Active vs configured model display during fallback

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #1660 fix(gateway): /model shows active fallback model instead of config default (#1615)

  merged to main

  files: gateway/run.py

  Show the diff

  • gateway/run.py

    @@ -342,7 +342,13 @@ def __init__(self, config: Optional[GatewayConfig] = None):
             # Key: session_key, Value: AIAgent instance
             self._running_agents: Dict[str, Any] = {}
             self._pending_messages: Dict[str, str] = {}  # Queued messages during interrupt
    -        
    +
    +        # Track active fallback model/provider when primary is rate-limited.
    +        # Set after an agent run where fallback was activated; cleared when
    +        # the primary model succeeds again or the user switches via /model.
    +        self._effective_model: Optional[str] = None
    +        self._effective_provider: Optional[str] = None
    +
             # Track pending exec approvals per session
             # Key: session_key, Value: {"command": str, "pattern_key": str, ...}
             self._pending_approvals: Dict[str, Dict[str, Any]] = {}
    @@ -2204,6 +2210,21 @@ async def _handle_model_command(self, event: MessageEvent) -> str:
                 current_provider = "custom"
     
             if not args:
    +            # If a fallback model is active, show it instead of config
    +            if self._effective_model:
    +                eff_provider = self._effective_provider or 'unknown'
    +                eff_label = _PROVIDER_LABELS.get(eff_provider, eff_provider)
    +                cfg_label = _PROVIDER_LABELS.get(current_provider, current_provider)
    +                lines = [
    +                    f"🤖 **Active model:** `{self._effective_model}` (fallback)",
    +                    f"**Provider:** {eff_label}",
    +                    f"**Primary model** (`{current}` via {cfg_label}) is rate-limited.",
    +                    "",
    +                ]
    +                lines.append("To change: `/model model-name`")
    +                lines.append("Switch provider: `/model provider:model-name`")
    +                return "\n".join(lines)
    +
                 provider_label = _PROVIDER_LABELS.get(current_provider, current_provider)
                 lines = [
                     f"🤖 **Current model:** `{current}`",
    @@ -2303,6 +2324,9 @@ async def _handle_model_command(self, event: MessageEvent) -> str:
                 persist_note = "saved to config"
             else:
                 persist_note = "this session only — will revert on restart"
    +        # Clear fallback state since user explicitly chose a model
    +        self._effective_model = None
    +        self._effective_provider = None
             return f"🤖 Model changed to `{new_model}` ({persist_note}){provider_note}{warning}\n_(takes effect on next message)_"
     
         async def _handle_provider_command(self, event: MessageEvent) -> str:
    @@ -4531,7 +4555,21 @@ async def monitor_for_interrupt():
                 # Run in thread pool to not block
                 loop = asyncio.get_event_loop()
                 response = await loop.run_in_executor(None, run_sync)
    -            
    +
    +            # Track fallback model state: if the agent switched to a
    +            # fallback model during this run, persist it so /model shows
    +            # the actually-active model instead of the config default.
    +            _agent = agent_holder[0]
    +            if _agent is not None and hasattr(_agent, 'model'):
    +                _cfg_model = _resolve_gateway_model()
    +                if _agent.model != _cfg_model:
    +                    self._effective_model = _agent.model
    +                    self._effective_provider = getattr(_agent, 'provider', None)
    +                else:
    +                    # Primary model worked — clear any stale fallback state
    +                    self._effective_model = None
    +                    self._effective_provider = None
    +
                 # Check if we were interrupted and have a pending message
                 result = result_holder[0]
                 adapter = self.adapters.get(source.platform)

• #6754 fix: fallback header preservation, kimi credential pool, TUI stale model display

  merged to main

  files: agent/auxiliary_client.py, agent/credential_pool.py, cli.py, hermes_cli/auth.py, run_agent.py

  Show the diff

  • agent/auxiliary_client.py

    @@ -702,7 +702,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
                 logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
                 extra = {}
                 if "api.kimi.com" in base_url.lower():
    -                extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
    +                extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
                 elif "api.githubcopilot.com" in base_url.lower():
                     from hermes_cli.models import copilot_default_headers
     
    @@ -721,7 +721,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             logger.debug("Auxiliary text client: %s (%s)", pconfig.name, model)
             extra = {}
             if "api.kimi.com" in base_url.lower():
    -            extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
    +            extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
             elif "api.githubcopilot.com" in base_url.lower():
                 from hermes_cli.models import copilot_default_headers
     
    @@ -1195,7 +1195,7 @@ def _to_async_client(sync_client, model: str):
     
             async_kwargs["default_headers"] = copilot_default_headers()
         elif "api.kimi.com" in base_lower:
    -        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
    +        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
         return AsyncOpenAI(**async_kwargs), model
     
     
    @@ -1315,7 +1315,13 @@ def resolve_provider_client(
                     )
                     return None, None
                 final_model = model or _read_main_model() or "gpt-4o-mini"
    -            client = OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base)
    +            extra = {}
    +            if "api.kimi.com" in custom_base.lower():
    +                extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
    +            elif "api.githubcopilot.com" in custom_base.lower():
    +                from hermes_cli.models import copilot_default_headers
    +                extra["default_headers"] = copilot_default_headers()
    +            client = OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base, **extra)
                 return (_to_async_client(client, final_model) if async_mode
                         else (client, final_model))
             # Try custom first, then codex, then API-key providers
    @@ -1394,7 +1400,7 @@ def resolve_provider_client(
             # Provider-specific headers
             headers = {}
             if "api.kimi.com" in base_url.lower():
    -            headers["User-Agent"] = "KimiCLI/1.0"
    +            headers["User-Agent"] = "KimiCLI/1.3"
             elif "api.githubcopilot.com" in base_url.lower():
                 from hermes_cli.models import copilot_default_headers
     

  • agent/credential_pool.py

    @@ -18,12 +18,14 @@
     from hermes_cli.auth import (
         CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
         DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
    +    KIMI_CODE_BASE_URL,
         PROVIDER_REGISTRY,
         _codex_access_token_is_expiring,
         _decode_jwt_claims,
         _import_codex_cli_tokens,
         _load_auth_store,
         _load_provider_state,
    +    _resolve_kimi_base_url,
         _resolve_zai_base_url,
         read_credential_pool,
         write_credential_pool,
    @@ -1084,7 +1086,9 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
             active_sources.add(source)
             auth_type = AUTH_TYPE_OAUTH if provider == "anthropic" and not token.startswith("sk-ant-api") else AUTH_TYPE_API_KEY
             base_url = env_url or pconfig.inference_base_url
    -        if provider == "zai":
    +        if provider == "kimi-coding":
    +            base_url = _resolve_kimi_base_url(token, pconfig.inference_base_url, env_url)
    +        elif provider == "zai":
                 base_url = _resolve_zai_base_url(token, pconfig.inference_base_url, env_url)
             changed |= _upsert_entry(
                 entries,

  • cli.py

    @@ -1603,7 +1603,12 @@ def _build_context_bar(self, percent_used: Optional[int], width: int = 10) -> st
             return f"[{('█' * filled) + ('░' * max(0, width - filled))}]"
     
         def _get_status_bar_snapshot(self) -> Dict[str, Any]:
    -        model_name = self.model or "unknown"
    +        # Prefer the agent's model name — it updates on fallback.
    +        # self.model reflects the originally configured model and never
    +        # changes mid-session, so the TUI would show a stale name after
    +        # _try_activate_fallback() switches provider/model.
    +        agent = getattr(self, "agent", None)
    +        model_name = (getattr(agent, "model", None) or self.model or "unknown")
             model_short = model_name.split("/")[-1] if "/" in model_name else model_name
             if model_short.endswith(".gguf"):
                 model_short = model_short[:-5]
    @@ -1629,7 +1634,6 @@ def _get_status_bar_snapshot(self) -> Dict[str, Any]:
                 "compressions": 0,
             }
     
    -        agent = getattr(self, "agent", None)
             if not agent:
                 return snapshot
     

  • hermes_cli/auth.py

    @@ -250,7 +250,7 @@ class ProviderConfig:
     # Kimi Code Endpoint Detection
     # =============================================================================
     
    -# Kimi Code (platform.kimi.ai) issues keys prefixed "sk-kimi-" that only work
    +# Kimi Code (kimi.com/code) issues keys prefixed "sk-kimi-" that only work
     # on api.kimi.com/coding/v1.  Legacy keys from platform.moonshot.ai work on
     # api.moonshot.ai/v1 (the default).  Auto-detect when user hasn't set
     # KIMI_BASE_URL explicitly.

  • run_agent.py

    @@ -4968,9 +4968,21 @@ def _try_activate_fallback(self) -> bool:
                     # Swap OpenAI client and config in-place
                     self.api_key = [redacted:secret-assignment]
                     self.client = fb_client
    +                # Preserve provider-specific headers that
    +                # resolve_provider_client() may have baked into
    +                # fb_client via the default_headers kwarg.  The OpenAI
    +                # SDK stores these in _custom_headers.  Without this,
    +                # subsequent request-client rebuilds (via
    +                # _create_request_openai_client) drop the headers,
    +                # causing 403s from providers like Kimi Coding that
    +                # require a User-Agent sentinel.
    +                fb_headers = getattr(fb_client, "_custom_headers", None)
    +                if not fb_headers:
    +                    fb_headers = getattr(fb_client, "default_headers", None)
                     self._client_kwargs = {
                         "api_key": fb_client.api_key,
                         "base_url": fb_base_url,
    +                    **({"default_headers": dict(fb_headers)} if fb_headers else {}),
                     }
     
                 # Re-evaluate prompt caching for the new provider/model

• #133961 fix(dashboard): badge follows the PTY runtime model, not config, during fallback

  merged to main

  files: web/src/components/ChatSidebar.test.tsx, web/src/components/ChatSidebar.tsx