strictly better than discarding context for a transient blip
-        # (#29559, #25585). Independent of abort_on_summary_failure.
-        self._last_summary_network_failure: bool = False
+        # When a user-configured summary model fails and we recover by
         # retrying on the main model, record the failure so gateway /
         # CLI callers can still warn the user even though compression
         # succeeded.  Silent recovery would hide the broken config.
@@ -1695,7 +1687,6 @@ This compaction should PRIORITISE preserving all information related to the focu
             self._summary_model_fallen_back = False
             self._last_summary_error = None
             self._last_summary_auth_failure = False
-            self._last_summary_network_failure = False
             return self._with_summary_prefix(summary)
         except Exception as e:
             # ``call_llm`` raises ``RuntimeError`` for two very different cases:
@@ -1828,15 +1819,6 @@ This compaction should PRIORITISE preserving all information related to the focu
             if len(err_text) > 220:
                 err_text = err_text[:217].rstrip() + "..."
             self._last_summary_error = err_text
-            # A terminal connection/network failure (we reach this branch only
-            # after any main-model fallback has already been tried or is
-            # unavailable). Flag it so compress() ABORTS and preserves the
-            # session unchanged instead of destroying the middle window for a
-            # placeholder marker — retrying once the network recovers is
-            # strictly better than dropping context (#29559, #25585). Mirrors
-            # the auth-failure carve-out; independent of abort_on_summary_failure.
-            if _is_streaming_closed:
-                self._last_summary_network_failure = True
             logger.warning(
                 "Failed to generate context summary: %s. "
                 "Further summary attempts paused for %d seconds.",
@@ -2400,7 +2382,6 @@ This compaction should PRIORITISE preserving all information related to the focu
         self._last_aux_model_failure_model = None
         self._last_compress_aborted = False
         self._last_summary_auth_failure = False
-        self._last_summary_network_failure = False
 
         # Manual /compress (force=True) bypasses the failure cooldown so the
         # user can retry immediately after an auto-compress abort.  Without
@@ -2517,21 +2498,15 @@ This compaction should PRIORITISE preserving all information related to the focu
         #           surface a warning.
         # Default is False (historical behavior).
         #
-        # EXCEPTION — auth AND transient network failures always abort. A
-        # 401/403 from the summary call means the credential or endpoint is
-        # broken (invalid/blocked key, or a token pointed at the wrong
-        # inference host). A connection/stream-close error means the network
-        # blipped at the compaction moment (#29559). In BOTH cases rotating into
+        # EXCEPTION — auth failures always abort. A 401/403 from the summary
+        # call means the credential or endpoint is broken (invalid/blocked
+        # key, or a token pointed at the wrong inference host). Rotating into
         # a child session with a placeholder summary on a broken credential
         # strands the user on a degraded session for zero benefit — every
         # subsequent call fails the same way. So when the failure was an auth
         # error we abort regardless of abort_on_summary_failure, preserving
         # the conversation unchanged until the credential is fixed.
-        if not summary and (
-            self.abort_on_summary_failure
-            or self._last_summary_auth_failure
-            or self._last_summary_network_failure
-        ):
+        if not summary and (self.abort_on_summary_failure or self._last_summary_auth_failure):
             n_skipped = compress_end - compress_start
             self._last_summary_dropped_count = 0  # nothing actually dropped
             self._last_summary_fallback_used = False
@@ -2546,15 +2521,6 @@ This compaction should PRIORITISE preserving all information related to the focu
                         "with /compress or start fresh with /new.",
                         n_skipped,
                     )
-                elif self._last_summary_network_failure:
-                    logger.warning(
-                        "Summary generation failed with a network/connection "
-                        "error — aborting compression. %d message(s) preserved "
-                        "unchanged; the session was NOT rotated. This is "
-                        "transient: retry with /compress once connectivity "
-                        "recovers, or continue the conversation as-is.",
-                        n_skipped,
-                    )
                 else:
                     logger.warning(
                         "Summary generation failed — aborting compression "

agent/conversation_compression.py

@@ -90,7 +90,6 @@ def check_compression_model_feasibility(agent: Any) -> None:
     try:
         from agent.auxiliary_client import (
             _resolve_task_provider_model,
-            _try_configured_fallback_for_unavailable_client,
             get_text_auxiliary_client,
         )
         from agent.model_metadata import (
@@ -98,6 +97,10 @@ def check_compression_model_feasibility(agent: Any) -> None:
             get_model_context_length,
         )
 
+        client, aux_model = get_text_auxiliary_client(
+            "compression",
+            main_runtime=agent._current_main_runtime(),
+        )
         # Best-effort aux provider label for the warning message. The
         # configured provider may be "auto", in which case we fall back
         # to the client's base_url hostname so the user can still tell
@@ -106,19 +109,6 @@ def check_compression_model_feasibility(agent: Any) -> None:
             _aux_cfg_provider, _, _, _, _ = _resolve_task_provider_model("compression")
         except Exception:
             _aux_cfg_provider = ""
-        client, aux_model = get_text_auxiliary_client(
-            "compression",
-            main_runtime=agent._current_main_runtime(),
-        )
-        if client is None or not aux_model:
-            fb_client, fb_model, fb_label = _try_configured_fallback_for_unavailable_client(
-                "compression",
-                _aux_cfg_provider,
-            )
-            if fb_client is not None and fb_model:
-                client, aux_model = fb_client, fb_model
-                if "(" in fb_label and fb_label.endswith(")"):
-                    _aux_cfg_provider = fb_label.rsplit("(", 1)[1][:-1]
         if client is None or not aux_model:
             if _aux_cfg_provider and _aux_cfg_provider != "auto":
                 msg = (

agent/conversation_loop.py

@@ -35,7 +35,6 @@ from agent.turn_context import build_turn_context
 from agent.turn_retry_state import TurnRetryState
 from agent.memory_manager import build_memory_context_block
 from agent.message_sanitization import (
-    close_interrupted_tool_sequence,
     _repair_tool_call_arguments,
     _sanitize_messages_non_ascii,
     _sanitize_messages_surrogates,
@@ -56,7 +55,7 @@ from agent.model_metadata import (
 )
 from agent.process_bootstrap import _install_safe_stdio
 from agent.prompt_caching import apply_anthropic_cache_control
-from agent.retry_utils import adaptive_rate_limit_backoff, jittered_backoff
+from agent.retry_utils import jittered_backoff
 from agent.trajectory import has_incomplete_scratchpad
 from agent.usage_pricing import estimate_usage_cost, normalize_usage
 from hermes_constants import PARTIAL_STREAM_STUB_ID
@@ -502,7 +501,6 @@ def run_conversation(
     stream_callback: Optional[callable] = None,
     persist_user_message: Optional[str] = None,
     persist_user_timestamp: Optional[float] = None,
-    moa_config: Optional[dict[str, Any]] = None,
 ) -> Dict[str, Any]:
     """
     Run a complete conversation with tool calling until completion.
@@ -525,19 +523,6 @@ def run_conversation(
     Returns:
         Dict: Complete conversation result with final response and message history
     """
-    if moa_config is None:
-        try:
-            from hermes_cli.moa_config import decode_moa_turn
-
-            _decoded_message, _decoded_moa_config = decode_moa_turn(user_message)
-            if _decoded_moa_config is not None:
-                user_message = _decoded_message
-                moa_config = _decoded_moa_config
-                if persist_user_message is None:
-                    persist_user_message = _decoded_message
-        except Exception:
-            pass
-
     # ── Per-turn setup (the prologue) ──
     # All once-per-turn setup — stdio guarding, retry-counter resets, user
     # message sanitization, todo/nudge hydration, system-prompt restore-or-
@@ -816,29 +801,6 @@ def run_conversation(
         if effective_system:
             api_messages = [{"role": "system", "content": effective_system}] + api_messages
 
-        if moa_config:
-            try:
-                from agent.moa_loop import aggregate_moa_context
-
-                _moa_context = aggregate_moa_context(
-                    user_prompt=original_user_message if isinstance(original_user_message, str) else str(original_user_message),
-                    api_messages=api_messages,
-                    reference_models=moa_config.get("reference_models") or [],
-                    aggregator=moa_config.get("aggregator") or {},
-                    temperature=float(moa_config.get("reference_temperature", 0.6) or 0.6),
-                    aggregator_temperature=float(moa_config.get("aggregator_temperature", 0.4) or 0.4),
-                    max_tokens=int(moa_config.get("max_tokens", 4096) or 4096),
-                )
-                if _moa_context:
-                    for _msg in reversed(api_messages):
-                        if _msg.get("role") == "user":
-                            _base = _msg.get("content", "")
-                            if isinstance(_base, str):
-                                _msg["content"] = _base + "\n\n" + _moa_context
-                            break
-            except Exception as _moa_exc:
-                logger.warning("MoA context aggregation failed: %s", _moa_exc)
-
         # Inject ephemeral prefill messages right after the system prompt
         # but before conversation history. Same API-call-time-only pattern.
         if agent.prefill_messages:
@@ -1160,7 +1122,7 @@ def run_conversation(
                 # stream.  Mirror the ACP exclusion used for Responses
                 # API upgrade (lines ~1083-1085).
                 elif (
-                    agent.provider in {"copilot-acp", "moa"}
+                    agent.provider == "copilot-acp"
                     or str(agent.base_url or "").lower().startswith("acp://copilot")
                     or str(agent.base_url or "").lower().startswith("acp+tcp://")
                 ):
@@ -1434,12 +1396,10 @@ def run_conversation(
                     while time.time() < sleep_end:
                         if agent._interrupt_requested:
                             agent._vprint(f"{agent.log_prefix}⚡ Interrupt detected during retry wait, aborting.", force=True)
-                            _interrupt_text = f"Operation interrupted during retry ({_failure_hint}, attempt {retry_count}/{max_retries})."
-                            close_interrupted_tool_sequence(messages, _interrupt_text)
                             agent._persist_session(messages, conversation_history)
                             agent.clear_interrupt()
                             return {
-                                "final_response": _interrupt_text,
+                                "final_response": f"Operation interrupted during retry ({_failure_hint}, attempt {retry_count}/{max_retries}).",
                                 "messages": messages,
                                 "api_calls": api_call_count,
                                 "completed": False,
@@ -2011,21 +1971,9 @@ def run_conversation(
                     agent.thinking_callback("")
                 api_elapsed = time.time() - api_start_time
                 agent._vprint(f"{agent.log_prefix}⚡ Interrupted during API call.", force=True)
-                interrupted = True
-                # Preserve any assistant text already streamed to the user
-                # before the stop landed. Dropping it leaves history with no
-                # record of the half-finished reply on screen, so the next turn
-                # the model "forgets" what it just said — exactly what users hit
-                # when they stop to redirect mid-response.
-                _partial = agent._strip_think_blocks(
-                    getattr(agent, "_current_streamed_assistant_text", "") or ""
-                ).strip()
-                if _partial:
-                    messages.append({"role": "assistant", "content": _partial})
-                    final_response = _partial
-                else:
-                    final_response = f"{INTERRUPT_WAITING_FOR_MODEL_PREFIX}{api_elapsed:.1f}s elapsed)."
                 agent._persist_session(messages, conversation_history)
+                interrupted = True
+                final_response = f"{INTERRUPT_WAITING_FOR_MODEL_PREFIX}{api_elapsed:.1f}s elapsed)."
                 break
 
             except Exception as api_error:
@@ -2715,12 +2663,10 @@ def run_conversation(
                 # Check for interrupt before deciding to retry
                 if agent._interrupt_requested:
                     agent._vprint(f"{agent.log_prefix}⚡ Interrupt detected during error handling, aborting retries.", force=True)
-                    _interrupt_text = f"Operation interrupted: handling API error ({error_type}: {agent._clean_error_message(str(api_error))})."
-                    close_interrupted_tool_sequence(messages, _interrupt_text)
                     agent._persist_session(messages, conversation_history)
                     agent.clear_interrupt()
                     return {
-                        "final_response": _interrupt_text,
+                        "final_response": f"Operation interrupted: handling API error ({error_type}: {agent._clean_error_message(str(api_error))}).",
                         "messages": messages,
                         "api_calls": api_call_count,
                         "completed": False,
@@ -3539,65 +3485,6 @@ def run_conversation(
                             force=True,
                         )
 
-                    # Detect thinking-timeout pattern: a known reasoning model
-                    # hit a transport-layer error before the first content
-                    # token arrived.  Distinct from _is_stream_drop above
-                    # (which fires for large file-write stream drops) and
-                    # from any classifier reason that's not a transport
-                    # timeout.  Reuses the reasoning-model allowlist from
-                    # agent/reasoning_timeouts.py (Fixes #52217) so the
-                    # trigger is consistent with what the per-model
-                    # stale-timeout floor covers.  After the classifier
-                    # override at agent/error_classifier.py:720-738 (this
-                    # PR), transport disconnects on reasoning models route
-                    # to FailoverReason.timeout rather than
-                    # context_overflow, so this branch actually fires.
-                    # Detection and message text live in
-                    # agent.thinking_timeout_guidance so they're
-                    # unit-testable without driving the full retry loop.
-                    # (Part 2 of Fixes #52310.)
-                    from agent.thinking_timeout_guidance import (
-                        is_thinking_timeout,
-                    )
-                    _is_thinking_timeout = is_thinking_timeout(
-                        classified,
-                        _model,
-                        error_msg,
-                    )
-                    if _is_thinking_timeout:
-                        agent._vprint(
-                            f"{agent.log_prefix}   💡 The model's thinking "
-                            f"phase exceeded the upstream proxy's idle "
-                            f"timeout before the first content token "
-                            f"arrived. This is a known issue with "
-                            f"reasoning models behind cloud gateways "
-                            f"(NVIDIA NIM, OpenAI, Anthropic, DeepSeek).",
-                            force=True,
-                        )
-                        agent._vprint(
-                            f"{agent.log_prefix}      Workarounds in priority order:",
-                            force=True,
-                        )
-                        agent._vprint(
-                            f"{agent.log_prefix}      1. Set "
-                            f"`providers.{_provider}.models.{_model}.stale_timeout_seconds: 900` "
-                            f"in `~/.hermes/config.yaml` to extend the per-call "
-                            f"timeout. (Hermes's built-in floor is 600s for "
-                            f"known reasoning models — if you still see this "
-                            f"after raising, the upstream cap is even shorter.)",
-                            force=True,
-                        )
-                        agent._vprint(
-                            f"{agent.log_prefix}      2. Lower `reasoning_budget` or set "
-                            f"`reasoning_effort: medium` on this model if the provider supports it.",
-                            force=True,
-                        )
-                        agent._vprint(
-                            f"{agent.log_prefix}      3. Use a smaller / faster reasoning "
-                            f"model if the task doesn't require deep thinking.",
-                            force=True,
-                        )
-
                     logger.error(
                         "%sAPI call failed after %s retries. %s | provider=%s model=%s msgs=%s tokens=~%s",
                         agent.log_prefix, max_retries, _final_summary,
@@ -3614,22 +3501,7 @@ def run_conversation(
                             _final_response += f"\n\n{_billing_guidance}"
                     else:
                         _final_response = f"API call failed after {max_retries} retries: {_final_summary}"
-                    if _is_thinking_timeout:
-                        # Thinking-timeout guidance overrides the generic
-                        # stream-drop guidance — the latter is wrong for
-                        # this case (it suggests splitting large file
-                        # writes, which isn't what happened).  See the
-                        # reasoning-model override at
-                        # agent/error_classifier.py:720-738 and the
-                        # detection block above for context.
-                        from agent.thinking_timeout_guidance import (
-                            build_thinking_timeout_guidance,
-                        )
-                        _final_response += build_thinking_timeout_guidance(
-                            provider=_provider,
-                            model=_model,
-                        )
-                    elif _is_stream_drop:
+                    if _is_stream_drop:
                         _final_response += (
                             "\n\nThe provider's stream connection keeps "
                             "dropping — this often happens when generating "
@@ -3665,38 +3537,16 @@ def run_conversation(
                             except (TypeError, ValueError):
                                 pass
                 wait_time = _retry_after if _retry_after else jittered_backoff(retry_count, base_delay=2.0, max_delay=60.0)
-                _backoff_policy = None
-                if is_rate_limited and not _retry_after:
-                    wait_time, _backoff_policy = adaptive_rate_limit_backoff(
-                        retry_count,
-                        base_url=str(_base),
-                        model=_model,
-                        error=api_error,
-                        default_wait=wait_time,
-                    )
                 if is_rate_limited:
-                    _policy_note = ""
-                    if _backoff_policy == "zai_coding_overload_long":
-                        _policy_note = " (Z.AI Coding overload adaptive long backoff)"
-                    elif _backoff_policy == "zai_coding_overload_short":
-                        _policy_note = " (Z.AI Coding overload short retry)"
-                    _rate_limit_status = f"⏱️ Rate limited. Waiting {wait_time:.1f}s (attempt {retry_count + 1}/{max_retries}){_policy_note}..."
-                    # Normal retries are buffered to avoid noisy transient chatter. Long
-                    # Z.AI Coding waits are different: they can last minutes, so surface
-                    # progress immediately instead of making the TUI look frozen.
-                    if _backoff_policy == "zai_coding_overload_long":
-                        agent._emit_status(_rate_limit_status)
-                    else:
-                        agent._buffer_status(_rate_limit_status)
+                    agent._buffer_status(f"⏱️ Rate limited. Waiting {wait_time:.1f}s (attempt {retry_count + 1}/{max_retries})...")
                 else:
                     agent._buffer_status(f"⏳ Retrying in {wait_time:.1f}s (attempt {retry_count}/{max_retries})...")
                 logger.warning(
-                    "Retrying API call in %ss (attempt %s/%s) %s policy=%s error=%s",
+                    "Retrying API call in %ss (attempt %s/%s) %s error=%s",
                     wait_time,
                     retry_count,
                     max_retries,
                     agent._client_log_context(),
-                    _backoff_policy or "default",
                     api_error,
                 )
                 # Sleep in small increments so we can respond to interrupts quickly
@@ -3706,12 +3556,10 @@ def run_conversation(
                 while time.time() < sleep_end:
                     if agent._interrupt_requested:
                         agent._vprint(f"{agent.log_prefix}⚡ Interrupt detected during retry wait, aborting.", force=True)
-                        _interrupt_text = f"Operation interrupted: retrying API call after error (retry {retry_count}/{max_retries})."
-                        close_interrupted_tool_sequence(messages, _interrupt_text)
                         agent._persist_session(messages, conversation_history)
                         agent.clear_interrupt()
                         return {
-                            "final_response": _interrupt_text,
+                            "final_response": f"Operation interrupted: retrying API call after error (retry {retry_count}/{max_retries}).",
                             "messages": messages,
                             "api_calls": api_call_count,
                             "completed": False,
@@ -4644,10 +4492,9 @@ def run_conversation(
                 final_msg = agent._build_assistant_message(assistant_message, finish_reason)
 
                 # Pop thinking-only prefill and empty-response retry
-                # scaffolding before appending either a final response or a
-                # verification-stop follow-up. These internal turns are only
-                # for the next API retry and should not become durable
-                # transcript context.
+                # scaffolding before appending the final response.  These
+                # internal turns are only for the next API retry and should
+                # not become durable transcript context.
                 while (
                     messages
                     and isinstance(messages[-1], dict)
@@ -4659,44 +4506,6 @@ def run_conversation(
                 ):
                     messages.pop()
 
-                try:
-                    from agent.verification_stop import (
-                        build_verify_on_stop_nudge,
-                        verify_on_stop_enabled,
-                    )
-
-                    if verify_on_stop_enabled():
-                        _verify_nudge = build_verify_on_stop_nudge(
-                            session_id=getattr(agent, "session_id", None),
-                            changed_paths=getattr(agent, "_turn_file_mutation_paths", set()),
-                            attempts=getattr(agent, "_verification_stop_nudges", 0),
-                        )
-                    else:
-                        _verify_nudge = None
-                except Exception:
-                    logger.debug("verification stop-loop check failed", exc_info=True)
-                    _verify_nudge = None
-
-                if _verify_nudge:
-                    agent._verification_stop_nudges = (
-                        getattr(agent, "_verification_stop_nudges", 0) + 1
-                    )
-                    final_msg["finish_reason"] = "verification_required"
-                    messages.append(final_msg)
-                    # Keep the attempted final answer in model history so the
-                    # synthetic user nudge preserves role alternation, but do
-                    # not surface it to the user as an interim answer. The
-                    # whole point of this guard is to prevent premature
-                    # "done" claims before checks run.
-                    messages.append({
-                        "role": "user",
-                        "content": _verify_nudge,
-                        "_verification_stop_synthetic": True,
-                    })
-                    agent._session_messages = messages
-                    agent._emit_status("↻ Verification required before finishing")
-                    continue
-
                 messages.append(final_msg)
                 
                 _turn_exit_reason = f"text_response(finish_reason={finish_reason})"

agent/curator.py

@@ -377,10 +377,8 @@ CURATOR_REVIEW_PROMPT = (
     "bodies + `references/`, `templates/`, and `scripts/` subfiles for "
     "session-specific detail — not one-session-one-skill micro-entries.\n\n"
     "Hard rules — do not violate:\n"
-    "1. DO NOT touch bundled, hub-installed, or external-dir skills "
-    "(`skills.external_dirs`). The candidate list below is already filtered "
-    "to local curator-managed skills only; external skills are externally "
-    "owned and read-only to this background curator.\n"
+    "1. DO NOT touch bundled or hub-installed skills. The candidate list "
+    "below is already filtered to agent-created skills only.\n"
     "2. DO NOT delete any skill. Archiving (moving the skill's directory "
     "into ~/.hermes/skills/.archive/) is the maximum destructive action. "
     "Archives are recoverable; deletion is not.\n"
@@ -471,9 +469,8 @@ CURATOR_REVIEW_PROMPT = (
     "skill, or `absorbed_into=\"\"` when you're truly pruning with no "
     "forwarding target. This drives cron-job skill-reference migration — "
     "guessing from your YAML summary after the fact is fragile.\n"
-    "  - terminal                       — move LOCAL candidate content into "
-    "a support subfile when package integrity requires it; never mv, cp, rm, "
-    "patch, or rewrite bundled, hub-installed, or external-dir skills\n\n"
+    "  - terminal                       — mv a sibling into the archive "
+    "OR move its content into a support subfile\n\n"
     "'keep' is a legitimate decision ONLY when the skill is already a "
     "class-level umbrella and none of the proposed merges would improve "
     "discoverability. 'This is narrow but distinct from its siblings' "
@@ -1846,14 +1843,6 @@ def _run_llm_review(prompt: str) -> Dict[str, Any]:
         # Disable recursive nudges — the curator must never spawn its own review.
         review_agent._memory_nudge_interval = 0
         review_agent._skill_nudge_interval = 0
-        # Tag this fork as autonomous background curation so skill_manage's
-        # background-review write guard fires. Without this the fork inherits
-        # the default "assistant_tool" origin, is_background_review() is False,
-        # and the external/bundled/hub-installed skill_manage guards never
-        # trigger during the curation pass they exist to protect against.
-        # turn_context.py binds this onto the write-origin ContextVar at turn
-        # start (see agent/turn_context.py).
-        review_agent._memory_write_origin = "background_review"
 
         # Redirect the forked agent's stdout/stderr to /dev/null while it
         # runs so its tool-call chatter doesn't pollute the foreground

agent/display.py

@@ -6,7 +6,6 @@ Used by AIAgent._execute_tool_calls for CLI feedback.
 
 import logging
 import os
-import re
 import sys
 import threading
 import time
@@ -16,7 +15,6 @@ from pathlib import Path
 from typing import Any
 
 from utils import safe_json_loads
-from agent.redact import redact_sensitive_text
 from agent.tool_result_classification import file_mutation_result_landed
 
 # ANSI escape codes for coloring tool failure indicators
@@ -179,223 +177,6 @@ def _truncate_preview(text: str, max_len: int | None) -> str:
     return text
 
 
-_SHELL_SILENT_HEADS = {"cd", "pushd", "popd", "export", "set", "unset", "source", ".", "true", "false", ":"}
-_SHELL_PIPE_TAIL_HEADS = {"head", "tail", "wc", "sort", "uniq"}
-
-
-def _shell_basename(head: str) -> str:
-    return head.rsplit("/", 1)[-1] if head else ""
-
-
-def _split_shell_words(segment: str) -> list[str]:
-    words: list[str] = []
-    buf: list[str] = []
-    quote: str | None = None
-
-    for i, ch in enumerate(segment):
-        if quote:
-            buf.append(ch)
-            if ch == quote and (i == 0 or segment[i - 1] != "\\"):
-                quote = None
-            continue
-
-        if ch in {"'", '"'}:
-            quote = ch
-            buf.append(ch)
-            continue
-
-        if ch.isspace():
-            if buf:
-                words.append("".join(buf))
-                buf = []
-            continue
-
-        buf.append(ch)
-
-    if buf:
-        words.append("".join(buf))
-
-    return words
-
-
-def _strip_shell_pipe_tail(segment: str) -> str:
-    words = _split_shell_words(segment)
-    out: list[str] = []
-
-    for i, word in enumerate(words):
-        if word == "|" and _shell_basename(words[i + 1] if i + 1 < len(words) else "") in _SHELL_PIPE_TAIL_HEADS:
-            break
-        out.append(word)
-
-    return " ".join(out).strip()
-
-
-def _split_shell_compound(command: str) -> list[str]:
-    segments: list[str] = []
-    buf: list[str] = []
-    quote: str | None = None
-    i = 0
-
-    while i < len(command):
-        ch = command[i]
-
-        if quote:
-            buf.append(ch)
-            if ch == quote and (i == 0 or command[i - 1] != "\\"):
-                quote = None
-            i += 1
-            continue
-
-        if ch in {"'", '"'}:
-            quote = ch
-            buf.append(ch)
-            i += 1
-            continue
-
-        op_len = 2 if command.startswith("&&", i) or command.startswith("||", i) else 1 if ch in {";", "\n"} else 0
-        if op_len:
-            segment = _strip_shell_pipe_tail("".join(buf).strip())
-            if segment:
-                segments.append(segment)
-            buf = []
-            i += op_len
-            continue
-
-        buf.append(ch)
-        i += 1
-
-    segment = _strip_shell_pipe_tail("".join(buf).strip())
-    if segment:
-        segments.append(segment)
-
-    return segments
-
-
-def _shell_head_word(segment: str) -> str:
-    words = _split_shell_words(segment)
-    index = 0
-    while index < len(words) and re.match(r"^[A-Za-z_]\w*=", words[index]):
-        index += 1
-    return _shell_basename(words[index] if index < len(words) else "")
-
-
-def _clean_shell_segment(segment: str) -> str:
-    words = _split_shell_words(segment)
-    out: list[str] = []
-    i = 0
-    while i < len(words):
-        word = words[i]
-        if re.match(r"^\d*(?:>>?|<)$", word):
-            i += 2
-            continue
-        if re.match(r"^\d*(?:>&|<&)\d+$", word) or re.match(r"^\d*>&\d+$", word):
-            i += 1
-            continue
-        out.append(word)
-        i += 1
-    return " ".join(out).strip()
-
-
-def _is_shell_boundary_echo(segment: str) -> bool:
-    words = _split_shell_words(segment)
-    if _shell_basename(words[0] if words else "") != "echo":
-        return False
-    rest = " ".join(words[1:])
-    return bool(re.search(r"-{2,}|_exit=|(?:^|\s|=)\$[?{]|PIPESTATUS", rest))
-
-
-def summarize_shell_command(command: str) -> str:
-    """Compact shell wrapper/plumbing for display while preserving raw command elsewhere."""
-    original = _oneline(command)
-    if not original:
-        return ""
-
-    segments = _split_shell_compound(original)
-    if len(segments) <= 1:
-        return _clean_shell_segment(segments[0] if segments else original) or original
-
-    core: list[str] = []
-    for segment in segments:
-        cleaned = _clean_shell_segment(segment)
-        head = _shell_head_word(cleaned)
-        if cleaned and head not in _SHELL_SILENT_HEADS and not _is_shell_boundary_echo(cleaned):
-            core.append(cleaned)
-
-    if not core:
-        return original
-    if len(core) == 1:
-        return core[0]
-
-    count = len(core) - 1
-    return f"{core[0]} + {count} {'command' if count == 1 else 'commands'}"
-
-
-def _read_file_line_label(args: dict) -> str:
-    offset = args.get("offset")
-    limit = args.get("limit")
-    if not isinstance(offset, int) or offset <= 0:
-        return ""
-    if not isinstance(limit, int) or limit <= 1:
-        return f"L{offset}"
-    return f"L{offset}-{offset + limit - 1}"
-
-
-def redact_browser_typed_text_for_display(value: Any, typed_text: Any) -> Any:
-    """Apply secret redaction to browser_type text in display-facing payloads.
-
-    Backends sometimes echo the attempted input in error strings or fallback
-    metadata.  When the raw typed value contains a recognizable secret (API
-    key, token, JWT, etc.) the redacted form differs from the raw value, so we
-    replace every occurrence of the raw value with its redacted form before a
-    browser_type result reaches logs, callbacks, the model, or chat history.
-
-    Normal typed text (search queries, addresses, form fields) matches no
-    secret pattern, so it passes through unchanged and stays readable.
-
-    Redaction is forced here regardless of the global ``security.redact_secrets``
-    preference: a typed credential leaking into chat history is a security
-    boundary, not mere log hygiene.
-    """
-    if typed_text is None:
-        return value
-    needle = str(typed_text)
-    if needle == "":
-        return value
-    redacted = redact_sensitive_text(needle, force=True)
-    if redacted == needle:
-        # Nothing secret-looking in the typed text; leave payload untouched.
-        return value
-    if isinstance(value, str):
-        return value.replace(needle, redacted)
-    if isinstance(value, dict):
-        return {
-            key: redact_browser_typed_text_for_display(item, typed_text)
-            for key, item in value.items()
-        }
-    if isinstance(value, list):
-        return [redact_browser_typed_text_for_display(item, typed_text) for item in value]
-    if isinstance(value, tuple):
-        return tuple(redact_browser_typed_text_for_display(item, typed_text) for item in value)
-    return value
-
-
-def redact_tool_args_for_display(tool_name: str, args: dict | None) -> dict | None:
-    """Return a copy of tool args safe for logs/progress UI.
-
-    For ``browser_type`` the ``text`` argument is run through the same
-    secret-pattern redactor used for logs.  Recognizable credentials (API
-    keys, tokens) are masked before the value reaches tool progress
-    notifications; normal typed text is left intact for debuggability.
-    """
-    if not isinstance(args, dict):
-        return args
-    if tool_name == "browser_type" and isinstance(args.get("text"), str):
-        safe_args = dict(args)
-        safe_args["text"] = redact_sensitive_text(args["text"], force=True)
-        return safe_args
-    return args
-
-
 def _delegate_task_goal_parts(tasks: Any, *, per_goal_len: int) -> tuple[int, list[str]]:
     if not isinstance(tasks, list):
         return 0, []
@@ -419,14 +200,13 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -
         max_len = _tool_preview_max_len
     if not args:
         return None
-    args = redact_tool_args_for_display(tool_name, args) or args
     primary_args = {
         "terminal": "command", "web_search": "query", "web_extract": "urls",
         "read_file": "path", "write_file": "path", "patch": "path",
         "search_files": "pattern", "browser_navigate": "url",
         "browser_click": "ref", "browser_type": "text",
         "image_generate": "prompt", "text_to_speech": "text",
-        "vision_analyze": "question",
+        "vision_analyze": "question", "mixture_of_agents": "user_prompt",
         "skill_view": "name", "skills_list": "category",
         "cronjob": "action",
         "execute_code": "code", "delegate_task": "goal",
@@ -473,23 +253,6 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -
         else:
             return f"planning {len(todos_arg)} task(s)"
 
-    if tool_name in {"terminal", "execute_code"}:
-        key = "code" if tool_name == "execute_code" else "command"
-        command = args.get(key)
-        if command is None:
-            return None
-        preview = summarize_shell_command(str(command))
-        return _truncate_preview(preview, max_len) if preview else None
-
-    if tool_name == "read_file":
-        path = args.get("path") or args.get("file") or args.get("filepath")
-        if path is None:
-            return None
-        label = Path(str(path).replace("\\", "/")).name or str(path)
-        line_label = _read_file_line_label(args)
-        preview = f"{label} {line_label}".strip()
-        return _truncate_preview(preview, max_len) if preview else None
-
     if tool_name == "session_search":
         query = _oneline(args.get("query", ""))
         return f"recall: \"{query[:25]}{'...' if len(query) > 25 else ''}\""
@@ -1143,7 +906,6 @@ def get_cute_tool_message(
     When *result* is provided the line is checked for failure indicators.
     Failed tool calls get a red prefix and an informational suffix.
     """
-    args = redact_tool_args_for_display(tool_name, args) or args
     dur = f"{duration:.1f}s"
     is_failure, failure_suffix = _detect_tool_failure(tool_name, result)
     skin_prefix = get_skin_tool_prefix()
@@ -1181,7 +943,7 @@ def get_cute_tool_message(
             return _wrap(f"┊ 📄 fetch     {_trunc(domain, 35)}{extra}  {dur}")
         return _wrap(f"┊ 📄 fetch     pages  {dur}")
     if tool_name == "terminal":
-        return _wrap(f"┊ 💻 $         {_trunc(build_tool_preview(tool_name, args) or args.get('command', ''), 42)}  {dur}")
+        return _wrap(f"┊ 💻 $         {_trunc(args.get('command', ''), 42)}  {dur}")
     if tool_name == "process":
         action = args.get("action", "?")
         sid = args.get("session_id", "")[:12]
@@ -1189,7 +951,7 @@ def get_cute_tool_message(
                   "wait": f"wait {sid}", "kill": f"kill {sid}", "write": f"write {sid}", "submit": f"submit {sid}"}
         return _wrap(f"┊ ⚙️  proc      {labels.get(action, f'{action} {sid}')}  {dur}")
     if tool_name == "read_file":
-        return _wrap(f"┊ 📖 read      {_trunc(build_tool_preview(tool_name, args) or args.get('path', ''), 42)}  {dur}")
+        return _wrap(f"┊ 📖 read      {_path(args.get('path', ''))}  {dur}")
     if tool_name == "write_file":
         return _wrap(f"┊ ✍️  write     {_path(args.get('path', ''))}  {dur}")
     if tool_name == "patch":
@@ -1275,6 +1037,8 @@ def get_cute_tool_message(
         return _wrap(f"┊ 🔊 speak     {_trunc(args.get('text', ''), 30)}  {dur}")
     if tool_name == "vision_analyze":
         return _wrap(f"┊ 👁️  vision    {_trunc(args.get('question', ''), 30)}  {dur}")
+    if tool_name == "mixture_of_agents":
+        return _wrap(f"┊ 🧠 reason    {_trunc(args.get('user_prompt', ''), 30)}  {dur}")
     if tool_name == "send_message":
         return _wrap(f"┊ 📨 send      {args.get('target', '?')}: \"{_trunc(args.get('message', ''), 25)}\"  {dur}")
     if tool_name == "cronjob":

agent/error_classifier.py

@@ -717,26 +717,6 @@ def classify_api_error(
 
     is_disconnect = any(p in error_msg for p in _SERVER_DISCONNECT_PATTERNS)
     if is_disconnect and not status_code:
-        # Reasoning-model override: a transport disconnect on a reasoning
-        # model is much more likely the upstream proxy idle-killing a
-        # long thinking stream than a true context overflow — even on
-        # large sessions.  The default disconnect+large-session routing
-        # below would otherwise send the user into the compression
-        # branch (should_compress=True) and silently delete
-        # conversation history on a phantom context-length error.
-        # Reasoning models have multi-minute thinking phases that
-        # routinely exceed the cloud gateway's idle window (NVIDIA
-        # NIM ~120s — first-party repro at NVIDIA/NemoClaw#4846;
-        # OpenAI worker / Anthropic stream-idle similar).  The
-        # per-reasoning-model stale-timeout floor in
-        # agent/reasoning_timeouts.py raises the stale-detector
-        # threshold to tolerate long thinking, so a true
-        # transport-layer failure here is recoverable via the retry
-        # path — not via context compression.  Reclassify as timeout.
-        # (Part 1 of Fixes #52310.)
-        from agent.reasoning_timeouts import get_reasoning_stale_timeout_floor
-        if get_reasoning_stale_timeout_floor(model) is not None:
-            return _result(FailoverReason.timeout, retryable=True)
         # 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.

agent/learn_prompt.py

@@ -28,35 +28,15 @@ from __future__ import annotations
 # (HARDLINE)" and the hermes-agent-dev new-skill salvage reference. Embedded in
 # the prompt so the agent authors skills the way a maintainer would by hand.
 _AUTHORING_STANDARDS = """\
-Follow the Hermes skill-authoring standards exactly. These are the same
-HARDLINE rules a maintainer enforces in review:
+Follow the Hermes skill-authoring standards exactly:
 
 Frontmatter:
 - name: lowercase-hyphenated, <=64 chars, no spaces.
-- description: ONE sentence, **<=60 characters**, ends with a period. State the
+- description: ONE sentence, <=60 characters, ends with a period. State the
   capability, not the implementation. No marketing words (powerful,
-  comprehensive, seamless, advanced, robust). Do NOT repeat the skill name. If
-  the description contains a colon, wrap the whole value in double quotes.
-  This is the most-violated rule and it is NOT cosmetic: the system-prompt
-  skill index truncates the description to 60 chars and loads it every
-  session, so anything past char 60 is silently cut and never routes. After
-  you write the description, COUNT the characters; if it is over 60, cut it
-  down before saving — do not ship a sentence and hope.
-    Good (<=60): `Search arXiv papers by keyword, author, or ID.`
-    Bad (123):   `A comprehensive skill that lets the agent search arXiv for
-                  academic papers using keywords, authors, and categories.`
+  comprehensive, seamless, advanced). Do NOT repeat the skill name. If the
+  description contains a colon, wrap the whole value in double quotes.
 - version: 0.1.0
-- author: always the literal value `Hermes`. NEVER fill it from the host
-  environment — the OS/login username (e.g. the `user=` line in your
-  environment hints), git config, or any identity you can probe must not be
-  written. Skills get shared and published, so an environment-derived name is
-  a privacy leak the user never opted into; the skill names itself as Hermes.
-- platforms: declare `[macos]`, `[linux]`, and/or `[windows]` IF the skill
-  uses OS-bound primitives (osascript/apt/systemctl => the matching OS; /proc,
-  os.setsid, signal.SIGKILL => linux; fcntl/termios => POSIX). Prefer fixing it
-  cross-platform first (tempfile.gettempdir(), pathlib.Path, psutil); gate only
-  when the dependency is genuinely platform-bound. Omit the field for portable
-  skills.
 - metadata.hermes.tags: a few Capitalized, Relevant, Tags.
 
 Body section order (omit a section only if it genuinely has no content):
@@ -72,16 +52,10 @@ Body section order (omit a section only if it genuinely has no content):
 
 Hermes-tool framing (this is what makes it a skill, not shell docs):
 - Frame running scripts as "invoke through the `terminal` tool".
-- Reference Hermes tools by name in backticks: `terminal`, `read_file`,
-  `write_file`, `search_files`, `patch`, `web_extract`, `web_search`,
-  `vision_analyze`, `browser_navigate`, `delegate_task`, `image_generate`,
-  `text_to_speech`, `cronjob`, `memory`, `skill_view`, `execute_code`.
-- Do NOT name shell utilities the agent already has wrapped: say `read_file`
-  not cat/head/tail, `search_files` not grep/rg/find/ls, `patch` not sed/awk,
-  `web_extract` not curl-to-scrape, `write_file` not echo>file or heredocs.
-- Third-party CLIs (ffmpeg, gh, an SDK) are fine inside a script file, but the
-  prose still frames them as "invoke through the `terminal` tool". If the
-  skill needs an MCP server, name it and document its setup in Prerequisites.
+- Use `read_file` (not cat/head/tail), `search_files` (not grep/find/ls),
+  `patch` (not sed/awk), `web_extract` (not curl-to-scrape),
+  `vision_analyze` for images. Reference these tools by name in backticks.
+- Do NOT name shell utilities the agent already has wrapped.
 
 Quality bar:
 - Prefer exact commands, endpoint URLs, function signatures, and config keys
@@ -92,8 +66,7 @@ Quality bar:
 - Don't write a router/index/hub skill that only points at other skills.
 - Larger scripts/parsers belong in a `scripts/` file (add via
   `skill_manage` write_file), referenced from SKILL.md by relative path — not
-  inlined for the agent to re-type every run. References go in `references/`,
-  templates in `templates/`."""
+  inlined for the agent to re-type every run."""
 
 
 def build_learn_prompt(user_request: str) -> str:

agent/memory_manager.py

@@ -46,39 +46,6 @@ logger = logging.getLogger(__name__)
 _SYNC_DRAIN_TIMEOUT_S = 5.0
 
 
-def normalize_tool_schema(schema: Any) -> Optional[Dict[str, Any]]:
-    """Return a function-tool dict with a resolvable top-level ``name``.
-
-    Context engines and memory providers expose tool schemas via
-    ``get_tool_schemas()``. The expected shape is a bare function schema
-    (``{"name": ..., "description": ..., "parameters": ...}``) which callers
-    wrap as ``{"type": "function", "function": schema}``.
-
-    Some providers instead return an entry that is *already* in OpenAI tool
-    form (``{"type": "function", "function": {"name": ...}}``). Wrapping that
-    a second time produces ``{"type": "function", "function": {"type":
-    "function", "function": {...}}}`` whose ``function`` has no top-level
-    ``name``. Strict providers (e.g. DeepSeek) reject the *entire* request
-    with ``tools[N].function: missing field name`` (HTTP 400), so one bad
-    schema disables the whole toolset and breaks every turn (#47707).
-
-    This helper normalizes both shapes to the bare function schema and
-    returns ``None`` for anything without a resolvable name, so callers can
-    skip-with-warning rather than appending a nameless tool.
-    """
-    if not isinstance(schema, dict):
-        return None
-    # Unwrap an already-wrapped OpenAI tool entry.
-    if schema.get("type") == "function" and isinstance(schema.get("function"), dict):
-        schema = schema["function"]
-        if not isinstance(schema, dict):
-            return None
-    name = schema.get("name", "")
-    if not name or not isinstance(name, str):
-        return None
-    return schema
-
-
 def memory_provider_tools_enabled(enabled_toolsets: Optional[List[str]]) -> bool:
     """Return whether external memory-provider tools should be exposed."""
     if enabled_toolsets is None:
@@ -125,17 +92,11 @@ def inject_memory_provider_tools(agent: Any) -> int:
         agent.valid_tool_names = valid_tool_names
 
     added = 0
-    for raw_schema in get_schemas():
-        schema = normalize_tool_schema(raw_schema)
-        if schema is None:
-            logger.warning(
-                "Memory provider returned a tool schema with no resolvable "
-                "name; skipping to avoid poisoning the request (%r)",
-                raw_schema,
-            )
+    for schema in get_schemas():
+        if not isinstance(schema, dict):
             continue
-        tool_name = schema["name"]
-        if tool_name in existing_tool_names:
+        tool_name = schema.get("name", "")
+        if not tool_name or tool_name in existing_tool_names:
             continue
         tools.append({"type": "function", "function": schema})
         valid_tool_names.add(tool_name)
@@ -409,11 +370,8 @@ class MemoryManager:
         _core_tool_names = set(_HERMES_CORE_TOOLS)
 
         # Index tool names → provider for routing
-        for raw_schema in provider.get_tool_schemas():
-            schema = normalize_tool_schema(raw_schema)
-            if schema is None:
-                continue
-            tool_name = schema["name"]
+        for schema in provider.get_tool_schemas():
+            tool_name = schema.get("name", "")
             if tool_name in _core_tool_names:
                 logger.warning(
                     "Memory provider '%s' tool '%s' shadows a reserved core "
@@ -700,19 +658,11 @@ class MemoryManager:
         seen = set()
         for provider in self._providers:
             try:
-                for raw_schema in provider.get_tool_schemas():
-                    schema = normalize_tool_schema(raw_schema)
-                    if schema is None:
-                        logger.warning(
-                            "Memory provider '%s' returned a tool schema with "
-                            "no resolvable name; skipping (%r)",
-                            provider.name, raw_schema,
-                        )
-                        continue
-                    name = schema["name"]
+                for schema in provider.get_tool_schemas():
+                    name = schema.get("name", "")
                     if name in _core_tool_names:
                         continue
-                    if name not in seen:
+                    if name and name not in seen:
                         schemas.append(schema)
                         seen.add(name)
             except Exception as e:

agent/message_sanitization.py

@@ -279,38 +279,6 @@ def _repair_tool_call_arguments(raw_args: str, tool_name: str = "?") -> str:
     return "{}"
 
 
-def close_interrupted_tool_sequence(messages: list, final_response: Any = None) -> bool:
-    """Append a synthetic assistant turn when an interrupted tail is a tool result.
-
-    A turn cut short by ``/stop`` can leave the transcript ending on a raw
-    ``tool`` message (a tool finished, or its execution was cancelled, but the
-    model never streamed a closing assistant turn). Persisting that tail means
-    the next user message lands as ``… tool → user`` — a role-alternation
-    violation that strict providers (Gemini, Claude) react to by hallucinating
-    a continuation of the user's message and ignoring prior context, which
-    reads to the user as "lost context" (#48879).
-
-    ``finalize_turn`` closes this on the happy interrupt path, but the
-    retry/backoff/error interrupt aborts in ``conversation_loop`` ``return``
-    early and never reach it — this shared helper closes the sequence on all of
-    them. ``final_response`` is usually empty on an interrupt, so an explicit
-    placeholder is used rather than an empty-content assistant turn.
-
-    Mutates ``messages`` in place. Returns True if a closing turn was appended.
-    """
-    if not messages:
-        return False
-    last = messages[-1]
-    if not isinstance(last, dict) or last.get("role") != "tool":
-        return False
-    text = final_response if isinstance(final_response, str) else ""
-    messages.append({
-        "role": "assistant",
-        "content": text.strip() or "Operation interrupted.",
-    })
-    return True
-
-
 def _strip_non_ascii(text: str) -> str:
     """Remove non-ASCII characters, replacing with closest ASCII equivalent or removing.
 
@@ -463,7 +431,6 @@ def _sanitize_structure_non_ascii(payload: Any) -> bool:
 
 __all__ = [
     "_SURROGATE_RE",
-    "close_interrupted_tool_sequence",
     "_sanitize_surrogates",
     "_sanitize_structure_surrogates",
     "_sanitize_messages_surrogates",

agent/moa_loop.py

@@ -1,306 +0,0 @@
-"""Mixture-of-Agents runtime helpers for /moa turns.
-
-The slash command is deliberately not a model tool. It marks one user turn as
-MoA-enabled; the normal Hermes agent loop still owns tool calling and turn
-termination, while this module gathers reference-model context before each model
-iteration.
-"""
-
-from __future__ import annotations
-
-import logging
-from concurrent.futures import ThreadPoolExecutor
-from typing import Any
-
-from agent.auxiliary_client import call_llm
-from agent.transports import get_transport
-
-logger = logging.getLogger(__name__)
-
-# Upper bound on concurrent reference-model calls. References are independent
-# advisory calls (no tools, no inter-dependence), so we fan them out the same
-# way delegate_task runs a batch: all in flight at once, results collected when
-# every reference finishes. Presets rarely list more than a handful of
-# references; this cap just protects against a pathologically large preset
-# opening dozens of sockets at once.
-_MAX_REFERENCE_WORKERS = 8
-
-
-def _slot_label(slot: dict[str, str]) -> str:
-    return f"{slot.get('provider', '').strip()}:{slot.get('model', '').strip()}"
-
-
-def _run_reference(
-    slot: dict[str, str],
-    ref_messages: list[dict[str, Any]],
-    *,
-    temperature: float,
-    max_tokens: int,
-) -> tuple[str, str]:
-    """Call one reference model and return ``(label, text)``.
-
-    Never raises: a failed reference becomes a labelled note so the aggregator
-    can still act with partial context. Designed to run inside a thread pool —
-    ``call_llm`` is synchronous/blocking, so threads (not asyncio) are the right
-    concurrency primitive, mirroring ``delegate_task``'s batch fan-out.
-    """
-    label = _slot_label(slot)
-    try:
-        response = call_llm(
-            task="moa_reference",
-            provider=slot["provider"],
-            model=slot["model"],
-            messages=ref_messages,
-            temperature=temperature,
-            max_tokens=max_tokens,
-        )
-        return label, _extract_text(response) or "(empty response)"
-    except Exception as exc:
-        logger.warning("MoA reference model %s failed: %s", label, exc)
-        return label, f"[failed: {exc}]"
-
-
-def _run_references_parallel(
-    reference_models: list[dict[str, str]],
-    ref_messages: list[dict[str, Any]],
-    *,
-    temperature: float,
-    max_tokens: int,
-) -> list[tuple[str, str]]:
-    """Fan out all reference models in parallel, returning outputs in order.
-
-    Like ``delegate_task``'s batch mode, every reference is dispatched at once
-    and we block until all of them finish before handing the joined results to
-    the aggregator. Output order matches ``reference_models`` so the
-    ``Reference {idx}`` labelling stays stable. MoA presets that reference
-    another MoA preset are skipped here (recursion guard) with a labelled note.
-    """
-    if not reference_models:
-        return []
-
-    results: list[tuple[str, str] | None] = [None] * len(reference_models)
-    futures = {}
-    workers = min(_MAX_REFERENCE_WORKERS, len(reference_models))
-    with ThreadPoolExecutor(max_workers=workers) as executor:
-        for idx, slot in enumerate(reference_models):
-            if slot.get("provider") == "moa":
-                results[idx] = (
-                    _slot_label(slot),
-                    "[skipped: MoA presets cannot recursively reference MoA]",
-                )
-                continue
-            futures[
-                executor.submit(
-                    _run_reference,
-                    slot,
-                    ref_messages,
-                    temperature=temperature,
-                    max_tokens=max_tokens,
-                )
-            ] = idx
-        # Collect every reference before returning — the aggregator needs the
-        # complete set, so there is no early-exit / first-completed path here.
-        for future, idx in futures.items():
-            results[idx] = future.result()
-
-    return [r for r in results if r is not None]
-
-
-def _reference_messages(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
-    """Build an advisory-safe view of the conversation for reference models.
-
-    Reference calls are advisory: they never call tools and never emit the
-    ``tool_calls`` the main model did. Replaying the full transcript verbatim
-    (a) re-bills the ~8K-token Hermes system prompt per reference per
-    iteration and (b) risks 400s from strict providers (Mistral, Fireworks)
-    that reject orphan ``tool`` messages or ``tool_calls`` the reference never
-    produced. We keep only the user/assistant *text* turns, dropping the
-    system prompt, any ``tool``-role messages, and any ``tool_calls`` payloads.
-    """
-    trimmed: list[dict[str, Any]] = []
-    for msg in messages:
-        role = msg.get("role")
-        if role not in ("user", "assistant"):
-            # Drop system prompt and tool-result messages.
-            continue
-        content = msg.get("content")
-        if not isinstance(content, str):
-            # Skip non-text (multimodal/tool-call-only) assistant turns.
-            if not content:
-                continue
-        text = content if isinstance(content, str) else ""
-        if role == "assistant" and not text.strip():
-            # Assistant turn that was purely tool calls — nothing advisory.
-            continue
-        trimmed.append({"role": role, "content": text})
-    if not trimmed:
-        # Degenerate case (e.g. first turn was stripped): fall back to a
-        # minimal user turn so the reference still has something to answer.
-        for msg in reversed(messages):
-            if msg.get("role") == "user" and isinstance(msg.get("content"), str):
-                return [{"role": "user", "content": msg["content"]}]
-    return trimmed
-
-
-
-def _extract_text(response: Any) -> str:
-    try:
-        transport = get_transport("chat_completions")
-        if transport is None:
-            raise RuntimeError("chat_completions transport unavailable")
-        normalized = transport.normalize_response(response)
-        text = (normalized.content or "").strip()
-        if text:
-            return text
-    except Exception:
-        pass
-    try:
-        content = response.choices[0].message.content
-        return (content or "").strip()
-    except Exception:
-        return ""
-
-
-def aggregate_moa_context(
-    *,
-    user_prompt: str,
-    api_messages: list[dict[str, Any]],
-    reference_models: list[dict[str, str]],
-    aggregator: dict[str, str],
-    temperature: float = 0.6,
-    aggregator_temperature: float = 0.4,
-    max_tokens: int = 4096,
-) -> str:
-    """Run configured reference models and synthesize their advice.
-
-    Failures are returned as model-specific notes instead of aborting the normal
-    agent loop; the main model can still act with partial context.
-    """
-    reference_outputs: list[tuple[str, str]] = []
-    ref_messages = _reference_messages(api_messages)
-    reference_outputs = _run_references_parallel(
-        reference_models,
-        ref_messages,
-        temperature=temperature,
-        max_tokens=max_tokens,
-    )
-
-    joined = "\n\n".join(
-        f"Reference {idx} — {label}:\n{text}"
-        for idx, (label, text) in enumerate(reference_outputs, start=1)
-    )
-    synth_prompt = (
-        "You are the aggregator in a Mixture of Agents process. Synthesize the "
-        "reference responses into concise, actionable guidance for the main "
-        "Hermes agent. Focus on next steps, tool-use strategy, risks, and any "
-        "disagreements. Do not answer the user directly unless that is all that "
-        "is needed; produce context the main agent should use in its normal loop.\n\n"
-        f"Original user prompt:\n{user_prompt}\n\n"
-        f"Reference responses:\n{joined}"
-    )
-
-    agg_label = _slot_label(aggregator)
-    try:
-        response = call_llm(
-            task="moa_aggregator",
-            provider=aggregator["provider"],
-            model=aggregator["model"],
-            messages=[{"role": "user", "content": synth_prompt}],
-            temperature=aggregator_temperature,
-            max_tokens=max_tokens,
-        )
-        synthesis = _extract_text(response)
-    except Exception as exc:
-        logger.warning("MoA aggregator model %s failed: %s", agg_label, exc)
-        synthesis = ""
-
-    if not synthesis:
-        synthesis = joined
-
-    return (
-        "[Mixture of Agents context — use this as private guidance for the "
-        "normal Hermes agent loop. You may call tools, continue reasoning, or "
-        "finish normally.]\n"
-        f"Aggregator: {agg_label}\n"
-        f"References: {', '.join(_slot_label(slot) for slot in reference_models)}\n\n"
-        f"{synthesis.strip()}"
-    )
-
-
-class MoAChatCompletions:
-    """OpenAI-chat-compatible facade where the aggregator is the acting model."""
-
-    def __init__(self, preset_name: str):
-        self.preset_name = preset_name or "default"
-
-    def create(self, **api_kwargs: Any) -> Any:
-        from hermes_cli.config import load_config
-        from hermes_cli.moa_config import resolve_moa_preset
-
-        preset = resolve_moa_preset(load_config().get("moa") or {}, self.preset_name)
-        messages = list(api_kwargs.get("messages") or [])
-        reference_models = preset.get("reference_models") or []
-        aggregator = preset.get("aggregator") or {}
-        max_tokens = int(preset.get("max_tokens", api_kwargs.get("max_tokens") or 4096) or 4096)
-        temperature = float(preset.get("reference_temperature", 0.6) or 0.6)
-        aggregator_temperature = float(preset.get("aggregator_temperature", api_kwargs.get("temperature") or 0.4) or 0.4)
-
-        # When the preset is disabled, skip the reference fan-out and let the
-        # configured aggregator act alone — it is the preset's acting model, so
-        # a disabled MoA preset is simply "use the aggregator directly."
-        if not preset.get("enabled", True):
-            reference_models = []
-
-        reference_outputs: list[tuple[str, str]] = []
-        ref_messages = _reference_messages(messages)
-        reference_outputs = _run_references_parallel(
-            reference_models,
-            ref_messages,
-            temperature=temperature,
-            max_tokens=max_tokens,
-        )
-
-        agg_messages = [dict(m) for m in messages]
-        if reference_outputs:
-            joined = "\n\n".join(
-                f"Reference {idx} — {label}:\n{text}"
-                for idx, (label, text) in enumerate(reference_outputs, start=1)
-            )
-            guidance = (
-                "[Mixture of Agents reference context]\n"
-                f"Preset: {self.preset_name}\n"
-                f"Aggregator/acting model: {_slot_label(aggregator)}\n"
-                f"References: {', '.join(label for label, _ in reference_outputs)}\n\n"
-                "Use the reference responses below as private context. You are the aggregator and acting model: "
-                "answer the user directly or call tools as needed.\n\n"
-                f"{joined}"
-            )
-            for msg in reversed(agg_messages):
-                if msg.get("role") == "user" and isinstance(msg.get("content"), str):
-                    msg["content"] = msg["content"] + "\n\n" + guidance
-                    break
-            else:
-                agg_messages.append({"role": "user", "content": guidance})
-
-        if aggregator.get("provider") == "moa":
-            raise RuntimeError("MoA aggregator cannot be another MoA preset")
-        agg_kwargs = dict(api_kwargs)
-        agg_kwargs["messages"] = agg_messages
-        agg_kwargs["model"] = aggregator.get("model")
-        agg_kwargs["temperature"] = aggregator_temperature
-        return call_llm(
-            task="moa_aggregator",
-            provider=aggregator.get("provider"),
-            model=aggregator.get("model"),
-            messages=agg_messages,
-            temperature=aggregator_temperature,
-            max_tokens=agg_kwargs.get("max_tokens"),
-            tools=agg_kwargs.get("tools"),
-            extra_body=agg_kwargs.get("extra_body"),
-        )
-
-
-class MoAClient:
-    def __init__(self, preset_name: str):
-        self.chat = type("_MoAChat", (), {})()
-        self.chat.completions = MoAChatCompletions(preset_name)

agent/pet/generate/__init__.py

@@ -1,29 +0,0 @@
-"""Pet generation — base-draft → hatch pipeline.
-
-Public surface used by the gateway RPCs, the CLI ``hermes pets generate``
-command, and tests:
-
-- :func:`generate_base_drafts` / :func:`hatch_pet` — the two-step flow.
-- :class:`HatchResult`, :class:`GenerationError`.
-- :mod:`atlas` — deterministic frame extraction + atlas composition/validation.
-
-Image generation is delegated to the active reference-capable
-:class:`~agent.image_gen_provider.ImageGenProvider` (OpenAI gpt-image-2 or Krea);
-atlas assembly is fully deterministic so it's testable without any API calls.
-"""
-
-from __future__ import annotations
-
-from agent.pet.generate.imagegen import GenerationError
-from agent.pet.generate.orchestrate import (
-    HatchResult,
-    generate_base_drafts,
-    hatch_pet,
-)
-
-__all__ = [
-    "GenerationError",
-    "HatchResult",
-    "generate_base_drafts",
-    "hatch_pet",
-]

agent/pet/generate/imagegen.py

@@ -1,251 +0,0 @@
-"""Thin image-generation layer for pet sprites.
-
-Wraps the active :class:`~agent.image_gen_provider.ImageGenProvider` with the
-two things sprite generation needs that the agent-facing ``image_generate`` tool
-doesn't expose: **N variants** (loop) and **reference-image grounding** (so each
-animation row stays the same character as the chosen base).
-
-Reference grounding only works on providers that support it — currently OpenAI
-``gpt-image-2`` (image edits) and Krea (style references). We resolve to one of
-those and surface a clear, actionable error otherwise rather than silently
-producing an ungrounded, drifting pet.
-"""
-
-from __future__ import annotations
-
-import logging
-import os
-from dataclasses import dataclass
-from pathlib import Path
-
-logger = logging.getLogger(__name__)
-
-# Providers that can ground generation on a reference image, in preference order
-# (Nous Portal → OpenAI → OpenRouter → …). OpenRouter/Nous run a quality-first
-# model chain and may fall back depending on account access and endpoint behavior,
-# so fidelity can vary by configured backend + model availability.
-_REF_CAPABLE = ("nous", "openai", "openai-codex", "openrouter", "krea")
-
-# Friendly display label per reference-capable provider, surfaced in the desktop
-# pet-gen picker.
-_PROVIDER_LABELS: dict[str, str] = {
-    "nous": "Nous Portal",
-    "openrouter": "OpenRouter",
-    "openai": "OpenAI",
-    "openai-codex": "OpenAI (Codex)",
-    "krea": "Krea",
-}
-
-
-def _forced_provider_from_env() -> str | None:
-    """Optional QA override to force a pet-gen backend.
-
-    `HERMES_PET_IMAGE_PROVIDER=<name>` (e.g. `openrouter`) bypasses the normal
-    active/default provider resolution for pet generation only. Unknown values are
-    ignored so existing users are unaffected.
-    """
-    forced = os.environ.get("HERMES_PET_IMAGE_PROVIDER", "").strip().lower()
-    return forced if forced in _REF_CAPABLE else None
-
-
-class GenerationError(RuntimeError):
-    """Raised on any image-generation failure (no provider, API error, IO)."""
-
-
-@dataclass(frozen=True)
-class SpriteProvider:
-    """Resolved provider plus whether it can take reference images."""
-
-    name: str
-    provider: object
-    supports_references: bool
-
-
-def _discover() -> None:
-    try:
-        from hermes_cli.plugins import _ensure_plugins_discovered
-
-        _ensure_plugins_discovered()
-    except Exception as exc:  # noqa: BLE001 - discovery is best-effort
-        logger.debug("image-gen plugin discovery failed: %s", exc)
-
-
-def resolve_provider(*, require_references: bool = True, prefer: str | None = None) -> SpriteProvider:
-    """Pick the image provider to use for sprite work.
-
-    Preference: an explicit *prefer* choice (the desktop pet-gen picker) when it's
-    reference-capable and configured, then the configured/active provider when
-    it's reference-capable, else the first available reference-capable provider.
-    With *require_references* off we fall back to any available provider (used for
-    prompt-only base drafts).
-    """
-    _discover()
-    from agent.image_gen_registry import get_active_provider, get_provider
-
-    # QA override: force one provider for pet-gen iteration regardless of the
-    # globally active image_gen backend.
-    forced = _forced_provider_from_env()
-    if forced:
-        chosen = get_provider(forced)
-        if chosen is not None and chosen.is_available():
-            return SpriteProvider(name=forced, provider=chosen, supports_references=True)
-
-    # An explicit user pick wins when it's reference-capable and has credentials;
-    # otherwise we ignore it and fall through to the normal resolution.
-    if prefer:
-        chosen = get_provider(prefer)
-        if prefer in _REF_CAPABLE and chosen is not None and chosen.is_available():
-            return SpriteProvider(name=prefer, provider=chosen, supports_references=True)
-
-    # Configured / active provider first.
-    active = None
-    try:
-        active = get_active_provider()
-    except Exception:  # noqa: BLE001
-        active = None
-    if active is not None:
-        name = getattr(active, "name", "")
-        if name in _REF_CAPABLE and active.is_available():
-            return SpriteProvider(name=name, provider=active, supports_references=True)
-
-    # Any available reference-capable provider.
-    for name in _REF_CAPABLE:
-        provider = get_provider(name)
-        if provider is not None and provider.is_available():
-            return SpriteProvider(name=name, provider=provider, supports_references=True)
-
-    if not require_references and active is not None and active.is_available():
-        return SpriteProvider(
-            name=getattr(active, "name", "unknown"), provider=active, supports_references=False
-        )
-
-    raise GenerationError(
-        "Pet generation needs an image backend that supports reference images. "
-        "Open `hermes tools` → Image Generation and configure Nous Portal, "
-        "OpenRouter, or OpenAI (gpt-image-2) with an API key."
-    )
-
-
-def list_sprite_providers() -> list[dict]:
-    """The reference-capable providers available to pick for pet generation.
-
-    Returns ``[{name, label, default}]`` for every ref-capable provider the user
-    actually has credentials for, in preference order, marking the one
-    :func:`resolve_provider` would choose with no explicit preference. Empty when
-    none is configured (the picker hides itself). Best-effort: discovery hiccups
-    yield an empty list.
-    """
-    _discover()
-    from agent.image_gen_registry import get_provider
-
-    try:
-        default_name = resolve_provider(require_references=True).name
-    except GenerationError:
-        default_name = ""
-
-    out: list[dict] = []
-    for name in _REF_CAPABLE:
-        provider = get_provider(name)
-        if provider is None or not provider.is_available():
-            continue
-        out.append(
-            {
-                "name": name,
-                "label": _PROVIDER_LABELS.get(name, name),
-                "default": name == default_name,
-            }
-        )
-    return out
-
-
-def _save_local(image_ref: str, *, prefix: str) -> Path:
-    """Return a local path for *image_ref*, downloading it if it's a URL."""
-    if image_ref.startswith(("http://", "https://")):
-        from agent.image_gen_provider import save_url_image
-
-        return Path(save_url_image(image_ref, prefix=prefix))
-    return Path(image_ref)
-
-
-def _rejected_background(error: str) -> bool:
-    """True when a provider error is specifically about the ``background`` param.
-
-    Transparent backgrounds are a per-model capability (e.g. some gpt-image tiers
-    reject ``background=transparent`` outright). We detect that one rejection so
-    we can retry without the flag rather than failing the whole pet — our chroma
-    key pass makes the result transparent regardless.
-    """
-    lowered = (error or "").lower()
-    return "background" in lowered and ("not supported" in lowered or "transparent" in lowered)
-
-
-def generate(
-    prompt: str,
-    *,
-    n: int = 1,
-    reference_images: list[Path] | None = None,
-    provider: SpriteProvider | None = None,
-    prefix: str = "pet_gen",
-    aspect_ratio: str = "square",
-) -> list[Path]:
-    """Generate *n* sprite images and return their local paths.
-
-    *reference_images* grounds the output on a base image (required for rows).
-    *aspect_ratio* picks the canvas: ``"square"`` for single-character base
-    drafts, ``"landscape"`` for multi-frame row strips (the wider 1536px canvas
-    gives every frame real horizontal room so winged poses don't have to be
-    shrunk to avoid touching their neighbors).
-    We *ask* for a transparent background, but fall back to an opaque generation
-    (cleaned up downstream by the chroma-key pass) on models that reject the
-    flag. Raises :class:`GenerationError` if nothing usable comes back.
-    """
-    sprite = provider or resolve_provider(require_references=bool(reference_images))
-    if reference_images and not sprite.supports_references:
-        raise GenerationError(
-            f"image backend '{sprite.name}' cannot use reference images; "
-            "configure OpenAI gpt-image-2 or Krea for pet generation"
-        )
-
-    refs = [str(p) for p in (reference_images or [])]
-
-    def _run(extra: dict) -> tuple[Path | None, str]:
-        kwargs: dict = {"aspect_ratio": aspect_ratio, **extra}
-        if refs:
-            # Providers disagree on the ref kwarg name: our OpenRouter/Nous
-            # backends read ``reference_images``, OpenAI's gpt-image-2 reads
-            # ``reference_image_urls``. Send both; each ignores the other.
-            kwargs["reference_images"] = refs
-            kwargs["reference_image_urls"] = refs
-        try:
-            result = sprite.provider.generate(prompt, **kwargs)
-        except Exception as exc:  # noqa: BLE001 - normalize provider crashes
-            logger.debug("provider.generate crashed: %s", exc)
-            return None, str(exc)
-        if not isinstance(result, dict) or not result.get("success"):
-            return None, (result or {}).get("error", "unknown error") if isinstance(result, dict) else "no result"
-        image_ref = result.get("image")
-        if not image_ref:
-            return None, "provider returned no image"
-        try:
-            return _save_local(str(image_ref), prefix=prefix), ""
-        except Exception as exc:  # noqa: BLE001
-            return None, f"could not save generated image: {exc}"
-
-    out: list[Path] = []
-    last_error = ""
-    allow_transparent = True
-    for _ in range(max(1, n)):
-        path, err = _run({"background": "transparent"} if allow_transparent else {})
-        # Model doesn't support the transparent flag → drop it for this and every
-        # remaining variant (no point re-probing a capability we just disproved).
-        if path is None and allow_transparent and _rejected_background(err):
-            allow_transparent = False
-            path, err = _run({})
-        if path is not None:
-            out.append(path)
-        else:
-            last_error = err
-
-    if not out:
-        raise GenerationError(last_error or "image generation produced no output")
-    return out

agent/pet/generate/orchestrate.py

@@ -1,358 +0,0 @@
-"""Pet generation orchestration — the base-draft → hatch flow.
-
-Two steps, mirroring the UX across every surface:
-
-1. :func:`generate_base_drafts` — a handful of prompt-only "what should this pet
-   look like" variants. Cheap; the user picks one (or retries for a fresh set).
-2. :func:`hatch_pet` — takes the chosen base and generates one grounded row
-   strip per Hermes state, slices each into frames, composes the atlas, validates
-   it, and writes the pet into the store.
-
-Splitting it this way bounds cost (4 cheap base calls per round; the ~6 row
-calls happen once, on the pet you actually keep) and gives each UI a natural
-preview/loading point.
-"""
-
-from __future__ import annotations
-
-import logging
-import time
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Callable
-
-from agent.pet.generate import atlas, imagegen, prompts
-from agent.pet.generate.imagegen import GenerationError, SpriteProvider
-
-logger = logging.getLogger(__name__)
-
-# (event, detail) — e.g. ("row", "idle"), ("compose", ""), ("save", "<slug>").
-ProgressFn = Callable[[str, str], None]
-
-# Image generations are independent network calls, so we fan them out instead of
-# blocking on each in turn — a hatch is ~8 row calls that would otherwise run
-# back-to-back and routinely blow past the client's RPC timeout. Capped so we
-# don't hammer the provider's rate limit (one cold call can still be slow).
-_MAX_PARALLEL_GENERATIONS = 4
-# How many times to (re)generate a single row before accepting a best-effort
-# slice. Early attempts demand clean per-pose gutters; the last is lenient so a
-# stubborn row still yields frames instead of dropping out entirely.
-_ROW_GEN_ATTEMPTS = 3
-_MIN_FILLED_STATES = 6
-_REQUIRED_STATES = frozenset({"idle", "running-right", "waving"})
-
-
-@dataclass(frozen=True)
-class HatchResult:
-    """Outcome of a successful :func:`hatch_pet`."""
-
-    slug: str
-    display_name: str
-    spritesheet: Path
-    states: list[str]
-    validation: dict
-
-
-def _harden_transparency(path: Path) -> Path:
-    """Key out any solid backdrop the provider painted; save as an RGBA PNG.
-
-    ``background=transparent`` is requested on every call, but image models honor
-    it inconsistently — some still paint a flat (often near-white) backdrop. We
-    run the same chroma-key pass the row extractor uses so every base draft the
-    user picks between (and the reference the rows are grounded on) is a clean
-    cutout. Best-effort: a decode failure leaves the original untouched.
-    """
-    from PIL import Image
-
-    try:
-        with Image.open(path) as opened:
-            keyed = atlas.remove_background(opened.convert("RGBA"))
-        # Zero the RGB of any leftover semi-transparent edge pixels so a keyed
-        # draft has no colored halo when composited on the dark UI.
-        keyed = atlas._clear_transparent_rgb(keyed)
-        out = path.with_suffix(".png")
-        keyed.save(out, format="PNG")
-        return out
-    except Exception as exc:  # noqa: BLE001 - cosmetic; fall back to the raw image
-        logger.debug("base draft transparency hardening failed for %s: %s", path, exc)
-        return path
-
-
-def generate_base_drafts(
-    concept: str,
-    *,
-    n: int = 4,
-    style: str = "auto",
-    reference_images: list[Path] | None = None,
-    provider: SpriteProvider | None = None,
-    on_draft: Callable[[int, Path], None] | None = None,
-    is_cancelled: Callable[[], bool] | None = None,
-) -> list[Path]:
-    """Generate *n* candidate base looks for *concept*; returns image paths.
-
-    Each draft is hardened to a transparent cutout (see :func:`_harden_transparency`).
-    Drafts are generated concurrently and *on_draft(index, path)* fires as each
-    one finishes (not at the end) so callers can stream previews to the UI
-    instead of leaving it blank until the whole batch is done.
-
-    *is_cancelled*, when supplied, is polled cooperatively: a draft that hasn't
-    started yet is skipped, and once it trips we stop staging/streaming further
-    drafts and cancel any queued work (already-in-flight provider calls can't be
-    hard-killed, but their results are dropped).
-    """
-    # A user reference image (e.g. their own pet) grounds every draft, so it
-    # needs a reference-capable provider — same requirement as the row passes.
-    refs = reference_images or None
-    sprite = provider or imagegen.resolve_provider(require_references=bool(refs))
-    cancelled = is_cancelled or (lambda: False)
-
-    # Each draft is its own one-shot generation, run concurrently so the user
-    # waits for one image, not N. A single draft failing must not sink the set.
-    # Each gets a distinct variation nudge so the options aren't near-duplicates.
-    logger.info("pet generate: drafting %d base looks for %r (style=%s)", n, concept, style)
-
-    def _one(index: int) -> tuple[int, Path | None, str | None]:
-        if cancelled():
-            return index, None, None
-        t0 = time.monotonic()
-        variation = prompts.BASE_VARIATIONS[index % len(prompts.BASE_VARIATIONS)]
-        prompt = prompts.build_base_prompt(concept, style=style, variation=variation)
-        try:
-            out = imagegen.generate(prompt, n=1, reference_images=refs, provider=sprite, prefix="pet_base")
-        except Exception as exc:  # noqa: BLE001 - tolerate a single failed draft
-            logger.warning("pet generate: draft %d failed after %.1fs: %s", index, time.monotonic() - t0, exc)
-            return index, None, str(exc)
-        if not out:
-            logger.warning("pet generate: draft %d produced no image", index)
-            return index, None, "the image provider returned no image"
-        logger.info("pet generate: draft %d ready in %.1fs", index, time.monotonic() - t0)
-        return index, _harden_transparency(out[0]), None
-
-    workers = max(1, min(n, _MAX_PARALLEL_GENERATIONS))
-    results: dict[int, Path] = {}
-    errors: list[str] = []
-    with ThreadPoolExecutor(max_workers=workers) as pool:
-        futures = [pool.submit(_one, i) for i in range(n)]
-        # as_completed runs in *this* (the caller's) thread, so on_draft — and any
-        # gateway event it emits — inherits the request's bound transport, unlike
-        # the worker threads above.
-        for fut in as_completed(futures):
-            if cancelled():
-                logger.info("pet generate: cancelled — dropping remaining drafts")
-                for pending in futures:
-                    pending.cancel()
-                break
-            index, path, err = fut.result()
-            if path is None:
-                if err:
-                    errors.append(err)
-                continue
-            results[index] = path
-            if on_draft is not None:
-                try:
-                    on_draft(index, path)
-                except Exception as exc:  # noqa: BLE001 - progress is best-effort
-                    logger.debug("on_draft callback failed: %s", exc)
-
-    drafts = [results[i] for i in sorted(results)]
-    if not drafts and not cancelled():
-        # Surface *why* — every draft failed for a reason (a content-policy refusal
-        # on a name like "minion", a provider/auth error, …); the most common one
-        # is the representative cause. Far more useful than "no usable drafts".
-        raise GenerationError(_drafts_failed_reason(errors))
-    return drafts
-
-
-def _drafts_failed_reason(errors: list[str]) -> str:
-    """The representative reason a draft round produced nothing, humanized."""
-    if not errors:
-        return "image generation produced no usable drafts"
-    from collections import Counter
-
-    return _humanize_image_error(Counter(errors).most_common(1)[0][0])
-
-
-def _humanize_image_error(error: str) -> str:
-    """Turn a raw provider error into a friendly, actionable sentence.
-
-    The big one is moderation: image models refuse trademarked characters and
-    real people (e.g. "minion"), which reads as an opaque 400 otherwise.
-    """
-    low = error.lower()
-    if any(s in low for s in ("moderation_blocked", "safety system", "content policy", "content_policy")):
-        return (
-            "The image provider blocked this prompt — its safety filter rejects "
-            "trademarked characters and real people. Try an original description."
-        )
-    if any(s in low for s in ("api key", "unauthorized", "401", "auth")):
-        return "The image provider rejected the request — check your API key in Settings → Providers."
-    if "rate limit" in low or "429" in low:
-        return "The image provider is rate-limiting — wait a moment and try again."
-    # Otherwise the first line, trimmed of the noisy provider envelope.
-    return error.splitlines()[0].strip()[:200]
-
-
-def hatch_pet(
-    *,
-    base_image: str | Path,
-    slug: str,
-    display_name: str = "",
-    description: str = "",
-    concept: str = "",
-    style: str = "auto",
-    on_progress: ProgressFn | None = None,
-    provider: SpriteProvider | None = None,
-    is_cancelled: Callable[[], bool] | None = None,
-) -> HatchResult:
-    """Turn an approved base image into a full, installed Hermes pet.
-
-    Generates a grounded row strip per state, extracts frames, composes +
-    validates the atlas, and registers it. The idle row falls back to the base
-    look so the pet always renders. Raises :class:`GenerationError` on failure.
-
-    *is_cancelled*, when supplied, is polled cooperatively: rows that haven't
-    started are skipped, queued rows are cancelled, and once every row is done we
-    abort (raising :class:`GenerationError`) before composing/saving so a stopped
-    hatch never writes a half-built pet.
-    """
-    base = Path(base_image)
-    if not base.is_file():
-        raise GenerationError(f"base image not found: {base}")
-
-    sprite = provider or imagegen.resolve_provider(require_references=True)
-    progress = on_progress or (lambda *_: None)
-    cancelled = is_cancelled or (lambda: False)
-    label = concept or display_name or slug
-
-    frames_by_state: dict[str, list] = {}
-    total_rows = len(atlas.ROW_SPECS)
-    logger.info("pet hatch %r: generating %d animation rows", slug, total_rows)
-
-    # Generate every state's row strip concurrently — they're independent
-    # grounded calls, so the hatch waits for the slowest row, not their sum. A
-    # single row failing is tolerated (idle is guaranteed below).
-    def _gen_row(spec: tuple[str, int, int]) -> tuple[str, list | None]:
-        state, _row, count = spec
-        if cancelled():
-            return state, None
-        t0 = time.monotonic()
-        last_exc: Exception | None = None
-        # Self-healing: a model occasionally returns a row whose poses are touching
-        # (no clean gutters), which slices badly. We retry such rolls; only the
-        # final attempt falls back to lenient ``auto`` slicing so a stubborn row
-        # still yields *something* rather than dropping the whole row.
-        for attempt in range(_ROW_GEN_ATTEMPTS):
-            if cancelled():
-                return state, None
-            strict = attempt < _ROW_GEN_ATTEMPTS - 1
-            try:
-                strips = imagegen.generate(
-                    prompts.build_row_prompt(state, count, label, style=style),
-                    n=1,
-                    reference_images=[base],
-                    provider=sprite,
-                    prefix=f"pet_row_{state}",
-                    # Wider canvas → each frame gets real horizontal room, so winged
-                    # poses keep a full, healthy size and still leave clean gutters.
-                    aspect_ratio="landscape",
-                )
-                # ``components`` requires clean per-pose gutters (raises otherwise),
-                # so a touching roll is rejected and regenerated; the last attempt
-                # uses ``auto`` (equal-slot fallback, never raises). Raw (fit=False)
-                # so normalize_cells registers the whole pet at once.
-                method = "components" if strict else "auto"
-                frames = atlas.extract_strip_frames(strips[0], count, method=method, fit=False)
-                logger.info(
-                    "pet hatch %r: row %r ready in %.1fs (attempt %d)",
-                    slug, state, time.monotonic() - t0, attempt + 1,
-                )
-                return state, frames
-            except Exception as exc:  # noqa: BLE001 - retried; one bad row is tolerated
-                last_exc = exc
-                logger.warning(
-                    "pet hatch %r: row %r attempt %d/%d failed: %s",
-                    slug, state, attempt + 1, _ROW_GEN_ATTEMPTS, exc,
-                )
-        logger.warning(
-            "pet hatch %r: row %r gave up after %.1fs: %s",
-            slug, state, time.monotonic() - t0, last_exc,
-        )
-        return state, None
-
-    # running-left is derived by mirroring running-right (guaranteed-consistent
-    # and one fewer generation), so we don't generate it directly.
-    generated_specs = [spec for spec in atlas.ROW_SPECS if spec[0] != "running-left"]
-
-    workers = max(1, min(len(generated_specs), _MAX_PARALLEL_GENERATIONS))
-    done = 0
-    with ThreadPoolExecutor(max_workers=workers) as pool:
-        futures = [pool.submit(_gen_row, spec) for spec in generated_specs]
-        # as_completed runs on the caller (request) thread, so progress events
-        # emitted here inherit the request transport — unlike the worker threads.
-        for fut in as_completed(futures):
-            if cancelled():
-                logger.info("pet hatch %r: cancelled — dropping remaining rows", slug)
-                for pending in futures:
-                    pending.cancel()
-                break
-            state, frames = fut.result()
-            done += 1
-            progress("row", f"{state}:{done}:{total_rows}")
-            if frames:
-                frames_by_state[state] = frames
-
-    if cancelled():
-        raise GenerationError("hatch cancelled")
-
-    # Derive running-left from the approved running-right row (per-frame mirror,
-    # preserving order/timing). Missing running-right is rejected below; a pet
-    # without its canonical walk cycle is a failed hatch, not a shippable mascot.
-    right = frames_by_state.get("running-right")
-    if right:
-        done += 1
-        progress("row", f"running-left:{done}:{total_rows}")
-        frames_by_state["running-left"] = atlas.mirror_frames(right)
-        logger.info("pet hatch %r: row 'running-left' mirrored from running-right", slug)
-    else:
-        logger.warning("pet hatch %r: no running-right to mirror; left walk left empty", slug)
-
-    # Idle is the resting state the renderer falls back to — guarantee it.
-    if not frames_by_state.get("idle"):
-        progress("row", "idle-fallback")
-        frames_by_state["idle"] = [atlas.single_frame(base, fit=False)]
-
-    progress("compose", "")
-    logger.info("pet hatch %r: composing atlas from %d states", slug, len(frames_by_state))
-    # One shared scale + baseline across every state so the pet never slides or
-    # pulses size between frames; compose just packs the normalized cells.
-    sheet = atlas.compose_atlas(atlas.normalize_cells(frames_by_state))
-    validation = atlas.validate_atlas(sheet)
-    if not validation["ok"]:
-        raise GenerationError("; ".join(validation["errors"]) or "atlas validation failed")
-    filled_states = set(validation["filled_states"])
-    missing_required = sorted(_REQUIRED_STATES - filled_states)
-    if missing_required:
-        raise GenerationError(f"missing required animation row(s): {', '.join(missing_required)}")
-    if len(filled_states) < _MIN_FILLED_STATES:
-        raise GenerationError(
-            f"only {len(filled_states)}/{len(atlas.ROW_SPECS)} animation rows were usable; regenerate"
-        )
-
-    from agent.pet import store
-
-    progress("save", slug)
-    logger.info("pet hatch %r: saving pet", slug)
-    pet = store.register_local_pet(
-        sheet,
-        slug=slug,
-        display_name=display_name or slug,
-        description=description,
-    )
-    return HatchResult(
-        slug=pet.slug,
-        display_name=pet.display_name,
-        spritesheet=pet.spritesheet,
-        states=validation["filled_states"],
-        validation=validation,
-    )

agent/pet/generate/prompts.py

@@ -1,183 +0,0 @@
-"""Prompt builders for pet generation.
-
-Two prompt shapes: a *base* prompt (prompt-only, produces the canonical look the
-user picks between) and per-*state* *row* prompts (grounded on the chosen base,
-produce one horizontal strip of N poses). Prompts stay concise and
-sprite-production oriented; the identity lock and "one transparent row" framing
-matter more than flowery description.
-
-We generate the full petdex/Codex nine-state set (see
-:data:`agent.pet.generate.atlas.ROW_SPECS`) so a hatched pet is a valid
-``petdex submit`` spritesheet.
-"""
-
-from __future__ import annotations
-
-# What each petdex/Codex state should depict (kept short — these go straight into
-# the row prompt). Phrased to avoid the common sprite-gen failure modes (detached
-# effects, motion lines, shadows). Critical distinction: ``running`` is the
-# *working* state (in place), while ``running-right`` / ``running-left`` are the
-# actual directional walk/run cycles.
-STATE_ACTIONS: dict[str, str] = {
-    "idle": "a calm idle loop: subtle breathing, a tiny blink or gentle bob, no big gestures",
-    "running-right": (
-        "a sideways walk/run locomotion cycle moving to the RIGHT: the character "
-        "faces and travels right with clear directional steps, a smooth gait loop"
-    ),
-    "running-left": (
-        "a sideways walk/run locomotion cycle moving to the LEFT: the character "
-        "faces and travels left with clear directional steps (the mirror of the "
-        "right-facing run)"
-    ),
-    "waving": "a friendly greeting: raising a paw/hand/limb to wave, clear up-and-down gesture",
-    "jumping": "a happy celebration jump: anticipation, lift off the ground, peak, and land",
-    "failed": "a sad or deflated reaction: slumped, dejected, small frown — readable but not noisy",
-    "waiting": (
-        "an expectant 'waiting on you' pose: looking up/out as if asking for input "
-        "or approval — distinct from idle and review"
-    ),
-    "running": (
-        "focused active work, staying IN PLACE (NOT walking or foot-running): "
-        "leaning in, concentrating, busy 'thinking / processing / typing' energy"
-    ),
-    "review": "careful inspection: a focused lean, head tilt, studying something intently",
-}
-
-_STYLE_HINTS: dict[str, str] = {
-    # Default to the popular petdex look: crisp 16-bit PIXEL ART, not the smooth
-    # 2D illustration (let alone 3D render) gpt-image reaches for by default.
-    "auto": (
-        " Style: crisp 16-bit PIXEL-ART game sprite — visible square pixels, a small "
-        "limited palette, clean dark outline, flat cel shading, chunky chibi "
-        "proportions, like a classic SNES/JRPG party member or a petdex.dev mascot. "
-        "Absolutely NOT 3D-rendered, NOT a smooth painted or vector illustration, "
-        "NOT photorealistic — no soft gradients, no realistic lighting, no figurine look."
-    ),
-    "pixel": " Render in clean 16-bit pixel-art style with visible square pixels and a limited palette.",
-    "plush": " Render as a soft plush toy.",
-    "clay": " Render as a claymation / soft 3D clay figure.",
-    "sticker": " Render as a glossy die-cut sticker.",
-    "flat-vector": " Render in flat vector mascot style.",
-    "3d-toy": " Render as a glossy 3D toy.",
-    "painterly": " Render in a soft painterly style.",
-}
-
-_BACKGROUND = (
-    "Center the character on a SINGLE flat, uniform, high-contrast chroma-key "
-    "background — pure hot magenta #FF00FF (only if magenta appears on the "
-    "character, use pure green #00FF00 instead). The background is ONE continuous "
-    "even color that completely surrounds the character with NO gradient, "
-    "vignette, texture, pattern, scenery, shadow, ground line, frame, border, "
-    "panel, comic cell, gutter line, grid, or divider of any kind, so it keys out "
-    "cleanly. The background color must not appear anywhere on the character. "
-    "No text, no labels, no speech bubbles, no UI."
-)
-
-
-def style_hint(style: str | None) -> str:
-    return _STYLE_HINTS.get((style or "auto").strip().lower(), "")
-
-
-# Row strips are generated on the wider landscape canvas (see imagegen.generate /
-# orchestrate). The extra width is what lets each pose stay a healthy size AND
-# leave a real gutter — used here only to cite concrete pixel numbers.
-_ASSUMED_STRIP_WIDTH = 1536
-
-
-def _spacing_spec(frame_count: int) -> tuple[int, int]:
-    """(per-pose width px, gap px) for a row of *frame_count* poses.
-
-    Pixel counts alone don't hold — the model fills each slot edge-to-edge with
-    the full wingspan, so neighbors touch even when bodies are spaced. The lever
-    that works is proportional containment on a wide canvas: give each pose its
-    own equal cell and keep the ENTIRE silhouette (wings/tail/halo included)
-    inside it. On the 1536px landscape strip ~70% occupancy still leaves a
-    generous gutter, so the pet stays a normal, good-looking size — no shrinking.
-    """
-    slots = max(1, frame_count)
-    slot_w = _ASSUMED_STRIP_WIDTH / slots
-    pose_px = round(slot_w * 0.7)
-    gap_px = max(48, round(slot_w * 0.3))
-    return pose_px, gap_px
-
-
-# Per-draft nudges so the 4 base options are actually distinct — gpt-image returns
-# near-duplicates for a single prompt. We vary the *look* (palette, build,
-# expression, accents), NOT the pose, so the chosen base still grounds clean,
-# consistent animation rows.
-BASE_VARIATIONS: tuple[str, ...] = (
-    "",
-    "a distinctly different colour palette and markings",
-    "a heavier, broader silhouette with sturdier proportions",
-    "a different facial structure and expression matching the concept tone, with unique accent/accessory details",
-    "a leaner, taller build and an alternate colour scheme",
-    "bolder, more saturated colours and a stronger expression matching the concept tone",
-)
-
-
-def build_base_prompt(concept: str, *, style: str | None = "auto", variation: str = "") -> str:
-    """The base look: a single, clean, centered full-body mascot.
-
-    *variation* differentiates one draft from the next (see :data:`BASE_VARIATIONS`).
-    """
-    concept = (concept or "a distinctive mascot creature").strip()
-    nudge = f" Make this design distinct: {variation}." if variation else ""
-    return (
-        f"A stylized mascot pet character: {concept}. "
-        "Honor the requested tone and mood exactly (cute, eerie, scary, menacing, whimsical, etc.) "
-        "while staying non-graphic. "
-        "Compact, whole-body silhouette that reads clearly at small size, "
-        "clear readable facial features, simple consistent palette. "
-        # A neutral, symmetric, at-rest stance makes the cleanest identity anchor
-        "Neutral front-facing standing pose, upright and symmetric, arms/limbs "
-        "relaxed at the sides, feet together on the ground, any cape/accessories "
-        "hanging straight and still."
-        f"{nudge} "
-        f"{_BACKGROUND}{style_hint(style)}"
-    )
-
-
-def build_row_prompt(state: str, frame_count: int, concept: str, *, style: str | None = "auto") -> str:
-    """A row strip: *frame_count* poses of the SAME character, left→right.
-
-    The attached base image is the identity source of truth; the prompt locks
-    species, palette, face, and props to it.
-    """
-    action = STATE_ACTIONS.get(state, "a simple idle pose")
-    concept = (concept or "the mascot").strip()
-    pose_px, gap_px = _spacing_spec(frame_count)
-    return (
-        f"Using the attached reference image as the exact same character "
-        f"(same species, face, colors, markings, proportions, and props), "
-        "preserving the same emotional tone/mood (e.g., scary stays scary, cute stays cute), "
-        f"draw a single WIDE horizontal strip of {frame_count} animation frames showing {action}. "
-        f"LAYOUT: arrange {frame_count} poses in ONE horizontal row at equal spacing, "
-        "each pose centered in its own imaginary equal region. Draw NO panel borders, "
-        "NO comic cells, NO boxes, NO vertical divider/gutter lines, NO grid, NO frame "
-        "outlines between poses — the backdrop is one unbroken flat field behind all of them. "
-        "Fill the WHOLE strip with the SAME single flat chroma-key color as the attached "
-        "reference image's background (identical hue in every frame, no per-pose color shifts). "
-        f"SPACING (critical): draw each pose at a consistent, healthy, clearly "
-        f"visible size (roughly {pose_px}px wide on a {_ASSUMED_STRIP_WIDTH}px "
-        f"strip) — do NOT shrink it tiny — but keep its ENTIRE silhouette "
-        f"(wings, tail, halo, horns, cape, every appendage) fully INSIDE its own "
-        f"cell. Leave at least {gap_px}px of empty chroma-key background between "
-        f"neighboring silhouettes at their closest point (wingtip to wingtip), and "
-        f"the same empty margin before the first pose and after the last. If a wing, "
-        f"cape, or tail would reach into a neighbor, FOLD or angle it inward rather "
-        f"than letting it cross the gap. Silhouettes must NEVER touch, overlap, "
-        f"share a shadow, share a ground line, share motion trails, or merge into "
-        f"one connected shape. "
-        # Registration: a clean sprite sheet keeps the character locked in place
-        # so only the action moves — this is what stops the loop sliding/pulsing.
-        "REGISTRATION (critical): the character is the SAME height and SAME width "
-        "in every frame, drawn at the SAME scale, centered over the SAME point, "
-        "with all feet aligned to the SAME invisible horizontal baseline across the "
-        "whole strip — this baseline is conceptual ONLY: draw NO ground line, floor, "
-        "platform, horizon, or contact shadow beneath the feet. Keep the body's center, size, and stance fixed frame to "
-        "frame — ONLY the limbs/features the action needs may move. Capes, cloaks, "
-        "bags, and scarves stay in the SAME place and shape every frame (no "
-        "swinging, flowing, or drifting) unless the action itself requires it. No "
-        "pose is cropped at the strip edges. "
-        f"{_BACKGROUND}{style_hint(style)}"
-    )

agent/pet/manifest.py

@@ -21,7 +21,6 @@ Read-only and unauthenticated; no credentials involved.
 from __future__ import annotations
 
 import logging
-import threading
 import time
 from dataclasses import dataclass
 
@@ -29,7 +28,7 @@ logger = logging.getLogger(__name__)
 
 MANIFEST_URL = "https://petdex.dev/api/manifest"
 
-_DEFAULT_TIMEOUT = 10.0
+_DEFAULT_TIMEOUT = 20.0
 
 # In-process cache for the (large, slow, identical-per-call) manifest. The list
 # is a static CDN object that barely changes, yet a single session can ask for
@@ -39,9 +38,6 @@ _DEFAULT_TIMEOUT = 10.0
 _MANIFEST_TTL = 300.0
 _cache: tuple[float, list[ManifestEntry]] | None = None
 
-_prefetch_lock = threading.Lock()
-_prefetching = False
-
 
 def clear_cache() -> None:
     """Drop the cached manifest (forces the next fetch to hit the network)."""
@@ -49,39 +45,6 @@ def clear_cache() -> None:
     _cache = None
 
 
-def _cache_is_warm() -> bool:
-    return _cache is not None and time.monotonic() - _cache[0] < _MANIFEST_TTL
-
-
-def prefetch(*, timeout: float = _DEFAULT_TIMEOUT) -> None:
-    """Warm the manifest cache in a daemon thread — idempotent, never blocks.
-
-    The desktop picker calls this when it loads the (instant) local-only gallery
-    so the full petdex catalog is usually cached by the time it's requested,
-    without ever holding up the user's own pets on a network round-trip.
-    """
-    global _prefetching
-
-    if _cache_is_warm():
-        return
-
-    with _prefetch_lock:
-        if _prefetching:
-            return
-        _prefetching = True
-
-    def _run() -> None:
-        global _prefetching
-        try:
-            fetch_manifest(timeout=timeout)
-        except Exception as exc:  # noqa: BLE001 - best-effort warm
-            logger.debug("petdex manifest prefetch failed: %s", exc)
-        finally:
-            _prefetching = False
-
-    threading.Thread(target=_run, name="petdex-prefetch", daemon=True).start()
-
-
 @dataclass(frozen=True)
 class ManifestEntry:
     """A single pet's row in the manifest."""

agent/pet/store.py

@@ -18,7 +18,6 @@ from __future__ import annotations
 
 import json
 import logging
-import re
 from dataclasses import dataclass
 from pathlib import Path
 
@@ -42,16 +41,11 @@ class InstalledPet:
     description: str
     directory: Path
     spritesheet: Path
-    created_by: str = ""  # "generator" for pets hatched locally; "" for petdex installs
 
     @property
     def exists(self) -> bool:
         return self.spritesheet.is_file()
 
-    @property
-    def generated(self) -> bool:
-        return self.created_by == "generator"
-
 
 def pets_dir() -> Path:
     """Return the profile-scoped pets directory (created on demand)."""
@@ -119,7 +113,6 @@ def load_pet(slug: str) -> InstalledPet | None:
         description=str(meta.get("description", "") or ""),
         directory=directory,
         spritesheet=_resolve_spritesheet(directory, meta),
-        created_by=str(meta.get("createdBy", "") or ""),
     )
 
 
@@ -204,101 +197,6 @@ def install_pet(slug: str, *, force: bool = False, timeout: float = _DOWNLOAD_TI
     return pet
 
 
-def slugify(name: str) -> str:
-    """Lowercase, hyphenate, and strip a display name into a filesystem slug."""
-    slug = re.sub(r"[^a-z0-9]+", "-", (name or "").strip().lower()).strip("-")
-    return slug or "pet"
-
-
-def unique_slug(name: str) -> str:
-    """A :func:`slugify` result that doesn't collide with an existing pet dir."""
-    base = slugify(name)
-    slug = base
-    counter = 2
-    while (pets_dir() / slug).exists():
-        slug = f"{base}-{counter}"
-        counter += 1
-    return slug
-
-
-def _write_spritesheet(source, dest: Path) -> None:
-    """Write *source* (PIL image, bytes, or path) as a lossless WebP at *dest*."""
-    if isinstance(source, (bytes, bytearray)):
-        dest.write_bytes(bytes(source))
-        return
-
-    from PIL import Image
-
-    if isinstance(source, (str, Path)):
-        with Image.open(source) as opened:
-            image = opened.convert("RGBA")
-    else:
-        image = source.convert("RGBA")
-    image.save(dest, format="WEBP", lossless=True, quality=100, method=6, exact=True)
-
-
-def register_local_pet(
-    spritesheet,
-    *,
-    slug: str,
-    display_name: str = "",
-    description: str = "",
-) -> InstalledPet:
-    """Write a locally-generated pet into the store and return it.
-
-    *spritesheet* may be a PIL image, raw WebP/PNG bytes, or a path. The pet
-    appears in :func:`installed_pets` immediately, and because :func:`install_pet`
-    returns an already-on-disk pet before consulting the manifest, it can be
-    adopted (``pet.select`` / ``/pet <slug>``) without a manifest entry.
-    """
-    slug = slugify(slug)
-    directory = pets_dir() / slug
-    directory.mkdir(parents=True, exist_ok=True)
-    sprite_path = directory / "spritesheet.webp"
-    try:
-        _write_spritesheet(spritesheet, sprite_path)
-    except Exception as exc:  # noqa: BLE001 - normalize to one error type
-        raise PetStoreError(f"could not write spritesheet for '{slug}': {exc}") from exc
-
-    meta = {
-        "id": slug,
-        "displayName": display_name or slug,
-        "description": description or "",
-        "spritesheetPath": sprite_path.name,
-        "createdBy": "generator",
-    }
-    (directory / "pet.json").write_text(json.dumps(meta, indent=2), encoding="utf-8")
-
-    pet = load_pet(slug)
-    if pet is None or not pet.exists:
-        raise PetStoreError(f"register of generated pet '{slug}' did not produce a spritesheet")
-    return pet
-
-
-def export_pet(slug: str) -> tuple[str, bytes]:
-    """Zip an installed pet's folder (pet.json + spritesheet) → (filename, bytes).
-
-    Dotfiles (cached thumbs, backups) are skipped so the archive is a clean,
-    re-importable pet package. Raises :class:`PetStoreError` if not installed.
-    """
-    import io
-    import zipfile
-
-    root = pets_dir()
-    directory = root / slug.strip()
-    # Guard against traversal: the target must be a direct child of pets_dir.
-    if directory.resolve().parent != root.resolve() or not directory.is_dir():
-        raise PetStoreError(f"pet '{slug}' is not installed")
-
-    name = directory.name
-    buf = io.BytesIO()
-    with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as archive:
-        for path in sorted(directory.iterdir()):
-            if path.is_file() and not path.name.startswith("."):
-                archive.write(path, f"{name}/{path.name}")
-    return f"{name}.zip", buf.getvalue()
-
-
 _THUMB_FRAME_W = 192
 _THUMB_FRAME_H = 208
 _THUMB_W = 96  # rendered ~40px; 2x+ keeps it crisp on HiDPI
@@ -403,15 +301,6 @@ def remove_pet(slug: str) -> bool:
     slug = _safe_slug(slug)
     if not slug:
         return False
-
-    # The cached thumbnail lives in pets/.thumbs/<slug>.png — OUTSIDE the pet
-    # dir, so rmtree won't catch it. Drop it too, or a later pet that reuses this
-    # slug renders this one's stale thumbnail.
-    try:
-        (_thumbs_dir() / f"{slug}.png").unlink(missing_ok=True)
-    except OSError:
-        pass
-
     directory = pets_dir() / slug
     if not directory.is_dir():
         return False
@@ -419,55 +308,6 @@ def remove_pet(slug: str) -> bool:
     return not directory.exists()
 
 
-def rename_pet(slug: str, display_name: str) -> str | None:
-    """Rename a pet's ``displayName`` AND realign its slug/dir to match.
-
-    Generated pets are hatched under a provisional, prompt-derived slug; when
-    the user names the pet on the reveal screen we make that name the real
-    identity so lists/subtitles show what they typed, not the prompt. The dir is
-    renamed to ``slugify(name)`` (and the cached thumbnail moved alongside it)
-    whenever that yields a free, different slug — otherwise the slug is left as
-    is. Returns the resulting slug on success, or ``None`` on failure.
-    """
-    slug = _safe_slug(slug)
-    display_name = (display_name or "").strip()
-    if not slug or not display_name:
-        return None
-    directory = pets_dir() / slug
-    pet_json = directory / "pet.json"
-    if not pet_json.is_file():
-        return None
-    try:
-        meta = json.loads(pet_json.read_text(encoding="utf-8"))
-    except (OSError, ValueError):
-        meta = {}
-    if not isinstance(meta, dict):
-        meta = {}
-    meta["displayName"] = display_name
-
-    new_slug = slug
-    desired = slugify(display_name)
-    if desired and desired != slug and not (pets_dir() / desired).exists():
-        try:
-            directory.rename(pets_dir() / desired)
-            try:
-                (_thumbs_dir() / f"{slug}.png").rename(_thumbs_dir() / f"{desired}.png")
-            except OSError:
-                pass
-            directory = pets_dir() / desired
-            pet_json = directory / "pet.json"
-            new_slug = desired
-            meta["id"] = new_slug
-        except OSError:
-            new_slug = slug  # keep the provisional slug if the move fails
-
-    try:
-        pet_json.write_text(json.dumps(meta, indent=2), encoding="utf-8")
-    except OSError:
-        return None
-    return new_slug
-
-
 def _download(url: str, dest: Path, *, timeout: float) -> None:
     import httpx
 

agent/prompt_builder.py

@@ -243,10 +243,7 @@ KANBAN_GUIDANCE = (
     "- **Workspace.** `cd $HERMES_KANBAN_WORKSPACE` first. For a `worktree` kind "
     "with no `.git`, `git worktree add <path> "
     "${HERMES_KANBAN_BRANCH:-wt/$HERMES_KANBAN_TASK}` from the main repo, then "
-    "cd there. For a project-linked task the workspace is a fresh "
-    "`<repo>/.worktrees/<task-id>` and `$HERMES_KANBAN_BRANCH` a deterministic "
-    "`<project-slug>/<task-id>` — the main repo is two levels up, so run "
-    "`git worktree add` from there.\n"
+    "cd there.\n"
     "- **Deliverables.** Files a human wants go in "
     "`kanban_complete(artifacts=[<absolute paths>])` (top-level param; paths in "
     "`metadata` are NOT uploaded). Files must exist at completion.\n"

agent/proxy_sources/__init__.py

@@ -1,8 +0,0 @@
-"""Egress proxy integrations.
-
-Currently ships an iron-proxy (ironsh/iron-proxy) wrapper that intercepts
-outbound traffic from remote terminal sandboxes and swaps proxy tokens
-for real upstream credentials at the network edge.
-
-Design notes live in :mod:`agent.proxy_sources.iron_proxy`.
-"""

agent/reasoning_timeouts.py

@@ -1,216 +0,0 @@
-"""Per-reasoning-model stale-timeout floor for known reasoning models.
-
-Reasoning models (those that emit extended thinking blocks before their
-first content token) routinely exceed Hermes's default chat-model
-stale detectors:
-
-* Stream stale detector:   ``HERMES_STREAM_STALE_TIMEOUT``     default 180s
-                           ``agent/chat_completion_helpers.py:2544``
-* Non-stream stale detector: ``HERMES_API_CALL_STALE_TIMEOUT``  default 90s
-                           ``run_agent.py:1140``
-
-For NVIDIA Nemotron 3 Ultra on the hosted NIM gateway the empirical
-upstream idle kill is ~120s (first-party reproduction at
-NVIDIA/NemoClaw#4846 — TTFB ~31s, stream dies at 120s). The same
-failure mode exists on OpenAI o1/o3, Anthropic Opus 4.x thinking,
-DeepSeek R1, Qwen QwQ, xAI Grok reasoning — every cloud reasoning
-model hits upstream-proxies / load-balancers with idle timeouts
-shorter than the model's thinking phase. Result: the stale detector
-kills the connection mid-think, surfacing as
-``BrokenPipeError``/``RemoteProtocolError`` on the next read.
-
-This module provides a floor that the existing stale-detector scaling
-blocks consult via :func:`get_reasoning_stale_timeout_floor` and
-apply as ``max(default, floor)``. It is a FLOOR:
-
-* Never overrides explicit user config (``providers.<id>.models.<model>.stale_timeout_seconds``
-  or ``request_timeout_seconds`` already wins — this code never runs
-  in that branch).
-* Never lowers an existing threshold.
-* Has zero effect on non-reasoning models — they are not in the
-  allowlist and the resolver returns ``None``.
-
-Matching uses start-anchored regex on the slug-only component of
-the model name (after stripping any aggregator prefix like
-``openai/``, ``x-ai/``, ``anthropic/``).  The right-anchor matches
-end-of-string or a ``-``/``.``/``_`` slug separator, so ``qwen3-235b``
-matches the ``qwen3`` family entry (a future model slug would be
-``qwen3-235b-instruct`` and would also match) but ``some-other-qwen3``
-does NOT match ``qwen3`` (the ``-qwen3`` is not at start of slug).
-
-The ``o1`` case is the most delicate: a model named
-``llama-4-70b-o1-preview`` is a hypothetical community derivative that
-should NOT trigger the reasoning-model floor for the user (the user
-chose a non-OpenAI model, not a reasoning model).  The start-of-slug
-anchor naturally excludes this — the matched ``o1-preview`` is at
-position 11 of the slug, not at position 0.  The previous substring-
-with-trailing-hyphen design would have over-matched here, which is
-why start-of-slug anchoring is the right shape.
-
-Fixes #52217.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Optional
-
-
-# (slug, floor_seconds).  Each slug is matched as a discrete
-# word-boundary component via the wrapper regex in ``_match_any``
-# below.  Order is irrelevant — the first regex match wins.
-_REASONING_STALE_TIMEOUT_FLOORS: tuple[tuple[str, int], ...] = (
-    # NVIDIA Nemotron — reasoning models behind hosted NIM with
-    # documented 60-180s upstream idle kill (NVIDIA/NemoClaw#4846:
-    # 120s measured).
-    ("nemotron-3-ultra", 600),
-    ("nemotron-3-super", 600),
-    ("nemotron-3-nano",  300),
-    # DeepSeek — R1 reasoning model on hosted NIM / DeepSeek direct.
-    ("deepseek-r1", 600),
-    ("deepseek-reasoner", 600),
-    # Qwen — QwQ reasoning + Qwen3 thinking variants.  QwQ-32B
-    # preview is the stable slug; ``qwen3`` covers the family of
-    # thinking-mode Qwen3 models (qwen3-235b-a22b, qwen3-32b, etc.)
-    # without over-matching every Qwen3 instruct variant — the
-    # right-anchor requires the slug to be at the start of the
-    # remaining model name, so ``qwen3-235b-instruct`` (instruct is
-    # NOT a thinking variant) would still match.  Acceptable
-    # trade-off: instruct variants of qwen3 get the 180s floor
-    # even though they don't reason.  The cost is a slightly longer
-    # wait on a hung provider; the alternative (matching only
-    # ``qwen3-.*-thinking``) breaks the moment NVIDIA or Alibaba
-    # ships a slightly different naming shape.
-    ("qwq-32b", 300),
-    ("qwen3", 180),
-    # OpenAI o-series — known multi-minute TTFB.  Each variant
-    # enumerated explicitly so bare ``o1`` doesn't over-match
-    # ``olmo-1`` or hypothetical future community derivatives.
-    ("o1", 600),
-    ("o1-mini", 600),
-    ("o1-pro", 600),
-    ("o1-preview", 600),
-    ("o3", 600),
-    ("o3-pro", 600),
-    ("o3-mini", 300),
-    ("o4-mini", 300),
-    # Anthropic Claude 4.x thinking variants.  Anchored at
-    # ``claude-opus-4`` so non-thinking Claude 3.x or future
-    # non-reasoning Claude variants don't match.
-    ("claude-opus-4", 240),
-    ("claude-sonnet-4.5", 180),
-    ("claude-sonnet-4.6", 180),
-    # xAI Grok reasoning variants.  Explicit reasoning-only keys
-    # plus one for the ``non-reasoning`` variant so users picking
-    # the fast variant don't get the 300s floor.  Bare ``grok-3``,
-    # ``grok-4`` etc. don't match — only the explicit reasoning /
-    # non-reasoning pairs.
-    ("grok-4-fast-reasoning", 300),
-    ("grok-4.20-reasoning", 300),
-    ("grok-4-fast-non-reasoning", 180),
-)
-
-
-# Pre-compile each pattern.  Wrapper = start-of-slug + slug + end-or-
-# separator, where ``start-of-slug`` means start-of-string OR
-# immediately after the last ``/`` (aggregator separator) and
-# ``end-or-separator`` means end-of-string OR a ``-``/``.``/``_``.
-#
-# Why start-of-slug and not start-of-string: aggregator prefixes
-# like ``openai/`` should not affect matching — the slug identity is
-# the part after the last ``/``.  Stripping the aggregator prefix in
-# :func:`get_reasoning_stale_timeout_floor` before regex matching
-# gives the wrapper a clean start-of-string anchor.
-#
-# Why end-or-separator on the right: ``openai/o3-mini`` must match
-# the ``o3-mini`` slug (the right anchor is end-of-string).  And
-# ``openai/o3-mini-2025-01-31`` must also match ``o3-mini`` (the right
-# anchor is the ``-`` separator).  But ``openai/o3-mini-fork`` should
-# NOT match ``o3-mini`` if we wanted to exclude forks — though the
-# pattern ``o3-mini-fork`` would be matched as a derivative anyway,
-# so we accept that community forks inheriting the same prefix are
-# treated as reasoning models (a reasonable default — the upstream
-# gateway timing is the same).
-_PATTERN_CACHE: dict[str, re.Pattern[str]] = {}
-
-
-def _get_pattern(slug: str) -> re.Pattern[str]:
-    compiled = _PATTERN_CACHE.get(slug)
-    if compiled is None:
-        compiled = re.compile(
-            r"^"
-            + re.escape(slug)
-            + r"(?:$|[\-._])"
-        )
-        _PATTERN_CACHE[slug] = compiled
-    return compiled
-
-
-def _match_any(model_lower: str) -> Optional[float]:
-    """Return the floor for the first matching slug, else None.
-
-    Each table entry is matched as a start-of-slug prefix with the
-    slug-separator-or-end-of-string right-anchor.  Table iteration
-    order is irrelevant: longest slug wins (so ``o3-mini`` beats
-    ``o3`` on a model like ``openai/o3-mini``).
-    """
-    # Sort by slug length descending so longer / more-specific slugs
-    # win on shared prefixes (o3-mini beats o3).
-    sorted_floors = sorted(
-        _REASONING_STALE_TIMEOUT_FLOORS, key=lambda kv: -len(kv[0])
-    )
-    for slug, floor in sorted_floors:
-        if _get_pattern(slug).search(model_lower):
-            return float(floor)
-    return None
-
-
-def get_reasoning_stale_timeout_floor(model: object) -> Optional[float]:
-    """Return the stale-timeout floor (seconds) for a known reasoning model.
-
-    Returns ``None`` when the model is not in the allowlist or the
-    argument is empty / not a string.  Matching uses
-    word-boundary-anchored regex on the lowercased model name, so
-    ``openai/o3-mini`` matches the ``o3-mini`` slug but
-    ``olmo-1`` does NOT match ``o1`` (the ``o1`` substring is not
-    at a word boundary inside ``olmo-1``).
-
-    Aggregator prefixes (``openai/``, ``x-ai/``, ``anthropic/`` etc.)
-    are preserved through matching — the ``/`` is itself a word
-    boundary, so ``openai/o3-mini`` matches ``o3-mini`` because the
-    ``/`` before ``o3-mini`` satisfies the left-anchor alternation.
-
-    This is a FLOOR — callers must apply it as ``max(default, floor)``
-    and only when no explicit user-configured per-model
-    ``stale_timeout_seconds`` exists.
-
-    >>> get_reasoning_stale_timeout_floor("nvidia/nemotron-3-ultra-550b-a55b")
-    600.0
-    >>> get_reasoning_stale_timeout_floor("openai/o3-mini")
-    300.0
-    >>> get_reasoning_stale_timeout_floor("deepseek/deepseek-r1")
-    600.0
-    >>> get_reasoning_stale_timeout_floor("qwen/qwen3-235b-a22b-thinking")
-    180.0
-    >>> get_reasoning_stale_timeout_floor("x-ai/grok-4-fast-reasoning")
-    300.0
-    >>> get_reasoning_stale_timeout_floor("anthropic/claude-opus-4-6")
-    240.0
-    >>> get_reasoning_stale_timeout_floor("gpt-4o") is None
-    True
-    >>> get_reasoning_stale_timeout_floor("olmo-1") is None
-    True
-    >>> get_reasoning_stale_timeout_floor(None) is None
-    True
-    """
-    if not model or not isinstance(model, str):
-        return None
-    name = model.strip().lower()
-    if not name:
-        return None
-    # Strip aggregator prefix (everything before and including the
-    # last ``/``).  The wrapper regex anchors at start-of-string, so
-    # the slug identity is the bare model name.
-    if "/" in name:
-        name = name.rsplit("/", 1)[1]
-    return _match_any(name)

agent/retry_utils.py

@@ -8,7 +8,6 @@ rate-limited provider concurrently.
 import random
 import threading
 import time
-from typing import Any
 
 # Monotonic counter for jitter seed uniqueness within the same process.
 # Protected by a lock to avoid race conditions in concurrent retry paths
@@ -16,14 +15,6 @@ from typing import Any
 _jitter_counter = 0
 _jitter_lock = threading.Lock()
 
-# Z.AI Coding Plan's GLM-5.2 endpoint often returns HTTP 429 code 1305
-# ("The service may be temporarily overloaded...") for otherwise valid
-# Hermes requests. Short retries tend to hammer the same overloaded window;
-# after a few normal retries, progressively widen the wait window. Keep the
-# cap interactive-friendly: a simple TUI message should fail visibly in minutes,
-# not sit silent for 20+ minutes.
-_ZAI_CODING_OVERLOAD_LONG_BACKOFF = (30.0, 60.0, 90.0, 120.0)
-
 
 def jittered_backoff(
     attempt: int,
@@ -64,66 +55,3 @@ def jittered_backoff(
     jitter = rng.uniform(0, jitter_ratio * delay)
 
     return delay + jitter
-
-
-def _error_text(error: Any) -> str:
-    """Best-effort flattened provider error text for retry classification."""
-    parts = [
-        error,
-        getattr(error, "message", None),
-        getattr(error, "body", None),
-        getattr(error, "response", None),
-    ]
-    return " ".join(str(part) for part in parts if part is not None).lower()
-
-
-def is_zai_coding_overload_error(*, base_url: str | None, model: str | None, error: Any) -> bool:
-    """Return True for Z.AI Coding Plan transient overload 429s.
-
-    The coding-plan endpoint reports overload as HTTP 429 with body code 1305
-    and message "The service may be temporarily overloaded...". Treat only
-    that narrow shape specially so ordinary quota/billing 429s still fail fast
-    through the existing classifier.
-    """
-    base = (base_url or "").lower()
-    model_name = (model or "").lower()
-    status = getattr(error, "status_code", None)
-    text = _error_text(error)
-    return (
-        status == 429
-        and "api.z.ai/api/coding/paas/v4" in base
-        and "glm-5.2" in model_name
-        and ("1305" in text or "temporarily overloaded" in text)
-    )
-
-
-def adaptive_rate_limit_backoff(
-    attempt: int,
-    *,
-    base_url: str | None,
-    model: str | None,
-    error: Any,
-    default_wait: float,
-    short_attempts: int = 3,
-) -> tuple[float, str | None]:
-    """Provider-aware rate-limit backoff.
-
-    For most providers this returns ``default_wait`` unchanged. For Z.AI
-    Coding Plan GLM-5.2 overloads, keep the first ``short_attempts`` retries on
-    the normal short exponential schedule, then switch to progressively longer
-    waits (30s → 60s → 90s → 120s, capped) plus light jitter.
-
-    ``attempt`` is 1-based, matching the retry loop's logged attempt number.
-    Returns ``(wait_seconds, reason_label)`` where ``reason_label`` is suitable
-    for status/log decoration when a provider-specific policy fired.
-    """
-    if not is_zai_coding_overload_error(base_url=base_url, model=model, error=error):
-        return default_wait, None
-    if attempt <= short_attempts:
-        return default_wait, "zai_coding_overload_short"
-
-    idx = min(attempt - short_attempts - 1, len(_ZAI_CODING_OVERLOAD_LONG_BACKOFF) - 1)
-    base_delay = _ZAI_CODING_OVERLOAD_LONG_BACKOFF[idx]
-    # A smaller jitter ratio keeps long waits readable while still avoiding
-    # synchronized retry storms across concurrent Hermes sessions.
-    return jittered_backoff(1, base_delay=base_delay, max_delay=base_delay, jitter_ratio=0.2), "zai_coding_overload_long"

agent/skill_utils.py

@@ -507,34 +507,6 @@ def get_all_skills_dirs() -> List[Path]:
     return dirs
 
 
-def _resolve_for_skill_ownership(path) -> Path:
-    path_obj = path if isinstance(path, Path) else Path(str(path))
-    try:
-        return path_obj.expanduser().resolve()
-    except (OSError, RuntimeError):
-        return path_obj.expanduser().absolute()
-
-
-def is_external_skill_path(path) -> bool:
-    """Return True when ``path`` lives under a configured external skills dir.
-
-    ``skills.external_dirs`` are externally owned: Hermes can discover and view
-    their skills, and foreground user-directed tool calls may still edit them,
-    but autonomous lifecycle maintenance must treat them as read-only. This
-    helper centralizes the ownership boundary so curator/reporting/tool paths do
-    not each need to re-interpret the config.
-    """
-    candidate = _resolve_for_skill_ownership(path)
-    for root in get_external_skills_dirs():
-        resolved_root = _resolve_for_skill_ownership(root)
-        try:
-            candidate.relative_to(resolved_root)
-            return True
-        except ValueError:
-            continue
-    return False
-
-
 # ── Condition extraction ──────────────────────────────────────────────────
 
 

agent/thinking_timeout_guidance.py

@@ -1,136 +0,0 @@
-"""Thinking-timeout detection and user-facing guidance for reasoning models.
-
-When a known reasoning model (NVIDIA Nemotron 3 Ultra, OpenAI o1/o3,
-Anthropic Opus 4.x thinking, DeepSeek R1, Qwen QwQ, xAI Grok reasoning)
-hits a transport-layer error before the first content token arrives, the
-upstream proxy has almost certainly idle-killed a long thinking stream —
-not a true context overflow or a configuration error.  The user needs
-distinct guidance for this case:
-
-    "The model's thinking phase exceeded the upstream proxy's idle
-     timeout before the first content token arrived.  This is a known
-     issue with reasoning models behind cloud gateways (NVIDIA NIM,
-     OpenAI, Anthropic, DeepSeek).  Workarounds in priority order:
-     1. Set `providers.<provider>.models.<model>.stale_timeout_seconds: 900`
-        in `~/.hermes/config.yaml` to extend the per-call timeout...
-     2. Lower `reasoning_budget` or set `reasoning_effort: medium`...
-     3. Use a smaller / faster reasoning model..."
-
-The existing `_is_stream_drop` guidance at
-``agent/conversation_loop.py:3464-3486`` fires for large-file-write
-stream drops ("try execute_code with Python's open() for large files")
-which is the WRONG advice for the thinking-timeout case.  This module
-provides the detection and the message as standalone helpers so the
-detection logic is unit-testable without driving the full retry loop,
-and the message text can be regression-tested for spelling and accuracy.
-
-Part 2 of Fixes #52310.
-"""
-
-from __future__ import annotations
-
-from typing import Optional
-
-
-# Substring set that identifies a transport-layer failure on the
-# response stream.  Same shape as the existing
-# ``_SERVER_DISCONNECT_PATTERNS`` in ``agent/error_classifier.py:394``
-# but extended to also catch the OSS-level error signature
-# (``broken pipe`` / ``errno 32``) that the upstream kill surfaces
-# to the OpenAI SDK wrapper.
-_THINKING_TIMEOUT_SUBSTRINGS: tuple[str, ...] = (
-    "broken pipe",
-    "errno 32",
-    "remote protocol",
-    "connection reset",
-    "connection lost",
-    "peer closed",
-    "server disconnected",
-)
-
-
-def is_thinking_timeout(classified: object, model: str, error_msg: str) -> bool:
-    """Return True when a reasoning model's thinking phase hit a transport kill.
-
-    Args:
-        classified: a :class:`agent.error_classifier.ClassifiedError` instance
-            (duck-typed here to avoid an import cycle in unit tests).
-        model: the model slug at failure time (e.g.
-            ``"nvidia/nemotron-3-ultra-550b-a55b"``).
-        error_msg: lowercased string representation of the underlying
-            exception (typically ``str(api_error).lower()``).
-
-    Returns True when ALL conditions hold:
-        1. ``classified.reason == FailoverReason.timeout`` (the classifier
-           override at ``agent/error_classifier.py:720-738`` ensures this
-           is the case for reasoning models even on large sessions).
-        2. ``api_error`` has no ``.status_code`` attribute set (transport
-           disconnect, not an HTTP error).
-        3. ``model`` is in the reasoning-model allowlist (reuses
-           ``agent.reasoning_timeouts.get_reasoning_stale_timeout_floor``).
-        4. ``error_msg`` contains one of the transport-kill substrings.
-
-    Non-reasoning models always return False.  Non-transport errors
-    (billing / rate_limit / auth / context_overflow / format_error)
-    always return False.  HTTP-status errors always return False.
-    """
-    # Import here (not at module top) to keep this helper cheap to
-    # import even from callers that don't need it.  ``agent.reasoning_timeouts``
-    # is small and dependency-free.
-    from agent.reasoning_timeouts import get_reasoning_stale_timeout_floor
-
-    # Condition 1: classifier says timeout.  Use a string/value check
-    # rather than importing FailoverReason so this module has zero
-    # import cycles from the error_classifier package.
-    reason = getattr(classified, "reason", None)
-    reason_value = getattr(reason, "value", None)
-    if reason_value != "timeout":
-        return False
-
-    # Condition 2: no HTTP status code (transport, not API error).
-    # Caller is expected to gate on ``getattr(api_error, "status_code", None) is None``
-    # before calling this helper; the surface here is just the post-gate
-    # boolean so the caller can pass an already-prepped error_msg.
-
-    # Condition 3: reasoning model allowlist.
-    if get_reasoning_stale_timeout_floor(model) is None:
-        return False
-
-    # Condition 4: transport-kill substring in the error message.
-    error_msg_lower = (error_msg or "").lower()
-    return any(p in error_msg_lower for p in _THINKING_TIMEOUT_SUBSTRINGS)
-
-
-def build_thinking_timeout_guidance(
-    provider: str, model: str, model_label: Optional[str] = None,
-) -> str:
-    """Return the user-facing guidance string appended to ``_final_response``.
-
-    Args:
-        provider: provider slug (e.g. ``"nvidia"``, ``"openai"``).
-        model: bare model slug the user would put in their config
-            (e.g. ``"nemotron-3-ultra-550b-a55b"`` if the user uses
-            NVIDIA direct, or the full ``"nvidia/nemotron-3-ultra-550b-a55b"``
-            if they go through an aggregator).  Used verbatim in the
-            config snippet so the user can copy-paste.
-        model_label: optional short label for the model name in the
-            prose (e.g. ``"Nemotron 3 Ultra"``).  Falls back to the
-            slug if not provided.
-    """
-    label = model_label or model
-    return (
-        "\n\nThe model's thinking phase exceeded the upstream proxy's "
-        "idle timeout before the first content token arrived. This is a "
-        f"known issue with reasoning models (like {label}) behind cloud "
-        "gateways (NVIDIA NIM, OpenAI, Anthropic, DeepSeek). Workarounds "
-        "in priority order:\n"
-        f"1. Set `providers.{provider}.models.{model}.stale_timeout_seconds: 900` "
-        "in `~/.hermes/config.yaml` to extend the per-call timeout. "
-        "(Hermes's built-in floor is 600s for known reasoning models — "
-        "if you still see this after raising, the upstream cap is even "
-        "shorter.)\n"
-        "2. Lower `reasoning_budget` or set `reasoning_effort: medium` on this "
-        "model if the provider supports it.\n"
-        "3. Use a smaller / faster reasoning model if the task doesn't "
-        "require deep thinking."
-    )

agent/tool_dispatch_helpers.py

@@ -11,8 +11,7 @@ Pure module-level utilities extracted from ``run_agent.py``:
   ``_append_subdir_hint_to_multimodal`` — envelope helpers for the
   ``{"_multimodal": True, "content": [...], "text_summary": ...}`` dict
   shape returned by tools like ``computer_use``.
-* ``_extract_file_mutation_targets`` / ``_extract_landed_file_mutation_paths`` /
-  ``_extract_error_preview`` —
+* ``_extract_file_mutation_targets`` / ``_extract_error_preview`` —
   per-turn file-mutation verifier inputs.
 * ``_trajectory_normalize_msg`` — strip image blobs from a message for
   trajectory saving.
@@ -270,35 +269,6 @@ def _extract_file_mutation_targets(tool_name: str, args: Dict[str, Any]) -> List
     return []
 
 
-def _extract_landed_file_mutation_paths(
-    tool_name: str,
-    args: Dict[str, Any],
-    result: Any,
-) -> List[str]:
-    """Return the concrete file paths a successful mutation reports."""
-    targets = _extract_file_mutation_targets(tool_name, args)
-    if tool_name not in _FILE_MUTATING_TOOLS or not isinstance(result, str):
-        return targets
-    try:
-        data = json.loads(result.strip())
-    except Exception:
-        return targets
-    if not isinstance(data, dict):
-        return targets
-
-    files = data.get("files_modified")
-    if isinstance(files, list):
-        landed = [str(p) for p in files if p]
-        if landed:
-            return landed
-
-    resolved = data.get("resolved_path")
-    if resolved:
-        return [str(resolved)]
-
-    return targets
-
-
 def _extract_error_preview(result: Any, max_len: int = 180) -> str:
     """Pull a one-line error summary out of a tool result for footer display."""
     text = _multimodal_text_summary(result) if result is not None else ""
@@ -441,7 +411,6 @@ __all__ = [
     "_multimodal_text_summary",
     "_append_subdir_hint_to_multimodal",
     "_extract_file_mutation_targets",
-    "_extract_landed_file_mutation_paths",
     "_extract_error_preview",
     "_trajectory_normalize_msg",
     "make_tool_result_message",

agent/tool_executor.py

@@ -26,7 +26,6 @@ from agent.display import (
     build_tool_preview as _build_tool_preview,
     get_cute_tool_message as _get_cute_tool_message_impl,
     get_tool_emoji as _get_tool_emoji,
-    redact_tool_args_for_display as _redact_tool_args_for_display,
     _detect_tool_failure,
 )
 from agent.tool_guardrails import ToolGuardrailDecision
@@ -470,11 +469,10 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
     if not agent.quiet_mode and getattr(agent, "tool_progress_mode", "all") != "off":
         print(f"  ⚡ Concurrent: {num_tools} tool calls — {tool_names_str}")
         for i, (tc, name, args, middleware_trace, block_result, blocked_by_guardrail) in enumerate(parsed_calls, 1):
-            display_args = _redact_tool_args_for_display(name, args) or args
-            args_str = json.dumps(display_args, ensure_ascii=False)
+            args_str = json.dumps(args, ensure_ascii=False)
             if agent.verbose_logging:
-                print(f"  📞 Tool {i}: {name}({list(display_args.keys())})")
-                print(agent._wrap_verbose("Args: ", json.dumps(display_args, indent=2, ensure_ascii=False)))
+                print(f"  📞 Tool {i}: {name}({list(args.keys())})")
+                print(agent._wrap_verbose("Args: ", json.dumps(args, indent=2, ensure_ascii=False)))
             else:
                 args_preview = args_str[:agent.log_prefix_chars] + "..." if len(args_str) > agent.log_prefix_chars else args_str
                 print(f"  📞 Tool {i}: {name}({list(args.keys())}) - {args_preview}")
@@ -484,9 +482,8 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
             continue
         if agent.tool_progress_callback:
             try:
-                display_args = _redact_tool_args_for_display(name, args) or args
-                preview = _build_tool_preview(name, display_args)
-                agent.tool_progress_callback("tool.started", name, preview, display_args)
+                preview = _build_tool_preview(name, args)
+                agent.tool_progress_callback("tool.started", name, preview, args)
             except Exception as cb_err:
                 logging.debug(f"Tool progress callback error: {cb_err}")
 
@@ -495,8 +492,7 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
             continue
         if agent.tool_start_callback:
             try:
-                display_args = _redact_tool_args_for_display(name, args) or args
-                agent.tool_start_callback(tc.id, name, display_args)
+                agent.tool_start_callback(tc.id, name, args)
             except Exception as cb_err:
                 logging.debug(f"Tool start callback error: {cb_err}")
 
@@ -796,8 +792,7 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
 
         if not blocked and agent.tool_complete_callback:
             try:
-                display_args = _redact_tool_args_for_display(name, args) or args
-                agent.tool_complete_callback(tc.id, name, display_args, function_result)
+                agent.tool_complete_callback(tc.id, name, args, function_result)
             except Exception as cb_err:
                 logging.debug(f"Tool complete callback error: {cb_err}")
 
@@ -959,11 +954,10 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
             agent._iters_since_skill = 0
 
         if not agent.quiet_mode and getattr(agent, "tool_progress_mode", "all") != "off":
-            display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-            args_str = json.dumps(display_args, ensure_ascii=False)
+            args_str = json.dumps(function_args, ensure_ascii=False)
             if agent.verbose_logging:
-                print(f"  📞 Tool {i}: {function_name}({list(display_args.keys())})")
-                print(agent._wrap_verbose("Args: ", json.dumps(display_args, indent=2, ensure_ascii=False)))
+                print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())})")
+                print(agent._wrap_verbose("Args: ", json.dumps(function_args, indent=2, ensure_ascii=False)))
             else:
                 args_preview = args_str[:agent.log_prefix_chars] + "..." if len(args_str) > agent.log_prefix_chars else args_str
                 print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())}) - {args_preview}")
@@ -984,16 +978,14 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
 
         if not _execution_blocked and agent.tool_progress_callback:
             try:
-                display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-                preview = _build_tool_preview(function_name, display_args)
-                agent.tool_progress_callback("tool.started", function_name, preview, display_args)
+                preview = _build_tool_preview(function_name, function_args)
+                agent.tool_progress_callback("tool.started", function_name, preview, function_args)
             except Exception as cb_err:
                 logging.debug(f"Tool progress callback error: {cb_err}")
 
         if not _execution_blocked and agent.tool_start_callback:
             try:
-                display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-                agent.tool_start_callback(tool_call.id, function_name, display_args)
+                agent.tool_start_callback(tool_call.id, function_name, function_args)
             except Exception as cb_err:
                 logging.debug(f"Tool start callback error: {cb_err}")
 
@@ -1223,8 +1215,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
             if agent._should_emit_quiet_tool_messages():
                 face = random.choice(KawaiiSpinner.get_waiting_faces())
                 emoji = _get_tool_emoji(function_name)
-                display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-                preview = _build_tool_preview(function_name, display_args) or function_name
+                preview = _build_tool_preview(function_name, function_args) or function_name
                 spinner = KawaiiSpinner(f"{face} {emoji} {preview}", spinner_type='dots', print_fn=agent._print_fn)
                 spinner.start()
             _ce_result = None
@@ -1257,8 +1248,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
             if agent._should_emit_quiet_tool_messages() and agent._should_start_quiet_spinner():
                 face = random.choice(KawaiiSpinner.get_waiting_faces())
                 emoji = _get_tool_emoji(function_name)
-                display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-                preview = _build_tool_preview(function_name, display_args) or function_name
+                preview = _build_tool_preview(function_name, function_args) or function_name
                 spinner = KawaiiSpinner(f"{face} {emoji} {preview}", spinner_type='dots', print_fn=agent._print_fn)
                 spinner.start()
             _mem_result = None
@@ -1289,8 +1279,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
             if agent._should_emit_quiet_tool_messages() and agent._should_start_quiet_spinner():
                 face = random.choice(KawaiiSpinner.get_waiting_faces())
                 emoji = _get_tool_emoji(function_name)
-                display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-                preview = _build_tool_preview(function_name, display_args) or function_name
+                preview = _build_tool_preview(function_name, function_args) or function_name
                 spinner = KawaiiSpinner(f"{face} {emoji} {preview}", spinner_type='dots', print_fn=agent._print_fn)
                 spinner.start()
             _spinner_result = None
@@ -1452,8 +1441,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
 
         if not _execution_blocked and agent.tool_complete_callback:
             try:
-                display_args = _redact_tool_args_for_display(function_name, function_args) or function_args
-                agent.tool_complete_callback(tool_call.id, function_name, display_args, function_result)
+                agent.tool_complete_callback(tool_call.id, function_name, function_args, function_result)
             except Exception as cb_err:
                 logging.debug(f"Tool complete callback error: {cb_err}")
 

agent/transports/codex.py

@@ -5,47 +5,12 @@ This transport owns format conversion and normalization — NOT client lifecycle
 streaming, or the _run_codex_stream() call path.
 """
 
-import hashlib
-import json
 from typing import Any, Dict, List, Optional
 
 from agent.transports.base import ProviderTransport
 from agent.transports.types import NormalizedResponse, ToolCall
 
 
-def _content_cache_key(instructions: str, tools: Optional[List[Dict[str, Any]]]) -> Optional[str]:
-    """Content-address the prompt cache key from the static request prefix.
-
-    Returns ``pck_<sha256[:24]>`` of (instructions + sorted tool schemas), or
-    None when there is nothing static to key on. The cache key is a routing
-    hint only — never a correctness boundary — so two requests sharing a system
-    prompt and tool set intentionally resolve to the same warm prefix bucket.
-
-    The fix this exists for: recurring cron jobs build session_id as
-    ``cron_<id>_<timestamp>``, so using session_id as the cache key made every
-    fire cache-cold. The static prefix (identity + tools) is identical across
-    fires, so hashing it gives a stable key that stays warm within the
-    provider's cache TTL. Sorting tools by name keeps the hash insertion-order
-    independent.
-    """
-    if not instructions and not tools:
-        return None
-    tools_part = ""
-    if tools:
-        sorted_tools = sorted(
-            (t for t in tools if isinstance(t, dict)),
-            key=lambda t: str(t.get("name") or t.get("type") or ""),
-        )
-        tools_part = json.dumps(
-            sorted_tools, sort_keys=True, ensure_ascii=False, separators=(",", ":")
-        )
-    # \x00 separator so instructions ending in the tool JSON can't collide with
-    # a request whose instructions contain that JSON and whose tools are empty.
-    content = f"{instructions or ''}\x00{tools_part}"
-    digest = hashlib.sha256(content.encode("utf-8", errors="replace")).hexdigest()[:24]
-    return f"pck_{digest}"
-
-
 class ResponsesApiTransport(ProviderTransport):
     """Transport for api_mode='codex_responses'.
 
@@ -106,10 +71,7 @@ class ResponsesApiTransport(ProviderTransport):
         params:
             instructions: str — system prompt (extracted from messages[0] if not given)
             reasoning_config: dict | None — {effort, enabled}
-            session_id: str | None — transcript/session id; drives the xAI
-                x-grok-conv-id header and the Codex cache-scope headers, and is
-                the fallback prompt_cache_key when there is no static prefix to
-                content-address
+            session_id: str | None — used for prompt_cache_key + xAI conv header
             max_tokens: int | None — max_output_tokens
             timeout: float | None — per-request timeout forwarded to the SDK
             request_overrides: dict | None — extra kwargs merged in
@@ -250,17 +212,10 @@ class ResponsesApiTransport(ProviderTransport):
             kwargs["parallel_tool_calls"] = True
 
         session_id = params.get("session_id")
-        # prompt_cache_key is content-addressed from the static prefix
-        # (instructions + tools), NOT session_id — recurring cron jobs carry a
-        # per-fire timestamp in session_id (cron_<id>_<ts>) that made every run
-        # cache-cold. session_id is left untouched for transcript isolation and
-        # the cache-scope routing headers below. Falls back to session_id when
-        # there is no static content to hash.
-        cache_key = _content_cache_key(instructions, response_tools) or session_id
         # xAI Responses takes prompt_cache_key in extra_body (set further
         # down); GitHub Models opts out of cache-key routing entirely.
-        if not is_github_responses and not is_xai_responses and cache_key:
-            kwargs["prompt_cache_key"] = cache_key
+        if not is_github_responses and not is_xai_responses and session_id:
+            kwargs["prompt_cache_key"] = session_id
 
         if reasoning_enabled and is_xai_responses:
             from agent.model_metadata import grok_supports_reasoning_effort
@@ -371,7 +326,7 @@ class ResponsesApiTransport(ProviderTransport):
             merged_extra_body: Dict[str, Any] = {}
             if isinstance(existing_extra_body, dict):
                 merged_extra_body.update(existing_extra_body)
-            merged_extra_body.setdefault("prompt_cache_key", cache_key)
+            merged_extra_body.setdefault("prompt_cache_key", session_id)
             kwargs["extra_body"] = merged_extra_body
 
         return kwargs

agent/turn_context.py

@@ -29,10 +29,7 @@ from dataclasses import dataclass
 from typing import Any, Dict, List, Optional
 
 from agent.iteration_budget import IterationBudget
-from agent.model_metadata import (
-    estimate_messages_tokens_rough,
-    estimate_request_tokens_rough,
-)
+from agent.model_metadata import estimate_request_tokens_rough
 
 logger = logging.getLogger(__name__)
 
@@ -60,34 +57,6 @@ def _compression_made_progress(
     return orig_tokens > 0 and new_tokens < orig_tokens * 0.95
 
 
-def _should_run_preflight_estimate(
-    messages: List[Dict[str, Any]],
-    protect_first_n: int,
-    protect_last_n: int,
-    threshold_tokens: int,
-) -> bool:
-    """Cheap gate for the (expensive) full preflight token estimate.
-
-    Returns ``True`` when either:
-      (a) message count exceeds the protected ranges (the historical gate), or
-      (b) a cheap char-based estimate already crosses the configured threshold
-          — the few-but-huge case from issue #27405 that the count-only gate
-          would silently skip (a handful of very large messages never trips
-          the count condition, so compression was never attempted and the
-          turn hit a hard context-overflow error).
-
-    Branch (b) uses ``estimate_messages_tokens_rough`` (the shared char-based
-    estimator) so a single large base64 image isn't mistaken for ~250K tokens.
-    It intentionally undercounts vs. the full request estimate — it omits the
-    system prompt and tool schemas — because it is only a *hint* deciding
-    whether to pay for the authoritative ``estimate_request_tokens_rough``,
-    which (together with ``should_compress``) makes the real decision.
-    """
-    if len(messages) > protect_first_n + protect_last_n + 1:
-        return True
-    return estimate_messages_tokens_rough(messages) >= threshold_tokens
-
-
 @dataclass
 class TurnContext:
     """Values produced by the turn prologue and consumed by the turn loop."""
@@ -142,13 +111,7 @@ def build_turn_context(
     # Guard stdio against OSError from broken pipes (systemd/headless/daemon).
     install_safe_stdio()
 
-    # NOTE: the DB session row is created later, AFTER the system prompt is
-    # restored/built (see _ensure_db_session() below the system-prompt block).
-    # Creating it here — before _cached_system_prompt is populated — inserts a
-    # row with system_prompt=NULL on a fresh API/gateway agent that carries
-    # client-managed history, which then trips the "stored system prompt is
-    # null; rebuilding from scratch" warning and a needless first-turn prefix
-    # cache miss. (Issue #45499.)
+    agent._ensure_db_session()
 
     # Tell auxiliary_client what the live main provider/model are for this turn.
     try:
@@ -315,11 +278,6 @@ def build_turn_context(
 
     active_system_prompt = agent._cached_system_prompt
 
-    # Create the DB session row now that _cached_system_prompt is populated, so
-    # the persisted snapshot is written non-NULL on the first turn (Issue
-    # #45499). Idempotent: _ensure_db_session() no-ops once the row exists.
-    agent._ensure_db_session()
-
     # Crash-resilience: persist the inbound user turn as soon as the session row exists.
     try:
         agent._persist_session(messages, conversation_history)
@@ -331,14 +289,10 @@ def build_turn_context(
         )
 
     # ── Preflight context compression ──
-    # Gate the (expensive) full token estimate behind a cheap pre-check.
-    # See ``_should_run_preflight_estimate`` for the OR semantics that fix
-    # issue #27405 (a few very large messages slipping past the count gate).
-    if agent.compression_enabled and _should_run_preflight_estimate(
-        messages,
-        agent.context_compressor.protect_first_n,
-        agent.context_compressor.protect_last_n,
-        agent.context_compressor.threshold_tokens,
+    if (
+        agent.compression_enabled
+        and len(messages) > agent.context_compressor.protect_first_n
+                            + agent.context_compressor.protect_last_n + 1
     ):
         _preflight_tokens = estimate_request_tokens_rough(
             messages,
@@ -438,8 +392,6 @@ def build_turn_context(
 
     # Per-turn file-mutation verifier state.
     agent._turn_failed_file_mutations = {}
-    agent._turn_file_mutation_paths = set()
-    agent._verification_stop_nudges = 0
 
     # Record the execution thread so interrupt()/clear_interrupt() can scope
     # the tool-level interrupt signal to THIS agent's thread only.

agent/turn_finalizer.py

@@ -181,9 +181,13 @@ def finalize_turn(
         # here instead. On an interrupt ``final_response`` is typically
         # empty, so fall back to an explicit placeholder rather than
         # persisting an empty-content assistant turn.
-        if interrupted:
-            from agent.message_sanitization import close_interrupted_tool_sequence
-            close_interrupted_tool_sequence(messages, final_response)
+        if interrupted and messages and messages[-1].get("role") == "tool":
+            messages.append(
+                {
+                    "role": "assistant",
+                    "content": (final_response or "").strip() or "Operation interrupted.",
+                }
+            )
 
         agent._persist_session(messages, conversation_history)
     except Exception as _persist_err:

agent/verification_evidence.py

@@ -1,618 +0,0 @@
-"""Coding verification evidence ledger.
-
-This module records what the agent actually proved while working in a code
-workspace. It is deliberately passive: it never decides to run a suite, never
-blocks completion, and never upgrades targeted checks into "repo green".
-"""
-
-from __future__ import annotations
-
-import json
-import re
-import shlex
-import sqlite3
-import tempfile
-import threading
-from dataclasses import dataclass
-from datetime import datetime, timedelta, timezone
-from pathlib import Path
-from typing import Any, Optional
-
-from hermes_constants import get_hermes_home
-
-
-_DB_LOCK = threading.Lock()
-_MAX_OUTPUT_SUMMARY_CHARS = 2000
-_MAX_EVIDENCE_AGE_DAYS = 30
-_MAX_EVENTS_PER_SESSION_ROOT = 100
-_MAX_TOTAL_UNREFERENCED_EVENTS = 10_000
-_AD_HOC_SCRIPT_NAME_PREFIXES = ("hermes-verify-", "hermes-ad-hoc-")
-_VERIFY_SCHEMA_VERSION = 1
-_SHELL_SPLIT_RE = re.compile(r"\s*(?:&&|\|\||;)\s*")
-
-
-@dataclass(frozen=True)
-class VerificationEvidence:
-    """A classified command result worth recording."""
-
-    command: str
-    canonical_command: str
-    kind: str
-    scope: str
-    status: str
-    exit_code: int
-    cwd: str
-    root: str
-    session_id: str
-    output_summary: str = ""
-
-
-def _utc_now() -> str:
-    return datetime.now(timezone.utc).isoformat()
-
-
-def _retention_cutoff() -> str:
-    return (datetime.now(timezone.utc) - timedelta(days=_MAX_EVIDENCE_AGE_DAYS)).isoformat()
-
-
-def _db_path() -> Path:
-    return get_hermes_home() / "verification_evidence.db"
-
-
-def _connect() -> sqlite3.Connection:
-    path = _db_path()
-    path.parent.mkdir(parents=True, exist_ok=True)
-    conn = sqlite3.connect(path)
-    conn.execute("PRAGMA journal_mode=WAL")
-    conn.execute("PRAGMA busy_timeout=5000")
-    conn.row_factory = sqlite3.Row
-    _ensure_schema(conn)
-    return conn
-
-
-def _ensure_schema(conn: sqlite3.Connection) -> None:
-    conn.execute(
-        """
-        CREATE TABLE IF NOT EXISTS meta (
-            key TEXT PRIMARY KEY,
-            value TEXT NOT NULL
-        )
-        """
-    )
-    conn.execute(
-        """
-        CREATE TABLE IF NOT EXISTS verification_events (
-            id INTEGER PRIMARY KEY AUTOINCREMENT,
-            created_at TEXT NOT NULL,
-            session_id TEXT NOT NULL,
-            cwd TEXT NOT NULL,
-            root TEXT NOT NULL,
-            command TEXT NOT NULL,
-            canonical_command TEXT NOT NULL,
-            kind TEXT NOT NULL,
-            scope TEXT NOT NULL,
-            status TEXT NOT NULL,
-            exit_code INTEGER NOT NULL,
-            output_summary TEXT NOT NULL
-        )
-        """
-    )
-    conn.execute(
-        """
-        CREATE TABLE IF NOT EXISTS verification_state (
-            session_id TEXT NOT NULL,
-            root TEXT NOT NULL,
-            last_event_id INTEGER,
-            last_edit_at TEXT,
-            changed_paths_json TEXT NOT NULL DEFAULT '[]',
-            PRIMARY KEY (session_id, root)
-        )
-        """
-    )
-    conn.execute(
-        """
-        CREATE INDEX IF NOT EXISTS idx_verification_events_session_root
-        ON verification_events(session_id, root, id DESC)
-        """
-    )
-    conn.execute(
-        "INSERT OR REPLACE INTO meta(key, value) VALUES ('schema_version', ?)",
-        (str(_VERIFY_SCHEMA_VERSION),),
-    )
-    conn.commit()
-
-
-def _split_segment_tokens(command: str) -> list[list[str]]:
-    segments: list[list[str]] = []
-    for segment in _SHELL_SPLIT_RE.split(command.strip()):
-        if not segment:
-            continue
-        try:
-            tokens = shlex.split(segment)
-        except ValueError:
-            continue
-        if tokens:
-            segments.append(tokens)
-    return segments
-
-
-def _clean_token(token: str) -> str:
-    token = token.strip()
-    while token.startswith("./"):
-        token = token[2:]
-    return token
-
-
-def _canonical_tokens(canonical: str) -> list[str]:
-    try:
-        return [_clean_token(t) for t in shlex.split(canonical) if t]
-    except ValueError:
-        return []
-
-
-def _find_subsequence(tokens: list[str], needle: list[str]) -> Optional[int]:
-    if not tokens or not needle or len(needle) > len(tokens):
-        return None
-    cleaned = [_clean_token(t) for t in tokens]
-    for idx in range(0, len(cleaned) - len(needle) + 1):
-        if cleaned[idx:idx + len(needle)] == needle:
-            return idx
-    return None
-
-
-def _strip_command_prefix(tokens: list[str]) -> list[str]:
-    """Remove harmless command prefixes before matching canonical commands."""
-    remaining = list(tokens)
-    if remaining and remaining[0] == "env":
-        remaining = remaining[1:]
-    while remaining and "=" in remaining[0] and not remaining[0].startswith("-"):
-        remaining = remaining[1:]
-    while remaining and remaining[0] in {"command", "time", "noglob"}:
-        remaining = remaining[1:]
-    return remaining
-
-
-def _equivalent_needles(needle: list[str]) -> list[list[str]]:
-    """Return command spellings equivalent to the detected canonical command."""
-    candidates = [needle]
-    if len(needle) >= 3 and needle[1] == "run":
-        package_manager = needle[0]
-        script_name = needle[2]
-        if package_manager in {"npm", "pnpm", "yarn", "bun"}:
-            candidates.append([package_manager, script_name])
-    if len(needle) == 1 and "/" in needle[0]:
-        candidates.extend([["bash", needle[0]], ["sh", needle[0]]])
-    if needle == ["pytest"]:
-        candidates.extend(
-            [
-                ["python", "-m", "pytest"],
-                ["python3", "-m", "pytest"],
-                ["uv", "run", "pytest"],
-                ["poetry", "run", "pytest"],
-                ["pipenv", "run", "pytest"],
-            ]
-        )
-    return candidates
-
-
-def _find_canonical_match(command: str, canonical_commands: list[str]) -> Optional[tuple[str, list[str]]]:
-    """Return ``(canonical, trailing_args)`` for the first detected command."""
-
-    segments = _split_segment_tokens(command)
-    for canonical in canonical_commands:
-        needle = _canonical_tokens(canonical)
-        if not needle:
-            continue
-        for tokens in segments:
-            candidate_tokens = _strip_command_prefix(tokens)
-            for candidate in _equivalent_needles(needle):
-                if candidate_tokens[:len(candidate)] == candidate:
-                    return canonical, candidate_tokens[len(candidate):]
-    return None
-
-
-def _kind_for_command(canonical: str) -> str:
-    lowered = canonical.lower()
-    if any(word in lowered for word in ("lint", "eslint", "ruff")):
-        return "lint"
-    if any(word in lowered for word in ("typecheck", "tsc", "mypy", "pyright", "ty")):
-        return "typecheck"
-    if "build" in lowered:
-        return "build"
-    if "fmt" in lowered or "format" in lowered:
-        return "format"
-    if "check" in lowered and "test" not in lowered:
-        return "check"
-    return "test"
-
-
-def _looks_like_target(arg: str) -> bool:
-    if not arg or arg.startswith("-") or "=" in arg:
-        return False
-    return (
-        "/" in arg
-        or "\\" in arg
-        or "::" in arg
-        or arg.endswith((".py", ".js", ".jsx", ".ts", ".tsx", ".rs", ".go", ".java"))
-        or arg.startswith(("test_", "tests", "spec", "__tests__"))
-    )
-
-
-def _scope_for_args(args: list[str]) -> str:
-    return "targeted" if any(_looks_like_target(arg) for arg in args) else "full"
-
-
-def _is_under_temp_dir(token: str) -> bool:
-    if not token or token.startswith("-"):
-        return False
-    try:
-        path = Path(token).expanduser()
-        if not path.is_absolute():
-            return False
-        resolved = path.resolve()
-        temp_root = Path(tempfile.gettempdir()).resolve()
-        return resolved == temp_root or temp_root in resolved.parents
-    except Exception:
-        return False
-
-
-def _is_under_root(token: str, root: str | Path | None) -> bool:
-    if not root:
-        return False
-    try:
-        path = Path(token).expanduser().resolve()
-        root_path = Path(root).expanduser().resolve()
-        return path == root_path or root_path in path.parents
-    except Exception:
-        return False
-
-
-def _is_temp_script_path(token: str, root: str | Path | None) -> bool:
-    try:
-        name = Path(token).expanduser().name
-    except Exception:
-        return False
-    return (
-        name.startswith(_AD_HOC_SCRIPT_NAME_PREFIXES)
-        and _is_under_temp_dir(token)
-        and not _is_under_root(token, root)
-    )
-
-
-def _ad_hoc_script_args(tokens: list[str], root: str | Path | None) -> Optional[list[str]]:
-    candidate_tokens = _strip_command_prefix(tokens)
-    if not candidate_tokens:
-        return None
-    command = candidate_tokens[0]
-    if _is_temp_script_path(command, root):
-        return candidate_tokens[1:]
-    if command in {"python", "python3", "node", "bash", "sh", "ruby", "perl"}:
-        for idx, token in enumerate(candidate_tokens[1:], start=1):
-            if token == "--":
-                continue
-            if _is_temp_script_path(token, root):
-                return candidate_tokens[idx + 1:]
-            if not token.startswith("-"):
-                return None
-    return None
-
-
-def _find_ad_hoc_match(command: str, root: str | Path | None) -> Optional[list[str]]:
-    for tokens in _split_segment_tokens(command):
-        trailing_args = _ad_hoc_script_args(tokens, root)
-        if trailing_args is not None:
-            return trailing_args
-    return None
-
-
-def _summarize_output(output: str) -> str:
-    text = (output or "").strip()
-    if len(text) <= _MAX_OUTPUT_SUMMARY_CHARS:
-        return text
-    head = _MAX_OUTPUT_SUMMARY_CHARS // 3
-    tail = _MAX_OUTPUT_SUMMARY_CHARS - head
-    return (
-        text[:head]
-        + f"\n... [{len(text) - _MAX_OUTPUT_SUMMARY_CHARS} chars omitted] ...\n"
-        + text[-tail:]
-    )
-
-
-def _prune_old_events(conn: sqlite3.Connection, *, session_id: str, root: str) -> None:
-    """Bound ledger growth without deleting the current state pointer."""
-    cutoff = _retention_cutoff()
-    conn.execute(
-        """
-        DELETE FROM verification_events
-        WHERE session_id = ?
-          AND root = ?
-          AND id NOT IN (
-              SELECT id FROM verification_events
-              WHERE session_id = ? AND root = ?
-              ORDER BY id DESC
-              LIMIT ?
-          )
-        """,
-        (session_id, root, session_id, root, _MAX_EVENTS_PER_SESSION_ROOT),
-    )
-    conn.execute(
-        """
-        DELETE FROM verification_state
-        WHERE (
-            last_edit_at IS NOT NULL
-            AND last_edit_at < ?
-        )
-        OR (
-            last_edit_at IS NULL
-            AND last_event_id IN (
-                SELECT id FROM verification_events
-                WHERE created_at < ?
-            )
-        )
-        """,
-        (cutoff, cutoff),
-    )
-    conn.execute(
-        """
-        DELETE FROM verification_events
-        WHERE created_at < ?
-          AND id NOT IN (
-              SELECT last_event_id FROM verification_state
-              WHERE last_event_id IS NOT NULL
-          )
-        """,
-        (cutoff,),
-    )
-    conn.execute(
-        """
-        DELETE FROM verification_events
-        WHERE id NOT IN (
-            SELECT id FROM verification_events
-            ORDER BY id DESC
-            LIMIT ?
-        )
-          AND id NOT IN (
-              SELECT last_event_id FROM verification_state
-              WHERE last_event_id IS NOT NULL
-          )
-        """,
-        (_MAX_TOTAL_UNREFERENCED_EVENTS,),
-    )
-
-
-def classify_verification_command(
-    command: str,
-    *,
-    cwd: str | Path | None = None,
-    session_id: str | None = None,
-    exit_code: int = 0,
-    output: str = "",
-) -> Optional[VerificationEvidence]:
-    """Classify a terminal command as verification evidence, if applicable."""
-
-    if not command or not isinstance(command, str):
-        return None
-    try:
-        from agent.coding_context import project_facts_for
-
-        facts = project_facts_for(cwd)
-    except Exception:
-        facts = None
-    if not facts:
-        return None
-
-    verify_commands = list(facts.get("verifyCommands") or [])
-    match = _find_canonical_match(command, verify_commands)
-    is_ad_hoc = False
-    if match is None and not verify_commands:
-        ad_hoc_args = _find_ad_hoc_match(command, facts.get("root"))
-        if ad_hoc_args is not None:
-            match = ("ad-hoc verification script", ad_hoc_args)
-            is_ad_hoc = True
-    if match is None:
-        return None
-
-    canonical, trailing_args = match
-    return VerificationEvidence(
-        command=command,
-        canonical_command=canonical,
-        kind="ad_hoc" if is_ad_hoc else _kind_for_command(canonical),
-        scope="targeted" if is_ad_hoc else _scope_for_args(trailing_args),
-        status="passed" if int(exit_code) == 0 else "failed",
-        exit_code=int(exit_code),
-        cwd=str(Path(cwd or ".").resolve()),
-        root=str(facts.get("root") or Path(cwd or ".").resolve()),
-        session_id=str(session_id or "default"),
-        output_summary=_summarize_output(output),
-    )
-
-
-def record_terminal_result(
-    *,
-    command: str,
-    cwd: str | Path | None,
-    session_id: str | None,
-    exit_code: int,
-    output: str = "",
-) -> Optional[dict[str, Any]]:
-    """Record a foreground terminal result when it is verification evidence."""
-
-    evidence = classify_verification_command(
-        command,
-        cwd=cwd,
-        session_id=session_id,
-        exit_code=exit_code,
-        output=output,
-    )
-    if evidence is None:
-        return None
-
-    created_at = _utc_now()
-    with _DB_LOCK:
-        with _connect() as conn:
-            cur = conn.execute(
-                """
-                INSERT INTO verification_events(
-                    created_at, session_id, cwd, root, command, canonical_command,
-                    kind, scope, status, exit_code, output_summary
-                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-                """,
-                (
-                    created_at,
-                    evidence.session_id,
-                    evidence.cwd,
-                    evidence.root,
-                    evidence.command,
-                    evidence.canonical_command,
-                    evidence.kind,
-                    evidence.scope,
-                    evidence.status,
-                    evidence.exit_code,
-                    evidence.output_summary,
-                ),
-            )
-            if cur.lastrowid is None:
-                raise RuntimeError("verification event insert did not return an id")
-            event_id = int(cur.lastrowid)
-            conn.execute(
-                """
-                INSERT INTO verification_state(
-                    session_id, root, last_event_id, last_edit_at, changed_paths_json
-                ) VALUES (?, ?, ?, NULL, '[]')
-                ON CONFLICT(session_id, root) DO UPDATE SET
-                    last_event_id = excluded.last_event_id,
-                    last_edit_at = NULL,
-                    changed_paths_json = '[]'
-                """,
-                (evidence.session_id, evidence.root, event_id),
-            )
-            _prune_old_events(conn, session_id=evidence.session_id, root=evidence.root)
-            conn.commit()
-
-    return {"id": event_id, **evidence.__dict__, "created_at": created_at}
-
-
-def mark_workspace_edited(
-    *,
-    session_id: str | None,
-    cwd: str | Path | None,
-    paths: list[str] | tuple[str, ...] | None = None,
-) -> Optional[dict[str, Any]]:
-    """Mark verification evidence stale after a successful file edit."""
-
-    try:
-        from agent.coding_context import project_facts_for
-
-        facts = project_facts_for(cwd)
-    except Exception:
-        facts = None
-    if not facts:
-        return None
-
-    sid = str(session_id or "default")
-    root = str(facts.get("root") or Path(cwd or ".").resolve())
-    changed_paths = sorted({str(p) for p in (paths or []) if p})
-    edited_at = _utc_now()
-
-    with _DB_LOCK:
-        with _connect() as conn:
-            row = conn.execute(
-                """
-                SELECT changed_paths_json FROM verification_state
-                WHERE session_id = ? AND root = ?
-                """,
-                (sid, root),
-            ).fetchone()
-            existing: set[str] = set()
-            if row is not None:
-                try:
-                    existing = set(json.loads(row["changed_paths_json"] or "[]"))
-                except (TypeError, ValueError):
-                    existing = set()
-            merged = sorted((existing | set(changed_paths)))[-200:]
-            conn.execute(
-                """
-                INSERT INTO verification_state(
-                    session_id, root, last_event_id, last_edit_at, changed_paths_json
-                ) VALUES (?, ?, NULL, ?, ?)
-                ON CONFLICT(session_id, root) DO UPDATE SET
-                    last_edit_at = excluded.last_edit_at,
-                    changed_paths_json = excluded.changed_paths_json
-                """,
-                (sid, root, edited_at, json.dumps(merged)),
-            )
-            conn.commit()
-
-    return {"session_id": sid, "root": root, "last_edit_at": edited_at, "changed_paths": changed_paths}
-
-
-def verification_status(
-    *,
-    session_id: str | None,
-    cwd: str | Path | None,
-) -> dict[str, Any]:
-    """Return the best known verification state for a session/workspace."""
-
-    try:
-        from agent.coding_context import project_facts_for
-
-        facts = project_facts_for(cwd)
-    except Exception:
-        facts = None
-    if not facts:
-        return {"status": "not_applicable", "evidence": None}
-
-    sid = str(session_id or "default")
-    root = str(facts.get("root") or Path(cwd or ".").resolve())
-    with _DB_LOCK:
-        with _connect() as conn:
-            state = conn.execute(
-                """
-                SELECT last_event_id, last_edit_at, changed_paths_json
-                FROM verification_state
-                WHERE session_id = ? AND root = ?
-                """,
-                (sid, root),
-            ).fetchone()
-            if state is None:
-                return {
-                    "status": "unverified",
-                    "evidence": None,
-                    "root": root,
-                    "session_id": sid,
-                    "changed_paths": [],
-                }
-            event = None
-            if state["last_event_id"] is not None:
-                event = conn.execute(
-                    "SELECT * FROM verification_events WHERE id = ?",
-                    (state["last_event_id"],),
-                ).fetchone()
-
-    changed_paths: list[str] = []
-    try:
-        changed_paths = json.loads(state["changed_paths_json"] or "[]")
-    except (TypeError, ValueError):
-        changed_paths = []
-
-    if event is None:
-        return {
-            "status": "unverified",
-            "evidence": None,
-            "root": root,
-            "session_id": sid,
-            "changed_paths": changed_paths,
-        }
-
-    evidence = dict(event)
-    if state["last_edit_at"] and state["last_edit_at"] > evidence["created_at"]:
-        status = "stale"
-    else:
-        status = evidence["status"]
-    return {
-        "status": status,
-        "evidence": evidence,
-        "root": root,
-        "session_id": sid,
-        "changed_paths": changed_paths,
-    }

agent/verification_stop.py

@@ -1,240 +0,0 @@
-"""Turn-end verification guard for coding edits.
-
-This module is intentionally policy-only. It never runs checks itself; it turns
-the passive verification ledger into a bounded follow-up when the model tries to
-finish immediately after editing code without fresh evidence.
-"""
-
-from __future__ import annotations
-
-import os
-import tempfile
-from pathlib import Path
-from typing import Any, Iterable
-
-
-_MAX_CHANGED_PATHS_IN_NUDGE = 8
-
-# Session identities (platform or source) that are NOT human conversational
-# messaging surfaces: interactive coding surfaces (CLI, TUI, desktop, codex,
-# local, gateway) and programmatic callers (API server, webhooks, tools).
-# Verify-on-stop stays ON by default for these. Any other resolved gateway
-# platform is a conversational messaging surface (Telegram, Discord, WhatsApp,
-# Signal, Slack, etc.) where the verification narrative would reach a human as
-# chat noise, so it defaults OFF. Mirrors LOCAL_SESSION_SOURCE_IDS in
-# apps/desktop/src/lib/session-source.ts; keep roughly in sync when adding a
-# local or programmatic surface. Default-deny by design: an unrecognized
-# identity is treated as messaging (OFF) so a new chat platform never leaks the
-# verification receipt before this set is updated.
-_NON_MESSAGING_SESSION_SURFACES = frozenset(
-    {
-        "",
-        "cli",
-        "codex",
-        "desktop",
-        "gateway",
-        "local",
-        "tui",
-        "tool",
-        "api_server",
-        "webhook",
-        "msgraph_webhook",
-    }
-)
-
-
-def _session_is_messaging_surface() -> bool:
-    """Return whether this turn is delivered over a human messaging channel.
-
-    The gateway binds the platform value (e.g. ``telegram``) to
-    ``HERMES_SESSION_PLATFORM``; the CLI and TUI set ``HERMES_SESSION_SOURCE``
-    (e.g. ``cli``, ``tui``) instead. Both are consulted via the session-context
-    helper (with an ``os.environ`` fallback), alongside the ``HERMES_PLATFORM``
-    override, matching the sibling platform resolution in
-    ``agent/skill_commands.py`` and ``agent/prompt_builder.py``. A turn is a
-    messaging surface when a resolved identity is present and is not a known
-    non-messaging surface.
-    """
-    try:
-        from gateway.session_context import get_session_env
-
-        platform = (
-            os.getenv("HERMES_PLATFORM")
-            or get_session_env("HERMES_SESSION_PLATFORM", "")
-        )
-        source = get_session_env("HERMES_SESSION_SOURCE", "")
-    except Exception:
-        platform = os.getenv("HERMES_PLATFORM", "") or os.environ.get(
-            "HERMES_SESSION_PLATFORM", ""
-        )
-        source = os.environ.get("HERMES_SESSION_SOURCE", "")
-    for identity in (platform, source):
-        identity = str(identity or "").strip().lower()
-        if identity and identity not in _NON_MESSAGING_SESSION_SURFACES:
-            return True
-    return False
-
-
-def verify_on_stop_enabled(config: dict[str, Any] | None = None) -> bool:
-    """Return whether edit -> verify-before-finish behavior is enabled.
-
-    Precedence: an explicit ``HERMES_VERIFY_ON_STOP`` env var wins, then an
-    explicit boolean ``agent.verify_on_stop`` config value, then a surface-aware
-    default. The config default is the sentinel ``"auto"`` (see
-    ``DEFAULT_CONFIG``), which resolves to ON for interactive coding surfaces
-    (CLI, TUI, desktop) and programmatic callers, and OFF for conversational
-    messaging surfaces (Telegram, Discord, etc.) where the verification
-    narrative would otherwise reach a human as chat noise.
-    """
-    env = os.environ.get("HERMES_VERIFY_ON_STOP")
-    if env is not None:
-        return env.strip().lower() not in {"0", "false", "no", "off"}
-    if config is None:
-        try:
-            from hermes_cli.config import load_config
-
-            config = load_config()
-        except Exception:
-            config = {}
-    agent_cfg = (config or {}).get("agent") if isinstance(config, dict) else None
-    cfg_val = agent_cfg.get("verify_on_stop") if isinstance(agent_cfg, dict) else None
-    if isinstance(cfg_val, bool):
-        return cfg_val
-    if isinstance(cfg_val, str):
-        token = cfg_val.strip().lower()
-        if token in {"1", "true", "yes", "on"}:
-            return True
-        if token in {"0", "false", "no", "off"}:
-            return False
-    # "auto", missing, or any other value -> surface-aware default.
-    return not _session_is_messaging_surface()
-
-
-def _candidate_cwds(paths: Iterable[str]) -> list[Path]:
-    candidates: list[Path] = []
-    seen: set[str] = set()
-    for raw in paths:
-        if not raw:
-            continue
-        try:
-            path = Path(raw).expanduser()
-            candidate = path if path.is_dir() else path.parent
-            resolved = str(candidate.resolve())
-        except Exception:
-            continue
-        if resolved not in seen:
-            seen.add(resolved)
-            candidates.append(Path(resolved))
-    return candidates
-
-
-def _verification_snapshot(
-    *,
-    session_id: str | None,
-    changed_paths: list[str],
-) -> tuple[dict[str, Any], dict[str, Any]] | None:
-    """Return ``(status, facts)`` for the first edited workspace needing proof."""
-    try:
-        from agent.coding_context import project_facts_for
-        from agent.verification_evidence import verification_status
-    except Exception:
-        return None
-
-    first_snapshot: tuple[dict[str, Any], dict[str, Any]] | None = None
-    for cwd in _candidate_cwds(changed_paths):
-        facts = project_facts_for(cwd)
-        if not facts:
-            continue
-        status = verification_status(session_id=session_id, cwd=cwd)
-        snapshot = (status, facts)
-        if first_snapshot is None:
-            first_snapshot = snapshot
-        if str(status.get("status") or "unverified") != "passed":
-            return snapshot
-    return first_snapshot
-
-
-def _format_changed_paths(paths: list[str]) -> str:
-    shown = paths[:_MAX_CHANGED_PATHS_IN_NUDGE]
-    lines = [f"- `{path}`" for path in shown]
-    remaining = len(paths) - len(shown)
-    if remaining > 0:
-        lines.append(f"- ... and {remaining} more")
-    return "\n".join(lines)
-
-
-def _status_detail(status: dict[str, Any]) -> str:
-    state = str(status.get("status") or "unverified")
-    evidence = status.get("evidence") if isinstance(status.get("evidence"), dict) else None
-    if not evidence:
-        return state
-
-    command = evidence.get("canonical_command") or evidence.get("command")
-    summary = str(evidence.get("output_summary") or "").strip()
-    parts = [state]
-    if command:
-        parts.append(f"last command `{command}`")
-    if summary:
-        max_summary = 1200
-        if len(summary) > max_summary:
-            summary = summary[:max_summary].rstrip() + "\n... [truncated]"
-        parts.append(f"last output:\n{summary}")
-    return "\n".join(parts)
-
-
-def build_verify_on_stop_nudge(
-    *,
-    session_id: str | None,
-    changed_paths: Iterable[str],
-    attempts: int = 0,
-    max_attempts: int = 2,
-) -> str | None:
-    """Return a synthetic follow-up when edited code lacks fresh verification."""
-    paths = sorted({str(p) for p in changed_paths if p})
-    if not paths or attempts >= max_attempts:
-        return None
-
-    snapshot = _verification_snapshot(session_id=session_id, changed_paths=paths)
-    if snapshot is None:
-        return None
-    status, facts = snapshot
-
-    verify_commands = [
-        str(cmd).strip()
-        for cmd in (facts.get("verifyCommands") or [])
-        if str(cmd).strip()
-    ]
-
-    state = str(status.get("status") or "unverified")
-    if state == "passed":
-        return None
-
-    if verify_commands:
-        command_instruction = (
-            "Run the relevant verification command now ("
-            + ", ".join(f"`{cmd}`" for cmd in verify_commands[:3])
-            + (", ..." if len(verify_commands) > 3 else "")
-            + "), read any failure, repair the code, and summarize what passed."
-        )
-    else:
-        temp_dir = tempfile.gettempdir()
-        command_instruction = (
-            "No canonical test/lint/build command was detected. Create a focused "
-            f"temporary verification script under `{temp_dir}` using an OS-safe "
-            "`tempfile` path with a `hermes-verify-` filename prefix, run it "
-            "against the changed behavior, clean it up when possible, and "
-            "summarize it explicitly as ad-hoc verification rather than suite "
-            "green."
-        )
-
-    return (
-        "[System: You edited code in this turn, but the workspace does not have "
-        "fresh passing verification evidence yet.\n\n"
-        f"Verification status: {_status_detail(status)}\n\n"
-        f"Changed paths:\n{_format_changed_paths(paths)}\n\n"
-        f"{command_instruction} If verification is not possible, explain the "
-        "concrete blocker instead of claiming the work is fully verified.]"
-    )
-
-
-__all__ = ["build_verify_on_stop_nudge", "verify_on_stop_enabled"]

apps/desktop/components.json

@@ -17,5 +17,5 @@
     "lib": "@/lib",
     "hooks": "@/hooks"
   },
-  "iconLibrary": "tabler"
+  "iconLibrary": "lucide"
 }

apps/desktop/electron/backend-env.cjs

@@ -61,7 +61,10 @@ function buildDesktopBackendPath({
   const venvBin = venvRoot ? pathModule.join(venvRoot, platform === 'win32' ? 'Scripts' : 'bin') : null
   const saneEntries = platform === 'win32' ? [] : POSIX_SANE_PATH_ENTRIES
 
-  return appendUniquePathEntries([hermesNodeBin, venvBin, currentPath, saneEntries], { delimiter })
+  return appendUniquePathEntries(
+    [hermesNodeBin, venvBin, currentPath, saneEntries],
+    { delimiter }
+  )
 }
 
 function normalizeHermesHomeRoot(hermesHome, { pathModule = pathModuleForPlatform(process.platform) } = {}) {

apps/desktop/electron/backend-env.test.cjs

@@ -76,7 +76,10 @@ test('normalizeHermesHomeRoot maps profile homes back to the global Hermes root'
     normalizeHermesHomeRoot('C:\\Users\\test\\AppData\\Local\\hermes\\profiles\\oracle', { pathModule: path.win32 }),
     'C:\\Users\\test\\AppData\\Local\\hermes'
   )
-  assert.equal(normalizeHermesHomeRoot('/Users/test/.hermes', { pathModule: path.posix }), '/Users/test/.hermes')
+  assert.equal(
+    normalizeHermesHomeRoot('/Users/test/.hermes', { pathModule: path.posix }),
+    '/Users/test/.hermes'
+  )
 })
 
 test('Windows PATH casing and delimiter are preserved without POSIX sane entries', () => {
@@ -101,5 +104,8 @@ test('Windows PATH casing and delimiter are preserved without POSIX sane entries
 })
 
 test('appendUniquePathEntries drops empty entries and keeps first occurrence', () => {
-  assert.equal(appendUniquePathEntries([':/a::/b', ['/a', '/c']], { delimiter: ':' }), '/a:/b:/c')
+  assert.equal(
+    appendUniquePathEntries([':/a::/b', ['/a', '/c']], { delimiter: ':' }),
+    '/a:/b:/c'
+  )
 })

apps/desktop/electron/backend-ready.cjs

@@ -1,5 +1,3 @@
-const fs = require('node:fs')
-
 const _READY_RE = /^HERMES_DASHBOARD_READY port=(\d+)/m
 
 // The announcement clock starts the instant the backend process is spawned —
@@ -96,76 +94,9 @@ function waitForDashboardPort(child, timeoutMs = resolvePortAnnounceTimeoutMs())
   })
 }
 
-function readDashboardReadyFile(readyFile) {
-  if (!readyFile) return null
-  try {
-    const parsed = JSON.parse(fs.readFileSync(readyFile, 'utf8'))
-    const port = Number(parsed?.port)
-    return Number.isInteger(port) && port > 0 ? port : null
-  } catch {
-    return null
-  }
-}
-
-function waitForDashboardReadyFile(readyFile, child, timeoutMs = resolvePortAnnounceTimeoutMs()) {
-  return new Promise((resolve, reject) => {
-    let done = false
-    let interval = null
-
-    function cleanup() {
-      if (done) return
-      done = true
-      clearTimeout(timer)
-      if (interval) clearInterval(interval)
-      child.off('exit', onExit)
-      child.off('error', onError)
-    }
-
-    function check() {
-      const port = readDashboardReadyFile(readyFile)
-      if (port) {
-        cleanup()
-        resolve(port)
-      }
-    }
-
-    function onExit(code, signal) {
-      cleanup()
-      reject(new Error(`Hermes backend: exited before port announcement (${signal || code})`))
-    }
-
-    function onError(err) {
-      cleanup()
-      reject(err)
-    }
-
-    const timer = setTimeout(() => {
-      cleanup()
-      reject(new Error(`Timed out waiting for Hermes backend port announcement (${timeoutMs}ms)`))
-    }, timeoutMs)
-
-    child.on('exit', onExit)
-    child.on('error', onError)
-    interval = setInterval(check, 50)
-    if (typeof interval.unref === 'function') interval.unref()
-    check()
-  })
-}
-
-function waitForDashboardPortAnnouncement(child, options = {}) {
-  const timeoutMs = options.timeoutMs ?? resolvePortAnnounceTimeoutMs()
-  if (options.readyFile) {
-    return waitForDashboardReadyFile(options.readyFile, child, timeoutMs)
-  }
-  return waitForDashboardPort(child, timeoutMs)
-}
-
 module.exports = {
   waitForDashboardPort,
-  waitForDashboardPortAnnouncement,
-  waitForDashboardReadyFile,
-  readDashboardReadyFile,
   resolvePortAnnounceTimeoutMs,
   DEFAULT_PORT_ANNOUNCE_TIMEOUT_MS,
-  MIN_PORT_ANNOUNCE_TIMEOUT_MS
+  MIN_PORT_ANNOUNCE_TIMEOUT_MS,
 }

apps/desktop/electron/backend-ready.test.cjs

@@ -14,18 +14,12 @@
 const test = require('node:test')
 const assert = require('node:assert/strict')
 const { EventEmitter } = require('node:events')
-const fs = require('node:fs')
-const os = require('node:os')
-const path = require('node:path')
 
 const {
-  readDashboardReadyFile,
   waitForDashboardPort,
-  waitForDashboardPortAnnouncement,
-  waitForDashboardReadyFile,
   resolvePortAnnounceTimeoutMs,
   DEFAULT_PORT_ANNOUNCE_TIMEOUT_MS,
-  MIN_PORT_ANNOUNCE_TIMEOUT_MS
+  MIN_PORT_ANNOUNCE_TIMEOUT_MS,
 } = require('./backend-ready.cjs')
 
 // A minimal stand-in for a spawned child process: an EventEmitter with a
@@ -125,75 +119,3 @@ test('a late announcement after timeout does not throw (listeners torn down)', a
     child.stdout.emit('data', 'HERMES_DASHBOARD_READY port=9999\n')
   })
 })
-
-// ---------------------------------------------------------------------------
-// ready-file port announcement
-// ---------------------------------------------------------------------------
-
-function mkTmpReadyFile() {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-ready-test-'))
-  return {
-    dir,
-    file: path.join(dir, 'ready.json'),
-    cleanup: () => fs.rmSync(dir, { recursive: true, force: true })
-  }
-}
-
-test('readDashboardReadyFile returns a valid port from JSON', () => {
-  const tmp = mkTmpReadyFile()
-  try {
-    fs.writeFileSync(tmp.file, JSON.stringify({ port: 4567 }))
-    assert.equal(readDashboardReadyFile(tmp.file), 4567)
-  } finally {
-    tmp.cleanup()
-  }
-})
-
-test('readDashboardReadyFile ignores missing, malformed, or invalid files', () => {
-  const tmp = mkTmpReadyFile()
-  try {
-    assert.equal(readDashboardReadyFile(tmp.file), null)
-    fs.writeFileSync(tmp.file, '{')
-    assert.equal(readDashboardReadyFile(tmp.file), null)
-    fs.writeFileSync(tmp.file, JSON.stringify({ port: 0 }))
-    assert.equal(readDashboardReadyFile(tmp.file), null)
-  } finally {
-    tmp.cleanup()
-  }
-})
-
-test('waitForDashboardReadyFile resolves when the ready file appears', async () => {
-  const tmp = mkTmpReadyFile()
-  const child = makeFakeChild()
-  try {
-    const p = waitForDashboardReadyFile(tmp.file, child, 1000)
-    setTimeout(() => fs.writeFileSync(tmp.file, JSON.stringify({ port: 8765 })), 20)
-    assert.equal(await p, 8765)
-  } finally {
-    tmp.cleanup()
-  }
-})
-
-test('waitForDashboardPortAnnouncement uses ready file when provided', async () => {
-  const tmp = mkTmpReadyFile()
-  const child = makeFakeChild()
-  try {
-    const p = waitForDashboardPortAnnouncement(child, { readyFile: tmp.file, timeoutMs: 1000 })
-    setTimeout(() => fs.writeFileSync(tmp.file, JSON.stringify({ port: 9876 })), 20)
-    assert.equal(await p, 9876)
-  } finally {
-    tmp.cleanup()
-  }
-})
-
-test('waitForDashboardReadyFile rejects when the child exits before file readiness', async () => {
-  const tmp = mkTmpReadyFile()
-  const child = makeFakeChild()
-  try {
-    const p = waitForDashboardReadyFile(tmp.file, child, 1000)
-    child.emit('exit', 1, null)
-    await assert.rejects(p, /exited before port announcement/)
-  } finally {
-    tmp.cleanup()
-  }
-})

apps/desktop/electron/bootstrap-runner.cjs

@@ -179,13 +179,7 @@ function downloadInstallScript(commit, destPath) {
   })
 }
 
-async function resolveInstallScript({
-  installStamp,
-  sourceRepoRoot,
-  hermesHome,
-  emit,
-  _download = downloadInstallScript
-}) {
+async function resolveInstallScript({ installStamp, sourceRepoRoot, hermesHome, emit, _download = downloadInstallScript }) {
   // 1. Dev shortcut: prefer a local checkout's installer so we can iterate
   //    without pushing. SOURCE_REPO_ROOT comes from main.cjs (path.resolve
   //    of APP_ROOT/../..).
@@ -299,19 +293,15 @@ function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, herme
     const ps = process.platform === 'win32' ? resolveWindowsPowerShell() : 'pwsh'
     const fullArgs = ['-NoProfile', '-ExecutionPolicy', 'Bypass', '-File', scriptPath, ...args]
 
-    const child = spawn(
-      ps,
-      fullArgs,
-      hiddenWindowsChildOptions({
-        stdio: ['ignore', 'pipe', 'pipe'],
-        env: {
-          ...process.env,
-          // Pass HERMES_HOME through so install.ps1 respects the caller's
-          // choice rather than re-computing the default.
-          HERMES_HOME: hermesHome || process.env.HERMES_HOME || ''
-        }
-      })
-    )
+    const child = spawn(ps, fullArgs, hiddenWindowsChildOptions({
+      stdio: ['ignore', 'pipe', 'pipe'],
+      env: {
+        ...process.env,
+        // Pass HERMES_HOME through so install.ps1 respects the caller's
+        // choice rather than re-computing the default.
+        HERMES_HOME: hermesHome || process.env.HERMES_HOME || ''
+      }
+    }))
 
     let stdout = ''
     let stderr = ''

apps/desktop/electron/connection-config.cjs

@@ -261,7 +261,12 @@ function cookiesHaveSession(cookies) {
  */
 function cookiesHaveLiveSession(cookies) {
   if (!Array.isArray(cookies)) return false
-  return cookies.some(c => c && c.value && (AT_COOKIE_VARIANTS.includes(c.name) || RT_COOKIE_VARIANTS.includes(c.name)))
+  return cookies.some(
+    c =>
+      c &&
+      c.value &&
+      (AT_COOKIE_VARIANTS.includes(c.name) || RT_COOKIE_VARIANTS.includes(c.name))
+  )
 }
 
 module.exports = {

apps/desktop/electron/desktop-uninstall.cjs

@@ -138,7 +138,10 @@ function buildPosixCleanupScript({ desktopPid, pythonExe, pythonPath, agentRoot,
   if (pythonPath) {
     lines.push(`export PYTHONPATH=${q(pythonPath)}\${PYTHONPATH:+:$PYTHONPATH}`)
   }
-  lines.push(`cd ${q(agentRoot)} 2>/dev/null || true`, `${q(pythonExe)} ${uninstallArgs.map(q).join(' ')} || true`)
+  lines.push(
+    `cd ${q(agentRoot)} 2>/dev/null || true`,
+    `${q(pythonExe)} ${uninstallArgs.map(q).join(' ')} || true`
+  )
   if (appPath) {
     lines.push(`rm -rf ${q(appPath)} || true`)
   }
@@ -166,15 +169,7 @@ function buildPosixCleanupScript({ desktopPid, pythonExe, pythonPath, agentRoot,
  * Removal: even after the desktop PID is gone, Windows releases directory
  * handles lazily, so a single `rmdir /s /q` can half-fail — retry up to 10x.
  */
-function buildWindowsCleanupScript({
-  desktopPid,
-  pythonExe,
-  pythonPath,
-  agentRoot,
-  uninstallArgs,
-  appPath,
-  hermesHome
-}) {
+function buildWindowsCleanupScript({ desktopPid, pythonExe, pythonPath, agentRoot, uninstallArgs, appPath, hermesHome }) {
   const pid = Number(desktopPid) || 0
   // cmd.exe has no string escaping inside quotes; strip embedded quotes (paths
   // under %LOCALAPPDATA% never contain them). `&`/`^` in a path would still be

apps/desktop/electron/desktop-uninstall.test.cjs

@@ -101,7 +101,10 @@ test('resolveRemovableAppPath uses APPIMAGE on Linux when set', () => {
 })
 
 test('resolveRemovableAppPath finds the unpacked dir on Linux', () => {
-  assert.equal(resolveRemovableAppPath('/opt/hermes/linux-unpacked/hermes', 'linux', {}), '/opt/hermes/linux-unpacked')
+  assert.equal(
+    resolveRemovableAppPath('/opt/hermes/linux-unpacked/hermes', 'linux', {}),
+    '/opt/hermes/linux-unpacked'
+  )
   // A system-package install (/usr/bin) → null, left to apt/dnf.
   assert.equal(resolveRemovableAppPath('/usr/bin/hermes', 'linux', {}), null)
 })

apps/desktop/electron/fs-read-dir.cjs

@@ -92,7 +92,9 @@ async function readDirForIpc(dirPath, options = {}) {
   try {
     const dirents = await fsImpl.promises.readdir(resolved, { withFileTypes: true })
     const visibleDirents = dirents.filter(dirent => !FS_READDIR_HIDDEN.has(dirent.name))
-    const entries = await mapWithStatConcurrency(visibleDirents, dirent => entryForDirent(dirent, resolved, fsImpl))
+    const entries = await mapWithStatConcurrency(visibleDirents, dirent =>
+      entryForDirent(dirent, resolved, fsImpl)
+    )
 
     entries.sort((a, b) => Number(b.isDirectory) - Number(a.isDirectory) || a.name.localeCompare(b.name))
 

apps/desktop/electron/fs-read-dir.test.cjs

@@ -349,10 +349,7 @@ test('readDirForIpc bounds concurrent stats while preserving complete sorted out
   assert.equal(result.error, undefined)
   assert.equal(result.entries.length, names.length)
   assert.equal(statCalls.length, names.length)
-  assert.equal(
-    statCalls.some(fullPath => fullPath.endsWith(`${path.sep}node_modules`)),
-    false
-  )
+  assert.equal(statCalls.some(fullPath => fullPath.endsWith(`${path.sep}node_modules`)), false)
   assert.ok(peak > 1, `expected concurrent stats, observed peak ${peak}`)
   assert.ok(peak <= 16, `expected at most 16 concurrent stats, observed peak ${peak}`)
   assert.deepEqual(
@@ -360,5 +357,8 @@ test('readDirForIpc bounds concurrent stats while preserving complete sorted out
     expectedNames
   )
   assert.equal(result.entries.find(entry => entry.name === failedName)?.isDirectory, false)
-  assert.equal(result.entries.filter(entry => entry.isDirectory).length, successfulDirectoryNames.size)
+  assert.equal(
+    result.entries.filter(entry => entry.isDirectory).length,
+    successfulDirectoryNames.size
+  )
 })

apps/desktop/electron/git-repo-scan.cjs

@@ -1,96 +0,0 @@
-'use strict'
-
-// Repo-first discovery: walk bounded roots for git repos using only Node's `fs`
-// — no native addon, so it just works for anyone who pulls main (no
-// electron-rebuild). Mirrors how GitHub Desktop scans: stop at the first `.git`
-// (don't descend into a repo), cap depth, and skip heavy non-repo trees so the
-// first scan stays fast. Results are cached by the backend after the first run.
-
-const fs = require('node:fs')
-const os = require('node:os')
-const path = require('node:path')
-
-const fsp = fs.promises
-
-// Shallow on purpose: real projects live a few levels under home
-// (`~/www/repo`, `~/code/org/repo`); deeper `.git` dirs are almost always
-// fixtures/vendored/eval checkouts (e.g. `~/www/ha-evals/tasks/*/repo`). Repos
-// you actually use but keep deeper still surface via session-derived discovery,
-// so this only prunes noise, never repos with history.
-const DEFAULT_MAX_DEPTH = 3
-const MAX_CONCURRENCY = 32
-
-// Big trees that are never themselves repos and would waste the walk. Anything
-// hidden (dotdirs like .cache/.Trash/.npm) is skipped wholesale below, so this
-// only needs the non-hidden heavyweights.
-const JUNK_DIRS = new Set(['Applications', 'Library', 'node_modules', 'site-packages', 'vendor', 'venv'])
-
-async function mapLimit(items, limit, fn) {
-  let cursor = 0
-
-  async function worker() {
-    while (cursor < items.length) {
-      const index = cursor
-      cursor += 1
-      await fn(items[index])
-    }
-  }
-
-  await Promise.all(Array.from({ length: Math.min(limit, items.length) }, worker))
-}
-
-/**
- * Scan `roots` (default: the home dir) for git repositories. Returns deduped
- * `{ root, label }` entries. `options.maxDepth` caps recursion (default 3).
- */
-async function scanGitRepos(roots, options = {}) {
-  const maxDepth = Number(options.maxDepth) || DEFAULT_MAX_DEPTH
-  const searchRoots = Array.isArray(roots) && roots.length > 0 ? roots : [os.homedir()]
-  const found = new Map()
-
-  async function walk(dir, depth) {
-    if (depth > maxDepth) {
-      return
-    }
-
-    let entries
-    try {
-      entries = await fsp.readdir(dir, { withFileTypes: true })
-    } catch {
-      return // unreadable / permission denied
-    }
-
-    // A `.git` DIRECTORY marks a real repo root (a main checkout). A `.git`
-    // FILE is a linked worktree or submodule — those belong to their parent
-    // repo as lanes, not as separate projects, so we don't list them (and we
-    // keep descending in case a real repo sits deeper). This is what kills the
-    // worktree/eval-repo duplicate explosion.
-    if (entries.some(entry => entry.name === '.git' && entry.isDirectory())) {
-      const root = dir.replace(/[/\\]+$/, '')
-      found.set(root, path.basename(root) || root)
-
-      return
-    }
-
-    const subdirs = []
-    for (const entry of entries) {
-      // Real directories only (skip symlinks to avoid loops), no hidden dirs, no
-      // known heavy trees.
-      if (!entry.isDirectory() || entry.name.startsWith('.') || JUNK_DIRS.has(entry.name)) {
-        continue
-      }
-
-      subdirs.push(path.join(dir, entry.name))
-    }
-
-    await mapLimit(subdirs, MAX_CONCURRENCY, sub => walk(sub, depth + 1))
-  }
-
-  await mapLimit(searchRoots.map(root => String(root || '').trim()).filter(Boolean), MAX_CONCURRENCY, root =>
-    walk(root, 0)
-  )
-
-  return [...found.entries()].map(([root, label]) => ({ label, root }))
-}
-
-module.exports = { scanGitRepos }

apps/desktop/electron/git-review-ops.cjs

@@ -1,684 +0,0 @@
-'use strict'
-
-// Git ops backing the coding rail + Codex-style review pane. Built on `simple-git`
-// (a maintained wrapper around the system git binary — same git the rest of the
-// app shells to, no native build) so we read structured status()/diffSummary()
-// results instead of hand-parsing porcelain. Reads degrade to null/empty on a
-// non-repo / remote backend; mutations reject so the renderer can toast.
-
-const { execFile } = require('node:child_process')
-const fs = require('node:fs/promises')
-const path = require('node:path')
-
-const simpleGit = require('simple-git')
-
-const { resolveRequestedPathForIpc } = require('./hardening.cjs')
-
-const COMMIT_CONTEXT_DIFF_MAX_CHARS = 120_000
-const COMMIT_CONTEXT_UNTRACKED_MAX = 80
-const UNTRACKED_LINE_COUNT_CONCURRENCY = 16
-const UNTRACKED_LINE_COUNT_MAX_BYTES = 1024 * 1024
-
-// GUI-launched Electron apps on macOS inherit only a minimal PATH (no
-// /opt/homebrew/bin or /usr/local/bin), so `gh` — and the `git` gh shells out
-// to — aren't found. Augment PATH with the resolved gh dir + the common
-// package-manager bins so gh runs the same way it does in a terminal.
-function ghEnv(ghBin) {
-  const extra = [ghBin ? path.dirname(ghBin) : '', '/opt/homebrew/bin', '/usr/local/bin', '/usr/bin'].filter(
-    dir => dir && dir !== '.'
-  )
-
-  return { ...process.env, PATH: [...extra, process.env.PATH].filter(Boolean).join(path.delimiter) }
-}
-
-// Run the `gh` CLI in a repo. Resolves { ok, stdout } so callers branch on
-// availability/auth without a throw. gh missing/unauthed → ok:false.
-function runGh(args, cwd, ghBin) {
-  return new Promise(resolve => {
-    execFile(
-      ghBin || 'gh',
-      args,
-      { cwd, env: ghEnv(ghBin), windowsHide: true, timeout: 30_000, maxBuffer: 8 * 1024 * 1024 },
-      (err, stdout) => resolve({ ok: !err, stdout: String(stdout || '') })
-    )
-  })
-}
-
-function gitFor(cwd, gitBin) {
-  return simpleGit({ baseDir: cwd, binary: gitBin || 'git', maxConcurrentProcesses: 4, trimmed: false })
-}
-
-// simple-git reports renames as `old => new` (and `dir/{old => new}/f`); resolve
-// to the NEW path so the row addresses the real file for diff/stage.
-function resolveRenamePath(raw) {
-  const path = String(raw || '').trim()
-
-  if (!path.includes(' => ')) {
-    return path
-  }
-
-  const brace = path.match(/^(.*)\{(.*) => (.*)\}(.*)$/)
-
-  if (brace) {
-    const [, prefix, , to, suffix] = brace
-
-    return `${prefix}${to}${suffix}`.replace(/\/{2,}/g, '/')
-  }
-
-  return path.split(' => ').pop().trim()
-}
-
-// DiffResult.files → Map<path, {added, removed}> (binary files carry no line
-// delta).
-function countsByPath(summary) {
-  const map = new Map()
-
-  for (const file of summary.files) {
-    map.set(resolveRenamePath(file.file), {
-      added: file.binary ? 0 : file.insertions,
-      removed: file.binary ? 0 : file.deletions
-    })
-  }
-
-  return map
-}
-
-// Untracked files don't appear in diffSummary(); count insertions from disk so
-// the review tree can show +N for new files (matches an all-add diff view).
-// Insertions = line count: newline bytes, plus one for a final unterminated
-// line. Binary (NUL byte) → 0, mirroring git numstat's "-".
-async function untrackedInsertions(cwd, relPath) {
-  try {
-    const fullPath = path.join(cwd, relPath)
-    const stat = await fs.stat(fullPath)
-
-    if (!stat.isFile() || stat.size > UNTRACKED_LINE_COUNT_MAX_BYTES) {
-      return 0
-    }
-
-    const buf = await fs.readFile(fullPath)
-
-    if (buf.includes(0)) {
-      return 0
-    }
-
-    let lines = 0
-
-    for (const byte of buf) {
-      if (byte === 10) {
-        lines++
-      }
-    }
-
-    return buf.length > 0 && buf[buf.length - 1] !== 10 ? lines + 1 : lines
-  } catch {
-    return 0
-  }
-}
-
-function capText(text, maxChars, label = 'truncated') {
-  const value = String(text || '')
-
-  if (value.length <= maxChars) {
-    return value
-  }
-
-  return `${value.slice(0, maxChars)}\n# ${label}: ${value.length - maxChars} chars omitted\n`
-}
-
-async function fillUntrackedCounts(cwd, files) {
-  const pending = files.filter(file => file.status === '?' && file.added === 0 && file.removed === 0)
-
-  for (let i = 0; i < pending.length; i += UNTRACKED_LINE_COUNT_CONCURRENCY) {
-    await Promise.all(
-      pending.slice(i, i + UNTRACKED_LINE_COUNT_CONCURRENCY).map(async file => {
-        file.added = await untrackedInsertions(cwd, file.path)
-      })
-    )
-  }
-}
-
-// Resolve the base ref for "all branch changes": merge-base with the remote
-// default branch (origin/HEAD), falling back to common trunk names.
-async function branchBase(git) {
-  const candidates = []
-
-  try {
-    const head = (await git.revparse(['--abbrev-ref', 'origin/HEAD'])).trim()
-
-    if (head) {
-      candidates.push(head)
-    }
-  } catch {
-    // No origin/HEAD configured.
-  }
-
-  candidates.push('origin/main', 'origin/master', 'main', 'master')
-
-  for (const ref of candidates) {
-    try {
-      const base = (await git.raw(['merge-base', 'HEAD', ref])).trim()
-
-      if (base) {
-        return base
-      }
-    } catch {
-      // Ref doesn't exist; try the next candidate.
-    }
-  }
-
-  return null
-}
-
-// Resolve the repo's default branch NAME ("main" / "master" / …), preferring
-// the remote's HEAD, then common local trunk names. Null when none is found
-// (e.g. a fresh repo with only a feature branch). Used to offer "branch off the
-// trunk" regardless of which branch you're currently on.
-async function defaultBranchName(git) {
-  try {
-    const head = (await git.revparse(['--abbrev-ref', 'origin/HEAD'])).trim()
-
-    // "origin/main" → "main"; skip the bare "origin/HEAD" placeholder.
-    if (head && head !== 'origin/HEAD') {
-      return head.replace(/^origin\//, '')
-    }
-  } catch {
-    // No origin/HEAD configured.
-  }
-
-  // Prefer a local trunk, then a remote-only one (returns the clean name either
-  // way) so "branch off main" works even before main is checked out locally.
-  for (const ref of [
-    'refs/heads/main',
-    'refs/heads/master',
-    'refs/remotes/origin/main',
-    'refs/remotes/origin/master'
-  ]) {
-    try {
-      await git.raw(['rev-parse', '--verify', '--quiet', ref])
-
-      return ref.replace(/^refs\/(?:heads|remotes\/origin)\//, '')
-    } catch {
-      // Ref doesn't exist; try the next candidate.
-    }
-  }
-
-  return null
-}
-
-// A status file's single-letter classification, preferring the staged (index)
-// code over the worktree code; untracked wins (simple-git marks both '?').
-function statusLetter(file) {
-  if (file.index === '?' || file.working_dir === '?') {
-    return '?'
-  }
-
-  const code = file.index && file.index !== ' ' ? file.index : file.working_dir
-
-  return (code || 'M').toUpperCase()
-}
-
-const isStaged = file => Boolean(file.index && file.index !== ' ' && file.index !== '?')
-
-async function reviewList(repoPath, scope, baseRef, gitBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review list' })
-  } catch {
-    return { files: [], base: null }
-  }
-
-  const git = gitFor(cwd, gitBin)
-
-  try {
-    if (scope === 'branch' || scope === 'lastTurn') {
-      const base = scope === 'branch' ? await branchBase(git) : baseRef
-
-      if (!base) {
-        return { files: [], base: null }
-      }
-
-      const range = scope === 'branch' ? `${base}...HEAD` : base
-      const summary = await git.diffSummary([range])
-      const files = summary.files.map(file => ({
-        path: resolveRenamePath(file.file),
-        added: file.binary ? 0 : file.insertions,
-        removed: file.binary ? 0 : file.deletions,
-        status: 'M',
-        staged: false
-      }))
-
-      // "Last turn" also surfaces files created since the baseline (untracked).
-      if (scope === 'lastTurn') {
-        const status = await git.status()
-
-        for (const path of status.not_added) {
-          if (!files.some(f => f.path === path)) {
-            files.push({ path, added: 0, removed: 0, status: '?', staged: false })
-          }
-        }
-      }
-
-      files.sort((a, b) => a.path.localeCompare(b.path))
-      await fillUntrackedCounts(cwd, files)
-
-      return { files, base }
-    }
-
-    // Default: uncommitted (staged + unstaged + untracked), one row per path.
-    const [status, staged, unstaged] = await Promise.all([
-      git.status(),
-      git.diffSummary(['--cached']),
-      git.diffSummary([])
-    ])
-    const stagedCounts = countsByPath(staged)
-    const unstagedCounts = countsByPath(unstaged)
-
-    const files = status.files.map(file => {
-      const filePath = resolveRenamePath(file.path)
-      const sc = stagedCounts.get(filePath) || { added: 0, removed: 0 }
-      const uc = unstagedCounts.get(filePath) || { added: 0, removed: 0 }
-
-      return {
-        path: filePath,
-        added: sc.added + uc.added,
-        removed: sc.removed + uc.removed,
-        status: statusLetter(file),
-        staged: isStaged(file)
-      }
-    })
-
-    files.sort((a, b) => a.path.localeCompare(b.path))
-    await fillUntrackedCounts(cwd, files)
-
-    return { files, base: null }
-  } catch {
-    return { files: [], base: null }
-  }
-}
-
-async function reviewDiff(repoPath, filePath, scope, baseRef, staged, gitBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review diff' })
-  } catch {
-    return ''
-  }
-
-  const git = gitFor(cwd, gitBin)
-  const safe = args => git.diff(args).catch(() => '')
-
-  if (scope === 'branch') {
-    const base = await branchBase(git)
-
-    return base ? safe([`${base}...HEAD`, '--', filePath]) : ''
-  }
-
-  if (scope === 'lastTurn') {
-    return baseRef ? safe([baseRef, '--', filePath]) : ''
-  }
-
-  if (staged) {
-    return safe(['--cached', '--', filePath])
-  }
-
-  const worktree = await safe(['--', filePath])
-
-  if (worktree.trim()) {
-    return worktree
-  }
-
-  // Untracked file: no worktree diff exists, so synthesize an all-add diff via
-  // --no-index (exits non-zero by design when files differ, so go around
-  // simple-git's reject-on-nonzero with a raw execFile).
-  return new Promise(resolve => {
-    execFile(
-      gitBin || 'git',
-      ['diff', '--no-index', '--', '/dev/null', filePath],
-      { cwd, windowsHide: true, timeout: 30_000, maxBuffer: 32 * 1024 * 1024 },
-      (_err, stdout) => resolve(String(stdout || ''))
-    )
-  })
-}
-
-// Working-tree-vs-HEAD diff for ONE file — the "what changed since the last
-// commit" view used by the file preview. Unlike reviewDiff this never synthesizes
-// a full-add for a clean tracked file (so a pristine file shows no diff); it only
-// all-adds a genuinely untracked file.
-async function fileDiffVsHead(repoPath, filePath, gitBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'File diff' })
-  } catch {
-    return ''
-  }
-
-  const git = gitFor(cwd, gitBin)
-  const head = await git.diff(['HEAD', '--', filePath]).catch(() => '')
-
-  if (head.trim()) {
-    return head
-  }
-
-  // No tracked changes vs HEAD. Only synthesize an all-add diff for a file git
-  // doesn't know yet; a clean tracked file must return empty.
-  const status = await git.raw(['status', '--porcelain', '--', filePath]).catch(() => '')
-
-  if (!status.trim().startsWith('??')) {
-    return ''
-  }
-
-  return new Promise(resolve => {
-    execFile(
-      gitBin || 'git',
-      ['diff', '--no-index', '--', '/dev/null', filePath],
-      { cwd, windowsHide: true, timeout: 30_000, maxBuffer: 32 * 1024 * 1024 },
-      (_err, stdout) => resolve(String(stdout || ''))
-    )
-  })
-}
-
-async function reviewStage(repoPath, filePath, gitBin) {
-  const cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review stage' })
-
-  await gitFor(cwd, gitBin).raw(filePath ? ['add', '--', filePath] : ['add', '-A'])
-
-  return { ok: true }
-}
-
-async function reviewUnstage(repoPath, filePath, gitBin) {
-  const cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review unstage' })
-
-  await gitFor(cwd, gitBin).raw(filePath ? ['reset', '-q', 'HEAD', '--', filePath] : ['reset', '-q', 'HEAD'])
-
-  return { ok: true }
-}
-
-// Discard changes back to the committed state. Destructive — the renderer
-// confirms first. Restores tracked files and removes untracked ones.
-async function reviewRevert(repoPath, filePath, gitBin) {
-  const cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review revert' })
-  const git = gitFor(cwd, gitBin)
-
-  if (filePath) {
-    await git.raw(['checkout', 'HEAD', '--', filePath]).catch(() => undefined)
-    await git.raw(['clean', '-fd', '--', filePath]).catch(() => undefined)
-  } else {
-    await git.raw(['checkout', 'HEAD', '--', '.']).catch(() => undefined)
-    await git.raw(['clean', '-fd']).catch(() => undefined)
-  }
-
-  return { ok: true }
-}
-
-// Resolve a ref to a commit sha (captures the turn baseline for "Last turn").
-async function reviewRevParse(repoPath, ref, gitBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review rev-parse' })
-  } catch {
-    return null
-  }
-
-  try {
-    return (await gitFor(cwd, gitBin).revparse([ref || 'HEAD'])).trim() || null
-  } catch {
-    return null
-  }
-}
-
-// Commit the working tree. Mirrors VS Code: if nothing is staged, stage
-// everything first ("commit all"), then commit. Optionally push afterward,
-// setting upstream on the first push.
-async function reviewCommit(repoPath, message, push, gitBin) {
-  const cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review commit' })
-  const git = gitFor(cwd, gitBin)
-  const status = await git.status()
-
-  if (status.staged.length === 0) {
-    await git.raw(['add', '-A'])
-  }
-
-  await git.commit(message)
-
-  if (push) {
-    const fresh = await git.status()
-
-    if (fresh.tracking) {
-      await git.push()
-    } else if (fresh.current) {
-      await git.raw(['push', '-u', 'origin', fresh.current])
-    }
-  }
-
-  return { ok: true }
-}
-
-// Gather the context the model needs to draft a commit message: the diff of
-// what *will* be committed (staged when anything is staged, else everything
-// vs HEAD — mirroring reviewCommit's "stage all when nothing staged" rule),
-// the names of untracked files (which carry no diff), and recent commit
-// subjects for style. Diff is capped so the payload stays bounded. Reads only.
-async function reviewCommitContext(repoPath, gitBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review commit context' })
-  } catch {
-    return { diff: '', recent: '' }
-  }
-
-  const git = gitFor(cwd, gitBin)
-  const safe = args => git.diff(args).catch(() => '')
-
-  let status
-  try {
-    status = await git.status()
-  } catch {
-    return { diff: '', recent: '' }
-  }
-
-  // What will land: staged changes if any, otherwise all tracked changes vs HEAD.
-  let diff = capText(
-    status.staged.length > 0 ? await safe(['--cached']) : await safe(['HEAD']),
-    COMMIT_CONTEXT_DIFF_MAX_CHARS,
-    'diff truncated for commit-message generation'
-  )
-
-  // Untracked files have no diff — list them so new files aren't invisible.
-  const untracked = status.not_added || []
-  if (untracked.length > 0) {
-    const visible = untracked.slice(0, COMMIT_CONTEXT_UNTRACKED_MAX)
-    const omitted = untracked.length - visible.length
-    const note =
-      `\n# New (untracked) files:\n${visible.map(p => `#   ${p}`).join('\n')}\n` +
-      (omitted > 0 ? `#   ... ${omitted} more omitted\n` : '')
-
-    diff = diff ? `${diff}${note}` : note
-  }
-
-  const recent = await git.raw(['log', '-n', '10', '--pretty=format:%s']).catch(() => '')
-
-  return { diff: diff || '', recent: String(recent || '').trim() }
-}
-
-async function reviewPush(repoPath, gitBin) {
-  const cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review push' })
-  const git = gitFor(cwd, gitBin)
-  const status = await git.status()
-
-  if (status.tracking) {
-    await git.push()
-  } else if (status.current) {
-    await git.raw(['push', '-u', 'origin', status.current])
-  }
-
-  return { ok: true }
-}
-
-// gh availability + auth + whether this branch already has a PR. Reads only;
-// drives the PR button's enabled/label state. `ghReady` is false when gh is
-// missing OR not authenticated — either way the PR action can't run.
-async function reviewShipInfo(repoPath, ghBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review ship info' })
-  } catch {
-    return { ghReady: false, pr: null }
-  }
-
-  const auth = await runGh(['auth', 'status'], cwd, ghBin)
-
-  if (!auth.ok) {
-    return { ghReady: false, pr: null }
-  }
-
-  const view = await runGh(['pr', 'view', '--json', 'url,state,number'], cwd, ghBin)
-
-  if (!view.ok) {
-    // gh exits non-zero when no PR exists for the branch — that's not an error.
-    return { ghReady: true, pr: null }
-  }
-
-  try {
-    const pr = JSON.parse(view.stdout)
-
-    return { ghReady: true, pr: pr && pr.url ? { url: pr.url, state: pr.state, number: pr.number } : null }
-  } catch {
-    return { ghReady: true, pr: null }
-  }
-}
-
-// Create a PR for the current branch (pushing first so gh has a remote ref),
-// letting gh fill title/body from the commits. Returns the new PR url.
-async function reviewCreatePr(repoPath, gitBin, ghBin) {
-  const cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Review create PR' })
-
-  await reviewPush(repoPath, gitBin).catch(() => undefined)
-
-  const created = await runGh(['pr', 'create', '--fill'], cwd, ghBin)
-
-  if (!created.ok) {
-    throw new Error('gh pr create failed (is gh installed and authenticated?)')
-  }
-
-  const url = created.stdout.trim().split('\n').filter(Boolean).pop() || ''
-
-  return { url }
-}
-
-// Compact working-tree status for the composer coding rail: branch, ahead/behind,
-// per-state change counts, +/- vs HEAD, and a capped changed-file list.
-async function repoStatus(repoPath, gitBin) {
-  let cwd
-
-  try {
-    cwd = resolveRequestedPathForIpc(repoPath, { purpose: 'Repo status' })
-  } catch {
-    return null
-  }
-
-  // Session cwds can point at a deleted worktree for a moment (or forever in a
-  // stale row). simple-git throws at construction time on a missing baseDir, so
-  // fail soft and hide the coding rail instead of spamming IPC handler errors.
-  try {
-    const stat = await fs.stat(cwd)
-    if (!stat.isDirectory()) {
-      return null
-    }
-  } catch {
-    return null
-  }
-
-  let git
-  try {
-    git = gitFor(cwd, gitBin)
-  } catch {
-    return null
-  }
-  let status
-
-  try {
-    status = await git.status()
-  } catch {
-    // Not a repo / git unavailable / remote backend.
-    return null
-  }
-
-  const detached = typeof status.detached === 'boolean' ? status.detached : !status.current
-  const files = status.files.map(file => ({
-    path: file.path,
-    staged: isStaged(file),
-    unstaged: Boolean(file.working_dir && file.working_dir !== ' ' && file.working_dir !== '?'),
-    untracked: file.index === '?' || file.working_dir === '?',
-    conflicted: file.index === 'U' || file.working_dir === 'U'
-  }))
-
-  const result = {
-    branch: detached ? null : status.current || null,
-    defaultBranch: await defaultBranchName(git),
-    detached,
-    ahead: status.ahead || 0,
-    behind: status.behind || 0,
-    staged: files.filter(f => f.staged).length,
-    unstaged: files.filter(f => f.unstaged).length,
-    untracked: status.not_added.length,
-    conflicted: status.conflicted.length,
-    changed: files.length,
-    added: 0,
-    removed: 0,
-    files: files.slice(0, 200)
-  }
-
-  // +/- vs HEAD (staged + unstaged tracked changes). No HEAD yet → leave 0.
-  try {
-    const summary = await git.diffSummary(['HEAD'])
-    result.added = summary.insertions
-    result.removed = summary.deletions
-  } catch {
-    // No commits yet.
-  }
-
-  // `git diff HEAD` ignores untracked files, so a turn that only creates new
-  // files (the common case — a fresh module, a demo dir) showed +0 in the rail
-  // while the review pane counted them. Fold untracked insertions into `added`
-  // so the rail matches reality. Bounded (size cap + concurrency) like the
-  // review tree; only the capped file slice is counted so a huge untracked tree
-  // can't stall the probe.
-  try {
-    const untracked = status.not_added.slice(0, 500)
-    for (let i = 0; i < untracked.length; i += UNTRACKED_LINE_COUNT_CONCURRENCY) {
-      const batch = await Promise.all(
-        untracked.slice(i, i + UNTRACKED_LINE_COUNT_CONCURRENCY).map(path => untrackedInsertions(cwd, path))
-      )
-      result.added += batch.reduce((sum, n) => sum + n, 0)
-    }
-  } catch {
-    // Best-effort: a probe failure just leaves untracked lines uncounted.
-  }
-
-  return result
-}
-
-module.exports = {
-  branchBase,
-  fileDiffVsHead,
-  repoStatus,
-  resolveRenamePath,
-  reviewCommit,
-  reviewCommitContext,
-  reviewCreatePr,
-  reviewDiff,
-  reviewList,
-  reviewPush,
-  reviewRevParse,
-  reviewRevert,
-  reviewShipInfo,
-  reviewStage,
-  reviewUnstage
-}

apps/desktop/electron/git-review-ops.test.cjs

@@ -1,22 +0,0 @@
-'use strict'
-
-const assert = require('node:assert/strict')
-const test = require('node:test')
-
-const { resolveRenamePath } = require('./git-review-ops.cjs')
-
-test('resolveRenamePath: plain path is unchanged', () => {
-  assert.equal(resolveRenamePath('src/a.ts'), 'src/a.ts')
-})
-
-test('resolveRenamePath: simple rename resolves to the new path', () => {
-  assert.equal(resolveRenamePath('old.ts => new.ts'), 'new.ts')
-})
-
-test('resolveRenamePath: brace rename resolves to the new path', () => {
-  assert.equal(resolveRenamePath('src/{old => new}/file.ts'), 'src/new/file.ts')
-})
-
-test('resolveRenamePath: brace rename collapsing a segment', () => {
-  assert.equal(resolveRenamePath('src/{lib => }/file.ts'), 'src/file.ts')
-})

apps/desktop/electron/git-worktree-ops.cjs

@@ -1,350 +0,0 @@
-'use strict'
-
-// Git-driven worktree operations for the desktop "Start work" flow: spin up a
-// fresh worktree the lightest way (`git worktree add -b`), list real worktrees,
-// and remove them. Git is the source of truth; the renderer just drives these.
-
-const path = require('node:path')
-const fs = require('node:fs')
-const { execFile } = require('node:child_process')
-
-const { resolveRequestedPathForIpc } = require('./hardening.cjs')
-
-function runGit(gitBin, args, cwd) {
-  return new Promise((resolve, reject) => {
-    execFile(
-      gitBin,
-      args,
-      { cwd, windowsHide: true, timeout: 30_000, maxBuffer: 8 * 1024 * 1024 },
-      (err, stdout, stderr) => {
-        if (err) {
-          err.stderr = String(stderr || '')
-          reject(err)
-
-          return
-        }
-
-        resolve(String(stdout || ''))
-      }
-    )
-  })
-}
-
-// Parse `git worktree list --porcelain`. The first record is the main worktree.
-function parseWorktrees(out) {
-  const trees = []
-  let cur = null
-
-  for (const line of out.split('\n')) {
-    if (line.startsWith('worktree ')) {
-      if (cur) {
-        trees.push(cur)
-      }
-
-      cur = { path: line.slice(9).trim(), branch: null, detached: false, bare: false, locked: false }
-    } else if (!cur) {
-      continue
-    } else if (line.startsWith('branch ')) {
-      cur.branch = line
-        .slice(7)
-        .trim()
-        .replace(/^refs\/heads\//, '')
-    } else if (line === 'detached') {
-      cur.detached = true
-    } else if (line === 'bare') {
-      cur.bare = true
-    } else if (line.startsWith('locked')) {
-      cur.locked = true
-    }
-  }
-
-  if (cur) {
-    trees.push(cur)
-  }
-
-  return trees
-}
-
-async function listWorktrees(repoPath, gitBin) {
-  let resolved
-
-  try {
-    resolved = resolveRequestedPathForIpc(repoPath, { purpose: 'Worktree list' })
-  } catch {
-    return []
-  }
-
-  try {
-    const out = await runGit(gitBin, ['worktree', 'list', '--porcelain'], resolved)
-
-    return parseWorktrees(out).map((tree, index) => ({
-      path: tree.path,
-      branch: tree.branch,
-      isMain: index === 0,
-      detached: tree.detached,
-      locked: tree.locked
-    }))
-  } catch {
-    return []
-  }
-}
-
-// A git-ref-safe branch name (spaces → "-", drop forbidden chars, trim edges),
-// or "" when nothing usable remains. Mirrors the renderer's `gitRef`, so a bad
-// value can't reach `git` no matter the caller (the GUI also enforces live).
-function sanitizeBranch(name) {
-  return String(name || '')
-    .replace(/\s+/g, '-')
-    .replace(/[^\w./-]/g, '')
-    .replace(/-{2,}/g, '-')
-    .replace(/\/{2,}/g, '/')
-    .replace(/\.{2,}/g, '.')
-    .replace(/^[-./]+|[-./]+$/g, '')
-}
-
-function slugify(name) {
-  const slug = String(name || '')
-    .trim()
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-+|-+$/g, '')
-    .slice(0, 40)
-    .replace(/-+$/g, '')
-
-  return slug || 'work'
-}
-
-const TRUNK_BRANCHES = ['main', 'master']
-
-async function gitLine(gitBin, args, cwd) {
-  try {
-    return (await runGit(gitBin, args, cwd)).trim()
-  } catch {
-    return ''
-  }
-}
-
-async function defaultBranch(gitBin, cwd) {
-  const remote = (
-    await gitLine(gitBin, ['symbolic-ref', '--quiet', '--short', 'refs/remotes/origin/HEAD'], cwd)
-  ).replace(/^origin\//, '')
-
-  if (remote) {
-    return remote
-  }
-
-  const configured = await gitLine(gitBin, ['config', '--get', 'init.defaultBranch'], cwd)
-
-  if (configured) {
-    return configured
-  }
-
-  for (const branch of TRUNK_BRANCHES) {
-    if (await gitLine(gitBin, ['show-ref', '--verify', `refs/heads/${branch}`], cwd)) {
-      return branch
-    }
-  }
-
-  return ''
-}
-
-// A brand-new project folder isn't a git repo — and a freshly-init'd one has no
-// commit to branch from — so `git worktree add` would fail. Make the dir a repo
-// with a root commit on the user's behalf so worktrees "just work". No-op for a
-// repo that already has commits; never touches the user's files (the seed commit
-// is `--allow-empty`), and never inits a dir that already lives inside a repo.
-async function ensureGitRepo(gitBin, dir) {
-  let needsRoot = false
-
-  try {
-    const inside = (await runGit(gitBin, ['rev-parse', '--is-inside-work-tree'], dir)).trim()
-
-    if (inside !== 'true') {
-      await runGit(gitBin, ['init'], dir)
-      needsRoot = true
-    } else {
-      // Repo exists; a worktree still needs a HEAD to branch from.
-      try {
-        await runGit(gitBin, ['rev-parse', '--verify', 'HEAD'], dir)
-      } catch {
-        needsRoot = true
-      }
-    }
-  } catch {
-    await runGit(gitBin, ['init'], dir)
-    needsRoot = true
-  }
-
-  if (needsRoot) {
-    // Inline identity so the seed commit lands even with no global git config.
-    await runGit(
-      gitBin,
-      [
-        '-c',
-        'user.email=hermes@localhost',
-        '-c',
-        'user.name=Hermes',
-        'commit',
-        '--allow-empty',
-        '-m',
-        'Initial commit'
-      ],
-      dir
-    )
-  }
-}
-
-// Resolve the repo's MAIN worktree root, so `.worktrees/` always nests under the
-// primary checkout even when called from a linked worktree.
-async function mainRoot(gitBin, cwd) {
-  const list = await listWorktrees(cwd, gitBin)
-  const main = list.find(tree => tree.isMain)
-
-  return main ? main.path : cwd
-}
-
-function uniqueDir(base) {
-  let dir = base
-  let n = 1
-
-  while (fs.existsSync(dir)) {
-    n += 1
-    dir = `${base}-${n}`
-  }
-
-  return dir
-}
-
-async function addExistingBranchWorktree(gitBin, root, name) {
-  const branch = sanitizeBranch(name)
-
-  if (!branch) {
-    throw new Error('Branch name is required.')
-  }
-
-  if (branch === (await defaultBranch(gitBin, root))) {
-    await runGit(gitBin, ['switch', branch], root)
-
-    return { path: root, branch, repoRoot: root }
-  }
-
-  const dir = uniqueDir(path.join(root, '.worktrees', slugify(branch)))
-  await runGit(gitBin, ['worktree', 'add', dir, branch], root)
-
-  return { path: dir, branch, repoRoot: root }
-}
-
-async function addWorktree(repoPath, options, gitBin) {
-  const resolved = resolveRequestedPathForIpc(repoPath, { purpose: 'Worktree add' })
-  // A new project's folder may not be a git repo yet — init it (with a root
-  // commit) so the worktree has something to branch from.
-  await ensureGitRepo(gitBin, resolved)
-  const root = await mainRoot(gitBin, resolved)
-  const opts = options || {}
-
-  if (opts.existingBranch) {
-    return addExistingBranchWorktree(gitBin, root, opts.existingBranch)
-  }
-
-  const slug = slugify(opts.name || `work-${Date.now().toString(36)}`)
-  const branch = sanitizeBranch(opts.branch) || `hermes/${slug}`
-  const dir = uniqueDir(path.join(root, '.worktrees', slug))
-
-  const args = ['worktree', 'add', '-b', branch, dir]
-
-  if (opts.base) {
-    args.push(String(opts.base))
-  }
-
-  try {
-    await runGit(gitBin, args, root)
-  } catch (err) {
-    // Branch name may already exist — retry checking out the existing branch
-    // into a fresh worktree dir instead of failing the whole flow.
-    if (/already exists/i.test(err.stderr || '')) {
-      await runGit(gitBin, ['worktree', 'add', dir, branch], root)
-    } else {
-      throw err
-    }
-  }
-
-  return { path: dir, branch, repoRoot: root }
-}
-
-async function removeWorktree(repoPath, worktreePath, options, gitBin) {
-  const resolvedRepo = resolveRequestedPathForIpc(repoPath, { purpose: 'Worktree remove (repo)' })
-  const resolvedTree = resolveRequestedPathForIpc(worktreePath, { purpose: 'Worktree remove (tree)' })
-  const root = await mainRoot(gitBin, resolvedRepo)
-  const args = ['worktree', 'remove']
-
-  if (options && options.force) {
-    args.push('--force')
-  }
-
-  args.push(resolvedTree)
-  await runGit(gitBin, args, root)
-
-  return { removed: resolvedTree }
-}
-
-// List local branches for the "convert a branch into a worktree" picker, most
-// recently committed first. Each carries whether it's already checked out in a
-// worktree and, when checked out, that worktree's path. Empty on a non-repo /
-// remote backend where the probe can't run.
-async function listBranches(repoPath, gitBin) {
-  let resolved
-
-  try {
-    resolved = resolveRequestedPathForIpc(repoPath, { purpose: 'Branch list' })
-  } catch {
-    return []
-  }
-
-  try {
-    const out = await runGit(
-      gitBin,
-      ['for-each-ref', '--format=%(refname:short)', '--sort=-committerdate', 'refs/heads'],
-      resolved
-    )
-    const trees = await listWorktrees(resolved, gitBin)
-    const pathByBranch = new Map(trees.filter(tree => tree.branch).map(tree => [tree.branch, tree.path]))
-    const trunk = await defaultBranch(gitBin, resolved)
-
-    return out
-      .split('\n')
-      .map(line => line.trim())
-      .filter(Boolean)
-      .map(name => ({
-        name,
-        checkedOut: pathByBranch.has(name),
-        isDefault: Boolean(trunk && name === trunk),
-        worktreePath: pathByBranch.get(name) || null
-      }))
-  } catch {
-    return []
-  }
-}
-
-async function switchBranch(repoPath, branch, gitBin) {
-  const resolved = resolveRequestedPathForIpc(repoPath, { purpose: 'Branch switch' })
-  const target = sanitizeBranch(branch)
-
-  if (!target) {
-    throw new Error('Branch name is required.')
-  }
-
-  await runGit(gitBin, ['switch', target], resolved)
-
-  return { branch: target }
-}
-
-module.exports = {
-  addWorktree,
-  ensureGitRepo,
-  listBranches,
-  listWorktrees,
-  parseWorktrees,
-  removeWorktree,
-  sanitizeBranch,
-  switchBranch
-}

apps/desktop/electron/git-worktree-ops.test.cjs

@@ -1,214 +0,0 @@
-'use strict'
-
-const assert = require('node:assert/strict')
-const { execFileSync } = require('node:child_process')
-const fs = require('node:fs')
-const os = require('node:os')
-const path = require('node:path')
-const test = require('node:test')
-
-const {
-  addWorktree,
-  ensureGitRepo,
-  listBranches,
-  parseWorktrees,
-  sanitizeBranch,
-  switchBranch
-} = require('./git-worktree-ops.cjs')
-
-test('sanitizeBranch: spaces → hyphens, forbidden chars dropped, edges trimmed', () => {
-  assert.equal(sanitizeBranch('beach vibes'), 'beach-vibes')
-  assert.equal(sanitizeBranch('feat/cool thing'), 'feat/cool-thing')
-  assert.equal(sanitizeBranch('  wip~^:? '), 'wip')
-  assert.equal(sanitizeBranch('///'), '')
-})
-
-test('parseWorktrees: main checkout + linked worktree', () => {
-  const out = [
-    'worktree /repo',
-    'HEAD abc123',
-    'branch refs/heads/main',
-    '',
-    'worktree /repo/.worktrees/feat',
-    'HEAD def456',
-    'branch refs/heads/hermes/feat',
-    ''
-  ].join('\n')
-
-  const trees = parseWorktrees(out)
-
-  assert.equal(trees.length, 2)
-  assert.equal(trees[0].path, '/repo')
-  assert.equal(trees[0].branch, 'main')
-  assert.equal(trees[1].path, '/repo/.worktrees/feat')
-  assert.equal(trees[1].branch, 'hermes/feat')
-})
-
-test('parseWorktrees: detached + locked flags', () => {
-  const out = ['worktree /repo/wt', 'HEAD abc', 'detached', 'locked reason', ''].join('\n')
-  const trees = parseWorktrees(out)
-
-  assert.equal(trees.length, 1)
-  assert.equal(trees[0].detached, true)
-  assert.equal(trees[0].locked, true)
-  assert.equal(trees[0].branch, null)
-})
-
-test('parseWorktrees: empty input', () => {
-  assert.deepEqual(parseWorktrees(''), [])
-})
-
-test('ensureGitRepo: inits a plain dir with a root commit so worktrees branch', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-wt-'))
-  const git = (...args) => execFileSync('git', args, { cwd: dir }).toString().trim()
-
-  try {
-    await ensureGitRepo('git', dir)
-    assert.match(git('rev-parse', '--verify', 'HEAD'), /^[0-9a-f]{7,}$/)
-
-    // The whole point: a worktree can now branch off the seeded root commit.
-    execFileSync('git', ['worktree', 'add', '-b', 'wt', path.join(dir, '.worktrees', 'wt')], { cwd: dir })
-    assert.ok(fs.existsSync(path.join(dir, '.worktrees', 'wt')))
-
-    // Idempotent: an already-committed repo gets no extra commit.
-    await ensureGitRepo('git', dir)
-    assert.equal(git('rev-list', '--count', 'HEAD'), '1')
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('switchBranch: switches a normal checkout branch', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-switch-'))
-  const git = (...args) => execFileSync('git', args, { cwd: dir }).toString().trim()
-
-  try {
-    await ensureGitRepo('git', dir)
-    execFileSync('git', ['branch', 'feature'], { cwd: dir })
-
-    await switchBranch(dir, 'feature', 'git')
-
-    assert.equal(git('branch', '--show-current'), 'feature')
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('listBranches: lists locals and flags the checked-out branch', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-branches-'))
-
-  try {
-    await ensureGitRepo('git', dir)
-    const current = execFileSync('git', ['branch', '--show-current'], { cwd: dir }).toString().trim()
-    execFileSync('git', ['branch', 'feature'], { cwd: dir })
-
-    const branches = await listBranches(dir, 'git')
-    const names = branches.map(b => b.name).sort()
-
-    assert.deepEqual(names, [current, 'feature'].sort())
-    // The repo's own checkout is flagged; the unused branch is convertible.
-    assert.equal(branches.find(b => b.name === current).checkedOut, true)
-    assert.equal(branches.find(b => b.name === current).isDefault, true)
-    assert.equal(fs.realpathSync(branches.find(b => b.name === current).worktreePath), fs.realpathSync(dir))
-    assert.equal(branches.find(b => b.name === 'feature').checkedOut, false)
-    assert.equal(branches.find(b => b.name === 'feature').isDefault, false)
-    assert.equal(branches.find(b => b.name === 'feature').worktreePath, null)
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('listBranches: flags a free default branch as default, not checked out', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-branches-default-'))
-  const git = (...args) => execFileSync('git', args, { cwd: dir }).toString().trim()
-
-  try {
-    await ensureGitRepo('git', dir)
-    const trunk = git('branch', '--show-current')
-    execFileSync('git', ['switch', '-c', 'rawr'], { cwd: dir })
-
-    const branches = await listBranches(dir, 'git')
-    const defaultBranch = branches.find(b => b.name === trunk)
-
-    assert.equal(defaultBranch.checkedOut, false)
-    assert.equal(defaultBranch.isDefault, true)
-    assert.equal(defaultBranch.worktreePath, null)
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('listBranches: a branch claimed by a worktree is flagged checked out', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-branches-wt-'))
-
-  try {
-    await ensureGitRepo('git', dir)
-    execFileSync('git', ['branch', 'feature'], { cwd: dir })
-    // addWorktree converts the existing "feature" branch into a worktree.
-    const result = await addWorktree(dir, { existingBranch: 'feature' }, 'git')
-
-    assert.equal(result.branch, 'feature')
-    assert.ok(fs.existsSync(result.path))
-
-    const branches = await listBranches(dir, 'git')
-
-    assert.equal(branches.find(b => b.name === 'feature').checkedOut, true)
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('listBranches: empty on a non-repo path', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-nonrepo-'))
-
-  try {
-    assert.deepEqual(await listBranches(dir, 'git'), [])
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('addWorktree: existingBranch checks the branch out without a new branch', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-convert-'))
-  const git = (...args) => execFileSync('git', args, { cwd: dir }).toString().trim()
-
-  try {
-    await ensureGitRepo('git', dir)
-    execFileSync('git', ['branch', 'cool/feature'], { cwd: dir })
-
-    const before = git('branch', '--list').split('\n').length
-    const result = await addWorktree(dir, { existingBranch: 'cool/feature' }, 'git')
-
-    // No new branch was created — only the existing one is checked out.
-    assert.equal(git('branch', '--list').split('\n').length, before)
-    assert.equal(result.branch, 'cool/feature')
-    // Dir is named off the branch slug, nested under the main repo's .worktrees.
-    assert.match(result.path, /[/\\]\.worktrees[/\\]cool-feature/)
-    assert.equal(
-      execFileSync('git', ['branch', '--show-current'], { cwd: result.path }).toString().trim(),
-      'cool/feature'
-    )
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})
-
-test('addWorktree: existing default branch switches the main checkout, not .worktrees/main', async () => {
-  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-convert-default-'))
-  const git = (...args) => execFileSync('git', args, { cwd: dir }).toString().trim()
-
-  try {
-    await ensureGitRepo('git', dir)
-    const trunk = git('branch', '--show-current')
-    execFileSync('git', ['switch', '-c', 'rawr'], { cwd: dir })
-
-    const result = await addWorktree(dir, { existingBranch: trunk }, 'git')
-
-    assert.equal(result.branch, trunk)
-    assert.equal(fs.realpathSync(result.path), fs.realpathSync(dir))
-    assert.equal(git('branch', '--show-current'), trunk)
-    assert.equal(fs.existsSync(path.join(dir, '.worktrees', trunk)), false)
-  } finally {
-    fs.rmSync(dir, { recursive: true, force: true })
-  }
-})

apps/desktop/electron/git-worktrees.cjs

@@ -0,0 +1,174 @@
+'use strict'
+
+// Resolve git-worktree relationships for a set of session cwds, reading git's
+// on-disk metadata directly (no `git` spawn per path):
+//
+//   - A normal checkout has a `.git` DIRECTORY at its root → it's the main
+//     worktree; its repo root IS that directory's parent.
+//   - A linked worktree has a `.git` FILE: `gitdir: <repo>/.git/worktrees/<name>`.
+//     That admin dir's `commondir` points back at the shared `<repo>/.git`, whose
+//     parent is the main repo root.
+//
+// Grouping by repoRoot therefore clusters a repo's main checkout with all of its
+// linked worktrees, regardless of how the worktree directories are named. The
+// branch (read from the worktree's own HEAD) gives each worktree a meaningful
+// label.
+
+const fs = require('node:fs')
+const path = require('node:path')
+const { resolveRequestedPathForIpc } = require('./hardening.cjs')
+
+// Walk up from `start` to the nearest ancestor that carries a `.git` entry
+// (file for a linked worktree, dir for the main checkout). Capped so a stray
+// path can't loop forever.
+function findGitHost(start, fsImpl) {
+  let dir = start
+
+  for (let i = 0; i < 64; i += 1) {
+    const dotgit = path.join(dir, '.git')
+
+    try {
+      if (fsImpl.existsSync(dotgit)) {
+        return dir
+      }
+    } catch {
+      return null
+    }
+
+    const parent = path.dirname(dir)
+
+    if (parent === dir) {
+      return null
+    }
+
+    dir = parent
+  }
+
+  return null
+}
+
+function readBranch(gitDir, fsImpl) {
+  try {
+    const head = fsImpl.readFileSync(path.join(gitDir, 'HEAD'), 'utf8').trim()
+    const ref = head.match(/^ref:\s*refs\/heads\/(.+)$/)
+
+    if (ref) {
+      return ref[1]
+    }
+
+    // Detached HEAD: surface a short sha so the worktree still gets a label.
+    return /^[0-9a-f]{7,40}$/i.test(head) ? head.slice(0, 8) : null
+  } catch {
+    return null
+  }
+}
+
+// Given the directory that owns the `.git` entry, resolve its worktree identity.
+function resolveFromHost(host, fsImpl) {
+  const dotgit = path.join(host, '.git')
+  let stat
+
+  try {
+    stat = fsImpl.statSync(dotgit)
+  } catch {
+    return null
+  }
+
+  if (stat.isDirectory()) {
+    return {
+      repoRoot: host,
+      worktreeRoot: host,
+      isMainWorktree: true,
+      branch: readBranch(dotgit, fsImpl)
+    }
+  }
+
+  // Linked worktree: `.git` is a file pointing at the admin dir.
+  let contents
+
+  try {
+    contents = fsImpl.readFileSync(dotgit, 'utf8').trim()
+  } catch {
+    return null
+  }
+
+  const match = contents.match(/^gitdir:\s*(.+)$/m)
+
+  if (!match) {
+    return null
+  }
+
+  const adminDir = path.resolve(host, match[1].trim())
+
+  // `commondir` resolves to the shared `<repo>/.git`; fall back to walking two
+  // levels up from `<repo>/.git/worktrees/<name>` if it's missing.
+  let commonDir
+
+  try {
+    const rel = fsImpl.readFileSync(path.join(adminDir, 'commondir'), 'utf8').trim()
+    commonDir = path.resolve(adminDir, rel)
+  } catch {
+    commonDir = path.dirname(path.dirname(adminDir))
+  }
+
+  return {
+    repoRoot: path.dirname(commonDir),
+    worktreeRoot: host,
+    isMainWorktree: false,
+    branch: readBranch(adminDir, fsImpl)
+  }
+}
+
+function resolveWorktree(startPath, fsImpl = fs) {
+  let resolved
+
+  try {
+    resolved = resolveRequestedPathForIpc(startPath, { purpose: 'Worktree lookup' })
+  } catch {
+    return null
+  }
+
+  let start = resolved
+
+  try {
+    const stat = fsImpl.statSync(resolved)
+
+    if (!stat.isDirectory()) {
+      start = path.dirname(resolved)
+    }
+  } catch {
+    return null
+  }
+
+  const host = findGitHost(start, fsImpl)
+
+  if (!host) {
+    return null
+  }
+
+  return resolveFromHost(host, fsImpl)
+}
+
+// Batch entry point for the renderer: maps each requested cwd to its worktree
+// info (or null when it isn't inside a git checkout / can't be read). Dedupes so
+// many sessions sharing a cwd cost one lookup.
+async function worktreesForIpc(cwds, options = {}) {
+  const fsImpl = options.fs || fs
+  const list = Array.isArray(cwds) ? cwds : []
+  const out = {}
+
+  for (const cwd of list) {
+    if (typeof cwd !== 'string' || !cwd.trim() || cwd in out) {
+      continue
+    }
+
+    out[cwd] = resolveWorktree(cwd, fsImpl)
+  }
+
+  return out
+}
+
+module.exports = {
+  resolveWorktree,
+  worktreesForIpc
+}

apps/desktop/electron/hardening.cjs

@@ -186,10 +186,7 @@ async function statForIpc(fsImpl, resolvedPath, purpose, typeLabel) {
     if (code === 'ENOENT' || code === 'ENOTDIR') {
       throw ipcPathError(code || 'ENOENT', `${purpose} failed: ${typeLabel} does not exist.`)
     }
-    throw ipcPathError(
-      code || 'read-error',
-      `${purpose} failed: ${error instanceof Error ? error.message : String(error)}`
-    )
+    throw ipcPathError(code || 'read-error', `${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
   }
 }
 
@@ -204,10 +201,7 @@ async function realpathForIpc(fsImpl, resolvedPath, purpose) {
     return realPath
   } catch (error) {
     const code = error && typeof error === 'object' ? error.code : ''
-    throw ipcPathError(
-      code || 'read-error',
-      `${purpose} failed: ${error instanceof Error ? error.message : String(error)}`
-    )
+    throw ipcPathError(code || 'read-error', `${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
   }
 }
 

apps/desktop/electron/main.cjs

@@ -12,7 +12,6 @@ const {
   powerMonitor,
   protocol,
   safeStorage,
-  screen,
   session,
   shell,
   systemPreferences
@@ -21,6 +20,7 @@ const crypto = require('node:crypto')
 const fs = require('node:fs')
 const http = require('node:http')
 const https = require('node:https')
+const net = require('node:net')
 const path = require('node:path')
 const { pathToFileURL } = require('node:url')
 const { execFileSync, spawn } = require('node:child_process')
@@ -37,13 +37,11 @@ const { canImportHermesCli, verifyHermesCli } = require('./backend-probes.cjs')
 const { createLinkTitleWindow } = require('./link-title-window.cjs')
 const { probeGatewayWebSocket } = require('./gateway-ws-probe.cjs')
 const { adoptServedDashboardToken } = require('./dashboard-token.cjs')
-const { waitForDashboardPortAnnouncement } = require('./backend-ready.cjs')
+const { waitForDashboardPort } = require('./backend-ready.cjs')
 const { serializeJsonBody, setJsonRequestHeaders } = require('./oauth-net-request.cjs')
 const { fetchMarketplaceThemes, searchMarketplaceThemes } = require('./vscode-marketplace.cjs')
 const { buildDesktopBackendEnv, normalizeHermesHomeRoot } = require('./backend-env.cjs')
 const { readWindowsUserEnvVar } = require('./windows-user-env.cjs')
-const { readWslWindowsClipboardImage } = require('./wsl-clipboard-image.cjs')
-const { nativeOverlayWidth: computeNativeOverlayWidth } = require('./titlebar-overlay-width.cjs')
 const { readDirForIpc } = require('./fs-read-dir.cjs')
 const { readLiveUpdateMarker } = require('./update-marker.cjs')
 const {
@@ -56,25 +54,8 @@ const {
   buildRelaunchScript
 } = require('./update-relaunch.cjs')
 const { gitRootForIpc } = require('./git-root.cjs')
-const { addWorktree, listBranches, listWorktrees, removeWorktree, switchBranch } = require('./git-worktree-ops.cjs')
-const {
-  fileDiffVsHead,
-  repoStatus,
-  reviewCommit,
-  reviewCommitContext,
-  reviewCreatePr,
-  reviewDiff,
-  reviewList,
-  reviewPush,
-  reviewRevParse,
-  reviewRevert,
-  reviewShipInfo,
-  reviewStage,
-  reviewUnstage
-} = require('./git-review-ops.cjs')
-const { scanGitRepos } = require('./git-repo-scan.cjs')
+const { worktreesForIpc } = require('./git-worktrees.cjs')
 const { OFFICIAL_REPO_HTTPS_URL, isOfficialSshRemote } = require('./update-remote.cjs')
-const { resolveBehindCount, shouldCountCommits } = require('./update-count.cjs')
 const { runRebuildWithRetry } = require('./update-rebuild.cjs')
 const {
   buildPosixCleanupScript,
@@ -86,13 +67,6 @@ const {
   uninstallArgsForMode
 } = require('./desktop-uninstall.cjs')
 const { isPackagedInstallPath: isPackagedInstallPathUnderRoots } = require('./workspace-cwd.cjs')
-const {
-  MIN_WIDTH: WINDOW_MIN_WIDTH,
-  MIN_HEIGHT: WINDOW_MIN_HEIGHT,
-  sanitizeWindowState,
-  computeWindowOptions,
-  debounce
-} = require('./window-state.cjs')
 const {
   authModeFromStatus,
   buildGatewayWsUrl,
@@ -187,16 +161,6 @@ if (REMOTE_DISPLAY_REASON) {
   )
 }
 
-// WSLg: Chromium blocklists the Mesa vGPU → software compositing → typing lag.
-// /dev/dxg means a real GPU is available; un-blocklist it. Skipped when a remote
-// display already forced software (SSH'd-into-WSL).
-if (IS_WSL && !REMOTE_DISPLAY_REASON && fs.existsSync('/dev/dxg')) {
-  app.commandLine.appendSwitch('ignore-gpu-blocklist')
-  app.commandLine.appendSwitch('enable-gpu-rasterization')
-  app.commandLine.appendSwitch('enable-zero-copy')
-  console.log('[hermes] WSL GPU passthrough (/dev/dxg) detected; enabling GPU acceleration')
-}
-
 ipcMain.handle('hermes:get-remote-display-reason', () => REMOTE_DISPLAY_REASON)
 
 // Keep the renderer running at full speed while the window is in the background
@@ -329,7 +293,9 @@ function hermesManagedNodePathEntries() {
 }
 
 function pathWithHermesManagedNode(...entries) {
-  return [...hermesManagedNodePathEntries(), ...entries, process.env.PATH].filter(Boolean).join(path.delimiter)
+  return [...hermesManagedNodePathEntries(), ...entries, process.env.PATH]
+    .filter(Boolean)
+    .join(path.delimiter)
 }
 
 // ACTIVE_HERMES_ROOT — the canonical mutable Hermes install. Same path
@@ -354,7 +320,6 @@ const BOOTSTRAP_MARKER_SCHEMA_VERSION = 1
 
 const DESKTOP_CONNECTION_CONFIG_PATH = path.join(app.getPath('userData'), 'connection.json')
 const DESKTOP_UPDATE_CONFIG_PATH = path.join(app.getPath('userData'), 'updates.json')
-const DESKTOP_WINDOW_STATE_PATH = path.join(app.getPath('userData'), 'window-state.json')
 // active-profile.json records which Hermes profile the desktop launches its
 // local backend as. When set, startHermes() passes `hermes --profile <name>
 // dashboard …`, which deterministically pins HERMES_HOME (see
@@ -407,10 +372,14 @@ const WINDOW_BUTTON_POSITION = {
   x: 24,
   y: TITLEBAR_HEIGHT / 2 - MACOS_TRAFFIC_LIGHTS_HEIGHT / 2
 }
-// Right-edge window-control reservation lives in titlebar-overlay-width.cjs
-// (pure + unit-testable); computeNativeOverlayWidth() applies it per platform.
-// It's only the pre-layout fallback — the renderer measures the exact overlay
-// width live via the Window Controls Overlay API.
+// Width Electron reserves for the Windows/Linux native min/max/close cluster
+// when `titleBarOverlay` is enabled. The OS paints these buttons in the
+// top-right corner of the renderer; we have to leave that much room on the
+// right edge so our system tools (file browser, haptics, settings) don't sit
+// underneath them. macOS uses left-side traffic lights instead and reports a
+// position via getWindowButtonPosition(), so this width is non-zero only on
+// non-macOS platforms.
+const NATIVE_OVERLAY_BUTTON_WIDTH = 144
 const APP_ICON_PATHS = [
   path.join(APP_ROOT, 'public', 'apple-touch-icon.png'),
   path.join(APP_ROOT, 'dist', 'apple-touch-icon.png'),
@@ -524,48 +493,25 @@ function getWindowBackgroundColor() {
   return nativeTheme.shouldUseDarkColors ? '#111111' : '#f7f7f7'
 }
 
-// Transparent WCO — renderer chrome shows through. rgba(0,0,0,0) can fall back
-// to GetFrameColor() on some Electron builds; rgba(1,0,0,0) is the escape hatch.
-const TITLEBAR_OVERLAY_COLOR = 'rgba(1, 0, 0, 0)'
-
 function getTitleBarOverlayOptions() {
   if (IS_MAC) {
     return { height: TITLEBAR_HEIGHT }
   }
 
-  // Windows + WSLg paint WCO natively; plain Linux disables it (frameless hidden
-  // titlebar still applies).
-  if (!IS_WINDOWS && !IS_WSL) {
-    return false
+  if (rendererTitleBarTheme) {
+    return {
+      color: rendererTitleBarTheme.background,
+      height: TITLEBAR_HEIGHT,
+      symbolColor: rendererTitleBarTheme.foreground
+    }
   }
 
+  const useDarkColors = nativeTheme.shouldUseDarkColors
+
   return {
-    color: TITLEBAR_OVERLAY_COLOR,
+    color: useDarkColors ? '#111111' : '#f7f7f7',
     height: TITLEBAR_HEIGHT,
-    symbolColor:
-      rendererTitleBarTheme && isHexColor(rendererTitleBarTheme.foreground)
-        ? rendererTitleBarTheme.foreground
-        : nativeTheme.shouldUseDarkColors
-          ? '#f7f7f7'
-          : '#242424'
-  }
-}
-
-// Push refreshed overlay options to a live window after a theme/appearance
-// change. No-op only on plain (non-WSL) Linux, where getTitleBarOverlayOptions()
-// returns false; the try/catch additionally guards builds where
-// setTitleBarOverlay isn't supported.
-function applyTitleBarOverlay(win) {
-  const options = getTitleBarOverlayOptions()
-  if (!options || typeof options !== 'object') {
-    return
-  }
-
-  try {
-    win?.setTitleBarOverlay?.(options)
-  } catch {
-    // Overlay not supported on this platform/build — leave the frameless
-    // titlebar as-is.
+    symbolColor: useDarkColors ? '#f7f7f7' : '#242424'
   }
 }
 
@@ -788,9 +734,6 @@ let rendererReloadTimes = []
 // instead of re-running install.ps1 in a hot loop. Cleared explicitly by
 // the renderer's "Reload and retry" path or by quitting the app.
 let bootstrapFailure = null
-// Latched non-bootstrap backend spawn failure — stops getConnection() from
-// respawning hermes dashboard children in a tight loop while boot is broken.
-let backendStartFailure = null
 // Active first-launch install, so the renderer's Cancel button (and app quit)
 // can abort the in-flight install.sh/ps1 instead of leaving it running.
 let bootstrapAbortController = null
@@ -1301,36 +1244,6 @@ function isCommandScript(command) {
   return IS_WINDOWS && /\.(cmd|bat)$/i.test(command || '')
 }
 
-function unwrapWindowsVenvHermesCommand(command, dashboardArgs) {
-  if (!IS_WINDOWS || !command || isCommandScript(command)) return null
-
-  const resolved = path.resolve(String(command))
-  if (!/^hermes(?:\.exe)?$/i.test(path.basename(resolved))) return null
-
-  const scriptsDir = path.dirname(resolved)
-  if (path.basename(scriptsDir).toLowerCase() !== 'scripts') return null
-
-  const venvRoot = path.dirname(scriptsDir)
-  const python = getNoConsoleVenvPython(venvRoot)
-  if (!fileExists(python)) return null
-
-  const root = path.dirname(venvRoot)
-  return {
-    label: `existing Hermes no-console Python at ${python}`,
-    command: python,
-    args: ['-m', 'hermes_cli.main', ...dashboardArgs],
-    bootstrap: false,
-    env: buildDesktopBackendEnv({
-      hermesHome: HERMES_HOME,
-      pythonPathEntries: [...(directoryExists(root) ? [root] : []), ...getVenvSitePackagesEntries(venvRoot)],
-      venvRoot
-    }),
-    kind: 'python',
-    readyFile: true,
-    shell: false
-  }
-}
-
 function normalizeExecutablePathForCompare(commandPath) {
   if (!commandPath) return null
 
@@ -1551,97 +1464,6 @@ function getVenvPython(venvRoot) {
   return path.join(venvRoot, IS_WINDOWS ? path.join('Scripts', 'python.exe') : path.join('bin', 'python'))
 }
 
-function readVenvHome(venvRoot) {
-  try {
-    const cfg = fs.readFileSync(path.join(venvRoot, 'pyvenv.cfg'), 'utf8')
-    const match = cfg.match(/^home\s*=\s*(.+?)\s*$/im)
-    return match ? match[1].trim() : null
-  } catch {
-    return null
-  }
-}
-
-function getNoConsoleVenvPython(venvRoot) {
-  if (!IS_WINDOWS) return getVenvPython(venvRoot)
-
-  // Prefer the venv's own pythonw shim — it carries pyvenv.cfg / site-packages
-  // wiring. Falling back to the base uv/python.org pythonw.exe skips the venv
-  // and breaks imports (yaml, hermes_cli, …) even when PYTHONPATH is patched.
-  const venvPythonw = path.join(venvRoot, 'Scripts', 'pythonw.exe')
-  if (fileExists(venvPythonw)) return venvPythonw
-
-  const baseHome = readVenvHome(venvRoot)
-  if (baseHome) {
-    const basePythonw = path.join(baseHome, 'pythonw.exe')
-    if (fileExists(basePythonw)) return basePythonw
-  }
-
-  return venvPythonw
-}
-
-function toNoConsolePython(pythonPath) {
-  if (!IS_WINDOWS || !pythonPath) return pythonPath
-
-  const resolved = String(pythonPath)
-  if (/pythonw\.exe$/i.test(resolved)) return resolved
-
-  if (/python\.exe$/i.test(resolved)) {
-    const pythonw = path.join(path.dirname(resolved), 'pythonw.exe')
-    if (fileExists(pythonw)) return pythonw
-  }
-
-  return pythonPath
-}
-
-function applyWindowsNoConsoleSpawnHints(backend) {
-  if (!IS_WINDOWS || !backend?.command) return backend
-
-  const usesHermesModule =
-    backend.kind === 'python' ||
-    (Array.isArray(backend.args) && backend.args[0] === '-m' && backend.args[1] === 'hermes_cli.main')
-
-  if (!usesHermesModule) return backend
-
-  backend.command = toNoConsolePython(backend.command)
-  if (/pythonw\.exe$/i.test(path.basename(String(backend.command || '')))) {
-    backend.readyFile = true
-  }
-
-  return backend
-}
-
-function getVenvSitePackagesEntries(venvRoot) {
-  const entries = []
-  if (!venvRoot) return entries
-
-  if (IS_WINDOWS) {
-    const sitePackages = path.join(venvRoot, 'Lib', 'site-packages')
-    if (directoryExists(sitePackages)) entries.push(sitePackages)
-    return entries
-  }
-
-  const version = (() => {
-    try {
-      const cfg = fs.readFileSync(path.join(venvRoot, 'pyvenv.cfg'), 'utf8')
-      const match = cfg.match(/^version_info\s*=\s*(\d+\.\d+)/im)
-      return match ? match[1].trim() : null
-    } catch {
-      return null
-    }
-  })()
-  if (version) {
-    const sitePackages = path.join(venvRoot, 'lib', `python${version}`, 'site-packages')
-    if (directoryExists(sitePackages)) entries.push(sitePackages)
-  }
-  return entries
-}
-
-function makeDashboardReadyFile() {
-  const dir = path.join(app.getPath('userData'), 'backend-ready')
-  fs.mkdirSync(dir, { recursive: true })
-  return path.join(dir, `dashboard-${process.pid}-${Date.now()}-${crypto.randomBytes(6).toString('hex')}.json`)
-}
-
 // resolveGitBinary — locate git.exe on Windows. A fresh installer-driven
 // install only has PortableGit under %LOCALAPPDATA%\hermes\git (never on
 // PATH), so a bare spawn('git') ENOENTs and self-update checks fail with
@@ -1671,30 +1493,6 @@ function resolveGitBinary() {
   return _gitBinaryCache
 }
 
-// resolveGhBinary — locate the GitHub CLI. GUI-launched apps get a minimal PATH
-// that omits Homebrew (/opt/homebrew/bin, /usr/local/bin) where `gh` usually
-// lives, so a bare spawn('gh') ENOENTs even though `gh` works in the user's
-// terminal. Check the common install locations first, then PATH. Cached.
-let _ghBinaryCache = null
-function resolveGhBinary() {
-  if (_ghBinaryCache) return _ghBinaryCache
-
-  const candidates = []
-
-  if (IS_WINDOWS) {
-    candidates.push(path.join(process.env['ProgramFiles'] || 'C:\\Program Files', 'GitHub CLI', 'gh.exe'))
-    if (process.env.LOCALAPPDATA) {
-      candidates.push(path.join(process.env.LOCALAPPDATA, 'Microsoft', 'WinGet', 'Links', 'gh.exe'))
-    }
-  } else {
-    const home = app.getPath('home')
-    candidates.push('/opt/homebrew/bin/gh', '/usr/local/bin/gh', '/usr/bin/gh', path.join(home, '.local', 'bin', 'gh'))
-  }
-
-  _ghBinaryCache = candidates.find(fileExists) || findOnPath('gh') || 'gh'
-  return _ghBinaryCache
-}
-
 function recentHermesLog() {
   return hermesLog.slice(-20).join('\n')
 }
@@ -1724,36 +1522,6 @@ function writeDesktopUpdateConfig(config) {
   writeFileAtomic(DESKTOP_UPDATE_CONFIG_PATH, JSON.stringify(config, null, 2))
 }
 
-// ─── Main-window geometry persistence (window-state.json) ──────────────────
-
-function readWindowState() {
-  try {
-    return sanitizeWindowState(JSON.parse(fs.readFileSync(DESKTOP_WINDOW_STATE_PATH, 'utf8')))
-  } catch {
-    return null
-  }
-}
-
-// Persist the window's restored (non-maximized) bounds plus its maximized flag.
-// getNormalBounds() keeps the pre-maximize size, so un-maximizing next session
-// lands back where the user actually sized the window.
-function persistWindowState() {
-  if (!mainWindow || mainWindow.isDestroyed() || mainWindow.isMinimized()) return
-  try {
-    const { x, y, width, height } = mainWindow.getNormalBounds()
-    fs.mkdirSync(path.dirname(DESKTOP_WINDOW_STATE_PATH), { recursive: true })
-    writeFileAtomic(
-      DESKTOP_WINDOW_STATE_PATH,
-      JSON.stringify({ x, y, width, height, isMaximized: mainWindow.isMaximized() }, null, 2)
-    )
-  } catch (err) {
-    rememberLog(`[window-state] persist failed: ${err?.message || err}`)
-  }
-}
-
-// resized/moved fire many times mid-drag on Linux; debounce to one write.
-const schedulePersistWindowState = debounce(persistWindowState, 250)
-
 // Match the backend's source resolution but bias toward a real git checkout.
 // Dev → SOURCE_REPO_ROOT. Packaged/CLI install → ACTIVE_HERMES_ROOT.
 // HERMES_DESKTOP_HERMES_ROOT always wins so devs can pin a worktree.
@@ -1899,34 +1667,15 @@ async function checkUpdates() {
   }
 
   const git = args => runGit(args, { cwd: updateRoot }).then(r => r.stdout.trim())
-  const [currentSha, targetSha, dirtyStr, currentBranch, shallowStr, mergeBaseStr] = await Promise.all([
+  const [currentSha, targetSha, countStr, dirtyStr, currentBranch] = await Promise.all([
     git(['rev-parse', 'HEAD']),
     git(['rev-parse', `origin/${branch}`]),
+    git(['rev-list', `HEAD..origin/${branch}`, '--count']),
     git(['status', '--porcelain']),
-    git(['rev-parse', '--abbrev-ref', 'HEAD']),
-    git(['rev-parse', '--is-shallow-repository']),
-    // merge-base exits non-zero with empty stdout when HEAD shares no common
-    // ancestor with the freshly fetched tip — exactly the shallow-clone case.
-    git(['merge-base', 'HEAD', `origin/${branch}`])
+    git(['rev-parse', '--abbrev-ref', 'HEAD'])
   ])
 
-  const isShallow = shallowStr === 'true'
-  const hasMergeBase = Boolean(mergeBaseStr)
-  // Only enumerate the commit count when it is meaningful. On a shallow checkout
-  // with no merge-base, `rev-list --count` walks the entire remote ancestry
-  // (thousands of commits, see #51922) and resolveBehindCount discards the
-  // result anyway in favour of a SHA compare — so skip the expensive query.
-  const countStr = shouldCountCommits({ isShallow, hasMergeBase })
-    ? await git(['rev-list', `HEAD..origin/${branch}`, '--count'])
-    : ''
-
-  const behind = resolveBehindCount({
-    countStr,
-    currentSha,
-    targetSha,
-    isShallow,
-    hasMergeBase
-  })
+  const behind = Number.parseInt(countStr, 10) || 0
   const commits = behind > 0 ? await readCommitLog(updateRoot, branch) : []
 
   return {
@@ -2174,8 +1923,7 @@ async function applyUpdates(opts = {}) {
 
     emitUpdateProgress({
       stage: 'restart',
-      message:
-        'Updating Hermes — this window will close and the updater will open. Don’t reopen Hermes yourself; it restarts automatically when the update finishes.',
+      message: 'Updating Hermes — this window will close and the updater will open. Don’t reopen Hermes yourself; it restarts automatically when the update finishes.',
       percent: 100
     })
     repairMacUpdaterHelper(updater)
@@ -2258,9 +2006,7 @@ async function handOffWindowsBootstrapRecovery(reason) {
   })
   child.unref()
 
-  rememberLog(
-    `[bootstrap] handed off ${reason} recovery to updater: ${updater} ${updaterArgs.join(' ')}; exiting desktop to release app.asar`
-  )
+  rememberLog(`[bootstrap] handed off ${reason} recovery to updater: ${updater} ${updaterArgs.join(' ')}; exiting desktop to release app.asar`)
   // Same dwell as the in-app update hand-off (#50419): give the updater's
   // window time to appear before we vanish, so the recovery doesn't look like
   // a crash and provoke a mid-recovery relaunch.
@@ -2785,24 +2531,20 @@ function createPythonBackend(root, label, dashboardArgs, options = {}) {
   const python = findPythonForRoot(root)
   if (!python) return null
 
-  const venvRoot = path.join(root, 'venv')
-  const venvPython = getVenvPython(venvRoot)
-  const command = IS_WINDOWS && fileExists(venvPython) ? getNoConsoleVenvPython(venvRoot) : toNoConsolePython(python)
-
-  return applyWindowsNoConsoleSpawnHints({
+  return {
     kind: 'python',
     label,
-    command,
+    command: python,
     args: ['-m', 'hermes_cli.main', ...dashboardArgs],
     env: buildDesktopBackendEnv({
       hermesHome: HERMES_HOME,
       pythonPathEntries: [root],
-      venvRoot
+      venvRoot: path.join(root, 'venv')
     }),
     root,
     bootstrap: Boolean(options.bootstrap),
     shell: false
-  })
+  }
 }
 
 // createActiveBackend — build a backend pointing at ACTIVE_HERMES_ROOT, the
@@ -2811,12 +2553,11 @@ function createPythonBackend(root, label, dashboardArgs, options = {}) {
 // ensureRuntime() to create / refresh it before launch.
 function createActiveBackend(dashboardArgs) {
   const venvPython = getVenvPython(VENV_ROOT)
-  const command = fileExists(venvPython) ? getNoConsoleVenvPython(VENV_ROOT) : toNoConsolePython(findSystemPython())
 
-  return applyWindowsNoConsoleSpawnHints({
+  return {
     kind: 'python',
     label: `Hermes at ${ACTIVE_HERMES_ROOT}`,
-    command,
+    command: fileExists(venvPython) ? venvPython : findSystemPython(),
     args: ['-m', 'hermes_cli.main', ...dashboardArgs],
     env: buildDesktopBackendEnv({
       hermesHome: HERMES_HOME,
@@ -2826,7 +2567,7 @@ function createActiveBackend(dashboardArgs) {
     root: ACTIVE_HERMES_ROOT,
     bootstrap: true,
     shell: false
-  })
+  }
 }
 
 function resolveHermesBackend(dashboardArgs) {
@@ -2887,11 +2628,6 @@ function resolveHermesBackend(dashboardArgs) {
     }
 
     if (hermesCommand) {
-      const unwrapped = unwrapWindowsVenvHermesCommand(hermesCommand, dashboardArgs)
-      if (unwrapped) {
-        return unwrapped
-      }
-
       // Smoke-test the candidate before trusting it. A `hermes` shim
       // left behind by a half-uninstalled pip install (or a venv
       // entry-point pointing at a deleted interpreter) still resolves
@@ -2901,17 +2637,15 @@ function resolveHermesBackend(dashboardArgs) {
       // and lets the resolver fall through to step 6 / bootstrap.
       const shellForProbe = isCommandScript(hermesCommand)
       if (verifyHermesCli(hermesCommand, { shell: shellForProbe })) {
-        return (
-          unwrapWindowsVenvHermesCommand(hermesCommand, dashboardArgs) || {
-            label: `existing Hermes CLI at ${hermesCommand}`,
-            command: hermesCommand,
-            args: dashboardArgs,
-            bootstrap: false,
-            env: {},
-            kind: 'command',
-            shell: shellForProbe
-          }
-        )
+        return {
+          label: `existing Hermes CLI at ${hermesCommand}`,
+          command: hermesCommand,
+          args: dashboardArgs,
+          bootstrap: false,
+          env: {},
+          kind: 'command',
+          shell: shellForProbe
+        }
       }
       rememberLog(
         `Ignoring existing Hermes CLI at ${hermesCommand}: --version probe failed; falling through to bootstrap.`
@@ -2933,15 +2667,15 @@ function resolveHermesBackend(dashboardArgs) {
     // failure, fall through to step 6 so the bootstrap runner pulls
     // a uv-managed 3.11 into %LOCALAPPDATA%\hermes\hermes-agent\venv.
     if (canImportHermesCli(python)) {
-      return applyWindowsNoConsoleSpawnHints({
+      return {
         kind: 'python',
         label: `installed hermes_cli module via ${python}`,
-        command: toNoConsolePython(python),
+        command: python,
         args: ['-m', 'hermes_cli.main', ...dashboardArgs],
         bootstrap: false,
         env: {},
         shell: false
-      })
+      }
     }
     rememberLog(`Ignoring system Python ${python}: hermes_cli is not importable; falling through to bootstrap.`)
   }
@@ -2975,7 +2709,7 @@ function resolveHermesBackend(dashboardArgs) {
 async function ensureRuntime(backend) {
   if (!backend.bootstrap) {
     await advanceBootProgress('runtime.external', `Using ${backend.label}`, 32)
-    return applyWindowsNoConsoleSpawnHints(backend)
+    return backend
   }
 
   // backend.kind === 'bootstrap-needed' means resolveHermesBackend couldn't
@@ -2991,9 +2725,7 @@ async function ensureRuntime(backend) {
     rememberLog('[bootstrap] no Hermes install found; starting first-launch bootstrap')
 
     if (await handOffWindowsBootstrapRecovery('bootstrap-needed')) {
-      const handoffError = new Error(
-        'Hermes recovery was handed off to Hermes Setup. The desktop will restart when recovery completes.'
-      )
+      const handoffError = new Error('Hermes recovery was handed off to Hermes Setup. The desktop will restart when recovery completes.')
       handoffError.isBootstrapFailure = true
       handoffError.bootstrapHandedOff = true
       bootstrapFailure = handoffError
@@ -3117,7 +2849,7 @@ async function ensureRuntime(backend) {
     )
   }
 
-  backend.command = getNoConsoleVenvPython(VENV_ROOT)
+  backend.command = venvPython
   backend.label = `Hermes at ${ACTIVE_HERMES_ROOT} (venv: ${VENV_ROOT})`
   updateBootProgress({
     phase: 'runtime.ready',
@@ -3126,9 +2858,10 @@ async function ensureRuntime(backend) {
     running: true,
     error: null
   })
-  return applyWindowsNoConsoleSpawnHints(backend)
+  return backend
 }
 
+
 function fetchJson(url, token, options = {}) {
   return new Promise((resolve, reject) => {
     const body = options.body === undefined ? undefined : Buffer.from(JSON.stringify(options.body))
@@ -3787,7 +3520,11 @@ function getWindowButtonPosition() {
 }
 
 function getNativeOverlayWidth() {
-  return computeNativeOverlayWidth({ isWindows: IS_WINDOWS, isWsl: IS_WSL })
+  // macOS reports traffic-light coords via windowButtonPosition; the
+  // titlebarOverlay there doesn't reserve right-edge space. Windows/Linux
+  // render the native window-controls overlay on the right, so the renderer
+  // needs to inset its right cluster by this much to clear them.
+  return IS_MAC ? 0 : NATIVE_OVERLAY_BUTTON_WIDTH
 }
 
 function getWindowState() {
@@ -5035,7 +4772,6 @@ function resetBootProgressForReconnect() {
 
 function resetHermesConnection() {
   connectionPromise = null
-  backendStartFailure = null
 
   if (hermesProcess && !hermesProcess.killed) {
     hermesProcess.kill('SIGTERM')
@@ -5197,7 +4933,6 @@ async function spawnPoolBackend(profile, entry) {
   const backend = await ensureRuntime(resolveHermesBackend(dashboardArgs))
   const hermesCwd = resolveHermesCwd()
   const webDist = resolveWebDist()
-  const readyFile = backend.readyFile ? makeDashboardReadyFile() : null
 
   rememberLog(`Starting Hermes backend for profile "${profile}" via ${backend.label}`)
 
@@ -5218,8 +4953,7 @@ async function spawnPoolBackend(profile, entry) {
         // Marks this dashboard backend as desktop-spawned so it runs the cron
         // scheduler tick loop (the gateway isn't running under the app).
         HERMES_DESKTOP: '1',
-        HERMES_WEB_DIST: webDist,
-        ...(readyFile ? { HERMES_DESKTOP_READY_FILE: readyFile } : {})
+        HERMES_WEB_DIST: webDist
       },
       shell: backend.shell,
       stdio: ['ignore', 'pipe', 'pipe']
@@ -5252,10 +4986,7 @@ async function spawnPoolBackend(profile, entry) {
   })
 
   // Discover the ephemeral port the child bound to
-  const port = await Promise.race([waitForDashboardPortAnnouncement(child, { readyFile }), startFailed])
-  if (readyFile) {
-    fs.unlink(readyFile, () => {})
-  }
+  const port = await Promise.race([waitForDashboardPort(child), startFailed])
   entry.port = port
 
   const baseUrl = `http://127.0.0.1:${port}`
@@ -5368,9 +5099,6 @@ async function startHermes() {
   if (bootstrapFailure) {
     throw bootstrapFailure
   }
-  if (backendStartFailure) {
-    throw backendStartFailure
-  }
   if (connectionPromise) return connectionPromise
 
   connectionPromise = (async () => {
@@ -5424,7 +5152,6 @@ async function startHermes() {
     const backend = await ensureRuntime(resolveHermesBackend(dashboardArgs))
     const hermesCwd = resolveHermesCwd()
     const webDist = resolveWebDist()
-    const readyFile = backend.readyFile ? makeDashboardReadyFile() : null
 
     await advanceBootProgress('backend.spawn', `Starting Hermes backend via ${backend.label}`, 84)
     rememberLog(`Starting Hermes backend via ${backend.label}`)
@@ -5451,8 +5178,7 @@ async function startHermes() {
           // Marks this dashboard backend as desktop-spawned so it runs the cron
           // scheduler tick loop (the gateway isn't running under the app).
           HERMES_DESKTOP: '1',
-          HERMES_WEB_DIST: webDist,
-          ...(readyFile ? { HERMES_DESKTOP_READY_FILE: readyFile } : {})
+          HERMES_WEB_DIST: webDist
         },
         shell: backend.shell,
         stdio: ['ignore', 'pipe', 'pipe']
@@ -5508,19 +5234,12 @@ async function startHermes() {
 
     await advanceBootProgress('backend.port', 'Waiting for Hermes backend to launch', 86)
     // Discover the ephemeral port the child bound to
-    const port = await Promise.race([
-      waitForDashboardPortAnnouncement(hermesProcess, { readyFile }),
-      backendStartFailed
-    ])
-    if (readyFile) {
-      fs.unlink(readyFile, () => {})
-    }
+    const port = await Promise.race([waitForDashboardPort(hermesProcess), backendStartFailed])
 
     const baseUrl = `http://127.0.0.1:${port}`
     await advanceBootProgress('backend.wait', 'Waiting for Hermes backend to become ready', 90)
     await Promise.race([waitForHermes(baseUrl, token), backendStartFailed])
     backendReady = true
-    backendStartFailure = null
     const authToken = await adoptServedDashboardToken(baseUrl, token, {
       // The exit/error handlers null hermesProcess when the child dies.
       childAlive: () => hermesProcess !== null && hermesProcess.exitCode === null && !hermesProcess.killed,
@@ -5546,7 +5265,6 @@ async function startHermes() {
     }
   })().catch(error => {
     const message = error instanceof Error ? error.message : String(error)
-    backendStartFailure = error instanceof Error ? error : new Error(message)
     updateBootProgress(
       {
         error: message,
@@ -5805,11 +5523,11 @@ function closePetOverlay() {
 
 function createWindow() {
   const icon = getAppIconPath()
-  const savedWindowState = readWindowState()
   mainWindow = new BrowserWindow({
-    ...computeWindowOptions(savedWindowState, screen.getAllDisplays()),
-    minWidth: WINDOW_MIN_WIDTH,
-    minHeight: WINDOW_MIN_HEIGHT,
+    width: 1220,
+    height: 800,
+    minWidth: 400,
+    minHeight: 620,
     title: 'Hermes',
     // Frameless title bar on every platform so the renderer can paint the
     // "hide sidebar" button (and other left-side titlebar tools) flush with
@@ -5846,13 +5564,11 @@ function createWindow() {
     if (!nativeThemeListenerInstalled) {
       nativeThemeListenerInstalled = true
       nativeTheme.on('updated', () => {
-        applyTitleBarOverlay(mainWindow)
+        mainWindow?.setTitleBarOverlay?.(getTitleBarOverlayOptions())
       })
     }
   }
 
-  if (savedWindowState?.isMaximized) mainWindow.maximize()
-
   mainWindow.once('ready-to-show', () => {
     if (mainWindow && !mainWindow.isDestroyed()) mainWindow.show()
   })
@@ -5862,14 +5578,6 @@ function createWindow() {
   mainWindow.on('will-leave-full-screen', () => sendWindowStateChanged(false))
   mainWindow.on('leave-full-screen', () => sendWindowStateChanged(false))
 
-  // Reopen where the user left off. resized/moved settle once per drag; close is
-  // the cross-platform backstop, flushed synchronously before the window is gone.
-  mainWindow.on('resized', schedulePersistWindowState)
-  mainWindow.on('moved', schedulePersistWindowState)
-  mainWindow.on('maximize', schedulePersistWindowState)
-  mainWindow.on('unmaximize', schedulePersistWindowState)
-  mainWindow.on('close', () => schedulePersistWindowState.flush())
-
   // The overlay rides the main window — closing the app's primary window must
   // tear it down too (otherwise it strands as an orphan that blocks
   // window-all-closed from quitting on Windows/Linux).
@@ -6030,32 +5738,19 @@ ipcMain.handle('hermes:pet-overlay:close', async () => {
 
   return { ok: true }
 })
-// Drag/resize: the overlay reports new absolute screen bounds (it already knows
-// the pointer's screen coords). Drag keeps the size constant; the wheel-to-scale
-// gesture grows/shrinks it so the sprite is never cropped by the window edge.
-// The window is created non-resizable (no stray edge-drag on the transparent
-// frameless panel), which on Windows/Linux also blocks programmatic setBounds
-// sizing — so briefly flip resizable on whenever the size actually changes.
+// Drag: the overlay reports a new absolute screen position (it already knows the
+// pointer's screen coords), we just move the window.
 ipcMain.on('hermes:pet-overlay:set-bounds', (_event, bounds) => {
   if (!petOverlayWindow || petOverlayWindow.isDestroyed() || !bounds) {
     return
   }
 
-  const win = petOverlayWindow
-  const width = Math.max(80, Math.round(bounds.width))
-  const height = Math.max(80, Math.round(bounds.height))
-  const [curW, curH] = win.getSize()
-  const resizing = width !== curW || height !== curH
-
-  if (resizing && !win.isResizable()) {
-    win.setResizable(true)
-  }
-
-  win.setBounds({ x: Math.round(bounds.x), y: Math.round(bounds.y), width, height })
-
-  if (resizing) {
-    win.setResizable(false)
-  }
+  petOverlayWindow.setBounds({
+    x: Math.round(bounds.x),
+    y: Math.round(bounds.y),
+    width: Math.max(80, Math.round(bounds.width)),
+    height: Math.max(80, Math.round(bounds.height))
+  })
 })
 // Click-through: the overlay window is a full rectangle but only the pet pixels
 // should be interactive. The renderer toggles this as the cursor enters/leaves
@@ -6125,7 +5820,6 @@ ipcMain.handle('hermes:bootstrap:reset', async () => {
   rememberLog('[bootstrap] reset requested by renderer; clearing latched failure')
   await teardownPrimaryBackendAndWait()
   bootstrapFailure = null
-  backendStartFailure = null
   bootstrapState = {
     active: false,
     manifest: null,
@@ -6152,7 +5846,6 @@ ipcMain.handle('hermes:bootstrap:repair', async () => {
     rememberLog(`[bootstrap] failed to remove marker during repair: ${error.message}`)
   }
   bootstrapFailure = null
-  backendStartFailure = null
   resetHermesConnection()
   return { ok: true }
 })
@@ -6521,21 +6214,11 @@ ipcMain.handle('hermes:saveImageBuffer', async (_event, payload) => {
 
 ipcMain.handle('hermes:saveClipboardImage', async () => {
   const image = clipboard.readImage()
-  if (image && !image.isEmpty()) {
-    return writeComposerImage(image.toPNG(), '.png')
+  if (!image || image.isEmpty()) {
+    return ''
   }
 
-  // WSL2/WSLg doesn't bridge clipboard *images* from the Windows host to the
-  // Linux clipboard Electron reads, so a host screenshot looks empty above.
-  // Pull it straight off the Windows clipboard via PowerShell as a fallback.
-  if (IS_WSL) {
-    const png = readWslWindowsClipboardImage()
-    if (png) {
-      return writeComposerImage(png, '.png')
-    }
-  }
-
-  return ''
+  return writeComposerImage(image.toPNG(), '.png')
 })
 
 ipcMain.handle('hermes:normalizePreviewTarget', (_event, target, baseDir) =>
@@ -6555,7 +6238,7 @@ ipcMain.on('hermes:titlebar-theme', (_event, payload) => {
     background: payload.background,
     foreground: payload.foreground
   }
-  applyTitleBarOverlay(mainWindow)
+  mainWindow?.setTitleBarOverlay?.(getTitleBarOverlayOptions())
 })
 
 // Pin the native appearance to the app theme (see NATIVE_THEME_CONFIG_PATH).
@@ -6844,160 +6527,7 @@ ipcMain.handle('hermes:fs:readDir', async (_event, dirPath) => readDirForIpc(dir
 
 ipcMain.handle('hermes:fs:gitRoot', async (_event, startPath) => gitRootForIpc(startPath))
 
-// Reveal a path in the OS file manager (Finder / Explorer / Files).
-ipcMain.handle('hermes:fs:reveal', async (_event, targetPath) => {
-  const target = String(targetPath || '').trim()
-
-  if (!target) {
-    return false
-  }
-
-  try {
-    shell.showItemInFolder(target)
-
-    return true
-  } catch {
-    return false
-  }
-})
-
-// Rename a file/folder in place. The renderer passes the existing path + a new
-// base name; the destination is resolved in the SAME parent dir so a rename can
-// never move the item elsewhere or traverse out. Rejects on a name collision.
-ipcMain.handle('hermes:fs:rename', async (_event, targetPath, newName) => {
-  const src = String(targetPath || '').trim()
-  const name = String(newName || '').trim()
-
-  if (!src || !name || name === '.' || name === '..' || name.includes('/') || name.includes('\\')) {
-    throw new Error('Invalid rename')
-  }
-
-  const dst = path.join(path.dirname(src), name)
-
-  if (dst === src) {
-    return { path: dst }
-  }
-
-  if (fs.existsSync(dst)) {
-    throw new Error(`"${name}" already exists`)
-  }
-
-  await fs.promises.rename(src, dst)
-
-  return { path: dst }
-})
-
-// Write a small UTF-8 text file (e.g. a project's IDEA.md at creation). The path
-// is hardened (resolveRequestedPathForIpc) and the parent must already exist —
-// this never creates directory trees or escapes the allowed roots, and content
-// is size-capped so it can't be abused as a bulk-write primitive.
-ipcMain.handle('hermes:fs:writeText', async (_event, filePath, content) => {
-  const raw = String(filePath || '').trim()
-
-  if (!raw) {
-    throw new Error('Invalid path')
-  }
-
-  const text = String(content ?? '')
-
-  if (text.length > 1_000_000) {
-    throw new Error('Content too large')
-  }
-
-  const resolved = resolveRequestedPathForIpc(expandUserPath(raw), { purpose: 'Write text file' })
-
-  if (!directoryExists(path.dirname(resolved))) {
-    throw new Error('Parent directory does not exist')
-  }
-
-  await fs.promises.writeFile(resolved, text, 'utf8')
-
-  return { path: resolved }
-})
-
-// Move a file/folder to the OS trash (recoverable) — the VS Code "Delete"
-// default. `shell.trashItem` routes to Finder/Explorer/Files trash per platform.
-ipcMain.handle('hermes:fs:trash', async (_event, targetPath) => {
-  const target = String(targetPath || '').trim()
-
-  if (!target) {
-    throw new Error('Invalid delete')
-  }
-
-  await shell.trashItem(target)
-
-  return true
-})
-
-// Git-driven worktree management ("Start work" flow). Errors surface to the
-// renderer as rejected promises so it can toast a friendly message.
-ipcMain.handle('hermes:git:worktreeList', async (_event, repoPath) => listWorktrees(repoPath, resolveGitBinary()))
-
-ipcMain.handle('hermes:git:worktreeAdd', async (_event, repoPath, options) =>
-  addWorktree(repoPath, options || {}, resolveGitBinary())
-)
-
-ipcMain.handle('hermes:git:worktreeRemove', async (_event, repoPath, worktreePath, options) =>
-  removeWorktree(repoPath, worktreePath, options || {}, resolveGitBinary())
-)
-
-ipcMain.handle('hermes:git:branchSwitch', async (_event, repoPath, branch) =>
-  switchBranch(repoPath, branch, resolveGitBinary())
-)
-
-ipcMain.handle('hermes:git:branchList', async (_event, repoPath) => listBranches(repoPath, resolveGitBinary()))
-
-// Compact repo status (branch, ahead/behind, change counts + files) for the
-// composer coding rail. Returns null on a non-repo / remote backend so the rail
-// hides cleanly rather than erroring.
-ipcMain.handle('hermes:git:repoStatus', async (_event, repoPath) => repoStatus(repoPath, resolveGitBinary()))
-
-// Codex-style review pane: list changed files for a scope, fetch one file's
-// unified diff, and stage / unstage / revert. Reads return empty on failure;
-// mutations reject so the renderer can toast.
-ipcMain.handle('hermes:git:review:list', async (_event, repoPath, scope, baseRef) =>
-  reviewList(repoPath, scope, baseRef, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:diff', async (_event, repoPath, filePath, scope, baseRef, staged) =>
-  reviewDiff(repoPath, filePath, scope, baseRef, staged, resolveGitBinary())
-)
-// Working-tree-vs-HEAD diff for one file (the preview's "show the diff" view).
-ipcMain.handle('hermes:git:fileDiff', async (_event, repoPath, filePath) =>
-  fileDiffVsHead(repoPath, filePath, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:stage', async (_event, repoPath, filePath) =>
-  reviewStage(repoPath, filePath ?? null, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:unstage', async (_event, repoPath, filePath) =>
-  reviewUnstage(repoPath, filePath ?? null, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:revert', async (_event, repoPath, filePath) =>
-  reviewRevert(repoPath, filePath ?? null, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:revParse', async (_event, repoPath, ref) =>
-  reviewRevParse(repoPath, ref, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:commit', async (_event, repoPath, message, push) =>
-  reviewCommit(repoPath, message, Boolean(push), resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:commitContext', async (_event, repoPath) =>
-  reviewCommitContext(repoPath, resolveGitBinary())
-)
-ipcMain.handle('hermes:git:review:push', async (_event, repoPath) => reviewPush(repoPath, resolveGitBinary()))
-ipcMain.handle('hermes:git:review:shipInfo', async (_event, repoPath) => reviewShipInfo(repoPath, resolveGhBinary()))
-ipcMain.handle('hermes:git:review:createPr', async (_event, repoPath) =>
-  reviewCreatePr(repoPath, resolveGitBinary(), resolveGhBinary())
-)
-
-// Repo-first project discovery: scan bounded roots for git repos (pure fs walk,
-// no native addon). Never throws to the renderer — failures yield an empty list.
-ipcMain.handle('hermes:git:scanRepos', async (_event, roots, options) => {
-  try {
-    return await scanGitRepos(roots || [], options || {})
-  } catch {
-    return []
-  }
-})
+ipcMain.handle('hermes:fs:worktrees', async (_event, cwds) => worktreesForIpc(cwds))
 
 ipcMain.handle('hermes:terminal:start', async (event, payload = {}) => {
   if (!nodePty) {

apps/desktop/electron/oauth-net-request.test.cjs

@@ -30,8 +30,5 @@ test('setJsonRequestHeaders does not set Electron-restricted Content-Length', ()
   setJsonRequestHeaders(request)
 
   assert.deepEqual(headers, [['Content-Type', 'application/json']])
-  assert.equal(
-    headers.some(([name]) => name.toLowerCase() === 'content-length'),
-    false
-  )
+  assert.equal(headers.some(([name]) => name.toLowerCase() === 'content-length'), false)
 })

apps/desktop/electron/preload.cjs

@@ -82,35 +82,7 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
   getRecentLogs: () => ipcRenderer.invoke('hermes:logs:recent'),
   readDir: dirPath => ipcRenderer.invoke('hermes:fs:readDir', dirPath),
   gitRoot: startPath => ipcRenderer.invoke('hermes:fs:gitRoot', startPath),
-  revealPath: targetPath => ipcRenderer.invoke('hermes:fs:reveal', targetPath),
-  renamePath: (targetPath, newName) => ipcRenderer.invoke('hermes:fs:rename', targetPath, newName),
-  writeTextFile: (filePath, content) => ipcRenderer.invoke('hermes:fs:writeText', filePath, content),
-  trashPath: targetPath => ipcRenderer.invoke('hermes:fs:trash', targetPath),
-  git: {
-    worktreeList: repoPath => ipcRenderer.invoke('hermes:git:worktreeList', repoPath),
-    worktreeAdd: (repoPath, options) => ipcRenderer.invoke('hermes:git:worktreeAdd', repoPath, options),
-    worktreeRemove: (repoPath, worktreePath, options) =>
-      ipcRenderer.invoke('hermes:git:worktreeRemove', repoPath, worktreePath, options),
-    branchSwitch: (repoPath, branch) => ipcRenderer.invoke('hermes:git:branchSwitch', repoPath, branch),
-    branchList: repoPath => ipcRenderer.invoke('hermes:git:branchList', repoPath),
-    repoStatus: repoPath => ipcRenderer.invoke('hermes:git:repoStatus', repoPath),
-    fileDiff: (repoPath, filePath) => ipcRenderer.invoke('hermes:git:fileDiff', repoPath, filePath),
-    scanRepos: (roots, options) => ipcRenderer.invoke('hermes:git:scanRepos', roots, options),
-    review: {
-      list: (repoPath, scope, baseRef) => ipcRenderer.invoke('hermes:git:review:list', repoPath, scope, baseRef),
-      diff: (repoPath, filePath, scope, baseRef, staged) =>
-        ipcRenderer.invoke('hermes:git:review:diff', repoPath, filePath, scope, baseRef, staged),
-      stage: (repoPath, filePath) => ipcRenderer.invoke('hermes:git:review:stage', repoPath, filePath),
-      unstage: (repoPath, filePath) => ipcRenderer.invoke('hermes:git:review:unstage', repoPath, filePath),
-      revert: (repoPath, filePath) => ipcRenderer.invoke('hermes:git:review:revert', repoPath, filePath),
-      revParse: (repoPath, ref) => ipcRenderer.invoke('hermes:git:review:revParse', repoPath, ref),
-      commit: (repoPath, message, push) => ipcRenderer.invoke('hermes:git:review:commit', repoPath, message, push),
-      commitContext: repoPath => ipcRenderer.invoke('hermes:git:review:commitContext', repoPath),
-      push: repoPath => ipcRenderer.invoke('hermes:git:review:push', repoPath),
-      shipInfo: repoPath => ipcRenderer.invoke('hermes:git:review:shipInfo', repoPath),
-      createPr: repoPath => ipcRenderer.invoke('hermes:git:review:createPr', repoPath)
-    }
-  },
+  worktrees: cwds => ipcRenderer.invoke('hermes:fs:worktrees', cwds),
   terminal: {
     dispose: id => ipcRenderer.invoke('hermes:terminal:dispose', id),
     resize: (id, size) => ipcRenderer.invoke('hermes:terminal:resize', id, size),

apps/desktop/electron/titlebar-overlay-width.cjs

@@ -1,11 +0,0 @@
-// Pre-layout fallback for WCO right-edge reservation (--titlebar-tools-right).
-// Live width comes from navigator.windowControlsOverlay in the renderer.
-
-const OVERLAY_FALLBACK_WIDTH = 144
-
-/** @param {{ isWindows?: boolean, isWsl?: boolean }} opts */
-function nativeOverlayWidth({ isWindows = false, isWsl = false } = {}) {
-  return isWindows || isWsl ? OVERLAY_FALLBACK_WIDTH : 0
-}
-
-module.exports = { OVERLAY_FALLBACK_WIDTH, nativeOverlayWidth }

apps/desktop/electron/titlebar-overlay-width.test.cjs

@@ -1,29 +0,0 @@
-const assert = require('node:assert/strict')
-const test = require('node:test')
-
-const { OVERLAY_FALLBACK_WIDTH, nativeOverlayWidth } = require('./titlebar-overlay-width.cjs')
-
-// This static reservation is only the pre-layout FALLBACK. Once laid out the
-// renderer reads the exact width from navigator.windowControlsOverlay
-// (use-window-controls-overlay-width.ts) and uses these values only when the WCO
-// API is unavailable.
-
-test('Windows reserves the overlay fallback width', () => {
-  assert.equal(nativeOverlayWidth({ isWindows: true }), OVERLAY_FALLBACK_WIDTH)
-})
-
-test('WSLg paints the same WCO, so it reserves the same fallback width', () => {
-  // The original bug: WSL fell through to 0, so the right tools sat under the
-  // controls and the title overran into them.
-  assert.equal(nativeOverlayWidth({ isWsl: true }), OVERLAY_FALLBACK_WIDTH)
-})
-
-test('plain Linux and macOS reserve nothing', () => {
-  assert.equal(nativeOverlayWidth({ isWindows: false, isWsl: false }), 0)
-  assert.equal(nativeOverlayWidth(), 0)
-  assert.equal(nativeOverlayWidth({}), 0)
-})
-
-test('the fallback width is a sane positive pixel value', () => {
-  assert.ok(Number.isInteger(OVERLAY_FALLBACK_WIDTH) && OVERLAY_FALLBACK_WIDTH > 0)
-})

apps/desktop/electron/update-count.cjs

@@ -1,28 +0,0 @@
-'use strict'
-
-// Whether `git rev-list HEAD..origin/<branch> --count` produces a meaningful
-// number worth computing. On a SHALLOW checkout (installer clones with
-// --depth 1) the local history often shares no merge-base with the freshly
-// fetched origin tip, so the count enumerates the entire remote ancestry and
-// returns a bogus huge number (e.g. 12104) — see #51922. resolveBehindCount
-// discards that bogus count in favour of a SHA compare, so the caller should
-// SKIP the expensive rev-list entirely in that case rather than run it and
-// throw the result away.
-function shouldCountCommits({ isShallow, hasMergeBase }) {
-  return !(isShallow && !hasMergeBase)
-}
-
-// Resolve how many commits the local checkout is behind origin for the desktop
-// update indicator. When the count isn't meaningful (shallow + no merge-base)
-// fall back to a binary up-to-date check by SHA, exactly like the official-SSH
-// path in checkUpdates() and the CLI guard in hermes_cli/banner.py. Full clones
-// (developers / Docker dev images) keep the exact count path unchanged.
-function resolveBehindCount({ countStr, currentSha, targetSha, isShallow, hasMergeBase }) {
-  if (!shouldCountCommits({ isShallow, hasMergeBase })) {
-    if (currentSha && targetSha && currentSha === targetSha) return 0
-    return 1 // behind by an unknown amount — show a generic "update available"
-  }
-  return Number.parseInt(countStr, 10) || 0
-}
-
-module.exports = { resolveBehindCount, shouldCountCommits }

apps/desktop/electron/update-count.test.cjs

@@ -1,127 +0,0 @@
-'use strict'
-const test = require('node:test')
-const assert = require('node:assert/strict')
-const { resolveBehindCount, shouldCountCommits } = require('./update-count.cjs')
-
-// FAIL-BEFORE: pre-fix the function did `Number.parseInt(countStr) || 0`
-// unconditionally, so a shallow checkout with no merge-base surfaced the bogus
-// rev-list count (e.g. 12104). This asserts the new shallow/no-merge-base branch.
-test('shallow checkout with no merge-base does NOT trust the bogus rev-list count', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '12104',
-      currentSha: 'aaa',
-      targetSha: 'bbb',
-      isShallow: true,
-      hasMergeBase: false
-    }),
-    1
-  )
-})
-
-test('shallow checkout with no merge-base but identical SHA reports up-to-date', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '12104',
-      currentSha: 'abc',
-      targetSha: 'abc',
-      isShallow: true,
-      hasMergeBase: false
-    }),
-    0
-  )
-})
-
-test('shallow checkout WITH a merge-base keeps the exact count (reliable)', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '3',
-      currentSha: 'aaa',
-      targetSha: 'bbb',
-      isShallow: true,
-      hasMergeBase: true
-    }),
-    3
-  )
-})
-
-test('full (non-shallow) clone keeps the exact count path unchanged', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '7',
-      currentSha: 'aaa',
-      targetSha: 'bbb',
-      isShallow: false,
-      hasMergeBase: true
-    }),
-    7
-  )
-})
-
-test('up-to-date full clone reports 0', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '0',
-      currentSha: 'x',
-      targetSha: 'x',
-      isShallow: false,
-      hasMergeBase: true
-    }),
-    0
-  )
-})
-
-test('non-numeric count falls back to 0 (defensive, unchanged behaviour)', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '',
-      currentSha: 'aaa',
-      targetSha: 'bbb',
-      isShallow: false,
-      hasMergeBase: true
-    }),
-    0
-  )
-})
-
-// shouldCountCommits gates the expensive `rev-list --count` in checkUpdates().
-// FAIL-BEFORE: in the shallow + no-merge-base case the caller ran rev-list
-// unconditionally and discarded the bogus result; this predicate lets the
-// caller SKIP the whole-ancestry enumeration in exactly that case (#51922).
-test('shallow checkout with no merge-base SKIPS the rev-list count', () => {
-  assert.equal(shouldCountCommits({ isShallow: true, hasMergeBase: false }), false)
-})
-
-test('shallow checkout WITH a merge-base still runs the count', () => {
-  assert.equal(shouldCountCommits({ isShallow: true, hasMergeBase: true }), true)
-})
-
-test('full (non-shallow) clone always runs the count', () => {
-  assert.equal(shouldCountCommits({ isShallow: false, hasMergeBase: true }), true)
-  assert.equal(shouldCountCommits({ isShallow: false, hasMergeBase: false }), true)
-})
-
-// The skip path produces an empty countStr; resolveBehindCount must NOT trust
-// it and must fall through to the SHA compare (mirrors the live call site).
-test('skipped-count path resolves via SHA compare, never via empty countStr', () => {
-  assert.equal(
-    resolveBehindCount({
-      countStr: '',
-      currentSha: 'aaa',
-      targetSha: 'bbb',
-      isShallow: true,
-      hasMergeBase: false
-    }),
-    1
-  )
-  assert.equal(
-    resolveBehindCount({
-      countStr: '',
-      currentSha: 'same',
-      targetSha: 'same',
-      isShallow: true,
-      hasMergeBase: false
-    }),
-    0
-  )
-})

apps/desktop/electron/update-relaunch.test.cjs

@@ -62,10 +62,7 @@ test('resolveUnpackedRelease is null for AppImage / .deb / .rpm / dev / unresolv
   assert.equal(resolveUnpackedRelease('/usr/lib/hermes/hermes', ROOT, 'linux'), null)
   assert.equal(resolveUnpackedRelease('/opt/Hermes/hermes', ROOT, 'linux'), null)
   // dev electron
-  assert.equal(
-    resolveUnpackedRelease('/home/u/.hermes/hermes-agent/node_modules/electron/dist/electron', ROOT, 'linux'),
-    null
-  )
+  assert.equal(resolveUnpackedRelease('/home/u/.hermes/hermes-agent/node_modules/electron/dist/electron', ROOT, 'linux'), null)
   // empty / missing
   assert.equal(resolveUnpackedRelease('', ROOT, 'linux'), null)
   assert.equal(resolveUnpackedRelease(path.join(UNPACKED, 'hermes'), '', 'linux'), null)

apps/desktop/electron/update-remote.cjs

@@ -39,9 +39,7 @@ function canonicalGitHubRemote(url) {
 }
 
 function isSshRemote(url) {
-  const value = String(url || '')
-    .trim()
-    .toLowerCase()
+  const value = String(url || '').trim().toLowerCase()
   return value.startsWith('git@') || value.startsWith('ssh://')
 }
 

apps/desktop/electron/vscode-marketplace.cjs

@@ -26,11 +26,7 @@ const REQUEST_TIMEOUT_MS = 20_000
 const ID_RE = /^[\w-]+\.[\w-]+$/
 
 /** Minimal HTTPS helper with redirect-following, timeout, and a size cap. */
-function request(
-  url,
-  { method = 'GET', headers = {}, body = null, maxBytes = MAX_VSIX_BYTES } = {},
-  redirectsLeft = MAX_REDIRECTS
-) {
+function request(url, { method = 'GET', headers = {}, body = null, maxBytes = MAX_VSIX_BYTES } = {}, redirectsLeft = MAX_REDIRECTS) {
   return new Promise((resolve, reject) => {
     const req = https.request(url, { method, headers }, res => {
       const status = res.statusCode ?? 0
@@ -46,13 +42,7 @@ function request(
         const next = new URL(res.headers.location, url).toString()
         res.resume()
         // Redirects to the CDN are plain GETs (drop the POST body).
-        resolve(
-          request(
-            next,
-            { method: 'GET', headers: { 'User-Agent': headers['User-Agent'] }, maxBytes },
-            redirectsLeft - 1
-          )
-        )
+        resolve(request(next, { method: 'GET', headers: { 'User-Agent': headers['User-Agent'] }, maxBytes }, redirectsLeft - 1))
 
         return
       }

apps/desktop/electron/window-state.cjs

@@ -1,117 +0,0 @@
-/**
- * Pure geometry helpers for window-state.json — restoring the main window's
- * size, position, and maximized flag across launches. Side-effect-free so the
- * part that actually matters (rejecting garbage + off-screen bounds) is
- * unit-testable without booting Electron; main.cjs owns the file I/O and the
- * live `screen` displays.
- */
-
-// Defaults mirror the historical hardcoded BrowserWindow size; MIN_* mirror its
-// minWidth/minHeight so a restored size never undershoots what the live window
-// allows. A fresh install (no saved state) is byte-identical to before.
-const DEFAULT_WIDTH = 1220
-const DEFAULT_HEIGHT = 800
-const MIN_WIDTH = 400
-const MIN_HEIGHT = 620
-
-// Keep at least this much of the window over a display work area before we trust
-// a saved position, so the title bar stays grabbable after a monitor unplugs.
-const MIN_VISIBLE = 48
-
-const finite = v => typeof v === 'number' && Number.isFinite(v)
-const clamp = (v, lo, hi) => Math.max(lo, Math.min(v, hi))
-
-// Parse raw JSON → clean state, or null if garbage. width/height are required
-// and floored; x/y survive only as a finite pair; isMaximized is strict.
-function sanitizeWindowState(raw) {
-  if (!raw || typeof raw !== 'object' || !finite(raw.width) || !finite(raw.height)) return null
-
-  const state = {
-    width: Math.max(MIN_WIDTH, Math.round(raw.width)),
-    height: Math.max(MIN_HEIGHT, Math.round(raw.height)),
-    isMaximized: raw.isMaximized === true
-  }
-  if (finite(raw.x) && finite(raw.y)) {
-    state.x = Math.round(raw.x)
-    state.y = Math.round(raw.y)
-  }
-  return state
-}
-
-// True when `bounds` overlaps some display's work area by ≥ MIN_VISIBLE on both
-// axes. `displays` is Electron's screen.getAllDisplays() shape.
-function onScreen(bounds, displays) {
-  if (!Array.isArray(displays)) return false
-  return displays.some(({ workArea: a } = {}) => {
-    if (!a) return false
-    const x = Math.min(bounds.x + bounds.width, a.x + a.width) - Math.max(bounds.x, a.x)
-    const y = Math.min(bounds.y + bounds.height, a.y + a.height) - Math.max(bounds.y, a.y)
-    return x >= MIN_VISIBLE && y >= MIN_VISIBLE
-  })
-}
-
-// Sanitized state (or null) → BrowserWindow size/position options. Always sets
-// width/height, capped to the largest current display so a size saved on a
-// since-disconnected bigger monitor can't exceed any screen the user now has.
-// Sets x/y only when still on-screen; otherwise Electron centers the window.
-function computeWindowOptions(state, displays) {
-  const opts = {
-    width: finite(state?.width) ? state.width : DEFAULT_WIDTH,
-    height: finite(state?.height) ? state.height : DEFAULT_HEIGHT
-  }
-
-  const cap = (Array.isArray(displays) ? displays : []).reduce(
-    (m, { workArea: a } = {}) =>
-      a && finite(a.width) && finite(a.height)
-        ? { width: Math.max(m.width, a.width), height: Math.max(m.height, a.height) }
-        : m,
-    { width: 0, height: 0 }
-  )
-  if (cap.width && cap.height) {
-    opts.width = clamp(opts.width, MIN_WIDTH, cap.width)
-    opts.height = clamp(opts.height, MIN_HEIGHT, cap.height)
-  }
-
-  if (
-    state &&
-    finite(state.x) &&
-    finite(state.y) &&
-    onScreen({ x: state.x, y: state.y, width: opts.width, height: opts.height }, displays)
-  ) {
-    opts.x = state.x
-    opts.y = state.y
-  }
-  return opts
-}
-
-// Trailing debounce: collapse a burst of resize/move events (Linux fires many
-// mid-drag) into a single run `delayMs` after the last. `.flush()` runs now and
-// cancels the pending timer — used on close, before the window is gone.
-function debounce(fn, delayMs) {
-  let timer = null
-  const debounced = () => {
-    clearTimeout(timer)
-    timer = setTimeout(() => {
-      timer = null
-      fn()
-    }, delayMs)
-  }
-  debounced.flush = () => {
-    clearTimeout(timer)
-    timer = null
-    fn()
-  }
-  return debounced
-}
-
-module.exports = {
-  DEFAULT_WIDTH,
-  DEFAULT_HEIGHT,
-  MIN_WIDTH,
-  MIN_HEIGHT,
-  MIN_VISIBLE,
-  sanitizeWindowState,
-  onScreen,
-  computeWindowOptions,
-  debounce
-}

apps/desktop/electron/window-state.test.cjs

@@ -1,150 +0,0 @@
-/**
- * Unit tests for the pure window-state geometry helpers. These cover the logic
- * that protects the user: garbage rejection, off-screen fallback, oversized
- * clamping, and the debounce that collapses mid-drag write storms.
- */
-
-const test = require('node:test')
-const assert = require('node:assert/strict')
-
-const {
-  DEFAULT_WIDTH,
-  DEFAULT_HEIGHT,
-  MIN_WIDTH,
-  MIN_HEIGHT,
-  sanitizeWindowState,
-  onScreen,
-  computeWindowOptions,
-  debounce
-} = require('./window-state.cjs')
-
-// A single 1920×1080 monitor (work area trimmed for the taskbar).
-const PRIMARY = [{ workArea: { x: 0, y: 0, width: 1920, height: 1040 } }]
-// A laptop panel left behind after a bigger external monitor is unplugged.
-const LAPTOP = [{ workArea: { x: 0, y: 0, width: 1366, height: 728 } }]
-
-// ─── sanitizeWindowState ───────────────────────────────────────────────────
-
-test('sanitizeWindowState rejects missing/garbage input', () => {
-  for (const bad of [
-    null,
-    undefined,
-    'nope',
-    42,
-    {},
-    { width: 'x', height: 800 },
-    { width: NaN, height: 800 },
-    { width: 1000 }
-  ]) {
-    assert.equal(sanitizeWindowState(bad), null)
-  }
-})
-
-test('sanitizeWindowState keeps a valid full state and rounds HiDPI fractions', () => {
-  assert.deepEqual(sanitizeWindowState({ x: 100.6, y: 50.2, width: 1400.4, height: 900.7, isMaximized: true }), {
-    x: 101,
-    y: 50,
-    width: 1400,
-    height: 901,
-    isMaximized: true
-  })
-})
-
-test('sanitizeWindowState floors size to the minimums', () => {
-  const state = sanitizeWindowState({ width: 10, height: 10 })
-  assert.equal(state.width, MIN_WIDTH)
-  assert.equal(state.height, MIN_HEIGHT)
-})
-
-test('sanitizeWindowState drops a partial position but keeps the size', () => {
-  assert.deepEqual(sanitizeWindowState({ x: 100, width: 1400, height: 900 }), {
-    width: 1400,
-    height: 900,
-    isMaximized: false
-  })
-})
-
-test('sanitizeWindowState treats isMaximized strictly', () => {
-  assert.equal(sanitizeWindowState({ width: 1400, height: 900, isMaximized: 'yes' }).isMaximized, false)
-})
-
-// ─── onScreen ──────────────────────────────────────────────────────────────
-
-test('onScreen accepts a window on the primary or a secondary display', () => {
-  const dual = [...PRIMARY, { workArea: { x: 1920, y: 0, width: 2560, height: 1400 } }]
-  assert.equal(onScreen({ x: 100, y: 100, width: 1220, height: 800 }, PRIMARY), true)
-  assert.equal(onScreen({ x: 2200, y: 200, width: 1220, height: 800 }, dual), true)
-})
-
-test('onScreen rejects off-screen, slivers, and bad input', () => {
-  assert.equal(onScreen({ x: 3000, y: 100, width: 1220, height: 800 }, PRIMARY), false) // past right edge
-  assert.equal(onScreen({ x: 100, y: -900, width: 1220, height: 800 }, PRIMARY), false) // above top
-  assert.equal(onScreen({ x: 1910, y: 100, width: 1220, height: 800 }, PRIMARY), false) // ~10px sliver
-  assert.equal(onScreen({ x: 0, y: 0, width: 1220, height: 800 }, []), false)
-  assert.equal(onScreen({ x: 0, y: 0, width: 1220, height: 800 }, null), false)
-})
-
-// ─── computeWindowOptions ──────────────────────────────────────────────────
-
-test('computeWindowOptions falls back to defaults with no saved state', () => {
-  assert.deepEqual(computeWindowOptions(null, PRIMARY), { width: DEFAULT_WIDTH, height: DEFAULT_HEIGHT })
-})
-
-test('computeWindowOptions restores an on-screen position', () => {
-  const saved = sanitizeWindowState({ x: 200, y: 150, width: 1400, height: 900 })
-  assert.deepEqual(computeWindowOptions(saved, PRIMARY), { width: 1400, height: 900, x: 200, y: 150 })
-})
-
-test('computeWindowOptions keeps the size but drops an off-screen position', () => {
-  const saved = sanitizeWindowState({ x: 5000, y: 150, width: 1400, height: 900 })
-  assert.deepEqual(computeWindowOptions(saved, PRIMARY), { width: 1400, height: 900 })
-})
-
-test('computeWindowOptions clamps a size larger than the only display', () => {
-  const saved = sanitizeWindowState({ width: 2560, height: 1440 })
-  assert.deepEqual(computeWindowOptions(saved, LAPTOP), { width: 1366, height: 728 })
-})
-
-test('computeWindowOptions keeps the MIN floor on a sub-minimum display', () => {
-  const tiny = [{ workArea: { x: 0, y: 0, width: 360, height: 480 } }]
-  const saved = sanitizeWindowState({ width: 2000, height: 1500 })
-  assert.deepEqual(computeWindowOptions(saved, tiny), { width: MIN_WIDTH, height: MIN_HEIGHT })
-})
-
-test('computeWindowOptions does not clamp when displays are unknown', () => {
-  const saved = sanitizeWindowState({ width: 2560, height: 1440 })
-  assert.deepEqual(computeWindowOptions(saved, []), { width: 2560, height: 1440 })
-})
-
-// ─── debounce ──────────────────────────────────────────────────────────────
-
-test('debounce coalesces a burst into one trailing run', t => {
-  t.mock.timers.enable({ apis: ['setTimeout'] })
-  let calls = 0
-  const d = debounce(() => {
-    calls += 1
-  }, 250)
-
-  d()
-  d()
-  d()
-  assert.equal(calls, 0)
-  t.mock.timers.tick(249)
-  assert.equal(calls, 0)
-  t.mock.timers.tick(1)
-  assert.equal(calls, 1)
-})
-
-test('debounce.flush runs now and cancels the pending timer', t => {
-  t.mock.timers.enable({ apis: ['setTimeout'] })
-  let calls = 0
-  const d = debounce(() => {
-    calls += 1
-  }, 250)
-
-  d()
-  d.flush()
-  assert.equal(calls, 1)
-  t.mock.timers.tick(1000)
-  assert.equal(calls, 1)
-})

apps/desktop/electron/windows-child-process.test.cjs

@@ -12,8 +12,7 @@ function readElectronFile(name) {
 }
 
 function requireHiddenChildOptions(source, needle) {
-  const match = needle instanceof RegExp ? needle.exec(source) : null
-  const index = needle instanceof RegExp ? (match?.index ?? -1) : source.indexOf(needle)
+  const index = source.indexOf(needle)
   assert.notEqual(index, -1, `missing call site: ${needle}`)
   const snippet = source.slice(index, index + 700)
   assert.match(
@@ -29,28 +28,14 @@ test('desktop background child processes opt into hidden Windows consoles', () =
   assert.match(source, /function hiddenWindowsChildOptions\(options = \{\}\)/)
 
   requireHiddenChildOptions(source, "execFileSync(\n          'reg'")
-  requireHiddenChildOptions(source, /execFileSync\(\s*pyExe/)
-  requireHiddenChildOptions(source, /spawn\(\s*resolveGitBinary\(\)/)
+  requireHiddenChildOptions(source, 'execFileSync(pyExe')
+  requireHiddenChildOptions(source, 'spawn(resolveGitBinary()')
   requireHiddenChildOptions(source, "execFileSync('taskkill'")
-  requireHiddenChildOptions(source, /spawn\(\s*command,\s*args/)
+  requireHiddenChildOptions(source, 'spawn(command, args')
   requireHiddenChildOptions(source, "spawn('curl'")
-  requireHiddenChildOptions(source, /spawn\(\s*backend\.command,\s*backend\.args/)
-  requireHiddenChildOptions(source, /hermesProcess = spawn\(\s*backend\.command,\s*backend\.args/)
-  requireHiddenChildOptions(source, /spawn\(\s*py,\s*\['-m', 'hermes_cli\.main', 'uninstall', '--gui-summary'\]/)
-
-  assert.match(source, /function unwrapWindowsVenvHermesCommand\(command, dashboardArgs\)/)
-  assert.match(source, /existing Hermes no-console Python at/)
-  assert.match(source, /function getNoConsoleVenvPython\(venvRoot\)/)
-  assert.match(source, /function toNoConsolePython\(pythonPath\)/)
-  assert.match(source, /function applyWindowsNoConsoleSpawnHints\(backend\)/)
-  assert.match(source, /function readVenvHome\(venvRoot\)/)
-  assert.match(source, /path\.join\(venvRoot, 'Scripts', 'pythonw\.exe'\)/)
-  assert.match(source, /backendStartFailure/)
-  assert.match(source, /HERMES_DESKTOP_READY_FILE/)
-  assert.match(source, /readyFile: true/)
-  assert.match(source, /function getVenvSitePackagesEntries\(venvRoot\)/)
-  assert.match(source, /path\.join\(venvRoot, 'Lib', 'site-packages'\)/)
-  assert.match(source, /args: \['-m', 'hermes_cli\.main', \.\.\.dashboardArgs\]/)
+  requireHiddenChildOptions(source, 'spawn(backend.command, backend.args')
+  requireHiddenChildOptions(source, 'hermesProcess = spawn(backend.command, backend.args')
+  requireHiddenChildOptions(source, "spawn(py, ['-m', 'hermes_cli.main', 'uninstall', '--gui-summary']")
 })
 
 test('intentional or interactive desktop child processes stay documented', () => {

apps/desktop/electron/windows-user-env.cjs

@@ -21,7 +21,8 @@ const { execFileSync } = require('node:child_process')
 // the requested value line isn't present.
 function parseRegQueryValue(stdout, name) {
   if (!stdout || !name) return null
-  const typePattern = /^(\S+)\s+(?:REG_SZ|REG_EXPAND_SZ|REG_MULTI_SZ|REG_DWORD|REG_QWORD|REG_BINARY|REG_NONE)\s+(.*)$/
+  const typePattern =
+    /^(\S+)\s+(?:REG_SZ|REG_EXPAND_SZ|REG_MULTI_SZ|REG_DWORD|REG_QWORD|REG_BINARY|REG_NONE)\s+(.*)$/
   for (const rawLine of String(stdout).split(/\r?\n/)) {
     const line = rawLine.trim()
     const match = line.match(typePattern)
@@ -46,7 +47,10 @@ function expandWindowsEnvRefs(value, env = process.env) {
 // Read a User-scoped env var from HKCU\Environment. Windows-only: returns null
 // off-Windows (without spawning), on any spawn error, when `reg` exits non-zero
 // (the value doesn't exist), or when the value is empty.
-function readWindowsUserEnvVar(name, { platform = process.platform, env = process.env, exec = execFileSync } = {}) {
+function readWindowsUserEnvVar(
+  name,
+  { platform = process.platform, env = process.env, exec = execFileSync } = {}
+) {
   if (platform !== 'win32' || !name) return null
   let stdout
   try {

apps/desktop/electron/windows-user-env.test.cjs

@@ -1,12 +1,21 @@
 const assert = require('node:assert/strict')
 const { test } = require('node:test')
 
-const { expandWindowsEnvRefs, parseRegQueryValue, readWindowsUserEnvVar } = require('./windows-user-env.cjs')
+const {
+  expandWindowsEnvRefs,
+  parseRegQueryValue,
+  readWindowsUserEnvVar
+} = require('./windows-user-env.cjs')
 
 // ── parseRegQueryValue ─────────────────────────────────────────────────────
 
 test('parseRegQueryValue extracts a REG_SZ value', () => {
-  const out = ['', 'HKEY_CURRENT_USER\\Environment', '    HERMES_HOME    REG_SZ    F:\\Hermes\\data', ''].join('\r\n')
+  const out = [
+    '',
+    'HKEY_CURRENT_USER\\Environment',
+    '    HERMES_HOME    REG_SZ    F:\\Hermes\\data',
+    ''
+  ].join('\r\n')
   assert.equal(parseRegQueryValue(out, 'HERMES_HOME'), 'F:\\Hermes\\data')
 })
 
@@ -30,7 +39,10 @@ test('parseRegQueryValue returns null when the value line is absent', () => {
 // ── expandWindowsEnvRefs ───────────────────────────────────────────────────
 
 test('expandWindowsEnvRefs expands %VAR% case-insensitively', () => {
-  assert.equal(expandWindowsEnvRefs('%UserProfile%\\h', { USERPROFILE: 'C:\\Users\\jeff' }), 'C:\\Users\\jeff\\h')
+  assert.equal(
+    expandWindowsEnvRefs('%UserProfile%\\h', { USERPROFILE: 'C:\\Users\\jeff' }),
+    'C:\\Users\\jeff\\h'
+  )
 })
 
 test('expandWindowsEnvRefs leaves literal paths and unknown refs intact', () => {

apps/desktop/electron/workspace-cwd.cjs

@@ -14,7 +14,11 @@ function isPackagedInstallPath(dir, { installRoots, isPackaged }) {
     return false
   }
 
-  const roots = new Set((installRoots ?? []).filter(Boolean).map(candidate => path.resolve(String(candidate))))
+  const roots = new Set(
+    (installRoots ?? [])
+      .filter(Boolean)
+      .map(candidate => path.resolve(String(candidate)))
+  )
 
   for (const root of roots) {
     if (resolved === root) {

apps/desktop/electron/workspace-cwd.test.cjs

@@ -13,21 +13,33 @@ const { isPackagedInstallPath } = require('./workspace-cwd.cjs')
 const installRoot = path.resolve('/opt/Hermes')
 
 test('isPackagedInstallPath returns false when not packaged', () => {
-  assert.equal(isPackagedInstallPath(installRoot, { isPackaged: false, installRoots: [installRoot] }), false)
+  assert.equal(
+    isPackagedInstallPath(installRoot, { isPackaged: false, installRoots: [installRoot] }),
+    false
+  )
 })
 
 test('isPackagedInstallPath flags the install root itself', () => {
-  assert.equal(isPackagedInstallPath(installRoot, { isPackaged: true, installRoots: [installRoot] }), true)
+  assert.equal(
+    isPackagedInstallPath(installRoot, { isPackaged: true, installRoots: [installRoot] }),
+    true
+  )
 })
 
 test('isPackagedInstallPath flags paths nested under the install root', () => {
   const nested = path.join(installRoot, 'resources', 'app.asar')
 
-  assert.equal(isPackagedInstallPath(nested, { isPackaged: true, installRoots: [installRoot] }), true)
+  assert.equal(
+    isPackagedInstallPath(nested, { isPackaged: true, installRoots: [installRoot] }),
+    true
+  )
 })
 
 test('isPackagedInstallPath ignores paths outside the install root', () => {
   const homeProject = path.resolve('/home/user/projects/demo')
 
-  assert.equal(isPackagedInstallPath(homeProject, { isPackaged: true, installRoots: [installRoot] }), false)
+  assert.equal(
+    isPackagedInstallPath(homeProject, { isPackaged: true, installRoots: [installRoot] }),
+    false
+  )
 })

apps/desktop/electron/wsl-clipboard-image.cjs

@@ -1,92 +0,0 @@
-// Pull a Windows-host clipboard image from inside WSL2 via PowerShell (WSLg
-// bridges text but not images). Returns PNG bytes or null; exec injectable.
-
-const { execFileSync } = require('node:child_process')
-
-// STA is mandatory: System.Windows.Forms.Clipboard throws ThreadStateException
-// off a single-threaded apartment. We emit base64 (not raw bytes) so the PNG
-// survives stdout's text decoding intact, and write with [Console]::Out.Write
-// to avoid a trailing newline.
-const PS_SCRIPT = [
-  'Add-Type -AssemblyName System.Windows.Forms,System.Drawing',
-  '$img = [System.Windows.Forms.Clipboard]::GetImage()',
-  'if ($null -eq $img) { exit 0 }',
-  '$ms = New-Object System.IO.MemoryStream',
-  '$img.Save($ms, [System.Drawing.Imaging.ImageFormat]::Png)',
-  '[Console]::Out.Write([System.Convert]::ToBase64String($ms.ToArray()))'
-].join('\n')
-
-// PowerShell's -EncodedCommand takes UTF-16LE base64. Encoding the whole script
-// this way sidesteps every layer of WSL→Windows quoting (spaces, quotes,
-// brackets, newlines) that plain -Command arguments would mangle.
-function encodePowerShellCommand(script) {
-  return Buffer.from(String(script), 'utf16le').toString('base64')
-}
-
-// Locate powershell.exe. The bare name resolves through WSL's Windows-interop
-// PATH on every standard WSL2 setup; the absolute fallback covers a stripped
-// PATH. Returns the first candidate — execFile surfaces ENOENT if it's wrong
-// and we fall back to null.
-function powershellCandidates() {
-  return ['powershell.exe', '/mnt/c/Windows/System32/WindowsPowerShell/v1.0/powershell.exe']
-}
-
-function decodeClipboardImageBase64(stdout) {
-  const b64 = String(stdout || '').trim()
-  if (!b64) return null
-
-  let buffer
-  try {
-    buffer = Buffer.from(b64, 'base64')
-  } catch {
-    return null
-  }
-
-  // Guard against partial / garbage output: require a real PNG signature.
-  const PNG_SIGNATURE = Buffer.from([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a])
-  if (buffer.length < PNG_SIGNATURE.length || !buffer.subarray(0, PNG_SIGNATURE.length).equals(PNG_SIGNATURE)) {
-    return null
-  }
-
-  return buffer
-}
-
-// Read the Windows clipboard image from inside WSL. Returns a PNG Buffer, or
-// null when there's no image, PowerShell is unreachable, or output is invalid.
-// Linux-only by contract (caller gates on IS_WSL); never throws.
-function readWslWindowsClipboardImage({ exec = execFileSync, candidates = powershellCandidates() } = {}) {
-  const encoded = encodePowerShellCommand(PS_SCRIPT)
-
-  for (const ps of candidates) {
-    try {
-      const stdout = exec(
-        ps,
-        ['-NoProfile', '-NonInteractive', '-STA', '-ExecutionPolicy', 'Bypass', '-EncodedCommand', encoded],
-        {
-          encoding: 'utf8',
-          windowsHide: true,
-          timeout: 8000,
-          // A 4K screenshot base64s to a few MB; give stdout generous headroom.
-          maxBuffer: 64 * 1024 * 1024,
-          // PowerShell writes progress/CLIXML noise to stderr — ignore it.
-          stdio: ['ignore', 'pipe', 'ignore']
-        }
-      )
-      const decoded = decodeClipboardImageBase64(stdout)
-      if (decoded) return decoded
-      // Empty stdout = no image on the clipboard; stop, don't try fallbacks.
-      if (String(stdout || '').trim() === '') return null
-    } catch {
-      // This powershell.exe candidate is missing/failed — try the next one.
-    }
-  }
-
-  return null
-}
-
-module.exports = {
-  decodeClipboardImageBase64,
-  encodePowerShellCommand,
-  powershellCandidates,
-  readWslWindowsClipboardImage
-}

apps/desktop/electron/wsl-clipboard-image.test.cjs

@@ -1,114 +0,0 @@
-const assert = require('node:assert/strict')
-const test = require('node:test')
-
-const {
-  decodeClipboardImageBase64,
-  encodePowerShellCommand,
-  powershellCandidates,
-  readWslWindowsClipboardImage
-} = require('./wsl-clipboard-image.cjs')
-
-const PNG_SIGNATURE = Buffer.from([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a])
-
-function fakePngBuffer(extraBytes = 16) {
-  return Buffer.concat([PNG_SIGNATURE, Buffer.alloc(extraBytes, 0x42)])
-}
-
-test('encodePowerShellCommand produces UTF-16LE base64 PowerShell can decode', () => {
-  const encoded = encodePowerShellCommand('Write-Output "hi"')
-  const roundTripped = Buffer.from(encoded, 'base64').toString('utf16le')
-  assert.equal(roundTripped, 'Write-Output "hi"')
-})
-
-test('decodeClipboardImageBase64 returns a Buffer for valid PNG base64', () => {
-  const png = fakePngBuffer()
-  const decoded = decodeClipboardImageBase64(png.toString('base64'))
-  assert.ok(Buffer.isBuffer(decoded))
-  assert.ok(decoded.equals(png))
-})
-
-test('decodeClipboardImageBase64 trims surrounding whitespace before decoding', () => {
-  const png = fakePngBuffer()
-  const decoded = decodeClipboardImageBase64(`\n  ${png.toString('base64')}  \r\n`)
-  assert.ok(decoded && decoded.equals(png))
-})
-
-test('decodeClipboardImageBase64 returns null for empty / whitespace input', () => {
-  assert.equal(decodeClipboardImageBase64(''), null)
-  assert.equal(decodeClipboardImageBase64('   \n  '), null)
-  assert.equal(decodeClipboardImageBase64(null), null)
-  assert.equal(decodeClipboardImageBase64(undefined), null)
-})
-
-test('decodeClipboardImageBase64 rejects base64 without a PNG signature', () => {
-  // Valid base64, but the decoded bytes are not a PNG.
-  const notPng = Buffer.from('this is not a png at all').toString('base64')
-  assert.equal(decodeClipboardImageBase64(notPng), null)
-})
-
-test('readWslWindowsClipboardImage decodes the first candidate that returns a PNG', () => {
-  const png = fakePngBuffer()
-  const calls = []
-  const exec = (cmd, args) => {
-    calls.push({ cmd, args })
-    return png.toString('base64')
-  }
-
-  const result = readWslWindowsClipboardImage({ exec, candidates: ['powershell.exe'] })
-  assert.ok(result && result.equals(png))
-  assert.equal(calls.length, 1)
-  assert.equal(calls[0].cmd, 'powershell.exe')
-  // -STA is mandatory for System.Windows.Forms.Clipboard.
-  assert.ok(calls[0].args.includes('-STA'))
-  assert.ok(calls[0].args.includes('-EncodedCommand'))
-})
-
-test('readWslWindowsClipboardImage returns null and stops when stdout is empty (no image)', () => {
-  let count = 0
-  const exec = () => {
-    count += 1
-    return ''
-  }
-
-  const result = readWslWindowsClipboardImage({
-    exec,
-    candidates: ['powershell.exe', '/mnt/c/Windows/System32/WindowsPowerShell/v1.0/powershell.exe']
-  })
-  assert.equal(result, null)
-  // Empty stdout means "no image on the clipboard" — don't probe further candidates.
-  assert.equal(count, 1)
-})
-
-test('readWslWindowsClipboardImage falls through to the next candidate when one throws', () => {
-  const png = fakePngBuffer()
-  const seen = []
-  const exec = cmd => {
-    seen.push(cmd)
-    if (cmd === 'powershell.exe') {
-      throw Object.assign(new Error('not found'), { code: 'ENOENT' })
-    }
-    return png.toString('base64')
-  }
-
-  const result = readWslWindowsClipboardImage({
-    exec,
-    candidates: ['powershell.exe', '/mnt/c/Windows/System32/WindowsPowerShell/v1.0/powershell.exe']
-  })
-  assert.ok(result && result.equals(png))
-  assert.deepEqual(seen, ['powershell.exe', '/mnt/c/Windows/System32/WindowsPowerShell/v1.0/powershell.exe'])
-})
-
-test('readWslWindowsClipboardImage returns null when every candidate throws', () => {
-  const exec = () => {
-    throw new Error('boom')
-  }
-
-  const result = readWslWindowsClipboardImage({ exec, candidates: ['a', 'b'] })
-  assert.equal(result, null)
-})
-
-test('powershellCandidates lists the bare name first, then the absolute fallback', () => {
-  const candidates = powershellCandidates()
-  assert.equal(candidates[0], 'powershell.exe')
-  assert.ok(candidates.some(c => c.endsWith('WindowsPowerShell/v1.0/powershell.exe')))
-})

apps/desktop/package.json

@@ -18,7 +18,7 @@
     "profile:main": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron --inspect=9229 .",
     "profile:main:cpu": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 NODE_OPTIONS=--cpu-prof HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron .",
     "start": "npm run build && electron .",
-    "build": "node scripts/assert-root-install.cjs && node scripts/write-build-stamp.cjs && node scripts/stage-native-deps.cjs && tsc -b && vite build &&  node scripts/bundle-electron-main.mjs && npm run postbuild",
+    "build": "node scripts/assert-root-install.cjs && node scripts/write-build-stamp.cjs && node scripts/stage-native-deps.cjs && tsc -b && vite build && npm run postbuild",
     "postbuild": "node scripts/assert-dist-built.cjs",
     "prebuilder": "node scripts/patch-electron-builder-mac-binary.cjs",
     "builder": "cross-env NODE_OPTIONS=--max-old-space-size=16384 node scripts/run-electron-builder.cjs",
@@ -37,7 +37,7 @@
     "test:desktop:nsis": "node scripts/test-desktop.mjs nsis",
     "test:desktop:existing": "node scripts/test-desktop.mjs existing",
     "test:desktop:fresh": "node scripts/test-desktop.mjs fresh",
-    "test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-env.test.cjs electron/backend-probes.test.cjs electron/backend-ready.test.cjs electron/bootstrap-runner.test.cjs electron/connection-config.test.cjs electron/dashboard-token.test.cjs electron/gateway-ws-probe.test.cjs electron/oauth-net-request.test.cjs electron/desktop-uninstall.test.cjs electron/session-windows.test.cjs electron/link-title-window.test.cjs electron/workspace-cwd.test.cjs electron/fs-read-dir.test.cjs electron/git-root.test.cjs electron/git-worktree-ops.test.cjs electron/windows-child-process.test.cjs electron/update-remote.test.cjs electron/update-count.test.cjs electron/update-rebuild.test.cjs electron/update-marker.test.cjs electron/update-relaunch.test.cjs electron/windows-user-env.test.cjs electron/wsl-clipboard-image.test.cjs electron/titlebar-overlay-width.test.cjs electron/window-state.test.cjs",
+    "test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-env.test.cjs electron/backend-probes.test.cjs electron/backend-ready.test.cjs electron/bootstrap-runner.test.cjs electron/connection-config.test.cjs electron/dashboard-token.test.cjs electron/gateway-ws-probe.test.cjs electron/oauth-net-request.test.cjs electron/desktop-uninstall.test.cjs electron/session-windows.test.cjs electron/link-title-window.test.cjs electron/workspace-cwd.test.cjs electron/fs-read-dir.test.cjs electron/git-root.test.cjs electron/windows-child-process.test.cjs electron/update-remote.test.cjs electron/update-rebuild.test.cjs electron/update-marker.test.cjs electron/update-relaunch.test.cjs electron/windows-user-env.test.cjs",
     "typecheck": "tsc -p . --noEmit",
     "lint": "eslint src/ electron/",
     "lint:fix": "eslint src/ electron/ --fix",
@@ -51,17 +51,11 @@
     "@assistant-ui/react-streamdown": "^0.1.11",
     "@audiowave/react": "^0.6.2",
     "@chenglou/pretext": "^0.0.6",
-    "@codemirror/commands": "^6.10.4",
-    "@codemirror/language": "^6.12.4",
-    "@codemirror/language-data": "^6.5.2",
-    "@codemirror/state": "^6.7.0",
-    "@codemirror/view": "^6.43.3",
     "@dnd-kit/core": "^6.3.1",
     "@dnd-kit/sortable": "^10.0.0",
     "@dnd-kit/utilities": "^3.2.2",
     "@hermes/shared": "file:../shared",
     "@icons-pack/react-simple-icons": "=13.11.1",
-    "@lezer/highlight": "^1.2.3",
     "@nanostores/react": "^1.1.0",
     "@nous-research/ui": "^0.13.0",
     "@radix-ui/react-slot": "^1.2.4",
@@ -99,7 +93,6 @@
     "remark-math": "^6.0.0",
     "remend": "^1.3.0",
     "shiki": "^4.0.2",
-    "simple-git": "^3.36.0",
     "streamdown": "^2.5.0",
     "tailwind-merge": "^3.5.0",
     "tailwindcss": "^4.2.4",

apps/desktop/scripts/bundle-electron-main.mjs

@@ -1,33 +0,0 @@
-#!/usr/bin/env node
-// bundle-electron-main.mjs — bundles electron/main.cjs into a single
-// self-contained file so the nix build doesn't need to ship node_modules/.
-//
-// `electron` is provided by the runtime; `node-pty` is staged separately
-// via stage-native-deps.cjs.  `preload.cjs` is NOT require()'d by main —
-// Electron loads it via path.join(__dirname, 'preload.cjs') — so it stays
-// as a separate file and doesn't need bundling.
-import { build } from 'esbuild'
-import { resolve, dirname } from 'node:path'
-import { fileURLToPath } from 'node:url'
-import { renameSync } from 'node:fs'
-
-const here = dirname(fileURLToPath(import.meta.url))
-const root = resolve(here, '..')
-const entry = resolve(root, 'electron/main.cjs')
-const tmp = resolve(root, 'electron/main.bundled.cjs')
-
-await build({
-  entryPoints: [entry],
-  bundle: true,
-  platform: 'node',
-  format: 'cjs',
-  target: 'node20',
-  outfile: tmp,
-  external: ['electron', 'node-pty'],
-  logLevel: 'info'
-})
-
-// Overwrite the original with the bundled version.
-renameSync(tmp, entry)
-
-console.log(`bundled ${entry}`)

apps/desktop/src/app/agents/index.tsx

@@ -3,16 +3,15 @@ import { type ReactNode, useEffect, useMemo, useState } from 'react'
 
 import { useElapsedSeconds } from '@/components/chat/activity-timer'
 import { ActivityTimerText } from '@/components/chat/activity-timer-text'
-import { Codicon } from '@/components/ui/codicon'
 import { FadeText } from '@/components/ui/fade-text'
 import { GlyphSpinner } from '@/components/ui/glyph-spinner'
 import { type Translations, useI18n } from '@/i18n'
-import { AlertCircle, CheckCircle2 } from '@/lib/icons'
+import { AlertCircle, CheckCircle2, Sparkles } from '@/lib/icons'
 import { useEnterAnimation } from '@/lib/use-enter-animation'
 import { cn } from '@/lib/utils'
+import { $activeSessionId } from '@/store/session'
 import {
   $subagentsBySession,
-  allSubagents,
   buildSubagentTree,
   type SubagentNode,
   type SubagentStatus,
@@ -78,12 +77,15 @@ interface AgentsViewProps {
 
 export function AgentsView({ onClose }: AgentsViewProps) {
   const { t } = useI18n()
+  const activeSessionId = useStore($activeSessionId)
   const subagentsBySession = useStore($subagentsBySession)
 
-  // Aggregate every session, matching the status-bar indicator — a subagent
-  // running in a background session must still be visible here, or the two
-  // desync ("Agents N running" vs an empty tree).
-  const tree = useMemo(() => buildSubagentTree(allSubagents(subagentsBySession)), [subagentsBySession])
+  const activeSubagents = useMemo(
+    () => (activeSessionId ? (subagentsBySession[activeSessionId] ?? []) : []),
+    [activeSessionId, subagentsBySession]
+  )
+
+  const tree = useMemo(() => buildSubagentTree(activeSubagents), [activeSubagents])
 
   return (
     <OverlayView
@@ -210,7 +212,7 @@ function SubagentTree({ tree }: { tree: SubagentNode[] }) {
   if (tree.length === 0) {
     return (
       <div className="grid place-items-center gap-3 py-12 text-center">
-        <Codicon className="text-muted-foreground/60" name="hubot" size="1.5rem" />
+        <Sparkles className="size-6 text-muted-foreground/60" />
         <p className="text-sm font-medium text-foreground/90">{t.agents.emptyTitle}</p>
         <p className="max-w-md text-xs leading-relaxed text-muted-foreground/75">{t.agents.emptyDesc}</p>
       </div>

apps/desktop/src/app/artifacts/index.tsx

@@ -477,20 +477,17 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
     }
   }, [artifacts])
 
-  const openArtifact = useCallback(
-    async (href: string) => {
-      try {
-        if (window.hermesDesktop?.openExternal) {
-          await window.hermesDesktop.openExternal(href)
-        } else {
-          window.open(href, '_blank', 'noopener,noreferrer')
-        }
-      } catch (err) {
-        notifyError(err, a.openFailed)
+  const openArtifact = useCallback(async (href: string) => {
+    try {
+      if (window.hermesDesktop?.openExternal) {
+        await window.hermesDesktop.openExternal(href)
+      } else {
+        window.open(href, '_blank', 'noopener,noreferrer')
       }
-    },
-    [a]
-  )
+    } catch (err) {
+      notifyError(err, a.openFailed)
+    }
+  }, [a])
 
   const markImageFailed = useCallback((id: string) => {
     setFailedImageIds(current => {
@@ -842,8 +839,7 @@ const ARTIFACT_COLUMNS: readonly ArtifactColumn[] = [
   {
     Cell: PrimaryCell,
     bodyClassName: 'p-0',
-    header: (filter, a) =>
-      filter === 'link' ? a.colTitleLink : filter === 'file' ? a.colTitleFile : a.colTitleDefault,
+    header: (filter, a) => (filter === 'link' ? a.colTitleLink : filter === 'file' ? a.colTitleFile : a.colTitleDefault),
     id: 'primary',
     width: filter => (filter === 'link' ? 'w-[50%]' : 'w-[35%]')
   },

apps/desktop/src/app/chat/composer/attachments.test.tsx

@@ -2,9 +2,9 @@ import { cleanup, render, screen } from '@testing-library/react'
 import { afterEach, describe, expect, it } from 'vitest'
 
 import { I18nProvider } from '@/i18n/context'
-import type { ComposerAttachment } from '@/store/composer'
 
 import { AttachmentList } from './attachments'
+import type { ComposerAttachment } from '@/store/composer'
 
 function makeAttachment(id: string, label = 'test.pdf'): ComposerAttachment {
   return { id, kind: 'file', label }
@@ -32,10 +32,7 @@ describe('AttachmentList', () => {
 
   it('renders empty list without error', () => {
     renderWithI18n(<AttachmentList attachments={[]} />)
-
-    const container =
-      screen.getByTestId?.('composer-attachments') ?? document.querySelector('[data-slot="composer-attachments"]')
-
+    const container = screen.getByTestId?.('composer-attachments') ?? document.querySelector('[data-slot="composer-attachments"]')
     expect(container).toBeDefined()
   })
 
@@ -58,7 +55,10 @@ describe('AttachmentList', () => {
   })
 
   it('does not crash when attachments array contains null entries', () => {
-    const attachments = [null as unknown as ComposerAttachment, makeAttachment('a', 'valid.txt')]
+    const attachments = [
+      null as unknown as ComposerAttachment,
+      makeAttachment('a', 'valid.txt')
+    ]
 
     expect(() => {
       renderWithI18n(<AttachmentList attachments={attachments} />)

apps/desktop/src/app/chat/composer/context-menu.tsx

@@ -73,11 +73,7 @@ export function ContextMenu({
           <ContextMenuItem disabled={!onPickImages} icon={ImageIcon} onSelect={onPickImages}>
             {c.images}
           </ContextMenuItem>
-          <ContextMenuItem
-            disabled={!onPasteClipboardImage}
-            icon={Clipboard}
-            onSelect={onPasteClipboardImage ? () => void onPasteClipboardImage() : undefined}
-          >
+          <ContextMenuItem disabled={!onPasteClipboardImage} icon={Clipboard} onSelect={onPasteClipboardImage}>
             {c.pasteImage}
           </ContextMenuItem>
           <ContextMenuItem icon={Link} onSelect={onOpenUrlDialog}>
@@ -171,7 +167,7 @@ interface ContextMenuItemProps {
 interface ContextMenuProps {
   onInsertText: (text: string) => void
   onOpenUrlDialog: () => void
-  onPasteClipboardImage?: (opts?: { silent?: boolean }) => Promise<boolean> | void
+  onPasteClipboardImage?: () => void
   onPickFiles?: () => void
   onPickFolders?: () => void
   onPickImages?: () => void

apps/desktop/src/app/chat/composer/enter-submit-dom-race.test.tsx

@@ -59,10 +59,8 @@ function Harness({
     }
 
     const editor = editorRef.current
-
     if (editor) {
       const domText = composerPlainText(editor)
-
       if (domText !== draftRef.current) {
         draftRef.current = domText
         setDraft(domText)
@@ -129,11 +127,9 @@ function Harness({
 describe('composer Enter submit — live DOM vs stale composer state (#39630)', () => {
   it('sends the just-typed text on Enter even when composer state has not synced', async () => {
     const onSubmit = vi.fn()
-
     const { getByTestId } = render(
       <Harness onCancel={vi.fn()} onDrain={vi.fn()} onQueue={vi.fn()} onSubmit={onSubmit} />
     )
-
     const editor = getByTestId('editor')
 
     // Fast typing: the DOM has the text but NO input event fired, so `draft`
@@ -150,11 +146,9 @@ describe('composer Enter submit — live DOM vs stale composer state (#39630)',
     const onQueue = vi.fn()
     const onDrain = vi.fn()
     const onCancel = vi.fn()
-
     const { getByTestId } = render(
       <Harness busy onCancel={onCancel} onDrain={onDrain} onQueue={onQueue} onSubmit={vi.fn()} queued={['queued-1']} />
     )
-
     const editor = getByTestId('editor')
 
     await act(async () => {
@@ -171,11 +165,9 @@ describe('composer Enter submit — live DOM vs stale composer state (#39630)',
     const onCancel = vi.fn()
     const onSubmit = vi.fn()
     const onQueue = vi.fn()
-
     const { getByTestId } = render(
       <Harness busy onCancel={onCancel} onDrain={vi.fn()} onQueue={onQueue} onSubmit={onSubmit} />
     )
-
     const editor = getByTestId('editor')
 
     await act(async () => {
@@ -191,11 +183,9 @@ describe('composer Enter submit — live DOM vs stale composer state (#39630)',
   it('drains the next queued prompt on Enter when idle with a truly empty editor', async () => {
     const onDrain = vi.fn()
     const onSubmit = vi.fn()
-
     const { getByTestId } = render(
       <Harness onCancel={vi.fn()} onDrain={onDrain} onQueue={vi.fn()} onSubmit={onSubmit} queued={['queued-1']} />
     )
-
     const editor = getByTestId('editor')
 
     await act(async () => {
@@ -210,18 +200,9 @@ describe('composer Enter submit — live DOM vs stale composer state (#39630)',
   it('keeps reconnect drafts editable but blocks Enter submit until the gateway returns', async () => {
     const onSubmit = vi.fn()
     const onDrain = vi.fn()
-
     const { getByTestId } = render(
-      <Harness
-        disabled
-        onCancel={vi.fn()}
-        onDrain={onDrain}
-        onQueue={vi.fn()}
-        onSubmit={onSubmit}
-        queued={['queued-1']}
-      />
+      <Harness disabled onCancel={vi.fn()} onDrain={onDrain} onQueue={vi.fn()} onSubmit={onSubmit} queued={['queued-1']} />
     )
-
     const editor = getByTestId('editor')
 
     await act(async () => {

apps/desktop/src/app/chat/composer/focus.ts

@@ -10,8 +10,8 @@
  * steal focus from the composer effect.
  */
 
-import type { InlineRefInput } from './inline-refs'
 import { RICH_INPUT_SLOT } from './rich-editor'
+import type { InlineRefInput } from './inline-refs'
 
 export type ComposerTarget = 'edit' | 'main'
 export type ComposerInsertMode = 'block' | 'inline'
@@ -34,13 +34,6 @@ interface InsertRefsDetail {
 const FOCUS_EVENT = 'hermes:composer-focus'
 const INSERT_EVENT = 'hermes:composer-insert'
 const INSERT_REFS_EVENT = 'hermes:composer-insert-refs'
-const SUBMIT_EVENT = 'hermes:composer-submit'
-const VOICE_TOGGLE_EVENT = 'hermes:composer-voice-toggle'
-
-interface SubmitDetail {
-  target: ComposerTarget
-  text: string
-}
 
 let activeTarget: ComposerTarget = 'main'
 
@@ -112,30 +105,6 @@ export const requestComposerInsertRefs = (
 export const onComposerInsertRefsRequest = (handler: (detail: InsertRefsDetail) => void) =>
   subscribe<InsertRefsDetail>(INSERT_REFS_EVENT, handler)
 
-/** Submit a prompt through a composer as if the user typed + sent it. Lets
- * external panels (e.g. the review pane's "let the agent ship it" button) hand
- * the agent a task without the user round-tripping through the input. */
-export const requestComposerSubmit = (
-  text: string,
-  { target = 'active' }: { target?: ComposerTarget | 'active' } = {}
-) => {
-  const trimmed = text.trim()
-
-  if (trimmed) {
-    dispatch<SubmitDetail>(SUBMIT_EVENT, { target: resolve(target), text: trimmed })
-  }
-}
-
-export const onComposerSubmitRequest = (handler: (detail: SubmitDetail) => void) =>
-  subscribe<SubmitDetail>(SUBMIT_EVENT, handler)
-
-/** Toggle the active composer's voice conversation — the `composer.voice`
- *  hotkey (Ctrl+B) reaching into the composer that owns the voice state. */
-export const requestVoiceToggle = () => dispatch<{ at: number }>(VOICE_TOGGLE_EVENT, { at: Date.now() })
-
-export const onComposerVoiceToggleRequest = (handler: () => void) =>
-  subscribe<{ at: number }>(VOICE_TOGGLE_EVENT, () => handler())
-
 /**
  * Focus a composer input across React commit + browser focus restore.
  *

apps/desktop/src/app/chat/composer/help-hint.tsx

@@ -33,7 +33,7 @@ export function HelpHint() {
 
       <Section title={c.hotkeys}>
         {COMPOSER_HOTKEY_ROWS.map(row => (
-          <HotkeyRow combos={[...row.combos]} description={c.hotkeyDescs[row.id] ?? ''} key={row.id} />
+          <HotkeyRow description={c.hotkeyDescs[row.id] ?? ''} combos={[...row.combos]} key={row.id} />
         ))}
       </Section>
 

apps/desktop/src/app/chat/composer/hooks/use-mic-recorder.ts

@@ -59,11 +59,7 @@ function micError(error: unknown, copy: MicRecorderErrorCopy): Error {
   return new Error(copy.microphoneStartFailed)
 }
 
-export function useMicRecorder(copy: MicRecorderErrorCopy): {
-  handle: MicRecorderHandle
-  level: number
-  recording: boolean
-} {
+export function useMicRecorder(copy: MicRecorderErrorCopy): { handle: MicRecorderHandle; level: number; recording: boolean } {
   const [level, setLevel] = useState(0)
   const [recording, setRecording] = useState(false)
 

apps/desktop/src/app/chat/composer/hooks/use-popout-drag.ts

@@ -1,12 +1,19 @@
-import { type PointerEvent as ReactPointerEvent, type RefObject, useCallback, useEffect, useRef, useState } from 'react'
+import {
+  type PointerEvent as ReactPointerEvent,
+  type RefObject,
+  useCallback,
+  useEffect,
+  useRef,
+  useState
+} from 'react'
 
 import {
   POPOUT_ESTIMATED_HEIGHT,
   POPOUT_WIDTH_REM,
-  type PopoutPosition,
-  type PopoutSize,
   readPopoutBounds,
-  setComposerPopoutPosition
+  setComposerPopoutPosition,
+  type PopoutPosition,
+  type PopoutSize
 } from '@/store/composer-popout'
 
 // Floating surface long-press before it becomes draggable (the 5px platform drags
@@ -73,7 +80,6 @@ function dockProximityOf(rect: DOMRect) {
   const verticalGap = window.innerHeight - DOCK_ZONE_BOTTOM_PX - rect.bottom
 
   const v = verticalGap <= 0 ? 1 : Math.max(0, 1 - verticalGap / DOCK_VERTICAL_FALLOFF_PX)
-
   const h =
     horizontalDist <= DOCK_ZONE_CENTER_TOLERANCE_PX
       ? 1

apps/desktop/src/app/chat/composer/hooks/use-slash-completions.ts

@@ -98,14 +98,12 @@ export function useSlashCompletions(options: {
 
         const matches = (
           needle
-            ? $sessions
-                .get()
-                .filter(
-                  session =>
-                    sessionTitle(session).toLowerCase().includes(needle) ||
-                    (session.preview ?? '').toLowerCase().includes(needle) ||
-                    session.id.toLowerCase().includes(needle)
-                )
+            ? $sessions.get().filter(
+                session =>
+                  sessionTitle(session).toLowerCase().includes(needle) ||
+                  (session.preview ?? '').toLowerCase().includes(needle) ||
+                  session.id.toLowerCase().includes(needle)
+              )
             : $sessions.get()
         ).slice(0, SESSION_INLINE_LIMIT)
 
@@ -137,7 +135,9 @@ export function useSlashCompletions(options: {
           // Prefer the categorized layout so the popover renders section headers
           // (Session, Tools & Skills, ...). Fall back to the flat list when the
           // backend didn't categorize.
-          const sections = catalog.categories?.length ? catalog.categories : [{ name: '', pairs: catalog.pairs ?? [] }]
+          const sections = catalog.categories?.length
+            ? catalog.categories
+            : [{ name: '', pairs: catalog.pairs ?? [] }]
 
           const items = sections.flatMap(section =>
             section.pairs.map(([command, meta]) => ({
@@ -151,9 +151,10 @@ export function useSlashCompletions(options: {
           return { items, query }
         }
 
-        const result = await gateway.request<{ items?: CompletionEntry[]; replace_from?: number }>('complete.slash', {
-          text
-        })
+        const result = await gateway.request<{ items?: CompletionEntry[]; replace_from?: number }>(
+          'complete.slash',
+          { text }
+        )
 
         // Arg-completion items (replace_from > 1) carry just the arg stub —
         // e.g. complete.slash returns `{text: "alice"}` for `/personality alic`

apps/desktop/src/app/chat/composer/hooks/use-voice-conversation.ts

@@ -220,25 +220,22 @@ export function useVoiceConversation({
     }
   }, [handle, handleTurn, onFatalError, voiceCopy.couldNotStartSession, voiceCopy.microphoneFailed])
 
-  const speak = useCallback(
-    async (text: string) => {
-      setStatus('speaking')
+  const speak = useCallback(async (text: string) => {
+    setStatus('speaking')
 
-      try {
-        await playSpeechText(text, { source: 'voice-conversation' })
-      } catch (error) {
-        notifyError(error, voiceCopy.playbackFailed)
-      } finally {
-        if (enabledRef.current) {
-          pendingStartRef.current = true
-          setStatus('idle')
-        } else {
-          setStatus('idle')
-        }
+    try {
+      await playSpeechText(text, { source: 'voice-conversation' })
+    } catch (error) {
+      notifyError(error, voiceCopy.playbackFailed)
+    } finally {
+      if (enabledRef.current) {
+        pendingStartRef.current = true
+        setStatus('idle')
+      } else {
+        setStatus('idle')
       }
-    },
-    [voiceCopy.playbackFailed]
-  )
+    }
+  }, [voiceCopy.playbackFailed])
 
   const start = useCallback(async () => {
     if (!onTranscribeAudio) {
@@ -258,14 +255,7 @@ export function useVoiceConversation({
     consumePendingResponse()
     pendingStartRef.current = true
     await startListening()
-  }, [
-    consumePendingResponse,
-    onFatalError,
-    onTranscribeAudio,
-    startListening,
-    voiceCopy.configureSpeechToText,
-    voiceCopy.unavailable
-  ])
+  }, [consumePendingResponse, onFatalError, onTranscribeAudio, startListening, voiceCopy.configureSpeechToText, voiceCopy.unavailable])
 
   const end = useCallback(async () => {
     pendingStartRef.current = false

apps/desktop/src/app/chat/composer/index.tsx

@@ -45,8 +45,8 @@ import {
   $composerPoppedOut,
   POPOUT_WIDTH_REM,
   readPopoutBounds,
-  setComposerPopoutPosition,
-  setComposerPoppedOut
+  setComposerPoppedOut,
+  setComposerPopoutPosition
 } from '@/store/composer-popout'
 import {
   $queuedPromptsBySession,
@@ -60,10 +60,8 @@ import {
   updateQueuedPrompt
 } from '@/store/composer-queue'
 import { $statusItemsBySession } from '@/store/composer-status'
-import { notify } from '@/store/notifications'
 import { $previewStatusBySession } from '@/store/preview-status'
-import { listRepoBranches, requestStartWorkSession, startWorkInRepo, switchBranchInRepo } from '@/store/projects'
-import { toggleReview } from '@/store/review'
+import { notify } from '@/store/notifications'
 import { $gatewayState, $messages, setSessionPickerOpen } from '@/store/session'
 import { $threadScrolledUp } from '@/store/thread-scroll'
 import { isSecondaryWindow } from '@/store/windows'
@@ -81,9 +79,7 @@ import {
   markActiveComposer,
   onComposerFocusRequest,
   onComposerInsertRefsRequest,
-  onComposerInsertRequest,
-  onComposerSubmitRequest,
-  onComposerVoiceToggleRequest
+  onComposerInsertRequest
 } from './focus'
 import { HelpHint } from './help-hint'
 import { useAtCompletions } from './hooks/use-at-completions'
@@ -111,7 +107,6 @@ import {
   slashChipElement
 } from './rich-editor'
 import { ComposerStatusStack } from './status-stack'
-import { CodingStatusRow } from './status-stack/coding-row'
 import { detectTrigger, extractClipboardImageBlobs, textBeforeCaret, type TriggerState } from './text-utils'
 import { ComposerTriggerPopover } from './trigger-popover'
 import type { ChatBarProps } from './types'
@@ -278,17 +273,14 @@ export function ChatBar({
     poppedOut ? handleComposerDock() : handleComposerPopOut()
   }, [handleComposerDock, handleComposerPopOut, poppedOut])
 
-  const {
-    dockProximity,
-    dragging,
-    onPointerDown: onComposerGesturePointerDown
-  } = useComposerPopoutGestures({
-    composerRef,
-    onDock: handleComposerDock,
-    onPopOut: handleComposerPopOut,
-    poppedOut,
-    position: popoutPosition
-  })
+  const { dockProximity, dragging, onPointerDown: onComposerGesturePointerDown } =
+    useComposerPopoutGestures({
+      composerRef,
+      onDock: handleComposerDock,
+      onPopOut: handleComposerPopOut,
+      poppedOut,
+      position: popoutPosition
+    })
 
   const draftRef = useRef(draft)
   const pendingDraftPersistRef = useRef<{ scope: string | null; text: string } | null>(null)
@@ -787,16 +779,6 @@ export function ChatBar({
     if (!pastedText) {
       event.preventDefault()
 
-      // Under WSL2/WSLg the Windows host clipboard doesn't bridge *images* to
-      // the Linux clipboard the DOM paste event reads, so a host screenshot
-      // arrives as an empty paste (no blobs, no text). Fall back to the main
-      // process, which pulls the image straight off the Windows clipboard.
-      // Silent so a genuinely-empty paste doesn't pop a "no image" warning.
-      if (onPasteClipboardImage) {
-        triggerHaptic('selection')
-        void onPasteClipboardImage({ silent: true })
-      }
-
       return
     }
 
@@ -829,7 +811,8 @@ export function ChatBar({
   // Suppress the "No matches" empty state once a slash command is past its name:
   // a no-arg command has nothing to offer, and a fully-typed arg commits on
   // Space/Tab — neither should dead-end on a popover.
-  const argStageEmpty = trigger?.kind === '/' && slashArgStage(trigger.query) && !triggerLoading && !triggerItems.length
+  const argStageEmpty =
+    trigger?.kind === '/' && slashArgStage(trigger.query) && !triggerLoading && !triggerItems.length
 
   const closeTrigger = () => {
     setTrigger(null)
@@ -856,14 +839,7 @@ export function ChatBar({
       id: text,
       type: 'slash',
       label: text.slice(1),
-      metadata: {
-        command: slashCommandToken(trigger.query),
-        display: text,
-        meta: '',
-        group: '',
-        action: '',
-        rawText: text
-      }
+      metadata: { command: slashCommandToken(trigger.query), display: text, meta: '', group: '', action: '', rawText: text }
     })
   }
 
@@ -1003,7 +979,10 @@ export function ChatBar({
 
     // Non-collapsed Backspace/Delete: native selection-delete is ~O(n²) on large
     // drafts (Ctrl+A → Delete froze ~1.3s). Collapsed carets fall through.
-    if ((event.key === 'Backspace' || event.key === 'Delete') && deleteSelectionInEditor(event.currentTarget)) {
+    if (
+      (event.key === 'Backspace' || event.key === 'Delete') &&
+      deleteSelectionInEditor(event.currentTarget)
+    ) {
       event.preventDefault()
       flushEditorToDraft(event.currentTarget)
 
@@ -1371,80 +1350,6 @@ export function ChatBar({
     }
   }, [setComposerText])
 
-  // Hand a worktree off to the controller: open a fresh session anchored there,
-  // carrying the composer draft as its first turn. Clearing here means the draft
-  // travels to the new session instead of getting stashed under this one.
-  const openInWorktree = useCallback(
-    (path: string) => {
-      const text = draftRef.current
-      clearDraft()
-      clearComposerAttachments()
-      requestStartWorkSession(path, text)
-    },
-    [clearDraft]
-  )
-
-  // Branch off into a NEW worktree (base = branch name, or current HEAD). A
-  // create failure throws back to the row (which toasts) before we touch the
-  // draft; a missing cwd / remote backend no-ops (the row hides the affordance).
-  const handleBranchOff = useCallback(
-    async (branch: string, base?: string) => {
-      const repoPath = cwd?.trim()
-      const result = repoPath && (await startWorkInRepo(repoPath, { base, branch, name: branch }))
-
-      if (result) {
-        openInWorktree(result.path)
-      }
-    },
-    [cwd, openInWorktree]
-  )
-
-  // Convert an EXISTING branch into a fresh worktree + session (no new branch).
-  // Mirrors handleBranchOff's hand-off: create the worktree, then open a session
-  // anchored there carrying the draft.
-  const handleConvertBranch = useCallback(
-    async (branch: string, path?: null | string, isDefault?: boolean) => {
-      if (path?.trim()) {
-        openInWorktree(path)
-
-        return
-      }
-
-      const repoPath = cwd?.trim()
-
-      if (repoPath && isDefault) {
-        await switchBranchInRepo(repoPath, branch)
-        openInWorktree(repoPath)
-
-        return
-      }
-
-      const result = repoPath && (await startWorkInRepo(repoPath, { existingBranch: branch }))
-
-      if (result) {
-        openInWorktree(result.path)
-      }
-    },
-    [cwd, openInWorktree]
-  )
-
-  const handleListBranches = useCallback(async () => {
-    const repoPath = cwd?.trim()
-
-    return repoPath ? listRepoBranches(repoPath) : []
-  }, [cwd])
-
-  const handleSwitchBranch = useCallback(
-    async (branch: string) => {
-      const repoPath = cwd?.trim()
-
-      if (repoPath) {
-        await switchBranchInRepo(repoPath, branch)
-      }
-    },
-    [cwd]
-  )
-
   const loadIntoComposer = (text: string, attachments: ComposerAttachment[]) => {
     draftRef.current = text
     setComposerText(text)
@@ -1768,43 +1673,6 @@ export function ChatBar({
     }
   }, [autoDrainNext, busy, queuedPrompts.length])
 
-  // Esc cancels the in-flight turn when the CHAT has focus — not just the
-  // composer input (which has its own handler above). Clicking into the
-  // transcript and hitting Esc now stops the run, matching the Stop button.
-  // Intentional only: we bail if (a) the composer/another field already
-  // handled Esc (defaultPrevented), (b) focus is in any input/textarea/
-  // contenteditable (you're typing, not stopping), or (c) a dialog/popover is
-  // open — Esc must close that overlay, never double as canceling the stream
-  // behind it. A latest-handler ref keeps the listener registered once.
-  const escCancelRef = useRef<(event: globalThis.KeyboardEvent) => void>(() => {})
-
-  escCancelRef.current = (event: globalThis.KeyboardEvent) => {
-    if (event.key !== 'Escape' || event.defaultPrevented || !busy) {
-      return
-    }
-
-    const active = document.activeElement as HTMLElement | null
-
-    if (active && (active.tagName === 'INPUT' || active.tagName === 'TEXTAREA' || active.isContentEditable)) {
-      return
-    }
-
-    if (document.querySelector('[role="dialog"],[role="alertdialog"],[data-radix-popper-content-wrapper]')) {
-      return
-    }
-
-    event.preventDefault()
-    triggerHaptic('cancel')
-    void Promise.resolve(onCancel())
-  }
-
-  useEffect(() => {
-    const onKeyDown = (event: globalThis.KeyboardEvent) => escCancelRef.current(event)
-    window.addEventListener('keydown', onKeyDown)
-
-    return () => window.removeEventListener('keydown', onKeyDown)
-  }, [])
-
   // Queue-edit cleanup: on session swap the scope effect already stashed the
   // edit snapshot; only restore into the composer when still on the same scope.
   useEffect(() => {
@@ -1837,22 +1705,6 @@ export function ChatBar({
       .catch(restore)
   }
 
-  // External "submit this prompt" requests (e.g. the review pane's agent-ship
-  // button) route through the same send path. A ref keeps the listener stable
-  // while always calling the latest dispatchSubmit closure.
-  const dispatchSubmitRef = useRef(dispatchSubmit)
-  dispatchSubmitRef.current = dispatchSubmit
-
-  useEffect(
-    () =>
-      onComposerSubmitRequest(({ target, text }) => {
-        if (target === 'main' && !inputDisabled) {
-          dispatchSubmitRef.current(text)
-        }
-      }),
-    [inputDisabled]
-  )
-
   const submitDraft = () => {
     if (disabled) {
       return
@@ -1992,24 +1844,6 @@ export function ChatBar({
     pendingResponse
   })
 
-  // The `composer.voice` hotkey (Ctrl+B) toggles the conversation. Starting
-  // with STT unconfigured lets the conversation surface its own "configure
-  // speech-to-text" notice rather than silently no-opping.
-  const toggleVoiceConversation = useCallback(() => {
-    if (disabled) {
-      return
-    }
-
-    if (voiceConversationActive) {
-      setVoiceConversationActive(false)
-      void conversation.end()
-    } else {
-      setVoiceConversationActive(true)
-    }
-  }, [conversation, disabled, voiceConversationActive])
-
-  useEffect(() => onComposerVoiceToggleRequest(toggleVoiceConversation), [toggleVoiceConversation])
-
   const contextMenu = (
     <ContextMenu
       onInsertText={insertText}
@@ -2246,7 +2080,7 @@ export function ChatBar({
           <div className="relative w-full rounded-[inherit]">
             <div
               className={cn(
-                'group/composer-surface relative z-4 isolate grid grid-rows-[auto_1fr] overflow-hidden rounded-[inherit] border border-[color-mix(in_srgb,var(--dt-composer-ring)_calc(18%*var(--composer-ring-strength)),var(--dt-input))]',
+                'group/composer-surface relative z-4 isolate rounded-[inherit] border border-[color-mix(in_srgb,var(--dt-composer-ring)_calc(18%*var(--composer-ring-strength)),var(--dt-input))] transition-[border-color] duration-200 ease-out focus-within:border-[color-mix(in_srgb,var(--dt-composer-ring)_calc(45%*var(--composer-ring-strength)),transparent)]',
                 COMPOSER_DROP_FADE_CLASS,
                 dragActive && COMPOSER_DROP_ACTIVE_CLASS
               )}
@@ -2261,20 +2095,10 @@ export function ChatBar({
                   composerSurfaceGlass
                 )}
               />
-              <CodingStatusRow
-                onBranchOff={handleBranchOff}
-                onConvertBranch={handleConvertBranch}
-                onListBranches={handleListBranches}
-                onOpen={toggleReview}
-                onOpenWorktree={openInWorktree}
-                onSwitchBranch={handleSwitchBranch}
-              />
               <div
                 className={cn(
                   'relative z-1 flex min-h-0 w-full flex-col gap-(--composer-row-gap) overflow-hidden rounded-[inherit] px-(--composer-surface-pad-x) py-(--composer-surface-pad-y) transition-opacity duration-200 ease-out',
-                  scrolledUp
-                    ? 'opacity-30 group-hover/composer:opacity-100 group-focus-within/composer-surface:opacity-100'
-                    : 'opacity-100'
+                  scrolledUp ? 'opacity-30 group-hover/composer:opacity-100 group-focus-within/composer-surface:opacity-100' : 'opacity-100'
                 )}
                 data-slot="composer-fade"
               >

apps/desktop/src/app/chat/composer/inline-refs.ts

@@ -3,7 +3,12 @@ import { contextPath } from '@/lib/chat-runtime'
 
 import type { DroppedFile } from '../hooks/use-composer-actions'
 
-import { composerPlainText, normalizeComposerEditorDom, placeCaretEnd, refChipElement } from './rich-editor'
+import {
+  composerPlainText,
+  normalizeComposerEditorDom,
+  placeCaretEnd,
+  refChipElement
+} from './rich-editor'
 
 /** A chip to insert: a raw `@kind:value` string, or a typed value + display label. */
 export type InlineRefInput = string | { kind: string; label?: string; value: string }
@@ -154,7 +159,6 @@ export function insertInlineRefsIntoEditor(editor: HTMLDivElement, refs: readonl
   editor.focus({ preventScroll: true })
 
   const selection = window.getSelection()
-
   const range =
     selection?.rangeCount && editor.contains(selection.getRangeAt(0).commonAncestorContainer)
       ? selection.getRangeAt(0)

apps/desktop/src/app/chat/composer/model-pill.tsx

@@ -94,7 +94,13 @@ export function ModelPill({
     <DropdownMenu onOpenChange={setOpen} open={open}>
       <Tip label={title} side="top">
         <DropdownMenuTrigger asChild>
-          <Button aria-label={title} className={pillClass} disabled={disabled} type="button" variant="ghost">
+          <Button
+            aria-label={title}
+            className={pillClass}
+            disabled={disabled}
+            type="button"
+            variant="ghost"
+          >
             {label}
           </Button>
         </DropdownMenuTrigger>

apps/desktop/src/app/chat/composer/status-stack/coding-row.tsx

@@ -1,469 +0,0 @@
-import { useStore } from '@nanostores/react'
-import { memo, useCallback, useEffect, useRef, useState } from 'react'
-
-import { StatusRow } from '@/components/chat/status-row'
-import { Button } from '@/components/ui/button'
-import { Codicon } from '@/components/ui/codicon'
-import { Command, CommandEmpty, CommandGroup, CommandInput, CommandItem, CommandList } from '@/components/ui/command'
-import {
-  Dialog,
-  DialogContent,
-  DialogDescription,
-  DialogFooter,
-  DialogHeader,
-  DialogTitle
-} from '@/components/ui/dialog'
-import { DiffCount } from '@/components/ui/diff-count'
-import {
-  DropdownMenu,
-  DropdownMenuContent,
-  DropdownMenuItem,
-  DropdownMenuLabel,
-  DropdownMenuSeparator,
-  DropdownMenuTrigger
-} from '@/components/ui/dropdown-menu'
-import { SanitizedInput } from '@/components/ui/sanitized-input'
-import type { HermesGitBranch } from '@/global'
-import { useI18n } from '@/i18n'
-import { gitRef } from '@/lib/sanitize'
-import { $repoStatus, $repoWorktrees } from '@/store/coding-status'
-import { notifyError } from '@/store/notifications'
-import { $newWorktreeRequest } from '@/store/projects'
-
-// Tiny uppercase section header, matching the composer "+" menu's labels.
-const MENU_SECTION = 'text-[0.625rem] font-semibold uppercase tracking-wider text-(--ui-text-tertiary)'
-
-interface BranchActionCopy {
-  branchCreateWorktree: string
-  branchOpenExisting: string
-  branchSwitchHome: string
-}
-
-const branchActionLabel = (branch: HermesGitBranch, copy: BranchActionCopy) => {
-  if (branch.checkedOut) {
-    return copy.branchOpenExisting
-  }
-
-  return branch.isDefault ? copy.branchSwitchHome : copy.branchCreateWorktree
-}
-
-interface CodingStatusRowProps {
-  /** Branch the current draft off into a fresh worktree + session, based on
-   *  `base` (a branch name; omitted = current HEAD). The composer owns the
-   *  draft, so it supplies the orchestration; the row just collects the new
-   *  branch name + base. Omitted (e.g. remote backend) hides the affordance. */
-  onBranchOff?: (branch: string, base?: string) => Promise<void>
-  /** Check an existing branch out into a fresh worktree + session (no new
-   *  branch). Drives the dialog's "convert a branch" picker. */
-  onConvertBranch?: (branch: string, path?: null | string, isDefault?: boolean) => Promise<void>
-  /** List the repo's local branches for the "convert a branch" picker. */
-  onListBranches?: () => Promise<HermesGitBranch[]>
-  /** Open the review pane (changed files + diffs). */
-  onOpen?: () => void
-  /** Jump into an existing worktree (open a fresh session anchored there). */
-  onOpenWorktree?: (path: string) => void
-  /** Switch the current repo checkout to another branch. */
-  onSwitchBranch?: (branch: string) => Promise<void>
-}
-
-/**
- * The always-on coding-context row, the BASE of the composer status stack:
- * current branch, dirty summary (+/-), and ahead/behind. A touch more prominent
- * than the per-turn rows above it (larger branch label, accent glyph), and the
- * entry point to the review pane. Hidden when the active session isn't in a
- * local git repo (the probe returns null).
- */
-export const CodingStatusRow = memo(function CodingStatusRow({
-  onBranchOff,
-  onConvertBranch,
-  onListBranches,
-  onOpen,
-  onOpenWorktree,
-  onSwitchBranch
-}: CodingStatusRowProps) {
-  const { t } = useI18n()
-  const s = t.statusStack.coding
-  const p = t.sidebar.projects
-  const status = useStore($repoStatus)
-  const worktrees = useStore($repoWorktrees)
-
-  const [branchOpen, setBranchOpen] = useState(false)
-  const [branchName, setBranchName] = useState('')
-  const [branchBase, setBranchBase] = useState<string | undefined>(undefined)
-  const [branchPending, setBranchPending] = useState(false)
-  const [convertMode, setConvertMode] = useState(false)
-  const [branches, setBranches] = useState<HermesGitBranch[]>([])
-  const [branchesLoading, setBranchesLoading] = useState(false)
-
-  const loadBranches = useCallback(async () => {
-    if (!onListBranches) {
-      return
-    }
-
-    setBranchesLoading(true)
-
-    try {
-      setBranches(await onListBranches())
-    } catch {
-      setBranches([])
-    } finally {
-      setBranchesLoading(false)
-    }
-  }, [onListBranches])
-
-  // Open the name dialog for a chosen base. Deferred so the dropdown finishes
-  // closing before the dialog grabs focus (Radix focus-trap handoff races
-  // otherwise).
-  const startBranch = (base: string | undefined) => {
-    setBranchBase(base)
-    setBranchName('')
-    setConvertMode(false)
-    setTimeout(() => setBranchOpen(true), 0)
-  }
-
-  const startConvert = () => {
-    setBranchBase(undefined)
-    setBranchName('')
-    setConvertMode(true)
-    void loadBranches()
-    setTimeout(() => setBranchOpen(true), 0)
-  }
-
-  const enterConvert = () => {
-    setConvertMode(true)
-    void loadBranches()
-  }
-
-  const convertBranch = async (branch: HermesGitBranch) => {
-    if (branchPending || !branch || !onConvertBranch) {
-      return
-    }
-
-    setBranchPending(true)
-
-    try {
-      await onConvertBranch(branch.name, branch.worktreePath, branch.isDefault)
-      setBranchOpen(false)
-    } catch (err) {
-      notifyError(err, p.startWorkFailed)
-    } finally {
-      setBranchPending(false)
-    }
-  }
-
-  // Global ⌘⇧B (workspace.newWorktree): open the name dialog for a worktree off
-  // current HEAD. The rail only renders inside a repo, so the hotkey naturally
-  // no-ops elsewhere. Guarded by a token ref so it fires on the keypress, not on
-  // mount or unrelated re-renders.
-  const worktreeReq = useStore($newWorktreeRequest)
-  const lastWorktreeReqRef = useRef(worktreeReq)
-
-  useEffect(() => {
-    if (worktreeReq === lastWorktreeReqRef.current) {
-      return
-    }
-
-    lastWorktreeReqRef.current = worktreeReq
-
-    if (!onBranchOff) {
-      return
-    }
-
-    setBranchBase(undefined)
-    setBranchName('')
-    setConvertMode(false)
-    setBranchOpen(true)
-  }, [onBranchOff, worktreeReq])
-
-  const submitBranch = async () => {
-    const branch = branchName.trim()
-
-    if (branchPending || !branch || !onBranchOff) {
-      return
-    }
-
-    setBranchPending(true)
-
-    try {
-      await onBranchOff(branch, branchBase)
-      setBranchOpen(false)
-      setBranchName('')
-    } catch (err) {
-      notifyError(err, p.startWorkFailed)
-    } finally {
-      setBranchPending(false)
-    }
-  }
-
-  const switchToBranch = async (branch: string) => {
-    if (!onSwitchBranch) {
-      return
-    }
-
-    try {
-      await onSwitchBranch(branch)
-    } catch (err) {
-      notifyError(err, s.switchFailed(branch))
-    }
-  }
-
-  if (!status) {
-    return null
-  }
-
-  const branchLabel = status.detached ? s.detached : status.branch || s.noBranch
-  // The kebab offers branching off the trunk and/or the current branch. The
-  // worktree-add bases the new branch on `base` (a branch name; undefined =
-  // current HEAD). We dedupe so "on main" shows a single trunk entry, and fall
-  // back to a plain off-HEAD branch when no trunk is detected.
-  const current = status.detached ? null : status.branch
-  const branchTargets: { base: string | undefined; label: string }[] = []
-
-  // Current branch first (the 99% "branch off where I am"), then the trunk just
-  // below it ("New branch from main"), deduped when they're the same.
-  if (current) {
-    branchTargets.push({ base: current, label: s.branchOffFrom(current) })
-  }
-
-  if (status.defaultBranch && status.defaultBranch !== current) {
-    branchTargets.push({ base: status.defaultBranch, label: s.branchOffFrom(status.defaultBranch) })
-  }
-
-  if (branchTargets.length === 0) {
-    branchTargets.push({ base: undefined, label: s.newBranch })
-  }
-
-  const switchTarget =
-    onSwitchBranch && current && status.defaultBranch && status.defaultBranch !== current ? status.defaultBranch : null
-
-  // Other worktrees to jump into — everything except the one we're already in
-  // (matched by its checked-out branch) and the bare/main placeholder entry.
-  const otherWorktrees = onOpenWorktree
-    ? worktrees.filter(w => w.path && !w.detached && w.branch && w.branch !== current)
-    : []
-
-  const hasLineDelta = status.added > 0 || status.removed > 0
-  // Untracked files carry no line delta vs HEAD, so surface them as a count when
-  // they're the only change (otherwise +/- tells the story).
-  const untrackedOnly = !hasLineDelta && status.untracked > 0
-
-  return (
-    <>
-      <StatusRow
-        // The base "where am I working" strip is part of the composer surface
-        // itself, so it inherits the composer's width and clipped top radius.
-        className="coding-status-bar min-h-7 rounded-t-[inherit] rounded-b-none border-b border-(--ui-stroke-tertiary) px-3.5 py-1.5 hover:bg-transparent"
-        // Static branch glyph — never the loading spinner. This row only renders
-        // once `status` exists, so a spinner here only ever fired on *refreshes*
-        // of an already-loaded repo (window focus, turn settle), reading as an
-        // annoying icon "blip" with no first-load value. Refreshes are silent.
-        leading={<Codicon className="text-(--ui-green)" name="git-branch" size="0.8rem" />}
-        onActivate={onOpen}
-      >
-        <div className="flex min-w-0 flex-1 items-center gap-1">
-          <span
-            className="min-w-0 truncate text-xs font-normal text-muted-foreground/92 transition-colors group-hover/status-row:text-foreground/90"
-            title={branchLabel}
-          >
-            {branchLabel}
-          </span>
-
-          {/* Branch actions kebab — same pattern as the session/worktree rows.
-              ALWAYS laid out; only its opacity flips on hover/focus/open, so
-              revealing it never reflows the row (no layout shift). pointer-events
-              follow opacity so the invisible trigger isn't clickable at rest. */}
-          {onBranchOff && (
-            <DropdownMenu>
-              <DropdownMenuTrigger asChild>
-                <Button
-                  aria-label={s.newBranch}
-                  className="pointer-events-none size-4 shrink-0 text-muted-foreground/60 opacity-0 transition hover:text-foreground group-hover/status-row:pointer-events-auto group-hover/status-row:opacity-100 group-focus-within/status-row:pointer-events-auto group-focus-within/status-row:opacity-100 data-[state=open]:pointer-events-auto data-[state=open]:opacity-100"
-                  onClick={event => event.stopPropagation()}
-                  onKeyDown={event => {
-                    // The row's onActivate also fires on Enter/Space; keep it from
-                    // opening the review pane when the kebab is the focus target.
-                    if (event.key === 'Enter' || event.key === ' ') {
-                      event.stopPropagation()
-                    }
-                  }}
-                  size="icon-xs"
-                  variant="ghost"
-                >
-                  <Codicon name="kebab-vertical" size="0.8rem" />
-                </Button>
-              </DropdownMenuTrigger>
-              {/* The row sits at the bottom of the screen (above the composer),
-                  so the menu opens upward. */}
-              <DropdownMenuContent align="end" className="w-60" side="top" sideOffset={6}>
-                <DropdownMenuLabel className={MENU_SECTION}>{s.newBranch}</DropdownMenuLabel>
-                {branchTargets.map(target => (
-                  <DropdownMenuItem key={target.base ?? '__head__'} onSelect={() => startBranch(target.base)}>
-                    <span className="truncate">{target.label}</span>
-                  </DropdownMenuItem>
-                ))}
-
-                {switchTarget && (
-                  <DropdownMenuItem onSelect={() => void switchToBranch(switchTarget)}>
-                    <span className="truncate">{s.switchTo(switchTarget)}</span>
-                  </DropdownMenuItem>
-                )}
-
-                <DropdownMenuSeparator />
-                <DropdownMenuLabel className={MENU_SECTION}>{s.worktrees}</DropdownMenuLabel>
-                {otherWorktrees.map(worktree => (
-                  <DropdownMenuItem key={worktree.path} onSelect={() => onOpenWorktree?.(worktree.path)}>
-                    <span className="truncate">{worktree.branch}</span>
-                  </DropdownMenuItem>
-                ))}
-                {/* Create a fresh worktree off the current HEAD (the generic
-                    "spin up a worktree here", mirroring the sidebar's + button). */}
-                <DropdownMenuItem onSelect={() => startBranch(undefined)}>
-                  <span className="truncate">{p.startWork}</span>
-                </DropdownMenuItem>
-                {/* Check an EXISTING branch out into a worktree (no new branch). */}
-                {onConvertBranch && (
-                  <DropdownMenuItem onSelect={() => startConvert()}>
-                    <span className="truncate">{p.convertBranch}</span>
-                  </DropdownMenuItem>
-                )}
-              </DropdownMenuContent>
-            </DropdownMenu>
-          )}
-        </div>
-
-        {(status.ahead > 0 || status.behind > 0) && (
-          <span className="ml-auto flex shrink-0 items-center gap-1.5 text-[0.68rem] leading-4 text-muted-foreground/75 tabular-nums">
-            {status.ahead > 0 && (
-              <span className="flex items-center gap-0.5" title={s.ahead(status.ahead)}>
-                <span aria-hidden>↑</span>
-                {status.ahead}
-              </span>
-            )}
-            {status.behind > 0 && (
-              <span className="flex items-center gap-0.5" title={s.behind(status.behind)}>
-                <span aria-hidden>↓</span>
-                {status.behind}
-              </span>
-            )}
-          </span>
-        )}
-
-        {hasLineDelta ? (
-          <DiffCount
-            added={status.added}
-            className={`text-[0.72rem] leading-4 ${status.ahead === 0 && status.behind === 0 ? 'ml-auto' : ''}`}
-            removed={status.removed}
-          />
-        ) : untrackedOnly ? (
-          <span
-            className={`shrink-0 text-[0.72rem] leading-4 text-amber-500/90 ${status.ahead === 0 && status.behind === 0 ? 'ml-auto' : ''}`}
-          >
-            {s.changed(status.untracked)}
-          </span>
-        ) : null}
-      </StatusRow>
-
-      <Dialog onOpenChange={open => !branchPending && setBranchOpen(open)} open={branchOpen}>
-        <DialogContent className="max-w-md">
-          <DialogHeader>
-            <DialogTitle>{convertMode ? p.convertBranchTitle : p.newWorktreeTitle}</DialogTitle>
-            <DialogDescription>
-              {convertMode ? p.convertBranchDesc : p.newWorktreeDesc}
-              {!convertMode && branchBase && (
-                <span className="mt-1 block text-(--ui-text-secondary)">{s.branchOffFrom(branchBase)}</span>
-              )}
-            </DialogDescription>
-          </DialogHeader>
-
-          {convertMode ? (
-            <Command
-              className="rounded-md border border-(--ui-stroke-tertiary)"
-              // The branch name is the authoritative key; filter on it directly.
-              filter={(value, search) => (value.toLowerCase().includes(search.toLowerCase()) ? 1 : 0)}
-            >
-              <CommandInput autoFocus disabled={branchPending} placeholder={p.convertBranchPlaceholder} />
-              <CommandList className="max-h-64">
-                <CommandEmpty>{branchesLoading ? p.branchesLoading : p.noBranches}</CommandEmpty>
-                <CommandGroup>
-                  {branches.map(branch => (
-                    <CommandItem
-                      disabled={branchPending}
-                      key={branch.name}
-                      onSelect={() => void convertBranch(branch)}
-                      value={branch.name}
-                    >
-                      <Codicon className="shrink-0 text-(--ui-text-tertiary)" name="git-branch" size="0.8rem" />
-                      <span className="truncate">{branch.name}</span>
-                      <span className="ml-auto shrink-0 text-[0.625rem] text-(--ui-text-tertiary)">
-                        {branchActionLabel(branch, p)}
-                      </span>
-                    </CommandItem>
-                  ))}
-                </CommandGroup>
-              </CommandList>
-            </Command>
-          ) : (
-            <SanitizedInput
-              autoFocus
-              disabled={branchPending}
-              onKeyDown={event => {
-                if (event.key === 'Enter') {
-                  event.preventDefault()
-                  void submitBranch()
-                } else if (event.key === 'Escape') {
-                  setBranchOpen(false)
-                }
-              }}
-              onValueChange={setBranchName}
-              placeholder={p.branchPlaceholder}
-              sanitize={gitRef}
-              value={branchName}
-            />
-          )}
-
-          {convertMode ? (
-            <DialogFooter className="sm:justify-start">
-              <Button
-                className="px-0 text-(--ui-text-secondary) hover:text-foreground"
-                disabled={branchPending}
-                onClick={() => setConvertMode(false)}
-                type="button"
-                variant="link"
-              >
-                {t.common.cancel}
-              </Button>
-            </DialogFooter>
-          ) : (
-            <DialogFooter className="sm:justify-between">
-              {onConvertBranch ? (
-                <Button
-                  className="px-0 text-(--ui-text-secondary) hover:text-foreground"
-                  disabled={branchPending}
-                  onClick={enterConvert}
-                  type="button"
-                  variant="link"
-                >
-                  {p.convertBranchInstead}
-                </Button>
-              ) : (
-                <span />
-              )}
-              <div className="flex items-center gap-2">
-                <Button disabled={branchPending} onClick={() => setBranchOpen(false)} type="button" variant="ghost">
-                  {t.common.cancel}
-                </Button>
-                <Button
-                  disabled={branchPending || !branchName.trim()}
-                  onClick={() => void submitBranch()}
-                  type="button"
-                >
-                  {p.startWork}
-                </Button>
-              </div>
-            </DialogFooter>
-          )}
-        </DialogContent>
-      </Dialog>
-    </>
-  )
-})

apps/desktop/src/app/chat/composer/status-stack/index.tsx

@@ -30,19 +30,6 @@ import { StatusItemRow } from './status-row'
 // emit no event when they die). Only armed while a running row is on screen.
 const BACKGROUND_POLL_MS = 5_000
 
-// A localhost/loopback preview is only meaningful while its dev server is up, so
-// we tie it to a live background process rather than persisting dismissals or
-// letting dead URLs pile up. File previews (a real on-disk artifact) stand alone.
-const isLocalhostPreview = (target: string): boolean => /\b(?:localhost|127\.0\.0\.1|0\.0\.0\.0)\b/i.test(target)
-
-// Real codicons per group (no sparkles): a checklist for todos, a bot for
-// subagents, a background process glyph for background tasks.
-const GROUP_ICON: Record<StatusGroup['type'], string> = {
-  todo: 'checklist',
-  subagent: 'hubot',
-  background: 'server-process'
-}
-
 const groupLabel = (group: StatusGroup, s: Translations['statusStack']) => {
   if (group.type === 'todo') {
     return s.todos(group.items.filter(i => i.todoStatus === 'completed').length, group.items.length)
@@ -87,10 +74,6 @@ export function ComposerStatusStack({ queue, sessionId }: ComposerStatusStackPro
 
   const hasRunningBackground = groups.some(g => g.type === 'background' && g.items.some(i => i.state === 'running'))
 
-  // Drop localhost previews once no dev server is left running — that's what made
-  // dead `localhost:5174` chips stick around. On-disk file previews are kept.
-  const visiblePreviews = previews.filter(item => hasRunningBackground || !isLocalhostPreview(item.target))
-
   useEffect(() => {
     if (!sessionId || !hasRunningBackground) {
       return
@@ -106,18 +89,6 @@ export function ComposerStatusStack({ queue, sessionId }: ComposerStatusStackPro
   const openSubagent = (item: ComposerStatusItem) =>
     item.sessionId ? void openSessionInNewWindow(item.sessionId, { watch: true }) : openAgents()
 
-  // Preview links live as child rows of the background group — a localhost dev
-  // server and its preview are the same thing — so they no longer float as an
-  // odd, differently-indented standalone block under the stack.
-  const previewRows =
-    visiblePreviews.length > 0 && sessionId
-      ? visiblePreviews.map(item => (
-          <PreviewStatusRow item={item} key={item.id} onDismiss={id => dismissPreviewArtifact(sessionId, id)} />
-        ))
-      : []
-
-  const hasBackgroundGroup = groups.some(g => g.type === 'background')
-
   const sections: { key: string; node: ReactNode }[] = groups.map(group => ({
     key: group.type,
     node: (
@@ -136,7 +107,11 @@ export function ComposerStatusStack({ queue, sessionId }: ComposerStatusStackPro
           ) : undefined
         }
         defaultCollapsed={group.type !== 'todo'}
-        icon={<Codicon className="text-muted-foreground/70" name={GROUP_ICON[group.type]} size="0.8rem" />}
+        icon={
+          group.type === 'todo' ? (
+            <Codicon className="text-muted-foreground/70" name="checklist" size="0.8rem" />
+          ) : undefined
+        }
         label={groupLabel(group, t.statusStack)}
       >
         {group.items.map(item => (
@@ -145,20 +120,25 @@ export function ComposerStatusStack({ queue, sessionId }: ComposerStatusStackPro
             key={item.id}
             onDismiss={sessionId ? id => dismissBackgroundProcess(sessionId, id) : undefined}
             onOpen={() => openSubagent(item)}
-            onStop={sessionId ? id => void stopBackgroundProcess(sessionId, id) : undefined}
+            onStop={sessionId ? id => stopBackgroundProcess(sessionId, id) : undefined}
           />
         ))}
-        {group.type === 'background' && previewRows}
       </StatusSection>
     )
   }))
 
-  // No background group to host them (e.g. a standalone on-disk file preview):
-  // keep the previews as their own row block so they don't disappear.
-  if (previewRows.length > 0 && !hasBackgroundGroup) {
+  if (previews.length > 0 && sessionId) {
     sections.push({
       key: 'preview',
-      node: <div className="px-1 py-0.5">{previewRows}</div>
+      // Not a collapsible group — preview links just sit there, one line each,
+      // each individually closeable.
+      node: (
+        <div className="px-1 py-0.5">
+          {previews.map(item => (
+            <PreviewStatusRow item={item} key={item.id} onDismiss={id => dismissPreviewArtifact(sessionId, id)} />
+          ))}
+        </div>
+      )
     })
   }
 
@@ -210,10 +190,12 @@ export function ComposerStatusStack({ queue, sessionId }: ComposerStatusStackPro
 
   return (
     <div
-      // Sits in the overlay lane above the composer. The composer root has pt-2
-      // before the actual surface; translate by that amount so the stack returns
-      // to its original attachment point without intruding into the repo strip.
-      className="absolute inset-x-0 bottom-full z-3 max-h-[40vh] translate-y-2 overflow-y-auto"
+      // Sits above the composer (bottom-full), nudged down by the shell's 0.5rem
+      // top pad (pt-2 on composer-root) plus 1px so its bottom edge overlaps the
+      // composer surface's top border. z BELOW the surface (z-4) so the surface's
+      // top border paints over our transparent bottom border — one seam, no
+      // double line.
+      className="absolute inset-x-0 bottom-full z-3 max-h-[40vh] translate-y-[calc(0.5rem+1px)] overflow-y-auto"
       onPointerDownCapture={() => blurComposerInput()}
       ref={stackRef}
     >
@@ -223,19 +205,17 @@ export function ComposerStatusStack({ queue, sessionId }: ComposerStatusStackPro
           Rounded top, square bottom; the bottom border is TRANSPARENT — the
           composer surface's visible top border (which sits at a higher z) is the
           single shared seam, so the two read as one fused capsule. */}
-      <div
-        className={cn(
-          composerDockCard('top'),
-          // Inset (mx-2) so the stack reads slightly narrower than the composer
-          // surface below it — the original look.
-          'mx-2 overflow-hidden rounded-b-none border-b border-b-transparent pt-0.5',
-          'transition-opacity duration-200 ease-out',
-          scrolledUp ? 'opacity-30 group-hover/composer:opacity-100' : 'opacity-100'
-        )}
-      >
-        {sections.map(section => (
-          <div key={section.key}>{section.node}</div>
-        ))}
+      <div className={cn(composerDockCard('top'), 'mx-2 rounded-b-none border-b border-b-transparent pt-0.5 pb-1')}>
+        <div
+          className={cn(
+            'transition-opacity duration-200 ease-out',
+            scrolledUp ? 'opacity-30 group-hover/composer:opacity-100' : 'opacity-100'
+          )}
+        >
+          {sections.map(section => (
+            <div key={section.key}>{section.node}</div>
+          ))}
+        </div>
       </div>
     </div>
   )

apps/desktop/src/app/chat/composer/status-stack/preview-row.tsx

@@ -6,6 +6,7 @@ import { Button } from '@/components/ui/button'
 import { Codicon } from '@/components/ui/codicon'
 import { Tip } from '@/components/ui/tooltip'
 import { useI18n } from '@/i18n'
+import { ChevronRight, X } from '@/lib/icons'
 import { normalizeOrLocalPreviewTarget } from '@/lib/local-preview'
 import { cn } from '@/lib/utils'
 import { PREVIEW_PANE_ID } from '@/store/layout'
@@ -75,52 +76,50 @@ export const PreviewStatusRow = memo(function PreviewStatusRow({ item, onDismiss
 
   return (
     <StatusRow
-      leading={
-        <Codicon
-          aria-hidden
-          className={cn('text-muted-foreground/70', opening && 'animate-pulse')}
-          name="globe"
-          size="0.8rem"
-        />
-      }
-      // Plain click opens the link in the browser; ⌘/Ctrl-click opens it in the
-      // in-app preview pane instead. (isOpen still toggles the pane closed.)
-      onActivate={event => {
-        if (event.metaKey || event.ctrlKey) {
-          void togglePreview()
-        } else {
-          void openInBrowser()
-        }
-      }}
+      leading={<ChevronRight aria-hidden className="size-3 text-muted-foreground/80" />}
+      onActivate={() => void togglePreview()}
       trailing={
-        <Tip label={t.statusStack.dismiss}>
-          <Button
-            aria-label={t.statusStack.dismiss}
-            className="-my-1 size-4 rounded-md text-muted-foreground/60 hover:text-foreground/90"
-            onClick={event => {
-              event.stopPropagation()
-              onDismiss(item.id)
-            }}
-            size="icon-xs"
-            type="button"
-            variant="ghost"
-          >
-            <Codicon name="close" size="0.75rem" />
-          </Button>
-        </Tip>
+        <span className="-my-1 flex items-center gap-0.5">
+          <Tip label={t.preview.openInBrowser}>
+            <Button
+              aria-label={t.preview.openInBrowser}
+              className="size-4 rounded-md text-muted-foreground/60 hover:text-foreground/90"
+              onClick={event => {
+                event.stopPropagation()
+                void openInBrowser()
+              }}
+              size="icon-xs"
+              type="button"
+              variant="ghost"
+            >
+              <Codicon name="link-external" size="0.75rem" />
+            </Button>
+          </Tip>
+          <Tip label={t.statusStack.dismiss}>
+            <Button
+              aria-label={t.statusStack.dismiss}
+              className="size-4 rounded-md text-muted-foreground/60 hover:text-foreground/90"
+              onClick={event => {
+                event.stopPropagation()
+                onDismiss(item.id)
+              }}
+              size="icon-xs"
+              type="button"
+              variant="ghost"
+            >
+              <X size={12} />
+            </Button>
+          </Tip>
+        </span>
       }
       trailingVisible
     >
-      <Tip
-        label={
-          <span className="flex flex-col gap-0.5">
-            <span>{item.target}</span>
-            <span className="opacity-70">{t.preview.linkHint}</span>
-          </span>
-        }
-      >
-        <span className="min-w-0 max-w-[18rem] truncate text-[0.73rem] leading-4 text-foreground/92">{item.label}</span>
-      </Tip>
+      <span className="min-w-0 max-w-[18rem] truncate text-[0.73rem] leading-4 text-foreground/92" title={item.target}>
+        {item.label}
+      </span>
+      <span className={cn('shrink-0 text-[0.62rem] leading-4 text-muted-foreground/70', opening && 'animate-pulse')}>
+        {opening ? t.preview.opening : isOpen ? t.preview.hide : t.preview.openPreview}
+      </span>
     </StatusRow>
   )
 })

apps/desktop/src/app/chat/composer/status-stack/status-row.tsx

@@ -8,6 +8,7 @@ import { DisclosureCaret } from '@/components/ui/disclosure-caret'
 import { GlyphSpinner } from '@/components/ui/glyph-spinner'
 import { Tip } from '@/components/ui/tooltip'
 import { type Translations, useI18n } from '@/i18n'
+import { ArrowUpRight, X } from '@/lib/icons'
 import type { TodoStatus } from '@/lib/todos'
 import { cn } from '@/lib/utils'
 import type { ComposerStatusItem } from '@/store/composer-status'
@@ -49,7 +50,7 @@ function leadingGlyph(item: ComposerStatusItem, s: Translations['statusStack']):
     return (
       <GlyphSpinner
         ariaLabel={s.running}
-        className="text-[0.85rem] leading-none text-muted-foreground/80"
+        className="text-[0.9rem] leading-none text-muted-foreground/80"
         spinner="braille"
       />
     )
@@ -116,11 +117,11 @@ export const StatusItemRow = memo(function StatusItemRow({ item, onDismiss, onOp
                 type="button"
                 variant="ghost"
               >
-                <Codicon name="close" size="0.75rem" />
+                <X size={12} />
               </Button>
             </Tip>
           ) : canOpen ? (
-            <Codicon aria-hidden className="text-muted-foreground/55" name="link-external" size="0.85rem" />
+            <ArrowUpRight aria-hidden className="size-3.5 text-muted-foreground/55" />
           ) : undefined
         }
       >

apps/desktop/src/app/chat/composer/trigger-popover.test.tsx

@@ -11,14 +11,7 @@ function renderPopover(kind: '@' | '/', loading = false) {
 
   const rendered = render(
     <I18nProvider configClient={null} initialLocale="zh">
-      <ComposerTriggerPopover
-        activeIndex={0}
-        items={[]}
-        kind={kind}
-        loading={loading}
-        onHover={onHover}
-        onPick={onPick}
-      />
+      <ComposerTriggerPopover activeIndex={0} items={[]} kind={kind} loading={loading} onHover={onHover} onPick={onPick} />
     </I18nProvider>
   )
 

apps/desktop/src/app/chat/composer/types.ts

@@ -46,7 +46,7 @@ export interface ChatBarProps {
   onAddUrl?: (url: string) => void
   onAttachImageBlob?: (blob: Blob) => Promise<boolean | void> | boolean | void
   onAttachDroppedItems?: (candidates: DroppedFile[]) => Promise<boolean | void> | boolean | void
-  onPasteClipboardImage?: (opts?: { silent?: boolean }) => Promise<boolean> | void
+  onPasteClipboardImage?: () => void
   onPickFiles?: () => void
   onPickFolders?: () => void
   onPickImages?: () => void

apps/desktop/src/app/chat/hooks/use-composer-actions.ts

@@ -226,10 +226,9 @@ const attachToMain = (attachment: ComposerAttachment) => {
 export function useComposerActions({ activeSessionId, currentCwd, requestGateway }: ComposerActionsOptions) {
   const { t } = useI18n()
   const copy = t.desktop
-
   const addTextToDraft = useCallback((text: string) => {
     requestComposerInsert(text, { mode: 'block' })
-  }, [])
+  }, [copy.imagePreviewFailed])
 
   const addTerminalSelectionAttachment = useCallback((text: string, label = 'selection') => {
     const trimmed = text.trim()
@@ -330,38 +329,35 @@ export function useComposerActions({ activeSessionId, currentCwd, requestGateway
     [currentCwd]
   )
 
-  const attachImagePath = useCallback(
-    async (filePath: string) => {
-      if (!filePath) {
-        return false
+  const attachImagePath = useCallback(async (filePath: string) => {
+    if (!filePath) {
+      return false
+    }
+
+    const baseAttachment: ComposerAttachment = {
+      id: attachmentId('image', filePath),
+      kind: 'image',
+      label: pathLabel(filePath),
+      detail: filePath,
+      path: filePath
+    }
+
+    attachToMain(baseAttachment)
+
+    try {
+      const previewUrl = await window.hermesDesktop?.readFileDataUrl(filePath)
+
+      if (previewUrl) {
+        addComposerAttachment({ ...baseAttachment, previewUrl })
       }
 
-      const baseAttachment: ComposerAttachment = {
-        id: attachmentId('image', filePath),
-        kind: 'image',
-        label: pathLabel(filePath),
-        detail: filePath,
-        path: filePath
-      }
+      return true
+    } catch (err) {
+      notifyError(err, copy.imagePreviewFailed)
 
-      attachToMain(baseAttachment)
-
-      try {
-        const previewUrl = await window.hermesDesktop?.readFileDataUrl(filePath)
-
-        if (previewUrl) {
-          addComposerAttachment({ ...baseAttachment, previewUrl })
-        }
-
-        return true
-      } catch (err) {
-        notifyError(err, copy.imagePreviewFailed)
-
-        return true
-      }
-    },
-    [copy.imagePreviewFailed]
-  )
+      return true
+    }
+  }, [])
 
   const attachImageBlob = useCallback(
     async (blob: Blob) => {
@@ -415,36 +411,25 @@ export function useComposerActions({ activeSessionId, currentCwd, requestGateway
     }
   }, [attachImagePath, copy.attachImages, currentCwd, t.composer.images])
 
-  const pasteClipboardImage = useCallback(
-    async ({ silent = false }: { silent?: boolean } = {}) => {
-      try {
-        const path = await window.hermesDesktop?.saveClipboardImage()
+  const pasteClipboardImage = useCallback(async () => {
+    try {
+      const path = await window.hermesDesktop?.saveClipboardImage()
 
-        if (!path) {
-          if (!silent) {
-            notify({
-              kind: 'warning',
-              title: copy.clipboard,
-              message: copy.noClipboardImage
-            })
-          }
+      if (!path) {
+        notify({
+          kind: 'warning',
+          title: copy.clipboard,
+          message: copy.noClipboardImage
+        })
 
-          return false
-        }
-
-        await attachImagePath(path)
-
-        return true
-      } catch (err) {
-        if (!silent) {
-          notifyError(err, copy.clipboardPasteFailed)
-        }
-
-        return false
+        return
       }
-    },
-    [attachImagePath, copy.clipboard, copy.clipboardPasteFailed, copy.noClipboardImage]
-  )
+
+      await attachImagePath(path)
+    } catch (err) {
+      notifyError(err, copy.clipboardPasteFailed)
+    }
+  }, [attachImagePath, copy.clipboard, copy.clipboardPasteFailed, copy.noClipboardImage])
 
   const attachContextFolderPath = useCallback(
     (folderPath: string) => {