feat(tui): add model picker and approval/clarify prompt workflows

Three new static prompt components for showroom capture (no useInput):

- ApprovalPromptStatic: double-bordered warning box with command preview,
  4 options (allow once/session/always/deny), ▸ selection, footer hints
- ClarifyPromptStatic: heading + numbered choices with 'Other' option
- ModelPickerStatic: double-bordered popup with provider/model lists,
  current model header, persist toggle, quick-pick numbers

New workflows:
- interactive-prompts: approval → clarify → deploy result
- model-picker: provider stage → model stage → switch result

agent/anthropic_adapter.py

@@ -390,16 +390,7 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
         "timeout": Timeout(timeout=float(_read_timeout), connect=10.0),
     }
     if normalized_base_url:
-        # Azure Anthropic endpoints require an ``api-version`` query parameter.
-        # Pass it via default_query so the SDK appends it to every request URL
-        # without corrupting the base_url (appending it directly produces
-        # malformed paths like /anthropic?api-version=.../v1/messages).
-        _is_azure_endpoint = "azure.com" in normalized_base_url.lower()
-        if _is_azure_endpoint and "api-version" not in normalized_base_url:
-            kwargs["base_url"] = normalized_base_url.rstrip("/")
-            kwargs["default_query"] = {"api-version": "2025-04-15"}
-        else:
-            kwargs["base_url"] = normalized_base_url
+        kwargs["base_url"] = normalized_base_url
     common_betas = _common_betas_for_base_url(normalized_base_url)
 
     if _is_kimi_coding_endpoint(base_url):

agent/auxiliary_client.py

@@ -42,7 +42,6 @@ import time
 from pathlib import Path  # noqa: F401 — used by test mocks
 from types import SimpleNamespace
 from typing import Any, Dict, List, Optional, Tuple
-from urllib.parse import urlparse, parse_qs, urlunparse
 
 from openai import OpenAI
 
@@ -53,17 +52,6 @@ from utils import base_url_host_matches, base_url_hostname, normalize_proxy_env_
 
 logger = logging.getLogger(__name__)
 
-
-def _extract_url_query_params(url: str):
-    """Extract query params from URL, return (clean_url, default_query dict or None)."""
-    parsed = urlparse(url)
-    if parsed.query:
-        clean = urlunparse(parsed._replace(query=""))
-        params = {k: v[0] for k, v in parse_qs(parsed.query).items()}
-        return clean, params
-    return url, None
-
-
 # Module-level flag: only warn once per process about stale OPENAI_BASE_URL.
 _stale_base_url_warned = False
 
@@ -1169,10 +1157,8 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
         return None, None
     model = _read_main_model() or "gpt-4o-mini"
     logger.debug("Auxiliary client: custom endpoint (%s, api_mode=%s)", model, custom_mode or "chat_completions")
-    _clean_base, _dq = _extract_url_query_params(custom_base)
-    _extra = {"default_query": _dq} if _dq else {}
     if custom_mode == "codex_responses":
-        real_client = OpenAI(api_key=custom_key, base_url=_clean_base, **_extra)
+        real_client = OpenAI(api_key=custom_key, base_url=custom_base)
         return CodexAuxiliaryClient(real_client, model), model
     if custom_mode == "anthropic_messages":
         # Third-party Anthropic-compatible gateway (MiniMax, Zhipu GLM,
@@ -1186,12 +1172,12 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
                 "Custom endpoint declares api_mode=anthropic_messages but the "
                 "anthropic SDK is not installed — falling back to OpenAI-wire."
             )
-            return OpenAI(api_key=custom_key, base_url=_clean_base, **_extra), model
+            return OpenAI(api_key=custom_key, base_url=custom_base), model
         return (
             AnthropicAuxiliaryClient(real_client, model, custom_key, custom_base, is_oauth=False),
             model,
         )
-    return OpenAI(api_key=custom_key, base_url=_clean_base, **_extra), model
+    return OpenAI(api_key=custom_key, base_url=custom_base), model
 
 
 def _try_codex() -> Tuple[Optional[Any], Optional[str]]:
@@ -1839,15 +1825,12 @@ def resolve_provider_client(
                 provider,
             )
             extra = {}
-            _clean_base, _dq = _extract_url_query_params(custom_base)
-            if _dq:
-                extra["default_query"] = _dq
             if base_url_host_matches(custom_base, "api.kimi.com"):
                 extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
             elif base_url_host_matches(custom_base, "api.githubcopilot.com"):
                 from hermes_cli.models import copilot_default_headers
                 extra["default_headers"] = copilot_default_headers()
-            client = OpenAI(api_key=custom_key, base_url=_clean_base, **extra)
+            client = OpenAI(api_key=custom_key, base_url=custom_base, **extra)
             client = _wrap_if_needed(client, final_model, custom_base)
             return (_to_async_client(client, final_model) if async_mode
                     else (client, final_model))
@@ -1884,8 +1867,6 @@ def resolve_provider_client(
                     model or custom_entry.get("model") or _read_main_model() or "gpt-4o-mini",
                     provider,
                 )
-                _clean_base2, _dq2 = _extract_url_query_params(custom_base)
-                _extra2 = {"default_query": _dq2} if _dq2 else {}
                 logger.debug(
                     "resolve_provider_client: named custom provider %r (%s, api_mode=%s)",
                     provider, final_model, entry_api_mode or "chat_completions")
@@ -1903,7 +1884,7 @@ def resolve_provider_client(
                             "installed — falling back to OpenAI-wire.",
                             provider,
                         )
-                        client = OpenAI(api_key=custom_key, base_url=_clean_base2, **_extra2)
+                        client = OpenAI(api_key=custom_key, base_url=custom_base)
                         return (_to_async_client(client, final_model) if async_mode
                                 else (client, final_model))
                     sync_anthropic = AnthropicAuxiliaryClient(
@@ -1912,7 +1893,7 @@ def resolve_provider_client(
                     if async_mode:
                         return AsyncAnthropicAuxiliaryClient(sync_anthropic), final_model
                     return sync_anthropic, final_model
-                client = OpenAI(api_key=custom_key, base_url=_clean_base2, **_extra2)
+                client = OpenAI(api_key=custom_key, base_url=custom_base)
                 # codex_responses or inherited auto-detect (via _wrap_if_needed).
                 # _wrap_if_needed reads the closed-over `api_mode` (the task-level
                 # override). Named-provider entry api_mode=codex_responses also

agent/codex_responses_adapter.py

@@ -227,23 +227,6 @@ def _responses_tools(tools: Optional[List[Dict[str, Any]]] = None) -> Optional[L
 # Message format conversion
 # ---------------------------------------------------------------------------
 
-_RESPONSE_MESSAGE_STATUSES = {"completed", "incomplete", "in_progress"}
-
-
-def _normalize_responses_message_status(value: Any, *, default: str = "completed") -> str:
-    """Normalize a Responses assistant message status for replay.
-
-    The API accepts completed/incomplete/in_progress on replayed assistant
-    output messages.  Preserve those exactly (modulo case/hyphen spelling) so
-    incomplete Codex continuation turns don't get falsely marked completed.
-    """
-    if isinstance(value, str):
-        status = value.strip().lower().replace("-", "_").replace(" ", "_")
-        if status in _RESPONSE_MESSAGE_STATUSES:
-            return status
-    return default
-
-
 def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
     """Convert internal chat-style messages to Responses input items."""
     items: List[Dict[str, Any]] = []
@@ -289,57 +272,7 @@ def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Di
                                 seen_item_ids.add(item_id)
                             has_codex_reasoning = True
 
-                # Replay exact assistant message items (with id/phase) from
-                # previous turns so the API can maintain prefix-cache hits.
-                # OpenAI docs: "preserve and resend phase on all assistant
-                # messages — dropping it can degrade performance."
-                codex_message_items = msg.get("codex_message_items")
-                replayed_message_items = 0
-                if isinstance(codex_message_items, list):
-                    for raw_item in codex_message_items:
-                        if not isinstance(raw_item, dict):
-                            continue
-                        if raw_item.get("type") != "message" or raw_item.get("role") != "assistant":
-                            continue
-                        raw_content_parts = raw_item.get("content")
-                        if not isinstance(raw_content_parts, list):
-                            continue
-
-                        normalized_content_parts = []
-                        for part in raw_content_parts:
-                            if not isinstance(part, dict):
-                                continue
-                            part_type = str(part.get("type") or "").strip()
-                            if part_type not in {"output_text", "text"}:
-                                continue
-                            text = part.get("text", "")
-                            if text is None:
-                                text = ""
-                            if not isinstance(text, str):
-                                text = str(text)
-                            normalized_content_parts.append({"type": "output_text", "text": text})
-
-                        if not normalized_content_parts:
-                            continue
-
-                        replay_item = {
-                            "type": "message",
-                            "role": "assistant",
-                            "status": _normalize_responses_message_status(raw_item.get("status")),
-                            "content": normalized_content_parts,
-                        }
-                        item_id = raw_item.get("id")
-                        if isinstance(item_id, str) and item_id.strip():
-                            replay_item["id"] = item_id.strip()
-                        phase = raw_item.get("phase")
-                        if isinstance(phase, str) and phase.strip():
-                            replay_item["phase"] = phase.strip()
-                        items.append(replay_item)
-                        replayed_message_items += 1
-
-                if replayed_message_items > 0:
-                    pass
-                elif content_parts:
+                if content_parts:
                     items.append({"role": "assistant", "content": content_parts})
                 elif content_text.strip():
                     items.append({"role": "assistant", "content": content_text})
@@ -499,47 +432,6 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
                 normalized.append(reasoning_item)
             continue
 
-        if item_type == "message":
-            role = item.get("role")
-            if role != "assistant":
-                raise ValueError(f"Codex Responses input[{idx}] message items must have role='assistant'.")
-            content = item.get("content")
-            if not isinstance(content, list):
-                raise ValueError(f"Codex Responses input[{idx}] message item must have content list.")
-            normalized_content = []
-            for part_idx, part in enumerate(content):
-                if not isinstance(part, dict):
-                    raise ValueError(
-                        f"Codex Responses input[{idx}] message content[{part_idx}] must be an object."
-                    )
-                part_type = part.get("type")
-                if part_type not in {"output_text", "text"}:
-                    raise ValueError(
-                        f"Codex Responses input[{idx}] message content[{part_idx}] has unsupported type {part_type!r}."
-                    )
-                text = part.get("text", "")
-                if text is None:
-                    text = ""
-                if not isinstance(text, str):
-                    text = str(text)
-                normalized_content.append({"type": "output_text", "text": text})
-            if not normalized_content:
-                raise ValueError(f"Codex Responses input[{idx}] message item must contain at least one text part.")
-            normalized_item: Dict[str, Any] = {
-                "type": "message",
-                "role": "assistant",
-                "status": _normalize_responses_message_status(item.get("status")),
-                "content": normalized_content,
-            }
-            item_id = item.get("id")
-            if isinstance(item_id, str) and item_id.strip():
-                normalized_item["id"] = item_id.strip()
-            phase = item.get("phase")
-            if isinstance(phase, str) and phase.strip():
-                normalized_item["phase"] = phase.strip()
-            normalized.append(normalized_item)
-            continue
-
         role = item.get("role")
         if role in {"user", "assistant"}:
             content = item.get("content", "")
@@ -824,7 +716,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
     content_parts: List[str] = []
     reasoning_parts: List[str] = []
     reasoning_items_raw: List[Dict[str, Any]] = []
-    message_items_raw: List[Dict[str, Any]] = []
     tool_calls: List[Any] = []
     has_incomplete_items = response_status in {"queued", "in_progress", "incomplete"}
     saw_commentary_phase = False
@@ -843,7 +734,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
 
         if item_type == "message":
             item_phase = getattr(item, "phase", None)
-            normalized_phase = None
             if isinstance(item_phase, str):
                 normalized_phase = item_phase.strip().lower()
                 if normalized_phase in {"commentary", "analysis"}:
@@ -853,18 +743,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
             message_text = _extract_responses_message_text(item)
             if message_text:
                 content_parts.append(message_text)
-                raw_message_item: Dict[str, Any] = {
-                    "type": "message",
-                    "role": "assistant",
-                    "status": _normalize_responses_message_status(item_status),
-                    "content": [{"type": "output_text", "text": message_text}],
-                }
-                item_id = getattr(item, "id", None)
-                if isinstance(item_id, str) and item_id:
-                    raw_message_item["id"] = item_id
-                if normalized_phase:
-                    raw_message_item["phase"] = normalized_phase
-                message_items_raw.append(raw_message_item)
         elif item_type == "reasoning":
             reasoning_text = _extract_responses_reasoning_text(item)
             if reasoning_text:
@@ -977,7 +855,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
         reasoning_content=None,
         reasoning_details=None,
         codex_reasoning_items=reasoning_items_raw or None,
-        codex_message_items=message_items_raw or None,
     )
 
     if tool_calls:

agent/model_metadata.py

@@ -106,11 +106,9 @@ _endpoint_model_metadata_cache_time: Dict[str, float] = {}
 _ENDPOINT_MODEL_CACHE_TTL = 300
 
 # Descending tiers for context length probing when the model is unknown.
-# We start at 256K (covers GPT-5.x, many current large-context models) and
-# step down on context-length errors until one works.  Tier[0] is also the
-# default fallback when no detection method succeeds.
+# We start at 128K (a safe default for most modern models) and step down
+# on context-length errors until one works.
 CONTEXT_PROBE_TIERS = [
-    256_000,
     128_000,
     64_000,
     32_000,
@@ -145,11 +143,10 @@ DEFAULT_CONTEXT_LENGTHS = {
     "claude": 200000,
     # OpenAI — GPT-5 family (most have 400k; specific overrides first)
     # Source: https://developers.openai.com/api/docs/models
-    # GPT-5.5 (launched Apr 23 2026) is 1.05M on the direct OpenAI API and
-    # ChatGPT Codex OAuth caps it at 272K; both paths resolve via their own
-    # provider-aware branches (_resolve_codex_oauth_context_length + models.dev).
-    # This hardcoded value is only reached when every probe misses.
-    "gpt-5.5": 1050000,
+    # GPT-5.5 (launched Apr 23 2026). 400k is the fallback for providers we
+    # can't probe live. ChatGPT Codex OAuth actually caps lower (272k as of
+    # Apr 2026) and is resolved via _resolve_codex_oauth_context_length().
+    "gpt-5.5": 400000,
     "gpt-5.4-nano": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4-mini": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4": 1050000,               # GPT-5.4, GPT-5.4 Pro (1.05M context)
@@ -165,17 +162,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "gemma-4-31b": 256000,
     "gemma-3": 131072,
     "gemma": 8192,  # fallback for older gemma models
-    # DeepSeek — V4 family ships with a 1M context window. The legacy
-    # aliases ``deepseek-chat`` / ``deepseek-reasoner`` are server-side
-    # mapped to the non-thinking / thinking modes of ``deepseek-v4-flash``
-    # and inherit the same 1M window. The ``deepseek`` substring entry
-    # below remains as a 128K fallback for older / unknown DeepSeek model
-    # ids (e.g. via custom endpoints).
-    # https://api-docs.deepseek.com/zh-cn/quick_start/pricing
-    "deepseek-v4-pro": 1_000_000,
-    "deepseek-v4-flash": 1_000_000,
-    "deepseek-chat": 1_000_000,
-    "deepseek-reasoner": 1_000_000,
+    # DeepSeek
     "deepseek": 128000,
     # Meta
     "llama": 131072,
@@ -1206,7 +1193,6 @@ def get_model_context_length(
     api_key: str = "",
     config_context_length: int | None = None,
     provider: str = "",
-    custom_providers: list | None = None,
 ) -> int:
     """Get the context length for a model.
 
@@ -1227,23 +1213,6 @@ def get_model_context_length(
     if config_context_length is not None and isinstance(config_context_length, int) and config_context_length > 0:
         return config_context_length
 
-    # 0b. custom_providers per-model override — check before any probe.
-    # This closes the gap where /model switch and display paths used to fall
-    # back to 128K despite the user having a per-model context_length set.
-    # See #15779.
-    if custom_providers and base_url and model:
-        try:
-            from hermes_cli.config import get_custom_provider_context_length
-            cp_ctx = get_custom_provider_context_length(
-                model=model,
-                base_url=base_url,
-                custom_providers=custom_providers,
-            )
-            if cp_ctx:
-                return cp_ctx
-        except Exception:
-            pass  # fall through to probing
-
     # Normalise provider-prefixed model names (e.g. "local:model-name" →
     # "model-name") so cache lookups and server queries use the bare ID that
     # local servers actually know about.  Ollama "model:tag" colons are preserved.
@@ -1383,7 +1352,7 @@ def get_model_context_length(
     # 6. OpenRouter live API metadata (provider-unaware fallback)
     metadata = fetch_model_metadata()
     if model in metadata:
-        return metadata[model].get("context_length", DEFAULT_FALLBACK_CONTEXT)
+        return metadata[model].get("context_length", 128000)
 
     # 8. Hardcoded defaults (fuzzy match — longest key first for specificity)
     # Only check `default_model in model` (is the key a substring of the input).

agent/nous_rate_guard.py

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

agent/onboarding.py

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

agent/prompt_builder.py

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

agent/transports/__init__.py

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

agent/transports/chat_completions.py

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

agent/transports/codex.py

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

agent/transports/types.py

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

cli-config.yaml.example

@@ -824,9 +824,7 @@ delegation:
 # Display
 # =============================================================================
 display:
-  # Use compact banner mode (hides the ASCII-art banner, shows a single line).
-  #   true:  Compact single-line banner
-  #   false: Full ASCII banner with tool/skill summary (default)
+  # Use compact banner mode
   compact: false
 
   # Tool progress display level (CLI and gateway)
@@ -840,15 +838,12 @@ display:
   # Gateway-only natural mid-turn assistant updates.
   # When true, completed assistant status messages are sent as separate chat
   # messages. This is independent of tool_progress and gateway streaming.
-  #   true:  Send mid-turn assistant updates as separate messages (default)
-  #   false: Only send the final response
   interim_assistant_messages: true
 
-  # What Enter does when Hermes is already busy (CLI and gateway platforms).
+  # What Enter does when Hermes is already busy in the CLI.
   #   interrupt: Interrupt the current run and redirect Hermes (default)
   #   queue:     Queue your message for the next turn
-  # Ctrl+C (or /stop in gateway) always interrupts regardless of this setting.
-  # Toggle at runtime with /busy_input_mode <interrupt|queue>.
+  # Ctrl+C always interrupts regardless of this setting.
   busy_input_mode: interrupt
 
   # Background process notifications (gateway/messaging only).
@@ -864,22 +859,17 @@ display:
   # Play terminal bell when agent finishes a response.
   # Useful for long-running tasks — your terminal will ding when the agent is done.
   # Works over SSH. Most terminals can be configured to flash the taskbar or play a sound.
-  #   true:  Ring the terminal bell on each response
-  #   false: Silent (default)
   bell_on_complete: false
 
   # Show model reasoning/thinking before each response.
   # When enabled, a dim box shows the model's thought process above the response.
   # Toggle at runtime with /reasoning show or /reasoning hide.
-  #   true:  Show the reasoning box
-  #   false: Hide reasoning (default)
   show_reasoning: false
 
   # Stream tokens to the terminal as they arrive instead of waiting for the
   # full response. The response box opens on first token and text appears
   # line-by-line. Tool calls are still captured silently.
-  #   true:  Stream tokens as they arrive (default)
-  #   false: Wait for the full response before rendering
+  # Stream tokens to the terminal in real-time. Disable to wait for full responses.
   streaming: true
 
   # ───────────────────────────────────────────────────────────────────────────
@@ -889,15 +879,10 @@ display:
   # response box label, and branding text. Change at runtime with /skin <name>.
   #
   # Built-in skins:
-  #   default        — Classic Hermes gold/kawaii
-  #   ares           — Crimson/bronze war-god theme with spinner wings
-  #   mono           — Clean grayscale monochrome
-  #   slate          — Cool blue developer-focused
-  #   daylight       — Bright light-mode theme
-  #   warm-lightmode — Warm paper-tone light-mode theme
-  #   poseidon       — Sea-green/teal Olympian theme
-  #   sisyphus       — Earthy stone-and-moss theme
-  #   charizard      — Fiery orange dragon theme
+  #   default  — Classic Hermes gold/kawaii
+  #   ares     — Crimson/bronze war-god theme with spinner wings
+  #   mono     — Clean grayscale monochrome
+  #   slate    — Cool blue developer-focused
   #
   # Custom skins: drop a YAML file in ~/.hermes/skins/<name>.yaml
   # Schema (all fields optional, missing values inherit from default):

cli.py

@@ -22,7 +22,6 @@ import re
 import concurrent.futures
 import base64
 import atexit
-import errno
 import tempfile
 import time
 import uuid
@@ -417,11 +416,6 @@ def load_cli_config() -> Dict[str, Any]:
             "base_url": "",    # Direct OpenAI-compatible endpoint for subagents
             "api_key": "",     # API key for delegation.base_url (falls back to OPENAI_API_KEY)
         },
-        "onboarding": {
-            # First-touch hint flags (see agent/onboarding.py).  Each hint is
-            # shown once per install then latched here.
-            "seen": {},
-        },
     }
     
     # Track whether the config file explicitly set terminal config.
@@ -5158,29 +5152,27 @@ class HermesCLI:
         _cprint(f"  ✓ Model switched: {result.new_model}")
         _cprint(f"    Provider: {provider_label}")
 
-        # Context: always resolve via the provider-aware chain so Codex OAuth,
-        # Copilot, and Nous-enforced caps win over the raw models.dev entry
-        # (e.g. gpt-5.5 is 1.05M on openai but 272K on Codex OAuth).
         mi = result.model_info
-        try:
-            from hermes_cli.model_switch import resolve_display_context_length
-            ctx = resolve_display_context_length(
-                result.new_model,
-                result.target_provider,
-                base_url=result.base_url or self.base_url or "",
-                api_key=result.api_key or self.api_key or "",
-                model_info=mi,
-            )
-            if ctx:
-                _cprint(f"    Context: {ctx:,} tokens")
-        except Exception:
-            pass
         if mi:
+            if mi.context_window:
+                _cprint(f"    Context: {mi.context_window:,} tokens")
             if mi.max_output:
                 _cprint(f"    Max output: {mi.max_output:,} tokens")
             if mi.has_cost_data():
                 _cprint(f"    Cost: {mi.format_cost()}")
             _cprint(f"    Capabilities: {mi.format_capabilities()}")
+        else:
+            try:
+                from agent.model_metadata import get_model_context_length
+                ctx = get_model_context_length(
+                    result.new_model,
+                    base_url=result.base_url or self.base_url,
+                    api_key=result.api_key or self.api_key,
+                    provider=result.target_provider,
+                )
+                _cprint(f"    Context: {ctx:,} tokens")
+            except Exception:
+                pass
 
         cache_enabled = (
             (base_url_host_matches(result.base_url or "", "openrouter.ai") and "claude" in result.new_model.lower())
@@ -5281,22 +5273,24 @@ class HermesCLI:
         # Parse --provider and --global flags
         model_input, explicit_provider, persist_global = parse_model_flags(raw_args)
 
-        # Load providers for switch_model (picker path needs them below)
         user_provs = None
         custom_provs = None
-        try:
-            from hermes_cli.config import get_compatible_custom_providers, load_config
-            cfg = load_config()
-            user_provs = cfg.get("providers")
-            custom_provs = get_compatible_custom_providers(cfg)
-        except Exception:
-            pass
 
         # No args at all: open prompt_toolkit-native picker modal
         if not model_input and not explicit_provider:
             model_display = self.model or "unknown"
             provider_display = get_label(self.provider) if self.provider else "unknown"
 
+            user_provs = None
+            custom_provs = None
+            try:
+                from hermes_cli.config import get_compatible_custom_providers, load_config
+                cfg = load_config()
+                user_provs = cfg.get("providers")
+                custom_provs = get_compatible_custom_providers(cfg)
+            except Exception:
+                pass
+
             try:
                 providers = list_authenticated_providers(
                     current_provider=self.provider or "",
@@ -5818,28 +5812,7 @@ class HermesCLI:
 
         print(f"(._.) Unknown cron command: {subcommand}")
         print("  Available: list, add, edit, pause, resume, run, remove")
-
-    def _handle_kanban_command(self, cmd: str):
-        """Handle the /kanban command — delegate to the shared kanban CLI.
-
-        The string form passed here is the user's full ``/kanban ...``
-        including the leading slash; we strip it and hand the remainder
-        to ``kanban.run_slash`` which returns a single formatted string.
-        """
-        from hermes_cli.kanban import run_slash
-
-        rest = cmd.strip()
-        if rest.startswith("/"):
-            rest = rest.lstrip("/")
-        if rest.startswith("kanban"):
-            rest = rest[len("kanban"):].lstrip()
-        try:
-            output = run_slash(rest)
-        except Exception as exc:  # pragma: no cover - defensive
-            output = f"(._.) kanban error: {exc}"
-        if output:
-            print(output)
-
+    
     def _handle_skills_command(self, cmd: str):
         """Handle /skills slash command — delegates to hermes_cli.skills_hub."""
         from hermes_cli.skills_hub import handle_skills_slash
@@ -6076,8 +6049,6 @@ class HermesCLI:
             self.save_conversation()
         elif canonical == "cron":
             self._handle_cron_command(cmd_original)
-        elif canonical == "kanban":
-            self._handle_kanban_command(cmd_original)
         elif canonical == "skills":
             with self._busy_command(self._slow_command_status(cmd_original)):
                 self._handle_skills_command(cmd_original)
@@ -6152,6 +6123,8 @@ class HermesCLI:
             self._handle_agents_command()
         elif canonical == "background":
             self._handle_background_command(cmd_original)
+        elif canonical == "btw":
+            self._handle_btw_command(cmd_original)
         elif canonical == "queue":
             # Extract prompt after "/queue " or "/q "
             parts = cmd_original.split(None, 1)
@@ -6438,6 +6411,122 @@ class HermesCLI:
         self._background_tasks[task_id] = thread
         thread.start()
 
+    def _handle_btw_command(self, cmd: str):
+        """Handle /btw <question> — ephemeral side question using session context.
+
+        Snapshots the current conversation history, spawns a no-tools agent in
+        a background thread, and prints the answer without persisting anything
+        to the main session.
+        """
+        parts = cmd.strip().split(maxsplit=1)
+        if len(parts) < 2 or not parts[1].strip():
+            _cprint("  Usage: /btw <question>")
+            _cprint("  Example: /btw what module owns session title sanitization?")
+            _cprint("  Answers using session context. No tools, not persisted.")
+            return
+
+        question = parts[1].strip()
+        task_id = f"btw_{datetime.now().strftime('%H%M%S')}_{uuid.uuid4().hex[:6]}"
+
+        if not self._ensure_runtime_credentials():
+            _cprint("  (>_<) Cannot start /btw: no valid credentials.")
+            return
+
+        turn_route = self._resolve_turn_agent_config(question)
+        history_snapshot = list(self.conversation_history)
+
+        preview = question[:60] + ("..." if len(question) > 60 else "")
+        _cprint(f'  💬 /btw: "{preview}"')
+
+        def run_btw():
+            try:
+                btw_agent = AIAgent(
+                    model=turn_route["model"],
+                    api_key=turn_route["runtime"].get("api_key"),
+                    base_url=turn_route["runtime"].get("base_url"),
+                    provider=turn_route["runtime"].get("provider"),
+                    api_mode=turn_route["runtime"].get("api_mode"),
+                    acp_command=turn_route["runtime"].get("command"),
+                    acp_args=turn_route["runtime"].get("args"),
+                    max_iterations=8,
+                    enabled_toolsets=[],
+                    quiet_mode=True,
+                    verbose_logging=False,
+                    session_id=task_id,
+                    platform="cli",
+                    reasoning_config=self.reasoning_config,
+                    service_tier=self.service_tier,
+                    request_overrides=turn_route.get("request_overrides"),
+                    providers_allowed=self._providers_only,
+                    providers_ignored=self._providers_ignore,
+                    providers_order=self._providers_order,
+                    provider_sort=self._provider_sort,
+                    provider_require_parameters=self._provider_require_params,
+                    provider_data_collection=self._provider_data_collection,
+                    fallback_model=self._fallback_model,
+                    session_db=None,
+                    skip_memory=True,
+                    skip_context_files=True,
+                    persist_session=False,
+                )
+
+                btw_prompt = (
+                    "[Ephemeral /btw side question. Answer using the conversation "
+                    "context. No tools available. Be direct and concise.]\n\n"
+                    + question
+                )
+                result = btw_agent.run_conversation(
+                    user_message=btw_prompt,
+                    conversation_history=history_snapshot,
+                    task_id=task_id,
+                )
+
+                response = (result.get("final_response") or "") if result else ""
+                if not response and result and result.get("error"):
+                    response = f"Error: {result['error']}"
+
+                # TUI refresh before printing
+                if self._app:
+                    self._app.invalidate()
+                    time.sleep(0.05)
+                print()
+
+                if response:
+                    try:
+                        from hermes_cli.skin_engine import get_active_skin
+                        _skin = get_active_skin()
+                        _resp_color = _skin.get_color("response_border", "#4F6D4A")
+                    except Exception:
+                        _resp_color = "#4F6D4A"
+
+                    ChatConsole().print(Panel(
+                        _render_final_assistant_content(response, mode=self.final_response_markdown),
+                        title=f"[{_resp_color} bold]⚕ /btw[/]",
+                        title_align="left",
+                        border_style=_resp_color,
+                        box=rich_box.HORIZONTALS,
+                        padding=(1, 4),
+                    ))
+                else:
+                    _cprint("  💬 /btw: (no response)")
+
+                if self.bell_on_complete:
+                    sys.stdout.write("\a")
+                    sys.stdout.flush()
+
+            except Exception as e:
+                if self._app:
+                    self._app.invalidate()
+                    time.sleep(0.05)
+                print()
+                _cprint(f"  ❌ /btw failed: {e}")
+            finally:
+                if self._app:
+                    self._invalidate(min_interval=0)
+
+        thread = threading.Thread(target=run_btw, daemon=True, name=f"btw-{task_id}")
+        thread.start()
+
     @staticmethod
     def _try_launch_chrome_debug(port: int, system: str) -> bool:
         """Try to launch Chrome/Chromium with remote debugging enabled.
@@ -7322,31 +7411,6 @@ class HermesCLI:
                     _cprint(f"  {line}")
                 except Exception:
                     pass
-                # First-touch onboarding: on the first tool in this process
-                # that takes longer than the threshold while we're in the
-                # noisiest progress mode, print a one-time hint about
-                # /verbose.  Latched on self so it fires at most once per
-                # process; persisted to config.yaml so it never fires again
-                # across processes either.
-                try:
-                    if (
-                        not getattr(self, "_long_tool_hint_fired", False)
-                        and self.tool_progress_mode == "all"
-                        and duration >= 30.0
-                    ):
-                        from agent.onboarding import (
-                            TOOL_PROGRESS_FLAG,
-                            is_seen,
-                            mark_seen,
-                            tool_progress_hint_cli,
-                        )
-                        if not is_seen(CLI_CONFIG, TOOL_PROGRESS_FLAG):
-                            self._long_tool_hint_fired = True
-                            _cprint(f"  {_DIM}{tool_progress_hint_cli()}{_RST}")
-                            mark_seen(_hermes_home / "config.yaml", TOOL_PROGRESS_FLAG)
-                            CLI_CONFIG.setdefault("onboarding", {}).setdefault("seen", {})[TOOL_PROGRESS_FLAG] = True
-                except Exception:
-                    pass
             self._invalidate()
             return
         if event_type != "tool.started":
@@ -9230,24 +9294,6 @@ class HermesCLI:
                                          f"agent_running={self._agent_running}\n")
                         except Exception:
                             pass
-                    # First-touch onboarding: on the very first busy-while-running
-                    # event for this install, print a one-line tip explaining the
-                    # /busy knob.  Flag persists to config.yaml and never fires
-                    # again.  Guarded for exceptions so onboarding can't break
-                    # the input loop.
-                    try:
-                        from agent.onboarding import (
-                            BUSY_INPUT_FLAG,
-                            busy_input_hint_cli,
-                            is_seen,
-                            mark_seen,
-                        )
-                        if not is_seen(CLI_CONFIG, BUSY_INPUT_FLAG):
-                            _cprint(f"  {_DIM}{busy_input_hint_cli(self.busy_input_mode)}{_RST}")
-                            mark_seen(_hermes_home / "config.yaml", BUSY_INPUT_FLAG)
-                            CLI_CONFIG.setdefault("onboarding", {}).setdefault("seen", {})[BUSY_INPUT_FLAG] = True
-                    except Exception:
-                        pass
                 else:
                     self._pending_input.put(payload)
                 event.app.current_buffer.reset(append_to_history=True)
@@ -10694,8 +10740,6 @@ class HermesCLI:
                 return  # silently suppress
             if isinstance(exc, KeyError) and "is not registered" in str(exc):
                 return  # suppress selector registration failures (#6393)
-            if isinstance(exc, OSError) and getattr(exc, "errno", None) == errno.EIO:
-                return  # suppress I/O errors from broken stdout on interrupt (#13710)
             # Fall back to default handler for everything else
             loop.default_exception_handler(context)
 
@@ -10728,11 +10772,9 @@ class HermesCLI:
         except (EOFError, KeyboardInterrupt, BrokenPipeError):
             pass
         except (KeyError, OSError) as _stdin_err:
-            # Catch selector registration failures from broken stdin (#6393)
-            # and I/O errors from broken stdout during interrupt (#13710).
-            if isinstance(_stdin_err, OSError) and getattr(_stdin_err, "errno", None) == errno.EIO:
-                pass  # suppress broken-stdout I/O errors on interrupt (#13710)
-            elif "is not registered" in str(_stdin_err) or "Bad file descriptor" in str(_stdin_err):
+            # Catch selector registration failures from broken stdin (#6393).
+            # This is the fallback for cases that slip past the fstat() guard.
+            if "is not registered" in str(_stdin_err) or "Bad file descriptor" in str(_stdin_err):
                 print(
                     f"\nError: stdin is not usable ({_stdin_err}).\n"
                     "This can happen with certain Python installations (e.g. uv-managed cPython on macOS).\n"

docker/entrypoint.sh

@@ -41,15 +41,6 @@ if [ "$(id -u)" = "0" ]; then
             echo "Warning: chown failed (rootless container?) — continuing anyway"
     fi
 
-    # Ensure config.yaml is readable by the hermes runtime user even if it was
-    # edited on the host after initial ownership setup. Must run here (as root)
-    # rather than after the gosu drop, otherwise a non-root caller like
-    # `docker run -u $(id -u):$(id -g)` hits "Operation not permitted" (#15865).
-    if [ -f "$HERMES_HOME/config.yaml" ]; then
-        chown hermes:hermes "$HERMES_HOME/config.yaml" 2>/dev/null || true
-        chmod 640 "$HERMES_HOME/config.yaml" 2>/dev/null || true
-    fi
-
     echo "Dropping root privileges"
     exec gosu hermes "$0" "$@"
 fi
@@ -76,6 +67,13 @@ if [ ! -f "$HERMES_HOME/config.yaml" ]; then
     cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
 fi
 
+# Ensure the main config file remains accessible to the hermes runtime user
+# even if it was edited on the host after initial ownership setup.
+if [ -f "$HERMES_HOME/config.yaml" ]; then
+    chown hermes:hermes "$HERMES_HOME/config.yaml"
+    chmod 640 "$HERMES_HOME/config.yaml"
+fi
+
 # SOUL.md
 if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
     cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"

gateway/hooks.py

@@ -21,7 +21,6 @@ Errors in hooks are caught and logged but never block the main pipeline.
 
 import asyncio
 import importlib.util
-import sys
 from typing import Any, Callable, Dict, List, Optional
 
 import yaml
@@ -104,28 +103,16 @@ class HookRegistry:
                     print(f"[hooks] Skipping {hook_name}: no events declared", flush=True)
                     continue
 
-                # Dynamically load the handler module.
-                # Register in sys.modules BEFORE exec_module so Pydantic /
-                # dataclasses / typing introspection can resolve forward
-                # references (triggered by `from __future__ import annotations`
-                # in the handler). Without this, a handler that declares a
-                # Pydantic BaseModel for webhook/event payloads fails at first
-                # dispatch with "TypeAdapter ... is not fully defined".
-                module_name = f"hermes_hook_{hook_name}"
+                # Dynamically load the handler module
                 spec = importlib.util.spec_from_file_location(
-                    module_name, handler_path
+                    f"hermes_hook_{hook_name}", handler_path
                 )
                 if spec is None or spec.loader is None:
                     print(f"[hooks] Skipping {hook_name}: could not load handler.py", flush=True)
                     continue
 
                 module = importlib.util.module_from_spec(spec)
-                sys.modules[module_name] = module
-                try:
-                    spec.loader.exec_module(module)
-                except Exception:
-                    sys.modules.pop(module_name, None)
-                    raise
+                spec.loader.exec_module(module)
 
                 handle_fn = getattr(module, "handle", None)
                 if handle_fn is None:

gateway/platforms/api_server.py

@@ -9,7 +9,6 @@ Exposes an HTTP server with endpoints:
 - GET  /v1/models                  — lists hermes-agent as an available model
 - POST /v1/runs                    — start a run, returns run_id immediately (202)
 - GET  /v1/runs/{run_id}/events    — SSE stream of structured lifecycle events
-- POST /v1/runs/{run_id}/stop    — interrupt a running agent
 - GET  /health                     — health check
 - GET  /health/detailed            — rich status for cross-container dashboard probing
 
@@ -587,9 +586,6 @@ class APIServerAdapter(BasePlatformAdapter):
         self._run_streams: Dict[str, "asyncio.Queue[Optional[Dict]]"] = {}
         # Creation timestamps for orphaned-run TTL sweep
         self._run_streams_created: Dict[str, float] = {}
-        # Active run agent/task references for stop support
-        self._active_run_agents: Dict[str, Any] = {}
-        self._active_run_tasks: Dict[str, "asyncio.Task"] = {}
         self._session_db: Optional[Any] = None  # Lazy-init SessionDB for session continuity
 
     @staticmethod
@@ -2445,7 +2441,6 @@ class APIServerAdapter(BasePlatformAdapter):
                     stream_delta_callback=_text_cb,
                     tool_progress_callback=event_cb,
                 )
-                self._active_run_agents[run_id] = agent
                 def _run_sync():
                     r = agent.run_conversation(
                         user_message=user_message,
@@ -2485,11 +2480,8 @@ class APIServerAdapter(BasePlatformAdapter):
                     q.put_nowait(None)
                 except Exception:
                     pass
-                self._active_run_agents.pop(run_id, None)
-                self._active_run_tasks.pop(run_id, None)
 
         task = asyncio.create_task(_run_and_close())
-        self._active_run_tasks[run_id] = task
         try:
             self._background_tasks.add(task)
         except TypeError:
@@ -2548,44 +2540,6 @@ class APIServerAdapter(BasePlatformAdapter):
 
         return response
 
-    async def _handle_stop_run(self, request: "web.Request") -> "web.Response":
-        """POST /v1/runs/{run_id}/stop — interrupt a running agent."""
-        auth_err = self._check_auth(request)
-        if auth_err:
-            return auth_err
-
-        run_id = request.match_info["run_id"]
-        agent = self._active_run_agents.get(run_id)
-        task = self._active_run_tasks.get(run_id)
-
-        if agent is None and task is None:
-            return web.json_response(_openai_error(f"Run not found: {run_id}", code="run_not_found"), status=404)
-
-        if agent is not None:
-            try:
-                agent.interrupt("Stop requested via API")
-            except Exception:
-                pass
-
-        if task is not None and not task.done():
-            task.cancel()
-            # Bounded wait: run_conversation() executes in the default
-            # executor thread which task.cancel() cannot preempt — we rely on
-            # agent.interrupt() above to break the loop. Cap the wait so a
-            # slow/unresponsive interrupt can't hang this handler.
-            try:
-                await asyncio.wait_for(asyncio.shield(task), timeout=5.0)
-            except asyncio.TimeoutError:
-                logger.warning(
-                    "[api_server] stop for run %s timed out after 5s; "
-                    "agent may still be finishing the current step",
-                    run_id,
-                )
-            except (asyncio.CancelledError, Exception):
-                pass
-
-        return web.json_response({"run_id": run_id, "status": "stopping"})
-
     async def _sweep_orphaned_runs(self) -> None:
         """Periodically clean up run streams that were never consumed."""
         while True:
@@ -2600,8 +2554,6 @@ class APIServerAdapter(BasePlatformAdapter):
                 logger.debug("[api_server] sweeping orphaned run %s", run_id)
                 self._run_streams.pop(run_id, None)
                 self._run_streams_created.pop(run_id, None)
-                self._active_run_agents.pop(run_id, None)
-                self._active_run_tasks.pop(run_id, None)
 
     # ------------------------------------------------------------------
     # BasePlatformAdapter interface
@@ -2637,7 +2589,6 @@ class APIServerAdapter(BasePlatformAdapter):
             # Structured event streaming
             self._app.router.add_post("/v1/runs", self._handle_runs)
             self._app.router.add_get("/v1/runs/{run_id}/events", self._handle_run_events)
-            self._app.router.add_post("/v1/runs/{run_id}/stop", self._handle_stop_run)
             # Start background sweep to clean up orphaned (unconsumed) run streams
             sweep_task = asyncio.create_task(self._sweep_orphaned_runs())
             try:

gateway/platforms/base.py

@@ -1025,20 +1025,7 @@ class BasePlatformAdapter(ABC):
         self._post_delivery_callbacks: Dict[str, Any] = {}
         self._expected_cancelled_tasks: set[asyncio.Task] = set()
         self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
-        # Auto-TTS on voice input: ``_auto_tts_default`` is the global default
-        # (``voice.auto_tts`` in config.yaml, pushed by GatewayRunner on connect).
-        # Per-chat overrides live in two sets populated from ``_voice_mode``:
-        #   - ``_auto_tts_enabled_chats``: chat explicitly opted in via ``/voice on``
-        #     or ``/voice tts`` (mode is ``voice_only`` or ``all``). Fires even when
-        #     the global default is False.
-        #   - ``_auto_tts_disabled_chats``: chat explicitly opted out via
-        #     ``/voice off`` (mode is ``off``). Suppresses auto-TTS even when the
-        #     global default is True.
-        # The gate in _process_message() is:
-        #   fire if chat in _auto_tts_enabled_chats
-        #     OR (_auto_tts_default and chat not in _auto_tts_disabled_chats)
-        self._auto_tts_default: bool = False
-        self._auto_tts_enabled_chats: set = set()
+        # Chats where auto-TTS on voice input is disabled (set by /voice off)
         self._auto_tts_disabled_chats: set = set()
         # Chats where typing indicator is paused (e.g. during approval waits).
         # _keep_typing skips send_typing when the chat_id is in this set.
@@ -1060,21 +1047,6 @@ class BasePlatformAdapter(ABC):
     def fatal_error_retryable(self) -> bool:
         return self._fatal_error_retryable
 
-    def _should_auto_tts_for_chat(self, chat_id: str) -> bool:
-        """Whether auto-TTS on voice input should fire for ``chat_id``.
-
-        Decision layers (Issue #16007):
-          1. Explicit ``/voice on`` or ``/voice tts`` → always fire (even if
-             ``voice.auto_tts`` is False).
-          2. Explicit ``/voice off`` → never fire.
-          3. Fall back to the global ``voice.auto_tts`` config default.
-        """
-        if chat_id in self._auto_tts_enabled_chats:
-            return True
-        if chat_id in self._auto_tts_disabled_chats:
-            return False
-        return bool(self._auto_tts_default)
-
     def set_fatal_error_handler(self, handler: Callable[["BasePlatformAdapter"], Awaitable[None] | None]) -> None:
         self._fatal_error_handler = handler
 
@@ -2242,14 +2214,12 @@ class BasePlatformAdapter(ABC):
                     logger.info("[%s] extract_local_files found %d file(s) in response", self.name, len(local_files))
                 
                 # Auto-TTS: if voice message, generate audio FIRST (before sending text)
-                # Gated via ``_should_auto_tts_for_chat``: fires when the chat has
-                # an explicit ``/voice on|tts`` opt-in OR when ``voice.auto_tts`` is
-                # True globally and no ``/voice off`` has been issued.
+                # Skipped when the chat has voice mode disabled (/voice off)
                 _tts_path = None
-                if (self._should_auto_tts_for_chat(event.source.chat_id)
-                        and event.message_type == MessageType.VOICE
+                if (event.message_type == MessageType.VOICE
                         and text_content
-                        and not media_files):
+                        and not media_files
+                        and event.source.chat_id not in self._auto_tts_disabled_chats):
                     try:
                         from tools.tts_tool import text_to_speech_tool, check_tts_requirements
                         if check_tts_requirements():

gateway/platforms/discord.py

@@ -2315,6 +2315,11 @@ class DiscordAdapter(BasePlatformAdapter):
         async def slash_background(interaction: discord.Interaction, prompt: str):
             await self._run_simple_slash(interaction, f"/background {prompt}", "Background task started~")
 
+        @tree.command(name="btw", description="Ephemeral side question using session context")
+        @discord.app_commands.describe(question="Your side question (no tools, not persisted)")
+        async def slash_btw(interaction: discord.Interaction, question: str):
+            await self._run_simple_slash(interaction, f"/btw {question}")
+
         # ── Auto-register any gateway-available commands not yet on the tree ──
         # This ensures new commands added to COMMAND_REGISTRY in
         # hermes_cli/commands.py automatically appear as Discord slash

gateway/session.py

@@ -1232,7 +1232,6 @@ class SessionStore:
                     reasoning_content=message.get("reasoning_content") if message.get("role") == "assistant" else None,
                     reasoning_details=message.get("reasoning_details") if message.get("role") == "assistant" else None,
                     codex_reasoning_items=message.get("codex_reasoning_items") if message.get("role") == "assistant" else None,
-                    codex_message_items=message.get("codex_message_items") if message.get("role") == "assistant" else None,
                 )
             except Exception as e:
                 logger.debug("Session DB operation failed: %s", e)
@@ -1265,7 +1264,6 @@ class SessionStore:
                         reasoning_content=msg.get("reasoning_content") if role == "assistant" else None,
                         reasoning_details=msg.get("reasoning_details") if role == "assistant" else None,
                         codex_reasoning_items=msg.get("codex_reasoning_items") if role == "assistant" else None,
-                        codex_message_items=msg.get("codex_message_items") if role == "assistant" else None,
                     )
             except Exception as e:
                 logger.debug("Failed to rewrite transcript in DB: %s", e)

hermes_cli/auth.py

@@ -356,14 +356,6 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=(),
         base_url_env_var="BEDROCK_BASE_URL",
     ),
-    "azure-foundry": ProviderConfig(
-        id="azure-foundry",
-        name="Azure Foundry",
-        auth_type="api_key",
-        inference_base_url="",  # User-provided endpoint
-        api_key_env_vars=("AZURE_FOUNDRY_API_KEY",),
-        base_url_env_var="AZURE_FOUNDRY_BASE_URL",
-    ),
 }
 
 
@@ -4244,10 +4236,10 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
                 )
 
             from hermes_cli.models import (
-                get_curated_nous_model_ids, get_pricing_for_provider,
+                _PROVIDER_MODELS, get_pricing_for_provider,
                 check_nous_free_tier, partition_nous_models_by_tier,
             )
-            model_ids = get_curated_nous_model_ids()
+            model_ids = _PROVIDER_MODELS.get("nous", [])
 
             print()
             unavailable_models: list = []

hermes_cli/azure_detect.py

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

hermes_cli/commands.py

@@ -84,7 +84,9 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("deny", "Deny a pending dangerous command", "Session",
                gateway_only=True),
     CommandDef("background", "Run a prompt in the background", "Session",
-               aliases=("bg", "btw"), args_hint="<prompt>"),
+               aliases=("bg",), args_hint="<prompt>"),
+    CommandDef("btw", "Ephemeral side question using session context (no tools, not persisted)", "Session",
+               args_hint="<question>"),
     CommandDef("agents", "Show active agents and running tasks", "Session",
                aliases=("tasks",)),
     CommandDef("queue", "Queue a prompt for the next turn (doesn't interrupt)", "Session",
@@ -140,11 +142,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("cron", "Manage scheduled tasks", "Tools & Skills",
                cli_only=True, args_hint="[subcommand]",
                subcommands=("list", "add", "create", "edit", "pause", "resume", "run", "remove")),
-    CommandDef("kanban", "Multi-profile collaboration board (tasks, links, comments)",
-               "Tools & Skills", args_hint="[subcommand]",
-               subcommands=("list", "ls", "show", "create", "assign", "link", "unlink",
-                            "claim", "comment", "complete", "block", "unblock", "archive",
-                            "tail", "dispatch", "context", "init", "gc")),
     CommandDef("reload", "Reload .env variables into the running session", "Tools & Skills",
                cli_only=True),
     CommandDef("reload-mcp", "Reload MCP servers from config", "Tools & Skills",

hermes_cli/config.py

@@ -959,27 +959,6 @@ DEFAULT_CONFIG = {
         "backup_count": 3,     # Number of rotated backup files to keep
     },
 
-    # Remotely-hosted model catalog manifest.  When enabled, the CLI fetches
-    # curated model lists for OpenRouter and Nous Portal from this URL,
-    # falling back to the in-repo snapshot on network failure.  Lets us
-    # update model picker lists without shipping a hermes-agent release.
-    # The default URL is served by the docs site GitHub Pages deploy.
-    "model_catalog": {
-        "enabled": True,
-        "url": "https://hermes-agent.nousresearch.com/docs/api/model-catalog.json",
-        # Disk cache TTL in hours.  Beyond this, the CLI refetches on the
-        # next /model or `hermes model` invocation; network failures
-        # silently fall back to the stale cache.
-        "ttl_hours": 24,
-        # Optional per-provider override URLs for third parties that want
-        # to self-host their own curation list using the same schema.
-        # Example:
-        #   providers:
-        #     openrouter:
-        #       url: https://example.com/my-curation.json
-        "providers": {},
-    },
-
     # Network settings — workarounds for connectivity issues.
     "network": {
         # Force IPv4 connections.  On servers with broken or unreachable IPv6,
@@ -1016,13 +995,6 @@ DEFAULT_CONFIG = {
         "min_interval_hours": 24,
     },
 
-    # Contextual first-touch onboarding hints (see agent/onboarding.py).
-    # Each hint is shown once per install and then latched here so it
-    # never fires again.  Users can wipe the section to re-see all hints.
-    "onboarding": {
-        "seen": {},
-    },
-
     # Config schema version - bump this when adding new required fields
     "_config_version": 22,
 }
@@ -1399,21 +1371,6 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
-    "AZURE_FOUNDRY_API_KEY": {
-        "description": "Azure Foundry API key for custom Azure endpoints",
-        "prompt": "Azure Foundry API Key",
-        "url": "https://ai.azure.com/",
-        "password": True,
-        "category": "provider",
-    },
-    "AZURE_FOUNDRY_BASE_URL": {
-        "description": "Azure Foundry base URL (set via 'hermes model' for endpoint-specific config)",
-        "prompt": "Azure Foundry base URL",
-        "url": None,
-        "password": False,
-        "category": "provider",
-        "advanced": True,
-    },
 
     # ── Tool API keys ──
     "EXA_API_KEY": {
@@ -2249,71 +2206,6 @@ def get_compatible_custom_providers(
     return compatible
 
 
-def get_custom_provider_context_length(
-    model: str,
-    base_url: str,
-    custom_providers: Optional[List[Dict[str, Any]]] = None,
-    config: Optional[Dict[str, Any]] = None,
-) -> Optional[int]:
-    """Look up a per-model ``context_length`` override from ``custom_providers``.
-
-    Matches any entry whose ``base_url`` equals ``base_url`` (trailing-slash
-    insensitive) and returns ``custom_providers[i].models.<model>.context_length``
-    if present and valid.  Returns ``None`` when no override applies.
-
-    This is the single source of truth for custom-provider context overrides,
-    used by:
-      * ``AIAgent.__init__`` (startup resolution)
-      * ``AIAgent.switch_model`` (mid-session ``/model`` switch)
-      * ``hermes_cli.model_switch.resolve_display_context_length`` (``/model`` confirmation display)
-      * ``gateway.run._format_session_info`` (``/info`` display)
-      * ``agent.model_metadata.get_model_context_length`` (when custom_providers is threaded through)
-
-    Before this helper existed, the lookup was duplicated in ``run_agent.py``'s
-    startup path only; every other path (notably ``/model`` switch) fell back
-    to the 128K default.  See #15779.
-    """
-    if not model or not base_url:
-        return None
-    if custom_providers is None:
-        try:
-            custom_providers = get_compatible_custom_providers(config)
-        except Exception:
-            if config is None:
-                return None
-            raw = config.get("custom_providers")
-            custom_providers = raw if isinstance(raw, list) else []
-    if not isinstance(custom_providers, list):
-        return None
-
-    target_url = (base_url or "").rstrip("/")
-    if not target_url:
-        return None
-
-    for entry in custom_providers:
-        if not isinstance(entry, dict):
-            continue
-        entry_url = (entry.get("base_url") or "").rstrip("/")
-        if not entry_url or entry_url != target_url:
-            continue
-        models = entry.get("models")
-        if not isinstance(models, dict):
-            continue
-        model_cfg = models.get(model)
-        if not isinstance(model_cfg, dict):
-            continue
-        raw_ctx = model_cfg.get("context_length")
-        if raw_ctx is None:
-            continue
-        try:
-            ctx = int(raw_ctx)
-        except (TypeError, ValueError):
-            continue
-        if ctx > 0:
-            return ctx
-    return None
-
-
 def check_config_version() -> Tuple[int, int]:
     """
     Check config version.

hermes_cli/doctor.py

@@ -320,11 +320,7 @@ def run_doctor(args):
                     known_providers.add("custom:" + name.lower().replace(" ", "-"))
 
             canonical_provider = provider
-            if (
-                provider
-                and _resolve_provider_full is not None
-                and provider not in ("auto", "custom")
-            ):
+            if provider and _resolve_provider_full is not None and provider != "auto":
                 provider_def = _resolve_provider_full(provider, user_providers, custom_providers)
                 canonical_provider = provider_def.id if provider_def is not None else None
 

hermes_cli/fallback_cmd.py

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

hermes_cli/hooks.py

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

hermes_cli/main.py

@@ -1527,83 +1527,6 @@ def select_provider_and_model(args=None):
     all_providers = [(p.slug, p.tui_desc) for p in CANONICAL_PROVIDERS]
 
     def _named_custom_provider_map(cfg) -> dict[str, dict[str, str]]:
-        from hermes_cli.config import read_raw_config
-
-        # Build a lookup of raw (un-expanded) api_key templates keyed by a
-        # stable identity. We intentionally bypass
-        # ``get_compatible_custom_providers(read_raw_config())`` here because
-        # its ``_normalize_custom_provider_entry`` step calls ``urlparse()``
-        # on ``base_url`` and drops any entry whose ``base_url`` is itself an
-        # env-ref template (e.g. ``${NEURALWATT_API_BASE}``). Dropping those
-        # entries is exactly how env-ref preservation fails for the user
-        # config that motivated this fix.
-        raw_api_key_refs: dict[tuple, str] = {}
-        raw_cfg = read_raw_config()
-
-        def _record_raw(
-            name: str,
-            provider_key: str,
-            model: str,
-            api_key: str,
-        ) -> None:
-            template = str(api_key or "").strip()
-            if "${" not in template:
-                return
-            name = str(name or "").strip()
-            provider_key = str(provider_key or "").strip()
-            model = str(model or "").strip()
-            # Index by every plausible identity the loaded (expanded) config
-            # might present: (name), (name, model), (provider_key), and
-            # (provider_key, model). Case-insensitive on name/provider_key so
-            # the loaded entry matches regardless of display casing.
-            if name:
-                raw_api_key_refs.setdefault((name.lower(),), template)
-                raw_api_key_refs.setdefault((name.lower(), model), template)
-            if provider_key:
-                raw_api_key_refs.setdefault((provider_key.lower(),), template)
-                raw_api_key_refs.setdefault(
-                    (provider_key.lower(), model), template
-                )
-
-        raw_list = raw_cfg.get("custom_providers")
-        if isinstance(raw_list, list):
-            for raw_entry in raw_list:
-                if not isinstance(raw_entry, dict):
-                    continue
-                _record_raw(
-                    raw_entry.get("name", ""),
-                    "",
-                    raw_entry.get("model", "")
-                    or raw_entry.get("default_model", ""),
-                    raw_entry.get("api_key", ""),
-                )
-        raw_providers = raw_cfg.get("providers")
-        if isinstance(raw_providers, dict):
-            for raw_key, raw_entry in raw_providers.items():
-                if not isinstance(raw_entry, dict):
-                    continue
-                _record_raw(
-                    raw_entry.get("name", "") or raw_key,
-                    raw_key,
-                    raw_entry.get("model", "")
-                    or raw_entry.get("default_model", ""),
-                    raw_entry.get("api_key", ""),
-                )
-
-        def _lookup_ref(name: str, provider_key: str, model: str) -> str:
-            name_lc = str(name or "").strip().lower()
-            pkey_lc = str(provider_key or "").strip().lower()
-            model = str(model or "").strip()
-            for identity in (
-                (pkey_lc, model),
-                (pkey_lc,),
-                (name_lc, model),
-                (name_lc,),
-            ):
-                if identity[0] and identity in raw_api_key_refs:
-                    return raw_api_key_refs[identity]
-            return ""
-
         custom_provider_map = {}
         for entry in get_compatible_custom_providers(cfg):
             if not isinstance(entry, dict):
@@ -1627,9 +1550,6 @@ def select_provider_and_model(args=None):
                 "model": entry.get("model", ""),
                 "api_mode": entry.get("api_mode", ""),
                 "provider_key": provider_key,
-                "api_key_ref": _lookup_ref(
-                    name, provider_key, entry.get("model", "")
-                ),
             }
         return custom_provider_map
 
@@ -1719,8 +1639,6 @@ def select_provider_and_model(args=None):
         _model_flow_stepfun(config, current_model)
     elif selected_provider == "bedrock":
         _model_flow_bedrock(config, current_model)
-    elif selected_provider == "azure-foundry":
-        _model_flow_azure_foundry(config, current_model)
     elif selected_provider in (
         "gemini",
         "deepseek",
@@ -2315,13 +2233,13 @@ def _model_flow_nous(config, current_model="", args=None):
     # The live /models endpoint returns hundreds of models; the curated list
     # shows only agentic models users recognize from OpenRouter.
     from hermes_cli.models import (
-        get_curated_nous_model_ids,
+        _PROVIDER_MODELS,
         get_pricing_for_provider,
         check_nous_free_tier,
         partition_nous_models_by_tier,
     )
 
-    model_ids = get_curated_nous_model_ids()
+    model_ids = _PROVIDER_MODELS.get("nous", [])
     if not model_ids:
         print("No curated models available for Nous Portal.")
         return
@@ -2864,19 +2782,6 @@ def _auto_provider_name(base_url: str) -> str:
     return name
 
 
-def _custom_provider_api_key_config_value(provider_info, resolved_api_key=""):
-    """Return the value that should be persisted for a custom provider key."""
-    api_key_ref = str(provider_info.get("api_key_ref", "") or "").strip()
-    if api_key_ref:
-        return api_key_ref
-
-    key_env = str(provider_info.get("key_env", "") or "").strip()
-    if key_env and not str(provider_info.get("api_key", "") or "").strip():
-        return f"${{{key_env}}}"
-
-    return str(resolved_api_key or "").strip()
-
-
 def _save_custom_provider(
     base_url, api_key="", model="", context_length=None, name=None
 ):
@@ -2932,203 +2837,6 @@ def _save_custom_provider(
     print(f'  💾 Saved to custom providers as "{name}" (edit in config.yaml)')
 
 
-def _model_flow_azure_foundry(config, current_model=""):
-    """Azure Foundry provider: configure endpoint, API mode, API key, and model.
-
-    Azure Foundry supports both OpenAI-style (``/v1/chat/completions``) and
-    Anthropic-style (``/v1/messages``) endpoints.  The wizard auto-detects
-    the transport and available models when possible:
-
-    * URLs ending in ``/anthropic`` → Anthropic Messages API.
-    * Successful ``GET <base>/models`` probe → OpenAI-style + populates
-      a picker with the returned deployment / model IDs.
-    * Anthropic Messages probe fallback when ``/models`` fails.
-    * Manual entry when every probe fails (private endpoints, etc.).
-
-    Context lengths for the chosen model are resolved via the standard
-    :func:`agent.model_metadata.get_model_context_length` chain
-    (models.dev, provider metadata, hardcoded family fallbacks).
-    """
-    from hermes_cli.auth import _save_model_choice, deactivate_provider  # noqa: F401
-    from hermes_cli.config import get_env_value, save_env_value, load_config, save_config
-    from hermes_cli import azure_detect
-    import getpass
-
-    # ── Load current Azure Foundry configuration ─────────────────────
-    model_cfg = config.get("model", {})
-    if isinstance(model_cfg, dict) and model_cfg.get("provider") == "azure-foundry":
-        current_base_url = str(model_cfg.get("base_url", "") or "")
-        current_api_mode = str(model_cfg.get("api_mode", "") or "")
-    else:
-        current_base_url = ""
-        current_api_mode = ""
-
-    current_api_key = get_env_value("AZURE_FOUNDRY_API_KEY") or ""
-
-    print()
-    print("Azure Foundry Configuration")
-    print("=" * 50)
-    print()
-    print("Azure Foundry can host models with either OpenAI-style or")
-    print("Anthropic-style API endpoints.  Hermes will probe your")
-    print("endpoint to auto-detect the transport and the deployed")
-    print("models when possible.")
-    print()
-
-    if current_base_url:
-        print(f"  Current endpoint: {current_base_url}")
-    if current_api_mode:
-        _lbl = "OpenAI-style" if current_api_mode == "chat_completions" else "Anthropic-style"
-        print(f"  Current API mode: {_lbl}")
-    if current_api_key:
-        print(f"  Current API key:  {current_api_key[:8]}...")
-    print()
-
-    # ── Step 1: endpoint URL ─────────────────────────────────────────
-    try:
-        base_url = input(
-            f"API endpoint URL [{current_base_url or 'e.g. https://your-resource.openai.azure.com/openai/v1'}]: "
-        ).strip()
-    except (KeyboardInterrupt, EOFError):
-        print("\nCancelled.")
-        return
-
-    effective_url = (base_url or current_base_url).rstrip("/")
-    if not effective_url:
-        print("No endpoint URL provided. Cancelled.")
-        return
-    if not effective_url.startswith(("http://", "https://")):
-        print(f"Invalid URL: {effective_url} (must start with http:// or https://)")
-        return
-
-    # ── Step 2: API key ──────────────────────────────────────────────
-    print()
-    try:
-        api_key = getpass.getpass(
-            f"API key [{current_api_key[:8] + '...' if current_api_key else 'required'}]: "
-        ).strip()
-    except (KeyboardInterrupt, EOFError):
-        print("\nCancelled.")
-        return
-
-    effective_key = api_key or current_api_key
-    if not effective_key:
-        print("No API key provided. Cancelled.")
-        return
-
-    # ── Step 3: auto-detect transport + models ───────────────────────
-    print()
-    print("◐ Probing endpoint to auto-detect transport and models...")
-    detection = azure_detect.detect(effective_url, effective_key)
-
-    discovered_models: list[str] = list(detection.models)
-    api_mode: str = detection.api_mode or ""
-
-    if api_mode:
-        mode_label = "OpenAI-style" if api_mode == "chat_completions" else "Anthropic-style"
-        print(f"✓ Detected API transport: {mode_label}")
-        if detection.reason:
-            print(f"    ({detection.reason})")
-        if discovered_models:
-            print(f"✓ Found {len(discovered_models)} deployed model(s) on this endpoint")
-    else:
-        print(f"⚠ Auto-detection incomplete: {detection.reason}")
-        print()
-        print("Select the API format your Azure Foundry endpoint uses:")
-        print("  1. OpenAI-style  (POST /v1/chat/completions)")
-        print("     For: GPT models, Llama, Mistral, and most open models")
-        print("  2. Anthropic-style  (POST /v1/messages)")
-        print("     For: Claude models deployed via Anthropic API format")
-        try:
-            default_choice = "2" if current_api_mode == "anthropic_messages" else "1"
-            mode_choice = input(f"API format [1/2] ({default_choice}): ").strip() or default_choice
-        except (KeyboardInterrupt, EOFError):
-            print("\nCancelled.")
-            return
-        api_mode = "anthropic_messages" if mode_choice == "2" else "chat_completions"
-
-    # ── Step 4: model name ───────────────────────────────────────────
-    print()
-    effective_model = ""
-    if discovered_models:
-        print("Available models on this endpoint:")
-        for i, mid in enumerate(discovered_models[:30], start=1):
-            print(f"  {i:>2}. {mid}")
-        if len(discovered_models) > 30:
-            print(f"  ... and {len(discovered_models) - 30} more (type name manually if not shown)")
-        print()
-        try:
-            pick = input(
-                f"Pick by number, or type a deployment name [{current_model or discovered_models[0]}]: "
-            ).strip()
-        except (KeyboardInterrupt, EOFError):
-            print("\nCancelled.")
-            return
-        if not pick:
-            effective_model = current_model or discovered_models[0]
-        elif pick.isdigit() and 1 <= int(pick) <= min(len(discovered_models), 30):
-            effective_model = discovered_models[int(pick) - 1]
-        else:
-            effective_model = pick
-    else:
-        try:
-            model_name = input(
-                f"Model / deployment name [{current_model or 'e.g. gpt-5.4, claude-sonnet-4-6'}]: "
-            ).strip()
-        except (KeyboardInterrupt, EOFError):
-            print("\nCancelled.")
-            return
-        effective_model = model_name or current_model
-
-    if not effective_model:
-        print("No model name provided. Cancelled.")
-        return
-
-    # ── Step 5: context-length lookup ────────────────────────────────
-    ctx_len = azure_detect.lookup_context_length(
-        effective_model, effective_url, effective_key,
-    )
-
-    # ── Step 6: persist ──────────────────────────────────────────────
-    save_env_value("AZURE_FOUNDRY_API_KEY", effective_key)
-
-    cfg = load_config()
-    model = cfg.get("model")
-    if not isinstance(model, dict):
-        model = {"default": model} if model else {}
-        cfg["model"] = model
-
-    model["provider"] = "azure-foundry"
-    model["base_url"] = effective_url
-    model["api_mode"] = api_mode
-    model["default"] = effective_model
-    if ctx_len:
-        model["context_length"] = ctx_len
-
-    save_config(cfg)
-    deactivate_provider()
-    config["model"] = dict(model)
-
-    # Clear any conflicting env vars so auxiliary clients don't poison
-    # themselves with a stale OpenAI base URL / key.
-    if get_env_value("OPENAI_BASE_URL"):
-        save_env_value("OPENAI_BASE_URL", "")
-    if get_env_value("OPENAI_API_KEY"):
-        save_env_value("OPENAI_API_KEY", "")
-
-    mode_label = "OpenAI-style" if api_mode == "chat_completions" else "Anthropic-style"
-    print()
-    print("✓ Azure Foundry configured:")
-    print(f"    Endpoint:       {effective_url}")
-    print(f"    API mode:       {mode_label}")
-    print(f"    Model:          {effective_model}")
-    if ctx_len:
-        print(f"    Context length: {ctx_len:,} tokens")
-    else:
-        print("    Context length: not auto-detected (will fall back at runtime)")
-    print()
-
-
 def _remove_custom_provider(config):
     """Let the user remove a saved custom provider from config.yaml."""
     from hermes_cli.config import load_config, save_config
@@ -3215,7 +2923,6 @@ def _model_flow_named_custom(config, provider_info):
     # Resolve key from env var if api_key not set directly
     if not api_key and key_env:
         api_key = os.environ.get(key_env, "")
-    config_api_key = _custom_provider_api_key_config_value(provider_info, api_key)
 
     print(f"  Provider: {name}")
     print(f"  URL:      {base_url}")
@@ -3312,8 +3019,8 @@ def _model_flow_named_custom(config, provider_info):
     else:
         model["provider"] = "custom"
         model["base_url"] = base_url
-        if config_api_key:
-            model["api_key"] = config_api_key
+        if api_key:
+            model["api_key"] = api_key
     # Apply api_mode from custom_providers entry, or clear stale value
     custom_api_mode = provider_info.get("api_mode", "")
     if custom_api_mode:
@@ -3331,15 +3038,15 @@ def _model_flow_named_custom(config, provider_info):
             provider_entry = providers_cfg.get(provider_key)
             if isinstance(provider_entry, dict):
                 provider_entry["default_model"] = model_name
-                if config_api_key and not str(provider_entry.get("api_key", "") or "").strip():
-                    provider_entry["api_key"] = config_api_key
+                if api_key and not str(provider_entry.get("api_key", "") or "").strip():
+                    provider_entry["api_key"] = api_key
                 if key_env and not str(provider_entry.get("key_env", "") or "").strip():
                     provider_entry["key_env"] = key_env
                 cfg["providers"] = providers_cfg
                 save_config(cfg)
     else:
         # Save model name to the custom_providers entry for next time
-        _save_custom_provider(base_url, config_api_key, model_name)
+        _save_custom_provider(base_url, api_key, model_name)
 
     print(f"\n✅ Model set to: {model_name}")
     print(f"   Provider: {name} ({base_url})")
@@ -4780,13 +4487,6 @@ def cmd_webhook(args):
     webhook_command(args)
 
 
-def cmd_kanban(args):
-    """Multi-profile collaboration board."""
-    from hermes_cli.kanban import kanban_command
-
-    return kanban_command(args)
-
-
 def cmd_hooks(args):
     """Shell-hook inspection and management."""
     from hermes_cli.hooks import hooks_command
@@ -5884,54 +5584,6 @@ def _finalize_update_output(state):
             pass
 
 
-def _cmd_update_check():
-    """Implement ``hermes update --check``: fetch and report without installing."""
-    git_dir = PROJECT_ROOT / ".git"
-    if not git_dir.exists():
-        print("✗ Not a git repository — cannot check for updates.")
-        sys.exit(1)
-
-    git_cmd = ["git"]
-    if sys.platform == "win32":
-        git_cmd = ["git", "-c", "windows.appendAtomically=false"]
-
-    print("→ Fetching from origin...")
-    fetch_result = subprocess.run(
-        git_cmd + ["fetch", "origin"],
-        cwd=PROJECT_ROOT,
-        capture_output=True,
-        text=True,
-    )
-    if fetch_result.returncode != 0:
-        stderr = fetch_result.stderr.strip()
-        if "Could not resolve host" in stderr or "unable to access" in stderr:
-            print("✗ Network error — cannot reach the remote repository.")
-        elif "Authentication failed" in stderr or "could not read Username" in stderr:
-            print("✗ Authentication failed — check your git credentials or SSH key.")
-        else:
-            print("✗ Failed to fetch from origin.")
-            if stderr:
-                print(f"  {stderr.splitlines()[0]}")
-        sys.exit(1)
-
-    rev_result = subprocess.run(
-        git_cmd + ["rev-list", "HEAD..origin/main", "--count"],
-        cwd=PROJECT_ROOT,
-        capture_output=True,
-        text=True,
-        check=True,
-    )
-    behind = int(rev_result.stdout.strip())
-
-    if behind == 0:
-        print("✓ Already up to date.")
-    else:
-        commits_word = "commit" if behind == 1 else "commits"
-        print(f"⚕ Update available: {behind} {commits_word} behind origin/main.")
-        from hermes_cli.config import recommended_update_command
-        print(f"  Run '{recommended_update_command()}' to install.")
-
-
 def cmd_update(args):
     """Update Hermes Agent to the latest version.
 
@@ -5945,10 +5597,6 @@ def cmd_update(args):
         managed_error("update Hermes Agent")
         return
 
-    if getattr(args, "check", False):
-        _cmd_update_check()
-        return
-
     gateway_mode = getattr(args, "gateway", False)
 
     # Protect against mid-update terminal disconnects (SIGHUP) and tolerate
@@ -7230,9 +6878,6 @@ Examples:
     hermes auth remove <p> <t>    Remove pooled credential by index, id, or label
     hermes auth reset <provider>  Clear exhaustion status for a provider
     hermes model                  Select default model
-    hermes fallback [list]        Show fallback provider chain
-    hermes fallback add           Add a fallback provider (same picker as `hermes model`)
-    hermes fallback remove        Remove a fallback provider from the chain
     hermes config                 View configuration
     hermes config edit            Edit config in $EDITOR
     hermes config set model gpt-4 Set a config value
@@ -7574,42 +7219,6 @@ For more help on a command:
     )
     model_parser.set_defaults(func=cmd_model)
 
-    # =========================================================================
-    # fallback command — manage the fallback provider chain
-    # =========================================================================
-    from hermes_cli.fallback_cmd import cmd_fallback
-
-    fallback_parser = subparsers.add_parser(
-        "fallback",
-        help="Manage fallback providers (tried when the primary model fails)",
-        description=(
-            "Manage the fallback provider chain.  Fallback providers are tried "
-            "in order when the primary model fails with rate-limit, overload, or "
-            "connection errors.  See: "
-            "https://hermes-agent.nousresearch.com/docs/user-guide/features/fallback-providers"
-        ),
-    )
-    fallback_subparsers = fallback_parser.add_subparsers(dest="fallback_command")
-    fallback_subparsers.add_parser(
-        "list",
-        aliases=["ls"],
-        help="Show the current fallback chain (default when no subcommand)",
-    )
-    fallback_subparsers.add_parser(
-        "add",
-        help="Pick a provider + model (same picker as `hermes model`) and append to the chain",
-    )
-    fallback_subparsers.add_parser(
-        "remove",
-        aliases=["rm"],
-        help="Pick an entry to delete from the chain",
-    )
-    fallback_subparsers.add_parser(
-        "clear",
-        help="Remove all fallback entries",
-    )
-    fallback_parser.set_defaults(func=cmd_fallback)
-
     # =========================================================================
     # gateway command
     # =========================================================================
@@ -7780,19 +7389,6 @@ For more help on a command:
     setup_parser.add_argument(
         "--reset", action="store_true", help="Reset configuration to defaults"
     )
-    setup_parser.add_argument(
-        "--reconfigure",
-        action="store_true",
-        help="(Default on existing installs.) Re-run the full wizard, "
-             "showing current values as defaults. Kept for backwards "
-             "compatibility — a bare 'hermes setup' now does this.",
-    )
-    setup_parser.add_argument(
-        "--quick",
-        action="store_true",
-        help="On existing installs: only prompt for items that are missing "
-             "or unset, instead of running the full reconfigure wizard.",
-    )
     setup_parser.set_defaults(func=cmd_setup)
 
     # =========================================================================
@@ -8123,13 +7719,6 @@ For more help on a command:
 
     webhook_parser.set_defaults(func=cmd_webhook)
 
-    # =========================================================================
-    # kanban command — multi-profile collaboration board
-    # =========================================================================
-    from hermes_cli.kanban import build_parser as _build_kanban_parser
-    kanban_parser = _build_kanban_parser(subparsers)
-    kanban_parser.set_defaults(func=cmd_kanban)
-
     # =========================================================================
     # hooks command — shell-hook inspection and management
     # =========================================================================
@@ -9282,12 +8871,6 @@ Examples:
         default=False,
         help="Gateway mode: use file-based IPC for prompts instead of stdin (used internally by /update)",
     )
-    update_parser.add_argument(
-        "--check",
-        action="store_true",
-        default=False,
-        help="Check whether an update is available without installing anything",
-    )
     update_parser.set_defaults(func=cmd_update)
 
     # =========================================================================

hermes_cli/model_catalog.py

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

hermes_cli/model_switch.py

@@ -533,7 +533,6 @@ def resolve_display_context_length(
     base_url: str = "",
     api_key: str = "",
     model_info: Optional[ModelInfo] = None,
-    custom_providers: list | None = None,
 ) -> Optional[int]:
     """Resolve the context length to show in /model output.
 
@@ -544,11 +543,6 @@ def resolve_display_context_length(
     about Codex OAuth, Copilot, Nous, and falls back to models.dev for the
     rest.
 
-    When ``custom_providers`` is provided, per-model ``context_length``
-    overrides from ``custom_providers[].models.<id>.context_length`` are
-    honored — this closes #15779 where ``/model`` switch ignored user-set
-    overrides.
-
     Prefer the provider-aware value; fall back to ``model_info.context_window``
     only if the resolver returns nothing.
     """
@@ -559,7 +553,6 @@ def resolve_display_context_length(
             base_url=base_url or "",
             api_key=api_key or "",
             provider=provider or None,
-            custom_providers=custom_providers,
         )
         if ctx:
             return int(ctx)
@@ -838,14 +831,9 @@ def switch_model(
                 requested=current_provider,
                 target_model=new_model,
             )
-            # If resolution fell through to "custom" (e.g. named custom provider like
-            # "ollama-launch" that resolve_runtime_provider doesn't know), keep existing
-            # credentials. Otherwise use the resolved values (picks up credential rotation,
-            # base_url adjustments for OpenCode, etc.).
-            if runtime.get("provider") != "custom":
-                api_key = runtime.get("api_key", "")
-                base_url = runtime.get("base_url", "")
-                api_mode = runtime.get("api_mode", "")
+            api_key = runtime.get("api_key", "")
+            base_url = runtime.get("base_url", "")
+            api_mode = runtime.get("api_mode", "")
         except Exception:
             pass
 
@@ -879,31 +867,16 @@ def switch_model(
             "message": f"Could not validate `{new_model}`: {e}",
         }
 
-    # Override rejection if model is in the user's saved provider config.
-    # API /v1/models may not list cloud/aliased models even though the server supports them.
     if not validation.get("accepted"):
-        override = False
-        if user_providers:
-            for up in user_providers:
-                if isinstance(up, dict) and up.get("provider") == target_provider:
-                    cfg_models = up.get("models", [])
-                    if new_model in cfg_models or any(
-                        m.get("name") == new_model for m in cfg_models if isinstance(m, dict)
-                    ):
-                        override = True
-                        break
-        if override:
-            validation = {"accepted": True, "persist": True, "recognized": False, "message": validation.get("message", "")}
-        else:
-            msg = validation.get("message", "Invalid model")
-            return ModelSwitchResult(
-                success=False,
-                new_model=new_model,
-                target_provider=target_provider,
-                provider_label=provider_label,
-                is_global=is_global,
-                error_message=msg,
-            )
+        msg = validation.get("message", "Invalid model")
+        return ModelSwitchResult(
+            success=False,
+            new_model=new_model,
+            target_provider=target_provider,
+            provider_label=provider_label,
+            is_global=is_global,
+            error_message=msg,
+        )
 
     # Apply auto-correction if validation found a closer match
     if validation.get("corrected_model"):

hermes_cli/models.py

@@ -383,9 +383,6 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "us.meta.llama4-maverick-17b-instruct-v1:0",
         "us.meta.llama4-scout-17b-instruct-v1:0",
     ],
-    # Azure Foundry: user-provided endpoint and model.
-    # Empty list because models depend on the endpoint configuration.
-    "azure-foundry": [],
 }
 
 # Vercel AI Gateway: derive the bare-model-id catalog from the curated
@@ -743,7 +740,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("opencode-zen",   "OpenCode Zen",             "OpenCode Zen (35+ curated models, pay-as-you-go)"),
     ProviderEntry("opencode-go",    "OpenCode Go",              "OpenCode Go (open models, $10/month subscription)"),
     ProviderEntry("bedrock",        "AWS Bedrock",              "AWS Bedrock (Claude, Nova, Llama, DeepSeek — IAM or API key)"),
-    ProviderEntry("azure-foundry",  "Azure Foundry",            "Azure Foundry (OpenAI-style or Anthropic-style endpoint — your Azure AI deployment)"),
 ]
 
 # Derived dicts — used throughout the codebase
@@ -876,16 +872,7 @@ def fetch_openrouter_models(
     if _openrouter_catalog_cache is not None and not force_refresh:
         return list(_openrouter_catalog_cache)
 
-    # Prefer the remotely-hosted catalog manifest; fall back to the in-repo
-    # snapshot when the manifest is unreachable. Both are curated lists that
-    # drive the picker; the OpenRouter live /v1/models filter (tool support,
-    # free pricing) is applied on top either way.
-    try:
-        from hermes_cli.model_catalog import get_curated_openrouter_models
-        remote = get_curated_openrouter_models()
-    except Exception:
-        remote = None
-    fallback = list(remote) if remote else list(OPENROUTER_MODELS)
+    fallback = list(OPENROUTER_MODELS)
     preferred_ids = [mid for mid, _ in fallback]
 
     try:
@@ -938,24 +925,6 @@ def model_ids(*, force_refresh: bool = False) -> list[str]:
     return [mid for mid, _ in fetch_openrouter_models(force_refresh=force_refresh)]
 
 
-def get_curated_nous_model_ids() -> list[str]:
-    """Return the curated Nous Portal model-id list.
-
-    Prefers the remotely-hosted catalog manifest (published under
-    ``website/static/api/model-catalog.json``); falls back to the in-repo
-    snapshot in ``_PROVIDER_MODELS["nous"]`` when the manifest is
-    unreachable. Always returns a list (never None).
-    """
-    try:
-        from hermes_cli.model_catalog import get_curated_nous_models
-        remote = get_curated_nous_models()
-    except Exception:
-        remote = None
-    if remote:
-        return list(remote)
-    return list(_PROVIDER_MODELS.get("nous", []))
-
-
 def _ai_gateway_model_is_free(pricing: Any) -> bool:
     """Return True if an AI Gateway model has $0 input AND output pricing."""
     if not isinstance(pricing, dict):
@@ -2653,8 +2622,8 @@ def validate_requested_model(
                 )
 
             return {
-                "accepted": True,
-                "persist": True,
+                "accepted": False,
+                "persist": False,
                 "recognized": False,
                 "message": message,
             }

hermes_cli/providers.py

@@ -167,12 +167,6 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         transport="openai_chat",
         base_url_env_var="OLLAMA_BASE_URL",
     ),
-    # Azure Foundry: supports both OpenAI-style and Anthropic-style endpoints.
-    # The transport is determined at runtime from config.yaml model.api_mode.
-    "azure-foundry": HermesOverlay(
-        transport="openai_chat",  # default; overridden by api_mode in config
-        base_url_env_var="AZURE_FOUNDRY_BASE_URL",
-    ),
 }
 
 

hermes_cli/runtime_provider.py

@@ -221,19 +221,6 @@ def _resolve_runtime_from_pool_entry(
     elif provider == "copilot":
         api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
         base_url = base_url or PROVIDER_REGISTRY["copilot"].inference_base_url
-    elif provider == "azure-foundry":
-        # Azure Foundry: read api_mode and base_url from config
-        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
-        if cfg_provider == "azure-foundry":
-            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
-            if cfg_base_url:
-                base_url = cfg_base_url
-            configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
-            if configured_mode:
-                api_mode = configured_mode
-        # For Anthropic-style endpoints, strip /v1 suffix
-        if api_mode == "anthropic_messages":
-            base_url = re.sub(r"/v1/?$", "", base_url)
     else:
         configured_provider = str(model_cfg.get("provider") or "").strip().lower()
         # Honour model.base_url from config.yaml when the configured provider
@@ -602,71 +589,6 @@ def _resolve_openrouter_runtime(
     }
 
 
-def _resolve_azure_foundry_runtime(
-    *,
-    requested_provider: str,
-    model_cfg: Dict[str, Any],
-    explicit_api_key: Optional[str] = None,
-    explicit_base_url: Optional[str] = None,
-) -> Dict[str, Any]:
-    """Resolve an Azure Foundry runtime entry.
-
-    Reads ``model.base_url`` + ``model.api_mode`` from config.yaml (or
-    explicit overrides), pulls the API key from ``.env`` / env var, and
-    strips a trailing ``/v1`` for Anthropic-style endpoints because the
-    Anthropic SDK appends ``/v1/messages`` internally.
-
-    Raises :class:`AuthError` when required values are missing.
-    """
-    explicit_api_key = str(explicit_api_key or "").strip()
-    explicit_base_url_clean = str(explicit_base_url or "").strip().rstrip("/")
-
-    cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
-    cfg_base_url = ""
-    cfg_api_mode = "chat_completions"
-    if cfg_provider == "azure-foundry":
-        cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
-        cfg_api_mode = _parse_api_mode(model_cfg.get("api_mode")) or "chat_completions"
-
-    env_base_url = os.getenv("AZURE_FOUNDRY_BASE_URL", "").strip().rstrip("/")
-    base_url = explicit_base_url_clean or cfg_base_url or env_base_url
-    if not base_url:
-        raise AuthError(
-            "Azure Foundry requires a base URL. Set it via 'hermes model' or "
-            "the AZURE_FOUNDRY_BASE_URL environment variable."
-        )
-
-    api_key = explicit_api_key
-    if not api_key:
-        try:
-            from hermes_cli.config import get_env_value
-            api_key = get_env_value("AZURE_FOUNDRY_API_KEY") or ""
-        except Exception:
-            api_key = ""
-    if not api_key:
-        api_key = os.getenv("AZURE_FOUNDRY_API_KEY", "").strip()
-    if not api_key:
-        raise AuthError(
-            "Azure Foundry requires an API key. Set AZURE_FOUNDRY_API_KEY in "
-            "~/.hermes/.env or run 'hermes model' to configure."
-        )
-
-    # Anthropic SDK appends /v1/messages itself, so strip any trailing /v1
-    # we inherited from the configured base_url to avoid double-/v1 paths.
-    if cfg_api_mode == "anthropic_messages":
-        base_url = re.sub(r"/v1/?$", "", base_url)
-
-    source = "explicit" if (explicit_api_key or explicit_base_url) else "config"
-    return {
-        "provider": "azure-foundry",
-        "api_mode": cfg_api_mode,
-        "base_url": base_url,
-        "api_key": api_key,
-        "source": source,
-        "requested_provider": requested_provider,
-    }
-
-
 def _resolve_explicit_runtime(
     *,
     provider: str,
@@ -756,15 +678,6 @@ def _resolve_explicit_runtime(
             "requested_provider": requested_provider,
         }
 
-    # Azure Foundry: user-configured endpoint with selectable API mode
-    if provider == "azure-foundry":
-        return _resolve_azure_foundry_runtime(
-            requested_provider=requested_provider,
-            model_cfg=model_cfg,
-            explicit_api_key=explicit_api_key,
-            explicit_base_url=explicit_base_url,
-        )
-
     pconfig = PROVIDER_REGISTRY.get(provider)
     if pconfig and pconfig.auth_type == "api_key":
         env_url = ""
@@ -833,40 +746,6 @@ def resolve_runtime_provider(
     """
     requested_provider = resolve_requested_provider(requested)
 
-    # Azure Anthropic short-circuit: when explicitly targeting an Azure endpoint
-    # with provider="anthropic", bypass _resolve_named_custom_runtime (which would
-    # return provider="custom" with chat_completions api_mode and no valid key).
-    # Instead, use the Azure key directly with anthropic_messages api_mode.
-    _eff_base = (explicit_base_url or "").strip()
-    if requested_provider == "anthropic" and "azure.com" in _eff_base:
-        _azure_key = (
-            (explicit_api_key or "").strip()
-            or os.getenv("AZURE_ANTHROPIC_KEY", "").strip()
-            or os.getenv("ANTHROPIC_API_KEY", "").strip()
-        )
-        return {
-            "provider": "anthropic",
-            "api_mode": "anthropic_messages",
-            "base_url": _eff_base.rstrip("/"),
-            "api_key": _azure_key,
-            "source": "azure-explicit",
-            "requested_provider": requested_provider,
-        }
-
-    # Azure Foundry: user-configured endpoint with selectable API mode
-    # (OpenAI-style chat_completions or Anthropic-style anthropic_messages).
-    # Resolve before the custom-runtime / pool / generic paths so Azure
-    # config is always picked up from model.base_url + model.api_mode,
-    # regardless of whether the caller passed explicit_* args.
-    if requested_provider == "azure-foundry":
-        azure_runtime = _resolve_azure_foundry_runtime(
-            requested_provider=requested_provider,
-            model_cfg=_get_model_config(),
-            explicit_api_key=explicit_api_key,
-            explicit_base_url=explicit_base_url,
-        )
-        return azure_runtime
-
     custom_runtime = _resolve_named_custom_runtime(
         requested_provider=requested_provider,
         explicit_api_key=explicit_api_key,
@@ -1045,6 +924,13 @@ def resolve_runtime_provider(
 
     # Anthropic (native Messages API)
     if provider == "anthropic":
+        from agent.anthropic_adapter import resolve_anthropic_token
+        token = resolve_anthropic_token()
+        if not token:
+            raise AuthError(
+                "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
+                "run 'claude setup-token', or authenticate with 'claude /login'."
+            )
         # Allow base URL override from config.yaml model.base_url, but only
         # when the configured provider is anthropic — otherwise a non-Anthropic
         # base_url (e.g. Codex endpoint) would leak into Anthropic requests.
@@ -1053,33 +939,6 @@ def resolve_runtime_provider(
         if cfg_provider == "anthropic":
             cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
         base_url = cfg_base_url or "https://api.anthropic.com"
-
-        # For Azure AI Foundry endpoints, use ANTHROPIC_API_KEY directly —
-        # Claude Code OAuth tokens (sk-ant-oat01) are not accepted by Azure.
-        # Azure keys don't start with "sk-ant-" so resolve_anthropic_token()
-        # would find the Claude Code OAuth token first (priority 3) and return
-        # that instead, causing 401s. Detect Azure endpoints and use the env
-        # key directly to bypass the OAuth priority chain.
-        _is_azure_endpoint = "azure.com" in base_url.lower() or (
-            cfg_base_url and "azure.com" in cfg_base_url.lower()
-        )
-        if _is_azure_endpoint:
-            token = (
-                os.getenv("AZURE_ANTHROPIC_KEY", "").strip()
-                or os.getenv("ANTHROPIC_API_KEY", "").strip()
-            )
-            if not token:
-                raise AuthError(
-                    "No Azure Anthropic API key found. Set AZURE_ANTHROPIC_KEY or ANTHROPIC_API_KEY."
-                )
-        else:
-            from agent.anthropic_adapter import resolve_anthropic_token
-            token = resolve_anthropic_token()
-            if not token:
-                raise AuthError(
-                    "No Anthropic credentials found. Set ANTHROPIC_TOKEN or ANTHROPIC_API_KEY, "
-                    "run 'claude setup-token', or authenticate with 'claude /login'."
-                )
         return {
             "provider": "anthropic",
             "api_mode": "anthropic_messages",

hermes_cli/setup.py

@@ -2863,6 +2863,17 @@ SETUP_SECTIONS = [
     ("agent", "Agent Settings", setup_agent_settings),
 ]
 
+# The returning-user menu intentionally omits standalone TTS because model setup
+# already includes TTS selection and tools setup covers the rest of the provider
+# configuration. Keep this list in the same order as the visible menu entries.
+RETURNING_USER_MENU_SECTION_KEYS = [
+    "model",
+    "terminal",
+    "gateway",
+    "tools",
+    "agent",
+]
+
 
 def run_setup_wizard(args):
     """Run the interactive setup wizard.
@@ -2887,9 +2898,6 @@ def run_setup_wizard(args):
         save_config(copy.deepcopy(DEFAULT_CONFIG))
         print_success("Configuration reset to defaults.")
 
-    reconfigure_requested = bool(getattr(args, "reconfigure", False))
-    quick_requested = bool(getattr(args, "quick", False))
-
     config = load_config()
     hermes_home = get_hermes_home()
 
@@ -2981,36 +2989,50 @@ def run_setup_wizard(args):
     migration_ran = False
 
     if is_existing:
-        # Existing install — default is the full-wizard reconfigure flow.
-        # Every prompt shows the current value as its default, so pressing
-        # Enter keeps it.  Opt into `--quick` for the narrow "just fill in
-        # missing items" flow (useful after a partial OpenClaw migration
-        # or when a required API key got cleared).
-        if quick_requested:
+        # ── Returning User Menu ──
+        print()
+        print_header("Welcome Back!")
+        print_success("You already have Hermes configured.")
+        print()
+
+        menu_choices = [
+            "Quick Setup - configure missing items only",
+            "Full Setup - reconfigure everything",
+            "Model & Provider",
+            "Terminal Backend",
+            "Messaging Platforms (Gateway)",
+            "Tools",
+            "Agent Settings",
+            "Exit",
+        ]
+        choice = prompt_choice("What would you like to do?", menu_choices, 0)
+
+        if choice == 0:
+            # Quick setup
             _run_quick_setup(config, hermes_home)
             return
-
-        print()
-        print_header("Reconfigure")
-        print_success("You already have Hermes configured.")
-        print_info("Running the full wizard — each prompt shows your current value.")
-        print_info("Press Enter to keep it, or type a new value to change it.")
-        print_info("")
-        print_info("Tip: jump straight to a section with 'hermes setup model|terminal|")
-        print_info("     gateway|tools|agent', or fill only missing items with --quick.")
-        # Fall through to the "Full Setup — run all sections" block below.
-        # --reconfigure is now the default on existing installs; the flag
-        # is preserved for backwards compatibility but is a no-op here.
+        elif choice == 1:
+            # Full setup — fall through to run all sections
+            pass
+        elif choice == 7:
+            print_info("Exiting. Run 'hermes setup' again when ready.")
+            return
+        elif 2 <= choice <= 6:
+            # Individual section — map by key, not by position.
+            # SETUP_SECTIONS includes TTS but the returning-user menu skips it,
+            # so positional indexing (choice - 2) would dispatch the wrong section.
+            section_key = RETURNING_USER_MENU_SECTION_KEYS[choice - 2]
+            section = next((s for s in SETUP_SECTIONS if s[0] == section_key), None)
+            if section:
+                _, label, func = section
+                func(config)
+                save_config(config)
+                _print_setup_summary(config, hermes_home)
+            return
     else:
         # ── First-Time Setup ──
         print()
 
-        # --reconfigure / --quick on a fresh install are meaningless — fall
-        # through to the normal first-time flow.
-        if reconfigure_requested or quick_requested:
-            print_info("No existing configuration found — running first-time setup.")
-            print()
-
         # Offer OpenClaw migration before configuration begins
         migration_ran = _offer_openclaw_migration(hermes_home)
         if migration_ran:

hermes_cli/tips.py

@@ -10,7 +10,8 @@ import random
 
 TIPS = [
     # --- Slash Commands ---
-    "/background <prompt> (alias /bg or /btw) runs a task in a separate session while your current one stays free.",
+    "/btw <question> asks a quick side question without tools or history — great for clarifications.",
+    "/background <prompt> runs a task in a separate session while your current one stays free.",
     "/branch forks the current session so you can explore a different direction without losing progress.",
     "/compress manually compresses conversation context when things get long.",
     "/rollback lists filesystem checkpoints — restore files the agent modified to any prior state.",

hermes_cli/web_server.py

@@ -3103,23 +3103,13 @@ def _mount_plugin_api_routes():
             _log.warning("Plugin %s declares api=%s but file not found", plugin["name"], api_file_name)
             continue
         try:
-            module_name = f"hermes_dashboard_plugin_{plugin['name']}"
-            spec = importlib.util.spec_from_file_location(module_name, api_path)
+            spec = importlib.util.spec_from_file_location(
+                f"hermes_dashboard_plugin_{plugin['name']}", api_path,
+            )
             if spec is None or spec.loader is None:
                 continue
             mod = importlib.util.module_from_spec(spec)
-            # Register in sys.modules BEFORE exec_module so pydantic/FastAPI
-            # can resolve forward references (e.g. models defined in a file
-            # that uses `from __future__ import annotations`). Without this,
-            # TypeAdapter lazy-build fails at first request with
-            # "is not fully defined" because the module namespace isn't
-            # reachable by name for string-annotation resolution.
-            sys.modules[module_name] = mod
-            try:
-                spec.loader.exec_module(mod)
-            except Exception:
-                sys.modules.pop(module_name, None)
-                raise
+            spec.loader.exec_module(mod)
             router = getattr(mod, "router", None)
             if router is None:
                 _log.warning("Plugin %s api file has no 'router' attribute", plugin["name"])

hermes_state.py

@@ -31,7 +31,7 @@ T = TypeVar("T")
 
 DEFAULT_DB_PATH = get_hermes_home() / "state.db"
 
-SCHEMA_VERSION = 9
+SCHEMA_VERSION = 8
 
 SCHEMA_SQL = """
 CREATE TABLE IF NOT EXISTS schema_version (
@@ -83,8 +83,7 @@ CREATE TABLE IF NOT EXISTS messages (
     reasoning TEXT,
     reasoning_content TEXT,
     reasoning_details TEXT,
-    codex_reasoning_items TEXT,
-    codex_message_items TEXT
+    codex_reasoning_items TEXT
 );
 
 CREATE TABLE IF NOT EXISTS state_meta (
@@ -357,15 +356,6 @@ class SessionDB:
                 except sqlite3.OperationalError:
                     pass  # Column already exists
                 cursor.execute("UPDATE schema_version SET version = 8")
-            if current_version < 9:
-                # v9: preserve replayable Codex assistant message ids/phases so
-                # follow-up turns can rebuild Responses API message items instead
-                # of flattening everything to plain assistant text.
-                try:
-                    cursor.execute('ALTER TABLE messages ADD COLUMN "codex_message_items" TEXT')
-                except sqlite3.OperationalError:
-                    pass  # Column already exists
-                cursor.execute("UPDATE schema_version SET version = 9")
 
         # Unique title index — always ensure it exists (safe to run after migrations
         # since the title column is guaranteed to exist at this point)
@@ -966,7 +956,6 @@ class SessionDB:
         reasoning_content: str = None,
         reasoning_details: Any = None,
         codex_reasoning_items: Any = None,
-        codex_message_items: Any = None,
     ) -> int:
         """
         Append a message to a session. Returns the message row ID.
@@ -983,10 +972,6 @@ class SessionDB:
             json.dumps(codex_reasoning_items)
             if codex_reasoning_items else None
         )
-        codex_message_items_json = (
-            json.dumps(codex_message_items)
-            if codex_message_items else None
-        )
         tool_calls_json = json.dumps(tool_calls) if tool_calls else None
 
         # Pre-compute tool call count
@@ -998,9 +983,8 @@ class SessionDB:
             cursor = conn.execute(
                 """INSERT INTO messages (session_id, role, content, tool_call_id,
                    tool_calls, tool_name, timestamp, token_count, finish_reason,
-                   reasoning, reasoning_content, reasoning_details, codex_reasoning_items,
-                   codex_message_items)
-                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
+                   reasoning, reasoning_content, reasoning_details, codex_reasoning_items)
+                   VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
                 (
                     session_id,
                     role,
@@ -1015,7 +999,6 @@ class SessionDB:
                     reasoning_content,
                     reasoning_details_json,
                     codex_items_json,
-                    codex_message_items_json,
                 ),
             )
             msg_id = cursor.lastrowid
@@ -1129,8 +1112,7 @@ class SessionDB:
         with self._lock:
             cursor = self._conn.execute(
                 "SELECT role, content, tool_call_id, tool_calls, tool_name, "
-                "reasoning, reasoning_content, reasoning_details, codex_reasoning_items, "
-                "codex_message_items "
+                "reasoning, reasoning_content, reasoning_details, codex_reasoning_items "
                 "FROM messages WHERE session_id = ? ORDER BY timestamp, id",
                 (session_id,),
             )
@@ -1168,12 +1150,6 @@ class SessionDB:
                     except (json.JSONDecodeError, TypeError):
                         logger.warning("Failed to deserialize codex_reasoning_items, falling back to None")
                         msg["codex_reasoning_items"] = None
-                if row["codex_message_items"]:
-                    try:
-                        msg["codex_message_items"] = json.loads(row["codex_message_items"])
-                    except (json.JSONDecodeError, TypeError):
-                        logger.warning("Failed to deserialize codex_message_items, falling back to None")
-                        msg["codex_message_items"] = None
             messages.append(msg)
         return messages
 

model_tools.py

@@ -24,7 +24,6 @@ import json
 import asyncio
 import logging
 import threading
-import time
 from typing import Dict, Any, List, Optional, Tuple
 
 from tools.registry import discover_builtin_tools, registry
@@ -568,14 +567,6 @@ def handle_function_call(
             except Exception:
                 pass  # file_tools may not be loaded yet
 
-        # Measure tool dispatch latency so post_tool_call and
-        # transform_tool_result hooks can observe per-tool duration.
-        # Inspired by Claude Code 2.1.119, which added ``duration_ms`` to
-        # PostToolUse hook inputs so plugin authors can build latency
-        # dashboards, budget alerts, and regression canaries without having
-        # to wrap every tool manually.  We use monotonic() so the value is
-        # unaffected by wall-clock adjustments during the call.
-        _dispatch_start = time.monotonic()
         if function_name == "execute_code":
             # Prefer the caller-provided list so subagents can't overwrite
             # the parent's tool set via the process-global.
@@ -591,7 +582,6 @@ def handle_function_call(
                 task_id=task_id,
                 user_task=user_task,
             )
-        duration_ms = int((time.monotonic() - _dispatch_start) * 1000)
 
         try:
             from hermes_cli.plugins import invoke_hook
@@ -603,7 +593,6 @@ def handle_function_call(
                 task_id=task_id or "",
                 session_id=session_id or "",
                 tool_call_id=tool_call_id or "",
-                duration_ms=duration_ms,
             )
         except Exception:
             pass
@@ -624,7 +613,6 @@ def handle_function_call(
                 task_id=task_id or "",
                 session_id=session_id or "",
                 tool_call_id=tool_call_id or "",
-                duration_ms=duration_ms,
             )
             for hook_result in hook_results:
                 if isinstance(hook_result, str):

plugins/kanban/dashboard/dist/style.css

@@ -1,752 +0,0 @@
-/*
- * Hermes Kanban — dashboard plugin styles.
- *
- * All colors reference theme CSS vars so the board reskins with the
- * active dashboard theme. No hardcoded palette.
- */
-
-.hermes-kanban {
-  width: 100%;
-}
-
-/* ---- Columns layout -------------------------------------------------- */
-
-.hermes-kanban-columns {
-  display: grid;
-  grid-template-columns: repeat(auto-fit, minmax(260px, 1fr));
-  gap: 0.75rem;
-  align-items: start;
-}
-
-.hermes-kanban-column {
-  display: flex;
-  flex-direction: column;
-  background: color-mix(in srgb, var(--color-card) 85%, transparent);
-  border: 1px solid var(--color-border);
-  border-radius: var(--radius);
-  padding: 0.5rem;
-  min-height: 200px;
-  max-height: calc(100vh - 220px);
-  transition: border-color 120ms ease, background-color 120ms ease;
-}
-
-.hermes-kanban-column--drop {
-  border-color: var(--color-ring);
-  background: color-mix(in srgb, var(--color-ring) 8%, var(--color-card));
-}
-
-.hermes-kanban-column-header {
-  display: flex;
-  align-items: center;
-  gap: 0.5rem;
-  padding: 0.25rem 0.25rem 0.35rem;
-  font-weight: 600;
-  font-size: 0.85rem;
-  color: var(--color-foreground);
-}
-
-.hermes-kanban-column-label {
-  flex: 1;
-  letter-spacing: 0.01em;
-}
-
-.hermes-kanban-column-count {
-  font-variant-numeric: tabular-nums;
-  color: var(--color-muted-foreground);
-  font-size: 0.75rem;
-  font-weight: 500;
-}
-
-.hermes-kanban-column-add {
-  appearance: none;
-  background: transparent;
-  border: 1px solid var(--color-border);
-  color: var(--color-foreground);
-  border-radius: var(--radius-sm, 0.25rem);
-  width: 22px;
-  height: 22px;
-  line-height: 1;
-  font-size: 1rem;
-  cursor: pointer;
-}
-.hermes-kanban-column-add:hover {
-  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
-}
-
-.hermes-kanban-column-sub {
-  padding: 0 0.25rem 0.5rem;
-  font-size: 0.7rem;
-  color: var(--color-muted-foreground);
-  border-bottom: 1px solid color-mix(in srgb, var(--color-border) 60%, transparent);
-  margin-bottom: 0.5rem;
-}
-
-.hermes-kanban-column-body {
-  display: flex;
-  flex-direction: column;
-  gap: 0.45rem;
-  overflow-y: auto;
-  padding-right: 0.1rem;
-}
-
-.hermes-kanban-empty {
-  padding: 1.5rem 0.5rem;
-  text-align: center;
-  font-size: 0.75rem;
-  color: var(--color-muted-foreground);
-  border: 1px dashed color-mix(in srgb, var(--color-border) 70%, transparent);
-  border-radius: var(--radius-sm, 0.25rem);
-}
-
-/* ---- Status dots ----------------------------------------------------- */
-
-.hermes-kanban-dot {
-  display: inline-block;
-  width: 0.5rem;
-  height: 0.5rem;
-  border-radius: 999px;
-  background: var(--color-muted-foreground);
-}
-.hermes-kanban-dot-triage   { background: #b47dd6; }  /* lilac — fresh/unspecified */
-.hermes-kanban-dot-todo     { background: var(--color-muted-foreground); }
-.hermes-kanban-dot-ready    { background: #d4b348; }  /* amber */
-.hermes-kanban-dot-running  { background: #3fb97d; }  /* green */
-.hermes-kanban-dot-blocked  { background: var(--color-destructive, #d14a4a); }
-.hermes-kanban-dot-done     { background: #4a8cd1; }  /* blue */
-.hermes-kanban-dot-archived { background: var(--color-border); }
-
-/* ---- Progress pill (N/M child tasks done) --------------------------- */
-
-.hermes-kanban-progress {
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.62rem;
-  padding: 0.05rem 0.35rem;
-  border-radius: 999px;
-  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
-  border: 1px solid color-mix(in srgb, var(--color-border) 80%, transparent);
-  color: var(--color-muted-foreground);
-  letter-spacing: 0.02em;
-}
-.hermes-kanban-progress--full {
-  background: color-mix(in srgb, #3fb97d 22%, transparent);
-  border-color: color-mix(in srgb, #3fb97d 45%, transparent);
-  color: var(--color-foreground);
-}
-
-/* ---- Lanes (per-profile sub-grouping inside Running) ---------------- */
-
-.hermes-kanban-lane {
-  display: flex;
-  flex-direction: column;
-  gap: 0.35rem;
-  padding: 0.25rem 0 0.35rem;
-  border-top: 1px dashed color-mix(in srgb, var(--color-border) 70%, transparent);
-}
-.hermes-kanban-lane:first-child {
-  border-top: 0;
-  padding-top: 0;
-}
-.hermes-kanban-lane-head {
-  display: flex;
-  align-items: center;
-  gap: 0.4rem;
-  font-size: 0.65rem;
-  text-transform: uppercase;
-  letter-spacing: 0.08em;
-  color: var(--color-muted-foreground);
-  padding: 0 0.1rem;
-}
-.hermes-kanban-lane-name {
-  font-weight: 600;
-  font-family: var(--font-mono, ui-monospace, monospace);
-}
-.hermes-kanban-lane-count {
-  margin-left: auto;
-  font-variant-numeric: tabular-nums;
-}
-
-/* ---- Card ------------------------------------------------------------ */
-
-.hermes-kanban-card {
-  cursor: grab;
-  transition: transform 100ms ease, box-shadow 100ms ease;
-}
-.hermes-kanban-card:hover {
-  box-shadow: 0 1px 0 0 var(--color-ring) inset, 0 0 0 1px var(--color-ring) inset;
-}
-.hermes-kanban-card:active {
-  cursor: grabbing;
-  transform: scale(0.995);
-}
-
-.hermes-kanban-card-content {
-  padding: 0.5rem 0.6rem !important;
-  display: flex;
-  flex-direction: column;
-  gap: 0.3rem;
-}
-
-.hermes-kanban-card-row {
-  display: flex;
-  align-items: center;
-  gap: 0.35rem;
-  flex-wrap: wrap;
-}
-
-.hermes-kanban-card-id {
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.65rem;
-  color: var(--color-muted-foreground);
-  letter-spacing: 0.03em;
-}
-
-.hermes-kanban-card-title {
-  font-size: 0.85rem;
-  font-weight: 500;
-  line-height: 1.3;
-  color: var(--color-foreground);
-  word-break: break-word;
-}
-
-.hermes-kanban-card-meta {
-  font-size: 0.7rem;
-  color: var(--color-muted-foreground);
-  gap: 0.55rem;
-}
-
-.hermes-kanban-priority {
-  font-size: 0.6rem !important;
-  padding: 0.05rem 0.3rem !important;
-  background: color-mix(in srgb, var(--color-ring) 18%, transparent);
-  color: var(--color-foreground);
-  border: 1px solid color-mix(in srgb, var(--color-ring) 40%, transparent);
-}
-
-.hermes-kanban-tag {
-  font-size: 0.6rem !important;
-  padding: 0.05rem 0.3rem !important;
-}
-
-.hermes-kanban-assignee {
-  font-weight: 500;
-  color: color-mix(in srgb, var(--color-foreground) 80%, var(--color-muted-foreground));
-}
-.hermes-kanban-unassigned {
-  font-style: italic;
-}
-.hermes-kanban-ago {
-  margin-left: auto;
-}
-
-/* ---- Inline create --------------------------------------------------- */
-
-.hermes-kanban-inline-create {
-  display: flex;
-  flex-direction: column;
-  gap: 0.35rem;
-  padding: 0.5rem;
-  margin-bottom: 0.5rem;
-  background: color-mix(in srgb, var(--color-card) 70%, transparent);
-  border: 1px dashed var(--color-border);
-  border-radius: var(--radius-sm, 0.25rem);
-}
-
-/* ---- Drawer (task detail side panel) --------------------------------- */
-
-.hermes-kanban-drawer-shade {
-  position: fixed;
-  inset: 0;
-  background: rgba(0, 0, 0, 0.45);
-  z-index: 60;
-  display: flex;
-  justify-content: flex-end;
-}
-
-.hermes-kanban-drawer {
-  width: min(480px, 92vw);
-  height: 100vh;
-  background: var(--color-card);
-  border-left: 1px solid var(--color-border);
-  display: flex;
-  flex-direction: column;
-  box-shadow: -4px 0 18px rgba(0, 0, 0, 0.35);
-  animation: hermes-kanban-drawer-in 180ms ease-out;
-}
-
-@keyframes hermes-kanban-drawer-in {
-  from { transform: translateX(100%); opacity: 0.3; }
-  to   { transform: translateX(0);    opacity: 1; }
-}
-
-.hermes-kanban-drawer-head {
-  display: flex;
-  align-items: center;
-  justify-content: space-between;
-  padding: 0.6rem 0.8rem;
-  border-bottom: 1px solid var(--color-border);
-  font-family: var(--font-mono, ui-monospace, monospace);
-}
-
-.hermes-kanban-drawer-close {
-  appearance: none;
-  background: transparent;
-  border: 0;
-  color: var(--color-muted-foreground);
-  font-size: 1.25rem;
-  line-height: 1;
-  cursor: pointer;
-  padding: 0 0.25rem;
-}
-.hermes-kanban-drawer-close:hover { color: var(--color-foreground); }
-
-.hermes-kanban-drawer-body {
-  flex: 1;
-  overflow-y: auto;
-  padding: 0.9rem;
-  display: flex;
-  flex-direction: column;
-  gap: 0.85rem;
-}
-
-.hermes-kanban-drawer-title {
-  display: flex;
-  align-items: center;
-  gap: 0.5rem;
-  font-size: 1rem;
-  font-weight: 600;
-}
-
-.hermes-kanban-drawer-meta {
-  display: flex;
-  flex-direction: column;
-  gap: 0.15rem;
-  padding: 0.5rem 0.6rem;
-  background: color-mix(in srgb, var(--color-foreground) 4%, transparent);
-  border: 1px solid var(--color-border);
-  border-radius: var(--radius-sm, 0.25rem);
-}
-
-.hermes-kanban-meta-row {
-  display: flex;
-  gap: 0.5rem;
-  font-size: 0.72rem;
-}
-.hermes-kanban-meta-label {
-  width: 92px;
-  color: var(--color-muted-foreground);
-}
-.hermes-kanban-meta-value {
-  color: var(--color-foreground);
-  word-break: break-word;
-}
-
-.hermes-kanban-actions {
-  display: flex;
-  flex-wrap: wrap;
-  gap: 0.3rem;
-}
-
-.hermes-kanban-section {
-  display: flex;
-  flex-direction: column;
-  gap: 0.35rem;
-}
-
-.hermes-kanban-section-head {
-  font-size: 0.72rem;
-  font-weight: 600;
-  text-transform: uppercase;
-  letter-spacing: 0.07em;
-  color: var(--color-muted-foreground);
-}
-
-.hermes-kanban-pre {
-  margin: 0;
-  padding: 0.45rem 0.55rem;
-  white-space: pre-wrap;
-  word-break: break-word;
-  background: color-mix(in srgb, var(--color-foreground) 4%, transparent);
-  border: 1px solid var(--color-border);
-  border-radius: var(--radius-sm, 0.25rem);
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.72rem;
-  color: var(--color-foreground);
-}
-
-.hermes-kanban-comment {
-  border-left: 2px solid color-mix(in srgb, var(--color-ring) 35%, transparent);
-  padding-left: 0.5rem;
-  display: flex;
-  flex-direction: column;
-  gap: 0.2rem;
-}
-
-.hermes-kanban-comment-head {
-  display: flex;
-  gap: 0.5rem;
-  font-size: 0.7rem;
-}
-.hermes-kanban-comment-author {
-  font-weight: 600;
-  color: var(--color-foreground);
-}
-.hermes-kanban-comment-ago {
-  color: var(--color-muted-foreground);
-}
-
-.hermes-kanban-event {
-  display: flex;
-  gap: 0.5rem;
-  font-size: 0.7rem;
-  color: var(--color-muted-foreground);
-  font-family: var(--font-mono, ui-monospace, monospace);
-}
-.hermes-kanban-event-kind {
-  color: var(--color-foreground);
-  min-width: 6rem;
-}
-.hermes-kanban-event-payload {
-  color: var(--color-muted-foreground);
-  overflow: hidden;
-  text-overflow: ellipsis;
-  white-space: nowrap;
-  max-width: 280px;
-}
-
-.hermes-kanban-drawer-comment-row {
-  display: flex;
-  gap: 0.4rem;
-  padding: 0.55rem 0.75rem;
-  border-top: 1px solid var(--color-border);
-  background: color-mix(in srgb, var(--color-card) 90%, transparent);
-}
-
-.hermes-kanban-count {
-  display: inline-flex;
-  gap: 0.2rem;
-  align-items: center;
-}
-
-/* ---- Selection chrome ----------------------------------------------- */
-
-.hermes-kanban-card--selected :where(.hermes-kanban-card-content) {
-  box-shadow: 0 0 0 2px var(--color-ring) inset,
-              0 0 0 1px var(--color-ring) inset;
-  background: color-mix(in srgb, var(--color-ring) 6%, var(--color-card));
-}
-
-.hermes-kanban-card-check {
-  width: 0.85rem;
-  height: 0.85rem;
-  margin: 0;
-  cursor: pointer;
-  accent-color: var(--color-ring);
-}
-
-/* ---- Bulk action bar ------------------------------------------------ */
-
-.hermes-kanban-bulk {
-  display: flex;
-  align-items: center;
-  gap: 0.5rem;
-  padding: 0.4rem 0.75rem;
-  background: color-mix(in srgb, var(--color-ring) 10%, var(--color-card));
-  border: 1px solid color-mix(in srgb, var(--color-ring) 40%, var(--color-border));
-  border-radius: var(--radius-sm, 0.25rem);
-  flex-wrap: wrap;
-}
-.hermes-kanban-bulk-count {
-  font-weight: 600;
-  font-size: 0.75rem;
-  padding-right: 0.25rem;
-}
-.hermes-kanban-bulk-btn {
-  height: 1.7rem !important;
-  padding: 0 0.5rem !important;
-  font-size: 0.7rem !important;
-  border: 1px solid var(--color-border);
-  cursor: pointer;
-}
-.hermes-kanban-bulk-btn:hover {
-  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
-}
-.hermes-kanban-bulk-reassign {
-  display: flex;
-  align-items: center;
-  gap: 0.25rem;
-  padding-left: 0.5rem;
-  border-left: 1px solid color-mix(in srgb, var(--color-border) 70%, transparent);
-}
-
-/* ---- Dependency editor chips --------------------------------------- */
-
-.hermes-kanban-deps-row {
-  display: flex;
-  align-items: center;
-  gap: 0.5rem;
-  margin-bottom: 0.4rem;
-}
-.hermes-kanban-deps-label {
-  font-size: 0.68rem;
-  text-transform: uppercase;
-  letter-spacing: 0.08em;
-  color: var(--color-muted-foreground);
-  min-width: 4rem;
-}
-.hermes-kanban-deps-chips {
-  display: flex;
-  gap: 0.3rem;
-  flex-wrap: wrap;
-  flex: 1;
-}
-.hermes-kanban-deps-empty {
-  font-size: 0.7rem;
-  color: var(--color-muted-foreground);
-  font-style: italic;
-}
-.hermes-kanban-dep-chip {
-  display: inline-flex;
-  align-items: center;
-  gap: 0.15rem;
-  padding: 0.1rem 0.35rem;
-  background: color-mix(in srgb, var(--color-foreground) 6%, transparent);
-  border: 1px solid var(--color-border);
-  border-radius: var(--radius-sm, 0.25rem);
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.68rem;
-  color: var(--color-foreground);
-}
-.hermes-kanban-dep-chip-x {
-  appearance: none;
-  background: transparent;
-  border: 0;
-  color: var(--color-muted-foreground);
-  cursor: pointer;
-  font-size: 0.85rem;
-  line-height: 1;
-  padding: 0 0.15rem;
-}
-.hermes-kanban-dep-chip-x:hover { color: var(--color-destructive, #d14a4a); }
-
-/* ---- Inline edit affordances --------------------------------------- */
-
-.hermes-kanban-editable {
-  cursor: pointer;
-  border-bottom: 1px dotted color-mix(in srgb, var(--color-border) 80%, transparent);
-}
-.hermes-kanban-editable:hover {
-  color: var(--color-foreground);
-  border-bottom-color: var(--color-ring);
-}
-
-.hermes-kanban-drawer-title-text {
-  cursor: pointer;
-}
-.hermes-kanban-drawer-title-text:hover {
-  text-decoration: underline;
-  text-decoration-color: var(--color-ring);
-  text-decoration-style: dotted;
-  text-underline-offset: 3px;
-}
-
-.hermes-kanban-edit-row {
-  display: flex;
-  align-items: center;
-  gap: 0.35rem;
-  width: 100%;
-}
-
-.hermes-kanban-section-head-row {
-  display: flex;
-  align-items: center;
-  justify-content: space-between;
-  gap: 0.5rem;
-}
-.hermes-kanban-edit-link {
-  appearance: none;
-  background: transparent;
-  border: 0;
-  color: var(--color-muted-foreground);
-  font-size: 0.7rem;
-  text-transform: uppercase;
-  letter-spacing: 0.05em;
-  cursor: pointer;
-  padding: 0;
-}
-.hermes-kanban-edit-link:hover { color: var(--color-ring); }
-
-.hermes-kanban-textarea {
-  width: 100%;
-  min-height: 8rem;
-  background: var(--color-card);
-  color: var(--color-foreground);
-  border: 1px solid var(--color-border);
-  border-radius: var(--radius-sm, 0.25rem);
-  padding: 0.5rem 0.6rem;
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.8rem;
-  line-height: 1.5;
-  resize: vertical;
-}
-.hermes-kanban-textarea:focus {
-  outline: none;
-  border-color: var(--color-ring);
-  box-shadow: 0 0 0 2px color-mix(in srgb, var(--color-ring) 30%, transparent);
-}
-
-/* ---- Markdown rendering -------------------------------------------- */
-
-.hermes-kanban-md {
-  font-size: 0.8rem;
-  line-height: 1.55;
-  color: var(--color-foreground);
-}
-.hermes-kanban-md p  { margin: 0.25rem 0; }
-.hermes-kanban-md h1,
-.hermes-kanban-md h2,
-.hermes-kanban-md h3,
-.hermes-kanban-md h4 {
-  margin: 0.6rem 0 0.2rem;
-  line-height: 1.25;
-}
-.hermes-kanban-md h1 { font-size: 1.05rem; }
-.hermes-kanban-md h2 { font-size: 0.95rem; }
-.hermes-kanban-md h3 { font-size: 0.88rem; }
-.hermes-kanban-md h4 { font-size: 0.82rem; }
-.hermes-kanban-md ul {
-  margin: 0.25rem 0 0.25rem 1.1rem;
-  padding: 0;
-}
-.hermes-kanban-md li { margin: 0.1rem 0; }
-.hermes-kanban-md a {
-  color: var(--color-ring);
-  text-decoration: underline;
-}
-.hermes-kanban-md code {
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-size: 0.75rem;
-  padding: 0.05rem 0.3rem;
-  background: color-mix(in srgb, var(--color-foreground) 8%, transparent);
-  border-radius: 3px;
-}
-.hermes-kanban-md-code {
-  margin: 0.35rem 0;
-  padding: 0.5rem 0.6rem;
-  background: color-mix(in srgb, var(--color-foreground) 5%, transparent);
-  border: 1px solid var(--color-border);
-  border-radius: var(--radius-sm, 0.25rem);
-  overflow-x: auto;
-}
-.hermes-kanban-md-code code {
-  background: transparent;
-  padding: 0;
-  font-size: 0.75rem;
-  white-space: pre;
-}
-.hermes-kanban-md strong { font-weight: 600; }
-
-/* ---- Touch-drag proxy ---------------------------------------------- */
-
-.hermes-kanban-touch-proxy {
-  pointer-events: none;
-  opacity: 0.85;
-  box-shadow: 0 8px 20px rgba(0, 0, 0, 0.35);
-  transform: scale(1.02);
-  transition: none;
-}
-
-
-/* ---- Staleness tiers ------------------------------------------------ */
-
-.hermes-kanban-card--stale-amber :where(.hermes-kanban-card-content) {
-  box-shadow: 0 0 0 1px #d4b34888 inset;
-}
-.hermes-kanban-card--stale-amber:hover :where(.hermes-kanban-card-content) {
-  box-shadow: 0 0 0 2px #d4b348 inset;
-}
-.hermes-kanban-card--stale-red :where(.hermes-kanban-card-content) {
-  box-shadow: 0 0 0 1px var(--color-destructive, #d14a4a) inset,
-              0 0 8px color-mix(in srgb, var(--color-destructive, #d14a4a) 30%, transparent);
-}
-.hermes-kanban-card--stale-red:hover :where(.hermes-kanban-card-content) {
-  box-shadow: 0 0 0 2px var(--color-destructive, #d14a4a) inset,
-              0 0 10px color-mix(in srgb, var(--color-destructive, #d14a4a) 45%, transparent);
-}
-
-/* ---- Worker log pane ------------------------------------------------ */
-
-.hermes-kanban-log {
-  max-height: 340px;
-  overflow: auto;
-  white-space: pre;
-  font-size: 0.7rem;
-  line-height: 1.45;
-}
-
-
-/* ---- Run history (per-attempt log in the drawer) ------------------- */
-
-.hermes-kanban-run {
-  border-left: 2px solid var(--color-border);
-  padding: 0.35rem 0.5rem;
-  margin-bottom: 0.4rem;
-  background: color-mix(in srgb, var(--color-foreground) 3%, transparent);
-  border-radius: var(--radius-sm, 0.25rem);
-}
-.hermes-kanban-run--active  { border-left-color: #3fb97d; }
-.hermes-kanban-run--completed { border-left-color: #4a8cd1; }
-.hermes-kanban-run--ended { border-left-color: #6b7280; }  /* generic fallback when outcome is unset */
-.hermes-kanban-run--blocked { border-left-color: var(--color-destructive, #d14a4a); }
-.hermes-kanban-run--crashed,
-.hermes-kanban-run--timed_out,
-.hermes-kanban-run--gave_up,
-.hermes-kanban-run--spawn_failed {
-  border-left-color: var(--color-destructive, #d14a4a);
-  background: color-mix(in srgb, var(--color-destructive, #d14a4a) 6%, transparent);
-}
-.hermes-kanban-run--reclaimed { border-left-color: #d4b348; }
-
-.hermes-kanban-run-head {
-  display: flex;
-  align-items: center;
-  gap: 0.6rem;
-  font-size: 0.7rem;
-}
-.hermes-kanban-run-outcome {
-  font-family: var(--font-mono, ui-monospace, monospace);
-  font-weight: 600;
-  text-transform: uppercase;
-  letter-spacing: 0.05em;
-  color: var(--color-foreground);
-}
-.hermes-kanban-run-profile {
-  color: var(--color-muted-foreground);
-}
-.hermes-kanban-run-elapsed {
-  font-variant-numeric: tabular-nums;
-  color: var(--color-muted-foreground);
-}
-.hermes-kanban-run-ago {
-  margin-left: auto;
-  color: var(--color-muted-foreground);
-}
-.hermes-kanban-run-summary {
-  font-size: 0.75rem;
-  padding: 0.2rem 0 0;
-  color: var(--color-foreground);
-}
-.hermes-kanban-run-error {
-  font-size: 0.7rem;
-  color: var(--color-destructive, #d14a4a);
-  padding: 0.15rem 0 0;
-  font-family: var(--font-mono, ui-monospace, monospace);
-}
-.hermes-kanban-run-meta {
-  display: block;
-  font-size: 0.65rem;
-  padding: 0.15rem 0 0;
-  color: var(--color-muted-foreground);
-  white-space: pre-wrap;
-  word-break: break-word;
-  font-family: var(--font-mono, ui-monospace, monospace);
-}

plugins/kanban/dashboard/manifest.json

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

plugins/kanban/dashboard/plugin_api.py

@@ -1,830 +0,0 @@
-"""Kanban dashboard plugin — backend API routes.
-
-Mounted at /api/plugins/kanban/ by the dashboard plugin system.
-
-This layer is intentionally thin: every handler is a small wrapper around
-``hermes_cli.kanban_db`` or a direct SQL query. Writes use the same code
-paths the CLI and gateway ``/kanban`` command use, so the three surfaces
-cannot drift.
-
-Live updates arrive via the ``/events`` WebSocket, which tails the
-append-only ``task_events`` table on a short poll interval (WAL mode lets
-reads run alongside the dispatcher's IMMEDIATE write transactions).
-
-Security note
--------------
-The dashboard's HTTP auth middleware (``web_server.auth_middleware``)
-explicitly skips ``/api/plugins/`` — plugin routes are unauthenticated by
-design because the dashboard binds to localhost by default. For the
-WebSocket we still require the session token as a ``?token=`` query
-parameter (browsers cannot set the ``Authorization`` header on an upgrade
-request), matching the established pattern used by the in-browser PTY
-bridge in ``hermes_cli/web_server.py``. If you run the dashboard with
-``--host 0.0.0.0``, every plugin route — kanban included — becomes
-reachable from the network. Don't do that on a shared host.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import hmac
-import json
-import logging
-import sqlite3
-import time
-from dataclasses import asdict
-from typing import Any, Optional
-
-from fastapi import APIRouter, HTTPException, Query, WebSocket, WebSocketDisconnect, status as http_status
-from pydantic import BaseModel, Field
-
-from hermes_cli import kanban_db
-
-log = logging.getLogger(__name__)
-
-router = APIRouter()
-
-
-# ---------------------------------------------------------------------------
-# Auth helper — WebSocket only (HTTP routes live behind the dashboard's
-# existing plugin-bypass; this is documented above).
-# ---------------------------------------------------------------------------
-
-def _check_ws_token(provided: Optional[str]) -> bool:
-    """Constant-time compare against the dashboard session token.
-
-    Imported lazily so the plugin still loads in test contexts where the
-    dashboard web_server module isn't importable (e.g. the bare-FastAPI
-    test harness).
-    """
-    if not provided:
-        return False
-    try:
-        from hermes_cli import web_server as _ws
-    except Exception:
-        # No dashboard context (tests). Accept so the tail loop is still
-        # testable; in production the dashboard module always imports
-        # cleanly because it's the caller.
-        return True
-    expected = getattr(_ws, "_SESSION_TOKEN", None)
-    if not expected:
-        return True
-    return hmac.compare_digest(str(provided), str(expected))
-
-
-def _conn():
-    """Open a kanban_db connection, creating the schema on first use.
-
-    Every handler that mutates the DB goes through this so the plugin
-    self-heals on a fresh install (no user-visible "no such table"
-    error if somebody hits POST /tasks before GET /board).
-    ``init_db`` is idempotent.
-    """
-    try:
-        kanban_db.init_db()
-    except Exception as exc:
-        log.warning("kanban init_db failed: %s", exc)
-    return kanban_db.connect()
-
-
-# ---------------------------------------------------------------------------
-# Serialization helpers
-# ---------------------------------------------------------------------------
-
-# Columns shown by the dashboard, in left-to-right order. "archived" is
-# available via a filter toggle rather than a visible column.
-BOARD_COLUMNS: list[str] = [
-    "triage", "todo", "ready", "running", "blocked", "done",
-]
-
-
-def _task_dict(task: kanban_db.Task) -> dict[str, Any]:
-    d = asdict(task)
-    # Add derived age metrics so the UI can colour stale cards without
-    # computing deltas client-side.
-    d["age"] = kanban_db.task_age(task)
-    # Keep body short on list endpoints; full body comes from /tasks/:id.
-    return d
-
-
-def _event_dict(event: kanban_db.Event) -> dict[str, Any]:
-    return {
-        "id": event.id,
-        "task_id": event.task_id,
-        "kind": event.kind,
-        "payload": event.payload,
-        "created_at": event.created_at,
-        "run_id": event.run_id,
-    }
-
-
-def _comment_dict(c: kanban_db.Comment) -> dict[str, Any]:
-    return {
-        "id": c.id,
-        "task_id": c.task_id,
-        "author": c.author,
-        "body": c.body,
-        "created_at": c.created_at,
-    }
-
-
-def _run_dict(r: kanban_db.Run) -> dict[str, Any]:
-    """Serialise a Run for the drawer's Run history section."""
-    return {
-        "id": r.id,
-        "task_id": r.task_id,
-        "profile": r.profile,
-        "step_key": r.step_key,
-        "status": r.status,
-        "claim_lock": r.claim_lock,
-        "claim_expires": r.claim_expires,
-        "worker_pid": r.worker_pid,
-        "max_runtime_seconds": r.max_runtime_seconds,
-        "last_heartbeat_at": r.last_heartbeat_at,
-        "started_at": r.started_at,
-        "ended_at": r.ended_at,
-        "outcome": r.outcome,
-        "summary": r.summary,
-        "metadata": r.metadata,
-        "error": r.error,
-    }
-
-
-def _links_for(conn: sqlite3.Connection, task_id: str) -> dict[str, list[str]]:
-    """Return {'parents': [...], 'children': [...]} for a task."""
-    parents = [
-        r["parent_id"]
-        for r in conn.execute(
-            "SELECT parent_id FROM task_links WHERE child_id = ? ORDER BY parent_id",
-            (task_id,),
-        )
-    ]
-    children = [
-        r["child_id"]
-        for r in conn.execute(
-            "SELECT child_id FROM task_links WHERE parent_id = ? ORDER BY child_id",
-            (task_id,),
-        )
-    ]
-    return {"parents": parents, "children": children}
-
-
-# ---------------------------------------------------------------------------
-# GET /board
-# ---------------------------------------------------------------------------
-
-@router.get("/board")
-def get_board(
-    tenant: Optional[str] = Query(None, description="Filter to a single tenant"),
-    include_archived: bool = Query(False),
-):
-    """Return the full board grouped by status column.
-
-    ``_conn()`` auto-initializes ``kanban.db`` on first call so a fresh
-    install doesn't surface a "failed to load" error on the plugin tab.
-    """
-    conn = _conn()
-    try:
-        tasks = kanban_db.list_tasks(
-            conn, tenant=tenant, include_archived=include_archived
-        )
-        # Pre-fetch link counts per task (cheap: one query).
-        link_counts: dict[str, dict[str, int]] = {}
-        for row in conn.execute(
-            "SELECT parent_id, child_id FROM task_links"
-        ).fetchall():
-            link_counts.setdefault(row["parent_id"], {"parents": 0, "children": 0})[
-                "children"
-            ] += 1
-            link_counts.setdefault(row["child_id"], {"parents": 0, "children": 0})[
-                "parents"
-            ] += 1
-
-        # Comment + event counts (both cheap aggregates).
-        comment_counts: dict[str, int] = {
-            r["task_id"]: r["n"]
-            for r in conn.execute(
-                "SELECT task_id, COUNT(*) AS n FROM task_comments GROUP BY task_id"
-            )
-        }
-
-        # Progress rollup: for each parent, how many children are done / total.
-        # One pass over task_links joined with child status — cheaper than
-        # N per-task queries and the plugin uses it to render "N/M".
-        progress: dict[str, dict[str, int]] = {}
-        for row in conn.execute(
-            "SELECT l.parent_id AS pid, t.status AS cstatus "
-            "FROM task_links l JOIN tasks t ON t.id = l.child_id"
-        ).fetchall():
-            p = progress.setdefault(row["pid"], {"done": 0, "total": 0})
-            p["total"] += 1
-            if row["cstatus"] == "done":
-                p["done"] += 1
-
-        latest_event_id = conn.execute(
-            "SELECT COALESCE(MAX(id), 0) AS m FROM task_events"
-        ).fetchone()["m"]
-
-        columns: dict[str, list[dict]] = {c: [] for c in BOARD_COLUMNS}
-        if include_archived:
-            columns["archived"] = []
-
-        for t in tasks:
-            d = _task_dict(t)
-            d["link_counts"] = link_counts.get(t.id, {"parents": 0, "children": 0})
-            d["comment_count"] = comment_counts.get(t.id, 0)
-            d["progress"] = progress.get(t.id)  # None when the task has no children
-            col = t.status if t.status in columns else "todo"
-            columns[col].append(d)
-
-        # Stable per-column ordering already applied by list_tasks
-        # (priority DESC, created_at ASC), keep as-is.
-
-        # List of known tenants for the UI filter dropdown.
-        tenants = [
-            r["tenant"]
-            for r in conn.execute(
-                "SELECT DISTINCT tenant FROM tasks WHERE tenant IS NOT NULL ORDER BY tenant"
-            )
-        ]
-        # List of distinct assignees for the lane-by-profile sub-grouping.
-        assignees = [
-            r["assignee"]
-            for r in conn.execute(
-                "SELECT DISTINCT assignee FROM tasks WHERE assignee IS NOT NULL "
-                "AND status != 'archived' ORDER BY assignee"
-            )
-        ]
-
-        return {
-            "columns": [
-                {"name": name, "tasks": columns[name]} for name in columns.keys()
-            ],
-            "tenants": tenants,
-            "assignees": assignees,
-            "latest_event_id": int(latest_event_id),
-            "now": int(time.time()),
-        }
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# GET /tasks/:id
-# ---------------------------------------------------------------------------
-
-@router.get("/tasks/{task_id}")
-def get_task(task_id: str):
-    conn = _conn()
-    try:
-        task = kanban_db.get_task(conn, task_id)
-        if task is None:
-            raise HTTPException(status_code=404, detail=f"task {task_id} not found")
-        return {
-            "task": _task_dict(task),
-            "comments": [_comment_dict(c) for c in kanban_db.list_comments(conn, task_id)],
-            "events": [_event_dict(e) for e in kanban_db.list_events(conn, task_id)],
-            "links": _links_for(conn, task_id),
-            "runs": [_run_dict(r) for r in kanban_db.list_runs(conn, task_id)],
-        }
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# POST /tasks
-# ---------------------------------------------------------------------------
-
-class CreateTaskBody(BaseModel):
-    title: str
-    body: Optional[str] = None
-    assignee: Optional[str] = None
-    tenant: Optional[str] = None
-    priority: int = 0
-    workspace_kind: str = "scratch"
-    workspace_path: Optional[str] = None
-    parents: list[str] = Field(default_factory=list)
-    triage: bool = False
-    idempotency_key: Optional[str] = None
-    max_runtime_seconds: Optional[int] = None
-    skills: Optional[list[str]] = None
-
-
-@router.post("/tasks")
-def create_task(payload: CreateTaskBody):
-    conn = _conn()
-    try:
-        task_id = kanban_db.create_task(
-            conn,
-            title=payload.title,
-            body=payload.body,
-            assignee=payload.assignee,
-            created_by="dashboard",
-            workspace_kind=payload.workspace_kind,
-            workspace_path=payload.workspace_path,
-            tenant=payload.tenant,
-            priority=payload.priority,
-            parents=payload.parents,
-            triage=payload.triage,
-            idempotency_key=payload.idempotency_key,
-            max_runtime_seconds=payload.max_runtime_seconds,
-            skills=payload.skills,
-        )
-        task = kanban_db.get_task(conn, task_id)
-        return {"task": _task_dict(task) if task else None}
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# PATCH /tasks/:id  (status / assignee / priority / title / body)
-# ---------------------------------------------------------------------------
-
-class UpdateTaskBody(BaseModel):
-    status: Optional[str] = None
-    assignee: Optional[str] = None
-    priority: Optional[int] = None
-    title: Optional[str] = None
-    body: Optional[str] = None
-    result: Optional[str] = None
-    block_reason: Optional[str] = None
-    # Structured handoff fields — forwarded to complete_task when status
-    # transitions to 'done'. Dashboard parity with ``hermes kanban
-    # complete --summary ... --metadata ...``.
-    summary: Optional[str] = None
-    metadata: Optional[dict] = None
-
-
-@router.patch("/tasks/{task_id}")
-def update_task(task_id: str, payload: UpdateTaskBody):
-    conn = _conn()
-    try:
-        task = kanban_db.get_task(conn, task_id)
-        if task is None:
-            raise HTTPException(status_code=404, detail=f"task {task_id} not found")
-
-        # --- assignee ----------------------------------------------------
-        if payload.assignee is not None:
-            try:
-                ok = kanban_db.assign_task(
-                    conn, task_id, payload.assignee or None,
-                )
-            except RuntimeError as e:
-                raise HTTPException(status_code=409, detail=str(e))
-            if not ok:
-                raise HTTPException(status_code=404, detail="task not found")
-
-        # --- status -------------------------------------------------------
-        if payload.status is not None:
-            s = payload.status
-            ok = True
-            if s == "done":
-                ok = kanban_db.complete_task(
-                    conn, task_id,
-                    result=payload.result,
-                    summary=payload.summary,
-                    metadata=payload.metadata,
-                )
-            elif s == "blocked":
-                ok = kanban_db.block_task(conn, task_id, reason=payload.block_reason)
-            elif s == "ready":
-                # Re-open a blocked task, or just an explicit status set.
-                current = kanban_db.get_task(conn, task_id)
-                if current and current.status == "blocked":
-                    ok = kanban_db.unblock_task(conn, task_id)
-                else:
-                    # Direct status write for drag-drop (todo -> ready etc).
-                    ok = _set_status_direct(conn, task_id, "ready")
-            elif s == "archived":
-                ok = kanban_db.archive_task(conn, task_id)
-            elif s in ("todo", "running", "triage"):
-                ok = _set_status_direct(conn, task_id, s)
-            else:
-                raise HTTPException(status_code=400, detail=f"unknown status: {s}")
-            if not ok:
-                raise HTTPException(
-                    status_code=409,
-                    detail=f"status transition to {s!r} not valid from current state",
-                )
-
-        # --- priority -----------------------------------------------------
-        if payload.priority is not None:
-            with kanban_db.write_txn(conn):
-                conn.execute(
-                    "UPDATE tasks SET priority = ? WHERE id = ?",
-                    (int(payload.priority), task_id),
-                )
-                conn.execute(
-                    "INSERT INTO task_events (task_id, kind, payload, created_at) "
-                    "VALUES (?, 'reprioritized', ?, ?)",
-                    (task_id, json.dumps({"priority": int(payload.priority)}),
-                     int(time.time())),
-                )
-
-        # --- title / body -------------------------------------------------
-        if payload.title is not None or payload.body is not None:
-            with kanban_db.write_txn(conn):
-                sets, vals = [], []
-                if payload.title is not None:
-                    if not payload.title.strip():
-                        raise HTTPException(status_code=400, detail="title cannot be empty")
-                    sets.append("title = ?")
-                    vals.append(payload.title.strip())
-                if payload.body is not None:
-                    sets.append("body = ?")
-                    vals.append(payload.body)
-                vals.append(task_id)
-                conn.execute(
-                    f"UPDATE tasks SET {', '.join(sets)} WHERE id = ?", vals,
-                )
-                conn.execute(
-                    "INSERT INTO task_events (task_id, kind, payload, created_at) "
-                    "VALUES (?, 'edited', NULL, ?)",
-                    (task_id, int(time.time())),
-                )
-
-        updated = kanban_db.get_task(conn, task_id)
-        return {"task": _task_dict(updated) if updated else None}
-    finally:
-        conn.close()
-
-
-def _set_status_direct(
-    conn: sqlite3.Connection, task_id: str, new_status: str,
-) -> bool:
-    """Direct status write for drag-drop moves that aren't covered by the
-    structured complete/block/unblock/archive verbs (e.g. todo<->ready,
-    running<->ready). Appends a ``status`` event row for the live feed.
-
-    When this transitions OFF ``running`` to anything other than the
-    terminal verbs above (which own their own run closing), we close the
-    active run with outcome='reclaimed' so attempt history isn't
-    orphaned. ``running -> ready`` via drag-drop is the common case
-    (user yanking a stuck worker back to the queue).
-    """
-    with kanban_db.write_txn(conn):
-        # Snapshot current state so we know whether to close a run.
-        prev = conn.execute(
-            "SELECT status, current_run_id FROM tasks WHERE id = ?",
-            (task_id,),
-        ).fetchone()
-        if prev is None:
-            return False
-        was_running = prev["status"] == "running"
-
-        cur = conn.execute(
-            "UPDATE tasks SET status = ?, "
-            "  claim_lock = CASE WHEN ? = 'running' THEN claim_lock ELSE NULL END, "
-            "  claim_expires = CASE WHEN ? = 'running' THEN claim_expires ELSE NULL END, "
-            "  worker_pid = CASE WHEN ? = 'running' THEN worker_pid ELSE NULL END "
-            "WHERE id = ?",
-            (new_status, new_status, new_status, new_status, task_id),
-        )
-        if cur.rowcount != 1:
-            return False
-        run_id = None
-        if was_running and new_status != "running" and prev["current_run_id"]:
-            run_id = kanban_db._end_run(
-                conn, task_id,
-                outcome="reclaimed", status="reclaimed",
-                summary=f"status changed to {new_status} (dashboard/direct)",
-            )
-        conn.execute(
-            "INSERT INTO task_events (task_id, run_id, kind, payload, created_at) "
-            "VALUES (?, ?, 'status', ?, ?)",
-            (task_id, run_id, json.dumps({"status": new_status}), int(time.time())),
-        )
-    # If we re-opened something, children may have gone stale.
-    if new_status in ("done", "ready"):
-        kanban_db.recompute_ready(conn)
-    return True
-
-
-# ---------------------------------------------------------------------------
-# Comments
-# ---------------------------------------------------------------------------
-
-class CommentBody(BaseModel):
-    body: str
-    author: Optional[str] = "dashboard"
-
-
-@router.post("/tasks/{task_id}/comments")
-def add_comment(task_id: str, payload: CommentBody):
-    if not payload.body.strip():
-        raise HTTPException(status_code=400, detail="body is required")
-    conn = _conn()
-    try:
-        if kanban_db.get_task(conn, task_id) is None:
-            raise HTTPException(status_code=404, detail=f"task {task_id} not found")
-        kanban_db.add_comment(
-            conn, task_id, author=payload.author or "dashboard", body=payload.body,
-        )
-        return {"ok": True}
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# Links
-# ---------------------------------------------------------------------------
-
-class LinkBody(BaseModel):
-    parent_id: str
-    child_id: str
-
-
-@router.post("/links")
-def add_link(payload: LinkBody):
-    conn = _conn()
-    try:
-        kanban_db.link_tasks(conn, payload.parent_id, payload.child_id)
-        return {"ok": True}
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    finally:
-        conn.close()
-
-
-@router.delete("/links")
-def delete_link(parent_id: str = Query(...), child_id: str = Query(...)):
-    conn = _conn()
-    try:
-        ok = kanban_db.unlink_tasks(conn, parent_id, child_id)
-        return {"ok": bool(ok)}
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# Bulk actions (multi-select on the board)
-# ---------------------------------------------------------------------------
-
-class BulkTaskBody(BaseModel):
-    ids: list[str]
-    status: Optional[str] = None
-    assignee: Optional[str] = None  # "" or None = unassign
-    priority: Optional[int] = None
-    archive: bool = False
-
-
-@router.post("/tasks/bulk")
-def bulk_update(payload: BulkTaskBody):
-    """Apply the same patch to every id in ``payload.ids``.
-
-    This is an *independent* iteration — per-task failures don't abort
-    siblings. Returns per-id outcome so the UI can surface partials.
-    """
-    ids = [i for i in (payload.ids or []) if i]
-    if not ids:
-        raise HTTPException(status_code=400, detail="ids is required")
-    results: list[dict] = []
-    conn = _conn()
-    try:
-        for tid in ids:
-            entry: dict[str, Any] = {"id": tid, "ok": True}
-            try:
-                task = kanban_db.get_task(conn, tid)
-                if task is None:
-                    entry.update(ok=False, error="not found")
-                    results.append(entry)
-                    continue
-                if payload.archive:
-                    if not kanban_db.archive_task(conn, tid):
-                        entry.update(ok=False, error="archive refused")
-                if payload.status is not None and not payload.archive:
-                    s = payload.status
-                    if s == "done":
-                        ok = kanban_db.complete_task(conn, tid)
-                    elif s == "blocked":
-                        ok = kanban_db.block_task(conn, tid)
-                    elif s == "ready":
-                        cur = kanban_db.get_task(conn, tid)
-                        if cur and cur.status == "blocked":
-                            ok = kanban_db.unblock_task(conn, tid)
-                        else:
-                            ok = _set_status_direct(conn, tid, "ready")
-                    elif s in ("todo", "running", "triage"):
-                        ok = _set_status_direct(conn, tid, s)
-                    else:
-                        entry.update(ok=False, error=f"unknown status {s!r}")
-                        results.append(entry)
-                        continue
-                    if not ok:
-                        entry.update(ok=False, error=f"transition to {s!r} refused")
-                if payload.assignee is not None:
-                    try:
-                        if not kanban_db.assign_task(
-                            conn, tid, payload.assignee or None,
-                        ):
-                            entry.update(ok=False, error="assign refused")
-                    except RuntimeError as e:
-                        entry.update(ok=False, error=str(e))
-                if payload.priority is not None:
-                    with kanban_db.write_txn(conn):
-                        conn.execute(
-                            "UPDATE tasks SET priority = ? WHERE id = ?",
-                            (int(payload.priority), tid),
-                        )
-                        conn.execute(
-                            "INSERT INTO task_events (task_id, kind, payload, created_at) "
-                            "VALUES (?, 'reprioritized', ?, ?)",
-                            (tid, json.dumps({"priority": int(payload.priority)}),
-                             int(time.time())),
-                        )
-            except Exception as e:  # defensive — one bad id shouldn't kill the batch
-                entry.update(ok=False, error=str(e))
-            results.append(entry)
-        return {"results": results}
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# Plugin config (read dashboard.kanban.* defaults from config.yaml)
-# ---------------------------------------------------------------------------
-
-@router.get("/config")
-def get_config():
-    """Return kanban dashboard preferences from ~/.hermes/config.yaml.
-
-    Reads the ``dashboard.kanban`` section if present; defaults otherwise.
-    Used by the UI to pre-select tenant filters, toggle markdown rendering,
-    or set column-width preferences without a round-trip per page load.
-    """
-    try:
-        from hermes_cli.config import load_config
-        cfg = load_config() or {}
-    except Exception:
-        cfg = {}
-    dash_cfg = (cfg.get("dashboard") or {})
-    # dashboard.kanban may itself be a dict; fall back to {}.
-    k_cfg = dash_cfg.get("kanban") or {}
-    return {
-        "default_tenant": k_cfg.get("default_tenant") or "",
-        "lane_by_profile": bool(k_cfg.get("lane_by_profile", True)),
-        "include_archived_by_default": bool(k_cfg.get("include_archived_by_default", False)),
-        "render_markdown": bool(k_cfg.get("render_markdown", True)),
-    }
-
-
-# ---------------------------------------------------------------------------
-# Stats (per-profile / per-status counts + oldest-ready age)
-# ---------------------------------------------------------------------------
-
-@router.get("/stats")
-def get_stats():
-    """Per-status + per-assignee counts + oldest-ready age.
-
-    Designed for the dashboard HUD and for router profiles that need to
-    answer "is this specialist overloaded?" without scanning the whole
-    board themselves.
-    """
-    conn = _conn()
-    try:
-        return kanban_db.board_stats(conn)
-    finally:
-        conn.close()
-
-
-@router.get("/assignees")
-def get_assignees():
-    """Known profiles + per-profile task counts.
-
-    Returns the union of ``~/.hermes/profiles/*`` on disk and every
-    distinct assignee currently used on the board. The dashboard uses
-    this to populate its assignee dropdown so a freshly-created profile
-    appears in the picker before it's been given any task.
-    """
-    conn = _conn()
-    try:
-        return {"assignees": kanban_db.known_assignees(conn)}
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# Worker log (read-only; file written by _default_spawn)
-# ---------------------------------------------------------------------------
-
-@router.get("/tasks/{task_id}/log")
-def get_task_log(task_id: str, tail: Optional[int] = Query(None, ge=1, le=2_000_000)):
-    """Return the worker's stdout/stderr log.
-
-    ``tail`` caps the response size (bytes) so the dashboard drawer
-    doesn't paginate megabytes into the browser. Returns 404 if the task
-    has never spawned. The on-disk log is rotated at 2 MiB per
-    ``_rotate_worker_log`` — a single ``.log.1`` is kept, no further
-    generations, so disk usage per task is bounded at ~4 MiB.
-    """
-    conn = _conn()
-    try:
-        task = kanban_db.get_task(conn, task_id)
-    finally:
-        conn.close()
-    if task is None:
-        raise HTTPException(status_code=404, detail=f"task {task_id} not found")
-    content = kanban_db.read_worker_log(task_id, tail_bytes=tail)
-    log_path = kanban_db.worker_log_path(task_id)
-    size = log_path.stat().st_size if log_path.exists() else 0
-    return {
-        "task_id": task_id,
-        "path": str(log_path),
-        "exists": content is not None,
-        "size_bytes": size,
-        "content": content or "",
-        # Truncated when the on-disk file was larger than the tail cap.
-        "truncated": bool(tail and size > tail),
-    }
-
-
-# ---------------------------------------------------------------------------
-# Dispatch nudge (optional quick-path so the UI doesn't wait 60 s)
-# ---------------------------------------------------------------------------
-
-@router.post("/dispatch")
-def dispatch(dry_run: bool = Query(False), max_n: int = Query(8, alias="max")):
-    conn = _conn()
-    try:
-        result = kanban_db.dispatch_once(
-            conn, dry_run=dry_run, max_spawn=max_n,
-        )
-        # DispatchResult is a dataclass.
-        try:
-            return asdict(result)
-        except TypeError:
-            return {"result": str(result)}
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# WebSocket: /events?since=<event_id>
-# ---------------------------------------------------------------------------
-
-# Poll interval for the event tail loop. SQLite WAL + 300 ms polling is
-# the simplest and most robust approach; it adds a fraction of a percent
-# of CPU and has no shared state to synchronize across workers.
-_EVENT_POLL_SECONDS = 0.3
-
-
-@router.websocket("/events")
-async def stream_events(ws: WebSocket):
-    # Enforce the dashboard session token as a query param — browsers can't
-    # set Authorization on a WS upgrade. This matches how the PTY bridge
-    # authenticates in hermes_cli/web_server.py.
-    token = ws.query_params.get("token")
-    if not _check_ws_token(token):
-        await ws.close(code=http_status.WS_1008_POLICY_VIOLATION)
-        return
-    await ws.accept()
-    try:
-        since_raw = ws.query_params.get("since", "0")
-        try:
-            cursor = int(since_raw)
-        except ValueError:
-            cursor = 0
-
-        def _fetch_new(cursor_val: int) -> tuple[int, list[dict]]:
-            conn = kanban_db.connect()
-            try:
-                rows = conn.execute(
-                    "SELECT id, task_id, run_id, kind, payload, created_at "
-                    "FROM task_events WHERE id > ? ORDER BY id ASC LIMIT 200",
-                    (cursor_val,),
-                ).fetchall()
-                out: list[dict] = []
-                new_cursor = cursor_val
-                for r in rows:
-                    try:
-                        payload = json.loads(r["payload"]) if r["payload"] else None
-                    except Exception:
-                        payload = None
-                    out.append({
-                        "id": r["id"],
-                        "task_id": r["task_id"],
-                        "run_id": r["run_id"],
-                        "kind": r["kind"],
-                        "payload": payload,
-                        "created_at": r["created_at"],
-                    })
-                    new_cursor = r["id"]
-                return new_cursor, out
-            finally:
-                conn.close()
-
-        while True:
-            cursor, events = await asyncio.to_thread(_fetch_new, cursor)
-            if events:
-                await ws.send_json({"events": events, "cursor": cursor})
-            await asyncio.sleep(_EVENT_POLL_SECONDS)
-    except WebSocketDisconnect:
-        return
-    except Exception as exc:  # defensive: never crash the dashboard worker
-        log.warning("Kanban event stream error: %s", exc)
-        try:
-            await ws.close()
-        except Exception:
-            pass

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

@@ -1,17 +0,0 @@
-[Unit]
-Description=Hermes Kanban dispatcher (hermes kanban daemon)
-Documentation=https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban
-After=network.target
-
-[Service]
-Type=simple
-ExecStart=/usr/bin/env hermes kanban daemon --interval 60 --pidfile %t/hermes-kanban-dispatcher.pid
-Restart=on-failure
-RestartSec=5
-# Log to the journal via stdout/stderr; the dispatcher also writes per-task
-# worker output to $HERMES_HOME/kanban/logs/<task>.log.
-StandardOutput=journal
-StandardError=journal
-
-[Install]
-WantedBy=default.target

run_agent.py

@@ -40,7 +40,6 @@ from types import SimpleNamespace
 import urllib.request
 import uuid
 from typing import List, Dict, Any, Optional
-from urllib.parse import urlparse, parse_qs, urlunparse
 from openai import OpenAI
 import fire
 from datetime import datetime
@@ -86,7 +85,6 @@ from agent.error_classifier import classify_api_error, FailoverReason
 from agent.prompt_builder import (
     DEFAULT_AGENT_IDENTITY, PLATFORM_HINTS,
     MEMORY_GUIDANCE, SESSION_SEARCH_GUIDANCE, SKILLS_GUIDANCE,
-    KANBAN_GUIDANCE,
     build_nous_subscription_prompt,
 )
 from agent.model_metadata import (
@@ -893,6 +891,7 @@ class AIAgent:
         checkpoints_enabled: bool = False,
         checkpoint_max_snapshots: int = 50,
         pass_session_id: bool = False,
+        persist_session: bool = True,
     ):
         """
         Initialize the AI Agent.
@@ -964,6 +963,7 @@ class AIAgent:
         self.background_review_callback = None  # Optional sync callback for gateway delivery
         self.skip_context_files = skip_context_files
         self.pass_session_id = pass_session_id
+        self.persist_session = persist_session
         self._credential_pool = credential_pool
         self.log_prefix_chars = log_prefix_chars
         self.log_prefix = f"{log_prefix} " if log_prefix else ""
@@ -1033,16 +1033,12 @@ class AIAgent:
         # surface.
         # When api_mode was explicitly provided, respect it — the user
         # knows what their endpoint supports (#10473).
-        # Exception: Azure OpenAI serves gpt-5.x on /chat/completions and
-        # does NOT support the Responses API — skip the upgrade for Azure
-        # (openai.azure.com), even though it looks OpenAI-compatible.
         if (
             api_mode is None
             and self.api_mode == "chat_completions"
             and self.provider != "copilot-acp"
             and not str(self.base_url or "").lower().startswith("acp://copilot")
             and not str(self.base_url or "").lower().startswith("acp+tcp://")
-            and not self._is_azure_openai_url()
             and (
                 self._is_direct_openai_url()
                 or self._provider_model_requires_responses_api(
@@ -1318,22 +1314,7 @@ class AIAgent:
             if api_key and base_url:
                 # Explicit credentials from CLI/gateway — construct directly.
                 # The runtime provider resolver already handled auth for us.
-                # Extract query params (e.g. Azure api-version) from base_url
-                # and pass via default_query to prevent loss during SDK URL
-                # joining (httpx drops query string when joining paths).
-                _parsed_url = urlparse(base_url)
-                if _parsed_url.query:
-                    _clean_url = urlunparse(_parsed_url._replace(query=""))
-                    _query_params = {
-                        k: v[0] for k, v in parse_qs(_parsed_url.query).items()
-                    }
-                    client_kwargs = {
-                        "api_key": api_key,
-                        "base_url": _clean_url,
-                        "default_query": _query_params,
-                    }
-                else:
-                    client_kwargs = {"api_key": api_key, "base_url": base_url}
+                client_kwargs = {"api_key": api_key, "base_url": base_url}
                 if _provider_timeout is not None:
                     client_kwargs["timeout"] = _provider_timeout
                 if self.provider == "copilot-acp":
@@ -1784,64 +1765,43 @@ class AIAgent:
         # Store for reuse in switch_model (so config override persists across model switches)
         self._config_context_length = _config_context_length
 
-        # Resolve custom_providers list once for reuse below (startup
-        # context-length override and plugin context-engine init).
-        try:
-            from hermes_cli.config import get_compatible_custom_providers
-            _custom_providers = get_compatible_custom_providers(_agent_cfg)
-        except Exception:
-            _custom_providers = _agent_cfg.get("custom_providers")
-            if not isinstance(_custom_providers, list):
-                _custom_providers = []
-
         # Check custom_providers per-model context_length
-        if _config_context_length is None and _custom_providers:
+        if _config_context_length is None:
             try:
-                from hermes_cli.config import get_custom_provider_context_length
-                _cp_ctx_resolved = get_custom_provider_context_length(
-                    model=self.model,
-                    base_url=self.base_url,
-                    custom_providers=_custom_providers,
-                )
-                if _cp_ctx_resolved:
-                    _config_context_length = int(_cp_ctx_resolved)
+                from hermes_cli.config import get_compatible_custom_providers
+                _custom_providers = get_compatible_custom_providers(_agent_cfg)
             except Exception:
-                _cp_ctx_resolved = None
-
-            # Surface a clear warning if the user set a context_length but it
-            # wasn't a valid positive int — the helper silently skips those.
-            if _config_context_length is None:
-                _target = self.base_url.rstrip("/") if self.base_url else ""
-                for _cp_entry in _custom_providers:
-                    if not isinstance(_cp_entry, dict):
-                        continue
-                    _cp_url = (_cp_entry.get("base_url") or "").rstrip("/")
-                    if _target and _cp_url == _target:
-                        _cp_models = _cp_entry.get("models", {})
-                        if isinstance(_cp_models, dict):
-                            _cp_model_cfg = _cp_models.get(self.model, {})
-                            if isinstance(_cp_model_cfg, dict):
-                                _cp_ctx = _cp_model_cfg.get("context_length")
-                                if _cp_ctx is not None:
-                                    try:
-                                        _parsed = int(_cp_ctx)
-                                        if _parsed <= 0:
-                                            raise ValueError
-                                    except (TypeError, ValueError):
-                                        logger.warning(
-                                            "Invalid context_length for model %r in "
-                                            "custom_providers: %r — must be a positive "
-                                            "integer (e.g. 256000, not '256K'). "
-                                            "Falling back to auto-detection.",
-                                            self.model, _cp_ctx,
-                                        )
-                                        print(
-                                            f"\n⚠ Invalid context_length for model {self.model!r} in custom_providers: {_cp_ctx!r}\n"
-                                            f"  Must be a positive integer (e.g. 256000, not '256K').\n"
-                                            f"  Falling back to auto-detected context window.\n",
-                                            file=sys.stderr,
-                                        )
-                        break
+                _custom_providers = _agent_cfg.get("custom_providers")
+                if not isinstance(_custom_providers, list):
+                    _custom_providers = []
+            for _cp_entry in _custom_providers:
+                if not isinstance(_cp_entry, dict):
+                    continue
+                _cp_url = (_cp_entry.get("base_url") or "").rstrip("/")
+                if _cp_url and _cp_url == self.base_url.rstrip("/"):
+                    _cp_models = _cp_entry.get("models", {})
+                    if isinstance(_cp_models, dict):
+                        _cp_model_cfg = _cp_models.get(self.model, {})
+                        if isinstance(_cp_model_cfg, dict):
+                            _cp_ctx = _cp_model_cfg.get("context_length")
+                            if _cp_ctx is not None:
+                                try:
+                                    _config_context_length = int(_cp_ctx)
+                                except (TypeError, ValueError):
+                                    logger.warning(
+                                        "Invalid context_length for model %r in "
+                                        "custom_providers: %r — must be a plain "
+                                        "integer (e.g. 256000, not '256K'). "
+                                        "Falling back to auto-detection.",
+                                        self.model, _cp_ctx,
+                                    )
+                                    print(
+                                        f"\n⚠ Invalid context_length for model {self.model!r} in custom_providers: {_cp_ctx!r}\n"
+                                        f"  Must be a plain integer (e.g. 256000, not '256K').\n"
+                                        f"  Falling back to auto-detected context window.\n",
+                                        file=sys.stderr,
+                                    )
+                    break
         
         # Select context engine: config-driven (like memory providers).
         # 1. Check config.yaml context.engine setting
@@ -1891,7 +1851,6 @@ class AIAgent:
                 api_key=getattr(self, "api_key", ""),
                 config_context_length=_config_context_length,
                 provider=self.provider,
-                custom_providers=_custom_providers,
             )
             self.context_compressor.update_model(
                 model=self.model,
@@ -2182,23 +2141,12 @@ class AIAgent:
         # ── Update context compressor ──
         if hasattr(self, "context_compressor") and self.context_compressor:
             from agent.model_metadata import get_model_context_length
-            # Re-read custom_providers from live config so per-model
-            # context_length overrides are honored when switching to a
-            # custom provider mid-session (closes #15779).
-            _sm_custom_providers = None
-            try:
-                from hermes_cli.config import load_config, get_compatible_custom_providers
-                _sm_cfg = load_config()
-                _sm_custom_providers = get_compatible_custom_providers(_sm_cfg)
-            except Exception:
-                _sm_custom_providers = None
             new_context_length = get_model_context_length(
                 self.model,
                 base_url=self.base_url,
                 api_key=self.api_key,
                 provider=self.provider,
                 config_context_length=getattr(self, "_config_context_length", None),
-                custom_providers=_sm_custom_providers,
             )
             self.context_compressor.update_model(
                 model=self.model,
@@ -2556,22 +2504,6 @@ class AIAgent:
             )
         return hostname == "api.openai.com"
 
-    def _is_azure_openai_url(self, base_url: str = None) -> bool:
-        """Return True when a base URL targets Azure OpenAI.
-
-        Azure OpenAI exposes an OpenAI-compatible endpoint at
-        ``{resource}.openai.azure.com/openai/v1`` that accepts the
-        standard ``openai`` Python client.  Unlike api.openai.com it
-        does NOT support the Responses API — gpt-5.x models are served
-        on the regular ``/chat/completions`` path — so routing decisions
-        must treat Azure separately from direct OpenAI.
-        """
-        if base_url is not None:
-            url = str(base_url).lower()
-        else:
-            url = getattr(self, "_base_url_lower", "") or ""
-        return "openai.azure.com" in url
-
     def _resolved_api_call_timeout(self) -> float:
         """Resolve the effective per-call request timeout in seconds.
 
@@ -2743,14 +2675,12 @@ class AIAgent:
 
     def _max_tokens_param(self, value: int) -> dict:
         """Return the correct max tokens kwarg for the current provider.
-
+        
         OpenAI's newer models (gpt-4o, o-series, gpt-5+) require
-        'max_completion_tokens'. Azure OpenAI also requires
-        'max_completion_tokens' for gpt-5.x models served via the
-        OpenAI-compatible endpoint. OpenRouter, local models, and older
+        'max_completion_tokens'. OpenRouter, local models, and older
         OpenAI models use 'max_tokens'.
         """
-        if self._is_direct_openai_url() or self._is_azure_openai_url():
+        if self._is_direct_openai_url():
             return {"max_completion_tokens": value}
         return {"max_tokens": value}
 
@@ -3108,28 +3038,13 @@ class AIAgent:
     )
 
     _SKILL_REVIEW_PROMPT = (
-        "Review the conversation above and consider whether a skill should be saved or updated.\n\n"
-        "Work in this order — do not skip steps:\n\n"
-        "1. SURVEY the existing skill landscape first. Call skills_list to see what you "
-        "have. If anything looks potentially relevant, skill_view it before deciding. "
-        "You are looking for the CLASS of task that just happened, not the exact task. "
-        "Example: a successful Tauri build is in the class \"desktop app build "
-        "troubleshooting\", not \"fix my specific Tauri error today\".\n\n"
-        "2. THINK CLASS-FIRST. What general pattern of task did the user just complete? "
-        "What conditions will trigger this pattern again? Describe the class in one "
-        "sentence before looking at what to save.\n\n"
-        "3. PREFER GENERALIZING AN EXISTING SKILL over creating a new one. If a skill "
-        "already covers the class — even partially — update it (skill_manage patch) "
-        "with the new insight. Broaden its \"when to use\" trigger if needed.\n\n"
-        "4. ONLY CREATE A NEW SKILL when no existing skill reasonably covers the class. "
-        "When you create one, name and scope it at the class level "
-        "(\"react-i18n-setup\", not \"add-i18n-to-my-dashboard-app\"). The trigger "
-        "section must describe the class of situations, not this one session.\n\n"
-        "5. If you notice two existing skills that overlap, note it in your response "
-        "so a future review can consolidate them. Do not consolidate now unless the "
-        "overlap is obvious and low-risk.\n\n"
-        "Only act when something is genuinely worth saving. "
-        "If nothing stands out, just say 'Nothing to save.' and stop."
+        "Review the conversation above and consider saving or updating a skill if appropriate.\n\n"
+        "Focus on: was a non-trivial approach used to complete a task that required trial "
+        "and error, or changing course due to experiential findings along the way, or did "
+        "the user expect or desire a different method or outcome?\n\n"
+        "If a relevant skill already exists, update it with what you learned. "
+        "Otherwise, create a new skill if the approach is reusable.\n"
+        "If nothing is worth saving, just say 'Nothing to save.' and stop."
     )
 
     _COMBINED_REVIEW_PROMPT = (
@@ -3139,16 +3054,9 @@ class AIAgent:
         "about how you should behave, their work style, or ways they want you to operate? "
         "If so, save using the memory tool.\n\n"
         "**Skills**: Was a non-trivial approach used to complete a task that required trial "
-        "and error, changing course due to experiential findings, or a different method "
-        "or outcome than the user expected? If so, work in this order:\n"
-        "  a. SURVEY existing skills first (skills_list, then skill_view on candidates).\n"
-        "  b. Identify the CLASS of task, not the specific task "
-        "(\"desktop app build troubleshooting\", not \"fix my Tauri error\").\n"
-        "  c. PREFER UPDATING/GENERALIZING an existing skill that covers the class.\n"
-        "  d. ONLY CREATE A NEW SKILL if no existing one covers the class. Scope at "
-        "the class level, not this one session.\n"
-        "  e. If you notice overlapping skills during the survey, note it so a future "
-        "review can consolidate them.\n\n"
+        "and error, or changing course due to experiential findings along the way, or did "
+        "the user expect or desire a different method or outcome? If a relevant skill "
+        "already exists, update it. Otherwise, create a new one if the approach is reusable.\n\n"
         "Only act if there's something genuinely worth saving. "
         "If nothing stands out, just say 'Nothing to save.' and stop."
     )
@@ -3246,25 +3154,12 @@ class AIAgent:
                 with open(os.devnull, "w") as _devnull, \
                      contextlib.redirect_stdout(_devnull), \
                      contextlib.redirect_stderr(_devnull):
-                    # Inherit the parent agent's live runtime (provider, model,
-                    # base_url, api_key, api_mode) so the fork uses the exact
-                    # same credentials the main turn is using.  Without this,
-                    # AIAgent.__init__ re-runs auto-resolution from env vars,
-                    # which fails for OAuth-only providers, session-scoped
-                    # creds, or credential-pool setups where the resolver can't
-                    # reconstruct auth from scratch -- producing the spurious
-                    # "No LLM provider configured" warning at end of turn.
-                    _parent_runtime = self._current_main_runtime()
                     review_agent = AIAgent(
                         model=self.model,
                         max_iterations=8,
                         quiet_mode=True,
                         platform=self.platform,
                         provider=self.provider,
-                        api_mode=_parent_runtime.get("api_mode") or None,
-                        base_url=_parent_runtime.get("base_url") or None,
-                        api_key=_parent_runtime.get("api_key") or None,
-                        credential_pool=getattr(self, "_credential_pool", None),
                         parent_session_id=self.session_id,
                     )
                     review_agent._memory_write_origin = "background_review"
@@ -3365,7 +3260,10 @@ class AIAgent:
         """Save session state to both JSON log and SQLite on any exit path.
 
         Ensures conversations are never lost, even on errors or early returns.
+        Skipped when ``persist_session=False`` (ephemeral helper flows).
         """
+        if not self.persist_session:
+            return
         self._apply_persist_user_message_override(messages)
         self._session_messages = messages
         self._save_session_log(messages)
@@ -3415,7 +3313,6 @@ class AIAgent:
                     reasoning_content=msg.get("reasoning_content") if role == "assistant" else None,
                     reasoning_details=msg.get("reasoning_details") if role == "assistant" else None,
                     codex_reasoning_items=msg.get("codex_reasoning_items") if role == "assistant" else None,
-                    codex_message_items=msg.get("codex_message_items") if role == "assistant" else None,
                 )
             self._last_flushed_db_idx = len(messages)
         except Exception as e:
@@ -4498,12 +4395,6 @@ class AIAgent:
             tool_guidance.append(SESSION_SEARCH_GUIDANCE)
         if "skill_manage" in self.valid_tool_names:
             tool_guidance.append(SKILLS_GUIDANCE)
-        # Kanban worker/orchestrator lifecycle — only present when the
-        # dispatcher spawned this process (kanban_show check_fn gates on
-        # HERMES_KANBAN_TASK env var). Normal chat sessions never see
-        # this block.
-        if "kanban_show" in self.valid_tool_names:
-            tool_guidance.append(KANBAN_GUIDANCE)
         if tool_guidance:
             prompt_parts.append(" ".join(tool_guidance))
 
@@ -5546,11 +5437,6 @@ class AIAgent:
         # Other anthropic_messages providers (MiniMax, Alibaba, etc.) use their own keys.
         if self.provider != "anthropic":
             return False
-        # Azure endpoints use static API keys — OAuth token rotation doesn't apply.
-        # Refreshing would pick up ~/.claude/.credentials.json OAuth token and break auth.
-        _base = getattr(self, "_anthropic_base_url", "") or ""
-        if "azure.com" in _base:
-            return False
 
         try:
             from agent.anthropic_adapter import resolve_anthropic_token, build_anthropic_client
@@ -6907,15 +6793,10 @@ class AIAgent:
             # Determine api_mode from provider / base URL / model
             fb_api_mode = "chat_completions"
             fb_base_url = str(fb_client.base_url)
-            _fb_is_azure = self._is_azure_openai_url(fb_base_url)
             if fb_provider == "openai-codex":
                 fb_api_mode = "codex_responses"
             elif fb_provider == "anthropic" or fb_base_url.rstrip("/").lower().endswith("/anthropic"):
                 fb_api_mode = "anthropic_messages"
-            elif _fb_is_azure:
-                # Azure OpenAI serves gpt-5.x on /chat/completions — does NOT
-                # support the Responses API. Stay on chat_completions.
-                fb_api_mode = "chat_completions"
             elif self._is_direct_openai_url(fb_base_url):
                 fb_api_mode = "codex_responses"
             elif self._provider_model_requires_responses_api(
@@ -7788,13 +7669,6 @@ class AIAgent:
         if codex_items:
             msg["codex_reasoning_items"] = codex_items
 
-        # Codex Responses API: preserve exact assistant message items (with
-        # id/phase) so follow-up turns can replay structured items instead of
-        # flattening to plain text. This is required for prefix cache hits.
-        codex_message_items = getattr(assistant_message, "codex_message_items", None)
-        if codex_message_items:
-            msg["codex_message_items"] = codex_message_items
-
         if assistant_message.tool_calls:
             tool_calls = []
             for tool_call in assistant_message.tool_calls:
@@ -7888,17 +7762,7 @@ class AIAgent:
             api_msg["reasoning_content"] = existing
             return
 
-        # 2. Healthy session: promote 'reasoning' field to 'reasoning_content'
-        # for providers that use the internal 'reasoning' key.
-        # This must happen BEFORE the DeepSeek/Kimi tool-call check so that
-        # genuine reasoning content is not overwritten by the empty-string
-        # fallback (#15812 regression in PR #15478).
-        normalized_reasoning = source_msg.get("reasoning")
-        if isinstance(normalized_reasoning, str) and normalized_reasoning:
-            api_msg["reasoning_content"] = normalized_reasoning
-            return
-
-        # 3. DeepSeek / Kimi thinking mode: tool-call turns that lack
+        # 2. DeepSeek / Kimi thinking mode: tool-call turns that lack
         # reasoning_content are "poisoned history" — a prior provider (MiniMax,
         # etc.) left them empty. DeepSeek returns HTTP 400 if reasoning_content
         # is absent on replay; inject "" to satisfy the provider's requirement
@@ -7914,6 +7778,13 @@ class AIAgent:
             api_msg["reasoning_content"] = ""
             return
 
+        # 3. Healthy session: promote 'reasoning' field to 'reasoning_content'
+        # for providers that use the internal 'reasoning' key.
+        normalized_reasoning = source_msg.get("reasoning")
+        if isinstance(normalized_reasoning, str) and normalized_reasoning:
+            api_msg["reasoning_content"] = normalized_reasoning
+            return
+
         # 4. DeepSeek / Kimi thinking mode: all assistant messages need
         # reasoning_content. Inject "" to satisfy the provider's requirement
         # when no explicit reasoning content is present.
@@ -11047,69 +10918,36 @@ class AIAgent:
                                 continue
 
                     # ── Nous Portal: record rate limit & skip retries ─────
-                    # When Nous returns a 429 that is a genuine account-
-                    # level rate limit, record the reset time to a shared
-                    # file so ALL sessions (cron, gateway, auxiliary) know
-                    # not to pile on, then skip further retries -- each
-                    # one burns another RPH request and deepens the hole.
-                    # The retry loop's top-of-iteration guard will catch
-                    # this on the next pass and try fallback or bail.
-                    #
-                    # IMPORTANT: Nous Portal multiplexes multiple upstream
-                    # providers (DeepSeek, Kimi, MiMo, Hermes).  A 429 can
-                    # also mean an UPSTREAM provider is out of capacity
-                    # for one specific model -- transient, clears in
-                    # seconds, nothing to do with the caller's quota.
-                    # Tripping the cross-session breaker on that would
-                    # block every Nous model for minutes.  We use
-                    # ``is_genuine_nous_rate_limit`` to tell the two
-                    # apart via the 429's own x-ratelimit-* headers and
-                    # the last-known-good state captured on the previous
-                    # successful response.
+                    # When Nous returns a 429, record the reset time to a
+                    # shared file so ALL sessions (cron, gateway, auxiliary)
+                    # know not to pile on.  Then skip further retries —
+                    # each one burns another RPH request and deepens the
+                    # rate limit hole.  The retry loop's top-of-iteration
+                    # guard will catch this on the next pass and try
+                    # fallback or bail with a clear message.
                     if (
                         is_rate_limited
                         and self.provider == "nous"
                         and classified.reason == FailoverReason.rate_limit
                         and not recovered_with_pool
                     ):
-                        _genuine_nous_rate_limit = False
                         try:
-                            from agent.nous_rate_guard import (
-                                is_genuine_nous_rate_limit,
-                                record_nous_rate_limit,
-                            )
+                            from agent.nous_rate_guard import record_nous_rate_limit
                             _err_resp = getattr(api_error, "response", None)
                             _err_hdrs = (
                                 getattr(_err_resp, "headers", None)
                                 if _err_resp else None
                             )
-                            _genuine_nous_rate_limit = is_genuine_nous_rate_limit(
+                            record_nous_rate_limit(
                                 headers=_err_hdrs,
-                                last_known_state=self._rate_limit_state,
+                                error_context=error_context,
                             )
-                            if _genuine_nous_rate_limit:
-                                record_nous_rate_limit(
-                                    headers=_err_hdrs,
-                                    error_context=error_context,
-                                )
-                            else:
-                                logging.info(
-                                    "Nous 429 looks like upstream capacity "
-                                    "(no exhausted bucket in headers or "
-                                    "last-known state) -- not tripping "
-                                    "cross-session breaker."
-                                )
                         except Exception:
                             pass
-                        if _genuine_nous_rate_limit:
-                            # Skip straight to max_retries -- the
-                            # top-of-loop guard will handle fallback or
-                            # bail cleanly.
-                            retry_count = max_retries
-                            continue
-                        # Upstream capacity 429: fall through to normal
-                        # retry logic.  A different model (or the same
-                        # model a moment later) will typically succeed.
+                        # Skip straight to max_retries — the top-of-loop
+                        # guard will handle fallback or bail cleanly.
+                        retry_count = max_retries
+                        continue
 
                     is_payload_too_large = (
                         classified.reason == FailoverReason.payload_too_large
@@ -11711,26 +11549,16 @@ class AIAgent:
                     interim_has_content = bool((interim_msg.get("content") or "").strip())
                     interim_has_reasoning = bool(interim_msg.get("reasoning", "").strip()) if isinstance(interim_msg.get("reasoning"), str) else False
                     interim_has_codex_reasoning = bool(interim_msg.get("codex_reasoning_items"))
-                    interim_has_codex_message_items = bool(interim_msg.get("codex_message_items"))
 
-                    if (
-                        interim_has_content
-                        or interim_has_reasoning
-                        or interim_has_codex_reasoning
-                        or interim_has_codex_message_items
-                    ):
+                    if interim_has_content or interim_has_reasoning or interim_has_codex_reasoning:
                         last_msg = messages[-1] if messages else None
                         # Duplicate detection: two consecutive incomplete assistant
                         # messages with identical content AND reasoning are collapsed.
-                        # For provider-state-only changes (encrypted reasoning
-                        # items or replayable message ids/phases/statuses differ
-                        # while visible content/reasoning are unchanged), compare
-                        # those opaque payloads too so we don't silently drop the
-                        # newer continuation state.
+                        # For reasoning-only messages (codex_reasoning_items differ but
+                        # visible content/reasoning are both empty), we also compare
+                        # the encrypted items to avoid silently dropping new state.
                         last_codex_items = last_msg.get("codex_reasoning_items") if isinstance(last_msg, dict) else None
                         interim_codex_items = interim_msg.get("codex_reasoning_items")
-                        last_codex_message_items = last_msg.get("codex_message_items") if isinstance(last_msg, dict) else None
-                        interim_codex_message_items = interim_msg.get("codex_message_items")
                         duplicate_interim = (
                             isinstance(last_msg, dict)
                             and last_msg.get("role") == "assistant"
@@ -11738,7 +11566,6 @@ class AIAgent:
                             and (last_msg.get("content") or "") == (interim_msg.get("content") or "")
                             and (last_msg.get("reasoning") or "") == (interim_msg.get("reasoning") or "")
                             and last_codex_items == interim_codex_items
-                            and last_codex_message_items == interim_codex_message_items
                         )
                         if not duplicate_interim:
                             messages.append(interim_msg)

scripts/build_model_catalog.py

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

scripts/release.py

@@ -43,7 +43,6 @@ AUTHOR_MAP = {
     "teknium1@gmail.com": "teknium1",
     "teknium@nousresearch.com": "teknium1",
     "127238744+teknium1@users.noreply.github.com": "teknium1",
-    "focusflow.app.help@gmail.com": "yes999zc",
     "343873859@qq.com": "DrStrangerUJN",
     "uzmpsk.dilekakbas@gmail.com": "dlkakbs",
     "jefferson@heimdallstrategy.com": "Mind-Dragon",
@@ -52,7 +51,6 @@ AUTHOR_MAP = {
     "web3blind@users.noreply.github.com": "web3blind",
     "julia@alexland.us": "alexg0bot",
     "1060770+benjaminsehl@users.noreply.github.com": "benjaminsehl",
-    "nerijusn76@gmail.com": "Nerijusas",
     # contributors (from noreply pattern)
     "david.vv@icloud.com": "davidvv",
     "wangqiang@wangqiangdeMac-mini.local": "xiaoqiang243",
@@ -69,9 +67,7 @@ AUTHOR_MAP = {
     "kshitijk4poor@gmail.com": "kshitijk4poor",
     "keira.voss94@gmail.com": "keiravoss94",
     "16443023+stablegenius49@users.noreply.github.com": "stablegenius49",
-    "fqsy1416@gmail.com": "EKKOLearnAI",
     "simbamax99@gmail.com": "simbam99",
-    "iris@growthpillars.co": "irispillars",
     "185121704+stablegenius49@users.noreply.github.com": "stablegenius49",
     "101283333+batuhankocyigit@users.noreply.github.com": "batuhankocyigit",
     "255305877+ismell0992-afk@users.noreply.github.com": "ismell0992-afk",
@@ -96,7 +92,6 @@ AUTHOR_MAP = {
     "104278804+Sertug17@users.noreply.github.com": "Sertug17",
     "112503481+caentzminger@users.noreply.github.com": "caentzminger",
     "258577966+voidborne-d@users.noreply.github.com": "voidborne-d",
-    "liusway405@gmail.com": "voidborne-d",
     "xydarcher@uestc.edu.cn": "Readon",
     "sir_even@icloud.com": "sirEven",
     "36056348+sirEven@users.noreply.github.com": "sirEven",
@@ -181,10 +176,6 @@ AUTHOR_MAP = {
     "jaisehgal11299@gmail.com": "jaisup",
     "percydikec@gmail.com": "PercyDikec",
     "noonou7@gmail.com": "HenkDz",
-    # Azure Foundry salvage (PRs #9029, #4599, #10086, #8766)
-    "tech@smartlogics.net": "TechPrototyper",
-    "637186+HangGlidersRule@users.noreply.github.com": "HangGlidersRule",
-    "pein892@gmail.com": "pein892",
     "dean.kerr@gmail.com": "deankerr",
     "socrates1024@gmail.com": "socrates1024",
     "seanalt555@gmail.com": "Salt-555",
@@ -419,7 +410,6 @@ AUTHOR_MAP = {
     "105142614+VTRiot@users.noreply.github.com": "VTRiot",
     "vivien000812@gmail.com": "iamagenius00",
     "89228157+Feranmi10@users.noreply.github.com": "Feranmi10",
-    "oluwadareferanmi11@gmail.com": "Feranmi10",
     "simon@gtcl.us": "simon-gtcl",
     "suzukaze.haduki@gmail.com": "houko",
     "cliff@cigii.com": "cgarwood82",

skills/autonomous-ai-agents/hermes-agent/SKILL.md

@@ -281,6 +281,7 @@ Type these during an interactive chat session.
 ### Utility
 ```
 /branch (/fork)      Branch the current session
+/btw                 Ephemeral side question (doesn't interrupt main task)
 /fast                Toggle priority/fast processing
 /browser             Open CDP browser connection
 /history             Show conversation history (CLI)

skills/devops/kanban-orchestrator/SKILL.md

@@ -1,152 +0,0 @@
----
-name: kanban-orchestrator
-description: Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
-version: 2.0.0
-metadata:
-  hermes:
-    tags: [kanban, multi-agent, orchestration, routing]
-    related_skills: [kanban-worker]
----
-
-# Kanban Orchestrator — Decomposition Playbook
-
-> The **core worker lifecycle** (including the `kanban_create` fan-out pattern and the "decompose, don't execute" rule) is auto-injected into every kanban process via the `KANBAN_GUIDANCE` system-prompt block. This skill is the deeper playbook when you're an orchestrator profile whose whole job is routing.
-
-## When to use the board (vs. just doing the work)
-
-Create Kanban tasks when any of these are true:
-
-1. **Multiple specialists are needed.** Research + analysis + writing is three profiles.
-2. **The work should survive a crash or restart.** Long-running, recurring, or important.
-3. **The user might want to interject.** Human-in-the-loop at any step.
-4. **Multiple subtasks can run in parallel.** Fan-out for speed.
-5. **Review / iteration is expected.** A reviewer profile loops on drafter output.
-6. **The audit trail matters.** Board rows persist in SQLite forever.
-
-If *none* of those apply — it's a small one-shot reasoning task — use `delegate_task` instead or answer the user directly.
-
-## The anti-temptation rules
-
-Your job description says "route, don't execute." The rules that enforce that:
-
-- **Do not execute the work yourself.** Your restricted toolset usually doesn't even include terminal/file/code/web for implementation. If you find yourself "just fixing this quickly" — stop and create a task for the right specialist.
-- **For any concrete task, create a Kanban task and assign it.** Every single time.
-- **If no specialist fits, ask the user which profile to create.** Do not default to doing it yourself under "close enough."
-- **Decompose, route, and summarize — that's the whole job.**
-
-## The standard specialist roster (convention)
-
-Unless the user's setup has customized profiles, assume these exist. Adjust to whatever the user actually has — ask if you're unsure.
-
-| Profile | Does | Typical workspace |
-|---|---|---|
-| `researcher` | Reads sources, gathers facts, writes findings | `scratch` |
-| `analyst` | Synthesizes, ranks, de-dupes. Consumes multiple `researcher` outputs | `scratch` |
-| `writer` | Drafts prose in the user's voice | `scratch` or `dir:` into their Obsidian vault |
-| `reviewer` | Reads output, leaves findings, gates approval | `scratch` |
-| `backend-eng` | Writes server-side code | `worktree` |
-| `frontend-eng` | Writes client-side code | `worktree` |
-| `ops` | Runs scripts, manages services, handles deployments | `dir:` into ops scripts repo |
-| `pm` | Writes specs, acceptance criteria | `scratch` |
-
-## Decomposition playbook
-
-### Step 1 — Understand the goal
-
-Ask clarifying questions if the goal is ambiguous. Cheap to ask; expensive to spawn the wrong fleet.
-
-### Step 2 — Sketch the task graph
-
-Before creating anything, draft the graph out loud (in your response to the user). Example for "Analyze whether we should migrate to Postgres":
-
-```
-T1  researcher        research: Postgres cost vs current
-T2  researcher        research: Postgres performance vs current
-T3  analyst           synthesize migration recommendation       parents: T1, T2
-T4  writer            draft decision memo                       parents: T3
-```
-
-Show this to the user. Let them correct it before you create anything.
-
-### Step 3 — Create tasks and link
-
-```python
-t1 = kanban_create(
-    title="research: Postgres cost vs current",
-    assignee="researcher",
-    body="Compare estimated infrastructure costs, migration costs, and ongoing ops costs over a 3-year window. Sources: AWS/GCP pricing, team time estimates, current Postgres bills from peers.",
-    tenant=os.environ.get("HERMES_TENANT"),
-)["task_id"]
-
-t2 = kanban_create(
-    title="research: Postgres performance vs current",
-    assignee="researcher",
-    body="Compare query latency, throughput, and scaling characteristics at our expected data volume (~500GB, 10k QPS peak). Sources: benchmark papers, public case studies, pgbench results if easy.",
-)["task_id"]
-
-t3 = kanban_create(
-    title="synthesize migration recommendation",
-    assignee="analyst",
-    body="Read the findings from T1 (cost) and T2 (performance). Produce a 1-page recommendation with explicit trade-offs and a go/no-go call.",
-    parents=[t1, t2],
-)["task_id"]
-
-t4 = kanban_create(
-    title="draft decision memo",
-    assignee="writer",
-    body="Turn the analyst's recommendation into a 2-page memo for the CTO. Match the tone of previous decision memos in the team's knowledge base.",
-    parents=[t3],
-)["task_id"]
-```
-
-`parents=[...]` gates promotion — children stay in `todo` until every parent reaches `done`, then auto-promote to `ready`. No manual coordination needed; the dispatcher and dependency engine handle it.
-
-### Step 4 — Complete your own task
-
-If you were spawned as a task yourself (e.g. `planner` profile was assigned `T0: "investigate Postgres migration"`), mark it done with a summary of what you created:
-
-```python
-kanban_complete(
-    summary="decomposed into T1-T4: 2 researchers parallel, 1 analyst on their outputs, 1 writer on the recommendation",
-    metadata={
-        "task_graph": {
-            "T1": {"assignee": "researcher", "parents": []},
-            "T2": {"assignee": "researcher", "parents": []},
-            "T3": {"assignee": "analyst", "parents": ["T1", "T2"]},
-            "T4": {"assignee": "writer", "parents": ["T3"]},
-        },
-    },
-)
-```
-
-### Step 5 — Report back to the user
-
-Tell them what you created in plain prose:
-
-> I've queued 4 tasks:
-> - **T1** (researcher): cost comparison
-> - **T2** (researcher): performance comparison, in parallel with T1
-> - **T3** (analyst): synthesizes T1 + T2 into a recommendation
-> - **T4** (writer): turns T3 into a CTO memo
->
-> The dispatcher will pick up T1 and T2 now. T3 starts when both finish. You'll get a gateway ping when T4 completes. Use the dashboard or `hermes kanban tail <id>` to follow along.
-
-## Common patterns
-
-**Fan-out + fan-in (research → synthesize):** N `researcher` tasks with no parents, one `analyst` task with all of them as parents.
-
-**Pipeline with gates:** `pm → backend-eng → reviewer`. Each stage's `parents=[previous_task]`. Reviewer blocks or completes; if reviewer blocks, the operator unblocks with feedback and respawns.
-
-**Same-profile queue:** 50 tasks, all assigned to `translator`, no dependencies between them. Dispatcher serializes — translator processes them in priority order, accumulating experience in their own memory.
-
-**Human-in-the-loop:** Any task can `kanban_block()` to wait for input. Dispatcher respawns after `/unblock`. The comment thread carries the full context.
-
-## Pitfalls
-
-**Reassignment vs. new task.** If a reviewer blocks with "needs changes," create a NEW task linked from the reviewer's task — don't re-run the same task with a stern look. The new task is assigned to the original implementer profile.
-
-**Argument order for links.** `kanban_link(parent_id=..., child_id=...)` — parent first. Mixing them up demotes the wrong task to `todo`.
-
-**Don't pre-create the whole graph if the shape depends on intermediate findings.** If T3's structure depends on what T1 and T2 find, let T3 exist as a "synthesize findings" task whose own first step is to read parent handoffs and plan the rest. Orchestrators can spawn orchestrators.
-
-**Tenant inheritance.** If `HERMES_TENANT` is set in your env, pass `tenant=os.environ.get("HERMES_TENANT")` on every `kanban_create` call so child tasks stay in the same namespace.

skills/devops/kanban-worker/SKILL.md

@@ -1,134 +0,0 @@
----
-name: kanban-worker
-description: Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
-version: 2.0.0
-metadata:
-  hermes:
-    tags: [kanban, multi-agent, collaboration, workflow, pitfalls]
-    related_skills: [kanban-orchestrator]
----
-
-# Kanban Worker — Pitfalls and Examples
-
-> You're seeing this skill because the Hermes Kanban dispatcher spawned you as a worker with `--skills kanban-worker` — it's loaded automatically for every dispatched worker. The **lifecycle** (6 steps: orient → work → heartbeat → block/complete) also lives in the `KANBAN_GUIDANCE` block that's auto-injected into your system prompt. This skill is the deeper detail: good handoff shapes, retry diagnostics, edge cases.
-
-## Workspace handling
-
-Your workspace kind determines how you should behave inside `$HERMES_KANBAN_WORKSPACE`:
-
-| Kind | What it is | How to work |
-|---|---|---|
-| `scratch` | Fresh tmp dir, yours alone | Read/write freely; it gets GC'd when the task is archived. |
-| `dir:<path>` | Shared persistent directory | Other runs will read what you write. Treat it like long-lived state. Path is guaranteed absolute (the kernel rejects relative paths). |
-| `worktree` | Git worktree at the resolved path | If `.git` doesn't exist, run `git worktree add <path> <branch>` from the main repo first, then cd and work normally. Commit work here. |
-
-## Tenant isolation
-
-If `$HERMES_TENANT` is set, the task belongs to a tenant namespace. When reading or writing persistent memory, prefix memory entries with the tenant so context doesn't leak across tenants:
-
-- Good: `business-a: Acme is our biggest customer`
-- Bad (leaks): `Acme is our biggest customer`
-
-## Good summary + metadata shapes
-
-The `kanban_complete(summary=..., metadata=...)` handoff is how downstream workers read what you did. Patterns that work:
-
-**Coding task:**
-```python
-kanban_complete(
-    summary="shipped rate limiter — token bucket, keys on user_id with IP fallback, 14 tests pass",
-    metadata={
-        "changed_files": ["rate_limiter.py", "tests/test_rate_limiter.py"],
-        "tests_run": 14,
-        "tests_passed": 14,
-        "decisions": ["user_id primary, IP fallback for unauthenticated requests"],
-    },
-)
-```
-
-**Research task:**
-```python
-kanban_complete(
-    summary="3 competing libraries reviewed; vLLM wins on throughput, SGLang on latency, Tensorrt-LLM on memory efficiency",
-    metadata={
-        "sources_read": 12,
-        "recommendation": "vLLM",
-        "benchmarks": {"vllm": 1.0, "sglang": 0.87, "trtllm": 0.72},
-    },
-)
-```
-
-**Review task:**
-```python
-kanban_complete(
-    summary="reviewed PR #123; 2 blocking issues found (SQL injection in /search, missing CSRF on /settings)",
-    metadata={
-        "pr_number": 123,
-        "findings": [
-            {"severity": "critical", "file": "api/search.py", "line": 42, "issue": "raw SQL concat"},
-            {"severity": "high", "file": "api/settings.py", "issue": "missing CSRF middleware"},
-        ],
-        "approved": False,
-    },
-)
-```
-
-Shape `metadata` so downstream parsers (reviewers, aggregators, schedulers) can use it without re-reading your prose.
-
-## Block reasons that get answered fast
-
-Bad: `"stuck"` — the human has no context.
-
-Good: one sentence naming the specific decision you need. Leave longer context as a comment instead.
-
-```python
-kanban_comment(
-    task_id=os.environ["HERMES_KANBAN_TASK"],
-    body="Full context: I have user IPs from Cloudflare headers but some users are behind NATs with thousands of peers. Keying on IP alone causes false positives.",
-)
-kanban_block(reason="Rate limit key choice: IP (simple, NAT-unsafe) or user_id (requires auth, skips anonymous endpoints)?")
-```
-
-The block message is what appears in the dashboard / gateway notifier. The comment is the deeper context a human reads when they open the task.
-
-## Heartbeats worth sending
-
-Good heartbeats name progress: `"epoch 12/50, loss 0.31"`, `"scanned 1.2M/2.4M rows"`, `"uploaded 47/120 videos"`.
-
-Bad heartbeats: `"still working"`, empty notes, sub-second intervals. Every few minutes max; skip entirely for tasks under ~2 minutes.
-
-## Retry scenarios
-
-If you open the task and `kanban_show` returns `runs: [...]` with one or more closed runs, you're a retry. The prior runs' `outcome` / `summary` / `error` tell you what didn't work. Don't repeat that path. Typical retry diagnostics:
-
-- `outcome: "timed_out"` — the previous attempt hit `max_runtime_seconds`. You may need to chunk the work or shorten it.
-- `outcome: "crashed"` — OOM or segfault. Reduce memory footprint.
-- `outcome: "spawn_failed"` + `error: "..."` — usually a profile config issue (missing credential, bad PATH). Ask the human via `kanban_block` instead of retrying blindly.
-- `outcome: "reclaimed"` + `summary: "task archived..."` — operator archived the task out from under the previous run; you probably shouldn't be running at all, check status carefully.
-- `outcome: "blocked"` — a previous attempt blocked; the unblock comment should be in the thread by now.
-
-## Do NOT
-
-- Call `delegate_task` as a substitute for `kanban_create`. `delegate_task` is for short reasoning subtasks inside YOUR run; `kanban_create` is for cross-agent handoffs that outlive one API loop.
-- Modify files outside `$HERMES_KANBAN_WORKSPACE` unless the task body says to.
-- Create follow-up tasks assigned to yourself — assign to the right specialist.
-- Complete a task you didn't actually finish. Block it instead.
-
-## Pitfalls
-
-**Task state can change between dispatch and your startup.** Between when the dispatcher claimed and when your process actually booted, the task may have been blocked, reassigned, or archived. Always `kanban_show` first. If it reports `blocked` or `archived`, stop — you shouldn't be running.
-
-**Workspace may have stale artifacts.** Especially `dir:` and `worktree` workspaces can have files from previous runs. Read the comment thread — it usually explains why you're running again and what state the workspace is in.
-
-**Don't rely on the CLI when the guidance is available.** The `kanban_*` tools work across all terminal backends (Docker, Modal, SSH). `hermes kanban <verb>` from your terminal tool will fail in containerized backends because the CLI isn't installed there. When in doubt, use the tool.
-
-## CLI fallback (for scripting)
-
-Every tool has a CLI equivalent for human operators and scripts:
-- `kanban_show` ↔ `hermes kanban show <id> --json`
-- `kanban_complete` ↔ `hermes kanban complete <id> --summary "..." --metadata '{...}'`
-- `kanban_block` ↔ `hermes kanban block <id> "reason"`
-- `kanban_create` ↔ `hermes kanban create "title" --assignee <profile> [--parent <id>]`
-- etc.
-
-Use the tools from inside an agent; the CLI exists for the human at the terminal.

tests/agent/test_model_metadata.py

@@ -192,43 +192,6 @@ class TestDefaultContextLengths:
                     f"{model_id}: expected {expected_ctx}, got {actual}"
                 )
 
-    def test_deepseek_v4_models_1m_context(self):
-        from agent.model_metadata import get_model_context_length
-        from unittest.mock import patch as mock_patch
-
-        expected_keys = {
-            "deepseek-v4-pro": 1_000_000,
-            "deepseek-v4-flash": 1_000_000,
-            "deepseek-chat": 1_000_000,
-            "deepseek-reasoner": 1_000_000,
-        }
-        for key, value in expected_keys.items():
-            assert key in DEFAULT_CONTEXT_LENGTHS, f"{key} missing"
-            assert DEFAULT_CONTEXT_LENGTHS[key] == value, (
-                f"{key} should be {value}, got {DEFAULT_CONTEXT_LENGTHS[key]}"
-            )
-
-        # Longest-first substring matching must resolve both the bare V4
-        # ids (native DeepSeek) and the vendor-prefixed forms (OpenRouter
-        # / Nous Portal) to 1M without probing down to the legacy 128K
-        # ``deepseek`` substring fallback.
-        with mock_patch("agent.model_metadata.fetch_model_metadata", return_value={}), \
-             mock_patch("agent.model_metadata.fetch_endpoint_model_metadata", return_value={}), \
-             mock_patch("agent.model_metadata.get_cached_context_length", return_value=None):
-            cases = [
-                ("deepseek-v4-pro", 1_000_000),
-                ("deepseek-v4-flash", 1_000_000),
-                ("deepseek/deepseek-v4-pro", 1_000_000),
-                ("deepseek/deepseek-v4-flash", 1_000_000),
-                ("deepseek-chat", 1_000_000),
-                ("deepseek-reasoner", 1_000_000),
-            ]
-            for model_id, expected_ctx in cases:
-                actual = get_model_context_length(model_id)
-                assert actual == expected_ctx, (
-                    f"{model_id}: expected {expected_ctx}, got {actual}"
-                )
-
     def test_all_values_positive(self):
         for key, value in DEFAULT_CONTEXT_LENGTHS.items():
             assert value > 0, f"{key} has non-positive context length"
@@ -340,9 +303,7 @@ class TestCodexOAuthContextLength:
         from agent.model_metadata import get_model_context_length
 
         # OpenRouter — should hit its own catalog path first; when mocked
-        # empty, falls through to hardcoded DEFAULT_CONTEXT_LENGTHS (1.05M,
-        # matching the real direct-API value — Codex OAuth's 272k cap is
-        # provider-specific and must not leak here).
+        # empty, falls through to hardcoded DEFAULT_CONTEXT_LENGTHS (400k).
         with patch("agent.model_metadata.fetch_model_metadata", return_value={}), \
              patch("agent.model_metadata.fetch_endpoint_model_metadata", return_value={}), \
              patch("agent.model_metadata.get_cached_context_length", return_value=None), \
@@ -353,7 +314,7 @@ class TestCodexOAuthContextLength:
                 api_key="",
                 provider="openrouter",
             )
-        assert ctx == 1_050_000, (
+        assert ctx == 400_000, (
             f"Non-Codex gpt-5.5 resolved to {ctx}; Codex 272k override "
             "leaked outside openai-codex provider"
         )
@@ -498,10 +459,9 @@ class TestGetModelContextLength:
 
     @patch("agent.model_metadata.fetch_model_metadata")
     def test_api_missing_context_length_key(self, mock_fetch):
-        """Model in API but without context_length → defaults to the top
-        probe tier (currently 256K)."""
+        """Model in API but without context_length → defaults to 128000."""
         mock_fetch.return_value = {"test/model": {"name": "Test"}}
-        assert get_model_context_length("test/model") == CONTEXT_PROBE_TIERS[0]
+        assert get_model_context_length("test/model") == 128000
 
     @patch("agent.model_metadata.fetch_model_metadata")
     def test_cache_takes_priority_over_api(self, mock_fetch, tmp_path):
@@ -854,17 +814,14 @@ class TestContextProbeTiers:
         for i in range(len(CONTEXT_PROBE_TIERS) - 1):
             assert CONTEXT_PROBE_TIERS[i] > CONTEXT_PROBE_TIERS[i + 1]
 
-    def test_first_tier_is_256k(self):
-        assert CONTEXT_PROBE_TIERS[0] == 256_000
+    def test_first_tier_is_128k(self):
+        assert CONTEXT_PROBE_TIERS[0] == 128_000
 
     def test_last_tier_is_8k(self):
         assert CONTEXT_PROBE_TIERS[-1] == 8_000
 
 
 class TestGetNextProbeTier:
-    def test_from_256k(self):
-        assert get_next_probe_tier(256_000) == 128_000
-
     def test_from_128k(self):
         assert get_next_probe_tier(128_000) == 64_000
 
@@ -884,8 +841,8 @@ class TestGetNextProbeTier:
         assert get_next_probe_tier(100_000) == 64_000
 
     def test_above_max_tier(self):
-        """Value above 256K should return 256K."""
-        assert get_next_probe_tier(500_000) == 256_000
+        """Value above 128K should return 128K."""
+        assert get_next_probe_tier(500_000) == 128_000
 
     def test_zero_returns_none(self):
         assert get_next_probe_tier(0) is None

tests/agent/test_nous_rate_guard.py

@@ -251,141 +251,3 @@ class TestAuxiliaryClientIntegration:
         monkeypatch.setattr(aux, "_read_nous_auth", lambda: None)
         result = aux._try_nous()
         assert result == (None, None)
-
-
-class TestIsGenuineNousRateLimit:
-    """Tell a real account-level 429 apart from an upstream-capacity 429.
-
-    Nous Portal multiplexes upstreams (DeepSeek, Kimi, MiMo, Hermes).
-    A 429 from an upstream out of capacity should NOT trip the
-    cross-session breaker; a real user-quota 429 should.
-    """
-
-    def test_exhausted_hourly_bucket_in_429_headers_is_genuine(self):
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-
-        headers = {
-            "x-ratelimit-limit-requests-1h": "800",
-            "x-ratelimit-remaining-requests-1h": "0",
-            "x-ratelimit-reset-requests-1h": "3100",
-            "x-ratelimit-limit-requests": "200",
-            "x-ratelimit-remaining-requests": "198",
-            "x-ratelimit-reset-requests": "40",
-        }
-        assert is_genuine_nous_rate_limit(headers=headers) is True
-
-    def test_exhausted_tokens_bucket_is_genuine(self):
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-
-        headers = {
-            "x-ratelimit-limit-tokens": "800000",
-            "x-ratelimit-remaining-tokens": "0",
-            "x-ratelimit-reset-tokens": "45",  # < 60s threshold -> not genuine
-            "x-ratelimit-limit-tokens-1h": "8000000",
-            "x-ratelimit-remaining-tokens-1h": "0",
-            "x-ratelimit-reset-tokens-1h": "1800",  # >= 60s threshold -> genuine
-        }
-        assert is_genuine_nous_rate_limit(headers=headers) is True
-
-    def test_healthy_headers_on_429_are_upstream_capacity(self):
-        # Classic upstream-capacity symptom: Nous edge reports plenty of
-        # headroom on every bucket, but returns 429 anyway because
-        # upstream (DeepSeek / Kimi / ...) is out of capacity.
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-
-        headers = {
-            "x-ratelimit-limit-requests": "200",
-            "x-ratelimit-remaining-requests": "198",
-            "x-ratelimit-reset-requests": "40",
-            "x-ratelimit-limit-requests-1h": "800",
-            "x-ratelimit-remaining-requests-1h": "750",
-            "x-ratelimit-reset-requests-1h": "3100",
-            "x-ratelimit-limit-tokens": "800000",
-            "x-ratelimit-remaining-tokens": "790000",
-            "x-ratelimit-reset-tokens": "40",
-            "x-ratelimit-limit-tokens-1h": "8000000",
-            "x-ratelimit-remaining-tokens-1h": "7800000",
-            "x-ratelimit-reset-tokens-1h": "3100",
-        }
-        assert is_genuine_nous_rate_limit(headers=headers) is False
-
-    def test_bare_429_with_no_headers_is_upstream(self):
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-
-        assert is_genuine_nous_rate_limit(headers=None) is False
-        assert is_genuine_nous_rate_limit(headers={}) is False
-        assert is_genuine_nous_rate_limit(
-            headers={"content-type": "application/json"}
-        ) is False
-
-    def test_exhausted_bucket_with_short_reset_is_not_genuine(self):
-        # remaining == 0 but reset in < 60s: almost certainly a
-        # secondary per-minute throttle that will clear immediately --
-        # not worth tripping the cross-session breaker.
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-
-        headers = {
-            "x-ratelimit-limit-requests": "200",
-            "x-ratelimit-remaining-requests": "0",
-            "x-ratelimit-reset-requests": "30",
-        }
-        assert is_genuine_nous_rate_limit(headers=headers) is False
-
-    def test_last_known_state_with_exhausted_bucket_triggers_genuine(self):
-        # Headers on the 429 lack rate-limit info, but the previous
-        # successful response already showed the hourly bucket
-        # exhausted -- the 429 is almost certainly that limit
-        # continuing.
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-        from agent.rate_limit_tracker import parse_rate_limit_headers
-
-        prior_headers = {
-            "x-ratelimit-limit-requests-1h": "800",
-            "x-ratelimit-remaining-requests-1h": "0",
-            "x-ratelimit-reset-requests-1h": "2000",
-            "x-ratelimit-limit-requests": "200",
-            "x-ratelimit-remaining-requests": "100",
-            "x-ratelimit-reset-requests": "30",
-            "x-ratelimit-limit-tokens": "800000",
-            "x-ratelimit-remaining-tokens": "700000",
-            "x-ratelimit-reset-tokens": "30",
-            "x-ratelimit-limit-tokens-1h": "8000000",
-            "x-ratelimit-remaining-tokens-1h": "7000000",
-            "x-ratelimit-reset-tokens-1h": "2000",
-        }
-        last_state = parse_rate_limit_headers(prior_headers, provider="nous")
-        assert is_genuine_nous_rate_limit(
-            headers=None, last_known_state=last_state
-        ) is True
-
-    def test_last_known_state_all_healthy_stays_upstream(self):
-        # Prior state was healthy; bare 429 arrives; should be treated
-        # as upstream capacity.
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-        from agent.rate_limit_tracker import parse_rate_limit_headers
-
-        prior_headers = {
-            "x-ratelimit-limit-requests-1h": "800",
-            "x-ratelimit-remaining-requests-1h": "750",
-            "x-ratelimit-reset-requests-1h": "2000",
-            "x-ratelimit-limit-requests": "200",
-            "x-ratelimit-remaining-requests": "180",
-            "x-ratelimit-reset-requests": "30",
-            "x-ratelimit-limit-tokens": "800000",
-            "x-ratelimit-remaining-tokens": "790000",
-            "x-ratelimit-reset-tokens": "30",
-            "x-ratelimit-limit-tokens-1h": "8000000",
-            "x-ratelimit-remaining-tokens-1h": "7900000",
-            "x-ratelimit-reset-tokens-1h": "2000",
-        }
-        last_state = parse_rate_limit_headers(prior_headers, provider="nous")
-        assert is_genuine_nous_rate_limit(
-            headers=None, last_known_state=last_state
-        ) is False
-
-    def test_none_last_state_and_no_headers_is_upstream(self):
-        from agent.nous_rate_guard import is_genuine_nous_rate_limit
-
-        assert is_genuine_nous_rate_limit(
-            headers=None, last_known_state=None
-        ) is False

tests/agent/test_onboarding.py

@@ -1,164 +0,0 @@
-"""Tests for agent/onboarding.py — contextual first-touch hint helpers."""
-
-from __future__ import annotations
-
-import yaml
-import pytest
-
-from agent.onboarding import (
-    BUSY_INPUT_FLAG,
-    TOOL_PROGRESS_FLAG,
-    busy_input_hint_cli,
-    busy_input_hint_gateway,
-    is_seen,
-    mark_seen,
-    tool_progress_hint_cli,
-    tool_progress_hint_gateway,
-)
-
-
-class TestIsSeen:
-    def test_empty_config_unseen(self):
-        assert is_seen({}, BUSY_INPUT_FLAG) is False
-
-    def test_missing_onboarding_unseen(self):
-        assert is_seen({"display": {}}, BUSY_INPUT_FLAG) is False
-
-    def test_onboarding_not_dict_unseen(self):
-        assert is_seen({"onboarding": "nope"}, BUSY_INPUT_FLAG) is False
-
-    def test_seen_dict_missing_flag(self):
-        assert is_seen({"onboarding": {"seen": {}}}, BUSY_INPUT_FLAG) is False
-
-    def test_seen_flag_true(self):
-        cfg = {"onboarding": {"seen": {BUSY_INPUT_FLAG: True}}}
-        assert is_seen(cfg, BUSY_INPUT_FLAG) is True
-
-    def test_seen_flag_falsy(self):
-        cfg = {"onboarding": {"seen": {BUSY_INPUT_FLAG: False}}}
-        assert is_seen(cfg, BUSY_INPUT_FLAG) is False
-
-    def test_other_flags_isolated(self):
-        cfg = {"onboarding": {"seen": {BUSY_INPUT_FLAG: True}}}
-        assert is_seen(cfg, TOOL_PROGRESS_FLAG) is False
-
-
-class TestMarkSeen:
-    def test_creates_missing_file_and_sets_flag(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-        assert mark_seen(cfg_path, BUSY_INPUT_FLAG) is True
-
-        loaded = yaml.safe_load(cfg_path.read_text())
-        assert loaded["onboarding"]["seen"][BUSY_INPUT_FLAG] is True
-
-    def test_preserves_other_config(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-        cfg_path.write_text(yaml.safe_dump({
-            "model": {"default": "claude-sonnet-4.6"},
-            "display": {"skin": "default"},
-        }))
-
-        assert mark_seen(cfg_path, BUSY_INPUT_FLAG) is True
-        loaded = yaml.safe_load(cfg_path.read_text())
-
-        assert loaded["model"]["default"] == "claude-sonnet-4.6"
-        assert loaded["display"]["skin"] == "default"
-        assert loaded["onboarding"]["seen"][BUSY_INPUT_FLAG] is True
-
-    def test_preserves_other_seen_flags(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-        cfg_path.write_text(yaml.safe_dump({
-            "onboarding": {"seen": {TOOL_PROGRESS_FLAG: True}},
-        }))
-
-        assert mark_seen(cfg_path, BUSY_INPUT_FLAG) is True
-        loaded = yaml.safe_load(cfg_path.read_text())
-
-        assert loaded["onboarding"]["seen"][TOOL_PROGRESS_FLAG] is True
-        assert loaded["onboarding"]["seen"][BUSY_INPUT_FLAG] is True
-
-    def test_idempotent(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-        mark_seen(cfg_path, BUSY_INPUT_FLAG)
-        first = cfg_path.read_text()
-
-        # Second call must be a no-op on-disk content (file may be touched,
-        # but the YAML contents should be identical).
-        mark_seen(cfg_path, BUSY_INPUT_FLAG)
-        second = cfg_path.read_text()
-
-        assert yaml.safe_load(first) == yaml.safe_load(second)
-
-    def test_handles_non_dict_onboarding(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-        cfg_path.write_text(yaml.safe_dump({"onboarding": "corrupted"}))
-
-        assert mark_seen(cfg_path, BUSY_INPUT_FLAG) is True
-        loaded = yaml.safe_load(cfg_path.read_text())
-        assert loaded["onboarding"]["seen"][BUSY_INPUT_FLAG] is True
-
-    def test_handles_non_dict_seen(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-        cfg_path.write_text(yaml.safe_dump({"onboarding": {"seen": "corrupted"}}))
-
-        assert mark_seen(cfg_path, BUSY_INPUT_FLAG) is True
-        loaded = yaml.safe_load(cfg_path.read_text())
-        assert loaded["onboarding"]["seen"][BUSY_INPUT_FLAG] is True
-
-
-class TestHintMessages:
-    def test_busy_input_hint_gateway_interrupt(self):
-        msg = busy_input_hint_gateway("interrupt")
-        assert "/busy queue" in msg
-        assert "interrupted" in msg.lower()
-
-    def test_busy_input_hint_gateway_queue(self):
-        msg = busy_input_hint_gateway("queue")
-        assert "/busy interrupt" in msg
-        assert "queued" in msg.lower()
-
-    def test_busy_input_hint_cli_interrupt(self):
-        msg = busy_input_hint_cli("interrupt")
-        assert "/busy queue" in msg
-
-    def test_busy_input_hint_cli_queue(self):
-        msg = busy_input_hint_cli("queue")
-        assert "/busy interrupt" in msg
-
-    def test_tool_progress_hints_mention_verbose(self):
-        assert "/verbose" in tool_progress_hint_gateway()
-        assert "/verbose" in tool_progress_hint_cli()
-
-    def test_hints_are_not_empty(self):
-        for hint in (
-            busy_input_hint_gateway("queue"),
-            busy_input_hint_gateway("interrupt"),
-            busy_input_hint_cli("queue"),
-            busy_input_hint_cli("interrupt"),
-            tool_progress_hint_gateway(),
-            tool_progress_hint_cli(),
-        ):
-            assert hint.strip()
-
-
-class TestRoundTrip:
-    """After mark_seen, is_seen on the re-loaded config must return True."""
-
-    def test_mark_then_is_seen(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-
-        assert mark_seen(cfg_path, BUSY_INPUT_FLAG) is True
-        loaded = yaml.safe_load(cfg_path.read_text())
-
-        assert is_seen(loaded, BUSY_INPUT_FLAG) is True
-        assert is_seen(loaded, TOOL_PROGRESS_FLAG) is False
-
-    def test_mark_both_flags_independently(self, tmp_path):
-        cfg_path = tmp_path / "config.yaml"
-
-        mark_seen(cfg_path, BUSY_INPUT_FLAG)
-        mark_seen(cfg_path, TOOL_PROGRESS_FLAG)
-        loaded = yaml.safe_load(cfg_path.read_text())
-
-        assert is_seen(loaded, BUSY_INPUT_FLAG) is True
-        assert is_seen(loaded, TOOL_PROGRESS_FLAG) is True

tests/agent/transports/test_chat_completions.py

@@ -33,18 +33,15 @@ class TestChatCompletionsBasic:
     def test_convert_messages_strips_codex_fields(self, transport):
         msgs = [
             {"role": "assistant", "content": "ok", "codex_reasoning_items": [{"id": "rs_1"}],
-             "codex_message_items": [{"id": "msg_1", "type": "message"}],
              "tool_calls": [{"id": "call_1", "call_id": "call_1", "response_item_id": "fc_1",
                             "type": "function", "function": {"name": "t", "arguments": "{}"}}]},
         ]
         result = transport.convert_messages(msgs)
         assert "codex_reasoning_items" not in result[0]
-        assert "codex_message_items" not in result[0]
         assert "call_id" not in result[0]["tool_calls"][0]
         assert "response_item_id" not in result[0]["tool_calls"][0]
         # Original list untouched (deepcopy-on-demand)
         assert "codex_reasoning_items" in msgs[0]
-        assert "codex_message_items" in msgs[0]
 
 
 class TestChatCompletionsBuildKwargs:

tests/agent/transports/test_codex_transport.py

@@ -194,36 +194,6 @@ class TestCodexNormalizeResponse:
         assert nr.content == "Hello world"
         assert nr.finish_reason == "stop"
 
-    def test_message_items_preserved_in_provider_data(self, transport):
-        """Codex assistant message item ids/phases must survive transport normalization."""
-        r = SimpleNamespace(
-            output=[
-                SimpleNamespace(
-                    type="message",
-                    role="assistant",
-                    id="msg_abc",
-                    phase="final_answer",
-                    content=[SimpleNamespace(type="output_text", text="Hello world")],
-                    status="completed",
-                ),
-            ],
-            status="completed",
-            incomplete_details=None,
-            usage=SimpleNamespace(input_tokens=10, output_tokens=5,
-                                  input_tokens_details=None, output_tokens_details=None),
-        )
-        nr = transport.normalize_response(r)
-        assert nr.codex_message_items == [
-            {
-                "type": "message",
-                "role": "assistant",
-                "status": "completed",
-                "content": [{"type": "output_text", "text": "Hello world"}],
-                "id": "msg_abc",
-                "phase": "final_answer",
-            }
-        ]
-
     def test_tool_call_response(self, transport):
         """Normalize a Codex response with tool calls."""
         r = SimpleNamespace(

tests/agent/transports/test_transport.py

@@ -60,13 +60,6 @@ class TestTransportRegistry:
         assert t is not None
         assert t.api_mode == "anthropic_messages"
 
-    def test_discovers_missing_transport_when_registry_partially_populated(self):
-        """Importing one transport directly must not hide other valid api_modes."""
-        import agent.transports.chat_completions  # noqa: F401
-        t = get_transport("codex_responses")
-        assert t is not None
-        assert t.api_mode == "codex_responses"
-
     def test_register_and_get(self):
         class DummyTransport(ProviderTransport):
             @property

tests/agent/transports/test_types.py

@@ -270,15 +270,3 @@ class TestNormalizedResponseBackwardCompat:
     def test_codex_reasoning_items_none_when_absent(self):
         nr = NormalizedResponse(content="hi", tool_calls=None, finish_reason="stop")
         assert nr.codex_reasoning_items is None
-
-    def test_codex_message_items_from_provider_data(self):
-        items = [{"id": "msg_1", "type": "message"}]
-        nr = NormalizedResponse(
-            content="hi", tool_calls=None, finish_reason="stop",
-            provider_data={"codex_message_items": items},
-        )
-        assert nr.codex_message_items == items
-
-    def test_codex_message_items_none_when_absent(self):
-        nr = NormalizedResponse(content="hi", tool_calls=None, finish_reason="stop")
-        assert nr.codex_message_items is None

tests/e2e/conftest.py

@@ -346,7 +346,6 @@ def make_discord_message(
 
     return SimpleNamespace(
         id=message_id, content=content, author=author, channel=channel,
-        guild=getattr(channel, "guild", None),
         mentions=mentions, attachments=attachments,
         type=getattr(discord, "MessageType", SimpleNamespace()).default,
         reference=None, created_at=datetime.now(timezone.utc),

tests/gateway/test_api_server_runs.py

@@ -1,365 +0,0 @@
-"""Tests for /v1/runs endpoints: start, events, and stop.
-
-Covers:
-- POST /v1/runs — start a run (202)
-- GET /v1/runs/{run_id}/events — SSE event stream
-- POST /v1/runs/{run_id}/stop — interrupt a running agent
-- Auth, error handling, and cleanup
-"""
-
-import asyncio
-import json
-import threading
-import time as _time
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-from aiohttp import web
-from aiohttp.test_utils import TestClient, TestServer
-
-from gateway.config import PlatformConfig
-from gateway.platforms.api_server import (
-    APIServerAdapter,
-    cors_middleware,
-    security_headers_middleware,
-)
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _make_adapter(api_key: str = "") -> APIServerAdapter:
-    """Create an adapter with optional API key."""
-    extra = {}
-    if api_key:
-        extra["key"] = api_key
-    config = PlatformConfig(enabled=True, extra=extra)
-    adapter = APIServerAdapter(config)
-    return adapter
-
-
-def _create_runs_app(adapter: APIServerAdapter) -> web.Application:
-    """Create an aiohttp app with /v1/runs routes registered."""
-    mws = [mw for mw in (cors_middleware, security_headers_middleware) if mw is not None]
-    app = web.Application(middlewares=mws)
-    app["api_server_adapter"] = adapter
-    app.router.add_post("/v1/runs", adapter._handle_runs)
-    app.router.add_get("/v1/runs/{run_id}/events", adapter._handle_run_events)
-    app.router.add_post("/v1/runs/{run_id}/stop", adapter._handle_stop_run)
-    return app
-
-
-def _make_slow_agent(**kwargs):
-    """Create a mock agent that blocks in run_conversation until interrupted.
-
-    Returns (mock_agent, agent_ready_event, interrupt_event) where
-    agent_ready_event is set once run_conversation starts, and
-    interrupt_event is set when interrupt() is called.
-    """
-    ready = threading.Event()
-    interrupted = threading.Event()
-
-    mock_agent = MagicMock()
-
-    def _do_interrupt(message=None):
-        interrupted.set()
-
-    mock_agent.interrupt = MagicMock(side_effect=_do_interrupt)
-
-    def _slow_run(user_message=None, conversation_history=None, task_id=None):
-        ready.set()
-        # Block until interrupt() is called
-        interrupted.wait(timeout=10)
-        return {"final_response": "interrupted"}
-
-    mock_agent.run_conversation.side_effect = _slow_run
-    mock_agent.session_prompt_tokens = 0
-    mock_agent.session_completion_tokens = 0
-    mock_agent.session_total_tokens = 0
-
-    return mock_agent, ready, interrupted
-
-
-@pytest.fixture
-def adapter():
-    return _make_adapter()
-
-
-@pytest.fixture
-def auth_adapter():
-    return _make_adapter(api_key="sk-secret")
-
-
-# ---------------------------------------------------------------------------
-# POST /v1/runs — start a run
-# ---------------------------------------------------------------------------
-
-
-class TestStartRun:
-    @pytest.mark.asyncio
-    async def test_start_returns_202(self, adapter):
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(adapter, "_create_agent") as mock_create:
-                mock_agent = MagicMock()
-                mock_agent.run_conversation.return_value = {"final_response": "done"}
-                mock_agent.session_prompt_tokens = 10
-                mock_agent.session_completion_tokens = 5
-                mock_agent.session_total_tokens = 15
-                mock_create.return_value = mock_agent
-
-                resp = await cli.post("/v1/runs", json={"input": "hello"})
-                assert resp.status == 202
-                data = await resp.json()
-                assert data["status"] == "started"
-                assert data["run_id"].startswith("run_")
-
-    @pytest.mark.asyncio
-    async def test_start_invalid_json_returns_400(self, adapter):
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.post(
-                "/v1/runs",
-                data="not json",
-                headers={"Content-Type": "application/json"},
-            )
-        assert resp.status == 400
-
-    @pytest.mark.asyncio
-    async def test_start_missing_input_returns_400(self, adapter):
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.post("/v1/runs", json={"model": "test"})
-            assert resp.status == 400
-            data = await resp.json()
-            assert "input" in data["error"]["message"]
-
-    @pytest.mark.asyncio
-    async def test_start_empty_input_returns_400(self, adapter):
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.post("/v1/runs", json={"input": ""})
-        assert resp.status == 400
-
-    @pytest.mark.asyncio
-    async def test_start_requires_auth(self, auth_adapter):
-        app = _create_runs_app(auth_adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.post("/v1/runs", json={"input": "hello"})
-        assert resp.status == 401
-
-    @pytest.mark.asyncio
-    async def test_start_with_valid_auth(self, auth_adapter):
-        app = _create_runs_app(auth_adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(auth_adapter, "_create_agent") as mock_create:
-                mock_agent = MagicMock()
-                mock_agent.run_conversation.return_value = {"final_response": "ok"}
-                mock_agent.session_prompt_tokens = 0
-                mock_agent.session_completion_tokens = 0
-                mock_agent.session_total_tokens = 0
-                mock_create.return_value = mock_agent
-
-                resp = await cli.post(
-                    "/v1/runs",
-                    json={"input": "hello"},
-                    headers={"Authorization": "Bearer sk-secret"},
-                )
-                assert resp.status == 202
-
-
-# ---------------------------------------------------------------------------
-# GET /v1/runs/{run_id}/events — SSE event stream
-# ---------------------------------------------------------------------------
-
-
-class TestRunEvents:
-    @pytest.mark.asyncio
-    async def test_events_stream_returns_completed(self, adapter):
-        """Events stream should receive run.completed when agent finishes."""
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(adapter, "_create_agent") as mock_create:
-                mock_agent = MagicMock()
-                mock_agent.run_conversation.return_value = {"final_response": "Hello!"}
-                mock_agent.session_prompt_tokens = 10
-                mock_agent.session_completion_tokens = 5
-                mock_agent.session_total_tokens = 15
-                mock_create.return_value = mock_agent
-
-                # Start run
-                resp = await cli.post("/v1/runs", json={"input": "hello"})
-                assert resp.status == 202
-                data = await resp.json()
-                run_id = data["run_id"]
-
-                # Subscribe to events
-                events_resp = await cli.get(f"/v1/runs/{run_id}/events")
-                assert events_resp.status == 200
-                body = await events_resp.text()
-
-                # Should contain run.completed
-                assert "run.completed" in body
-                assert "Hello!" in body
-
-    @pytest.mark.asyncio
-    async def test_events_not_found_returns_404(self, adapter):
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.get("/v1/runs/run_nonexistent/events")
-        assert resp.status == 404
-
-    @pytest.mark.asyncio
-    async def test_events_requires_auth(self, auth_adapter):
-        app = _create_runs_app(auth_adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.get("/v1/runs/run_any/events")
-        assert resp.status == 401
-
-
-# ---------------------------------------------------------------------------
-# POST /v1/runs/{run_id}/stop — interrupt a running agent
-# ---------------------------------------------------------------------------
-
-
-class TestStopRun:
-    @pytest.mark.asyncio
-    async def test_stop_running_agent(self, adapter):
-        """Stop should interrupt the agent and cancel the task."""
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(adapter, "_create_agent") as mock_create:
-                mock_agent, agent_ready, _ = _make_slow_agent()
-                mock_create.return_value = mock_agent
-
-                # Start run
-                resp = await cli.post("/v1/runs", json={"input": "hello"})
-                assert resp.status == 202
-                data = await resp.json()
-                run_id = data["run_id"]
-
-                # Wait for agent to start running in the thread
-                agent_ready.wait(timeout=3.0)
-                await asyncio.sleep(0.1)
-
-                # Verify agent ref is stored
-                assert run_id in adapter._active_run_agents
-
-                # Stop the run
-                stop_resp = await cli.post(f"/v1/runs/{run_id}/stop")
-                assert stop_resp.status == 200
-                stop_data = await stop_resp.json()
-                assert stop_data["run_id"] == run_id
-                assert stop_data["status"] == "stopping"
-
-                # Agent interrupt should have been called
-                mock_agent.interrupt.assert_called_once_with("Stop requested via API")
-
-                # Refs should be cleaned up
-                await asyncio.sleep(0.5)
-                assert run_id not in adapter._active_run_agents
-                assert run_id not in adapter._active_run_tasks
-
-    @pytest.mark.asyncio
-    async def test_stop_nonexistent_run_returns_404(self, adapter):
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.post("/v1/runs/run_nonexistent/stop")
-        assert resp.status == 404
-
-    @pytest.mark.asyncio
-    async def test_stop_requires_auth(self, auth_adapter):
-        app = _create_runs_app(auth_adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.post("/v1/runs/run_any/stop")
-        assert resp.status == 401
-
-    @pytest.mark.asyncio
-    async def test_stop_already_completed_run_returns_404(self, adapter):
-        """Stopping a run that already finished should return 404 (refs cleaned up)."""
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(adapter, "_create_agent") as mock_create:
-                mock_agent = MagicMock()
-                mock_agent.run_conversation.return_value = {"final_response": "done"}
-                mock_agent.session_prompt_tokens = 0
-                mock_agent.session_completion_tokens = 0
-                mock_agent.session_total_tokens = 0
-                mock_create.return_value = mock_agent
-
-                # Start and wait for completion
-                resp = await cli.post("/v1/runs", json={"input": "hello"})
-                assert resp.status == 202
-                data = await resp.json()
-                run_id = data["run_id"]
-
-                await asyncio.sleep(0.3)
-
-                # Run should be done, refs cleaned up
-                assert run_id not in adapter._active_run_agents
-
-                # Stop should return 404
-                stop_resp = await cli.post(f"/v1/runs/{run_id}/stop")
-                assert stop_resp.status == 404
-
-    @pytest.mark.asyncio
-    async def test_stop_interrupt_exception_does_not_crash(self, adapter):
-        """If agent.interrupt() raises, stop should still succeed."""
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(adapter, "_create_agent") as mock_create:
-                mock_agent, agent_ready, _ = _make_slow_agent()
-                # Override the interrupt side_effect to raise
-                mock_agent.interrupt = MagicMock(side_effect=RuntimeError("interrupt failed"))
-                mock_create.return_value = mock_agent
-
-                resp = await cli.post("/v1/runs", json={"input": "hello"})
-                assert resp.status == 202
-                data = await resp.json()
-                run_id = data["run_id"]
-
-                agent_ready.wait(timeout=3.0)
-                await asyncio.sleep(0.1)
-
-                stop_resp = await cli.post(f"/v1/runs/{run_id}/stop")
-                assert stop_resp.status == 200
-                stop_data = await stop_resp.json()
-                assert stop_data["status"] == "stopping"
-
-    @pytest.mark.asyncio
-    async def test_stop_sends_sentinel_to_events_stream(self, adapter):
-        """After stop, the events stream should close."""
-        app = _create_runs_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            with patch.object(adapter, "_create_agent") as mock_create:
-                mock_agent, agent_ready, _ = _make_slow_agent()
-                mock_create.return_value = mock_agent
-
-                # Start run
-                resp = await cli.post("/v1/runs", json={"input": "hello"})
-                assert resp.status == 202
-                data = await resp.json()
-                run_id = data["run_id"]
-
-                agent_ready.wait(timeout=3.0)
-                await asyncio.sleep(0.1)
-
-                # Subscribe to events in background
-                events_task = asyncio.ensure_future(
-                    cli.get(f"/v1/runs/{run_id}/events")
-                )
-
-                await asyncio.sleep(0.1)
-
-                # Stop the run
-                stop_resp = await cli.post(f"/v1/runs/{run_id}/stop")
-                assert stop_resp.status == 200
-
-                # Events stream should close
-                events_resp = await asyncio.wait_for(events_task, timeout=5.0)
-                assert events_resp.status == 200
-                body = await events_resp.text()
-                # Stream should have received run.failed and closed
-                assert "run.failed" in body or "stream closed" in body

tests/gateway/test_busy_session_ack.py

@@ -349,121 +349,3 @@ class TestBusySessionAck:
 
         result = await runner._handle_active_session_busy_message(event, sk)
         assert result is False  # not handled, let default path try
-
-
-class TestBusySessionOnboardingHint:
-    """First-touch hint appended to the busy-ack the first time it fires."""
-
-    @pytest.mark.asyncio
-    async def test_first_busy_ack_appends_interrupt_hint(self, tmp_path, monkeypatch):
-        """First busy-while-running message gets an extra hint about /busy."""
-        import gateway.run as _gr
-
-        monkeypatch.setattr(_gr, "_hermes_home", tmp_path)
-        # mark_seen imports utils.atomic_yaml_write; make sure it resolves
-        # against a writable dir by pointing _hermes_home at tmp_path.
-        monkeypatch.setattr(_gr, "_load_gateway_config", lambda: {})
-
-        runner, _sentinel = _make_runner()
-        runner._busy_input_mode = "interrupt"
-        adapter = _make_adapter()
-
-        event = _make_event(text="ping")
-        sk = build_session_key(event.source)
-
-        agent = MagicMock()
-        agent.get_activity_summary.return_value = {
-            "api_call_count": 3, "max_iterations": 60,
-            "current_tool": None, "last_activity_ts": time.time(),
-            "last_activity_desc": "api", "seconds_since_activity": 0.1,
-        }
-        runner._running_agents[sk] = agent
-        runner._running_agents_ts[sk] = time.time() - 5
-        runner.adapters[event.source.platform] = adapter
-
-        await runner._handle_active_session_busy_message(event, sk)
-
-        call_kwargs = adapter._send_with_retry.call_args
-        content = call_kwargs.kwargs.get("content", "")
-
-        # Normal ack body
-        assert "Interrupting" in content
-        # First-touch hint appended
-        assert "First-time tip" in content
-        assert "/busy queue" in content
-
-        # The flag is now persisted to tmp_path/config.yaml
-        import yaml
-        cfg = yaml.safe_load((tmp_path / "config.yaml").read_text())
-        assert cfg["onboarding"]["seen"]["busy_input_prompt"] is True
-
-    @pytest.mark.asyncio
-    async def test_second_busy_ack_omits_hint(self, tmp_path, monkeypatch):
-        """Once the flag is marked, the hint never appears again."""
-        import gateway.run as _gr
-        import yaml
-
-        monkeypatch.setattr(_gr, "_hermes_home", tmp_path)
-        # Pre-populate the config so is_seen() returns True from the start.
-        (tmp_path / "config.yaml").write_text(yaml.safe_dump({
-            "onboarding": {"seen": {"busy_input_prompt": True}},
-        }))
-        monkeypatch.setattr(
-            _gr, "_load_gateway_config",
-            lambda: yaml.safe_load((tmp_path / "config.yaml").read_text()),
-        )
-
-        runner, _sentinel = _make_runner()
-        runner._busy_input_mode = "interrupt"
-        adapter = _make_adapter()
-
-        event = _make_event(text="ping again")
-        sk = build_session_key(event.source)
-
-        agent = MagicMock()
-        agent.get_activity_summary.return_value = {
-            "api_call_count": 3, "max_iterations": 60,
-            "current_tool": None, "last_activity_ts": time.time(),
-            "last_activity_desc": "api", "seconds_since_activity": 0.1,
-        }
-        runner._running_agents[sk] = agent
-        runner._running_agents_ts[sk] = time.time() - 5
-        runner.adapters[event.source.platform] = adapter
-
-        await runner._handle_active_session_busy_message(event, sk)
-
-        call_kwargs = adapter._send_with_retry.call_args
-        content = call_kwargs.kwargs.get("content", "")
-
-        assert "Interrupting" in content
-        assert "First-time tip" not in content
-        assert "/busy queue" not in content
-
-    @pytest.mark.asyncio
-    async def test_queue_mode_hint_points_to_interrupt(self, tmp_path, monkeypatch):
-        """In queue mode the hint should suggest /busy interrupt, not /busy queue."""
-        import gateway.run as _gr
-
-        monkeypatch.setattr(_gr, "_hermes_home", tmp_path)
-        monkeypatch.setattr(_gr, "_load_gateway_config", lambda: {})
-
-        runner, _sentinel = _make_runner()
-        runner._busy_input_mode = "queue"
-        adapter = _make_adapter()
-
-        event = _make_event(text="queue me")
-        sk = build_session_key(event.source)
-        runner.adapters[event.source.platform] = adapter
-
-        agent = MagicMock()
-        runner._running_agents[sk] = agent
-
-        with patch("gateway.run.merge_pending_message_event"):
-            await runner._handle_active_session_busy_message(event, sk)
-
-        content = adapter._send_with_retry.call_args.kwargs.get("content", "")
-        assert "Queued for the next turn" in content
-        assert "First-time tip" in content
-        assert "/busy interrupt" in content
-        # Must NOT tell the user to /busy queue when they're already on queue.
-        assert "/busy queue" not in content

tests/gateway/test_reasoning_command.py

@@ -33,7 +33,6 @@ def _make_runner():
     runner._ephemeral_system_prompt = ""
     runner._prefill_messages = []
     runner._reasoning_config = None
-    runner._session_reasoning_overrides = {}
     runner._show_reasoning = False
     runner._provider_routing = {}
     runner._fallback_model = None
@@ -77,10 +76,6 @@ class TestReasoningCommand:
         source = inspect.getsource(gateway_run.GatewayRunner._handle_message)
         assert '"reasoning"' in source
 
-    def test_parse_reasoning_command_args_accepts_ascii_and_smart_global_flags(self):
-        assert gateway_run.GatewayRunner._parse_reasoning_command_args("high --global") == ("high", True)
-        assert gateway_run.GatewayRunner._parse_reasoning_command_args("—global xhigh") == ("xhigh", True)
-
     @pytest.mark.asyncio
     async def test_reasoning_command_reloads_current_state_from_config(self, tmp_path, monkeypatch):
         hermes_home = tmp_path / "hermes"
@@ -116,90 +111,13 @@ class TestReasoningCommand:
         runner = _make_runner()
         runner._reasoning_config = {"enabled": True, "effort": "medium"}
 
-        result = await runner._handle_reasoning_command(_make_event("/reasoning low --global"))
+        result = await runner._handle_reasoning_command(_make_event("/reasoning low"))
 
         saved = yaml.safe_load(config_path.read_text(encoding="utf-8"))
         assert saved["agent"]["reasoning_effort"] == "low"
         assert runner._reasoning_config == {"enabled": True, "effort": "low"}
         assert "takes effect on next message" in result
 
-    @pytest.mark.asyncio
-    async def test_handle_reasoning_command_defaults_to_session_only(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir()
-        config_path = hermes_home / "config.yaml"
-        config_path.write_text("agent:\n  reasoning_effort: medium\n", encoding="utf-8")
-
-        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-
-        runner = _make_runner()
-        event = _make_event("/reasoning high")
-        session_key = runner._session_key_for_source(event.source)
-
-        result = await runner._handle_reasoning_command(event)
-
-        saved = yaml.safe_load(config_path.read_text(encoding="utf-8"))
-        assert saved["agent"]["reasoning_effort"] == "medium"
-        assert runner._session_reasoning_overrides[session_key] == {"enabled": True, "effort": "high"}
-        assert runner._reasoning_config == {"enabled": True, "effort": "high"}
-        assert "session only" in result
-
-    @pytest.mark.asyncio
-    async def test_reasoning_global_clears_existing_session_override(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir()
-        config_path = hermes_home / "config.yaml"
-        config_path.write_text("agent:\n  reasoning_effort: medium\n", encoding="utf-8")
-
-        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-
-        runner = _make_runner()
-        event = _make_event("/reasoning low --global")
-        session_key = runner._session_key_for_source(event.source)
-        runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "xhigh"}
-
-        result = await runner._handle_reasoning_command(event)
-
-        saved = yaml.safe_load(config_path.read_text(encoding="utf-8"))
-        assert saved["agent"]["reasoning_effort"] == "low"
-        assert session_key not in runner._session_reasoning_overrides
-        assert "saved to config" in result
-
-    @pytest.mark.asyncio
-    async def test_reasoning_reset_clears_session_override_without_config_write(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir()
-        config_path = hermes_home / "config.yaml"
-        config_path.write_text("agent:\n  reasoning_effort: medium\n", encoding="utf-8")
-
-        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-
-        runner = _make_runner()
-        event = _make_event("/reasoning reset")
-        session_key = runner._session_key_for_source(event.source)
-        runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "xhigh"}
-
-        result = await runner._handle_reasoning_command(event)
-
-        saved = yaml.safe_load(config_path.read_text(encoding="utf-8"))
-        assert saved["agent"]["reasoning_effort"] == "medium"
-        assert session_key not in runner._session_reasoning_overrides
-        assert "cleared" in result
-
-    def test_resolve_session_reasoning_prefers_session_override(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir()
-        (hermes_home / "config.yaml").write_text("agent:\n  reasoning_effort: low\n", encoding="utf-8")
-
-        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-
-        runner = _make_runner()
-        source = _make_event("/reasoning").source
-        session_key = runner._session_key_for_source(source)
-        runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "xhigh"}
-
-        assert runner._resolve_session_reasoning_config(source=source) == {"enabled": True, "effort": "xhigh"}
-
     def test_run_agent_reloads_reasoning_config_per_message(self, tmp_path, monkeypatch):
         hermes_home = tmp_path / "hermes"
         hermes_home.mkdir()
@@ -249,56 +167,6 @@ class TestReasoningCommand:
         assert _CapturingAgent.last_init is not None
         assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": True, "effort": "low"}
 
-    def test_run_agent_prefers_session_reasoning_override(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir()
-        (hermes_home / "config.yaml").write_text("agent:\n  reasoning_effort: low\n", encoding="utf-8")
-
-        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
-        monkeypatch.setattr(gateway_run, "_env_path", hermes_home / ".env")
-        monkeypatch.setattr(gateway_run, "load_dotenv", lambda *args, **kwargs: None)
-        monkeypatch.setattr(
-            gateway_run,
-            "_resolve_runtime_agent_kwargs",
-            lambda: {
-                "provider": "openrouter",
-                "api_mode": "chat_completions",
-                "base_url": "https://openrouter.ai/api/v1",
-                "api_key": "***",
-            },
-        )
-        fake_run_agent = types.ModuleType("run_agent")
-        fake_run_agent.AIAgent = _CapturingAgent
-        monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
-
-        _CapturingAgent.last_init = None
-        runner = _make_runner()
-        session_key = "agent:main:local:dm"
-        runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "high"}
-
-        source = SessionSource(
-            platform=Platform.LOCAL,
-            chat_id="cli",
-            chat_name="CLI",
-            chat_type="dm",
-            user_id="user-1",
-        )
-
-        result = asyncio.run(
-            runner._run_agent(
-                message="ping",
-                context_prompt="",
-                history=[],
-                source=source,
-                session_id="session-1",
-                session_key=session_key,
-            )
-        )
-
-        assert result["final_response"] == "ok"
-        assert _CapturingAgent.last_init is not None
-        assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": True, "effort": "high"}
-
     def test_run_agent_includes_enabled_mcp_servers_in_gateway_toolsets(self, tmp_path, monkeypatch):
         hermes_home = tmp_path / "hermes"
         hermes_home.mkdir()

tests/gateway/test_run_progress_interrupt.py

@@ -1,215 +0,0 @@
-"""Tests for interrupt-aware tool-progress suppression in gateway.
-
-When a user sends `stop` while the agent is executing a batch of parallel
-tool calls, the gateway's progress_callback should stop queuing 🔍 bubbles
-and the drain loop should drop any already-queued events.  Without this
-guard, the stop acknowledgement appears first but is followed by a trail
-of tool-progress bubbles for calls that were already parsed from the LLM
-response — making the interrupt feel ignored.
-"""
-
-import asyncio
-import importlib
-import sys
-import time
-import types
-from types import SimpleNamespace
-
-import pytest
-
-from gateway.config import Platform, PlatformConfig
-from gateway.platforms.base import BasePlatformAdapter, SendResult
-from gateway.session import SessionSource
-
-
-class ProgressCaptureAdapter(BasePlatformAdapter):
-    def __init__(self, platform=Platform.TELEGRAM):
-        super().__init__(PlatformConfig(enabled=True, token="***"), platform)
-        self.sent = []
-        self.edits = []
-        self.typing = []
-
-    async def connect(self) -> bool:
-        return True
-
-    async def disconnect(self) -> None:
-        return None
-
-    async def send(self, chat_id, content, reply_to=None, metadata=None) -> SendResult:
-        self.sent.append({"chat_id": chat_id, "content": content})
-        return SendResult(success=True, message_id="progress-1")
-
-    async def edit_message(self, chat_id, message_id, content) -> SendResult:
-        self.edits.append({"message_id": message_id, "content": content})
-        return SendResult(success=True, message_id=message_id)
-
-    async def send_typing(self, chat_id, metadata=None) -> None:
-        self.typing.append(chat_id)
-
-    async def stop_typing(self, chat_id) -> None:
-        return None
-
-    async def get_chat_info(self, chat_id: str):
-        return {"id": chat_id}
-
-
-class PreInterruptAgent:
-    """Fires tool-progress events BEFORE the interrupt lands.
-
-    These should render normally.  Baseline for comparison with the
-    interrupted case — proves the harness renders events when no
-    interrupt is active.
-    """
-
-    def __init__(self, **kwargs):
-        self.tool_progress_callback = kwargs.get("tool_progress_callback")
-        self.tools = []
-        self._interrupt_requested = False
-
-    @property
-    def is_interrupted(self) -> bool:
-        return self._interrupt_requested
-
-    def run_conversation(self, message, conversation_history=None, task_id=None):
-        self.tool_progress_callback("tool.started", "web_search", "first search", {})
-        time.sleep(0.35)  # let the drain loop process
-        return {"final_response": "done", "messages": [], "api_calls": 1}
-
-
-class InterruptedAgent:
-    """Fires tool.started events AFTER interrupt — all should be suppressed.
-
-    Mirrors the failure mode in the bug report: LLM returned N parallel
-    web_search calls, interrupt flag flipped, remaining events still
-    rendered as bubbles.  With the fix, none of these should appear.
-    """
-
-    def __init__(self, **kwargs):
-        self.tool_progress_callback = kwargs.get("tool_progress_callback")
-        self.tools = []
-        # Start already interrupted — simulates stop having already landed
-        # by the time the agent batch starts firing tool.started events.
-        self._interrupt_requested = True
-
-    @property
-    def is_interrupted(self) -> bool:
-        return self._interrupt_requested
-
-    def run_conversation(self, message, conversation_history=None, task_id=None):
-        # Parallel tool batch — in production these come from one LLM
-        # response with 5 tool_calls.  All are post-interrupt.
-        self.tool_progress_callback("tool.started", "web_search", "cognee hermes", {})
-        self.tool_progress_callback("tool.started", "web_search", "McBee deer hunting", {})
-        self.tool_progress_callback("tool.started", "web_search", "kuzu graph db", {})
-        self.tool_progress_callback("tool.started", "web_search", "moonshot kimi api", {})
-        self.tool_progress_callback("tool.started", "web_search", "platform.moonshot.cn", {})
-        time.sleep(0.35)  # let the drain loop attempt to process the queue
-        return {"final_response": "interrupted", "messages": [], "api_calls": 1}
-
-
-def _make_runner(adapter):
-    gateway_run = importlib.import_module("gateway.run")
-    GatewayRunner = gateway_run.GatewayRunner
-
-    runner = object.__new__(GatewayRunner)
-    runner.adapters = {adapter.platform: adapter}
-    runner._voice_mode = {}
-    runner._prefill_messages = []
-    runner._ephemeral_system_prompt = ""
-    runner._reasoning_config = None
-    runner._provider_routing = {}
-    runner._fallback_model = None
-    runner._session_db = None
-    runner._running_agents = {}
-    runner._session_run_generation = {}
-    runner.hooks = SimpleNamespace(loaded_hooks=False)
-    runner.config = SimpleNamespace(
-        thread_sessions_per_user=False,
-        group_sessions_per_user=False,
-        stt_enabled=False,
-    )
-    return runner
-
-
-async def _run_once(monkeypatch, tmp_path, agent_cls, session_id):
-    monkeypatch.setenv("HERMES_TOOL_PROGRESS_MODE", "all")
-
-    fake_dotenv = types.ModuleType("dotenv")
-    fake_dotenv.load_dotenv = lambda *args, **kwargs: None
-    monkeypatch.setitem(sys.modules, "dotenv", fake_dotenv)
-
-    fake_run_agent = types.ModuleType("run_agent")
-    fake_run_agent.AIAgent = agent_cls
-    monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
-
-    adapter = ProgressCaptureAdapter()
-    runner = _make_runner(adapter)
-    gateway_run = importlib.import_module("gateway.run")
-    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
-    monkeypatch.setattr(
-        gateway_run,
-        "_resolve_runtime_agent_kwargs",
-        lambda: {"api_key": "fake"},
-    )
-    source = SessionSource(
-        platform=Platform.TELEGRAM,
-        chat_id="-1001",
-        chat_type="group",
-        thread_id="17585",
-    )
-    result = await runner._run_agent(
-        message="hi",
-        context_prompt="",
-        history=[],
-        source=source,
-        session_id=session_id,
-        session_key="agent:main:telegram:group:-1001:17585",
-    )
-    return adapter, result
-
-
-@pytest.mark.asyncio
-async def test_baseline_non_interrupted_agent_renders_progress(monkeypatch, tmp_path):
-    """Sanity check: when is_interrupted is False, tool-progress renders normally."""
-    adapter, result = await _run_once(monkeypatch, tmp_path, PreInterruptAgent, "sess-baseline")
-    assert result["final_response"] == "done"
-    rendered = " ".join(c["content"] for c in adapter.sent) + " " + " ".join(
-        c["content"] for c in adapter.edits
-    )
-    assert "first search" in rendered, (
-        "baseline agent should render its tool-progress event — "
-        "if this fails the test harness is broken, not the fix"
-    )
-
-
-@pytest.mark.asyncio
-async def test_progress_suppressed_when_agent_is_interrupted(monkeypatch, tmp_path):
-    """Post-interrupt tool.started events must not render as bubbles.
-
-    This is Bug B from the screenshot: user sends `stop`, agent acks with
-    ⚡ Interrupting, but 5 more 🔍 web_search bubbles still render because
-    their tool.started events were already parsed from the LLM response.
-    With the fix, progress_callback and the drain loop both check
-    is_interrupted and skip these events.
-    """
-    adapter, result = await _run_once(
-        monkeypatch, tmp_path, InterruptedAgent, "sess-interrupted"
-    )
-    assert result["final_response"] == "interrupted"
-
-    rendered = " ".join(c["content"] for c in adapter.sent) + " " + " ".join(
-        c["content"] for c in adapter.edits
-    )
-
-    # None of the post-interrupt queries should appear.
-    for leaked_query in (
-        "cognee hermes",
-        "McBee deer hunting",
-        "kuzu graph db",
-        "moonshot kimi api",
-        "platform.moonshot.cn",
-    ):
-        assert leaked_query not in rendered, (
-            f"event '{leaked_query}' leaked into the UI after interrupt — "
-            f"progress_callback / drain loop is not checking is_interrupted"
-        )

tests/gateway/test_running_agent_session_toggles.py

@@ -165,26 +165,3 @@ async def test_reasoning_rejected_mid_run():
     assert result is not None
     assert "can't run mid-turn" in result
     assert "/reasoning" in result
-
-
-@pytest.mark.asyncio
-async def test_btw_dispatches_mid_run():
-    """/btw mid-run must dispatch to /background's handler, not hit the catch-all.
-
-    /btw is an alias of /background (see hermes_cli/commands.py). Typing
-    /btw mid-turn must spawn a parallel background task — that's the whole
-    point of the command. Before the mid-turn bypass was added for
-    /background, /btw fell through to the "Agent is running — wait or
-    /stop first" catch-all, making it useless in exactly the scenario it
-    was designed for. The alias and the bypass together make it work.
-    """
-    runner = _make_runner()
-    runner._handle_background_command = AsyncMock(
-        return_value='🚀 Background task started: "what module owns titles?"'
-    )
-
-    result = await runner._handle_message(_make_event("/btw what module owns titles?"))
-
-    runner._handle_background_command.assert_awaited_once()
-    assert result is not None
-    assert "can't run mid-turn" not in result

tests/gateway/test_session_info.py

@@ -58,7 +58,7 @@ class TestFormatSessionInfo:
                                   {"provider": "", "base_url": "", "api_key": ""})
         with p1, p2, p3:
             info = runner._format_session_info()
-        assert "256K" in info
+        assert "128K" in info
         assert "model.context_length" in info
 
     def test_local_endpoint_shown(self, runner, tmp_path):

tests/gateway/test_session_model_override_routing.py

@@ -54,7 +54,6 @@ def _make_runner():
     runner._background_tasks = set()
     runner._session_db = None
     runner._session_model_overrides = {}
-    runner._session_reasoning_overrides = {}
     runner._pending_model_notes = {}
     runner._pending_approvals = {}
     runner._agent_cache = {}
@@ -103,7 +102,6 @@ def test_run_agent_prefers_session_override_over_global_runtime(monkeypatch):
     )
     session_key = "agent:main:local:dm"
     runner._session_model_overrides[session_key] = _codex_override()
-    runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "high"}
 
     result = asyncio.run(
         runner._run_agent(
@@ -123,7 +121,6 @@ def test_run_agent_prefers_session_override_over_global_runtime(monkeypatch):
     assert _CapturingAgent.last_init["api_mode"] == "codex_responses"
     assert _CapturingAgent.last_init["base_url"] == "https://chatgpt.com/backend-api/codex"
     assert _CapturingAgent.last_init["api_key"] == "***"
-    assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": True, "effort": "high"}
 
 
 @pytest.mark.asyncio
@@ -152,7 +149,6 @@ async def test_background_task_prefers_session_override_over_global_runtime(monk
     )
     session_key = runner._session_key_for_source(source)
     runner._session_model_overrides[session_key] = _codex_override()
-    runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "high"}
 
     await runner._run_background_task("say hello", source, "bg_test")
 
@@ -162,4 +158,3 @@ async def test_background_task_prefers_session_override_over_global_runtime(monk
     assert _CapturingAgent.last_init["api_mode"] == "codex_responses"
     assert _CapturingAgent.last_init["base_url"] == "https://chatgpt.com/backend-api/codex"
     assert _CapturingAgent.last_init["api_key"] == "***"
-    assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": True, "effort": "high"}

tests/gateway/test_session_model_reset.py

@@ -1,4 +1,4 @@
-"""Tests that /new (and its /reset alias) clears session-scoped overrides."""
+"""Tests that /new (and its /reset alias) clears the session-scoped model override."""
 from datetime import datetime
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, MagicMock
@@ -37,7 +37,6 @@ def _make_runner():
     runner._voice_mode = {}
     runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
     runner._session_model_overrides = {}
-    runner._session_reasoning_overrides = {}
     runner._pending_model_notes = {}
     runner._background_tasks = set()
 
@@ -76,16 +75,14 @@ async def test_new_command_clears_session_model_override():
     runner._session_model_overrides[session_key] = {
         "model": "gpt-4o",
         "provider": "openai",
-        "api_key": "***",
+        "api_key": "sk-test",
         "base_url": "",
         "api_mode": "openai",
     }
-    runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "high"}
 
     await runner._handle_reset_command(_make_event("/new"))
 
     assert session_key not in runner._session_model_overrides
-    assert session_key not in runner._session_reasoning_overrides
 
 
 @pytest.mark.asyncio
@@ -95,12 +92,10 @@ async def test_new_command_no_override_is_noop():
     session_key = build_session_key(_make_source())
 
     assert session_key not in runner._session_model_overrides
-    assert session_key not in runner._session_reasoning_overrides
 
     await runner._handle_reset_command(_make_event("/new"))
 
     assert session_key not in runner._session_model_overrides
-    assert session_key not in runner._session_reasoning_overrides
 
 
 @pytest.mark.asyncio
@@ -120,16 +115,12 @@ async def test_new_command_only_clears_own_session():
     runner._session_model_overrides[other_key] = {
         "model": "claude-sonnet-4-6",
         "provider": "anthropic",
-        "api_key": "***",
+        "api_key": "sk-ant-test",
         "base_url": "",
         "api_mode": "anthropic",
     }
-    runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "high"}
-    runner._session_reasoning_overrides[other_key] = {"enabled": True, "effort": "low"}
 
     await runner._handle_reset_command(_make_event("/new"))
 
     assert session_key not in runner._session_model_overrides
     assert other_key in runner._session_model_overrides
-    assert session_key not in runner._session_reasoning_overrides
-    assert other_key in runner._session_reasoning_overrides

tests/gateway/test_voice_command.py

@@ -177,53 +177,6 @@ class TestHandleVoiceCommand:
 
         assert adapter._auto_tts_disabled_chats == {"123"}
 
-    def test_sync_populates_enabled_chats_from_voice_modes(self, runner):
-        """Issue #16007: sync also restores per-chat /voice on|tts opt-ins.
-
-        The adapter's ``_auto_tts_enabled_chats`` must mirror chats whose
-        persisted voice_mode is ``voice_only`` or ``all`` — without this,
-        ``/voice on`` was relying on a "not in disabled set" default that
-        silently enabled auto-TTS for every chat.
-        """
-        from gateway.config import Platform
-        runner._voice_mode = {
-            "telegram:off_chat": "off",
-            "telegram:on_chat": "voice_only",
-            "telegram:tts_chat": "all",
-            "slack:999": "voice_only",  # wrong platform, must be ignored
-        }
-        adapter = SimpleNamespace(
-            _auto_tts_default=False,
-            _auto_tts_disabled_chats=set(),
-            _auto_tts_enabled_chats=set(),
-            platform=Platform.TELEGRAM,
-        )
-
-        runner._sync_voice_mode_state_to_adapter(adapter)
-
-        assert adapter._auto_tts_disabled_chats == {"off_chat"}
-        assert adapter._auto_tts_enabled_chats == {"on_chat", "tts_chat"}
-
-    def test_sync_pushes_config_default_onto_adapter(self, runner, monkeypatch):
-        """Issue #16007: ``voice.auto_tts`` must propagate to ``_auto_tts_default``."""
-        from gateway.config import Platform
-
-        fake_cfg = {"voice": {"auto_tts": True}}
-        monkeypatch.setattr(
-            "hermes_cli.config.load_config",
-            lambda: fake_cfg,
-        )
-        adapter = SimpleNamespace(
-            _auto_tts_default=False,
-            _auto_tts_disabled_chats=set(),
-            _auto_tts_enabled_chats=set(),
-            platform=Platform.TELEGRAM,
-        )
-
-        runner._sync_voice_mode_state_to_adapter(adapter)
-
-        assert adapter._auto_tts_default is True
-
     def test_restart_restores_voice_off_state(self, runner, tmp_path):
         from gateway.config import Platform
         runner._VOICE_MODE_PATH.write_text(json.dumps({"telegram:123": "off"}))
@@ -2753,56 +2706,3 @@ class TestUDPKeepalive:
             mock_conn.send_packet.assert_called_with(b'\xf8\xff\xfe')
         finally:
             DiscordAdapter._KEEPALIVE_INTERVAL = original_interval
-
-
-# =====================================================================
-# BasePlatformAdapter._should_auto_tts_for_chat — gate for auto-TTS
-# on voice input. Regression test for Issue #16007.
-# =====================================================================
-
-class TestShouldAutoTtsForChat:
-    """Three-layer gate: per-chat enable > per-chat disable > config default."""
-
-    def _make_adapter(self, *, default: bool, enabled=(), disabled=()):
-        """Build a bare adapter with only the attrs the gate reads."""
-        adapter = SimpleNamespace(
-            _auto_tts_default=default,
-            _auto_tts_enabled_chats=set(enabled),
-            _auto_tts_disabled_chats=set(disabled),
-        )
-        # Bind the unbound method — _should_auto_tts_for_chat only reads the
-        # three attrs above via ``self.``, so an unbound call works.
-        from gateway.platforms.base import BasePlatformAdapter
-        return BasePlatformAdapter._should_auto_tts_for_chat, adapter
-
-    def test_default_false_no_override_suppresses(self):
-        """Issue #16007: voice.auto_tts=False and no per-chat state → no TTS."""
-        fn, adapter = self._make_adapter(default=False)
-        assert fn(adapter, "chat1") is False
-
-    def test_default_true_no_override_fires(self):
-        fn, adapter = self._make_adapter(default=True)
-        assert fn(adapter, "chat1") is True
-
-    def test_explicit_enable_overrides_false_default(self):
-        """``/voice on`` with config auto_tts=False still fires."""
-        fn, adapter = self._make_adapter(default=False, enabled={"chat1"})
-        assert fn(adapter, "chat1") is True
-
-    def test_explicit_disable_overrides_true_default(self):
-        """``/voice off`` with config auto_tts=True still suppresses."""
-        fn, adapter = self._make_adapter(default=True, disabled={"chat1"})
-        assert fn(adapter, "chat1") is False
-
-    def test_enabled_wins_over_disabled(self):
-        """An explicit enable beats an explicit disable (enable takes priority)."""
-        fn, adapter = self._make_adapter(
-            default=False, enabled={"chat1"}, disabled={"chat1"}
-        )
-        assert fn(adapter, "chat1") is True
-
-    def test_per_chat_isolation(self):
-        """Enable for chat1 doesn't leak to chat2."""
-        fn, adapter = self._make_adapter(default=False, enabled={"chat1"})
-        assert fn(adapter, "chat1") is True
-        assert fn(adapter, "chat2") is False

tests/hermes_cli/test_apply_model_switch_result_context.py

@@ -1,152 +0,0 @@
-"""Regression test for the `/model` picker confirmation display.
-
-Bug (April 2026): after choosing a model from the interactive `/model` picker,
-``HermesCLI._apply_model_switch_result()`` printed ``ModelInfo.context_window``
-straight from models.dev, which always reports the vendor-wide value (e.g.
-gpt-5.5 = 1,050,000 on ``openai``). That ignored provider-specific caps — in
-particular, ChatGPT Codex OAuth enforces 272K on the same slug. The sibling
-``_handle_model_switch()`` (typed ``/model <name>``) was already fixed to use
-``resolve_display_context_length()``; the picker path was missed, causing
-"sometimes 1M, sometimes 272K" for the same model across sibling UI paths.
-
-Fix: both display paths now go through ``resolve_display_context_length()``.
-"""
-from __future__ import annotations
-
-from unittest.mock import patch
-
-from hermes_cli.model_switch import ModelSwitchResult
-
-
-class _FakeModelInfo:
-    context_window = 1_050_000
-    max_output = 0
-
-    def has_cost_data(self):
-        return False
-
-    def format_capabilities(self):
-        return ""
-
-
-class _StubCLI:
-    """Minimum attrs ``_apply_model_switch_result`` reads on ``self``."""
-    agent = None
-    model = ""
-    provider = ""
-    requested_provider = ""
-    api_key = ""
-    _explicit_api_key = ""
-    base_url = ""
-    _explicit_base_url = ""
-    api_mode = ""
-    _pending_model_switch_note = ""
-
-
-def _run_display(monkeypatch, result):
-    import cli as cli_mod
-
-    captured: list[str] = []
-    monkeypatch.setattr(cli_mod, "_cprint", lambda s, *a, **k: captured.append(str(s)))
-    # Avoid writing to ~/.hermes/config.yaml during the test.
-    monkeypatch.setattr(cli_mod, "save_config_value", lambda *a, **k: None)
-    cli_mod.HermesCLI._apply_model_switch_result(_StubCLI(), result, False)
-    return captured
-
-
-def test_picker_path_uses_provider_aware_context_on_codex(monkeypatch):
-    """``_apply_model_switch_result`` must prefer the provider-aware resolver
-    (272K on Codex) over the raw models.dev value (1.05M for gpt-5.5).
-    """
-    result = ModelSwitchResult(
-        success=True,
-        new_model="gpt-5.5",
-        target_provider="openai-codex",
-        provider_changed=True,
-        api_key="",
-        base_url="https://chatgpt.com/backend-api/codex",
-        api_mode="codex_responses",
-        warning_message="",
-        provider_label="ChatGPT Codex",
-        resolved_via_alias=False,
-        capabilities=None,
-        model_info=_FakeModelInfo(),  # models.dev says 1.05M
-        is_global=False,
-    )
-    with patch(
-        "agent.model_metadata.get_model_context_length",
-        return_value=272_000,
-    ):
-        lines = _run_display(monkeypatch, result)
-
-    ctx_line = next((l for l in lines if "Context:" in l), "")
-    assert "272,000" in ctx_line, (
-        f"picker-path display must show Codex's 272K cap, got: {ctx_line!r}"
-    )
-    assert "1,050,000" not in ctx_line, (
-        f"picker-path display leaked models.dev's 1.05M for Codex: {ctx_line!r}"
-    )
-
-
-def test_picker_path_shows_vendor_value_when_no_provider_cap(monkeypatch):
-    """On providers with no enforced cap (e.g. OpenRouter), the picker path
-    should surface the real 1.05M context for gpt-5.5 — resolver and models.dev
-    agree here.
-    """
-    result = ModelSwitchResult(
-        success=True,
-        new_model="openai/gpt-5.5",
-        target_provider="openrouter",
-        provider_changed=True,
-        api_key="",
-        base_url="https://openrouter.ai/api/v1",
-        api_mode="chat_completions",
-        warning_message="",
-        provider_label="OpenRouter",
-        resolved_via_alias=False,
-        capabilities=None,
-        model_info=_FakeModelInfo(),
-        is_global=False,
-    )
-    with patch(
-        "agent.model_metadata.get_model_context_length",
-        return_value=1_050_000,
-    ):
-        lines = _run_display(monkeypatch, result)
-
-    ctx_line = next((l for l in lines if "Context:" in l), "")
-    assert "1,050,000" in ctx_line, (
-        f"OpenRouter gpt-5.5 should show 1.05M context, got: {ctx_line!r}"
-    )
-
-
-def test_picker_path_falls_back_to_model_info_when_resolver_empty(monkeypatch):
-    """If ``get_model_context_length`` returns nothing (rare — truly unknown
-    endpoint), the display still surfaces ``ModelInfo.context_window`` so the
-    user sees *something* rather than a silent blank.
-    """
-    result = ModelSwitchResult(
-        success=True,
-        new_model="some-model",
-        target_provider="some-provider",
-        provider_changed=True,
-        api_key="",
-        base_url="",
-        api_mode="chat_completions",
-        warning_message="",
-        provider_label="Some Provider",
-        resolved_via_alias=False,
-        capabilities=None,
-        model_info=_FakeModelInfo(),  # context_window = 1_050_000
-        is_global=False,
-    )
-    with patch(
-        "agent.model_metadata.get_model_context_length",
-        return_value=None,
-    ):
-        lines = _run_display(monkeypatch, result)
-
-    ctx_line = next((l for l in lines if "Context:" in l), "")
-    assert "1,050,000" in ctx_line, (
-        f"resolver-empty path should fall back to ModelInfo, got: {ctx_line!r}"
-    )

tests/hermes_cli/test_azure_detect.py

@@ -1,237 +0,0 @@
-"""Tests for hermes_cli.azure_detect — transport & model auto-detection."""
-
-from __future__ import annotations
-
-import json
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from hermes_cli import azure_detect
-
-
-# ----------------------------------------------------------------------
-# Helpers
-# ----------------------------------------------------------------------
-
-class _FakeHTTPResponse:
-    """Minimal stand-in for urllib.request.urlopen's context manager."""
-
-    def __init__(self, status: int, body: bytes):
-        self.status = status
-        self._body = body
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc, tb):
-        return False
-
-    def read(self) -> bytes:
-        return self._body
-
-
-def _openai_models_body(*ids: str) -> bytes:
-    return json.dumps({
-        "object": "list",
-        "data": [{"id": i, "object": "model"} for i in ids],
-    }).encode()
-
-
-def _anthropic_error_body(msg: str = "model not found") -> bytes:
-    return json.dumps({
-        "type": "error",
-        "error": {"type": "invalid_request_error", "message": msg},
-    }).encode()
-
-
-# ----------------------------------------------------------------------
-# _looks_like_anthropic_path
-# ----------------------------------------------------------------------
-
-@pytest.mark.parametrize("url, expected", [
-    ("https://foo.services.ai.azure.com/anthropic", True),
-    ("https://foo.services.ai.azure.com/anthropic/", True),
-    ("https://foo.services.ai.azure.com/anthropic/v1", True),
-    ("https://foo.openai.azure.com/openai/v1", False),
-    ("https://foo.openai.azure.com/", False),
-    ("https://openrouter.ai/api/v1", False),
-])
-def test_looks_like_anthropic_path(url, expected):
-    assert azure_detect._looks_like_anthropic_path(url) is expected
-
-
-# ----------------------------------------------------------------------
-# _extract_model_ids
-# ----------------------------------------------------------------------
-
-def test_extract_model_ids_openai_shape():
-    body = {
-        "object": "list",
-        "data": [
-            {"id": "gpt-4.1-mini", "object": "model"},
-            {"id": "claude-sonnet-4-6", "object": "model"},
-        ],
-    }
-    assert azure_detect._extract_model_ids(body) == ["gpt-4.1-mini", "claude-sonnet-4-6"]
-
-
-def test_extract_model_ids_bad_shape_returns_empty():
-    assert azure_detect._extract_model_ids({}) == []
-    assert azure_detect._extract_model_ids({"data": "not-a-list"}) == []
-    assert azure_detect._extract_model_ids({"data": [{"no-id": True}]}) == []
-
-
-# ----------------------------------------------------------------------
-# detect() integration
-# ----------------------------------------------------------------------
-
-def test_detect_anthropic_path_wins_without_http():
-    """URL path sniff short-circuits — no HTTP call happens."""
-    with patch.object(azure_detect, "_http_get_json") as fake_get, \
-         patch.object(azure_detect, "_probe_anthropic_messages") as fake_probe:
-        result = azure_detect.detect(
-            "https://foo.services.ai.azure.com/anthropic", "key-abc",
-        )
-        assert result.api_mode == "anthropic_messages"
-        assert result.is_anthropic is True
-        assert "path" in result.reason.lower()
-        fake_get.assert_not_called()
-        fake_probe.assert_not_called()
-
-
-def test_detect_openai_models_probe_success():
-    """/models probe returning a model list → chat_completions."""
-    def _fake_get(url, api_key, timeout=6.0):
-        assert "key-abc" == api_key
-        return 200, json.loads(_openai_models_body("gpt-5.4", "claude-opus-4-6"))
-
-    with patch.object(azure_detect, "_http_get_json", side_effect=_fake_get):
-        result = azure_detect.detect(
-            "https://my.openai.azure.com/openai/v1", "key-abc",
-        )
-    assert result.api_mode == "chat_completions"
-    assert result.models_probe_ok is True
-    assert result.models == ["gpt-5.4", "claude-opus-4-6"]
-    assert "/models" in result.reason
-
-
-def test_detect_openai_models_probe_empty_list_still_counts():
-    """Endpoint returned OpenAI shape but no models → still chat_completions."""
-    def _fake_get(url, api_key, timeout=6.0):
-        return 200, {"object": "list", "data": []}
-
-    with patch.object(azure_detect, "_http_get_json", side_effect=_fake_get):
-        result = azure_detect.detect(
-            "https://my.openai.azure.com/openai/v1", "key-abc",
-        )
-    assert result.api_mode == "chat_completions"
-    assert result.models == []
-    assert result.models_probe_ok is True
-
-
-def test_detect_falls_back_to_anthropic_probe():
-    """/models fails but Anthropic Messages probe succeeds."""
-    def _fake_get(url, api_key, timeout=6.0):
-        return 401, None  # /models forbidden
-
-    with patch.object(azure_detect, "_http_get_json", side_effect=_fake_get), \
-         patch.object(azure_detect, "_probe_anthropic_messages", return_value=True):
-        result = azure_detect.detect(
-            "https://my.services.ai.azure.com/v1", "key-abc",
-        )
-    assert result.api_mode == "anthropic_messages"
-    assert result.is_anthropic is True
-
-
-def test_detect_all_probes_fail_returns_none():
-    """Every probe fails → api_mode is None and caller falls back to manual."""
-    with patch.object(azure_detect, "_http_get_json", return_value=(500, None)), \
-         patch.object(azure_detect, "_probe_anthropic_messages", return_value=False):
-        result = azure_detect.detect(
-            "https://some-private.example.com/", "key-abc",
-        )
-    assert result.api_mode is None
-    assert result.models == []
-    assert "manual" in result.reason.lower()
-
-
-# ----------------------------------------------------------------------
-# _probe_openai_models URL list (Azure vs v1 api-version)
-# ----------------------------------------------------------------------
-
-def test_probe_openai_models_tries_multiple_api_versions():
-    """First call (no api-version) fails, api-version fallback succeeds."""
-    calls = []
-
-    def _fake_get(url, api_key, timeout=6.0):
-        calls.append(url)
-        if "api-version" not in url:
-            return 404, None
-        return 200, json.loads(_openai_models_body("gpt-4.1"))
-
-    with patch.object(azure_detect, "_http_get_json", side_effect=_fake_get):
-        ok, models = azure_detect._probe_openai_models(
-            "https://my.openai.azure.com/openai/v1", "k",
-        )
-    assert ok is True
-    assert models == ["gpt-4.1"]
-    # Should have tried without api-version first, then with at least one
-    assert any("api-version" not in u for u in calls)
-    assert any("api-version" in u for u in calls)
-
-
-# ----------------------------------------------------------------------
-# _http_get_json error handling
-# ----------------------------------------------------------------------
-
-def test_http_get_json_on_urlerror_returns_zero_none():
-    """Network failure returns (0, None), never raises."""
-    import urllib.error
-    with patch("hermes_cli.azure_detect.urllib_request.urlopen",
-               side_effect=urllib.error.URLError("dns fail")):
-        status, body = azure_detect._http_get_json("https://bad.example/", "k")
-    assert status == 0
-    assert body is None
-
-
-def test_http_get_json_on_http_error_returns_code_none():
-    """HTTP 4xx/5xx returns (code, None)."""
-    import urllib.error
-    err = urllib.error.HTTPError("https://x/", 403, "Forbidden", {}, None)
-    with patch("hermes_cli.azure_detect.urllib_request.urlopen", side_effect=err):
-        status, body = azure_detect._http_get_json("https://x/", "k")
-    assert status == 403
-    assert body is None
-
-
-# ----------------------------------------------------------------------
-# lookup_context_length
-# ----------------------------------------------------------------------
-
-def test_lookup_context_length_returns_known():
-    """When model_metadata returns a non-fallback value, we pass it through."""
-    fake = MagicMock(return_value=400000)
-    with patch("agent.model_metadata.get_model_context_length", fake), \
-         patch("agent.model_metadata.DEFAULT_FALLBACK_CONTEXT", 128000):
-        n = azure_detect.lookup_context_length(
-            "gpt-5.4", "https://x.openai.azure.com/openai/v1", "k",
-        )
-    assert n == 400000
-
-
-def test_lookup_context_length_returns_none_on_fallback():
-    """When resolver falls through to DEFAULT_FALLBACK_CONTEXT, we return None."""
-    with patch("agent.model_metadata.get_model_context_length", return_value=128000), \
-         patch("agent.model_metadata.DEFAULT_FALLBACK_CONTEXT", 128000):
-        n = azure_detect.lookup_context_length(
-            "totally-unknown-model", "https://x.openai.azure.com/openai/v1", "k",
-        )
-    assert n is None
-
-
-def test_lookup_context_length_swallows_exceptions():
-    """Resolver raising must not crash the wizard."""
-    with patch("agent.model_metadata.get_model_context_length",
-               side_effect=RuntimeError("boom")):
-        assert azure_detect.lookup_context_length("m", "https://x/", "k") is None

tests/hermes_cli/test_custom_provider_context_length.py

@@ -1,240 +0,0 @@
-"""Regression tests for custom_providers per-model context_length resolution.
-
-Covers the fix for #15779 — mid-session /model switch to a named custom
-provider must honor ``custom_providers[].models.<id>.context_length`` the
-same way startup already does.
-"""
-from __future__ import annotations
-
-from unittest.mock import patch
-
-from hermes_cli.config import get_custom_provider_context_length
-
-
-class TestGetCustomProviderContextLength:
-    def test_returns_override_for_matching_entry(self):
-        custom = [
-            {
-                "name": "my-endpoint",
-                "base_url": "https://example.invalid/v1",
-                "models": {"gpt-5.5": {"context_length": 1_050_000}},
-            }
-        ]
-        assert (
-            get_custom_provider_context_length(
-                "gpt-5.5", "https://example.invalid/v1", custom
-            )
-            == 1_050_000
-        )
-
-    def test_trailing_slash_insensitive(self):
-        custom = [
-            {
-                "base_url": "https://example.invalid/v1/",
-                "models": {"m": {"context_length": 500_000}},
-            }
-        ]
-        # config has trailing slash, runtime doesn't — must match
-        assert (
-            get_custom_provider_context_length(
-                "m", "https://example.invalid/v1", custom
-            )
-            == 500_000
-        )
-        # and the reverse
-        custom2 = [
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"m": {"context_length": 500_000}},
-            }
-        ]
-        assert (
-            get_custom_provider_context_length(
-                "m", "https://example.invalid/v1/", custom2
-            )
-            == 500_000
-        )
-
-    def test_returns_none_when_url_does_not_match(self):
-        custom = [
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"m": {"context_length": 400_000}},
-            }
-        ]
-        assert (
-            get_custom_provider_context_length(
-                "m", "https://other.invalid/v1", custom
-            )
-            is None
-        )
-
-    def test_returns_none_when_model_does_not_match(self):
-        custom = [
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"gpt-5.5": {"context_length": 400_000}},
-            }
-        ]
-        assert (
-            get_custom_provider_context_length(
-                "different-model", "https://example.invalid/v1", custom
-            )
-            is None
-        )
-
-    def test_returns_none_for_string_value(self):
-        """'256K' string is not a valid int — skip silently.
-
-        (The inline startup path still emits a user-visible warning; the
-        helper itself returns None so downstream fallbacks can run.)
-        """
-        custom = [
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"m": {"context_length": "256K"}},
-            }
-        ]
-        assert (
-            get_custom_provider_context_length(
-                "m", "https://example.invalid/v1", custom
-            )
-            is None
-        )
-
-    def test_returns_none_for_zero_or_negative(self):
-        for bad in (0, -1, -100):
-            custom = [
-                {
-                    "base_url": "https://example.invalid/v1",
-                    "models": {"m": {"context_length": bad}},
-                }
-            ]
-            assert (
-                get_custom_provider_context_length(
-                    "m", "https://example.invalid/v1", custom
-                )
-                is None
-            ), f"value {bad!r} should be rejected"
-
-    def test_empty_inputs_return_none(self):
-        assert get_custom_provider_context_length("", "http://x", [{"base_url": "http://x", "models": {"": {"context_length": 1}}}]) is None
-        assert get_custom_provider_context_length("m", "", [{"base_url": "", "models": {"m": {"context_length": 1}}}]) is None
-        assert get_custom_provider_context_length("m", "http://x", None) is None
-        assert get_custom_provider_context_length("m", "http://x", []) is None
-
-    def test_ignores_non_dict_entries(self):
-        """Malformed entries must not crash the lookup."""
-        custom = [
-            "not a dict",
-            None,
-            {"base_url": "https://example.invalid/v1", "models": "not a dict"},
-            {"base_url": "https://example.invalid/v1", "models": {"m": "not a dict"}},
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"m": {"context_length": 400_000}},
-            },
-        ]
-        assert (
-            get_custom_provider_context_length(
-                "m", "https://example.invalid/v1", custom
-            )
-            == 400_000
-        )
-
-
-class TestGetModelContextLengthHonorsOverride:
-    """agent.model_metadata.get_model_context_length must honor the
-    custom_providers override at step 0b — before any probe, cache hit,
-    or models.dev lookup can override it.
-    """
-
-    def _mock_all_probes(self):
-        """Context manager that disables every downstream resolution step."""
-        from agent import model_metadata as _mm
-        return [
-            patch.object(_mm, "get_cached_context_length", return_value=None),
-            patch.object(_mm, "fetch_endpoint_model_metadata", return_value={}),
-            patch.object(_mm, "fetch_model_metadata", return_value={}),
-            patch.object(_mm, "is_local_endpoint", return_value=False),
-            patch.object(_mm, "_is_known_provider_base_url", return_value=False),
-        ]
-
-    def test_custom_providers_override_wins_over_default_fallback(self):
-        from agent.model_metadata import get_model_context_length
-        custom = [
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"gpt-5.5": {"context_length": 1_050_000}},
-            }
-        ]
-        patches = self._mock_all_probes()
-        for p in patches:
-            p.start()
-        try:
-            ctx = get_model_context_length(
-                "gpt-5.5",
-                base_url="https://example.invalid/v1",
-                provider="custom",
-                custom_providers=custom,
-            )
-        finally:
-            for p in patches:
-                p.stop()
-        assert ctx == 1_050_000
-
-    def test_explicit_config_context_length_still_wins(self):
-        """Top-level model.context_length (step 0) outranks custom_providers (step 0b).
-
-        Users who set both should see the top-level value — that's the
-        documented precedence and matches the long-standing step-0 behavior.
-        """
-        from agent.model_metadata import get_model_context_length
-        custom = [
-            {
-                "base_url": "https://example.invalid/v1",
-                "models": {"m": {"context_length": 1_050_000}},
-            }
-        ]
-        ctx = get_model_context_length(
-            "m",
-            base_url="https://example.invalid/v1",
-            provider="custom",
-            config_context_length=500_000,  # explicit top-level wins
-            custom_providers=custom,
-        )
-        assert ctx == 500_000
-
-    def test_no_override_falls_through_to_default(self):
-        """With custom_providers=None and all probes disabled, resolver
-        returns DEFAULT_FALLBACK_CONTEXT (256K after the stepdown bump).
-        """
-        from agent.model_metadata import get_model_context_length, DEFAULT_FALLBACK_CONTEXT
-        patches = self._mock_all_probes()
-        for p in patches:
-            p.start()
-        try:
-            ctx = get_model_context_length(
-                "unknown-model",
-                base_url="https://example.invalid/v1",
-                provider="custom",
-                custom_providers=None,
-            )
-        finally:
-            for p in patches:
-                p.stop()
-        assert ctx == DEFAULT_FALLBACK_CONTEXT
-
-
-class TestContextProbeTiers:
-    def test_256k_is_top_tier_and_default(self):
-        """The stepdown probe starts at 256K and 256K is the new default."""
-        from agent.model_metadata import CONTEXT_PROBE_TIERS, DEFAULT_FALLBACK_CONTEXT
-
-        assert CONTEXT_PROBE_TIERS[0] == 256_000
-        assert DEFAULT_FALLBACK_CONTEXT == 256_000
-        # Tiers still descend monotonically
-        for a, b in zip(CONTEXT_PROBE_TIERS, CONTEXT_PROBE_TIERS[1:]):
-            assert a > b, f"tiers must strictly descend, got {a} then {b}"
-        # 128K is still a tier (users relying on it probe-down get there)
-        assert 128_000 in CONTEXT_PROBE_TIERS

tests/hermes_cli/test_custom_provider_model_switch.py

@@ -52,12 +52,7 @@ class TestCustomProviderModelSwitch:
             _model_flow_named_custom({}, provider_info)
 
         # fetch_api_models MUST be called even though model was saved
-        mock_fetch.assert_called_once_with(
-            "sk-test",
-            "https://vllm.example.com/v1",
-            timeout=8.0,
-            api_mode=None,
-        )
+        mock_fetch.assert_called_once_with("sk-test", "https://vllm.example.com/v1", timeout=8.0)
 
     def test_can_switch_to_different_model(self, config_home):
         """User selects a different model than the saved one."""
@@ -178,147 +173,3 @@ class TestCustomProviderModelSwitch:
         model = config.get("model")
         assert isinstance(model, dict)
         assert "api_mode" not in model, "Stale api_mode should be removed"
-
-    def test_env_template_api_key_is_preserved_in_model_config(self, config_home, monkeypatch):
-        """Selecting an env-backed custom provider must not inline the secret."""
-        import yaml
-        from hermes_cli.main import _model_flow_named_custom
-
-        config_path = config_home / "config.yaml"
-        config_path.write_text(
-            "model:\n"
-            "  default: old-model\n"
-            "  provider: openrouter\n"
-            "custom_providers:\n"
-            "- name: Example Provider\n"
-            "  base_url: https://api.example-provider.test/v1\n"
-            "  api_key: ${EXAMPLE_PROVIDER_API_KEY}\n"
-            "  model: qwen3.6-35b-fast\n"
-        )
-        monkeypatch.setenv("EXAMPLE_PROVIDER_API_KEY", "sk-live-example-provider")
-
-        provider_info = {
-            "name": "Example Provider",
-            "base_url": "https://api.example-provider.test/v1",
-            "api_key": "sk-live-example-provider",
-            "api_key_ref": "${EXAMPLE_PROVIDER_API_KEY}",
-            "model": "qwen3.6-35b-fast",
-        }
-
-        with patch("hermes_cli.models.fetch_api_models", return_value=["qwen3.6-35b-fast"]) as mock_fetch, \
-             patch.dict("sys.modules", {"simple_term_menu": None}), \
-             patch("builtins.input", return_value="1"), \
-             patch("builtins.print"):
-            _model_flow_named_custom({}, provider_info)
-
-        mock_fetch.assert_called_once_with(
-            "sk-live-example-provider",
-            "https://api.example-provider.test/v1",
-            timeout=8.0,
-            api_mode=None,
-        )
-        config = yaml.safe_load(config_path.read_text()) or {}
-        assert config["model"]["api_key"] == "${EXAMPLE_PROVIDER_API_KEY}"
-        assert config["custom_providers"][0]["api_key"] == "${EXAMPLE_PROVIDER_API_KEY}"
-        assert "sk-live-example-provider" not in config_path.read_text()
-
-    def test_key_env_custom_provider_persists_reference_not_secret(self, config_home, monkeypatch):
-        """key_env custom providers should also avoid writing plaintext keys."""
-        import yaml
-        from hermes_cli.main import _model_flow_named_custom
-
-        config_path = config_home / "config.yaml"
-        config_path.write_text(
-            "model:\n"
-            "  default: old-model\n"
-            "custom_providers:\n"
-            "- name: Example Provider\n"
-            "  base_url: https://api.example-provider.test/v1\n"
-            "  key_env: EXAMPLE_PROVIDER_API_KEY\n"
-            "  model: qwen3.6-35b-fast\n"
-        )
-        monkeypatch.setenv("EXAMPLE_PROVIDER_API_KEY", "sk-live-example-provider")
-
-        provider_info = {
-            "name": "Example Provider",
-            "base_url": "https://api.example-provider.test/v1",
-            "api_key": "",
-            "key_env": "EXAMPLE_PROVIDER_API_KEY",
-            "model": "qwen3.6-35b-fast",
-        }
-
-        with patch("hermes_cli.models.fetch_api_models", return_value=["qwen3.6-35b-fast"]), \
-             patch.dict("sys.modules", {"simple_term_menu": None}), \
-             patch("builtins.input", return_value="1"), \
-             patch("builtins.print"):
-            _model_flow_named_custom({}, provider_info)
-
-        config = yaml.safe_load(config_path.read_text()) or {}
-        assert config["model"]["api_key"] == "${EXAMPLE_PROVIDER_API_KEY}"
-        assert config["custom_providers"][0]["key_env"] == "EXAMPLE_PROVIDER_API_KEY"
-        assert "sk-live-example-provider" not in config_path.read_text()
-
-    def test_env_ref_base_url_preserves_api_key_ref_through_picker(
-        self, config_home, monkeypatch
-    ):
-        """Integration regression: when BOTH ``base_url`` and ``api_key`` use
-        ``${VAR}`` templates (the Discord-reported NeuralWatt case), the picker
-        must still preserve the env reference in ``model.api_key``.
-
-        The earlier lookup went through ``get_compatible_custom_providers``
-        which dropped entries whose ``base_url`` was an env-ref template
-        (``urlparse("${NEURALWATT_API_BASE}")`` has no scheme/netloc), causing
-        ``api_key_ref`` to stay empty and the resolved secret to be written to
-        ``config.yaml``. This test drives the real picker-callsite code path.
-        """
-        import yaml
-        from hermes_cli.main import select_provider_and_model
-
-        config_path = config_home / "config.yaml"
-        config_path.write_text(
-            "model:\n"
-            "  default: old-model\n"
-            "  provider: openrouter\n"
-            "custom_providers:\n"
-            "- name: NeuralWatt\n"
-            "  base_url: ${NEURALWATT_API_BASE}\n"
-            "  api_key: ${NEURALWATT_API_KEY}\n"
-            "  model: qwen3.6-35b-fast\n"
-            "  models: []\n"
-        )
-        monkeypatch.setenv("NEURALWATT_API_BASE", "https://api.neuralwatt.com/v1")
-        monkeypatch.setenv("NEURALWATT_API_KEY", "sk-live-neuralwatt-secret")
-
-        # Exercise the real picker: select "custom:neuralwatt" from the
-        # provider menu. ``select_provider_and_model`` prompts for a provider
-        # choice (returns an index), then hands off to
-        # ``_model_flow_named_custom`` with the provider_info built by
-        # ``_named_custom_provider_map``.
-        def _pick_neuralwatt(labels, default=0):
-            for i, label in enumerate(labels):
-                if "NeuralWatt" in label:
-                    return i
-            raise AssertionError(
-                f"NeuralWatt entry missing from provider menu: {labels}"
-            )
-
-        with patch("hermes_cli.main._prompt_provider_choice",
-                   side_effect=_pick_neuralwatt), \
-             patch("hermes_cli.models.fetch_api_models",
-                   return_value=["qwen3.6-35b-fast"]) as mock_fetch, \
-             patch.dict("sys.modules", {"simple_term_menu": None}), \
-             patch("builtins.input", return_value="1"), \
-             patch("builtins.print"):
-            select_provider_and_model()
-
-        # The live probe must still use the resolved secret.
-        mock_fetch.assert_called_once()
-        probe_args, probe_kwargs = mock_fetch.call_args
-        assert probe_args[0] == "sk-live-neuralwatt-secret"
-
-        # But config.yaml must keep the env reference, not the plaintext secret.
-        saved = config_path.read_text()
-        config = yaml.safe_load(saved) or {}
-        assert config["model"]["api_key"] == "${NEURALWATT_API_KEY}"
-        assert config["custom_providers"][0]["api_key"] == "${NEURALWATT_API_KEY}"
-        assert "sk-live-neuralwatt-secret" not in saved

tests/hermes_cli/test_doctor.py

@@ -308,43 +308,6 @@ def test_run_doctor_accepts_named_provider_from_providers_section(monkeypatch, t
     assert "model.provider 'volcengine-plan' is not a recognised provider" not in out
 
 
-def test_run_doctor_accepts_bare_custom_provider(monkeypatch, tmp_path):
-    home = tmp_path / ".hermes"
-    home.mkdir(parents=True, exist_ok=True)
-    (home / "config.yaml").write_text(
-        "model:\n"
-        "  provider: custom\n"
-        "  default: local-model\n"
-        "  base_url: http://localhost:8000/v1\n",
-        encoding="utf-8",
-    )
-
-    monkeypatch.setattr(doctor_mod, "HERMES_HOME", home)
-    monkeypatch.setattr(doctor_mod, "PROJECT_ROOT", tmp_path / "project")
-    monkeypatch.setattr(doctor_mod, "_DHH", str(home))
-    (tmp_path / "project").mkdir(exist_ok=True)
-
-    fake_model_tools = types.SimpleNamespace(
-        check_tool_availability=lambda *a, **kw: ([], []),
-        TOOLSET_REQUIREMENTS={},
-    )
-    monkeypatch.setitem(sys.modules, "model_tools", fake_model_tools)
-
-    try:
-        from hermes_cli import auth as _auth_mod
-        monkeypatch.setattr(_auth_mod, "get_nous_auth_status", lambda: {})
-        monkeypatch.setattr(_auth_mod, "get_codex_auth_status", lambda: {})
-    except Exception:
-        pass
-
-    buf = io.StringIO()
-    with contextlib.redirect_stdout(buf):
-        doctor_mod.run_doctor(Namespace(fix=False))
-
-    out = buf.getvalue()
-    assert "model.provider 'custom' is not a recognised provider" not in out
-
-
 def test_run_doctor_termux_does_not_mark_browser_available_without_agent_browser(monkeypatch, tmp_path):
     home = tmp_path / ".hermes"
     home.mkdir(parents=True, exist_ok=True)

tests/hermes_cli/test_fallback_cmd.py

@@ -1,486 +0,0 @@
-"""Tests for `hermes fallback` — chain reading, add/remove/clear, legacy migration."""
-from __future__ import annotations
-
-import io
-import types
-from pathlib import Path
-from unittest.mock import patch
-
-import pytest
-import yaml
-
-
-# ---------------------------------------------------------------------------
-# Shared fixture — isolate HERMES_HOME so save_config writes to tmp_path
-# ---------------------------------------------------------------------------
-
-@pytest.fixture()
-def isolated_home(tmp_path, monkeypatch):
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    home = tmp_path / ".hermes"
-    home.mkdir(exist_ok=True)
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    return tmp_path
-
-
-def _write_config(home: Path, data: dict) -> None:
-    config_path = home / ".hermes" / "config.yaml"
-    config_path.write_text(yaml.safe_dump(data), encoding="utf-8")
-
-
-def _read_config(home: Path) -> dict:
-    config_path = home / ".hermes" / "config.yaml"
-    return yaml.safe_load(config_path.read_text(encoding="utf-8")) or {}
-
-
-# ---------------------------------------------------------------------------
-# _read_chain / _write_chain
-# ---------------------------------------------------------------------------
-
-class TestReadChain:
-    def test_returns_empty_list_when_unset(self):
-        from hermes_cli.fallback_cmd import _read_chain
-        assert _read_chain({}) == []
-
-    def test_reads_new_list_format(self):
-        from hermes_cli.fallback_cmd import _read_chain
-        cfg = {
-            "fallback_providers": [
-                {"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
-                {"provider": "nous", "model": "Hermes-4-Llama-3.1-405B"},
-            ]
-        }
-        assert _read_chain(cfg) == [
-            {"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
-            {"provider": "nous", "model": "Hermes-4-Llama-3.1-405B"},
-        ]
-
-    def test_migrates_legacy_single_dict(self):
-        from hermes_cli.fallback_cmd import _read_chain
-        cfg = {"fallback_model": {"provider": "openrouter", "model": "gpt-5.4"}}
-        assert _read_chain(cfg) == [{"provider": "openrouter", "model": "gpt-5.4"}]
-
-    def test_skips_incomplete_entries(self):
-        from hermes_cli.fallback_cmd import _read_chain
-        cfg = {
-            "fallback_providers": [
-                {"provider": "openrouter"},            # missing model
-                {"model": "gpt-5.4"},                  # missing provider
-                {"provider": "nous", "model": "foo"},  # valid
-                "not-a-dict",                          # noise
-            ]
-        }
-        assert _read_chain(cfg) == [{"provider": "nous", "model": "foo"}]
-
-    def test_returns_copies_not_aliases(self):
-        from hermes_cli.fallback_cmd import _read_chain
-        cfg = {"fallback_providers": [{"provider": "nous", "model": "foo"}]}
-        result = _read_chain(cfg)
-        result[0]["provider"] = "mutated"
-        assert cfg["fallback_providers"][0]["provider"] == "nous"
-
-
-# ---------------------------------------------------------------------------
-# _extract_fallback_from_model_cfg
-# ---------------------------------------------------------------------------
-
-class TestExtractFallback:
-    def test_extracts_from_default_field(self):
-        from hermes_cli.fallback_cmd import _extract_fallback_from_model_cfg
-        model_cfg = {"provider": "openrouter", "default": "anthropic/claude-sonnet-4.6"}
-        assert _extract_fallback_from_model_cfg(model_cfg) == {
-            "provider": "openrouter",
-            "model": "anthropic/claude-sonnet-4.6",
-        }
-
-    def test_extracts_optional_base_url_and_api_mode(self):
-        from hermes_cli.fallback_cmd import _extract_fallback_from_model_cfg
-        model_cfg = {
-            "provider": "custom",
-            "default": "local-model",
-            "base_url": "http://localhost:11434/v1",
-            "api_mode": "chat_completions",
-        }
-        assert _extract_fallback_from_model_cfg(model_cfg) == {
-            "provider": "custom",
-            "model": "local-model",
-            "base_url": "http://localhost:11434/v1",
-            "api_mode": "chat_completions",
-        }
-
-    def test_returns_none_without_provider(self):
-        from hermes_cli.fallback_cmd import _extract_fallback_from_model_cfg
-        assert _extract_fallback_from_model_cfg({"default": "foo"}) is None
-
-    def test_returns_none_without_model(self):
-        from hermes_cli.fallback_cmd import _extract_fallback_from_model_cfg
-        assert _extract_fallback_from_model_cfg({"provider": "openrouter"}) is None
-
-    def test_returns_none_for_non_dict(self):
-        from hermes_cli.fallback_cmd import _extract_fallback_from_model_cfg
-        assert _extract_fallback_from_model_cfg("plain-string") is None
-        assert _extract_fallback_from_model_cfg(None) is None
-
-
-# ---------------------------------------------------------------------------
-# cmd_fallback_list
-# ---------------------------------------------------------------------------
-
-class TestListCommand:
-    def test_list_empty(self, isolated_home, capsys):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback_list
-        cmd_fallback_list(types.SimpleNamespace())
-        out = capsys.readouterr().out
-        assert "No fallback providers configured" in out
-        assert "hermes fallback add" in out
-
-    def test_list_with_entries(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "model": {"provider": "anthropic", "default": "claude-sonnet-4-6"},
-            "fallback_providers": [
-                {"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
-                {"provider": "nous", "model": "Hermes-4"},
-            ],
-        })
-        from hermes_cli.fallback_cmd import cmd_fallback_list
-        cmd_fallback_list(types.SimpleNamespace())
-        out = capsys.readouterr().out
-        assert "Fallback chain (2 entries)" in out
-        assert "anthropic/claude-sonnet-4.6" in out
-        assert "Hermes-4" in out
-        # Primary should be shown too
-        assert "claude-sonnet-4-6" in out
-
-    def test_list_migrates_legacy_for_display(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "fallback_model": {"provider": "openrouter", "model": "gpt-5.4"},
-        })
-        from hermes_cli.fallback_cmd import cmd_fallback_list
-        cmd_fallback_list(types.SimpleNamespace())
-        out = capsys.readouterr().out
-        assert "1 entry" in out
-        assert "gpt-5.4" in out
-
-
-# ---------------------------------------------------------------------------
-# cmd_fallback_add — mock select_provider_and_model
-# ---------------------------------------------------------------------------
-
-class TestAddCommand:
-    def test_add_appends_new_entry(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "model": {"provider": "anthropic", "default": "claude-sonnet-4-6"},
-        })
-
-        def fake_picker(args=None):
-            # Simulate what the real picker does: writes the selection to config["model"]
-            from hermes_cli.config import load_config, save_config
-            cfg = load_config()
-            cfg["model"] = {
-                "provider": "openrouter",
-                "default": "anthropic/claude-sonnet-4.6",
-                "base_url": "https://openrouter.ai/api/v1",
-                "api_mode": "chat_completions",
-            }
-            save_config(cfg)
-
-        with patch("hermes_cli.main.select_provider_and_model", side_effect=fake_picker), \
-                patch("hermes_cli.main._require_tty"):
-            from hermes_cli.fallback_cmd import cmd_fallback_add
-            cmd_fallback_add(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        # Primary is preserved
-        assert cfg["model"]["provider"] == "anthropic"
-        assert cfg["model"]["default"] == "claude-sonnet-4-6"
-        # Fallback was appended
-        assert cfg["fallback_providers"] == [
-            {
-                "provider": "openrouter",
-                "model": "anthropic/claude-sonnet-4.6",
-                "base_url": "https://openrouter.ai/api/v1",
-                "api_mode": "chat_completions",
-            }
-        ]
-        out = capsys.readouterr().out
-        assert "Added fallback" in out
-
-    def test_add_rejects_duplicate(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "model": {"provider": "anthropic", "default": "claude-sonnet-4-6"},
-            "fallback_providers": [
-                {"provider": "openrouter", "model": "gpt-5.4"},
-            ],
-        })
-
-        def fake_picker(args=None):
-            from hermes_cli.config import load_config, save_config
-            cfg = load_config()
-            cfg["model"] = {"provider": "openrouter", "default": "gpt-5.4"}
-            save_config(cfg)
-
-        with patch("hermes_cli.main.select_provider_and_model", side_effect=fake_picker), \
-                patch("hermes_cli.main._require_tty"):
-            from hermes_cli.fallback_cmd import cmd_fallback_add
-            cmd_fallback_add(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        # Should still have exactly one entry
-        assert len(cfg["fallback_providers"]) == 1
-        out = capsys.readouterr().out
-        assert "already in the fallback chain" in out
-
-    def test_add_rejects_same_as_primary(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "model": {"provider": "openrouter", "default": "gpt-5.4"},
-        })
-
-        def fake_picker(args=None):
-            # User picks the same thing that's already the primary
-            from hermes_cli.config import load_config, save_config
-            cfg = load_config()
-            cfg["model"] = {"provider": "openrouter", "default": "gpt-5.4"}
-            save_config(cfg)
-
-        with patch("hermes_cli.main.select_provider_and_model", side_effect=fake_picker), \
-                patch("hermes_cli.main._require_tty"):
-            from hermes_cli.fallback_cmd import cmd_fallback_add
-            cmd_fallback_add(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        assert "fallback_providers" not in cfg or cfg["fallback_providers"] == []
-        out = capsys.readouterr().out
-        assert "matches the current primary" in out
-
-    def test_add_preserves_primary_when_picker_changes_it(self, isolated_home):
-        """The picker mutates config["model"]; fallback_add must restore the primary."""
-        _write_config(isolated_home, {
-            "model": {
-                "provider": "anthropic",
-                "default": "claude-sonnet-4-6",
-                "base_url": "https://api.anthropic.com",
-                "api_mode": "anthropic_messages",
-            },
-        })
-
-        def fake_picker(args=None):
-            from hermes_cli.config import load_config, save_config
-            cfg = load_config()
-            cfg["model"] = {
-                "provider": "openrouter",
-                "default": "anthropic/claude-sonnet-4.6",
-                "base_url": "https://openrouter.ai/api/v1",
-                "api_mode": "chat_completions",
-            }
-            save_config(cfg)
-
-        with patch("hermes_cli.main.select_provider_and_model", side_effect=fake_picker), \
-                patch("hermes_cli.main._require_tty"):
-            from hermes_cli.fallback_cmd import cmd_fallback_add
-            cmd_fallback_add(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        # Primary exactly as it was
-        assert cfg["model"]["provider"] == "anthropic"
-        assert cfg["model"]["default"] == "claude-sonnet-4-6"
-        assert cfg["model"]["base_url"] == "https://api.anthropic.com"
-        assert cfg["model"]["api_mode"] == "anthropic_messages"
-        # Fallback added
-        assert len(cfg["fallback_providers"]) == 1
-        assert cfg["fallback_providers"][0]["provider"] == "openrouter"
-
-    def test_add_noop_when_picker_cancelled(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "model": {"provider": "anthropic", "default": "claude-sonnet-4-6"},
-        })
-
-        def fake_picker(args=None):
-            # User cancelled — no change to config
-            pass
-
-        with patch("hermes_cli.main.select_provider_and_model", side_effect=fake_picker), \
-                patch("hermes_cli.main._require_tty"):
-            from hermes_cli.fallback_cmd import cmd_fallback_add
-            cmd_fallback_add(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        assert "fallback_providers" not in cfg or cfg["fallback_providers"] == []
-        out = capsys.readouterr().out
-        # Either "No fallback added" (picker fully cancelled) or "matches the current primary"
-        # (picker left config untouched) — both indicate a non-add outcome.
-        assert ("No fallback added" in out) or ("matches the current primary" in out)
-
-    def test_add_noop_when_picker_clears_model(self, isolated_home, capsys):
-        """Simulate picker explicitly clearing model.default (unusual but possible)."""
-        _write_config(isolated_home, {
-            "model": {"provider": "anthropic", "default": "claude-sonnet-4-6"},
-        })
-
-        def fake_picker(args=None):
-            from hermes_cli.config import load_config, save_config
-            cfg = load_config()
-            cfg["model"] = {"provider": "", "default": ""}
-            save_config(cfg)
-
-        with patch("hermes_cli.main.select_provider_and_model", side_effect=fake_picker), \
-                patch("hermes_cli.main._require_tty"):
-            from hermes_cli.fallback_cmd import cmd_fallback_add
-            cmd_fallback_add(types.SimpleNamespace())
-
-        out = capsys.readouterr().out
-        assert "No fallback added" in out
-
-
-# ---------------------------------------------------------------------------
-# cmd_fallback_remove
-# ---------------------------------------------------------------------------
-
-class TestRemoveCommand:
-    def test_remove_empty_chain(self, isolated_home, capsys):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback_remove
-        cmd_fallback_remove(types.SimpleNamespace())
-        out = capsys.readouterr().out
-        assert "nothing to remove" in out
-
-    def test_remove_selected_entry(self, isolated_home, capsys):
-        _write_config(isolated_home, {
-            "fallback_providers": [
-                {"provider": "openrouter", "model": "gpt-5.4"},
-                {"provider": "nous", "model": "Hermes-4"},
-                {"provider": "anthropic", "model": "claude-sonnet-4-6"},
-            ],
-        })
-
-        # Picker returns index 1 (the middle entry, "nous / Hermes-4")
-        with patch("hermes_cli.setup._curses_prompt_choice", return_value=1):
-            from hermes_cli.fallback_cmd import cmd_fallback_remove
-            cmd_fallback_remove(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        assert cfg["fallback_providers"] == [
-            {"provider": "openrouter", "model": "gpt-5.4"},
-            {"provider": "anthropic", "model": "claude-sonnet-4-6"},
-        ]
-        out = capsys.readouterr().out
-        assert "Removed fallback" in out
-        assert "Hermes-4" in out
-
-    def test_remove_cancel_keeps_chain(self, isolated_home):
-        _write_config(isolated_home, {
-            "fallback_providers": [
-                {"provider": "openrouter", "model": "gpt-5.4"},
-            ],
-        })
-
-        # Cancel = last item (index == len(chain) == 1 in our menu)
-        with patch("hermes_cli.setup._curses_prompt_choice", return_value=1):
-            from hermes_cli.fallback_cmd import cmd_fallback_remove
-            cmd_fallback_remove(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        assert len(cfg["fallback_providers"]) == 1
-
-
-# ---------------------------------------------------------------------------
-# cmd_fallback_clear
-# ---------------------------------------------------------------------------
-
-class TestClearCommand:
-    def test_clear_empty_chain(self, isolated_home, capsys):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback_clear
-        cmd_fallback_clear(types.SimpleNamespace())
-        out = capsys.readouterr().out
-        assert "nothing to clear" in out
-
-    def test_clear_with_confirmation(self, isolated_home, capsys, monkeypatch):
-        _write_config(isolated_home, {
-            "fallback_providers": [
-                {"provider": "openrouter", "model": "gpt-5.4"},
-                {"provider": "nous", "model": "Hermes-4"},
-            ],
-        })
-        monkeypatch.setattr("builtins.input", lambda *a, **kw: "y")
-        from hermes_cli.fallback_cmd import cmd_fallback_clear
-        cmd_fallback_clear(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        assert cfg.get("fallback_providers") == []
-        out = capsys.readouterr().out
-        assert "Fallback chain cleared" in out
-
-    def test_clear_cancelled(self, isolated_home, monkeypatch):
-        _write_config(isolated_home, {
-            "fallback_providers": [{"provider": "openrouter", "model": "gpt-5.4"}],
-        })
-        monkeypatch.setattr("builtins.input", lambda *a, **kw: "n")
-        from hermes_cli.fallback_cmd import cmd_fallback_clear
-        cmd_fallback_clear(types.SimpleNamespace())
-
-        cfg = _read_config(isolated_home)
-        assert len(cfg["fallback_providers"]) == 1
-
-
-# ---------------------------------------------------------------------------
-# cmd_fallback dispatcher
-# ---------------------------------------------------------------------------
-
-class TestDispatcher:
-    def test_no_subcommand_lists(self, isolated_home, capsys):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback
-        cmd_fallback(types.SimpleNamespace(fallback_command=None))
-        out = capsys.readouterr().out
-        assert "No fallback providers configured" in out
-
-    def test_list_alias(self, isolated_home, capsys):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback
-        cmd_fallback(types.SimpleNamespace(fallback_command="ls"))
-        out = capsys.readouterr().out
-        assert "No fallback providers configured" in out
-
-    def test_remove_alias(self, isolated_home, capsys):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback
-        cmd_fallback(types.SimpleNamespace(fallback_command="rm"))
-        out = capsys.readouterr().out
-        assert "nothing to remove" in out
-
-    def test_unknown_subcommand_exits(self, isolated_home):
-        _write_config(isolated_home, {})
-        from hermes_cli.fallback_cmd import cmd_fallback
-        with pytest.raises(SystemExit):
-            cmd_fallback(types.SimpleNamespace(fallback_command="nope"))
-
-
-# ---------------------------------------------------------------------------
-# argparse wiring — verify the subparser is registered
-# ---------------------------------------------------------------------------
-
-class TestArgparseWiring:
-    """Verify `hermes fallback` is wired into main.py's argparse tree.
-
-    main() builds the parser inline, so we invoke main([...]) via subprocess
-    with --help to introspect registered subcommands without side effects.
-    """
-
-    def test_fallback_help_lists_subcommands(self):
-        import subprocess
-        import sys
-        result = subprocess.run(
-            [sys.executable, "-m", "hermes_cli.main", "fallback", "--help"],
-            capture_output=True,
-            text=True,
-            timeout=30,
-        )
-        # --help exits 0
-        assert result.returncode == 0, f"stderr: {result.stderr}"
-        out = result.stdout + result.stderr
-        # All four subcommands should appear in help
-        assert "list" in out
-        assert "add" in out
-        assert "remove" in out
-        assert "clear" in out

tests/hermes_cli/test_kanban_cli.py

@@ -1,210 +0,0 @@
-"""Tests for the kanban CLI surface (hermes_cli.kanban)."""
-
-from __future__ import annotations
-
-import argparse
-import json
-import os
-from pathlib import Path
-
-import pytest
-
-from hermes_cli import kanban as kc
-from hermes_cli import kanban_db as kb
-
-
-@pytest.fixture
-def kanban_home(tmp_path, monkeypatch):
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    kb.init_db()
-    return home
-
-
-# ---------------------------------------------------------------------------
-# Workspace flag parsing
-# ---------------------------------------------------------------------------
-
-@pytest.mark.parametrize(
-    "value,expected",
-    [
-        ("scratch",              ("scratch", None)),
-        ("worktree",              ("worktree", None)),
-        ("dir:/tmp/work",         ("dir", "/tmp/work")),
-    ],
-)
-def test_parse_workspace_flag_valid(value, expected):
-    assert kc._parse_workspace_flag(value) == expected
-
-
-def test_parse_workspace_flag_expands_user():
-    kind, path = kc._parse_workspace_flag("dir:~/vault")
-    assert kind == "dir"
-    assert path.endswith("/vault")
-    assert not path.startswith("~")
-
-
-@pytest.mark.parametrize("bad", ["cloud", "dir:", "", "worktree:/x"])
-def test_parse_workspace_flag_rejects(bad):
-    if not bad:
-        # Empty -> defaults; not an error.
-        assert kc._parse_workspace_flag(bad) == ("scratch", None)
-        return
-    with pytest.raises(argparse.ArgumentTypeError):
-        kc._parse_workspace_flag(bad)
-
-
-# ---------------------------------------------------------------------------
-# run_slash smoke tests (end-to-end via the same entry both CLI and gateway use)
-# ---------------------------------------------------------------------------
-
-def test_run_slash_no_args_shows_usage(kanban_home):
-    out = kc.run_slash("")
-    assert "kanban" in out.lower()
-    assert "create" in out.lower() or "subcommand" in out.lower() or "action" in out.lower()
-
-
-def test_run_slash_create_and_list(kanban_home):
-    out = kc.run_slash("create 'ship feature' --assignee alice")
-    assert "Created" in out
-    out = kc.run_slash("list")
-    assert "ship feature" in out
-    assert "alice" in out
-
-
-def test_run_slash_create_with_parent_and_cascade(kanban_home):
-    # Parent then child via --parent
-    out1 = kc.run_slash("create 'parent' --assignee alice")
-    # Extract the "t_xxxx" id from "Created t_xxxx (ready, ...)"
-    import re
-    m = re.search(r"(t_[a-f0-9]+)", out1)
-    assert m
-    p = m.group(1)
-    out2 = kc.run_slash(f"create 'child' --assignee bob --parent {p}")
-    assert "todo" in out2  # child starts as todo
-
-    # Complete parent; list should promote child to ready
-    kc.run_slash(f"complete {p}")
-    # Explicit filter: child should now be ready (was todo before complete).
-    ready_list = kc.run_slash("list --status ready")
-    assert "child" in ready_list
-
-
-def test_run_slash_show_includes_comments(kanban_home):
-    out = kc.run_slash("create 'x'")
-    import re
-    tid = re.search(r"(t_[a-f0-9]+)", out).group(1)
-    kc.run_slash(f"comment {tid} 'source is paywalled'")
-    show = kc.run_slash(f"show {tid}")
-    assert "source is paywalled" in show
-
-
-def test_run_slash_block_unblock_cycle(kanban_home):
-    out = kc.run_slash("create 'x' --assignee alice")
-    import re
-    tid = re.search(r"(t_[a-f0-9]+)", out).group(1)
-    # Claim first so block() finds it running
-    kc.run_slash(f"claim {tid}")
-    assert "Blocked" in kc.run_slash(f"block {tid} 'need decision'")
-    assert "Unblocked" in kc.run_slash(f"unblock {tid}")
-
-
-def test_run_slash_json_output(kanban_home):
-    out = kc.run_slash("create 'jsontask' --assignee alice --json")
-    payload = json.loads(out)
-    assert payload["title"] == "jsontask"
-    assert payload["assignee"] == "alice"
-    assert payload["status"] == "ready"
-
-
-def test_run_slash_dispatch_dry_run_counts(kanban_home):
-    kc.run_slash("create 'a' --assignee alice")
-    kc.run_slash("create 'b' --assignee bob")
-    out = kc.run_slash("dispatch --dry-run")
-    assert "Spawned:" in out
-
-
-def test_run_slash_context_output_format(kanban_home):
-    out = kc.run_slash("create 'tech spec' --assignee alice --body 'write an RFC'")
-    import re
-    tid = re.search(r"(t_[a-f0-9]+)", out).group(1)
-    kc.run_slash(f"comment {tid} 'remember to include performance section'")
-    ctx = kc.run_slash(f"context {tid}")
-    assert "tech spec" in ctx
-    assert "write an RFC" in ctx
-    assert "performance section" in ctx
-
-
-def test_run_slash_tenant_filter(kanban_home):
-    kc.run_slash("create 'biz-a task' --tenant biz-a --assignee alice")
-    kc.run_slash("create 'biz-b task' --tenant biz-b --assignee alice")
-    a = kc.run_slash("list --tenant biz-a")
-    b = kc.run_slash("list --tenant biz-b")
-    assert "biz-a task" in a and "biz-b task" not in a
-    assert "biz-b task" in b and "biz-a task" not in b
-
-
-def test_run_slash_usage_error_returns_message(kanban_home):
-    # Missing required argument for create
-    out = kc.run_slash("create")
-    assert "usage" in out.lower() or "error" in out.lower()
-
-
-def test_run_slash_assign_reassigns(kanban_home):
-    out = kc.run_slash("create 'x' --assignee alice")
-    import re
-    tid = re.search(r"(t_[a-f0-9]+)", out).group(1)
-    assert "Assigned" in kc.run_slash(f"assign {tid} bob")
-    show = kc.run_slash(f"show {tid}")
-    assert "bob" in show
-
-
-def test_run_slash_link_unlink(kanban_home):
-    a = kc.run_slash("create 'a'")
-    b = kc.run_slash("create 'b'")
-    import re
-    ta = re.search(r"(t_[a-f0-9]+)", a).group(1)
-    tb = re.search(r"(t_[a-f0-9]+)", b).group(1)
-    assert "Linked" in kc.run_slash(f"link {ta} {tb}")
-    # After link, b is todo
-    show = kc.run_slash(f"show {tb}")
-    assert "todo" in show
-    assert "Unlinked" in kc.run_slash(f"unlink {ta} {tb}")
-
-
-# ---------------------------------------------------------------------------
-# Integration with the COMMAND_REGISTRY
-# ---------------------------------------------------------------------------
-
-def test_kanban_is_resolvable():
-    from hermes_cli.commands import resolve_command
-
-    cmd = resolve_command("kanban")
-    assert cmd is not None
-    assert cmd.name == "kanban"
-
-
-def test_kanban_bypasses_active_session_guard():
-    from hermes_cli.commands import should_bypass_active_session
-
-    assert should_bypass_active_session("kanban")
-
-
-def test_kanban_in_autocomplete_table():
-    from hermes_cli.commands import COMMANDS, SUBCOMMANDS
-
-    assert "/kanban" in COMMANDS
-    subs = SUBCOMMANDS.get("/kanban") or []
-    assert "create" in subs
-    assert "dispatch" in subs
-
-
-def test_kanban_not_gateway_only():
-    # kanban is available in BOTH CLI and gateway surfaces.
-    from hermes_cli.commands import COMMAND_REGISTRY
-
-    cmd = next(c for c in COMMAND_REGISTRY if c.name == "kanban")
-    assert not cmd.cli_only
-    assert not cmd.gateway_only

tests/hermes_cli/test_kanban_db.py

@@ -1,438 +0,0 @@
-"""Tests for the Kanban DB layer (hermes_cli.kanban_db)."""
-
-from __future__ import annotations
-
-import concurrent.futures
-import os
-import time
-from pathlib import Path
-
-import pytest
-
-from hermes_cli import kanban_db as kb
-
-
-@pytest.fixture
-def kanban_home(tmp_path, monkeypatch):
-    """Isolated HERMES_HOME with an empty kanban DB."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    kb.init_db()
-    return home
-
-
-# ---------------------------------------------------------------------------
-# Schema / init
-# ---------------------------------------------------------------------------
-
-def test_init_db_is_idempotent(kanban_home):
-    # Second call should not error or drop data.
-    with kb.connect() as conn:
-        kb.create_task(conn, title="persisted")
-    kb.init_db()
-    with kb.connect() as conn:
-        tasks = kb.list_tasks(conn)
-    assert len(tasks) == 1
-    assert tasks[0].title == "persisted"
-
-
-def test_init_creates_expected_tables(kanban_home):
-    with kb.connect() as conn:
-        rows = conn.execute(
-            "SELECT name FROM sqlite_master WHERE type='table' ORDER BY name"
-        ).fetchall()
-    names = {r["name"] for r in rows}
-    assert {"tasks", "task_links", "task_comments", "task_events"} <= names
-
-
-# ---------------------------------------------------------------------------
-# Task creation + status inference
-# ---------------------------------------------------------------------------
-
-def test_create_task_no_parents_is_ready(kanban_home):
-    with kb.connect() as conn:
-        tid = kb.create_task(conn, title="ship it", assignee="alice")
-        t = kb.get_task(conn, tid)
-    assert t is not None
-    assert t.status == "ready"
-    assert t.assignee == "alice"
-    assert t.workspace_kind == "scratch"
-
-
-def test_create_task_with_parent_is_todo_until_parent_done(kanban_home):
-    with kb.connect() as conn:
-        p = kb.create_task(conn, title="parent")
-        c = kb.create_task(conn, title="child", parents=[p])
-        assert kb.get_task(conn, c).status == "todo"
-        kb.complete_task(conn, p, result="ok")
-        assert kb.get_task(conn, c).status == "ready"
-
-
-def test_create_task_unknown_parent_errors(kanban_home):
-    with kb.connect() as conn, pytest.raises(ValueError, match="unknown parent"):
-        kb.create_task(conn, title="orphan", parents=["t_ghost"])
-
-
-def test_workspace_kind_validation(kanban_home):
-    with kb.connect() as conn, pytest.raises(ValueError, match="workspace_kind"):
-        kb.create_task(conn, title="bad ws", workspace_kind="cloud")
-
-
-# ---------------------------------------------------------------------------
-# Links + dependency resolution
-# ---------------------------------------------------------------------------
-
-def test_link_demotes_ready_child_to_todo_when_parent_not_done(kanban_home):
-    with kb.connect() as conn:
-        a = kb.create_task(conn, title="a")
-        b = kb.create_task(conn, title="b")
-        assert kb.get_task(conn, b).status == "ready"
-        kb.link_tasks(conn, a, b)
-        assert kb.get_task(conn, b).status == "todo"
-
-
-def test_link_keeps_ready_child_when_parent_already_done(kanban_home):
-    with kb.connect() as conn:
-        a = kb.create_task(conn, title="a")
-        kb.complete_task(conn, a)
-        b = kb.create_task(conn, title="b")
-        assert kb.get_task(conn, b).status == "ready"
-        kb.link_tasks(conn, a, b)
-        assert kb.get_task(conn, b).status == "ready"
-
-
-def test_link_rejects_self_loop(kanban_home):
-    with kb.connect() as conn:
-        a = kb.create_task(conn, title="a")
-        with pytest.raises(ValueError, match="itself"):
-            kb.link_tasks(conn, a, a)
-
-
-def test_link_detects_cycle(kanban_home):
-    with kb.connect() as conn:
-        a = kb.create_task(conn, title="a")
-        b = kb.create_task(conn, title="b", parents=[a])
-        c = kb.create_task(conn, title="c", parents=[b])
-        with pytest.raises(ValueError, match="cycle"):
-            kb.link_tasks(conn, c, a)
-        with pytest.raises(ValueError, match="cycle"):
-            kb.link_tasks(conn, b, a)
-
-
-def test_recompute_ready_cascades_through_chain(kanban_home):
-    with kb.connect() as conn:
-        a = kb.create_task(conn, title="a")
-        b = kb.create_task(conn, title="b", parents=[a])
-        c = kb.create_task(conn, title="c", parents=[b])
-        assert [kb.get_task(conn, x).status for x in (a, b, c)] == \
-               ["ready", "todo", "todo"]
-        kb.complete_task(conn, a)
-        assert kb.get_task(conn, b).status == "ready"
-        kb.complete_task(conn, b)
-        assert kb.get_task(conn, c).status == "ready"
-
-
-def test_recompute_ready_fan_in_waits_for_all_parents(kanban_home):
-    with kb.connect() as conn:
-        a = kb.create_task(conn, title="a")
-        b = kb.create_task(conn, title="b")
-        c = kb.create_task(conn, title="c", parents=[a, b])
-        kb.complete_task(conn, a)
-        assert kb.get_task(conn, c).status == "todo"
-        kb.complete_task(conn, b)
-        assert kb.get_task(conn, c).status == "ready"
-
-
-# ---------------------------------------------------------------------------
-# Atomic claim (CAS)
-# ---------------------------------------------------------------------------
-
-def test_claim_once_wins_second_loses(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        first = kb.claim_task(conn, t, claimer="host:1")
-        assert first is not None and first.status == "running"
-        second = kb.claim_task(conn, t, claimer="host:2")
-        assert second is None
-
-
-def test_claim_fails_on_non_ready(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x")
-        # Move to todo by introducing an unsatisfied parent.
-        p = kb.create_task(conn, title="p")
-        kb.link_tasks(conn, p, t)
-        assert kb.get_task(conn, t).status == "todo"
-        assert kb.claim_task(conn, t) is None
-
-
-def test_stale_claim_reclaimed(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        kb.claim_task(conn, t)
-        # Rewind claim_expires so it looks stale.
-        conn.execute(
-            "UPDATE tasks SET claim_expires = ? WHERE id = ?",
-            (int(time.time()) - 3600, t),
-        )
-        reclaimed = kb.release_stale_claims(conn)
-        assert reclaimed == 1
-        assert kb.get_task(conn, t).status == "ready"
-
-
-def test_heartbeat_extends_claim(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        claimer = "host:hb"
-        kb.claim_task(conn, t, claimer=claimer, ttl_seconds=60)
-        original = kb.get_task(conn, t).claim_expires
-        # Rewind then heartbeat.
-        conn.execute("UPDATE tasks SET claim_expires = ? WHERE id = ?", (0, t))
-        ok = kb.heartbeat_claim(conn, t, claimer=claimer, ttl_seconds=3600)
-        assert ok
-        new = kb.get_task(conn, t).claim_expires
-        assert new > int(time.time()) + 3000
-
-
-def test_concurrent_claims_only_one_wins(kanban_home):
-    """Fire N threads claiming the same task; exactly one must win."""
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="race", assignee="a")
-
-    def attempt(i):
-        with kb.connect() as c:
-            return kb.claim_task(c, t, claimer=f"host:{i}")
-
-    n_workers = 8
-    with concurrent.futures.ThreadPoolExecutor(max_workers=n_workers) as ex:
-        results = list(ex.map(attempt, range(n_workers)))
-    winners = [r for r in results if r is not None]
-    assert len(winners) == 1
-    assert winners[0].status == "running"
-
-
-# ---------------------------------------------------------------------------
-# Complete / block / unblock / archive / assign
-# ---------------------------------------------------------------------------
-
-def test_complete_records_result(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x")
-        assert kb.complete_task(conn, t, result="done and dusted")
-        task = kb.get_task(conn, t)
-    assert task.status == "done"
-    assert task.result == "done and dusted"
-    assert task.completed_at is not None
-
-
-def test_block_then_unblock(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        kb.claim_task(conn, t)
-        assert kb.block_task(conn, t, reason="need input")
-        assert kb.get_task(conn, t).status == "blocked"
-        assert kb.unblock_task(conn, t)
-        assert kb.get_task(conn, t).status == "ready"
-
-
-def test_assign_refuses_while_running(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        kb.claim_task(conn, t)
-        with pytest.raises(RuntimeError, match="currently running"):
-            kb.assign_task(conn, t, "b")
-
-
-def test_assign_reassigns_when_not_running(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        assert kb.assign_task(conn, t, "b")
-        assert kb.get_task(conn, t).assignee == "b"
-
-
-def test_archive_hides_from_default_list(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x")
-        kb.complete_task(conn, t)
-        assert kb.archive_task(conn, t)
-        assert len(kb.list_tasks(conn)) == 0
-        assert len(kb.list_tasks(conn, include_archived=True)) == 1
-
-
-# ---------------------------------------------------------------------------
-# Comments / events / worker context
-# ---------------------------------------------------------------------------
-
-def test_comments_recorded_in_order(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x")
-        kb.add_comment(conn, t, "user", "first")
-        kb.add_comment(conn, t, "researcher", "second")
-        comments = kb.list_comments(conn, t)
-    assert [c.body for c in comments] == ["first", "second"]
-    assert [c.author for c in comments] == ["user", "researcher"]
-
-
-def test_empty_comment_rejected(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x")
-        with pytest.raises(ValueError, match="body is required"):
-            kb.add_comment(conn, t, "user", "")
-
-
-def test_events_capture_lifecycle(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="a")
-        kb.claim_task(conn, t)
-        kb.complete_task(conn, t, result="ok")
-        events = kb.list_events(conn, t)
-    kinds = [e.kind for e in events]
-    assert "created" in kinds
-    assert "claimed" in kinds
-    assert "completed" in kinds
-
-
-def test_worker_context_includes_parent_results_and_comments(kanban_home):
-    with kb.connect() as conn:
-        p = kb.create_task(conn, title="p")
-        kb.complete_task(conn, p, result="PARENT_RESULT_MARKER")
-        c = kb.create_task(conn, title="child", parents=[p])
-        kb.add_comment(conn, c, "user", "CLARIFICATION_MARKER")
-        ctx = kb.build_worker_context(conn, c)
-    assert "PARENT_RESULT_MARKER" in ctx
-    assert "CLARIFICATION_MARKER" in ctx
-    assert c in ctx
-    assert "child" in ctx
-
-
-# ---------------------------------------------------------------------------
-# Dispatcher
-# ---------------------------------------------------------------------------
-
-def test_dispatch_dry_run_does_not_claim(kanban_home):
-    with kb.connect() as conn:
-        t1 = kb.create_task(conn, title="a", assignee="alice")
-        t2 = kb.create_task(conn, title="b", assignee="bob")
-        res = kb.dispatch_once(conn, dry_run=True)
-    assert {s[0] for s in res.spawned} == {t1, t2}
-    with kb.connect() as conn:
-        # Dry run must NOT mutate status.
-        assert kb.get_task(conn, t1).status == "ready"
-        assert kb.get_task(conn, t2).status == "ready"
-
-
-def test_dispatch_skips_unassigned(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="floater")
-        res = kb.dispatch_once(conn, dry_run=True)
-    assert t in res.skipped_unassigned
-    assert not res.spawned
-
-
-def test_dispatch_promotes_ready_and_spawns(kanban_home):
-    spawns = []
-
-    def fake_spawn(task, workspace):
-        spawns.append((task.id, task.assignee, workspace))
-
-    with kb.connect() as conn:
-        p = kb.create_task(conn, title="p", assignee="alice")
-        c = kb.create_task(conn, title="c", assignee="bob", parents=[p])
-        # Finish parent outside dispatch; promotion happens inside.
-        kb.complete_task(conn, p)
-        res = kb.dispatch_once(conn, spawn_fn=fake_spawn)
-    # Spawned c (a was already done when dispatch was called).
-    assert len(spawns) == 1
-    assert spawns[0][0] == c
-    assert spawns[0][1] == "bob"
-    # c is now running
-    with kb.connect() as conn:
-        assert kb.get_task(conn, c).status == "running"
-
-
-def test_dispatch_spawn_failure_releases_claim(kanban_home):
-    def boom(task, workspace):
-        raise RuntimeError("spawn failed")
-
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="boom", assignee="alice")
-        kb.dispatch_once(conn, spawn_fn=boom)
-        # Must return to ready so the next tick can retry.
-        assert kb.get_task(conn, t).status == "ready"
-        assert kb.get_task(conn, t).claim_lock is None
-
-
-def test_dispatch_reclaims_stale_before_spawning(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x", assignee="alice")
-        kb.claim_task(conn, t)
-        conn.execute(
-            "UPDATE tasks SET claim_expires = ? WHERE id = ?",
-            (int(time.time()) - 1, t),
-        )
-        res = kb.dispatch_once(conn, dry_run=True)
-    assert res.reclaimed == 1
-
-
-# ---------------------------------------------------------------------------
-# Workspace resolution
-# ---------------------------------------------------------------------------
-
-def test_scratch_workspace_created_under_hermes_home(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="x")
-        task = kb.get_task(conn, t)
-        ws = kb.resolve_workspace(task)
-    assert ws.exists()
-    assert ws.is_dir()
-    assert "kanban" in str(ws)
-
-
-def test_dir_workspace_honors_given_path(kanban_home, tmp_path):
-    target = tmp_path / "my-vault"
-    with kb.connect() as conn:
-        t = kb.create_task(
-            conn, title="biz", workspace_kind="dir", workspace_path=str(target)
-        )
-        task = kb.get_task(conn, t)
-        ws = kb.resolve_workspace(task)
-    assert ws == target
-    assert ws.exists()
-
-
-def test_worktree_workspace_returns_intended_path(kanban_home, tmp_path):
-    target = str(tmp_path / ".worktrees" / "my-task")
-    with kb.connect() as conn:
-        t = kb.create_task(
-            conn, title="ship", workspace_kind="worktree", workspace_path=target
-        )
-        task = kb.get_task(conn, t)
-        ws = kb.resolve_workspace(task)
-    # We do NOT auto-create worktrees; the worker's skill handles that.
-    assert str(ws) == target
-
-
-# ---------------------------------------------------------------------------
-# Tenancy
-# ---------------------------------------------------------------------------
-
-def test_tenant_column_filters_listings(kanban_home):
-    with kb.connect() as conn:
-        kb.create_task(conn, title="a1", tenant="biz-a")
-        kb.create_task(conn, title="b1", tenant="biz-b")
-        kb.create_task(conn, title="shared")  # no tenant
-        biz_a = kb.list_tasks(conn, tenant="biz-a")
-        biz_b = kb.list_tasks(conn, tenant="biz-b")
-    assert [t.title for t in biz_a] == ["a1"]
-    assert [t.title for t in biz_b] == ["b1"]
-
-
-def test_tenant_propagates_to_events(kanban_home):
-    with kb.connect() as conn:
-        t = kb.create_task(conn, title="tenant-task", tenant="biz-a")
-        events = kb.list_events(conn, t)
-    # The "created" event should have tenant in its payload.
-    created = [e for e in events if e.kind == "created"]
-    assert created and created[0].payload.get("tenant") == "biz-a"

tests/hermes_cli/test_model_catalog.py

@@ -1,284 +0,0 @@
-"""Tests for hermes_cli.model_catalog — remote manifest fetch + cache + fallback."""
-
-from __future__ import annotations
-
-import json
-import time
-from pathlib import Path
-from unittest.mock import patch
-
-import pytest
-
-
-@pytest.fixture
-def isolated_home(tmp_path, monkeypatch):
-    """Isolate HERMES_HOME + reset any module-level catalog cache per test."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    monkeypatch.setenv("HERMES_HOME", str(home))
-
-    # Force a fresh catalog module state for each test.
-    import importlib
-    from hermes_cli import model_catalog
-    importlib.reload(model_catalog)
-    yield home
-    model_catalog.reset_cache()
-
-
-def _valid_manifest() -> dict:
-    return {
-        "version": 1,
-        "updated_at": "2026-04-25T22:00:00Z",
-        "metadata": {"source": "test"},
-        "providers": {
-            "openrouter": {
-                "metadata": {"display_name": "OpenRouter"},
-                "models": [
-                    {"id": "anthropic/claude-opus-4.7", "description": "recommended"},
-                    {"id": "openai/gpt-5.4", "description": ""},
-                    {"id": "openrouter/elephant-alpha", "description": "free"},
-                ],
-            },
-            "nous": {
-                "metadata": {"display_name": "Nous Portal"},
-                "models": [
-                    {"id": "anthropic/claude-opus-4.7"},
-                    {"id": "moonshotai/kimi-k2.6"},
-                ],
-            },
-        },
-    }
-
-
-class TestValidation:
-    def test_accepts_well_formed_manifest(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        assert _validate_manifest(_valid_manifest()) is True
-
-    def test_rejects_non_dict(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        assert _validate_manifest("string") is False
-        assert _validate_manifest([]) is False
-        assert _validate_manifest(None) is False
-
-    def test_rejects_missing_version(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        m = _valid_manifest()
-        del m["version"]
-        assert _validate_manifest(m) is False
-
-    def test_rejects_future_version(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        m = _valid_manifest()
-        m["version"] = 999
-        assert _validate_manifest(m) is False
-
-    def test_rejects_missing_providers(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        m = _valid_manifest()
-        del m["providers"]
-        assert _validate_manifest(m) is False
-
-    def test_rejects_malformed_model_entry(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        m = _valid_manifest()
-        m["providers"]["openrouter"]["models"][0] = {"id": ""}  # empty id
-        assert _validate_manifest(m) is False
-
-    def test_rejects_non_string_model_id(self, isolated_home):
-        from hermes_cli.model_catalog import _validate_manifest
-        m = _valid_manifest()
-        m["providers"]["openrouter"]["models"][0] = {"id": 42}
-        assert _validate_manifest(m) is False
-
-
-class TestFetchSuccess:
-    def test_fetch_and_cache_writes_disk(self, isolated_home):
-        from hermes_cli import model_catalog
-        manifest = _valid_manifest()
-        with patch.object(
-            model_catalog, "_fetch_manifest", return_value=manifest
-        ) as fetch:
-            result = model_catalog.get_catalog(force_refresh=True)
-
-        assert result == manifest
-        assert fetch.called
-
-        cache_file = model_catalog._cache_path()
-        assert cache_file.exists()
-        with open(cache_file) as fh:
-            assert json.load(fh) == manifest
-
-    def test_second_call_uses_in_process_cache(self, isolated_home):
-        from hermes_cli import model_catalog
-        manifest = _valid_manifest()
-        with patch.object(
-            model_catalog, "_fetch_manifest", return_value=manifest
-        ) as fetch:
-            model_catalog.get_catalog(force_refresh=True)
-            model_catalog.get_catalog()  # should not hit network again
-        assert fetch.call_count == 1
-
-    def test_force_refresh_always_refetches(self, isolated_home):
-        from hermes_cli import model_catalog
-        manifest = _valid_manifest()
-        with patch.object(
-            model_catalog, "_fetch_manifest", return_value=manifest
-        ) as fetch:
-            model_catalog.get_catalog(force_refresh=True)
-            model_catalog.get_catalog(force_refresh=True)
-        assert fetch.call_count == 2
-
-
-class TestFetchFailure:
-    def test_network_failure_returns_empty_when_no_cache(self, isolated_home):
-        from hermes_cli import model_catalog
-        with patch.object(model_catalog, "_fetch_manifest", return_value=None):
-            result = model_catalog.get_catalog(force_refresh=True)
-        assert result == {}
-
-    def test_network_failure_falls_back_to_disk_cache(self, isolated_home):
-        from hermes_cli import model_catalog
-        # Prime disk cache with a fresh copy.
-        manifest = _valid_manifest()
-        with patch.object(model_catalog, "_fetch_manifest", return_value=manifest):
-            model_catalog.get_catalog(force_refresh=True)
-
-        # Now wipe in-process cache and simulate network failure on refetch.
-        model_catalog.reset_cache()
-        with patch.object(model_catalog, "_fetch_manifest", return_value=None):
-            result = model_catalog.get_catalog(force_refresh=True)
-
-        assert result == manifest
-
-    def test_fetch_failure_falls_back_to_stale_cache(self, isolated_home):
-        from hermes_cli import model_catalog
-        manifest = _valid_manifest()
-        # Write stale cache directly (mtime in the past).
-        cache = model_catalog._cache_path()
-        cache.parent.mkdir(parents=True, exist_ok=True)
-        with open(cache, "w") as fh:
-            json.dump(manifest, fh)
-        old = time.time() - 30 * 24 * 3600  # 30 days ago
-        import os as _os
-        _os.utime(cache, (old, old))
-
-        with patch.object(model_catalog, "_fetch_manifest", return_value=None):
-            result = model_catalog.get_catalog()
-
-        # Stale cache is better than nothing.
-        assert result == manifest
-
-
-class TestCuratedAccessors:
-    def test_openrouter_returns_tuples(self, isolated_home):
-        from hermes_cli import model_catalog
-        with patch.object(
-            model_catalog, "_fetch_manifest", return_value=_valid_manifest()
-        ):
-            result = model_catalog.get_curated_openrouter_models()
-        assert result == [
-            ("anthropic/claude-opus-4.7", "recommended"),
-            ("openai/gpt-5.4", ""),
-            ("openrouter/elephant-alpha", "free"),
-        ]
-
-    def test_nous_returns_ids(self, isolated_home):
-        from hermes_cli import model_catalog
-        with patch.object(
-            model_catalog, "_fetch_manifest", return_value=_valid_manifest()
-        ):
-            result = model_catalog.get_curated_nous_models()
-        assert result == ["anthropic/claude-opus-4.7", "moonshotai/kimi-k2.6"]
-
-    def test_openrouter_returns_none_when_catalog_empty(self, isolated_home):
-        from hermes_cli import model_catalog
-        with patch.object(model_catalog, "_fetch_manifest", return_value=None):
-            assert model_catalog.get_curated_openrouter_models() is None
-
-    def test_nous_returns_none_when_catalog_empty(self, isolated_home):
-        from hermes_cli import model_catalog
-        with patch.object(model_catalog, "_fetch_manifest", return_value=None):
-            assert model_catalog.get_curated_nous_models() is None
-
-
-class TestDisabled:
-    def test_disabled_config_short_circuits(self, isolated_home):
-        from hermes_cli import model_catalog
-        with patch.object(
-            model_catalog,
-            "_load_catalog_config",
-            return_value={
-                "enabled": False,
-                "url": "http://ignored",
-                "ttl_hours": 24.0,
-                "providers": {},
-            },
-        ):
-            with patch.object(model_catalog, "_fetch_manifest") as fetch:
-                result = model_catalog.get_catalog()
-        assert result == {}
-        fetch.assert_not_called()
-
-
-class TestProviderOverride:
-    def test_override_url_takes_precedence(self, isolated_home):
-        from hermes_cli import model_catalog
-
-        override_payload = {
-            "version": 1,
-            "providers": {
-                "openrouter": {
-                    "models": [
-                        {"id": "override/model", "description": "custom"},
-                    ]
-                }
-            },
-        }
-
-        def fake_fetch(url, timeout):
-            if "override" in url:
-                return override_payload
-            return _valid_manifest()
-
-        with patch.object(
-            model_catalog,
-            "_load_catalog_config",
-            return_value={
-                "enabled": True,
-                "url": "http://master",
-                "ttl_hours": 24.0,
-                "providers": {"openrouter": {"url": "http://override"}},
-            },
-        ):
-            with patch.object(model_catalog, "_fetch_manifest", side_effect=fake_fetch):
-                result = model_catalog.get_curated_openrouter_models()
-
-        assert result == [("override/model", "custom")]
-
-
-class TestIntegrationWithModelsModule:
-    """Exercise the fallback paths via the real callers in hermes_cli.models."""
-
-    def test_curated_nous_ids_falls_back_to_hardcoded_on_empty_catalog(
-        self, isolated_home
-    ):
-        from hermes_cli import model_catalog
-        from hermes_cli.models import get_curated_nous_model_ids, _PROVIDER_MODELS
-
-        with patch.object(model_catalog, "_fetch_manifest", return_value=None):
-            result = get_curated_nous_model_ids()
-
-        assert result == list(_PROVIDER_MODELS["nous"])
-
-    def test_curated_nous_ids_prefers_manifest(self, isolated_home):
-        from hermes_cli import model_catalog
-        from hermes_cli.models import get_curated_nous_model_ids
-
-        with patch.object(
-            model_catalog, "_fetch_manifest", return_value=_valid_manifest()
-        ):
-            result = get_curated_nous_model_ids()
-
-        assert result == ["anthropic/claude-opus-4.7", "moonshotai/kimi-k2.6"]

tests/hermes_cli/test_model_switch_context_display.py

@@ -88,61 +88,3 @@ class TestResolveDisplayContextLength:
                 model_info=fake_mi,
             )
         assert ctx == 128_000
-
-    def test_custom_providers_override_honored(self):
-        """Regression for #15779: /model switch onto a custom provider must
-        surface the configured per-model context_length, not the 128K/256K
-        fallback.
-        """
-        custom_provs = [
-            {
-                "name": "my-custom-endpoint",
-                "base_url": "https://example.invalid/v1",
-                "models": {"gpt-5.5": {"context_length": 1_050_000}},
-            }
-        ]
-        # Real resolver call — no mock — so the override path is exercised
-        # through agent.model_metadata.get_model_context_length.
-        from unittest.mock import patch as _p
-        from agent import model_metadata as _mm
-        with _p.object(_mm, "get_cached_context_length", return_value=None), \
-             _p.object(_mm, "fetch_endpoint_model_metadata", return_value={}), \
-             _p.object(_mm, "fetch_model_metadata", return_value={}), \
-             _p.object(_mm, "is_local_endpoint", return_value=False), \
-             _p.object(_mm, "_is_known_provider_base_url", return_value=False):
-            ctx = resolve_display_context_length(
-                "gpt-5.5",
-                "custom",
-                base_url="https://example.invalid/v1",
-                api_key="k",
-                custom_providers=custom_provs,
-            )
-        assert ctx == 1_050_000, (
-            "custom_providers[].models.gpt-5.5.context_length=1.05M must win "
-            "over probe-down fallback"
-        )
-
-    def test_custom_providers_trailing_slash_insensitive(self):
-        """Base URL comparison must tolerate trailing-slash differences
-        between config.yaml and the runtime value.
-        """
-        custom_provs = [
-            {
-                "base_url": "https://example.invalid/v1/",
-                "models": {"m": {"context_length": 400_000}},
-            }
-        ]
-        from unittest.mock import patch as _p
-        from agent import model_metadata as _mm
-        with _p.object(_mm, "get_cached_context_length", return_value=None), \
-             _p.object(_mm, "fetch_endpoint_model_metadata", return_value={}), \
-             _p.object(_mm, "fetch_model_metadata", return_value={}), \
-             _p.object(_mm, "is_local_endpoint", return_value=False), \
-             _p.object(_mm, "_is_known_provider_base_url", return_value=False):
-            ctx = resolve_display_context_length(
-                "m",
-                "custom",
-                base_url="https://example.invalid/v1",  # no trailing slash
-                custom_providers=custom_provs,
-            )
-        assert ctx == 400_000

tests/hermes_cli/test_runtime_provider_resolution.py

@@ -1,5 +1,3 @@
-import pytest
-
 from hermes_cli import runtime_provider as rp
 
 
@@ -1567,79 +1565,3 @@ class TestOllamaUrlSubstringLeak:
         resolved = rp.resolve_runtime_provider(requested="custom")
 
         assert resolved["api_key"] == "ol-legit-key"
-
-
-# =============================================================================
-# Azure Foundry — both OpenAI-style and Anthropic-style endpoints
-# =============================================================================
-
-class TestAzureFoundryResolution:
-    """Verify Azure Foundry resolves correctly for both API modes."""
-
-    def _make_cfg(self, base_url: str, api_mode: str = "chat_completions"):
-        return {
-            "provider": "azure-foundry",
-            "base_url": base_url,
-            "api_mode": api_mode,
-            "default": "gpt-5.4",
-        }
-
-    def test_azure_foundry_openai_style_explicit(self, monkeypatch):
-        """OpenAI-style Azure Foundry → chat_completions, keeps base_url as-is."""
-        monkeypatch.setenv("AZURE_FOUNDRY_API_KEY", "az-key-openai")
-        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "azure-foundry")
-        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
-            "https://my-resource.openai.azure.com/openai/v1",
-            "chat_completions",
-        ))
-        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
-
-        resolved = rp.resolve_runtime_provider(requested="azure-foundry")
-
-        assert resolved["provider"] == "azure-foundry"
-        assert resolved["api_mode"] == "chat_completions"
-        assert resolved["base_url"] == "https://my-resource.openai.azure.com/openai/v1"
-        assert resolved["api_key"] == "az-key-openai"
-
-    def test_azure_foundry_anthropic_style_strips_v1_suffix(self, monkeypatch):
-        """Anthropic-style Azure Foundry → anthropic_messages, /v1 stripped
-        because the Anthropic SDK appends /v1/messages itself."""
-        monkeypatch.setenv("AZURE_FOUNDRY_API_KEY", "az-key-ant")
-        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "azure-foundry")
-        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
-            "https://my-resource.services.ai.azure.com/anthropic/v1",
-            "anthropic_messages",
-        ))
-        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
-
-        resolved = rp.resolve_runtime_provider(requested="azure-foundry")
-
-        assert resolved["provider"] == "azure-foundry"
-        assert resolved["api_mode"] == "anthropic_messages"
-        # /v1 stripped so SDK can append /v1/messages cleanly
-        assert resolved["base_url"] == "https://my-resource.services.ai.azure.com/anthropic"
-
-    def test_azure_foundry_missing_base_url_raises(self, monkeypatch):
-        monkeypatch.setenv("AZURE_FOUNDRY_API_KEY", "az-key")
-        monkeypatch.delenv("AZURE_FOUNDRY_BASE_URL", raising=False)
-        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "azure-foundry")
-        monkeypatch.setattr(rp, "_get_model_config", lambda: {})
-        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
-
-        with pytest.raises(rp.AuthError, match="base URL"):
-            rp.resolve_runtime_provider(requested="azure-foundry")
-
-    def test_azure_foundry_missing_api_key_raises(self, monkeypatch):
-        monkeypatch.delenv("AZURE_FOUNDRY_API_KEY", raising=False)
-        # `get_env_value` reads from ~/.hermes/.env — mock it to return None
-        # so the resolver can't find a key there either.
-        import hermes_cli.config as cfg_mod
-        monkeypatch.setattr(cfg_mod, "get_env_value", lambda k: None)
-        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "azure-foundry")
-        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
-            "https://my-resource.openai.azure.com/openai/v1"
-        ))
-        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
-
-        with pytest.raises(rp.AuthError, match="API key"):
-            rp.resolve_runtime_provider(requested="azure-foundry")

tests/hermes_cli/test_setup_noninteractive.py

@@ -144,6 +144,91 @@ class TestNonInteractiveSetup:
         out = capsys.readouterr().out
         assert "hermes config set model.provider custom" in out
 
+    def test_returning_user_terminal_menu_choice_dispatches_terminal_section(self, tmp_path):
+        """Returning-user menu should map Terminal Backend to the terminal setup, not TTS."""
+        from hermes_cli import setup as setup_mod
+
+        args = _make_setup_args()
+        config = {}
+        model_section = MagicMock()
+        tts_section = MagicMock()
+        terminal_section = MagicMock()
+        gateway_section = MagicMock()
+        tools_section = MagicMock()
+        agent_section = MagicMock()
+
+        with (
+            patch.object(setup_mod, "ensure_hermes_home"),
+            patch.object(setup_mod, "load_config", return_value=config),
+            patch.object(setup_mod, "get_hermes_home", return_value=tmp_path),
+            patch.object(setup_mod, "is_interactive_stdin", return_value=True),
+            patch.object(
+                setup_mod,
+                "get_env_value",
+                side_effect=lambda key: "sk-test" if key == "OPENROUTER_API_KEY" else "",
+            ),
+            patch("hermes_cli.auth.get_active_provider", return_value=None),
+            patch.object(setup_mod, "prompt_choice", return_value=3),
+            patch.object(
+                setup_mod,
+                "SETUP_SECTIONS",
+                [
+                    ("model", "Model & Provider", model_section),
+                    ("tts", "Text-to-Speech", tts_section),
+                    ("terminal", "Terminal Backend", terminal_section),
+                    ("gateway", "Messaging Platforms (Gateway)", gateway_section),
+                    ("tools", "Tools", tools_section),
+                    ("agent", "Agent Settings", agent_section),
+                ],
+            ),
+            patch.object(setup_mod, "save_config"),
+            patch.object(setup_mod, "_print_setup_summary"),
+        ):
+            setup_mod.run_setup_wizard(args)
+
+        terminal_section.assert_called_once_with(config)
+        tts_section.assert_not_called()
+
+    def test_returning_user_menu_does_not_show_separator_rows(self, tmp_path):
+        """Returning-user menu should only show selectable actions."""
+        from hermes_cli import setup as setup_mod
+
+        args = _make_setup_args()
+        captured = {}
+
+        def fake_prompt_choice(question, choices, default=0):
+            captured["question"] = question
+            captured["choices"] = list(choices)
+            return len(choices) - 1
+
+        with (
+            patch.object(setup_mod, "ensure_hermes_home"),
+            patch.object(setup_mod, "load_config", return_value={}),
+            patch.object(setup_mod, "get_hermes_home", return_value=tmp_path),
+            patch.object(setup_mod, "is_interactive_stdin", return_value=True),
+            patch.object(
+                setup_mod,
+                "get_env_value",
+                side_effect=lambda key: "sk-test" if key == "OPENROUTER_API_KEY" else "",
+            ),
+            patch("hermes_cli.auth.get_active_provider", return_value=None),
+            patch.object(setup_mod, "prompt_choice", side_effect=fake_prompt_choice),
+        ):
+            setup_mod.run_setup_wizard(args)
+
+        assert captured["question"] == "What would you like to do?"
+        assert "---" not in captured["choices"]
+        assert captured["choices"] == [
+            "Quick Setup - configure missing items only",
+            "Full Setup - reconfigure everything",
+            "Model & Provider",
+            "Terminal Backend",
+            "Messaging Platforms (Gateway)",
+            "Tools",
+            "Agent Settings",
+            "Exit",
+        ]
+
     def test_main_accepts_tts_setup_section(self, monkeypatch):
         """`hermes setup tts` should parse and dispatch like other setup sections."""
         from hermes_cli import main as main_mod

tests/hermes_cli/test_setup_reconfigure.py

@@ -1,287 +0,0 @@
-"""Tests for the setup wizard's returning-user behavior.
-
-On an existing install:
-- Bare `hermes setup` drops straight into the full reconfigure wizard
-  (every prompt shows the current value as its default).
-- `hermes setup --quick` runs the narrower "fill in missing items" flow.
-- `hermes setup --reconfigure` is a backwards-compat alias for the
-  bare-setup default.
-
-On a fresh install, all three are no-ops — fall through to first-time setup.
-"""
-
-from argparse import Namespace
-from contextlib import ExitStack
-from unittest.mock import patch
-
-import pytest
-
-
-def _make_setup_args(**overrides):
-    return Namespace(
-        non_interactive=overrides.get("non_interactive", False),
-        section=overrides.get("section", None),
-        reset=overrides.get("reset", False),
-        reconfigure=overrides.get("reconfigure", False),
-        quick=overrides.get("quick", False),
-    )
-
-
-@pytest.fixture
-def existing_install(tmp_path, monkeypatch):
-    """Simulate a returning user with an existing configured install."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setattr("pathlib.Path.home", lambda: tmp_path)
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    return home
-
-
-@pytest.fixture
-def fresh_install(tmp_path, monkeypatch):
-    """Simulate a first-time user with no existing configuration."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setattr("pathlib.Path.home", lambda: tmp_path)
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    return home
-
-
-def _enter_existing_install_patches(stack, **extra):
-    """Apply standard existing-install mocks via an ExitStack.
-
-    Returns a dict of mocks from the `extra` kwargs (which map mock-name to
-    target path) so callers can assert on them.
-    """
-    # Unconditional mocks (no return values to assert against).
-    for target, kwargs in [
-        ("hermes_cli.setup.ensure_hermes_home", {}),
-        ("hermes_cli.setup.is_interactive_stdin", {"return_value": True}),
-        ("hermes_cli.config.is_managed", {"return_value": False}),
-        ("hermes_cli.setup.load_config", {"return_value": {}}),
-        ("hermes_cli.setup.save_config", {}),
-        ("hermes_cli.setup.get_env_value", {"return_value": None}),
-        ("hermes_cli.auth.get_active_provider", {"return_value": "openrouter"}),
-        ("hermes_cli.setup._print_setup_summary", {}),
-        ("hermes_cli.setup._offer_launch_chat", {}),
-        ("hermes_cli.setup._offer_openclaw_migration", {"return_value": False}),
-    ]:
-        stack.enter_context(patch(target, **kwargs))
-
-    # Named mocks caller wants to assert on.
-    named = {}
-    for name, target in extra.items():
-        named[name] = stack.enter_context(patch(target))
-    return named
-
-
-def _enter_fresh_install_patches(stack, **extra):
-    for target, kwargs in [
-        ("hermes_cli.setup.ensure_hermes_home", {}),
-        ("hermes_cli.setup.is_interactive_stdin", {"return_value": True}),
-        ("hermes_cli.config.is_managed", {"return_value": False}),
-        ("hermes_cli.setup.load_config", {"return_value": {}}),
-        ("hermes_cli.setup.save_config", {}),
-        ("hermes_cli.auth.get_active_provider", {"return_value": None}),
-        ("hermes_cli.setup.get_env_value", {"return_value": None}),
-        ("hermes_cli.setup._offer_openclaw_migration", {"return_value": False}),
-    ]:
-        stack.enter_context(patch(target, **kwargs))
-
-    named = {}
-    for name, target_spec in extra.items():
-        if isinstance(target_spec, tuple):
-            target, kwargs = target_spec
-            named[name] = stack.enter_context(patch(target, **kwargs))
-        else:
-            named[name] = stack.enter_context(patch(target_spec))
-    return named
-
-
-class TestExistingInstallDefault:
-    """Bare `hermes setup` on an existing install = full reconfigure wizard."""
-
-    def test_bare_setup_runs_full_reconfigure_without_menu(self, existing_install):
-        """No menu, no prompt_choice — just run every section in sequence."""
-        args = _make_setup_args()  # no flags
-
-        with ExitStack() as stack:
-            m = _enter_existing_install_patches(
-                stack,
-                prompt_choice="hermes_cli.setup.prompt_choice",
-                quick="hermes_cli.setup._run_quick_setup",
-                model="hermes_cli.setup.setup_model_provider",
-                terminal="hermes_cli.setup.setup_terminal_backend",
-                agent="hermes_cli.setup.setup_agent_settings",
-                gateway="hermes_cli.setup.setup_gateway",
-                tools="hermes_cli.setup.setup_tools",
-            )
-            from hermes_cli.setup import run_setup_wizard
-            run_setup_wizard(args)
-
-        # No menu shown.
-        m["prompt_choice"].assert_not_called()
-        # Quick-setup path NOT taken.
-        m["quick"].assert_not_called()
-        # All five sections ran.
-        m["model"].assert_called_once()
-        m["terminal"].assert_called_once()
-        m["agent"].assert_called_once()
-        m["gateway"].assert_called_once()
-        m["tools"].assert_called_once()
-
-    def test_reconfigure_flag_is_backwards_compat_noop(self, existing_install):
-        """`hermes setup --reconfigure` behaves the same as bare `hermes setup`."""
-        args = _make_setup_args(reconfigure=True)
-
-        with ExitStack() as stack:
-            m = _enter_existing_install_patches(
-                stack,
-                prompt_choice="hermes_cli.setup.prompt_choice",
-                model="hermes_cli.setup.setup_model_provider",
-                terminal="hermes_cli.setup.setup_terminal_backend",
-                agent="hermes_cli.setup.setup_agent_settings",
-                gateway="hermes_cli.setup.setup_gateway",
-                tools="hermes_cli.setup.setup_tools",
-            )
-            from hermes_cli.setup import run_setup_wizard
-            run_setup_wizard(args)
-
-        m["prompt_choice"].assert_not_called()
-        m["model"].assert_called_once()
-        m["terminal"].assert_called_once()
-        m["agent"].assert_called_once()
-        m["gateway"].assert_called_once()
-        m["tools"].assert_called_once()
-
-
-class TestQuickFlag:
-    """`--quick` on an existing install runs the fill-missing flow."""
-
-    def test_quick_flag_runs_quick_setup_only(self, existing_install):
-        args = _make_setup_args(quick=True)
-
-        with ExitStack() as stack:
-            m = _enter_existing_install_patches(
-                stack,
-                quick="hermes_cli.setup._run_quick_setup",
-                model="hermes_cli.setup.setup_model_provider",
-                terminal="hermes_cli.setup.setup_terminal_backend",
-                agent="hermes_cli.setup.setup_agent_settings",
-                gateway="hermes_cli.setup.setup_gateway",
-                tools="hermes_cli.setup.setup_tools",
-            )
-            from hermes_cli.setup import run_setup_wizard
-            run_setup_wizard(args)
-
-        m["quick"].assert_called_once()
-        # Full reconfigure sections must NOT run.
-        m["model"].assert_not_called()
-        m["terminal"].assert_not_called()
-        m["agent"].assert_not_called()
-        m["gateway"].assert_not_called()
-        m["tools"].assert_not_called()
-
-
-class TestFreshInstall:
-    """On a fresh install (no active provider), flags are no-ops."""
-
-    def test_bare_setup_runs_first_time_flow(self, fresh_install):
-        args = _make_setup_args()
-
-        with ExitStack() as stack:
-            m = _enter_fresh_install_patches(
-                stack,
-                prompt=("hermes_cli.setup.prompt_choice", {"return_value": 0}),
-                first="hermes_cli.setup._run_first_time_quick_setup",
-            )
-            from hermes_cli.setup import run_setup_wizard
-            run_setup_wizard(args)
-
-        m["prompt"].assert_called_once()  # quick-vs-full prompt
-        m["first"].assert_called_once()
-
-    def test_reconfigure_on_fresh_install_falls_through(self, fresh_install):
-        args = _make_setup_args(reconfigure=True)
-
-        with ExitStack() as stack:
-            m = _enter_fresh_install_patches(
-                stack,
-                prompt=("hermes_cli.setup.prompt_choice", {"return_value": 0}),
-                first="hermes_cli.setup._run_first_time_quick_setup",
-            )
-            from hermes_cli.setup import run_setup_wizard
-            run_setup_wizard(args)
-
-        m["prompt"].assert_called_once()
-        m["first"].assert_called_once()
-
-    def test_quick_on_fresh_install_falls_through(self, fresh_install):
-        args = _make_setup_args(quick=True)
-
-        with ExitStack() as stack:
-            m = _enter_fresh_install_patches(
-                stack,
-                prompt=("hermes_cli.setup.prompt_choice", {"return_value": 0}),
-                first="hermes_cli.setup._run_first_time_quick_setup",
-            )
-            from hermes_cli.setup import run_setup_wizard
-            run_setup_wizard(args)
-
-        m["prompt"].assert_called_once()
-        m["first"].assert_called_once()
-
-
-class TestArgparse:
-    """The flags are plumbed through argparse to cmd_setup."""
-
-    def test_reconfigure_flag_reaches_cmd_setup(self, monkeypatch):
-        import sys
-        from hermes_cli.main import main
-
-        captured = {}
-        monkeypatch.setattr(
-            "hermes_cli.setup.run_setup_wizard",
-            lambda args: captured.setdefault("args", args),
-        )
-        monkeypatch.setattr(sys, "argv", ["hermes", "setup", "--reconfigure"])
-        try:
-            main()
-        except SystemExit:
-            pass
-        assert captured["args"].reconfigure is True
-        assert captured["args"].quick is False
-
-    def test_quick_flag_reaches_cmd_setup(self, monkeypatch):
-        import sys
-        from hermes_cli.main import main
-
-        captured = {}
-        monkeypatch.setattr(
-            "hermes_cli.setup.run_setup_wizard",
-            lambda args: captured.setdefault("args", args),
-        )
-        monkeypatch.setattr(sys, "argv", ["hermes", "setup", "--quick"])
-        try:
-            main()
-        except SystemExit:
-            pass
-        assert captured["args"].quick is True
-        assert captured["args"].reconfigure is False
-
-    def test_bare_setup_has_both_flags_false(self, monkeypatch):
-        import sys
-        from hermes_cli.main import main
-
-        captured = {}
-        monkeypatch.setattr(
-            "hermes_cli.setup.run_setup_wizard",
-            lambda args: captured.setdefault("args", args),
-        )
-        monkeypatch.setattr(sys, "argv", ["hermes", "setup"])
-        try:
-            main()
-        except SystemExit:
-            pass
-        assert captured["args"].reconfigure is False
-        assert captured["args"].quick is False

tests/hermes_cli/test_suppress_eio_on_interrupt.py

@@ -1,115 +0,0 @@
-"""Tests for OSError EIO suppression during interrupt shutdown (#13710).
-
-When the user interrupts a running task, prompt_toolkit tries to flush
-stdout during emergency shutdown.  If stdout is already in a broken state
-(redirected to /dev/null, pipe closed, etc.), the flush raises
-``OSError: [Errno 5] Input/output error``.
-
-The ``_suppress_closed_loop_errors`` asyncio exception handler and the
-outer ``except (KeyError, OSError)`` block must both suppress this error
-to prevent a hard crash.
-"""
-
-from __future__ import annotations
-
-import errno
-import os
-from unittest.mock import MagicMock
-
-import pytest
-
-
-# ---------------------------------------------------------------------------
-# _suppress_closed_loop_errors – asyncio exception handler
-# ---------------------------------------------------------------------------
-
-def _make_suppress_fn():
-    """Build a standalone copy of ``_suppress_closed_loop_errors``.
-
-    The real function is defined as a closure inside
-    ``CLI._run_interactive``; we reconstruct an equivalent here so the
-    unit tests don't need a full CLI instance.
-    """
-    def _suppress_closed_loop_errors(loop, context):
-        exc = context.get("exception")
-        if isinstance(exc, RuntimeError) and "Event loop is closed" in str(exc):
-            return
-        if isinstance(exc, KeyError) and "is not registered" in str(exc):
-            return
-        if isinstance(exc, OSError) and getattr(exc, "errno", None) == errno.EIO:
-            return
-        loop.default_exception_handler(context)
-    return _suppress_closed_loop_errors
-
-
-class TestSuppressClosedLoopErrors:
-    """Verify the asyncio exception handler suppresses expected errors."""
-
-    def test_suppresses_event_loop_closed(self):
-        handler = _make_suppress_fn()
-        loop = MagicMock()
-        handler(loop, {"exception": RuntimeError("Event loop is closed")})
-        loop.default_exception_handler.assert_not_called()
-
-    def test_suppresses_key_not_registered(self):
-        handler = _make_suppress_fn()
-        loop = MagicMock()
-        handler(loop, {"exception": KeyError("0 is not registered")})
-        loop.default_exception_handler.assert_not_called()
-
-    def test_suppresses_oserror_eio(self):
-        """OSError with errno.EIO must be suppressed (#13710)."""
-        handler = _make_suppress_fn()
-        loop = MagicMock()
-        exc = OSError(errno.EIO, "Input/output error")
-        handler(loop, {"exception": exc})
-        loop.default_exception_handler.assert_not_called()
-
-    def test_does_not_suppress_oserror_other_errno(self):
-        """OSError with a different errno must still propagate."""
-        handler = _make_suppress_fn()
-        loop = MagicMock()
-        exc = OSError(errno.EACCES, "Permission denied")
-        handler(loop, {"exception": exc})
-        loop.default_exception_handler.assert_called_once()
-
-    def test_does_not_suppress_unrelated_exception(self):
-        """Unrelated exceptions must still propagate."""
-        handler = _make_suppress_fn()
-        loop = MagicMock()
-        handler(loop, {"exception": ValueError("something else")})
-        loop.default_exception_handler.assert_called_once()
-
-    def test_no_exception_key(self):
-        """Context without 'exception' must propagate to default handler."""
-        handler = _make_suppress_fn()
-        loop = MagicMock()
-        handler(loop, {"message": "some log"})
-        loop.default_exception_handler.assert_called_once()
-
-
-# ---------------------------------------------------------------------------
-# Outer except block – EIO handling
-# ---------------------------------------------------------------------------
-
-class TestOuterExceptEIO:
-    """Verify the outer ``except (KeyError, OSError)`` block logic."""
-
-    def test_eio_does_not_reraise(self):
-        """OSError with errno.EIO should be silently suppressed."""
-        exc = OSError(errno.EIO, "Input/output error")
-        # Simulate the condition check from the outer except block:
-        assert isinstance(exc, OSError)
-        assert getattr(exc, "errno", None) == errno.EIO
-
-    def test_bad_file_descriptor_matches(self):
-        """'Bad file descriptor' string should be caught."""
-        exc = OSError(errno.EBADF, "Bad file descriptor")
-        assert "Bad file descriptor" in str(exc)
-
-    def test_other_oserror_reraises(self):
-        """Other OSError variants must not match the EIO guard."""
-        exc = OSError(errno.EACCES, "Permission denied")
-        assert not (getattr(exc, "errno", None) == errno.EIO)
-        assert "is not registered" not in str(exc)
-        assert "Bad file descriptor" not in str(exc)

tests/plugins/test_kanban_dashboard_plugin.py

@@ -1,822 +0,0 @@
-"""Tests for the Kanban dashboard plugin backend (plugins/kanban/dashboard/plugin_api.py).
-
-The plugin mounts as /api/plugins/kanban/ inside the dashboard's FastAPI app,
-but here we attach its router to a bare FastAPI instance so we can test the
-REST surface without spinning up the whole dashboard.
-"""
-
-from __future__ import annotations
-
-import importlib.util
-import os
-import sys
-import time
-from pathlib import Path
-
-import pytest
-from fastapi import FastAPI
-from fastapi.testclient import TestClient
-
-from hermes_cli import kanban_db as kb
-
-
-# ---------------------------------------------------------------------------
-# Fixtures
-# ---------------------------------------------------------------------------
-
-
-def _load_plugin_router():
-    """Dynamically load plugins/kanban/dashboard/plugin_api.py and return its router."""
-    repo_root = Path(__file__).resolve().parents[2]
-    plugin_file = repo_root / "plugins" / "kanban" / "dashboard" / "plugin_api.py"
-    assert plugin_file.exists(), f"plugin file missing: {plugin_file}"
-
-    spec = importlib.util.spec_from_file_location(
-        "hermes_dashboard_plugin_kanban_test", plugin_file,
-    )
-    assert spec is not None and spec.loader is not None
-    mod = importlib.util.module_from_spec(spec)
-    sys.modules[spec.name] = mod
-    spec.loader.exec_module(mod)
-    return mod.router
-
-
-@pytest.fixture
-def kanban_home(tmp_path, monkeypatch):
-    """Isolated HERMES_HOME with an empty kanban DB."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    kb.init_db()
-    return home
-
-
-@pytest.fixture
-def client(kanban_home):
-    app = FastAPI()
-    app.include_router(_load_plugin_router(), prefix="/api/plugins/kanban")
-    return TestClient(app)
-
-
-# ---------------------------------------------------------------------------
-# GET /board on an empty DB
-# ---------------------------------------------------------------------------
-
-
-def test_board_empty(client):
-    r = client.get("/api/plugins/kanban/board")
-    assert r.status_code == 200
-    data = r.json()
-    # All canonical columns present (triage + the rest), each empty.
-    names = [c["name"] for c in data["columns"]]
-    for expected in ("triage", "todo", "ready", "running", "blocked", "done"):
-        assert expected in names, f"missing column {expected}: {names}"
-    assert all(len(c["tasks"]) == 0 for c in data["columns"])
-    assert data["tenants"] == []
-    assert data["assignees"] == []
-    assert data["latest_event_id"] == 0
-
-
-# ---------------------------------------------------------------------------
-# POST /tasks then GET /board sees it
-# ---------------------------------------------------------------------------
-
-
-def test_create_task_appears_on_board(client):
-    r = client.post(
-        "/api/plugins/kanban/tasks",
-        json={
-            "title": "Research LLM caching",
-            "assignee": "researcher",
-            "priority": 3,
-            "tenant": "acme",
-        },
-    )
-    assert r.status_code == 200, r.text
-    task = r.json()["task"]
-    assert task["title"] == "Research LLM caching"
-    assert task["assignee"] == "researcher"
-    assert task["status"] == "ready"  # no parents -> immediately ready
-    assert task["priority"] == 3
-    assert task["tenant"] == "acme"
-    task_id = task["id"]
-
-    # Board now lists it under 'ready'.
-    r = client.get("/api/plugins/kanban/board")
-    assert r.status_code == 200
-    data = r.json()
-    ready = next(c for c in data["columns"] if c["name"] == "ready")
-    assert len(ready["tasks"]) == 1
-    assert ready["tasks"][0]["id"] == task_id
-    assert "acme" in data["tenants"]
-    assert "researcher" in data["assignees"]
-
-
-def test_tenant_filter(client):
-    client.post("/api/plugins/kanban/tasks", json={"title": "A", "tenant": "t1"})
-    client.post("/api/plugins/kanban/tasks", json={"title": "B", "tenant": "t2"})
-
-    r = client.get("/api/plugins/kanban/board?tenant=t1")
-    counts = {c["name"]: len(c["tasks"]) for c in r.json()["columns"]}
-    total = sum(counts.values())
-    assert total == 1
-
-    r = client.get("/api/plugins/kanban/board?tenant=t2")
-    total = sum(len(c["tasks"]) for c in r.json()["columns"])
-    assert total == 1
-
-
-# ---------------------------------------------------------------------------
-# GET /tasks/:id returns body + comments + events + links
-# ---------------------------------------------------------------------------
-
-
-def test_task_detail_includes_links_and_events(client):
-    parent = client.post(
-        "/api/plugins/kanban/tasks", json={"title": "parent"},
-    ).json()["task"]
-    child = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "child", "parents": [parent["id"]]},
-    ).json()["task"]
-    assert child["status"] == "todo"  # parent not done yet
-
-    # Detail for the child shows the parent link.
-    r = client.get(f"/api/plugins/kanban/tasks/{child['id']}")
-    assert r.status_code == 200
-    data = r.json()
-    assert data["task"]["id"] == child["id"]
-    assert parent["id"] in data["links"]["parents"]
-
-    # Detail for the parent shows the child.
-    r = client.get(f"/api/plugins/kanban/tasks/{parent['id']}")
-    assert child["id"] in r.json()["links"]["children"]
-
-    # Events exist from creation.
-    assert len(data["events"]) >= 1
-
-
-def test_task_detail_404_on_unknown(client):
-    r = client.get("/api/plugins/kanban/tasks/does-not-exist")
-    assert r.status_code == 404
-
-
-# ---------------------------------------------------------------------------
-# PATCH /tasks/:id — status transitions
-# ---------------------------------------------------------------------------
-
-
-def test_patch_status_complete(client):
-    t = client.post("/api/plugins/kanban/tasks", json={"title": "x"}).json()["task"]
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}",
-        json={"status": "done", "result": "shipped"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["status"] == "done"
-
-    # Board reflects the move.
-    done = next(
-        c for c in client.get("/api/plugins/kanban/board").json()["columns"]
-        if c["name"] == "done"
-    )
-    assert any(x["id"] == t["id"] for x in done["tasks"])
-
-
-def test_patch_block_then_unblock(client):
-    t = client.post("/api/plugins/kanban/tasks", json={"title": "x"}).json()["task"]
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}",
-        json={"status": "blocked", "block_reason": "need input"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["status"] == "blocked"
-
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}",
-        json={"status": "ready"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["status"] == "ready"
-
-
-def test_patch_drag_drop_move_todo_to_ready(client):
-    """Direct status write: the drag-drop path for statuses without a
-    dedicated verb (e.g. manually promoting todo -> ready)."""
-    parent = client.post("/api/plugins/kanban/tasks", json={"title": "p"}).json()["task"]
-    child = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "c", "parents": [parent["id"]]},
-    ).json()["task"]
-    assert child["status"] == "todo"
-
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{child['id']}",
-        json={"status": "ready"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["status"] == "ready"
-
-
-def test_patch_reassign(client):
-    t = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "x", "assignee": "a"},
-    ).json()["task"]
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}",
-        json={"assignee": "b"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["assignee"] == "b"
-
-
-def test_patch_priority_and_edit(client):
-    t = client.post("/api/plugins/kanban/tasks", json={"title": "x"}).json()["task"]
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}",
-        json={"priority": 5, "title": "renamed"},
-    )
-    assert r.status_code == 200
-    data = r.json()["task"]
-    assert data["priority"] == 5
-    assert data["title"] == "renamed"
-
-
-def test_patch_invalid_status(client):
-    t = client.post("/api/plugins/kanban/tasks", json={"title": "x"}).json()["task"]
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}",
-        json={"status": "banana"},
-    )
-    assert r.status_code == 400
-
-
-# ---------------------------------------------------------------------------
-# Comments + Links
-# ---------------------------------------------------------------------------
-
-
-def test_add_comment(client):
-    t = client.post("/api/plugins/kanban/tasks", json={"title": "x"}).json()["task"]
-    r = client.post(
-        f"/api/plugins/kanban/tasks/{t['id']}/comments",
-        json={"body": "how's progress?", "author": "teknium"},
-    )
-    assert r.status_code == 200
-
-    r = client.get(f"/api/plugins/kanban/tasks/{t['id']}")
-    comments = r.json()["comments"]
-    assert len(comments) == 1
-    assert comments[0]["body"] == "how's progress?"
-    assert comments[0]["author"] == "teknium"
-
-
-def test_add_comment_empty_rejected(client):
-    t = client.post("/api/plugins/kanban/tasks", json={"title": "x"}).json()["task"]
-    r = client.post(
-        f"/api/plugins/kanban/tasks/{t['id']}/comments",
-        json={"body": "   "},
-    )
-    assert r.status_code == 400
-
-
-def test_add_link_and_delete_link(client):
-    a = client.post("/api/plugins/kanban/tasks", json={"title": "a"}).json()["task"]
-    b = client.post("/api/plugins/kanban/tasks", json={"title": "b"}).json()["task"]
-
-    r = client.post(
-        "/api/plugins/kanban/links",
-        json={"parent_id": a["id"], "child_id": b["id"]},
-    )
-    assert r.status_code == 200
-
-    r = client.get(f"/api/plugins/kanban/tasks/{b['id']}")
-    assert a["id"] in r.json()["links"]["parents"]
-
-    r = client.delete(
-        "/api/plugins/kanban/links",
-        params={"parent_id": a["id"], "child_id": b["id"]},
-    )
-    assert r.status_code == 200
-    assert r.json()["ok"] is True
-
-
-def test_add_link_cycle_rejected(client):
-    a = client.post("/api/plugins/kanban/tasks", json={"title": "a"}).json()["task"]
-    b = client.post("/api/plugins/kanban/tasks", json={"title": "b"}).json()["task"]
-    client.post(
-        "/api/plugins/kanban/links",
-        json={"parent_id": a["id"], "child_id": b["id"]},
-    )
-    r = client.post(
-        "/api/plugins/kanban/links",
-        json={"parent_id": b["id"], "child_id": a["id"]},
-    )
-    assert r.status_code == 400
-
-
-# ---------------------------------------------------------------------------
-# Dispatch nudge
-# ---------------------------------------------------------------------------
-
-
-def test_dispatch_dry_run(client):
-    client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "work", "assignee": "researcher"},
-    )
-    r = client.post("/api/plugins/kanban/dispatch?dry_run=true&max=4")
-    assert r.status_code == 200
-    body = r.json()
-    # DispatchResult is serialized as a dataclass dict.
-    assert isinstance(body, dict)
-
-
-# ---------------------------------------------------------------------------
-# Triage column (new v1 status)
-# ---------------------------------------------------------------------------
-
-
-def test_create_triage_lands_in_triage_column(client):
-    r = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "rough idea, spec me", "triage": True},
-    )
-    assert r.status_code == 200
-    task = r.json()["task"]
-    assert task["status"] == "triage"
-
-    r = client.get("/api/plugins/kanban/board")
-    triage = next(c for c in r.json()["columns"] if c["name"] == "triage")
-    assert len(triage["tasks"]) == 1
-    assert triage["tasks"][0]["title"] == "rough idea, spec me"
-
-
-def test_triage_task_not_promoted_to_ready(client):
-    """Triage tasks must stay in triage even when they have no parents."""
-    client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "must stay put", "triage": True},
-    )
-    # Run the dispatcher — it should NOT promote the triage task.
-    client.post("/api/plugins/kanban/dispatch?dry_run=false&max=4")
-    r = client.get("/api/plugins/kanban/board")
-    triage = next(c for c in r.json()["columns"] if c["name"] == "triage")
-    ready = next(c for c in r.json()["columns"] if c["name"] == "ready")
-    assert len(triage["tasks"]) == 1
-    assert len(ready["tasks"]) == 0
-
-
-def test_patch_status_triage_works(client):
-    """A user (or specifier) can push a task back into triage, and out of it."""
-    t = client.post(
-        "/api/plugins/kanban/tasks", json={"title": "x"},
-    ).json()["task"]
-    # Normal creation is 'ready'; push to triage.
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}", json={"status": "triage"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["status"] == "triage"
-
-    # Now promote to todo.
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{t['id']}", json={"status": "todo"},
-    )
-    assert r.status_code == 200
-    assert r.json()["task"]["status"] == "todo"
-
-
-# ---------------------------------------------------------------------------
-# Progress rollup (done children / total children)
-# ---------------------------------------------------------------------------
-
-
-def test_board_progress_rollup(client):
-    parent = client.post(
-        "/api/plugins/kanban/tasks", json={"title": "parent"},
-    ).json()["task"]
-    child_a = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "a", "parents": [parent["id"]]},
-    ).json()["task"]
-    child_b = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "b", "parents": [parent["id"]]},
-    ).json()["task"]
-    # Children start as "todo" because the parent isn't done yet; promote
-    # them to "ready" so complete_task will accept the transition.
-    for cid in (child_a["id"], child_b["id"]):
-        r = client.patch(
-            f"/api/plugins/kanban/tasks/{cid}", json={"status": "ready"},
-        )
-        assert r.status_code == 200
-
-    # 0/2 done.
-    r = client.get("/api/plugins/kanban/board")
-    parent_row = next(
-        t for col in r.json()["columns"] for t in col["tasks"]
-        if t["id"] == parent["id"]
-    )
-    assert parent_row["progress"] == {"done": 0, "total": 2}
-
-    # Complete one child. 1/2.
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{child_a['id']}",
-        json={"status": "done"},
-    )
-    assert r.status_code == 200
-    r = client.get("/api/plugins/kanban/board")
-    parent_row = next(
-        t for col in r.json()["columns"] for t in col["tasks"]
-        if t["id"] == parent["id"]
-    )
-    assert parent_row["progress"] == {"done": 1, "total": 2}
-
-    # Childless tasks report progress=None, not {0/0}.
-    assert next(
-        t for col in r.json()["columns"] for t in col["tasks"]
-        if t["id"] == child_b["id"]
-    )["progress"] is None
-
-
-# ---------------------------------------------------------------------------
-# Auto-init on first board read
-# ---------------------------------------------------------------------------
-
-
-def test_board_auto_initializes_missing_db(tmp_path, monkeypatch):
-    """If kanban.db doesn't exist yet, GET /board must create it, not 500."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    # Deliberately DO NOT call kb.init_db().
-
-    app = FastAPI()
-    app.include_router(_load_plugin_router(), prefix="/api/plugins/kanban")
-    c = TestClient(app)
-    r = c.get("/api/plugins/kanban/board")
-    assert r.status_code == 200
-    assert (home / "kanban.db").exists(), "init_db wasn't invoked by /board"
-
-
-# ---------------------------------------------------------------------------
-# WebSocket auth (query-param token)
-# ---------------------------------------------------------------------------
-
-
-def test_ws_events_rejects_when_token_required(tmp_path, monkeypatch):
-    """When _SESSION_TOKEN is set (normal dashboard context), a missing or
-    wrong ?token= query param must be rejected with policy-violation."""
-    home = tmp_path / ".hermes"
-    home.mkdir()
-    monkeypatch.setenv("HERMES_HOME", str(home))
-    monkeypatch.setattr(Path, "home", lambda: tmp_path)
-    kb.init_db()
-
-    # Stub web_server so _check_ws_token has a token to compare against.
-    import types
-    stub = types.SimpleNamespace(_SESSION_TOKEN="secret-xyz")
-    monkeypatch.setitem(sys.modules, "hermes_cli.web_server", stub)
-
-    app = FastAPI()
-    app.include_router(_load_plugin_router(), prefix="/api/plugins/kanban")
-    c = TestClient(app)
-
-    # No token → policy violation close.
-    from starlette.websockets import WebSocketDisconnect
-    with pytest.raises(WebSocketDisconnect) as exc:
-        with c.websocket_connect("/api/plugins/kanban/events"):
-            pass
-    assert exc.value.code == 1008
-
-    # Wrong token → policy violation close.
-    with pytest.raises(WebSocketDisconnect) as exc:
-        with c.websocket_connect("/api/plugins/kanban/events?token=nope"):
-            pass
-    assert exc.value.code == 1008
-
-    # Correct token → accepted (connect then close cleanly from our side).
-    with c.websocket_connect(
-        "/api/plugins/kanban/events?token=secret-xyz"
-    ) as ws:
-        assert ws is not None  # handshake succeeded
-
-
-# ---------------------------------------------------------------------------
-# Bulk actions
-# ---------------------------------------------------------------------------
-
-
-def test_bulk_status_ready(client):
-    a = client.post("/api/plugins/kanban/tasks", json={"title": "a"}).json()["task"]
-    b = client.post("/api/plugins/kanban/tasks", json={"title": "b"}).json()["task"]
-    c2 = client.post("/api/plugins/kanban/tasks", json={"title": "c"}).json()["task"]
-    # Parent-less tasks land in "ready" already; push them to blocked first.
-    for tid in (a["id"], b["id"], c2["id"]):
-        client.patch(f"/api/plugins/kanban/tasks/{tid}",
-                     json={"status": "blocked", "block_reason": "wait"})
-
-    r = client.post("/api/plugins/kanban/tasks/bulk",
-                    json={"ids": [a["id"], b["id"], c2["id"]], "status": "ready"})
-    assert r.status_code == 200
-    results = r.json()["results"]
-    assert all(r["ok"] for r in results)
-    # All three are now ready.
-    board = client.get("/api/plugins/kanban/board").json()
-    ready = next(col for col in board["columns"] if col["name"] == "ready")
-    ids = {t["id"] for t in ready["tasks"]}
-    assert {a["id"], b["id"], c2["id"]}.issubset(ids)
-
-
-def test_bulk_archive(client):
-    a = client.post("/api/plugins/kanban/tasks", json={"title": "a"}).json()["task"]
-    b = client.post("/api/plugins/kanban/tasks", json={"title": "b"}).json()["task"]
-    r = client.post("/api/plugins/kanban/tasks/bulk",
-                    json={"ids": [a["id"], b["id"]], "archive": True})
-    assert r.status_code == 200
-    assert all(r["ok"] for r in r.json()["results"])
-    # Default board (archived hidden) — both gone.
-    board = client.get("/api/plugins/kanban/board").json()
-    ids = {t["id"] for col in board["columns"] for t in col["tasks"]}
-    assert a["id"] not in ids
-    assert b["id"] not in ids
-
-
-def test_bulk_reassign(client):
-    a = client.post("/api/plugins/kanban/tasks",
-                    json={"title": "a", "assignee": "old"}).json()["task"]
-    b = client.post("/api/plugins/kanban/tasks",
-                    json={"title": "b", "assignee": "old"}).json()["task"]
-    r = client.post("/api/plugins/kanban/tasks/bulk",
-                    json={"ids": [a["id"], b["id"]], "assignee": "new"})
-    assert r.status_code == 200
-    for tid in (a["id"], b["id"]):
-        t = client.get(f"/api/plugins/kanban/tasks/{tid}").json()["task"]
-        assert t["assignee"] == "new"
-
-
-def test_bulk_unassign_via_empty_string(client):
-    a = client.post("/api/plugins/kanban/tasks",
-                    json={"title": "a", "assignee": "x"}).json()["task"]
-    r = client.post("/api/plugins/kanban/tasks/bulk",
-                    json={"ids": [a["id"]], "assignee": ""})
-    assert r.status_code == 200
-    t = client.get(f"/api/plugins/kanban/tasks/{a['id']}").json()["task"]
-    assert t["assignee"] is None
-
-
-def test_bulk_partial_failure_doesnt_abort_siblings(client):
-    """One bad id in the middle of a batch must not prevent others from
-    applying."""
-    a = client.post("/api/plugins/kanban/tasks", json={"title": "a"}).json()["task"]
-    c2 = client.post("/api/plugins/kanban/tasks", json={"title": "c"}).json()["task"]
-    r = client.post("/api/plugins/kanban/tasks/bulk",
-                    json={"ids": [a["id"], "bogus-id", c2["id"]], "priority": 7})
-    assert r.status_code == 200
-    results = r.json()["results"]
-    assert len(results) == 3
-    ok_ids = {r["id"] for r in results if r["ok"]}
-    assert a["id"] in ok_ids
-    assert c2["id"] in ok_ids
-    assert any(not r["ok"] and r["id"] == "bogus-id" for r in results)
-    # Good siblings actually got the priority bump.
-    for tid in (a["id"], c2["id"]):
-        t = client.get(f"/api/plugins/kanban/tasks/{tid}").json()["task"]
-        assert t["priority"] == 7
-
-
-def test_bulk_empty_ids_400(client):
-    r = client.post("/api/plugins/kanban/tasks/bulk", json={"ids": []})
-    assert r.status_code == 400
-
-
-# ---------------------------------------------------------------------------
-# /config endpoint
-# ---------------------------------------------------------------------------
-
-
-def test_config_returns_defaults_when_section_missing(client):
-    r = client.get("/api/plugins/kanban/config")
-    assert r.status_code == 200
-    data = r.json()
-    # Defaults when dashboard.kanban is missing.
-    assert data["default_tenant"] == ""
-    assert data["lane_by_profile"] is True
-    assert data["include_archived_by_default"] is False
-    assert data["render_markdown"] is True
-
-
-def test_config_reads_dashboard_kanban_section(tmp_path, monkeypatch, client):
-    home = Path(os.environ["HERMES_HOME"])
-    (home / "config.yaml").write_text(
-        "dashboard:\n"
-        "  kanban:\n"
-        "    default_tenant: acme\n"
-        "    lane_by_profile: false\n"
-        "    include_archived_by_default: true\n"
-        "    render_markdown: false\n"
-    )
-    r = client.get("/api/plugins/kanban/config")
-    assert r.status_code == 200
-    data = r.json()
-    assert data["default_tenant"] == "acme"
-    assert data["lane_by_profile"] is False
-    assert data["include_archived_by_default"] is True
-    assert data["render_markdown"] is False
-
-
-# ---------------------------------------------------------------------------
-# Runs surfacing (vulcan-artivus RFC feedback)
-# ---------------------------------------------------------------------------
-
-def test_task_detail_includes_runs(client):
-    """GET /tasks/:id carries a runs[] array with the attempt history."""
-    r = client.post("/api/plugins/kanban/tasks",
-                    json={"title": "port x", "assignee": "worker"}).json()
-    tid = r["task"]["id"]
-
-    # Drive status running to force a run creation: PATCH to running
-    # doesn't call claim_task (the PATCH path uses _set_status_direct),
-    # so use the bulk/claim indirection via the kernel.
-    import hermes_cli.kanban_db as _kb
-    conn = _kb.connect()
-    try:
-        _kb.claim_task(conn, tid)
-        _kb.complete_task(
-            conn, tid,
-            result="done",
-            summary="tested on rate limiter",
-            metadata={"changed_files": ["limiter.py"]},
-        )
-    finally:
-        conn.close()
-
-    d = client.get(f"/api/plugins/kanban/tasks/{tid}").json()
-    assert "runs" in d
-    assert len(d["runs"]) == 1
-    run = d["runs"][0]
-    assert run["outcome"] == "completed"
-    assert run["profile"] == "worker"
-    assert run["summary"] == "tested on rate limiter"
-    assert run["metadata"] == {"changed_files": ["limiter.py"]}
-    assert run["ended_at"] is not None
-
-
-def test_task_detail_runs_empty_before_claim(client):
-    """A task that's never been claimed has an empty runs[] list, not
-    a missing key."""
-    r = client.post("/api/plugins/kanban/tasks", json={"title": "fresh"}).json()
-    d = client.get(f"/api/plugins/kanban/tasks/{r['task']['id']}").json()
-    assert d["runs"] == []
-
-
-def test_patch_status_done_with_summary_and_metadata(client):
-    """PATCH /tasks/:id with status=done + summary + metadata must
-    reach complete_task, so the dashboard has CLI parity."""
-    # Create + claim.
-    r = client.post("/api/plugins/kanban/tasks", json={"title": "x", "assignee": "worker"})
-    tid = r.json()["task"]["id"]
-    from hermes_cli import kanban_db as kb
-    conn = kb.connect()
-    try:
-        kb.claim_task(conn, tid)
-    finally:
-        conn.close()
-
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{tid}",
-        json={
-            "status": "done",
-            "summary": "shipped the thing",
-            "metadata": {"changed_files": ["a.py", "b.py"], "tests_run": 7},
-        },
-    )
-    assert r.status_code == 200, r.text
-
-    # The run must have the summary + metadata attached.
-    conn = kb.connect()
-    try:
-        run = kb.latest_run(conn, tid)
-        assert run.outcome == "completed"
-        assert run.summary == "shipped the thing"
-        assert run.metadata == {"changed_files": ["a.py", "b.py"], "tests_run": 7}
-    finally:
-        conn.close()
-
-
-def test_patch_status_done_without_summary_still_works(client):
-    """Back-compat: PATCH without the new fields still completes."""
-    r = client.post("/api/plugins/kanban/tasks", json={"title": "y", "assignee": "worker"})
-    tid = r.json()["task"]["id"]
-    from hermes_cli import kanban_db as kb
-    conn = kb.connect()
-    try:
-        kb.claim_task(conn, tid)
-    finally:
-        conn.close()
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{tid}",
-        json={"status": "done", "result": "legacy shape"},
-    )
-    assert r.status_code == 200, r.text
-    conn = kb.connect()
-    try:
-        run = kb.latest_run(conn, tid)
-        assert run.outcome == "completed"
-        assert run.summary == "legacy shape"  # falls back to result
-    finally:
-        conn.close()
-
-
-def test_patch_status_archive_closes_running_run(client):
-    """PATCH to archived while running must close the in-flight run."""
-    r = client.post("/api/plugins/kanban/tasks", json={"title": "z", "assignee": "worker"})
-    tid = r.json()["task"]["id"]
-    from hermes_cli import kanban_db as kb
-    conn = kb.connect()
-    try:
-        kb.claim_task(conn, tid)
-        open_run = kb.latest_run(conn, tid)
-        assert open_run.ended_at is None
-    finally:
-        conn.close()
-    r = client.patch(
-        f"/api/plugins/kanban/tasks/{tid}",
-        json={"status": "archived"},
-    )
-    assert r.status_code == 200, r.text
-    conn = kb.connect()
-    try:
-        task = kb.get_task(conn, tid)
-        assert task.status == "archived"
-        assert task.current_run_id is None
-        assert kb.latest_run(conn, tid).outcome == "reclaimed"
-    finally:
-        conn.close()
-
-
-def test_event_dict_includes_run_id(client):
-    """GET /tasks/:id returns events with run_id populated."""
-    r = client.post("/api/plugins/kanban/tasks", json={"title": "e", "assignee": "worker"})
-    tid = r.json()["task"]["id"]
-    from hermes_cli import kanban_db as kb
-    conn = kb.connect()
-    try:
-        kb.claim_task(conn, tid)
-        run_id = kb.latest_run(conn, tid).id
-        kb.complete_task(conn, tid, summary="wss")
-    finally:
-        conn.close()
-
-    r = client.get(f"/api/plugins/kanban/tasks/{tid}")
-    assert r.status_code == 200
-    events = r.json()["events"]
-    # Every event in the response must have a run_id key (None or int).
-    for e in events:
-        assert "run_id" in e, f"missing run_id in event: {e}"
-    # completed event must have the actual run_id.
-    comp = [e for e in events if e["kind"] == "completed"]
-    assert comp[0]["run_id"] == run_id
-
-
-
-# ---------------------------------------------------------------------------
-# Per-task force-loaded skills via REST
-# ---------------------------------------------------------------------------
-
-def test_create_task_with_skills_roundtrips(client):
-    """POST /tasks accepts `skills: [...]`, GET /tasks/:id returns it."""
-    r = client.post(
-        "/api/plugins/kanban/tasks",
-        json={
-            "title": "translate docs",
-            "assignee": "linguist",
-            "skills": ["translation", "github-code-review"],
-        },
-    )
-    assert r.status_code == 200, r.text
-    task = r.json()["task"]
-    assert task["skills"] == ["translation", "github-code-review"]
-
-    # Fetch via GET /tasks/:id as the drawer does.
-    got = client.get(f"/api/plugins/kanban/tasks/{task['id']}").json()
-    assert got["task"]["skills"] == ["translation", "github-code-review"]
-
-
-def test_create_task_without_skills_defaults_to_empty_list(client):
-    """_task_dict serializes Task.skills=None as [] so the drawer can
-    always .length check without guarding against null."""
-    r = client.post(
-        "/api/plugins/kanban/tasks",
-        json={"title": "no skills", "assignee": "x"},
-    )
-    assert r.status_code == 200, r.text
-    task = r.json()["task"]
-    # Task.skills is None in-memory; _task_dict serializes via
-    # dataclasses.asdict which keeps it None. The drawer's
-    # `t.skills && t.skills.length > 0` guard handles both null and [].
-    assert task.get("skills") in (None, [])

tests/run_agent/test_provider_parity.py

@@ -716,103 +716,6 @@ class TestNormalizeCodexResponse:
         assert len(msg.tool_calls) == 1
         assert msg.tool_calls[0].function.name == "web_search"
 
-    def test_message_items_captured_with_id_and_phase(self, monkeypatch):
-        """Exact message items (with id/phase) must be captured for cache replay."""
-        agent = self._make_codex_agent(monkeypatch)
-        response = SimpleNamespace(
-            output=[
-                SimpleNamespace(
-                    type="message", status="completed", id="msg_abc",
-                    phase="commentary",
-                    content=[SimpleNamespace(type="output_text", text="Thinking...")],
-                ),
-                SimpleNamespace(
-                    type="message", status="completed", id="msg_def",
-                    phase="final_answer",
-                    content=[SimpleNamespace(type="output_text", text="Done!")],
-                ),
-            ],
-            status="completed",
-        )
-        msg, reason = _normalize_codex_response(response)
-        assert msg.codex_message_items is not None
-        assert len(msg.codex_message_items) == 2
-        assert msg.codex_message_items[0]["id"] == "msg_abc"
-        assert msg.codex_message_items[0]["phase"] == "commentary"
-        assert msg.codex_message_items[0]["content"][0]["text"] == "Thinking..."
-        assert msg.codex_message_items[1]["id"] == "msg_def"
-        assert msg.codex_message_items[1]["phase"] == "final_answer"
-        assert msg.codex_message_items[1]["content"][0]["text"] == "Done!"
-
-    def test_message_items_none_when_no_messages(self, monkeypatch):
-        """Only reasoning + tool calls should yield None codex_message_items."""
-        agent = self._make_codex_agent(monkeypatch)
-        response = SimpleNamespace(
-            output=[
-                SimpleNamespace(type="function_call", status="completed",
-                    call_id="call_1", name="web_search", arguments='{}', id="fc_1"),
-            ],
-            status="completed",
-        )
-        msg, reason = _normalize_codex_response(response)
-        assert msg.codex_message_items is None
-
-
-class TestChatMessagesToResponsesInputMessageItems:
-    """Verify codex_message_items are replayed verbatim instead of reconstructed."""
-
-    def test_replays_exact_message_items(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openai-codex", api_mode="codex_responses",
-                            base_url="https://chatgpt.com/backend-api/codex")
-        messages = [
-            {
-                "role": "assistant",
-                "content": "Hello world",
-                "codex_message_items": [
-                    {
-                        "type": "message",
-                        "role": "assistant",
-                        "status": "completed",
-                        "id": "msg_123",
-                        "phase": "final_answer",
-                        "content": [{"type": "output_text", "text": "Hello world"}],
-                    },
-                ],
-            },
-            {"role": "user", "content": "follow up"},
-        ]
-        items = _chat_messages_to_responses_input(messages)
-        msg_items = [i for i in items if i.get("type") == "message"]
-        assert len(msg_items) == 1
-        assert msg_items[0]["id"] == "msg_123"
-        assert msg_items[0]["phase"] == "final_answer"
-        assert msg_items[0]["content"][0]["text"] == "Hello world"
-
-    def test_fallback_to_plain_when_no_message_items(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openai-codex", api_mode="codex_responses",
-                            base_url="https://chatgpt.com/backend-api/codex")
-        messages = [{"role": "assistant", "content": "Hello world"}]
-        items = _chat_messages_to_responses_input(messages)
-        assert items == [{"role": "assistant", "content": "Hello world"}]
-
-    def test_skips_invalid_message_items(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openai-codex", api_mode="codex_responses",
-                            base_url="https://chatgpt.com/backend-api/codex")
-        messages = [
-            {
-                "role": "assistant",
-                "content": "fallback text",
-                "codex_message_items": [
-                    {"type": "function_call", "role": "assistant"},  # wrong type
-                    {"type": "message", "role": "user"},  # wrong role
-                    {"type": "message", "role": "assistant", "content": "not a list"},
-                ],
-            },
-        ]
-        items = _chat_messages_to_responses_input(messages)
-        # All invalid — falls back to plain text reconstruction
-        assert items == [{"role": "assistant", "content": "fallback text"}]
-
 
 # ── Chat completions response handling (OpenRouter/Nous) ─────────────────────
 

tests/run_agent/test_review_prompt_class_first.py

@@ -1,78 +0,0 @@
-"""Behavior tests for the class-first skill review prompts.
-
-The skill review / combined review prompts steer the background review agent
-toward generalizing existing skills rather than accumulating near-duplicates.
-These tests assert the behavioral *instructions* are present — they do NOT
-snapshot the full prompt text (change-detector).
-"""
-
-from run_agent import AIAgent
-
-
-def test_skill_review_prompt_instructs_survey_first():
-    """Prompt must tell the reviewer to list existing skills before deciding."""
-    prompt = AIAgent._SKILL_REVIEW_PROMPT
-    assert "skills_list" in prompt, "must instruct the reviewer to call skills_list"
-    assert "skill_view" in prompt, "must instruct the reviewer to skill_view candidates"
-    assert "SURVEY" in prompt, "must name the survey step explicitly"
-
-
-def test_skill_review_prompt_is_class_first():
-    """Prompt must steer toward the CLASS of task, not the specific task."""
-    prompt = AIAgent._SKILL_REVIEW_PROMPT
-    assert "CLASS" in prompt, "must tell the reviewer to think about the task class"
-    assert "class level" in prompt, "must anchor naming at the class level"
-
-
-def test_skill_review_prompt_prefers_updating_existing():
-    """Prompt must prefer generalizing an existing skill over creating a new one."""
-    prompt = AIAgent._SKILL_REVIEW_PROMPT
-    assert "PREFER GENERALIZING" in prompt or "PREFER UPDATING" in prompt, (
-        "must state the update-over-create preference"
-    )
-    assert "ONLY CREATE A NEW SKILL" in prompt, (
-        "must gate new-skill creation behind a last-resort clause"
-    )
-
-
-def test_skill_review_prompt_flags_overlap_for_followup():
-    """Prompt must ask the reviewer to note overlapping skills for future review."""
-    prompt = AIAgent._SKILL_REVIEW_PROMPT
-    assert "overlap" in prompt.lower(), "must mention the overlap-flagging protocol"
-
-
-def test_skill_review_prompt_preserves_opt_out_clause():
-    """The 'Nothing to save.' escape clause must remain."""
-    prompt = AIAgent._SKILL_REVIEW_PROMPT
-    assert "Nothing to save." in prompt
-
-
-def test_combined_review_prompt_keeps_memory_section():
-    """Combined prompt must still cover memory review."""
-    prompt = AIAgent._COMBINED_REVIEW_PROMPT
-    assert "**Memory**" in prompt
-    assert "memory tool" in prompt
-
-
-def test_combined_review_prompt_skills_section_is_class_first():
-    """The **Skills** half of the combined prompt must follow the same protocol."""
-    prompt = AIAgent._COMBINED_REVIEW_PROMPT
-    assert "**Skills**" in prompt
-    assert "SURVEY" in prompt
-    assert "CLASS" in prompt
-    assert "skills_list" in prompt
-    assert "ONLY CREATE A NEW SKILL" in prompt
-
-
-def test_combined_review_prompt_preserves_opt_out_clause():
-    prompt = AIAgent._COMBINED_REVIEW_PROMPT
-    assert "Nothing to save." in prompt
-
-
-def test_memory_review_prompt_unchanged_in_structure():
-    """Memory-only review prompt stays focused on user facts — not touched by this change."""
-    prompt = AIAgent._MEMORY_REVIEW_PROMPT
-    # Guardrails: the memory-only prompt must NOT mention skills/surveys.
-    assert "skills_list" not in prompt
-    assert "SURVEY" not in prompt
-    assert "memory tool" in prompt

tests/run_agent/test_run_agent.py

@@ -3386,61 +3386,6 @@ class TestMaxTokensParam:
         result = agent._max_tokens_param(4096)
         assert result == {"max_tokens": 4096}
 
-    def test_returns_max_completion_tokens_for_azure(self, agent):
-        """Azure OpenAI requires max_completion_tokens for gpt-5.x models."""
-        agent.base_url = "https://my-resource.openai.azure.com/openai/v1"
-        result = agent._max_tokens_param(4096)
-        assert result == {"max_completion_tokens": 4096}
-
-
-class TestAzureOpenAIRouting:
-    """Verify Azure OpenAI endpoints stay on chat_completions for gpt-5.x."""
-
-    def test_azure_gpt5_stays_on_chat_completions(self, agent):
-        """Azure serves gpt-5.x on /chat/completions — must not upgrade to codex_responses."""
-        agent.base_url = "https://my-resource.openai.azure.com/openai/v1"
-        agent.api_mode = "chat_completions"
-        agent.model = "gpt-5.4-mini"
-        # Mirror the routing logic from __init__
-        if (
-            agent.api_mode == "chat_completions"
-            and not agent._is_azure_openai_url()
-            and (
-                agent._is_direct_openai_url()
-                or agent._provider_model_requires_responses_api(
-                    agent.model, provider=agent.provider,
-                )
-            )
-        ):
-            agent.api_mode = "codex_responses"
-        assert agent.api_mode == "chat_completions"
-
-    def test_non_azure_gpt5_upgrades_to_codex_responses(self, agent):
-        """On api.openai.com, gpt-5.x must still upgrade to codex_responses."""
-        agent.base_url = "https://api.openai.com/v1"
-        agent.api_mode = "chat_completions"
-        agent.model = "gpt-5.4-mini"
-        if (
-            agent.api_mode == "chat_completions"
-            and not agent._is_azure_openai_url()
-            and (
-                agent._is_direct_openai_url()
-                or agent._provider_model_requires_responses_api(
-                    agent.model, provider=agent.provider,
-                )
-            )
-        ):
-            agent.api_mode = "codex_responses"
-        assert agent.api_mode == "codex_responses"
-
-    def test_is_azure_openai_url_detection(self, agent):
-        assert agent._is_azure_openai_url("https://foo.openai.azure.com/openai/v1") is True
-        assert agent._is_azure_openai_url("https://api.openai.com/v1") is False
-        assert agent._is_azure_openai_url("https://openrouter.ai/api/v1") is False
-        # Path-embedded azure string should still detect — we're ~substring matching
-        agent.base_url = "https://my-resource.openai.azure.com/openai/v1"
-        assert agent._is_azure_openai_url() is True
-
 
 # ---------------------------------------------------------------------------
 # System prompt stability for prompt caching

tests/run_agent/test_run_agent_codex_responses.py

@@ -943,33 +943,6 @@ def test_normalize_codex_response_marks_commentary_only_message_as_incomplete(mo
     assert "inspect the repository" in (assistant_message.content or "")
 
 
-def test_normalize_codex_response_preserves_message_status_for_replay(monkeypatch):
-    """Incomplete Codex output messages must not be replayed as completed."""
-    agent = _build_agent(monkeypatch)
-    from agent.codex_responses_adapter import _normalize_codex_response
-
-    response = SimpleNamespace(
-        output=[
-            SimpleNamespace(
-                type="message",
-                id="msg_partial",
-                phase="commentary",
-                status="in_progress",
-                content=[SimpleNamespace(type="output_text", text="Still working...")],
-            )
-        ],
-        usage=SimpleNamespace(input_tokens=4, output_tokens=2, total_tokens=6),
-        status="in_progress",
-        model="gpt-5-codex",
-    )
-
-    assistant_message, finish_reason = _normalize_codex_response(response)
-
-    assert finish_reason == "incomplete"
-    assert assistant_message.codex_message_items[0]["id"] == "msg_partial"
-    assert assistant_message.codex_message_items[0]["status"] == "in_progress"
-
-
 def test_normalize_codex_response_detects_leaked_tool_call_text(monkeypatch):
     """Harmony-style `to=functions.foo` leaked into assistant content with no
     structured function_call items must be treated as incomplete so the
@@ -1430,44 +1403,6 @@ def test_chat_messages_to_responses_input_reasoning_only_has_following_item(monk
     assert following.get("role") == "assistant"
 
 
-def test_codex_message_item_status_survives_conversion_and_preflight(monkeypatch):
-    """Stored Codex assistant message statuses must survive replay normalization."""
-    agent = _build_agent(monkeypatch)
-    from agent.codex_responses_adapter import (
-        _chat_messages_to_responses_input,
-        _preflight_codex_input_items,
-    )
-
-    items = _chat_messages_to_responses_input([
-        {
-            "role": "assistant",
-            "content": "partial",
-            "codex_message_items": [
-                {
-                    "type": "message",
-                    "role": "assistant",
-                    "status": "incomplete",
-                    "id": "msg_incomplete",
-                    "phase": "commentary",
-                    "content": [{"type": "output_text", "text": "partial"}],
-                }
-            ],
-        }
-    ])
-    replay_item = next(item for item in items if item.get("type") == "message")
-    assert replay_item["status"] == "incomplete"
-
-    normalized = _preflight_codex_input_items([
-        {
-            "type": "message",
-            "role": "assistant",
-            "status": "in_progress",
-            "content": [{"type": "output_text", "text": "working"}],
-        }
-    ])
-    assert normalized[0]["status"] == "in_progress"
-
-
 def test_duplicate_detection_distinguishes_different_codex_reasoning(monkeypatch):
     """Two consecutive reasoning-only responses with different encrypted content
     must NOT be treated as duplicates."""
@@ -1518,58 +1453,6 @@ def test_duplicate_detection_distinguishes_different_codex_reasoning(monkeypatch
     assert "enc_second" in encrypted_contents
 
 
-def test_duplicate_detection_distinguishes_different_codex_message_items(monkeypatch):
-    """Incomplete turns with new message ids/phases/statuses must not be collapsed."""
-    agent = _build_agent(monkeypatch)
-    responses = [
-        SimpleNamespace(
-            output=[
-                SimpleNamespace(
-                    type="message",
-                    id="msg_first",
-                    phase="commentary",
-                    status="in_progress",
-                    content=[SimpleNamespace(type="output_text", text="Still working...")],
-                )
-            ],
-            usage=SimpleNamespace(input_tokens=50, output_tokens=10, total_tokens=60),
-            status="in_progress",
-            model="gpt-5-codex",
-        ),
-        SimpleNamespace(
-            output=[
-                SimpleNamespace(
-                    type="message",
-                    id="msg_second",
-                    phase="commentary",
-                    status="in_progress",
-                    content=[SimpleNamespace(type="output_text", text="Still working...")],
-                )
-            ],
-            usage=SimpleNamespace(input_tokens=50, output_tokens=10, total_tokens=60),
-            status="in_progress",
-            model="gpt-5-codex",
-        ),
-        _codex_message_response("Final answer after progress updates."),
-    ]
-    monkeypatch.setattr(agent, "_interruptible_api_call", lambda api_kwargs: responses.pop(0))
-
-    result = agent.run_conversation("keep going")
-
-    assert result["completed"] is True
-    interim_msgs = [
-        msg for msg in result["messages"]
-        if msg.get("role") == "assistant"
-        and msg.get("finish_reason") == "incomplete"
-    ]
-    assert len(interim_msgs) == 2
-    assert [msg["codex_message_items"][0]["id"] for msg in interim_msgs] == [
-        "msg_first",
-        "msg_second",
-    ]
-    assert all(msg["codex_message_items"][0]["status"] == "in_progress" for msg in interim_msgs)
-
-
 def test_chat_messages_to_responses_input_deduplicates_reasoning_ids(monkeypatch):
     """Duplicate reasoning item IDs across multi-turn incomplete responses
     must be deduplicated so the Responses API doesn't reject with HTTP 400."""

tests/stress/README.md

@@ -1,41 +0,0 @@
-# Stress / battle-test suite
-
-Long-running tests that exercise the Kanban kernel under adversarial
-conditions. **Not run by `scripts/run_tests.sh`** because they can
-take 30+ seconds each and spawn real subprocesses.
-
-Run manually:
-
-```bash
-./venv/bin/python -m pytest tests/stress/ -v -s
-# or individual files:
-./venv/bin/python tests/stress/test_concurrency.py
-./venv/bin/python tests/stress/test_subprocess_e2e.py
-./venv/bin/python tests/stress/test_property_fuzzing.py
-./venv/bin/python tests/stress/test_benchmarks.py
-```
-
-## What's covered
-
-- **test_concurrency.py** — 5 workers, 100 tasks, race-for-claim. Asserts
-  no double-claims, no orphan runs, no SQLite errors escape retry.
-- **test_concurrency_mixed.py** — 10 workers + 1 reclaimer, 500 tasks,
-  random ops (claim/complete/block/unblock/archive). Same invariants
-  under adversarial scheduling.
-- **test_concurrency_reclaim_race.py** — TTL < work duration so the
-  reclaimer intentionally yanks tasks mid-work; verifies the worker's
-  late-complete is refused cleanly (CAS guard works).
-- **test_subprocess_e2e.py** — dispatcher spawns real Python subprocess
-  workers that heartbeat + complete via the CLI; crash detection
-  against a real dead PID.
-- **test_property_fuzzing.py** — 500 random operation sequences,
-  ~40k operations total, 9 invariant checks after each step.
-- **test_atypical_scenarios.py** — 28 scenarios covering atypical
-  user inputs: unicode/emoji/RTL, 1 MB strings, SQL injection
-  attempts, cycles, self-parents, wide fan-in/out, clock skew,
-  HERMES_HOME with spaces/unicode/symlinks, 1000 runs on one
-  task, idempotency-key race across processes, terminal-state
-  resurrection attempts, dashboard REST with weird JSON.
-- **test_benchmarks.py** — latency at 100/1k/10k tasks for dispatch,
-  recompute_ready, list_tasks, build_worker_context, etc. Results saved
-  to JSON for regression diffing.

tests/stress/_fake_worker.py

@@ -1,50 +0,0 @@
-#!/usr/bin/env python3
-"""Fake worker process that exercises the real subprocess contract.
-
-Reads HERMES_KANBAN_TASK from env, heartbeats periodically, does short
-work, completes via the CLI. Designed to be spawned by the dispatcher
-exactly the way `hermes chat -q` would be, minus the LLM cost.
-"""
-
-import json
-import os
-import subprocess
-import sys
-import time
-
-
-def main():
-    tid = os.environ["HERMES_KANBAN_TASK"]
-    workspace = os.environ.get("HERMES_KANBAN_WORKSPACE", "")
-
-    # Announce via CLI (goes through real argparse + init_db + etc)
-    subprocess.run(
-        ["hermes", "kanban", "heartbeat", tid, "--note", "started"],
-        check=True, capture_output=True,
-    )
-
-    # Simulate work with periodic heartbeats
-    for i in range(3):
-        time.sleep(0.3)
-        subprocess.run(
-            ["hermes", "kanban", "heartbeat", tid, "--note", f"progress {i+1}/3"],
-            check=True, capture_output=True,
-        )
-
-    # Complete with structured handoff
-    subprocess.run(
-        [
-            "hermes", "kanban", "complete", tid,
-            "--summary", f"real-subprocess worker finished {tid}",
-            "--metadata", json.dumps({
-                "workspace": workspace,
-                "worker_pid": os.getpid(),
-                "iterations": 3,
-            }),
-        ],
-        check=True, capture_output=True,
-    )
-
-
-if __name__ == "__main__":
-    main()

tests/stress/conftest.py

@@ -1,37 +0,0 @@
-"""pytest config for the stress/ subdirectory.
-
-These tests are slow (30s+), spawn subprocesses, and are not run by
-default. Enable via `pytest --run-stress` or by running the scripts
-directly.
-
-The scripts are primarily __main__-executable entry points; pytest
-isn't expected to collect individual test functions from them.
-"""
-import pytest
-
-
-def pytest_collection_modifyitems(config, items):
-    if config.getoption("--run-stress", default=False):
-        return
-    skip_stress = pytest.mark.skip(
-        reason="stress test (opt-in via --run-stress or run script directly)"
-    )
-    for item in items:
-        if "tests/stress" in str(item.fspath):
-            item.add_marker(skip_stress)
-
-
-def pytest_addoption(parser):
-    parser.addoption(
-        "--run-stress",
-        action="store_true",
-        default=False,
-        help="Run the stress/battle-test suite (slow, spawns subprocesses).",
-    )
-
-
-collect_ignore_glob = [
-    # The stress scripts have top-level code and hard-coded paths; they're
-    # meant to run as `python tests/stress/<name>.py`, not as pytest modules.
-    "*.py",
-]

tests/stress/test_benchmarks.py

@@ -1,221 +0,0 @@
-"""Scale benchmarks for the Kanban kernel.
-
-Measures:
-  - dispatch_once latency at 100, 1000, 10000 tasks
-  - recompute_ready latency at 100, 1000, 10000 todo tasks with wide parent graphs
-  - build_worker_context latency with 1, 10, 50 parent dependencies
-  - board list/stats query latency
-  - task_runs query latency at scale
-
-Results printed as a table. Saved to JSON for regression-diffing in CI
-or future reviews. Not a pass/fail test — records numbers so we know
-when a change regresses latency by 10x and can decide whether to care.
-"""
-
-import json
-import os
-import random
-import sys
-import tempfile
-import time
-from pathlib import Path
-
-WT = str(Path(__file__).resolve().parents[2])
-
-
-def bench(label, fn, iterations=5):
-    """Time fn over `iterations` runs, return (min, median, max) in ms."""
-    times = []
-    for _ in range(iterations):
-        t0 = time.perf_counter()
-        fn()
-        times.append((time.perf_counter() - t0) * 1000)
-    times.sort()
-    mn = times[0]
-    md = times[len(times) // 2]
-    mx = times[-1]
-    return {"label": label, "iter": iterations, "min_ms": mn, "median_ms": md, "max_ms": mx}
-
-
-def seed_tasks(conn, kb, n, assignee="bench-worker", with_parents=False):
-    """Seed n tasks. Optionally give each task 5 parents."""
-    ids = []
-    for i in range(n):
-        if with_parents and i >= 5:
-            parents = random.sample(ids[:i], 5)
-        else:
-            parents = ()
-        tid = kb.create_task(
-            conn, title=f"bench {i}", assignee=assignee,
-            tenant="bench", parents=parents,
-        )
-        ids.append(tid)
-    return ids
-
-
-def main():
-    home = tempfile.mkdtemp(prefix="hermes_bench_")
-    os.environ["HERMES_HOME"] = home
-    os.environ["HOME"] = home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    kb.init_db()
-
-    results = []
-
-    # ============ dispatch_once latency ============
-    for n in [100, 1000, 10000]:
-        print(f"\n== dispatch_once @ {n} tasks ==")
-        # Fresh DB each time so we're not measuring cumulative effects
-        import shutil
-        shutil.rmtree(home, ignore_errors=True)
-        os.makedirs(home)
-        kb._INITIALIZED_PATHS.clear()
-        kb.init_db()
-        conn = kb.connect()
-        seed_tasks(conn, kb, n, assignee=None)  # no assignee → won't spawn
-        r = bench(
-            f"dispatch_once (n={n}, no spawn)",
-            lambda: kb.dispatch_once(conn, spawn_fn=lambda *_: None),
-            iterations=5,
-        )
-        print(f"  min={r['min_ms']:.1f} median={r['median_ms']:.1f} max={r['max_ms']:.1f} ms")
-        r["n"] = n
-        results.append(r)
-        conn.close()
-
-    # ============ recompute_ready at scale with parent graphs ============
-    for n in [100, 1000, 10000]:
-        print(f"\n== recompute_ready @ {n} tasks (5 parents each) ==")
-        shutil.rmtree(home, ignore_errors=True)
-        os.makedirs(home)
-        kb._INITIALIZED_PATHS.clear()
-        kb.init_db()
-        conn = kb.connect()
-        ids = seed_tasks(conn, kb, n, assignee=None, with_parents=True)
-        # Complete the first 100 so some todo tasks might get promoted
-        for tid in ids[:min(100, n // 10)]:
-            kb.complete_task(conn, tid, result="bench")
-        r = bench(
-            f"recompute_ready (n={n}, with parents)",
-            lambda: kb.recompute_ready(conn),
-            iterations=5,
-        )
-        print(f"  min={r['min_ms']:.1f} median={r['median_ms']:.1f} max={r['max_ms']:.1f} ms")
-        r["n"] = n
-        results.append(r)
-        conn.close()
-
-    # ============ build_worker_context with N parents ============
-    for parent_count in [1, 10, 50]:
-        print(f"\n== build_worker_context with {parent_count} parents ==")
-        shutil.rmtree(home, ignore_errors=True)
-        os.makedirs(home)
-        kb._INITIALIZED_PATHS.clear()
-        kb.init_db()
-        conn = kb.connect()
-        # Create parents, complete them with summaries+metadata
-        parent_ids = []
-        for i in range(parent_count):
-            pid = kb.create_task(conn, title=f"parent {i}", assignee="p")
-            kb.claim_task(conn, pid)
-            kb.complete_task(
-                conn, pid,
-                summary=f"parent {i} result that is longer than a single token "
-                        f"so we actually measure the IO",
-                metadata={"files": [f"file_{j}.py" for j in range(5)], "i": i},
-            )
-            parent_ids.append(pid)
-        child_id = kb.create_task(
-            conn, title="child", assignee="c", parents=parent_ids,
-        )
-        r = bench(
-            f"build_worker_context (parents={parent_count})",
-            lambda: kb.build_worker_context(conn, child_id),
-            iterations=10,
-        )
-        print(f"  min={r['min_ms']:.1f} median={r['median_ms']:.1f} max={r['max_ms']:.1f} ms")
-        r["parent_count"] = parent_count
-        results.append(r)
-        conn.close()
-
-    # ============ list_tasks at scale ============
-    for n in [100, 1000, 10000]:
-        print(f"\n== list_tasks @ {n} ==")
-        shutil.rmtree(home, ignore_errors=True)
-        os.makedirs(home)
-        kb._INITIALIZED_PATHS.clear()
-        kb.init_db()
-        conn = kb.connect()
-        seed_tasks(conn, kb, n)
-        r = bench(
-            f"list_tasks (n={n})",
-            lambda: kb.list_tasks(conn),
-            iterations=5,
-        )
-        print(f"  min={r['min_ms']:.1f} median={r['median_ms']:.1f} max={r['max_ms']:.1f} ms")
-        r["n"] = n
-        results.append(r)
-        conn.close()
-
-    # ============ board_stats at scale ============
-    for n in [100, 1000, 10000]:
-        print(f"\n== board_stats @ {n} ==")
-        shutil.rmtree(home, ignore_errors=True)
-        os.makedirs(home)
-        kb._INITIALIZED_PATHS.clear()
-        kb.init_db()
-        conn = kb.connect()
-        seed_tasks(conn, kb, n)
-        r = bench(
-            f"board_stats (n={n})",
-            lambda: kb.board_stats(conn),
-            iterations=5,
-        )
-        print(f"  min={r['min_ms']:.1f} median={r['median_ms']:.1f} max={r['max_ms']:.1f} ms")
-        r["n"] = n
-        results.append(r)
-        conn.close()
-
-    # ============ list_runs at scale ============
-    for n in [100, 1000]:
-        print(f"\n== list_runs for task with {n} attempts ==")
-        shutil.rmtree(home, ignore_errors=True)
-        os.makedirs(home)
-        kb._INITIALIZED_PATHS.clear()
-        kb.init_db()
-        conn = kb.connect()
-        tid = kb.create_task(conn, title="x", assignee="w")
-        # Create N attempts via claim/release
-        for i in range(n):
-            kb.claim_task(conn, tid, ttl_seconds=0)
-            kb.release_stale_claims(conn)
-        r = bench(
-            f"list_runs (runs={n})",
-            lambda: kb.list_runs(conn, tid),
-            iterations=10,
-        )
-        print(f"  min={r['min_ms']:.1f} median={r['median_ms']:.1f} max={r['max_ms']:.1f} ms")
-        r["run_count"] = n
-        results.append(r)
-        conn.close()
-
-    # ============ SUMMARY TABLE ============
-    print()
-    print("=" * 60)
-    print("SUMMARY")
-    print("=" * 60)
-    print(f"{'Benchmark':<50} {'min':>8} {'median':>8} {'max':>8}")
-    for r in results:
-        print(f"{r['label']:<50} {r['min_ms']:>7.1f}ms {r['median_ms']:>7.1f}ms {r['max_ms']:>7.1f}ms")
-
-    # Save for future diffing.
-    out_path = "/tmp/kanban_bench_results.json"
-    with open(out_path, "w") as f:
-        json.dump(results, f, indent=2)
-    print(f"\nResults saved to {out_path}")
-
-
-if __name__ == "__main__":
-    main()

tests/stress/test_concurrency.py

@@ -1,302 +0,0 @@
-"""Multi-process concurrency stress test for the Kanban kernel.
-
-5 worker processes race for claims on a shared DB with 100 tasks. Each
-worker loops: claim -> simulate work -> complete. Asserts the invariants
-that make the system worth building:
-
-  - No task claimed by two workers simultaneously
-  - No task completed twice
-  - Every claim produces exactly one run row
-  - Every completion closes exactly one run row
-  - Zero SQLite locking errors that escape the retry layer
-  - Total run count == total claim events == total completed events
-
-This test is the primary justification for WAL + CAS-based claim. If it
-passes, the architecture holds. If it fails, we have a real bug to fix
-before anyone runs this in anger.
-"""
-
-import json
-import multiprocessing as mp
-import os
-import random
-import sqlite3
-import subprocess
-import sys
-import tempfile
-import time
-from pathlib import Path
-
-
-NUM_WORKERS = 5
-NUM_TASKS = 100
-WORKER_TIMEOUT_S = 60
-WT = str(Path(__file__).resolve().parents[2])
-
-
-def worker_loop(worker_id: int, hermes_home: str, result_file: str) -> None:
-    """One worker's inner loop. Runs in a fresh Python process.
-
-    Tries to claim a ready task, marks it done with a per-worker summary,
-    repeats until the ready pool is empty. Records every claim + complete
-    into its own JSON result file for later aggregation.
-    """
-    os.environ["HERMES_HOME"] = hermes_home
-    os.environ["HOME"] = hermes_home
-    sys.path.insert(0, WT)
-
-    from hermes_cli import kanban_db as kb
-
-    events = []
-    empty_polls = 0
-    start = time.monotonic()
-
-    while time.monotonic() - start < WORKER_TIMEOUT_S:
-        conn = kb.connect()
-        try:
-            # Find any ready task (non-deterministic order intentional — we
-            # want workers to race on popular assignees).
-            row = conn.execute(
-                "SELECT id FROM tasks WHERE status = 'ready' "
-                "AND claim_lock IS NULL LIMIT 1"
-            ).fetchone()
-            if row is None:
-                empty_polls += 1
-                if empty_polls > 20:
-                    break  # queue empty long enough, stop
-                time.sleep(0.01)
-                continue
-            empty_polls = 0
-
-            tid = row["id"]
-            try:
-                claimed = kb.claim_task(
-                    conn, tid, claimer=f"worker-{worker_id}",
-                )
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err_on_claim", "task": tid, "err": str(e)})
-                continue
-            if claimed is None:
-                # Someone else beat us — expected contention, not an error.
-                events.append({"kind": "lost_claim_race", "task": tid})
-                continue
-
-            run = kb.latest_run(conn, tid)
-            events.append({
-                "kind": "claimed",
-                "task": tid,
-                "worker": worker_id,
-                "run_id": run.id,
-                "t": time.monotonic() - start,
-            })
-
-            # Simulate short, variable work
-            time.sleep(random.uniform(0.001, 0.05))
-
-            try:
-                kb.complete_task(
-                    conn, tid,
-                    result=f"done by worker-{worker_id}",
-                    summary=f"worker-{worker_id} finished task {tid}",
-                    metadata={"worker_id": worker_id, "run_id": run.id},
-                )
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err_on_complete", "task": tid, "err": str(e)})
-                continue
-            events.append({
-                "kind": "completed",
-                "task": tid,
-                "worker": worker_id,
-                "run_id": run.id,
-                "t": time.monotonic() - start,
-            })
-        finally:
-            conn.close()
-
-    with open(result_file, "w") as f:
-        json.dump(events, f)
-
-
-def main():
-    home = tempfile.mkdtemp(prefix="hermes_concurrency_")
-    print(f"HERMES_HOME = {home}")
-
-    # Seed.
-    os.environ["HERMES_HOME"] = home
-    os.environ["HOME"] = home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    kb.init_db()
-    conn = kb.connect()
-    tids = []
-    for i in range(NUM_TASKS):
-        tid = kb.create_task(
-            conn, title=f"task #{i}", assignee="shared",
-            tenant="concurrency-test",
-        )
-        tids.append(tid)
-    conn.close()
-    print(f"Seeded {NUM_TASKS} tasks.")
-
-    # Spawn workers.
-    ctx = mp.get_context("spawn")
-    result_files = [f"/tmp/concurrency_worker_{i}.json" for i in range(NUM_WORKERS)]
-    procs = []
-    start = time.monotonic()
-    for i in range(NUM_WORKERS):
-        p = ctx.Process(target=worker_loop, args=(i, home, result_files[i]))
-        p.start()
-        procs.append(p)
-
-    for p in procs:
-        p.join(timeout=WORKER_TIMEOUT_S + 30)
-        if p.is_alive():
-            p.terminate()
-            p.join()
-
-    elapsed = time.monotonic() - start
-    print(f"All workers done in {elapsed:.1f}s")
-
-    # Aggregate worker events.
-    all_events = []
-    for i, f in enumerate(result_files):
-        if not os.path.isfile(f):
-            print(f"  WORKER {i} produced no result file — died?")
-            continue
-        with open(f) as fh:
-            events = json.load(fh)
-        all_events.extend(events)
-
-    # ============ INVARIANT CHECKS ============
-    print()
-    print("=" * 60)
-    print("INVARIANT CHECKS")
-    print("=" * 60)
-
-    failures = []
-
-    # Check 1: no task claimed by two different workers
-    claims_by_task = {}
-    for e in all_events:
-        if e["kind"] == "claimed":
-            if e["task"] in claims_by_task:
-                prev = claims_by_task[e["task"]]
-                if prev["worker"] != e["worker"]:
-                    failures.append(
-                        f"DOUBLE CLAIM: task {e['task']} claimed by "
-                        f"worker {prev['worker']} AND worker {e['worker']}"
-                    )
-            claims_by_task[e["task"]] = e
-
-    # Check 2: every completion has a matching claim from the same worker
-    for e in all_events:
-        if e["kind"] == "completed":
-            prev_claim = claims_by_task.get(e["task"])
-            if prev_claim is None:
-                failures.append(f"COMPLETION WITHOUT CLAIM: task {e['task']}")
-            elif prev_claim["worker"] != e["worker"]:
-                failures.append(
-                    f"WORKER MISMATCH: task {e['task']} claimed by "
-                    f"{prev_claim['worker']} but completed by {e['worker']}"
-                )
-
-    # Check 3: DB state — every task should be in 'done', no dangling claims
-    conn = kb.connect()
-    try:
-        bad_status = conn.execute(
-            "SELECT id, status, claim_lock, current_run_id FROM tasks "
-            "WHERE status != 'done' OR claim_lock IS NOT NULL "
-            "OR current_run_id IS NOT NULL"
-        ).fetchall()
-        if bad_status:
-            for row in bad_status:
-                failures.append(
-                    f"BAD FINAL STATE: task {row['id']} status={row['status']} "
-                    f"claim_lock={row['claim_lock']} current_run_id={row['current_run_id']}"
-                )
-
-        # Check 4: exactly one run per task, all closed as completed
-        bad_runs = conn.execute(
-            "SELECT task_id, COUNT(*) as n FROM task_runs "
-            "GROUP BY task_id HAVING n != 1"
-        ).fetchall()
-        if bad_runs:
-            for row in bad_runs:
-                failures.append(
-                    f"WRONG RUN COUNT: task {row['task_id']} has {row['n']} runs (expected 1)"
-                )
-
-        open_runs = conn.execute(
-            "SELECT id, task_id FROM task_runs WHERE ended_at IS NULL"
-        ).fetchall()
-        for row in open_runs:
-            failures.append(f"OPEN RUN: run {row['id']} on task {row['task_id']}")
-
-        wrong_outcomes = conn.execute(
-            "SELECT task_id, outcome FROM task_runs "
-            "WHERE outcome IS NULL OR outcome != 'completed'"
-        ).fetchall()
-        for row in wrong_outcomes:
-            failures.append(
-                f"WRONG OUTCOME: task {row['task_id']} run outcome={row['outcome']}"
-            )
-
-        # Check 5: event counts — exactly NUM_TASKS completed events
-        completed_events = conn.execute(
-            "SELECT COUNT(*) as n FROM task_events WHERE kind='completed'"
-        ).fetchone()["n"]
-        if completed_events != NUM_TASKS:
-            failures.append(
-                f"EVENT COUNT MISMATCH: {completed_events} completed events "
-                f"expected {NUM_TASKS}"
-            )
-
-        # Check 6: count SQLite errors that escaped retry
-        sqlite_errs = sum(
-            1 for e in all_events if e["kind"].startswith("sqlite_err")
-        )
-        if sqlite_errs > 0:
-            failures.append(f"UNRETRIED SQLITE ERRORS: {sqlite_errs}")
-
-    finally:
-        conn.close()
-
-    # ============ STATS ============
-    print()
-    total_claims = sum(1 for e in all_events if e["kind"] == "claimed")
-    total_completes = sum(1 for e in all_events if e["kind"] == "completed")
-    total_lost_races = sum(1 for e in all_events if e["kind"] == "lost_claim_race")
-
-    per_worker = {}
-    for e in all_events:
-        if e["kind"] == "completed":
-            per_worker.setdefault(e["worker"], 0)
-            per_worker[e["worker"]] += 1
-
-    print(f"Total claims:      {total_claims}")
-    print(f"Total completes:   {total_completes}")
-    print(f"Lost claim races:  {total_lost_races}  (expected contention; not a bug)")
-    print(f"Elapsed:           {elapsed:.2f}s")
-    print(f"Throughput:        {NUM_TASKS/elapsed:.1f} tasks/sec")
-    print(f"Per-worker completions:")
-    for w in sorted(per_worker.keys()):
-        print(f"  worker-{w}: {per_worker[w]}")
-
-    if failures:
-        print()
-        print("=" * 60)
-        print(f"FAILURES ({len(failures)}):")
-        print("=" * 60)
-        for f in failures[:20]:
-            print(f"  {f}")
-        if len(failures) > 20:
-            print(f"  ... and {len(failures) - 20} more")
-        sys.exit(1)
-    else:
-        print()
-        print("✔ ALL INVARIANTS HELD")
-
-
-if __name__ == "__main__":
-    main()

tests/stress/test_concurrency_mixed.py

@@ -1,350 +0,0 @@
-"""Harder concurrency stress: mixed operations + larger scale.
-
-Scales to 500 tasks, 10 workers, 60s runtime. Each worker randomly:
-  - claims + completes (70%)
-  - claims + blocks with a reason (15%)
-  - unblocks a random blocked task (10%)
-  - archives a random done task (5%)
-
-Adds a background "dispatcher" process that calls release_stale_claims
-and detect_crashed_workers every 200ms, racing against the workers to
-surface TTL + crash detection races.
-
-Pass criteria: runs invariant holds, no double-completions, no orphan
-runs, no SQLite errors escape the retry layer.
-"""
-
-import json
-import multiprocessing as mp
-import os
-import random
-import sqlite3
-import sys
-import tempfile
-import time
-from pathlib import Path
-
-NUM_WORKERS = 10
-NUM_TASKS = 500
-RUN_DURATION_S = 30
-WT = str(Path(__file__).resolve().parents[2])
-
-
-def worker_loop(worker_id: int, hermes_home: str, result_file: str) -> None:
-    os.environ["HERMES_HOME"] = hermes_home
-    os.environ["HOME"] = hermes_home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    events = []
-    start = time.monotonic()
-    idle_rounds = 0
-
-    while time.monotonic() - start < RUN_DURATION_S:
-        conn = kb.connect()
-        try:
-            op = random.random()
-
-            if op < 0.10:
-                # Try to unblock a blocked task.
-                row = conn.execute(
-                    "SELECT id FROM tasks WHERE status='blocked' "
-                    "ORDER BY RANDOM() LIMIT 1"
-                ).fetchone()
-                if row:
-                    try:
-                        ok = kb.unblock_task(conn, row["id"])
-                        events.append({"kind": "unblocked" if ok else "unblock_noop",
-                                       "task": row["id"], "worker": worker_id})
-                    except sqlite3.OperationalError as e:
-                        events.append({"kind": "sqlite_err", "op": "unblock",
-                                       "task": row["id"], "err": str(e)[:100]})
-                continue
-
-            if op < 0.15:
-                # Try to archive a done task.
-                row = conn.execute(
-                    "SELECT id FROM tasks WHERE status='done' "
-                    "ORDER BY RANDOM() LIMIT 1"
-                ).fetchone()
-                if row:
-                    try:
-                        kb.archive_task(conn, row["id"])
-                        events.append({"kind": "archived", "task": row["id"],
-                                       "worker": worker_id})
-                    except sqlite3.OperationalError as e:
-                        events.append({"kind": "sqlite_err", "op": "archive",
-                                       "task": row["id"], "err": str(e)[:100]})
-                continue
-
-            # Default: claim + complete-or-block.
-            row = conn.execute(
-                "SELECT id FROM tasks WHERE status='ready' "
-                "AND claim_lock IS NULL LIMIT 1"
-            ).fetchone()
-            if row is None:
-                idle_rounds += 1
-                if idle_rounds > 50:
-                    break
-                time.sleep(0.02)
-                continue
-            idle_rounds = 0
-
-            tid = row["id"]
-            try:
-                claimed = kb.claim_task(
-                    conn, tid, claimer=f"worker-{worker_id}",
-                    ttl_seconds=5,  # short TTL so reclaim races in
-                )
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err", "op": "claim",
-                               "task": tid, "err": str(e)[:100]})
-                continue
-            if claimed is None:
-                events.append({"kind": "lost_claim_race", "task": tid})
-                continue
-
-            run = kb.latest_run(conn, tid)
-            events.append({"kind": "claimed", "task": tid, "worker": worker_id,
-                           "run_id": run.id, "t": time.monotonic() - start})
-
-            time.sleep(random.uniform(0.005, 0.05))
-
-            # 20% of the time, block instead of complete
-            if random.random() < 0.20:
-                try:
-                    kb.block_task(conn, tid,
-                                  reason=f"blocked by worker-{worker_id}")
-                    events.append({"kind": "blocked", "task": tid,
-                                   "worker": worker_id, "run_id": run.id})
-                except sqlite3.OperationalError as e:
-                    events.append({"kind": "sqlite_err", "op": "block",
-                                   "task": tid, "err": str(e)[:100]})
-            else:
-                try:
-                    kb.complete_task(
-                        conn, tid,
-                        result=f"done by worker-{worker_id}",
-                        summary=f"worker-{worker_id} ok",
-                        metadata={"worker_id": worker_id},
-                    )
-                    events.append({"kind": "completed", "task": tid,
-                                   "worker": worker_id, "run_id": run.id,
-                                   "t": time.monotonic() - start})
-                except sqlite3.OperationalError as e:
-                    events.append({"kind": "sqlite_err", "op": "complete",
-                                   "task": tid, "err": str(e)[:100]})
-        finally:
-            conn.close()
-
-    with open(result_file, "w") as f:
-        json.dump(events, f)
-
-
-def reclaimer_loop(hermes_home: str, result_file: str) -> None:
-    """Background dispatcher-like loop that reclaims stale tasks."""
-    os.environ["HERMES_HOME"] = hermes_home
-    os.environ["HOME"] = hermes_home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    events = []
-    start = time.monotonic()
-    while time.monotonic() - start < RUN_DURATION_S + 2:
-        conn = kb.connect()
-        try:
-            try:
-                reclaimed = kb.release_stale_claims(conn)
-                if reclaimed:
-                    events.append({"kind": "reclaimed", "count": reclaimed,
-                                   "t": time.monotonic() - start})
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err", "op": "reclaim",
-                               "err": str(e)[:100]})
-        finally:
-            conn.close()
-        time.sleep(0.2)
-
-    with open(result_file, "w") as f:
-        json.dump(events, f)
-
-
-def main():
-    home = tempfile.mkdtemp(prefix="hermes_mixed_stress_")
-    print(f"HERMES_HOME = {home}")
-
-    os.environ["HERMES_HOME"] = home
-    os.environ["HOME"] = home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    kb.init_db()
-    conn = kb.connect()
-    for i in range(NUM_TASKS):
-        kb.create_task(
-            conn, title=f"t#{i}", assignee="shared", tenant="mixed-stress",
-        )
-    conn.close()
-    print(f"Seeded {NUM_TASKS} tasks, launching {NUM_WORKERS} workers + 1 reclaimer")
-
-    ctx = mp.get_context("spawn")
-    worker_results = [f"/tmp/mixed_worker_{i}.json" for i in range(NUM_WORKERS)]
-    reclaim_result = "/tmp/mixed_reclaim.json"
-
-    procs = []
-    start = time.monotonic()
-    for i in range(NUM_WORKERS):
-        p = ctx.Process(target=worker_loop, args=(i, home, worker_results[i]))
-        p.start()
-        procs.append(p)
-    r = ctx.Process(target=reclaimer_loop, args=(home, reclaim_result))
-    r.start()
-    procs.append(r)
-
-    for p in procs:
-        p.join(timeout=RUN_DURATION_S + 30)
-        if p.is_alive():
-            p.terminate()
-            p.join()
-
-    elapsed = time.monotonic() - start
-    print(f"Done in {elapsed:.1f}s")
-
-    # Aggregate.
-    all_events = []
-    for i, f in enumerate(worker_results):
-        if os.path.isfile(f):
-            with open(f) as fh:
-                all_events.extend(json.load(fh))
-        else:
-            print(f"  WORKER {i} died with no result file!")
-    reclaim_events = []
-    if os.path.isfile(reclaim_result):
-        with open(reclaim_result) as fh:
-            reclaim_events = json.load(fh)
-
-    # ============ INVARIANT CHECKS ============
-    print()
-    print("=" * 60)
-    print("INVARIANT CHECKS")
-    print("=" * 60)
-
-    failures = []
-
-    # Per-run attribution tracking
-    claims = [e for e in all_events if e["kind"] == "claimed"]
-    completions = [e for e in all_events if e["kind"] == "completed"]
-    blocks = [e for e in all_events if e["kind"] == "blocked"]
-
-    # Every completion must have a matching claim on the same run_id AND
-    # the same worker (workers don't steal each other's runs).
-    claims_by_run = {c["run_id"]: c for c in claims}
-    for comp in completions:
-        claim = claims_by_run.get(comp["run_id"])
-        if claim is None:
-            # It's possible this worker saw a reclaimed run from another worker
-            # — that's still a bug: the worker shouldn't be able to complete
-            # a run it didn't claim. But let me check if reclaim happened first.
-            failures.append(
-                f"COMPLETION WITHOUT CLAIM: task {comp['task']} run {comp['run_id']} "
-                f"by worker {comp['worker']}"
-            )
-        elif claim["worker"] != comp["worker"]:
-            failures.append(
-                f"CROSS-WORKER COMPLETION: run {comp['run_id']} claimed by "
-                f"worker {claim['worker']} but completed by worker {comp['worker']}"
-            )
-
-    # SQLite errors that escaped the retry layer
-    sqlite_errs = [e for e in all_events if e["kind"] == "sqlite_err"]
-    if sqlite_errs:
-        for e in sqlite_errs[:5]:
-            failures.append(f"SQLITE ERROR: op={e.get('op')} err={e.get('err')}")
-        if len(sqlite_errs) > 5:
-            failures.append(f"  ... and {len(sqlite_errs) - 5} more sqlite errs")
-
-    # DB final state — every task should be in a clean terminal state.
-    conn = kb.connect()
-    try:
-        # Invariant: current_run_id NULL iff latest run is terminal
-        inconsistent = conn.execute("""
-            SELECT t.id, t.status, t.current_run_id
-            FROM tasks t
-            WHERE t.current_run_id IS NOT NULL
-              AND EXISTS (SELECT 1 FROM task_runs r
-                          WHERE r.id = t.current_run_id AND r.ended_at IS NOT NULL)
-        """).fetchall()
-        for row in inconsistent:
-            failures.append(
-                f"INVARIANT VIOLATION: task {row['id']} status={row['status']} "
-                f"has current_run_id={row['current_run_id']} but run is ended"
-            )
-
-        # Invariant: no orphan open runs
-        orphans = conn.execute("""
-            SELECT r.id, r.task_id, r.status
-            FROM task_runs r
-            LEFT JOIN tasks t ON t.current_run_id = r.id
-            WHERE r.ended_at IS NULL AND t.id IS NULL
-        """).fetchall()
-        for row in orphans:
-            failures.append(
-                f"ORPHAN OPEN RUN: run {row['id']} on task {row['task_id']}"
-            )
-
-        # Counts — should roughly balance.
-        status_counts = dict(
-            conn.execute("SELECT status, COUNT(*) FROM tasks GROUP BY status").fetchall()
-        )
-        run_outcome_counts = dict(
-            conn.execute(
-                "SELECT outcome, COUNT(*) FROM task_runs "
-                "WHERE ended_at IS NOT NULL GROUP BY outcome"
-            ).fetchall()
-        )
-        active_runs = conn.execute(
-            "SELECT COUNT(*) FROM task_runs WHERE ended_at IS NULL"
-        ).fetchone()[0]
-
-    finally:
-        conn.close()
-
-    # ============ STATS ============
-    print()
-    print(f"Workers: {NUM_WORKERS}, Tasks: {NUM_TASKS}")
-    print(f"Elapsed: {elapsed:.1f}s")
-    print(f"Events collected: {len(all_events)} (+{len(reclaim_events)} reclaim)")
-    print()
-    print("Operations:")
-    op_counts = {}
-    for e in all_events:
-        op_counts[e["kind"]] = op_counts.get(e["kind"], 0) + 1
-    for k in sorted(op_counts.keys()):
-        print(f"  {k:<25} {op_counts[k]}")
-
-    print()
-    print("Final task status:")
-    for s, n in sorted(status_counts.items()):
-        print(f"  {s:<10} {n}")
-    print("Final run outcomes:")
-    for o, n in sorted(run_outcome_counts.items(), key=lambda x: (x[0] or '',)):
-        print(f"  {o:<12} {n}")
-    print(f"  active       {active_runs}")
-
-    if failures:
-        print()
-        print("=" * 60)
-        print(f"FAILURES ({len(failures)}):")
-        print("=" * 60)
-        for f in failures[:30]:
-            print(f"  {f}")
-        if len(failures) > 30:
-            print(f"  ... and {len(failures) - 30} more")
-        sys.exit(1)
-    else:
-        print()
-        print("✔ ALL INVARIANTS HELD UNDER MIXED STRESS")
-
-
-if __name__ == "__main__":
-    main()

tests/stress/test_concurrency_reclaim_race.py

@@ -1,241 +0,0 @@
-"""Target the reclaim race specifically.
-
-Workers claim tasks with a 1s TTL but sleep 2s before completing. The
-reclaimer runs every 200ms. Scenario: worker claims, reclaimer expires
-the claim mid-work, worker tries to complete AFTER its run has been
-reclaimed.
-
-Expected behavior (per design): the worker's complete_task should
-either succeed on the reclaimed-and-re-claimed-by-another-worker case
-(no, it should refuse — the claim was invalidated), OR succeed by
-grace (we "forgive" a late complete from the original worker if no
-one else picked it up).
-
-Actually looking at complete_task: it doesn't check claim_lock. It just
-transitions from 'running' -> 'done'. So if the reclaimer moved it back
-to 'ready', the late worker's complete_task will fail (CAS on
-status='running' fails). This is the CORRECT behavior.
-
-Invariant being tested: race between worker.complete and
-dispatcher.reclaim must not produce a double-run-close or other
-inconsistency.
-"""
-
-import json
-import multiprocessing as mp
-import os
-import random
-import sqlite3
-import sys
-import tempfile
-import time
-from pathlib import Path
-
-NUM_WORKERS = 5
-NUM_TASKS = 50
-TTL = 1
-WORK_DURATION_S = 2.0  # longer than TTL => reclaimer wins
-WT = str(Path(__file__).resolve().parents[2])
-
-
-def worker_loop(worker_id: int, hermes_home: str, result_file: str) -> None:
-    os.environ["HERMES_HOME"] = hermes_home
-    os.environ["HOME"] = hermes_home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    events = []
-    start = time.monotonic()
-    idle = 0
-
-    while time.monotonic() - start < 40:
-        conn = kb.connect()
-        try:
-            row = conn.execute(
-                "SELECT id FROM tasks WHERE status='ready' AND claim_lock IS NULL LIMIT 1"
-            ).fetchone()
-            if row is None:
-                idle += 1
-                if idle > 30:
-                    break
-                time.sleep(0.05)
-                continue
-            idle = 0
-            tid = row["id"]
-            try:
-                claimed = kb.claim_task(conn, tid, claimer=f"worker-{worker_id}",
-                                        ttl_seconds=TTL)
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err", "op": "claim", "err": str(e)[:100]})
-                continue
-            if claimed is None:
-                events.append({"kind": "lost_claim", "task": tid})
-                continue
-            run = kb.latest_run(conn, tid)
-            events.append({"kind": "claimed", "task": tid, "worker": worker_id,
-                           "run_id": run.id})
-
-            # Sleep longer than TTL so reclaimer has a chance to intervene
-            time.sleep(WORK_DURATION_S + random.uniform(-0.3, 0.3))
-
-            try:
-                ok = kb.complete_task(
-                    conn, tid,
-                    result=f"by worker-{worker_id}",
-                    summary=f"worker-{worker_id} finished",
-                )
-                events.append({"kind": "complete_ok" if ok else "complete_refused",
-                               "task": tid, "worker": worker_id, "run_id": run.id})
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err", "op": "complete", "err": str(e)[:100]})
-        finally:
-            conn.close()
-
-    with open(result_file, "w") as f:
-        json.dump(events, f)
-
-
-def reclaimer_loop(hermes_home: str, result_file: str) -> None:
-    os.environ["HERMES_HOME"] = hermes_home
-    os.environ["HOME"] = hermes_home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    events = []
-    start = time.monotonic()
-    while time.monotonic() - start < 42:
-        conn = kb.connect()
-        try:
-            try:
-                n = kb.release_stale_claims(conn)
-                if n:
-                    events.append({"kind": "reclaimed", "count": n,
-                                   "t": time.monotonic() - start})
-            except sqlite3.OperationalError as e:
-                events.append({"kind": "sqlite_err", "err": str(e)[:100]})
-        finally:
-            conn.close()
-        time.sleep(0.2)
-    with open(result_file, "w") as f:
-        json.dump(events, f)
-
-
-def main():
-    home = tempfile.mkdtemp(prefix="hermes_reclaim_race_")
-    os.environ["HERMES_HOME"] = home
-    os.environ["HOME"] = home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    kb.init_db()
-    conn = kb.connect()
-    for i in range(NUM_TASKS):
-        kb.create_task(conn, title=f"t{i}", assignee="shared",
-                       tenant="reclaim-race")
-    conn.close()
-    print(f"Seeded {NUM_TASKS} tasks. TTL={TTL}s, work_duration={WORK_DURATION_S}s")
-    print(f"(worker work > TTL guarantees reclaims)")
-
-    ctx = mp.get_context("spawn")
-    worker_results = [f"/tmp/rc_worker_{i}.json" for i in range(NUM_WORKERS)]
-    reclaim_result = "/tmp/rc_reclaim.json"
-    procs = []
-    for i in range(NUM_WORKERS):
-        p = ctx.Process(target=worker_loop, args=(i, home, worker_results[i]))
-        p.start()
-        procs.append(p)
-    r = ctx.Process(target=reclaimer_loop, args=(home, reclaim_result))
-    r.start()
-    procs.append(r)
-
-    for p in procs:
-        p.join(timeout=60)
-        if p.is_alive():
-            p.terminate()
-            p.join()
-
-    # Aggregate.
-    all_events = []
-    for f in worker_results:
-        if os.path.isfile(f):
-            with open(f) as fh:
-                all_events.extend(json.load(fh))
-    reclaim_events = []
-    if os.path.isfile(reclaim_result):
-        with open(reclaim_result) as fh:
-            reclaim_events = json.load(fh)
-
-    op_counts = {}
-    for e in all_events:
-        op_counts[e["kind"]] = op_counts.get(e["kind"], 0) + 1
-    total_reclaims = sum(e.get("count", 0) for e in reclaim_events)
-    print(f"\nReclaimer fired {len(reclaim_events)} times, total tasks reclaimed: {total_reclaims}")
-    print("Worker events:")
-    for k in sorted(op_counts):
-        print(f"  {k:<25} {op_counts[k]}")
-
-    # Invariant checks
-    failures = []
-    conn = kb.connect()
-    try:
-        # Any task stuck with current_run_id pointing at a closed run?
-        bad = conn.execute("""
-            SELECT t.id, t.status, t.current_run_id, r.ended_at, r.outcome
-            FROM tasks t
-            JOIN task_runs r ON r.id = t.current_run_id
-            WHERE r.ended_at IS NOT NULL
-        """).fetchall()
-        for row in bad:
-            failures.append(
-                f"INVARIANT VIOLATION: task {row['id']} status={row['status']} "
-                f"current_run_id={row['current_run_id']} but run ended "
-                f"outcome={row['outcome']}"
-            )
-        # Every run with NULL ended_at should still have the task pointing at it
-        orphans = conn.execute("""
-            SELECT r.id, r.task_id
-            FROM task_runs r
-            LEFT JOIN tasks t ON t.current_run_id = r.id
-            WHERE r.ended_at IS NULL AND t.id IS NULL
-        """).fetchall()
-        for row in orphans:
-            failures.append(f"ORPHAN OPEN RUN: run {row['id']} on task {row['task_id']}")
-        # Event counts
-        claim_evts = conn.execute(
-            "SELECT COUNT(*) FROM task_events WHERE kind='claimed'").fetchone()[0]
-        reclaim_evts = conn.execute(
-            "SELECT COUNT(*) FROM task_events WHERE kind='reclaimed'").fetchone()[0]
-        comp_evts = conn.execute(
-            "SELECT COUNT(*) FROM task_events WHERE kind='completed'").fetchone()[0]
-        print(f"\nDB event counts: claimed={claim_evts} reclaimed={reclaim_evts} completed={comp_evts}")
-        # Every reclaimed run must have ended_at set
-        unended_reclaims = conn.execute(
-            "SELECT COUNT(*) FROM task_runs WHERE outcome='reclaimed' AND ended_at IS NULL"
-        ).fetchone()[0]
-        if unended_reclaims:
-            failures.append(f"UNENDED RECLAIMED RUNS: {unended_reclaims}")
-        # Count of completed runs
-        comp_runs = conn.execute(
-            "SELECT COUNT(*) FROM task_runs WHERE outcome='completed'"
-        ).fetchone()[0]
-        reclaim_runs = conn.execute(
-            "SELECT COUNT(*) FROM task_runs WHERE outcome='reclaimed'"
-        ).fetchone()[0]
-        print(f"DB run outcomes: completed={comp_runs} reclaimed={reclaim_runs}")
-    finally:
-        conn.close()
-
-    if reclaim_runs == 0:
-        failures.append("NO RECLAIMS HAPPENED — test didn't stress what it was supposed to")
-
-    if failures:
-        print(f"\nFAILURES ({len(failures)}):")
-        for f in failures[:20]:
-            print(f"  {f}")
-        sys.exit(1)
-    else:
-        print("\n✔ RECLAIM RACE INVARIANTS HELD")
-
-
-if __name__ == "__main__":
-    main()

tests/stress/test_property_fuzzing.py

@@ -1,283 +0,0 @@
-"""Randomized property testing for the Kanban kernel.
-
-Generates 1000 random operation sequences, each 20-50 ops, on small
-task graphs. After each step, checks the full invariant set:
-
-  I1. If tasks.current_run_id IS NOT NULL, the run MUST exist AND
-      ended_at MUST be NULL (we never point at a closed run).
-  I2. If a run has ended_at NULL, SOME task MUST have current_run_id
-      pointing at it (no orphan open runs).
-  I3. task.status in the valid set {triage, todo, ready, running,
-      blocked, done, archived}.
-  I4. task.claim_lock NULL iff status not in (running,).
-  I5. Every run has started_at <= ended_at (or ended_at is NULL).
-  I6. If outcome is set, ended_at must also be set.
-  I7. Events are strictly monotonic in (created_at, id).
-  I8. task_events.run_id references a task_runs.id that exists
-      (or is NULL).
-  I9. Parent completion invariant: if all parents are 'done', the
-      child cannot be in 'todo' status (recompute_ready should have
-      promoted it). This is called out in the comment on
-      recompute_ready; verify it holds after every random seq.
-
-Not using hypothesis the lib; just Python random for simplicity.
-"""
-
-import os
-import random
-import sys
-import tempfile
-import time
-from pathlib import Path
-
-WT = str(Path(__file__).resolve().parents[2])
-NUM_SEQUENCES = 500
-OPS_PER_SEQUENCE = 100
-TASK_POOL = 10
-
-OPS = [
-    "create", "create_child", "claim", "complete", "block", "unblock",
-    "archive", "heartbeat", "release_stale", "detect_crashed",
-    "recompute_ready", "reassign",
-]
-
-
-def assert_invariants(conn, kb, ops_log):
-    """Run all invariant checks; raise AssertionError with context on any."""
-    failures = []
-
-    # I1: current_run_id → run exists and not ended
-    bad_ptr = conn.execute("""
-        SELECT t.id, t.current_run_id, r.ended_at, r.outcome
-        FROM tasks t
-        LEFT JOIN task_runs r ON r.id = t.current_run_id
-        WHERE t.current_run_id IS NOT NULL
-          AND (r.id IS NULL OR r.ended_at IS NOT NULL)
-    """).fetchall()
-    for row in bad_ptr:
-        if row["ended_at"] is None and row["outcome"] is None:
-            detail = "missing"
-        else:
-            detail = f"closed ({row['outcome']})"
-        failures.append(
-            f"I1: task {row['id']} points at run {row['current_run_id']} "
-            f"which is {detail}"
-        )
-
-    # I2: open run → some task points at it
-    orphans = conn.execute("""
-        SELECT r.id, r.task_id
-        FROM task_runs r
-        WHERE r.ended_at IS NULL
-          AND NOT EXISTS (SELECT 1 FROM tasks t WHERE t.current_run_id = r.id)
-    """).fetchall()
-    for row in orphans:
-        failures.append(f"I2: open run {row['id']} on task {row['task_id']} has no pointer")
-
-    # I3: valid statuses
-    valid = {"triage", "todo", "ready", "running", "blocked", "done", "archived"}
-    bad_status = conn.execute("SELECT id, status FROM tasks").fetchall()
-    for row in bad_status:
-        if row["status"] not in valid:
-            failures.append(f"I3: task {row['id']} has invalid status {row['status']!r}")
-
-    # I4: claim_lock set only when running
-    bad_lock = conn.execute("""
-        SELECT id, status, claim_lock FROM tasks
-        WHERE (status != 'running' AND claim_lock IS NOT NULL)
-    """).fetchall()
-    for row in bad_lock:
-        failures.append(
-            f"I4: task {row['id']} status={row['status']} but claim_lock={row['claim_lock']!r}"
-        )
-
-    # I5: run started_at <= ended_at
-    bad_times = conn.execute("""
-        SELECT id, started_at, ended_at FROM task_runs
-        WHERE ended_at IS NOT NULL AND started_at > ended_at
-    """).fetchall()
-    for row in bad_times:
-        failures.append(
-            f"I5: run {row['id']} started_at={row['started_at']} > ended_at={row['ended_at']}"
-        )
-
-    # I6: outcome set → ended_at set
-    bad_outcome = conn.execute("""
-        SELECT id, outcome, ended_at FROM task_runs
-        WHERE outcome IS NOT NULL AND ended_at IS NULL
-    """).fetchall()
-    for row in bad_outcome:
-        failures.append(f"I6: run {row['id']} outcome={row['outcome']} but ended_at NULL")
-
-    # I7: events monotonic in id (always true for autoincrement)
-    # Skip — autoincrement guarantees it.
-
-    # I8: event.run_id references existing run
-    bad_ev_fk = conn.execute("""
-        SELECT e.id, e.run_id FROM task_events e
-        LEFT JOIN task_runs r ON r.id = e.run_id
-        WHERE e.run_id IS NOT NULL AND r.id IS NULL
-    """).fetchall()
-    for row in bad_ev_fk:
-        failures.append(f"I8: event {row['id']} references missing run {row['run_id']}")
-
-    # I9: if all parents done → child not in todo
-    # (Only applies to children with at least one parent)
-    orphaned_todo = conn.execute("""
-        SELECT c.id AS child_id,
-               COUNT(*) AS n_parents,
-               SUM(CASE WHEN p.status = 'done' THEN 1 ELSE 0 END) AS done_parents
-        FROM tasks c
-        JOIN task_links l ON l.child_id = c.id
-        JOIN tasks p ON p.id = l.parent_id
-        WHERE c.status = 'todo'
-        GROUP BY c.id
-        HAVING n_parents > 0 AND n_parents = done_parents
-    """).fetchall()
-    for row in orphaned_todo:
-        failures.append(
-            f"I9: task {row['child_id']} is todo but all {row['n_parents']} parents are done"
-        )
-
-    if failures:
-        print(f"\n!!! INVARIANT VIOLATION after {len(ops_log)} ops:")
-        for f in failures[:10]:
-            print(f"  {f}")
-        if len(failures) > 10:
-            print(f"  ... and {len(failures) - 10} more")
-        print("\nLast 10 ops:")
-        for op in ops_log[-10:]:
-            print(f"  {op}")
-        return False
-    return True
-
-
-def random_op(rng, conn, kb, task_pool):
-    op = rng.choice(OPS)
-
-    if op == "create":
-        tid = kb.create_task(
-            conn,
-            title=f"rand {rng.randint(0, 1000)}",
-            assignee=rng.choice(["w1", "w2", "w3", None]),
-        )
-        task_pool.append(tid)
-        return {"op": "create", "tid": tid}
-
-    if op == "create_child" and task_pool:
-        parent = rng.choice(task_pool)
-        tid = kb.create_task(
-            conn, title=f"child of {parent}",
-            assignee=rng.choice(["w1", "w2", "w3", None]),
-            parents=[parent],
-        )
-        task_pool.append(tid)
-        return {"op": "create_child", "tid": tid, "parent": parent}
-
-    if not task_pool:
-        return None
-
-    tid = rng.choice(task_pool)
-    task = kb.get_task(conn, tid)
-    if task is None:
-        task_pool.remove(tid)
-        return None
-
-    if op == "claim":
-        claimed = kb.claim_task(conn, tid, ttl_seconds=rng.choice([1, 3, 10]))
-        return {"op": "claim", "tid": tid, "ok": claimed is not None}
-    if op == "complete":
-        summary = rng.choice([None, f"done via op {rng.randint(0, 1000)}"])
-        ok = kb.complete_task(conn, tid, summary=summary)
-        return {"op": "complete", "tid": tid, "ok": ok}
-    if op == "block":
-        reason = rng.choice([None, "rand block"])
-        ok = kb.block_task(conn, tid, reason=reason)
-        return {"op": "block", "tid": tid, "ok": ok}
-    if op == "unblock":
-        ok = kb.unblock_task(conn, tid)
-        return {"op": "unblock", "tid": tid, "ok": ok}
-    if op == "archive":
-        ok = kb.archive_task(conn, tid)
-        if ok:
-            task_pool.remove(tid)
-        return {"op": "archive", "tid": tid, "ok": ok}
-    if op == "heartbeat":
-        ok = kb.heartbeat_worker(conn, tid)
-        return {"op": "heartbeat", "tid": tid, "ok": ok}
-    if op == "release_stale":
-        n = kb.release_stale_claims(conn)
-        return {"op": "release_stale", "n": n}
-    if op == "detect_crashed":
-        # Force-kill a fake PID first so there's something to detect
-        crashed = kb.detect_crashed_workers(conn)
-        return {"op": "detect_crashed", "n": len(crashed)}
-    if op == "recompute_ready":
-        n = kb.recompute_ready(conn)
-        return {"op": "recompute_ready", "promoted": n}
-    if op == "reassign":
-        # Reassignment isn't a direct API; simulate via assign_task
-        new_a = rng.choice(["w1", "w2", "w3", None])
-        try:
-            kb.assign_task(conn, tid, new_a)
-            return {"op": "reassign", "tid": tid, "to": new_a}
-        except Exception as e:
-            return {"op": "reassign", "tid": tid, "err": str(e)[:50]}
-
-    return None
-
-
-def main():
-    total_ops = 0
-    total_violations = 0
-
-    for seq_idx in range(NUM_SEQUENCES):
-        seed = random.randint(0, 10**9)
-        rng = random.Random(seed)
-        home = tempfile.mkdtemp(prefix=f"hermes_fuzz_{seq_idx}_")
-        os.environ["HERMES_HOME"] = home
-        os.environ["HOME"] = home
-        sys.path.insert(0, WT)
-
-        # Fresh module state per sequence to avoid cached init paths.
-        for m in list(sys.modules.keys()):
-            if m.startswith("hermes_cli"):
-                del sys.modules[m]
-        from hermes_cli import kanban_db as kb
-
-        kb.init_db()
-        conn = kb.connect()
-        task_pool = []
-        ops_log = []
-
-        try:
-            for i in range(OPS_PER_SEQUENCE):
-                result = random_op(rng, conn, kb, task_pool)
-                if result is None:
-                    continue
-                ops_log.append(result)
-                total_ops += 1
-                if not assert_invariants(conn, kb, ops_log):
-                    total_violations += 1
-                    print(f"  sequence {seq_idx} (seed={seed}) failed at op {i}")
-                    break
-        finally:
-            conn.close()
-
-        if seq_idx % 10 == 0:
-            print(f"  seq {seq_idx:3d}: {total_ops} ops so far, {total_violations} violations")
-
-    print()
-    print("=" * 60)
-    print(f"Total sequences: {NUM_SEQUENCES}")
-    print(f"Total operations: {total_ops}")
-    print(f"Invariant violations: {total_violations}")
-    if total_violations == 0:
-        print("\n✔ ALL INVARIANTS HELD ACROSS RANDOMIZED SEQUENCES")
-    else:
-        print("\n✗ INVARIANT VIOLATIONS FOUND")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

tests/stress/test_subprocess_e2e.py

@@ -1,228 +0,0 @@
-"""E2E: dispatcher spawns real Python subprocess workers.
-
-This validates the IPC + lifecycle story that mocks can't:
-  - spawn_fn returns a real PID
-  - the child process resolves hermes_cli.kanban_db on its own
-  - the child writes heartbeats via the CLI (real argparse, real init_db)
-  - the child completes via the CLI with --summary + --metadata
-  - the dispatcher observes all of this through the DB only
-  - worker logs are captured to HERMES_HOME/kanban/logs/<task>.log
-  - crash detection works against a real dead PID
-"""
-
-import json
-import os
-import subprocess
-import sys
-import tempfile
-import time
-
-WT = str(Path(__file__).resolve().parents[2])
-FAKE_WORKER = str(Path(__file__).parent / "_fake_worker.py")
-PY = sys.executable
-
-
-def make_spawn_fn(home: str):
-    """Return a spawn_fn the dispatcher can call. Launches the fake
-    worker as a detached subprocess."""
-
-    def _spawn(task, workspace):
-        log_path = os.path.join(home, f"worker_{task.id}.log")
-        env = {
-            **os.environ,
-            "HERMES_HOME": home,
-            "HOME": home,
-            "PYTHONPATH": WT,
-            "HERMES_KANBAN_TASK": task.id,
-            "HERMES_KANBAN_WORKSPACE": workspace,
-            "PATH": f"{os.path.dirname(PY)}:{os.environ.get('PATH','')}",
-        }
-        log_f = open(log_path, "ab")
-        proc = subprocess.Popen(
-            [PY, FAKE_WORKER],
-            stdin=subprocess.DEVNULL,
-            stdout=log_f,
-            stderr=subprocess.STDOUT,
-            env=env,
-            start_new_session=True,
-        )
-        return proc.pid
-
-    return _spawn
-
-
-def main():
-    home = tempfile.mkdtemp(prefix="hermes_e2e_")
-    os.environ["HERMES_HOME"] = home
-    os.environ["HOME"] = home
-    sys.path.insert(0, WT)
-    from hermes_cli import kanban_db as kb
-
-    # Point the `hermes` CLI child processes will run at the worktree
-    # hermes_cli.main. We do this by putting a shim on PATH.
-    shim_dir = os.path.join(home, "bin")
-    os.makedirs(shim_dir, exist_ok=True)
-    shim_path = os.path.join(shim_dir, "hermes")
-    with open(shim_path, "w") as f:
-        f.write(f"""#!/bin/sh
-exec {PY} -m hermes_cli.main "$@"
-""")
-    os.chmod(shim_path, 0o755)
-    os.environ["PATH"] = f"{shim_dir}:{os.environ.get('PATH','')}"
-
-    kb.init_db()
-    conn = kb.connect()
-
-    # ============ SCENARIO A: happy path, 3 tasks ============
-    print("=" * 60)
-    print("A. Real-subprocess happy path (3 tasks)")
-    print("=" * 60)
-
-    tids = []
-    for i in range(3):
-        tid = kb.create_task(
-            conn, title=f"real-e2e-{i}", assignee="worker",
-        )
-        tids.append(tid)
-
-    spawn_fn = make_spawn_fn(home)
-    result = kb.dispatch_once(conn, spawn_fn=spawn_fn)
-    print(f"  dispatched: {len(result.spawned)} spawned")
-    spawned_pids = []
-    # The dispatcher sets worker_pid on each claimed task via _set_worker_pid.
-    for tid in tids:
-        task = kb.get_task(conn, tid)
-        spawned_pids.append(task.worker_pid)
-        print(f"  task {tid}: pid={task.worker_pid} status={task.status}")
-
-    # Wait for all workers to complete (up to 10s).
-    deadline = time.monotonic() + 10
-    while time.monotonic() < deadline:
-        statuses = [kb.get_task(conn, tid).status for tid in tids]
-        if all(s == "done" for s in statuses):
-            break
-        time.sleep(0.2)
-
-    print()
-    failures = []
-    for tid in tids:
-        task = kb.get_task(conn, tid)
-        runs = kb.list_runs(conn, tid)
-        print(f"  task {tid}: status={task.status}, current_run_id={task.current_run_id}, "
-              f"runs={[(r.id, r.outcome) for r in runs]}")
-        if task.status != "done":
-            failures.append(f"task {tid} not done: status={task.status}")
-        if task.current_run_id is not None:
-            failures.append(f"task {tid} has dangling current_run_id={task.current_run_id}")
-        if len(runs) != 1:
-            failures.append(f"task {tid} has {len(runs)} runs, expected 1")
-        else:
-            r = runs[0]
-            if r.outcome != "completed":
-                failures.append(f"task {tid} run outcome={r.outcome}, expected completed")
-            if not r.summary or "real-subprocess worker finished" not in r.summary:
-                failures.append(f"task {tid} summary missing: {r.summary!r}")
-            if not r.metadata or r.metadata.get("iterations") != 3:
-                failures.append(f"task {tid} metadata missing iterations: {r.metadata}")
-            # Heartbeat events should be present
-            events = kb.list_events(conn, tid)
-            heartbeats = [e for e in events if e.kind == "heartbeat"]
-            if len(heartbeats) < 3:  # start + 3 progress
-                failures.append(f"task {tid} heartbeats={len(heartbeats)} expected >=3")
-
-    if failures:
-        print("\nFAILURES:")
-        for f in failures:
-            print(f"  {f}")
-        sys.exit(1)
-
-    print("\n  ✔ Scenario A: all 3 real-subprocess workers completed cleanly")
-
-    # ============ SCENARIO B: crashed worker ============
-    print()
-    print("=" * 60)
-    print("B. Crashed worker (kill -9 mid-heartbeat)")
-    print("=" * 60)
-
-    crash_tid = kb.create_task(
-        conn, title="crash-e2e", assignee="worker",
-    )
-
-    # Spawn a worker that sleeps long enough for us to kill it.
-    # CRITICAL: spawn through a double-fork so when we kill the child it
-    # doesn't zombify under our pid (which would fool kill -0 liveness
-    # checks into thinking it's still alive). In production the
-    # dispatcher daemon is long-lived but its workers are reaped by init
-    # after exit; the test needs to match that orphaning behavior.
-    def spawn_sleeper(task, workspace):
-        r, w = os.pipe()
-        middleman = subprocess.Popen(
-            [
-                PY, "-c",
-                "import os,sys,subprocess;"
-                "p=subprocess.Popen(['sleep','30'],"
-                "stdin=subprocess.DEVNULL,"
-                "stdout=subprocess.DEVNULL,stderr=subprocess.DEVNULL,"
-                "start_new_session=True);"
-                "os.write(int(sys.argv[1]), str(p.pid).encode());"
-                "sys.exit(0)",
-                str(w),
-            ],
-            pass_fds=(w,),
-            stdin=subprocess.DEVNULL,
-            stdout=subprocess.DEVNULL,
-            stderr=subprocess.DEVNULL,
-        )
-        os.close(w)
-        middleman.wait()  # middleman exits immediately, orphaning the sleep
-        grandchild_pid = int(os.read(r, 16))
-        os.close(r)
-        return grandchild_pid
-
-    result = kb.dispatch_once(conn, spawn_fn=spawn_sleeper)
-    task = kb.get_task(conn, crash_tid)
-    print(f"  spawned sleeper pid={task.worker_pid} for {crash_tid}")
-    # Kill the sleeper forcibly
-    os.kill(task.worker_pid, 9)
-    # Give the OS a moment to reap
-    time.sleep(0.5)
-
-    # Simulate next dispatcher tick — should detect the crashed PID
-    crashed = kb.detect_crashed_workers(conn)
-    print(f"  detect_crashed_workers returned {len(crashed)} crashed (expected 1)")
-
-    task = kb.get_task(conn, crash_tid)
-    runs = kb.list_runs(conn, crash_tid)
-    print(f"  task status={task.status}, runs={[(r.id, r.outcome) for r in runs]}")
-
-    if len(crashed) < 1:
-        print("  ✗ crash NOT detected")
-        sys.exit(1)
-    if task.status != "ready":
-        print(f"  ✗ task should be back to ready, got {task.status}")
-        sys.exit(1)
-    if runs[0].outcome != "crashed":
-        print(f"  ✗ run outcome should be 'crashed', got {runs[0].outcome!r}")
-        sys.exit(1)
-    print("\n  ✔ Scenario B: crash detected, task re-queued, run outcome=crashed")
-
-    # ============ SCENARIO C: worker log was captured ============
-    print()
-    print("=" * 60)
-    print("C. Worker log captured to disk")
-    print("=" * 60)
-    # Scenario A workers wrote to /tmp/hermes_e2e_*/worker_*.log
-    import glob
-    logs = glob.glob(os.path.join(home, "worker_*.log"))
-    print(f"  {len(logs)} worker log files")
-    for lp in logs[:3]:
-        size = os.path.getsize(lp)
-        print(f"    {os.path.basename(lp)}: {size} bytes")
-        # Our fake worker is quiet (no prints); size=0 is fine
-
-    conn.close()
-    print("\n✔ ALL E2E SCENARIOS PASS")
-
-
-if __name__ == "__main__":
-    main()

tests/test_hermes_state.py

@@ -308,33 +308,6 @@ class TestMessageStorage:
         assert "reasoning_content" in conv[0]
         assert conv[0]["reasoning_content"] == ""
 
-    def test_codex_message_items_persisted_and_restored(self, db):
-        """codex_message_items must round-trip through JSON serialization."""
-        db.create_session(session_id="s1", source="cli")
-        items = [
-            {
-                "type": "message",
-                "role": "assistant",
-                "status": "completed",
-                "id": "msg_123",
-                "phase": "commentary",
-                "content": [{"type": "output_text", "text": "Thinking..."}],
-            },
-            {
-                "type": "message",
-                "role": "assistant",
-                "status": "completed",
-                "id": "msg_456",
-                "phase": "final_answer",
-                "content": [{"type": "output_text", "text": "Done!"}],
-            },
-        ]
-        db.append_message("s1", role="assistant", content="Done!", codex_message_items=items)
-
-        conv = db.get_messages_as_conversation("s1")
-        assert len(conv) == 1
-        assert conv[0].get("codex_message_items") == items
-
     def test_reasoning_not_set_for_non_assistant(self, db):
         """reasoning is never leaked onto user or tool messages."""
         db.create_session(session_id="s1", source="telegram")
@@ -1200,7 +1173,7 @@ class TestSchemaInit:
     def test_schema_version(self, db):
         cursor = db._conn.execute("SELECT version FROM schema_version")
         version = cursor.fetchone()[0]
-        assert version == 9
+        assert version == 8
 
     def test_title_column_exists(self, db):
         """Verify the title column was created in the sessions table."""
@@ -1256,12 +1229,12 @@ class TestSchemaInit:
         conn.commit()
         conn.close()
 
-        # Open with SessionDB — should migrate to v9
+        # Open with SessionDB — should migrate to v8
         migrated_db = SessionDB(db_path=db_path)
 
         # Verify migration
         cursor = migrated_db._conn.execute("SELECT version FROM schema_version")
-        assert cursor.fetchone()[0] == 9
+        assert cursor.fetchone()[0] == 8
 
         # Verify title column exists and is NULL for existing sessions
         session = migrated_db.get_session("existing")