Anthropic base URL and auxiliary provider routing fixes

Fixes on record

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

• #12846 fix(anthropic): complete third-party Anthropic-compatible provider support

  merged to main

  files: agent/auxiliary_client.py, hermes_cli/auth.py, hermes_cli/runtime_provider.py, run_agent.py, scripts/release.py, tests/agent/test_auxiliary_client_anthropic_custom.py, tests/hermes_cli/test_detect_api_mode_for_url.py, tests/hermes_cli/test_update_config_clears_custom_fields.py, tests/run_agent/test_anthropic_prompt_cache_policy.py, tests/run_agent/test_anthropic_third_party_oauth_guard.py, tests/run_agent/test_anthropic_truncation_continuation.py

  Show the diff

  • agent/auxiliary_client.py

    @@ -1098,7 +1098,7 @@ def _validate_base_url(base_url: str) -> None:
             ) from exc
     
     
    -def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
    +def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
         runtime = _resolve_custom_runtime()
         if len(runtime) == 2:
             custom_base, custom_key = runtime
    @@ -1114,6 +1114,23 @@ def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
         if custom_mode == "codex_responses":
             real_client = OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base)
             return CodexAuxiliaryClient(real_client, model), model
    +    if custom_mode == "anthropic_messages":
    +        # Third-party Anthropic-compatible gateway (MiniMax, Zhipu GLM,
    +        # LiteLLM proxies, etc.).  Must NEVER be treated as OAuth —
    +        # Anthropic OAuth claims only apply to api.anthropic.com.
    +        try:
    +            from agent.anthropic_adapter import build_anthropic_client
    +            real_client = build_anthropic_client(custom_key, custom_base)
    +        except ImportError:
    +            logger.warning(
    +                "Custom endpoint declares api_mode=anthropic_messages but the "
    +                "anthropic SDK is not installed — falling back to OpenAI-wire."
    +            )
    +            return OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base), model
    +        return (
    +            AnthropicAuxiliaryClient(real_client, model, custom_key, custom_base, is_oauth=False),
    +            model,
    +        )
         return OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base), model
     
     

  • hermes_cli/auth.py

    @@ -2732,6 +2732,17 @@ def _update_config_for_provider(
             # Clear stale base_url to prevent contamination when switching providers
             model_cfg.pop("base_url", None)
     
    +    # Clear stale api_key/api_mode left over from a previous custom provider.
    +    # When the user switches from e.g. a MiniMax custom endpoint
    +    # (api_mode=anthropic_messages, api_key=[redacted:secret-assignment] to a built-in provider
    +    # (e.g. OpenRouter), the stale api_key/api_mode would override the new
    +    # provider's credentials and transport choice.  Built-in providers that
    +    # need a specific api_mode (copilot, xai) set it at request-resolution
    +    # time via `_copilot_runtime_api_mode` / `_detect_api_mode_for_url`, so
    +    # removing the persisted value here is safe.
    +    model_cfg.pop("api_key", None)
    +    model_cfg.pop("api_mode", None)
    +
         # When switching to a non-OpenRouter provider, ensure model.default is
         # valid for the new provider.  An OpenRouter-formatted name like
         # "anthropic/claude-opus-4.6" will fail on direct-API providers.

  • hermes_cli/runtime_provider.py

    @@ -38,14 +38,21 @@ def _normalize_custom_provider_name(value: str) -> str:
     def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
         """Auto-detect api_mode from the resolved base URL.
     
    -    Direct api.openai.com endpoints need the Responses API for GPT-5.x
    -    tool calls with reasoning (chat/completions returns 400).
    +    - Direct api.openai.com endpoints need the Responses API for GPT-5.x
    +      tool calls with reasoning (chat/completions returns 400).
    +    - Third-party Anthropic-compatible gateways (MiniMax, Zhipu GLM,
    +      LiteLLM proxies, etc.) conventionally expose the native Anthropic
    +      protocol under a ``/anthropic`` suffix — treat those as
    +      ``anthropic_messages`` transport instead of the default
    +      ``chat_completions``.
         """
         normalized = (base_url or "").strip().lower().rstrip("/")
         if "api.x.ai" in normalized:
             return "codex_responses"
         if "api.openai.com" in normalized and "openrouter" not in normalized:
             return "codex_responses"
    +    if normalized.endswith("/anthropic"):
    +        return "anthropic_messages"
         return None
     
     
    @@ -194,8 +201,12 @@ def _resolve_runtime_from_pool_entry(
             elif provider in ("opencode-zen", "opencode-go"):
                 from hermes_cli.models import opencode_model_api_mode
                 api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
    -        elif base_url.rstrip("/").endswith("/anthropic"):
    -            api_mode = "anthropic_messages"
    +        else:
    +            # Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
    +            # api.openai.com → codex_responses, api.x.ai → codex_responses).
    +            detected = _detect_api_mode_for_url(base_url)
    +            if detected:
    +                api_mode = detected
     
         # OpenCode base URLs end with /v1 for OpenAI-compatible models, but the
         # Anthropic SDK prepends its own /v1/messages to the base_url.  Strip the
    @@ -642,8 +653,11 @@ def _resolve_explicit_runtime(
                 configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
                 if configured_mode:
                     api_mode = configured_mode
    -            elif base_url.rstrip("/").endswith("/anthropic"):
    -                api_mode = "anthropic_messages"
    +            else:
    +                # Auto-detect Anthropic-compatible endpoints (/anthropic suffix).
    +                detected = _detect_api_mode_for_url(base_url)
    +                if detected:
    +                    api_mode = detected
     
             return {
                 "provider": provider,
    @@ -965,10 +979,13 @@ def resolve_runtime_provider(
                 elif provider in ("opencode-zen", "opencode-go"):
                     from hermes_cli.models import opencode_model_api_mode
                     api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
    -            # Auto-detect Anthropic-compatible endpoints by URL convention
    -            # (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)
    -            elif base_url.rstrip("/").endswith("/anthropic"):
    -                api_mode = "anthropic_messages"
    +            else:
    +                # Auto-detect Anthropic-compatible endpoints by URL convention
    +                # (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)
    +                # plus api.openai.com → codex_responses and api.x.ai → codex_responses.
    +                detected = _detect_api_mode_for_url(base_url)
    +                if detected:
    +                    api_mode = detected
             # Strip trailing /v1 for OpenCode Anthropic models (see comment above).
             if api_mode == "anthropic_messages" and provider in ("opencode-zen", "opencode-go"):
                 base_url = re.sub(r"/v1/?$", "", base_url)

  • run_agent.py

    @@ -892,13 +892,15 @@ def __init__(
             self.prefill_messages = prefill_messages or []  # Prefilled conversation turns
             self._force_ascii_payload = False
             
    -        # Anthropic prompt caching: auto-enabled for Claude models via OpenRouter.
    -        # Reduces input costs by ~75% on multi-turn conversations by caching the
    -        # conversation prefix. Uses system_and_3 strategy (4 breakpoints).
    -        is_openrouter = self._is_openrouter_url()
    -        is_claude = "claude" in self.model.lower()
    -        is_native_anthropic = self.api_mode == "anthropic_messages" and self.provider == "anthropic"
    -        self._use_prompt_caching = (is_openrouter and is_claude) or is_native_anthropic
    +        # Anthropic prompt caching: auto-enabled for Claude models on native
    +        # Anthropic, OpenRouter, and third-party gateways that speak the
    +        # Anthropic protocol (``api_mode == 'anthropic_messages'``). Reduces
    +        # input costs by ~75% on multi-turn conversations. Uses system_and_3
    +        # strategy (4 breakpoints). See ``_anthropic_prompt_cache_policy``
    +        # for the layout-vs-transport decision.
    +        self._use_prompt_caching, self._use_native_cache_layout = (
    +            self._anthropic_prompt_cache_policy()
    +        )
             self._cache_ttl = "5m"  # Default 5-minute TTL (1.25x write cost)
             
             # Iteration budget: the LLM is only notified when it actually exhausts
    @@ -1013,8 +1015,15 @@ def __init__(
                     self.api_key = [redacted:secret-assignment]
                     self._anthropic_api_key = [redacted:secret-assignment]
                     self._anthropic_base_url = base_url
    +                # Only mark the session as OAuth-authenticated when the token
    +                # genuinely belongs to native Anthropic.  Third-party providers
    +                # (MiniMax, Kimi, GLM, LiteLLM proxies) that accept the
    +                # Anthropic protocol must never trip OAuth code paths — doing
    +                # so injects Claude-Code identity headers and system prompts
    +                # that cause 401/403 on their endpoints.  Guards #1739 and
    +                # the third-party identity-injection bug.
                     from agent.anthropic_adapter import _is_oauth_token as _is_oat
    -                self._is_anthropic_oauth = _is_oat(effective_key)
    +                self._is_anthropic_oauth = _is_oat(effective_key) if _is_native_anthropic else False
                     self._anthropic_client = build_anthropic_client(effective_key, base_url, timeout=_provider_timeout)
                     # No OpenAI client needed for Anthropic mode
                     self.client = None
    @@ -1227,7 +1236,12 @@ def __init__(
             
             # Show prompt caching status
             if self._use_prompt_caching and not self.quiet_mode:
    -            source = "native Anthropic" if is_native_anthropic else "Claude via OpenRouter"
    +            if self._use_native_cache_layout and self.provider == "anthropic":
    +                source = "native Anthropic"
    +            elif self._use_native_cache_layout:
    +                source = "Anthropic-compatible endpoint"
    +            else:
    +                source = "Claude via OpenRouter"
                 print(f"💾 Prompt caching: ENABLED ({source}, {self._cache_ttl} TTL)")
             
             # Session logging setup - auto-save conversation trajectories for debugging
    @@ -1701,6 +1715,7 @@ def __init__(
                 "api_key": getattr(self, "api_key", ""),
                 "client_kwargs": dict(self._client_kwargs),
                 "use_prompt_caching": self._use_prompt_caching,
    +            "use_native_cache_layout": self._use_native_cache_layout,
                 # Context engine state that _try_activate_fallback() overwrites.
                 # Use getattr for model/base_url/api_key/provider since plugin
                 # engines may not have these (they're ContextCompressor-specific).
    @@ -1822,7 +1837,7 @@ def switch_model(self, new_model, new_provider, api_key='', base_url='', api_mod
                     effective_key, self._anthropic_base_url,
                     timeout=get_provider_request_timeout(self.provider, self.model),
                 )
    -            self._is_anthropic_oauth = _is_oauth_token(effective_key)
    +            self._is_anthropic_oauth = _is_oauth_token(effective_key) if _is_native_anthropic else False
                 self.client = None
                 self._client_kwargs = {}
             else:
    @@ -1842,10 +1857,13 @@ def switch_model(self, new_model, new_provider, api_key='', base_url='', api_mod
                 )
     
             # ── Re-evaluate prompt caching ──
    -        is_native_anthropic = api_mode == "anthropic_messages" and new_provider == "anthropic"
    -        self._use_prompt_caching = (
    -            ("openrouter" in (self.base_url or "").lower() and "claude" in new_model.lower())
    -            or is_native_anthropic
    +        self._use_prompt_caching, self._use_native_cache_layout = (
    +            self._anthropic_prompt_cache_policy(
    +                provider=new_provider,
    +                base_url=self.base_url,
    +                api_mode=api_mode,
    +                model=new_model,
    +            )
             )
     
             # ── Update context compressor ──
    @@ -1880,6 +1898,7 @@ def switch_model(self, new_model, new_provider, api_key='', base_url='', api_mod
                 "api_key": getattr(self, "api_key", ""),
                 "client_kwargs": dict(self._client_kwargs),
                 "use_prompt_caching": self._use_prompt_caching,
    +            "use_native_cache_layout": self._use_native_cache_layout,
                 "compressor_model": getattr(_cc, "model", self.model) if _cc else self.model,
                 "compressor_base_url": getattr(_cc, "base_url", self.base_url) if _cc else self.base_url,
                 "compressor_api_key": getattr(_cc, "api_key", "") if _cc else "",
    @@ -2143,6 +2162,55 @@ def _is_openrouter_url(self) -> bool:
             """Return True when the base URL targets OpenRouter."""
             return "openrouter" in self._base_url_lower
     
    +    def _anthropic_prompt_cache_policy(
    +        self,
    +        *,
    +        provider: Optional[str] = None,
    +        base_url: Optional[str] = None,
    +        api_mode: Optional[str] = None,
    +        model: Optional[str] = None,
    +    ) -> tuple[bool, bool]:
    +        """Decide whether to apply Anthropic prompt caching and which layout to use.
    +
    +        Returns ``(should_cache, use_native_layout)``:
    +          * ``should_cache`` — inject ``cache_control`` breakpoints for this
    +            request (applies to OpenRouter Claude, native Anthropic, and
    +            third-party gateways that speak the native Anthropic protocol).
    +          * ``use_native_layout`` — place markers on the *inner* content
    +            blocks (native Anthropic accepts and requires this layout);
    +            when False markers go on the message envelope (OpenRouter and
    +            OpenAI-wire proxies expect the looser layout).
    +
    +        Third-party providers using the native Anthropic transport
    +        (``api_mode == 'anthropic_messages'`` + Claude-named model) get
    +        caching with the native layout so they benefit from the same
    +        cost reduction as direct Anthropic callers, provided their
    +        gateway implements the Anthropic cache_control contract
    +        (MiniMax, Zhipu GLM, LiteLLM's Anthropic proxy mode all do).
    +        """
    +        eff_provider = (provider if provider is not None else self.provider) or ""
    +        eff_base_url = base_url if base_url is not None else (self.base_url or "")
    +        eff_api_mode = api_mode if api_mode is not None else (self.api_mode or "")
    +        eff_model = (model if model is not None else self.model) or ""
    +
    +        base_lower = eff_base_url.lower()
    +        is_claude = "claude" in eff_model.lower()
    +        is_openrouter = "openrouter" in base_lower
    +        is_anthropic_wire = eff_api_mode == "anthropic_messages"
    +        is_native_anthropic = (
    +            is_anthropic_wire
    +            and (eff_provider == "anthropic" or "api.anthropic.com" in base_lower)
    +        )
    +
    +        if is_native_anthropic:
    +            return True, True
    +        if is_openrouter and is_claude:
    +            return True, False
    +        if is_anthropic_wire and is_claude:
    +            # Third-party Anthropic-compatible gateway.
    +            return True, True
    +        return False, False
    +
         @staticmethod
         def _model_requires_responses_api(model: str) -> bool:
             """Return True for models that require the Responses API path.
    @@ -5322,9 +5390,12 @@ def _try_refresh_anthropic_client_credentials(self) -> bool:
                 return False
     
             self._anthropic_api_key = [redacted:secret-assignment]
    -        # Update OAuth flag — token type may have changed (API key ↔ OAuth)
    +        # Update OAuth flag — token type may have changed (API key ↔ OAuth).
    +        # Only treat as OAuth on native Anthropic; third-party endpoints using
    +        # the Anthropic protocol must not trip OAuth paths (#1739 & third-party
    +        # identity-injection guard).
             from agent.anthropic_adapter import _is_oauth_token
    -        self._is_anthropic_oauth = _is_oauth_token(new_token)
    +        self._is_anthropic_oauth = _is_oauth_token(new_token) if self.provider == "anthropic" else False
             return True
     
         def _apply_client_headers_for_base_url(self, base_url: str) -> None:
    @@ -5367,7 +5438,7 @@ def _swap_credential(self, entry) -> None:
                     runtime_key, runtime_base,
                     timeout=get_provider_request_timeout(self.provider, self.model),
                 )
    -            self._is_anthropic_oauth = _is_oauth_token(runtime_key)
    +            self._is_anthropic_oauth = _is_oauth_token(runtime_key) if self.provider == "anthropic" else False
                 self.api_key = [redacted:secret-assignment]
                 self.base_url = runtime_base
                 return
    @@ -6523,7 +6594,7 @@ def _try_activate_fallback(self) -> bool:
                     self._anthropic_client = build_anthropic_client(
                         effective_key, self._anthropic_base_url, timeout=_fb_timeout,
                     )
    -                self._is_anthropic_oauth = _is_oauth_token(effective_key)
    +                self._is_anthropic_oauth = _is_oauth_token(effective_key) if fb_provider == "anthropic" else False
                     self.client = None
                     self._client_kwargs = {}
                 else:
    @@ -6554,10 +6625,13 @@ def _try_activate_fallback(self) -> bool:
                         self._replace_primary_openai_client(reason="fallback_timeout_apply")
     
                 # Re-evaluate prompt caching for the new provider/model
    -            is_native_anthropic = fb_api_mode == "anthropic_messages" and fb_provider == "anthropic"
    -            self._use_prompt_caching = (
    -                ("openrouter" in fb_base_url.lower() and "claude" in fb_model.lower())
    -                or is_native_anthropic
    +            self._use_prompt_caching, self._use_native_cache_layout = (
    +                self._anthropic_prompt_cache_policy(
    +                    provider=fb_provider,
    +                    base_url=fb_base_url,
    +                    api_mode=fb_api_mode,
    +                    model=fb_model,
    +                )
                 )
     
                 # Update context compressor limits for the fallback model.
    @@ -6617,6 +6691,12 @@ def _restore_primary_runtime(self) -> bool:
                 self.api_key = rt["api_key"]
                 self._client_kwargs = dict(rt["client_kwargs"])
                 self._use_prompt_caching = rt["use_prompt_caching"]
    +            # Default to native layout when the restored snapshot predates the
    +            # native-vs-proxy split (older sessions saved before this PR).
    +            self._use_native_cache_layout = rt.get(
    +                "use_native_cache_layout",
    +                self.api_mode == "anthropic_messages" and self.provider == "anthropic",
    +            )
     
                 # ── Rebuild client for the primary provider ──
                 if self.api_mode == "anthropic_messages":
    @@ -9317,12 +9397,19 @@ def run_conversation(
                     for idx, pfm in enumerate(self.prefill_messages):
                         api_messages.insert(sys_offset + idx, pfm.copy())
     
    -            # Apply Anthropic prompt caching for Claude models via OpenRouter.
    -            # Auto-detected: if model name contains "claude" and base_url is OpenRouter,
    -            # inject cache_control breakpoints (system + last 3 messages) to reduce
    -            # input token costs by ~75% on multi-turn conversations.
    +            # Apply Anthropic prompt caching for Claude models on native
    +            # Anthropic, OpenRouter, and third-party Anthropic-compatible
    +            # gateways. Auto-detected: if ``_use_prompt_caching`` is set,
    +            # inject cache_control breakpoints (system + last 3 messages)
    +            # to reduce input token costs by ~75% on multi-turn
    +            # conversations. Layout is chosen per endpoint by
    +            # ``_anthropic_prompt_cache_policy``.
                 if self._use_prompt_caching:
    -                api_messages = apply_anthropic_cache_control(api_messages, cache_ttl=self._cache_ttl, native_anthropic=(self.api_mode == 'anthropic_messages'))
    +                api_messages = apply_anthropic_cache_control(
    +                    api_messages,
    +                    cache_ttl=self._cache_ttl,
    +                    native_anthropic=self._use_native_cache_layout,
    +                )
     
                 # Safety net: strip orphaned tool results / add stubs for missing
                 # results before sending to the API.  Runs unconditionally — not
    @@ -9779,25 +9866,30 @@ def _stop_spinner():
                         if finish_reason == "length":
                             self._vprint(f"{self.log_prefix}⚠️  Response truncated (finish_reason='length') - model hit max output tokens", force=True)
     
    +                        # Normalize the truncated response to a single OpenAI-style
    +                        # message shape so text-continuation and tool-call retry
    +                        # work uniformly across chat_completions, bedrock_converse,
    +                        # and anthropic_messages.  For Anthropic we use the same
    +                        # adapter the agent loop already relies on so the rebuilt
    +                        # interim assistant message is byte-identical to what
    +                        # would have been appended in the non-truncated path.
    +                        _trunc_msg = None
    +                        if self.api_mode in ("chat_completions", "bedrock_converse"):
    +                            _trunc_msg = response.choices[0].message if (hasattr(response, "choices") and response.choices) else None
    +                        elif self.api_mode == "anthropic_messages":
    +                            from agent.anthropic_adapter import normalize_anthropic_response
    +                            _trunc_msg, _ = normalize_anthropic_response(
    +                                response, strip_tool_prefix=self._is_anthropic_oauth
    +                            )
    +
    +                        _trunc_content = getattr(_trunc_msg, "content", None) if _trunc_msg else None
    +                        _trunc_has_tool_calls = bool(getattr(_trunc_msg, "tool_calls", None)) if _trunc_msg else False
    +
                             # ── Detect thinking-budget exhaustion ──────────────
                             # When the model spends ALL output tokens on reasoning
                             # and has none left for the response, continuation
                             # retries are pointless.  Detect this early and give a
                             # targeted error instead of wasting 3 API calls.
    -                        _trunc_content = None
    -                        _trunc_has_tool_calls = False
    -                        if self.api_mode in ("chat_completions", "bedrock_converse"):
    -                            _trunc_msg = response.choices[0].message if (hasattr(response, "choices") and response.choices) else None
    -                            _trunc_content = getattr(_trunc_msg, "content", None) if _trunc_msg else None
    -                            _trunc_has_tool_calls = bool(getattr(_trunc_msg, "tool_calls", None)) if _trunc_msg else False
    -                        elif self.api_mode == "anthropic_messages":
    -                            # Anthropic response.content is a list of blocks
    -                            _text_parts = []
    -                            for _blk in getattr(response, "content", []):
    -                                if getattr(_blk, "type", None) == "text":
    -                                    _text_parts.append(getattr(_blk, "text", ""))
    -                            _trunc_content = "\n".join(_text_parts) if _text_parts else None
    -
                             # A response is "thinking exhausted" only when the model
                             # actually produced reasoning blocks but no visible text after
                             # them.  Models that do not use <think> tags (e.g. GLM-4.7 on
    @@ -9854,9 +9946,9 @@ def _stop_spinner():
                                     "error": _exhaust_error,
                                 }
     
    -                        if self.api_mode in ("chat_completions", "bedrock_converse"):
    -                            assistant_message = response.choices[0].message
    -                            if not assistant_message.tool_calls:
    +                        if self.api_mode in ("chat_completions", "bedrock_converse", "anthropic_messages"):
    +                            assistant_message = _trunc_msg
    +                            if assistant_message is not None and not _trunc_has_tool_calls:
                                     length_continue_retries += 1
                                     interim_msg = self._build_assistant_message(assistant_message, finish_reason)
                                     messages.append(interim_msg)
    @@ -9894,9 +9986,9 @@ def _stop_spinner():
                                         "error": "Response remained truncated after 3 continuation attempts",
                                     }
     
    -                        if self.api_mode in ("chat_completions", "bedrock_converse"):
    -                            assistant_message = response.choices[0].message
    -                            if assistant_message.tool_calls:
    +                        if self.api_mode in ("chat_completions", "bedrock_converse", "anthropic_messages"):
    +                            assistant_message = _trunc_msg
    +                            if assistant_message is not None and _trunc_has_tool_calls:
                                     if truncated_tool_call_retries < 1:
                                         truncated_tool_call_retries += 1
                                         self._vprint(

  • scripts/release.py

    @@ -80,6 +80,13 @@
         "[redacted:email]": "nish3451",
         "[redacted:email]": "Mibayy",
         "[redacted:email]": "sgaofen",
    +    "[redacted:email]": "nocoo",
    +    "[redacted:email]": "n-WN",
    +    "[redacted:email]": "keyuyuan",
    +    "[redacted:email]": "Only-Code-A",
    +    "[redacted:email]": "TroyMitchell911",
    +    "[redacted:email]": "zhongyueming1121",
    +    "[redacted:email]": "hansnow",
         # contributors (manual mapping from git names)
         "[redacted:email]": "asheriif",
         "[redacted:email]": "liujinkun2025",

  • tests/agent/test_auxiliary_client_anthropic_custom.py

    @@ -0,0 +1,107 @@
    +"""Tests for agent.auxiliary_client._try_custom_endpoint's anthropic_messages branch.
    +
    +When a user configures a custom endpoint with ``api_mode: anthropic_messages``
    +(e.g. MiniMax, Zhipu GLM, LiteLLM in Anthropic-proxy mode), auxiliary tasks
    +(compression, web_extract, session_search, title generation) must use the
    +native Anthropic transport rather than being silently downgraded to an
    +OpenAI-wire client that speaks the wrong protocol.
    +"""
    +
    +from __future__ import annotations
    +
    +from unittest.mock import MagicMock, patch
    +
    +import pytest
    +
    +
    [redacted:email](autouse=True)
    +def _clean_env(monkeypatch):
    +    for key in (
    +        "OPENAI_API_KEY", "OPENAI_BASE_URL",
    +        "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
    +    ):
    +        monkeypatch.delenv(key, raising=False)
    +
    +
    +def _install_anthropic_adapter_mocks():
    +    """Patch build_anthropic_client so the test doesn't need the SDK."""
    +    fake_client = MagicMock(name="anthropic_client")
    +    return patch(
    +        "agent.anthropic_adapter.build_anthropic_client",
    +        return_value=fake_client,
    +    ), fake_client
    +
    +
    +def test_custom_endpoint_anthropic_messages_builds_anthropic_wrapper():
    +    """api_mode=anthropic_messages → returns AnthropicAuxiliaryClient, not OpenAI."""
    +    from agent.auxiliary_client import _try_custom_endpoint, AnthropicAuxiliaryClient
    +
    +    with patch(
    +        "agent.auxiliary_client._resolve_custom_runtime",
    +        return_value=(
    +            "https://api.minimax.io/anthropic",
    +            "minimax-key",
    +            "anthropic_messages",
    +        ),
    +    ), patch(
    +        "agent.auxiliary_client._read_main_model",
    +        return_value="claude-sonnet-4-6",
    +    ):
    +        adapter_patch, fake_client = _install_anthropic_adapter_mocks()
    +        with adapter_patch:
    +            client, model = _try_custom_endpoint()
    +
    +    assert isinstance(client, AnthropicAuxiliaryClient), (
    +        "Custom endpoint with api_mode=anthropic_messages must return the "
    +        f"native Anthropic wrapper, got {type(client).__name__}"
    +    )
    +    assert model == "claude-sonnet-4-6"
    +    # Wrapper should NOT be marked as OAuth — third-party endpoints are
    +    # always API-key authenticated.
    +    assert client.api_key == "minimax-key"
    +    assert client.base_url == "https://api.minimax.io/anthropic"
    +
    +
    +def test_custom_endpoint_anthropic_messages_falls_back_when_sdk_missing():
    +    """Graceful degradation when anthropic SDK is unavailable."""
    +    from agent.auxiliary_client import _try_custom_endpoint
    +
    +    import_error = ImportError("anthropic package not installed")
    +
    +    with patch(
    +        "agent.auxiliary_client._resolve_custom_runtime",
    +        return_value=("https://api.minimax.io/anthropic", "k", "anthropic_messages"),
    +    ), patch(
    +        "agent.auxiliary_client._read_main_model",
    +        return_value="claude-sonnet-4-6",
    +    ), patch(
    +        "agent.anthropic_adapter.build_anthropic_client",
    +        side_effect=import_error,
    +    ):
    +        client, model = _try_custom_endpoint()
    +
    +    # Should fall back to an OpenAI-wire client rather than returning
    +    # (None, None) — the tool still needs to do *something*.
    +    assert client is not None
    +    assert model == "claude-sonnet-4-6"
    +    # OpenAI client, not AnthropicAuxiliaryClient.
    +    from agent.auxiliary_client import AnthropicAuxiliaryClient
    +    assert not isinstance(client, AnthropicAuxiliaryClient)
    +
    +
    +def test_custom_endpoint_chat_completions_still_uses_openai_wire():
    +    """Regression: default path (no api_mode) must remain OpenAI client."""
    +    from agent.auxiliary_client import _try_custom_endpoint, AnthropicAuxiliaryClient
    +
    +    with patch(
    +        "agent.auxiliary_client._resolve_custom_runtime",
    +        return_value=("https://api.example.com/v1", "key", None),
    +    ), patch(
    +        "agent.auxiliary_client._read_main_model",
    +        return_value="my-model",
    +    ):
    +        client, model = _try_custom_endpoint()
    +
    +    assert client is not None
    +    assert model == "my-model"
    +    assert not isinstance(client, AnthropicAuxiliaryClient)

  • tests/hermes_cli/test_detect_api_mode_for_url.py

    @@ -0,0 +1,70 @@
    +"""Tests for hermes_cli.runtime_provider._detect_api_mode_for_url.
    +
    +The helper maps base URLs to api_modes for three cases:
    +  * api.openai.com  → codex_responses
    +  * api.x.ai        → codex_responses
    +  * */anthropic     → anthropic_messages (third-party gateways like MiniMax,
    +                                          Zhipu GLM, LiteLLM proxies)
    +
    +Consolidating the /anthropic detection in this helper (instead of three
    +inline ``endswith`` checks spread across _resolve_runtime_from_pool_entry,
    +the explicit-provider path, and the api-key-provider path) means every
    +future update to the detection logic lives in one place.
    +"""
    +
    +from __future__ import annotations
    +
    +from hermes_cli.runtime_provider import _detect_api_mode_for_url
    +
    +
    +class TestCodexResponsesDetection:
    +    def test_openai_api_returns_codex_responses(self):
    +        assert _detect_api_mode_for_url("https://api.openai.com/v1") == "codex_responses"
    +
    +    def test_xai_api_returns_codex_responses(self):
    +        assert _detect_api_mode_for_url("https://api.x.ai/v1") == "codex_responses"
    +
    +    def test_openrouter_is_not_codex_responses(self):
    +        # api.openai.com check must exclude openrouter (which routes to openai-hosted models).
    +        assert _detect_api_mode_for_url("https://openrouter.ai/api/v1") is None
    +
    +
    +class TestAnthropicMessagesDetection:
    +    """Third-party gateways that speak the Anthropic protocol under /anthropic."""
    +
    +    def test_minimax_anthropic_endpoint(self):
    +        assert _detect_api_mode_for_url("https://api.minimax.io/anthropic") == "anthropic_messages"
    +
    +    def test_minimax_cn_anthropic_endpoint(self):
    +        assert _detect_api_mode_for_url("https://api.minimaxi.com/anthropic") == "anthropic_messages"
    +
    +    def test_dashscope_anthropic_endpoint(self):
    +        assert (
    +            _detect_api_mode_for_url("https://dashscope.aliyuncs.com/api/v2/apps/anthropic")
    +            == "anthropic_messages"
    +        )
    +
    +    def test_trailing_slash_tolerated(self):
    +        assert _detect_api_mode_for_url("https://api.minimax.io/anthropic/") == "anthropic_messages"
    +
    +    def test_uppercase_path_tolerated(self):
    +        assert _detect_api_mode_for_url("https://API.MINIMAX.IO/Anthropic") == "anthropic_messages"
    +
    +    def test_anthropic_in_middle_of_path_does_not_match(self):
    +        # The helper requires ``/anthropic`` as the path SUFFIX, not anywhere.
    +        # Protects against false positives on e.g. /anthropic/v1/models.
    +        assert _detect_api_mode_for_url("https://api.example.com/anthropic/v1") is None
    +
    +
    +class TestDefaultCase:
    +    def test_generic_url_returns_none(self):
    +        assert _detect_api_mode_for_url("https://api.together.xyz/v1") is None
    +
    +    def test_empty_string_returns_none(self):
    +        assert _detect_api_mode_for_url("") is None
    +
    +    def test_none_returns_none(self):
    +        assert _detect_api_mode_for_url(None) is None
    +
    +    def test_localhost_returns_none(self):
    +        assert _detect_api_mode_for_url("http://localhost:11434/v1") is None

  • tests/hermes_cli/test_update_config_clears_custom_fields.py

    @@ -0,0 +1,84 @@
    +"""Tests for hermes_cli.auth._update_config_for_provider clearing stale fields.
    +
    +When the user switches from a custom provider (e.g. MiniMax with
    +``api_mode: anthropic_messages``, ``api_key: [redacted:secret-assignment] to a built-in
    +provider (e.g. OpenRouter), the stale ``api_key`` and ``api_mode`` would
    +otherwise override the new provider's credentials and transport choice.
    +
    +Built-in providers that legitimately need a specific ``api_mode`` (copilot,
    +xai) compute it at request-resolution time in
    +``_copilot_runtime_api_mode`` / ``_detect_api_mode_for_url``, so removing
    +the persisted value here is safe.
    +"""
    +
    +from __future__ import annotations
    +
    +import yaml
    +
    +from hermes_cli.auth import _update_config_for_provider
    +from hermes_cli.config import get_config_path
    +
    +
    +def _read_model_cfg() -> dict:
    +    path = get_config_path()
    +    if not path.exists():
    +        return {}
    +    data = yaml.safe_load(path.read_text()) or {}
    +    model = data.get("model", {})
    +    return model if isinstance(model, dict) else {}
    +
    +
    +def _seed_custom_provider_config(api_mode: str = "anthropic_messages") -> None:
    +    """Write a config.yaml mimicking a user on a MiniMax-style custom provider."""
    +    path = get_config_path()
    +    path.parent.mkdir(parents=True, exist_ok=True)
    +    path.write_text(
    +        yaml.safe_dump(
    +            {
    +                "model": {
    +                    "provider": "custom",
    +                    "base_url": "https://api.minimax.io/anthropic",
    +                    "api_key": "mxp-stale-key",
    +                    "api_mode": api_mode,
    +                    "default": "claude-sonnet-4-6",
    +                }
    +            },
    +            sort_keys=False,
    +        )
    +    )
    +
    +
    +class TestUpdateConfigForProviderClearsStaleCustomFields:
    +    def test_switching_to_openrouter_clears_api_key_and_api_mode(self):
    +        _seed_custom_provider_config()
    +
    +        _update_config_for_provider(
    +            "openrouter",
    +            "https://openrouter.ai/api/v1",
    +            default_model="anthropic/claude-sonnet-4.6",
    +        )
    +
    +        model_cfg = _read_model_cfg()
    +        assert model_cfg.get("provider") == "openrouter"
    +        assert model_cfg.get("base_url") == "https://openrouter.ai/api/v1"
    +        assert "api_key" not in model_cfg, (
    +            "Stale custom api_key would leak into OpenRouter requests — must be cleared"
    +        )
    +        assert "api_mode" not in model_cfg, (
    +            "Stale api_mode=anthropic_messages from MiniMax would mis-route "
    +            "OpenRouter requests to the Anthropic SDK — must be cleared"
    +        )
    +
    +    def test_switching_to_nous_clears_stale_api_mode(self):
    +        _seed_custom_provider_config()
    +        _update_config_for_provider("nous", "https://inference-api.nousresearch.com/v1")
    +        model_cfg = _read_model_cfg()
    +        assert model_cfg.get("provider") == "nous"
    +        assert "api_mode" not in model_cfg
    +        assert "api_key" not in model_cfg
    +
    +    def test_switching_clears_codex_responses_api_mode(self):
    +        """Also covers codex_responses, not just anthropic_messages."""
    +        _seed_custom_provider_config(api_mode="codex_responses")
    +        _update_config_for_provider("openrouter", "https://openrouter.ai/api/v1")
    +        assert "api_mode" not in _read_model_cfg()

  • tests/run_agent/test_anthropic_prompt_cache_policy.py

    @@ -0,0 +1,152 @@
    +"""Tests for AIAgent._anthropic_prompt_cache_policy().
    +
    +The policy returns ``(should_cache, use_native_layout)`` for five endpoint
    +classes. The test matrix pins the decision for each so a regression (e.g.
    +silently dropping caching on third-party Anthropic gateways, or applying
    +the native layout on OpenRouter) surfaces loudly.
    +"""
    +
    +from __future__ import annotations
    +
    +from unittest.mock import MagicMock
    +
    +from run_agent import AIAgent
    +
    +
    +def _make_agent(
    +    *,
    +    provider: str = "openrouter",
    +    base_url: str = "https://openrouter.ai/api/v1",
    +    api_mode: str = "chat_completions",
    +    model: str = "anthropic/claude-sonnet-4.6",
    +) -> AIAgent:
    +    agent = AIAgent.__new__(AIAgent)
    +    agent.provider = provider
    +    agent.base_url = base_url
    +    agent.api_mode = api_mode
    +    agent.model = model
    +    agent._base_url_lower = (base_url or "").lower()
    +    agent.client = MagicMock()
    +    agent.quiet_mode = True
    +    return agent
    +
    +
    +class TestNativeAnthropic:
    +    def test_claude_on_native_anthropic_caches_with_native_layout(self):
    +        agent = _make_agent(
    +            provider="anthropic",
    +            base_url="https://api.anthropic.com",
    +            api_mode="anthropic_messages",
    +            model="claude-sonnet-4-6",
    +        )
    +        assert agent._anthropic_prompt_cache_policy() == (True, True)
    +
    +    def test_api_anthropic_host_detected_even_when_provider_label_differs(self):
    +        # Some pool configurations label native Anthropic as "anthropic-direct"
    +        # or similar; falling back to hostname keeps caching on.
    +        agent = _make_agent(
    +            provider="anthropic-direct",
    +            base_url="https://api.anthropic.com",
    +            api_mode="anthropic_messages",
    +            model="claude-opus-4.6",
    +        )
    +        assert agent._anthropic_prompt_cache_policy() == (True, True)
    +
    +
    +class TestOpenRouter:
    +    def test_claude_on_openrouter_caches_with_envelope_layout(self):
    +        agent = _make_agent(
    +            provider="openrouter",
    +            base_url="https://openrouter.ai/api/v1",
    +            api_mode="chat_completions",
    +            model="anthropic/claude-sonnet-4.6",
    +        )
    +        should, native = agent._anthropic_prompt_cache_policy()
    +        assert should is True
    +        assert native is False  # OpenRouter uses envelope layout
    +
    +    def test_non_claude_on_openrouter_does_not_cache(self):
    +        agent = _make_agent(
    +            provider="openrouter",
    +            base_url="https://openrouter.ai/api/v1",
    +            api_mode="chat_completions",
    +            model="openai/gpt-5.4",
    +        )
    +        assert agent._anthropic_prompt_cache_policy() == (False, False)
    +
    +
    +class TestThirdPartyAnthropicGateway:
    +    """Third-party gateways speaking the Anthropic protocol (MiniMax, Zhipu GLM, LiteLLM)."""
    +
    +    def test_minimax_claude_via_anthropic_messages(self):
    +        agent = _make_agent(
    +            provider="custom",
    +            base_url="https://api.minimax.io/anthropic",
    +            api_mode="anthropic_messages",
    +            model="claude-sonnet-4-6",
    +        )
    +        should, native = agent._anthropic_prompt_cache_policy()
    +        assert should is True, "Third-party Anthropic gateway with Claude must cache"
    +        assert native is True, "Third-party Anthropic gateway uses native cache_control layout"
    +
    +    def test_third_party_without_claude_name_does_not_cache(self):
    +        # A provider exposing e.g. GLM via anthropic_messages transport — we
    +        # don't know whether it supports cache_control, so stay conservative.
    +        agent = _make_agent(
    +            provider="custom",
    +            base_url="https://api.minimax.io/anthropic",
    +            api_mode="anthropic_messages",
    +            model="minimax-m2.7",
    +        )
    +        assert agent._anthropic_prompt_cache_policy() == (False, False)
    +
    +
    +class TestOpenAIWireFormatOnCustomProvider:
    +    """A custom provider using chat_completions (OpenAI wire) should NOT get caching."""
    +
    +    def test_custom_openai_wire_does_not_cache_even_with_claude_name(self):
    +        # This is the blocklist risk #9621 failed to avoid: sending
    +        # cache_control fields in OpenAI-wire JSON can trip strict providers
    +        # that reject unknown keys.  Stay off unless the transport is
    +        # explicitly anthropic_messages or the aggregator is OpenRouter.
    +        agent = _make_agent(
    +            provider="custom",
    +            base_url="https://api.fireworks.ai/inference/v1",
    +            api_mode="chat_completions",
    +            model="claude-sonnet-4",
    +        )
    +        assert agent._anthropic_prompt_cache_policy() == (False, False)
    +
    +
    +class TestExplicitOverrides:
    +    """Policy accepts keyword overrides for switch_model / fallback activation."""
    +
    +    def test_overrides_take_precedence_over_self(self):
    +        agent = _make_agent(
    +            provider="openrouter",
    +            base_url="https://openrouter.ai/api/v1",
    +            api_mode="chat_completions",
    +            model="openai/gpt-5.4",
    +        )
    +        # Simulate switch_model evaluating cache policy for a Claude target
    +        # before self.model is mutated.
    +        should, native = agent._anthropic_prompt_cache_policy(
    +            model="anthropic/claude-sonnet-4.6",
    +        )
    +        assert (should, native) == (True, False)
    +
    +    def test_fallback_target_evaluated_independently(self):
    +        # Starting on native Anthropic but falling back to OpenRouter.
    +        agent = _make_agent(
    +            provider="anthropic",
    +            base_url="https://api.anthropic.com",
    +            api_mode="anthropic_messages",
    +            model="claude-opus-4.6",
    +        )
    +        should, native = agent._anthropic_prompt_cache_policy(
    +            provider="openrouter",
    +            base_url="https://openrouter.ai/api/v1",
    +            api_mode="chat_completions",
    +            model="anthropic/claude-sonnet-4.6",
    +        )
    +        assert (should, native) == (True, False)

  • tests/run_agent/test_anthropic_third_party_oauth_guard.py

    @@ -0,0 +1,182 @@
    +"""Tests for ``_is_anthropic_oauth`` guard against third-party Anthropic-compatible providers.
    +
    +The invariant: ``self._is_anthropic_oauth`` must only ever be True when
    +``self.provider == 'anthropic'`` (native Anthropic).  Third-party providers
    +that speak the Anthropic protocol (MiniMax, Zhipu GLM, Alibaba DashScope,
    +Kimi, LiteLLM proxies, etc.) must never trip OAuth code paths — doing so
    +injects Claude-Code identity headers and system prompts that cause
    +401/403 from those endpoints.
    +
    +This test class covers all FIVE sites that assign ``_is_anthropic_oauth``:
    +
    +1. ``AIAgent.__init__``                              (line ~1022)
    +2. ``AIAgent.switch_model``                          (line ~1832)
    +3. ``AIAgent._try_refresh_anthropic_client_credentials`` (line ~5335)
    +4. ``AIAgent._swap_credential``                      (line ~5378)
    +5. ``AIAgent._try_activate_fallback``                (line ~6536)
    +"""
    +
    +from __future__ import annotations
    +
    +from unittest.mock import MagicMock, patch
    +
    +import pytest
    +
    +from run_agent import AIAgent
    +
    +
    +# A plausible-looking OAuth token (``sk-ant-`` without the ``-api`` suffix).
    +_OAUTH_LIKE_TOKEN = "[redacted:secret-assignment]"
    +_API_KEY_TOKEN = "[redacted:secret-assignment]"
    +
    +
    [redacted:email]
    +def agent():
    +    """Minimal AIAgent construction, skipping tool discovery."""
    +    with (
    +        patch("run_agent.get_tool_definitions", return_value=[]),
    +        patch("run_agent.check_toolset_requirements", return_value={}),
    +        patch("run_agent.OpenAI"),
    +    ):
    +        a = AIAgent(
    +            api_key="[redacted:secret-assignment]",
    +            base_url="https://openrouter.ai/api/v1",
    +            quiet_mode=True,
    +            skip_context_files=True,
    +            skip_memory=True,
    +        )
    +        a.client = MagicMock()
    +        return a
    +
    +
    +class TestOAuthFlagOnRefresh:
    +    """Site 3 — _try_refresh_anthropic_client_credentials."""
    +
    +    def test_third_party_provider_refresh_is_noop(self, agent):
    +        """Refresh path returns False immediately when provider != anthropic — the
    +        OAuth flag can never be mutated for third-party providers. Double-defended
    +        by the per-assignment guard at line ~5393 so future refactors can't
    +        reintroduce the bug."""
    +        agent.api_mode = "anthropic_messages"
    +        agent.provider = "minimax"          # ← third-party
    +        agent._anthropic_api_key = "***"
    +        agent._anthropic_client = MagicMock()
    +        agent._is_anthropic_oauth = False
    +
    +        with (
    +            patch("agent.anthropic_adapter.resolve_anthropic_token",
    +                  return_value=_OAUTH_LIKE_TOKEN),
    +            patch("agent.anthropic_adapter.build_anthropic_client",
    +                  return_value=MagicMock()),
    +        ):
    +            result = agent._try_refresh_anthropic_client_credentials()
    +
    +        # The function short-circuits on non-anthropic providers.
    +        assert result is False
    +        # And the flag is untouched regardless.
    +        assert agent._is_anthropic_oauth is False
    +
    +    def test_native_anthropic_preserves_existing_oauth_behaviour(self, agent):
    +        """Regression: native anthropic with OAuth token still flips flag to True."""
    +        agent.api_mode = "anthropic_messages"
    +        agent.provider = "anthropic"
    +        agent._anthropic_api_key = "***"
    +        agent._anthropic_client = MagicMock()
    +        agent._is_anthropic_oauth = False
    +
    +        with (
    +            patch("agent.anthropic_adapter.resolve_anthropic_token",
    +                  return_value=_OAUTH_LIKE_TOKEN),
    +            patch("agent.anthropic_adapter.build_anthropic_client",
    +                  return_value=MagicMock()),
    +        ):
    +            result = agent._try_refresh_anthropic_client_credentials()
    +
    +        assert result is True
    +        assert agent._is_anthropic_oauth is True
    +
    +
    +class TestOAuthFlagOnCredentialSwap:
    +    """Site 4 — _swap_credential (credential pool rotation)."""
    +
    +    def test_pool_swap_on_third_party_never_flips_oauth(self, agent):
    +        agent.api_mode = "anthropic_messages"
    +        agent.provider = "glm"              # ← Zhipu GLM via /anthropic
    +        agent._anthropic_api_key = "[redacted:secret-assignment]"
    +        agent._anthropic_base_url = "https://open.bigmodel.cn/api/anthropic"
    +        agent._anthropic_client = MagicMock()
    +        agent._is_anthropic_oauth = False
    +
    +        entry = MagicMock()
    +        entry.runtime_api_key = [redacted:secret-assignment]
    +        entry.runtime_base_url = "https://open.bigmodel.cn/api/anthropic"
    +
    +        with patch("agent.anthropic_adapter.build_anthropic_client",
    +                   return_value=MagicMock()):
    +            agent._swap_credential(entry)
    +
    +        assert agent._is_anthropic_oauth is False
    +
    +
    +class TestOAuthFlagOnConstruction:
    +    """Site 1 — AIAgent.__init__ on a third-party anthropic_messages provider."""
    +
    +    def test_minimax_init_does_not_flip_oauth(self):
    +        with (
    +            patch("run_agent.get_tool_definitions", return_value=[]),
    +            patch("run_agent.check_toolset_requirements", return_value={}),
    +            patch("agent.anthropic_adapter.build_anthropic_client",
    +                  return_value=MagicMock()),
    +            # Simulate a stale ANTHROPIC_TOKEN in the env — the init code
    +            # MUST NOT fall back to it when provider != anthropic.
    +            patch("agent.anthropic_adapter.resolve_anthropic_token",
    +                  return_value=_OAUTH_LIKE_TOKEN),
    +        ):
    +            agent = AIAgent(
    +                api_key="[redacted:secret-assignment]",
    +                base_url="https://api.minimax.io/anthropic",
    +                provider="minimax",
    +                api_mode="anthropic_messages",
    +                model="claude-sonnet-4-6",
    +                quiet_mode=True,
    +                skip_context_files=True,
    +                skip_memory=True,
    +            )
    +
    +        # The effective key should be the explicit minimax-key, not the
    +        # stale Anthropic OAuth token, and the OAuth flag must be False.
    +        assert agent._anthropic_api_key == "minimax-key-1234"
    +        assert agent._is_anthropic_oauth is False
    +
    +
    +class TestOAuthFlagOnFallbackActivation:
    +    """Site 5 — _try_activate_fallback targeting a third-party Anthropic endpoint."""
    +
    +    def test_fallback_to_third_party_does_not_flip_oauth(self, agent):
    +        """Directly mimic the post-fallback assignment at line ~6537."""
    +        from agent.anthropic_adapter import _is_oauth_token
    +
    +        # Emulate the relevant lines of _try_activate_fallback without
    +        # running the entire recovery stack (which pulls in streaming,
    +        # sessions, etc.).
    +        fb_provider = "minimax"
    +        effective_key = _OAUTH_LIKE_TOKEN
    +        agent._is_anthropic_oauth = (
    +            _is_oauth_token(effective_key) if fb_provider == "anthropic" else False
    +        )
    +        assert agent._is_anthropic_oauth is False
    +
    +
    +class TestApiKeyTokensAlwaysSafe:
    +    """Regression: plain API-key shapes must always resolve to non-OAuth, any provider."""
    +
    +    def test_native_anthropic_with_api_key_token(self):
    +        from agent.anthropic_adapter import _is_oauth_token
    +        assert _is_oauth_token(_API_KEY_TOKEN) is False
    +
    +    def test_third_party_key_shape(self):
    +        from agent.anthropic_adapter import _is_oauth_token
    +        # Third-party key shapes (MiniMax 'mxp-...', GLM 'glm.sess.', etc.)
    +        # already return False from _is_oauth_token; the guard adds a second
    +        # defense line in case future token formats accidentally look OAuth-y.
    +        assert _is_oauth_token("mxp-abcdef123") is False

  • tests/run_agent/test_anthropic_truncation_continuation.py

    @@ -0,0 +1,114 @@
    +"""Regression test for anthropic_messages truncation continuation.
    +
    +When an Anthropic response hits ``stop_reason: max_tokens`` (mapped to
    +``finish_reason == 'length'`` in run_agent), the agent must retry with
    +a continuation prompt — the same behavior it has always had for
    +chat_completions and bedrock_converse.  Before this PR, the
    +``if self.api_mode in ('chat_completions', 'bedrock_converse'):`` guard
    +silently dropped Anthropic-wire truncations on the floor, returning a
    +half-finished response with no retry.
    +
    +We don't exercise the full agent loop here (it's 3000 lines of inference,
    +streaming, plugin hooks, etc.) — instead we verify the normalization
    +adapter produces exactly the shape the continuation block now consumes.
    +"""
    +
    +from __future__ import annotations
    +
    +from types import SimpleNamespace
    +
    +import pytest
    +
    +
    +def _make_anthropic_text_block(text: str) -> SimpleNamespace:
    +    return SimpleNamespace(type="text", text=text)
    +
    +
    +def _make_anthropic_tool_use_block(name: str = "my_tool") -> SimpleNamespace:
    +    return SimpleNamespace(
    +        type="tool_use",
    +        id="toolu_01",
    +        name=name,
    +        input={"foo": "bar"},
    +    )
    +
    +
    +def _make_anthropic_response(blocks, stop_reason: str = "max_tokens"):
    +    return SimpleNamespace(
    +        id="msg_01",
    +        type="message",
    +        role="assistant",
    +        model="claude-sonnet-4-6",
    +        content=blocks,
    +        stop_reason=stop_reason,
    +        stop_sequence=None,
    +        usage=SimpleNamespace(input_tokens=100, output_tokens=200),
    +    )
    +
    +
    +class TestTruncatedAnthropicResponseNormalization:
    +    """normalize_anthropic_response() gives us the shape _build_assistant_message expects."""
    +
    +    def test_text_only_truncation_produces_text_content_no_tool_calls(self):
    +        """Pure-text Anthropic truncation → continuation path should fire."""
    +        from agent.anthropic_adapter import normalize_anthropic_response
    +
    +        response = _make_anthropic_response(
    +            [_make_anthropic_text_block("partial response that was cut off")]
    +        )
    +        msg, finish = normalize_anthropic_response(response)
    +
    +        # The continuation block checks these two attributes:
    +        #   assistant_message.content  → appended to truncated_response_prefix
    +        #   assistant_message.tool_calls → guards the text-retry branch
    +        assert msg.content is not None
    +        assert "partial response" in msg.content
    +        assert not msg.tool_calls, (
    +            "Pure-text truncation must have no tool_calls so the text-continuation "
    +            "branch (not the tool-retry branch) fires"
    +        )
    +        assert finish == "length", "max_tokens stop_reason must map to OpenAI-style 'length'"
    +
    +    def test_truncated_tool_call_produces_tool_calls(self):
    +        """Tool-use truncation → tool-call retry path should fire."""
    +        from agent.anthropic_adapter import normalize_anthropic_response
    +
    +        response = _make_anthropic_response(
    +            [
    +                _make_anthropic_text_block("thinking..."),
    +                _make_anthropic_tool_use_block(),
    +            ]
    +        )
    +        msg, finish = normalize_anthropic_response(response)
    +
    +        assert bool(msg.tool_calls), (
    +            "Truncation mid-tool_use must expose tool_calls so the "
    +            "tool-call retry branch fires instead of text continuation"
    +        )
    +        assert finish == "length"
    +
    +    def test_empty_content_does_not_crash(self):
    +        """Empty response.content — defensive: treat as a truncation with no text."""
    +        from agent.anthropic_adapter import normalize_anthropic_response
    +
    +        response = _make_anthropic_response([])
    +        msg, finish = normalize_anthropic_response(response)
    +        # Depending on the adapter, content may be "" or None — both are
    +        # acceptable; what matters is no exception.
    +        assert msg is not None
    +        assert not msg.tool_calls
    +
    +
    +class TestContinuationLogicBranching:
    +    """Symbolic check that the api_mode gate now includes anthropic_messages."""
    +
    +    @pytest.mark.parametrize("api_mode", ["chat_completions", "bedrock_converse", "anthropic_messages"])
    +    def test_all_three_api_modes_hit_continuation_branch(self, api_mode):
    +        # The guard in run_agent.py is:
    +        #   if self.api_mode in ("chat_completions", "bedrock_converse", "anthropic_messages"):
    +        assert api_mode in ("chat_completions", "bedrock_converse", "anthropic_messages")
    +
    +    def test_codex_responses_still_excluded(self):
    +        # codex_responses has its own truncation path (not continuation-based)
    +        # and should NOT be routed through the shared block.
    +        assert "codex_responses" not in ("chat_completions", "bedrock_converse", "anthropic_messages")

• #15059 fix(aux-client): honor api_mode: anthropic_messages for named custom providers

  merged to main

  files: agent/auxiliary_client.py, hermes_cli/runtime_provider.py, tests/agent/test_auxiliary_named_custom_providers.py

  Show the diff

  • agent/auxiliary_client.py

    @@ -1736,7 +1736,7 @@ def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = ""):
                            "but no endpoint credentials found")
             return None, None
     
    -    # ── Named custom providers (config.yaml custom_providers list) ───
    +    # ── Named custom providers (config.yaml providers dict / custom_providers list) ───
         try:
             from hermes_cli.runtime_provider import _get_named_custom_provider
             custom_entry = _get_named_custom_provider(provider)
    @@ -1747,16 +1747,51 @@ def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = ""):
                 if not custom_key and custom_key_env:
                     custom_key = os.getenv(custom_key_env, "").strip()
                 custom_key = custom_key or "no-key-required"
    +            # An explicit per-task api_mode override (from _resolve_task_provider_model)
    +            # wins; otherwise fall back to what the provider entry declared.
    +            entry_api_mode = (api_mode or custom_entry.get("api_mode") or "").strip()
                 if custom_base:
                     final_model = _normalize_resolved_model(
                         model or custom_entry.get("model") or _read_main_model() or "gpt-4o-mini",
                         provider,
                     )
    -                client = OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base)
    -                client = _wrap_if_needed(client, final_model, custom_base)
                     logger.debug(
    -                    "resolve_provider_client: named custom provider %r (%s)",
    -                    provider, final_model)
    +                    "resolve_provider_client: named custom provider %r (%s, api_mode=%s)",
    +                    provider, final_model, entry_api_mode or "chat_completions")
    +                # anthropic_messages: route through the Anthropic Messages API
    +                # via AnthropicAuxiliaryClient. Mirrors the anonymous-custom
    +                # branch in _try_custom_endpoint(). See #15033.
    +                if entry_api_mode == "anthropic_messages":
    +                    try:
    +                        from agent.anthropic_adapter import build_anthropic_client
    +                        real_client = build_anthropic_client(custom_key, custom_base)
    +                    except ImportError:
    +                        logger.warning(
    +                            "Named custom provider %r declares api_mode="
    +                            "anthropic_messages but the anthropic SDK is not "
    +                            "installed — falling back to OpenAI-wire.",
    +                            provider,
    +                        )
    +                        client = OpenAI(api_key=[redacted:secret-assignment] base_url=custom_base)
    +                        return (_to_async_client(client, final_model) if async_mode
    +                                else (client, final_model))
    +                    sync_anthropic = AnthropicAuxiliaryClient(
    +                        real_client, final_model, custom_key, custom_base, is_oauth=False,
    +                    )
    +                    if async_mode:
    +                        return AsyncAnthropicAuxiliaryClient(sync_anthropic), final_model
    +                    return sync_anthropic, final_model
    +                client = OpenAI(api_key=[redacted:secret-assignment] 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
    +                # flows through here.
    +                if entry_api_mode == "codex_responses" and not isinstance(
    +                    client, CodexAuxiliaryClient
    +                ):
    +                    client = CodexAuxiliaryClient(client, final_model)
    +                else:
    +                    client = _wrap_if_needed(client, final_model, custom_base)
                     return (_to_async_client(client, final_model) if async_mode
                             else (client, final_model))
                 logger.warning(

  • hermes_cli/runtime_provider.py

    @@ -323,12 +323,16 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
                     # Found match by provider key
                     base_url = entry.get("api") or entry.get("url") or entry.get("base_url") or ""
                     if base_url:
    -                    return {
    +                    result = {
                             "name": entry.get("name", ep_name),
                             "base_url": base_url.strip(),
                             "api_key": resolved_api_key,
                             "model": entry.get("default_model", ""),
                         }
    +                    api_mode = _parse_api_mode(entry.get("api_mode"))
    +                    if api_mode:
    +                        result["api_mode"] = api_mode
    +                    return result
                 # Also check the 'name' field if present
                 display_name = entry.get("name", "")
                 if display_name:
    @@ -337,12 +341,16 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
                         # Found match by display name
                         base_url = entry.get("api") or entry.get("url") or entry.get("base_url") or ""
                         if base_url:
    -                        return {
    +                        result = {
                                 "name": display_name,
                                 "base_url": base_url.strip(),
                                 "api_key": resolved_api_key,
                                 "model": entry.get("default_model", ""),
                             }
    +                        api_mode = _parse_api_mode(entry.get("api_mode"))
    +                        if api_mode:
    +                            result["api_mode"] = api_mode
    +                        return result
     
         # Fall back to custom_providers: list (legacy format)
         custom_providers = config.get("custom_providers")

  • tests/agent/test_auxiliary_named_custom_providers.py

    @@ -252,3 +252,158 @@ def test_explicit_provider_passes_api_mode(self, tmp_path):
             mock_gcc.assert_called_once()
             _, kwargs = mock_gcc.call_args
             assert kwargs.get("api_mode") == "chat_completions"
    +
    +
    +class TestProvidersDictApiModeAnthropicMessages:
    +    """Regression guard for #15033.
    +
    +    Named providers declared under the ``providers:`` dict with
    +    ``api_mode: anthropic_messages`` must route auxiliary calls through
    +    the Anthropic Messages API (via AnthropicAuxiliaryClient), not
    +    through an OpenAI chat-completions client.
    +
    +    The bug had two halves: the providers-dict branch of
    +    ``_get_named_custom_provider`` dropped the ``api_mode`` field, and
    +    ``resolve_provider_client``'s named-custom branch never read it.
    +    """
    +
    +    def test_providers_dict_propagates_api_mode(self, tmp_path, monkeypatch):
    +        monkeypatch.setenv("MYRELAY_API_KEY", "sk-test")
    +        _write_config(tmp_path, {
    +            "providers": {
    +                "myrelay": {
    +                    "name": "myrelay",
    +                    "base_url": "https://example-relay.test/anthropic",
    +                    "key_env": "MYRELAY_API_KEY",
    +                    "api_mode": "anthropic_messages",
    +                    "default_model": "claude-opus-4-7",
    +                },
    +            },
    +        })
    +        from hermes_cli.runtime_provider import _get_named_custom_provider
    +        entry = _get_named_custom_provider("myrelay")
    +        assert entry is not None
    +        assert entry.get("api_mode") == "anthropic_messages"
    +        assert entry.get("base_url") == "https://example-relay.test/anthropic"
    +        assert entry.get("api_key") == "sk-test"
    +
    +    def test_providers_dict_invalid_api_mode_is_dropped(self, tmp_path):
    +        _write_config(tmp_path, {
    +            "providers": {
    +                "weird": {
    +                    "name": "weird",
    +                    "base_url": "https://example.test",
    +                    "api_mode": "bogus_nonsense",
    +                    "default_model": "x",
    +                },
    +            },
    +        })
    +        from hermes_cli.runtime_provider import _get_named_custom_provider
    +        entry = _get_named_custom_provider("weird")
    +        assert entry is not None
    +        assert "api_mode" not in entry
    +
    +    def test_providers_dict_without_api_mode_is_unchanged(self, tmp_path):
    +        _write_config(tmp_path, {
    +            "providers": {
    +                "localchat": {
    +                    "name": "localchat",
    +                    "base_url": "http://127.0.0.1:1234/v1",
    +                    "api_key": "local-key",
    +                    "default_model": "llama-3",
    +                },
    +            },
    +        })
    +        from hermes_cli.runtime_provider import _get_named_custom_provider
    +        entry = _get_named_custom_provider("localchat")
    +        assert entry is not None
    +        assert "api_mode" not in entry
    +
    +    def test_resolve_provider_client_returns_anthropic_client(self, tmp_path, monkeypatch):
    +        """Named custom provider with api_mode=anthropic_messages must
    +        route through AnthropicAuxiliaryClient."""
    +        monkeypatch.setenv("MYRELAY_API_KEY", "sk-test")
    +        _write_config(tmp_path, {
    +            "providers": {
    +                "myrelay": {
    +                    "name": "myrelay",
    +                    "base_url": "https://example-relay.test/anthropic",
    +                    "key_env": "MYRELAY_API_KEY",
    +                    "api_mode": "anthropic_messages",
    +                    "default_model": "claude-opus-4-7",
    +                },
    +            },
    +        })
    +        from agent.auxiliary_client import (
    +            resolve_provider_client,
    +            AnthropicAuxiliaryClient,
    +            AsyncAnthropicAuxiliaryClient,
    +        )
    +        sync_client, sync_model = resolve_provider_client("myrelay", async_mode=False)
    +        assert isinstance(sync_client, AnthropicAuxiliaryClient), (
    +            f"expected AnthropicAuxiliaryClient, got {type(sync_client).__name__}"
    +        )
    +        assert sync_model == "claude-opus-4-7"
    +
    +        async_client, async_model = resolve_provider_client("myrelay", async_mode=True)
    +        assert isinstance(async_client, AsyncAnthropicAuxiliaryClient), (
    +            f"expected AsyncAnthropicAuxiliaryClient, got {type(async_client).__name__}"
    +        )
    +        assert async_model == "claude-opus-4-7"
    +
    +    def test_aux_task_override_routes_named_provider_to_anthropic(self, tmp_path, monkeypatch):
    +        """The full chain: auxiliary.<task>.provider: myrelay with
    +        api_mode anthropic_messages must produce an Anthropic client."""
    +        monkeypatch.setenv("MYRELAY_API_KEY", "sk-test")
    +        _write_config(tmp_path, {
    +            "providers": {
    +                "myrelay": {
    +                    "name": "myrelay",
    +                    "base_url": "https://example-relay.test/anthropic",
    +                    "key_env": "MYRELAY_API_KEY",
    +                    "api_mode": "anthropic_messages",
    +                    "default_model": "claude-opus-4-7",
    +                },
    +            },
    +            "auxiliary": {
    +                "flush_memories": {
    +                    "provider": "myrelay",
    +                    "model": "claude-sonnet-4.6",
    +                },
    +            },
    +            "model": {"provider": "openrouter", "default": "anthropic/claude-sonnet-4.6"},
    +        })
    +        from agent.auxiliary_client import (
    +            get_async_text_auxiliary_client,
    +            get_text_auxiliary_client,
    +            AnthropicAuxiliaryClient,
    +            AsyncAnthropicAuxiliaryClient,
    +        )
    +        async_client, async_model = get_async_text_auxiliary_client("flush_memories")
    +        assert isinstance(async_client, AsyncAnthropicAuxiliaryClient)
    +        assert async_model == "claude-sonnet-4.6"
    +
    +        sync_client, sync_model = get_text_auxiliary_client("flush_memories")
    +        assert isinstance(sync_client, AnthropicAuxiliaryClient)
    +        assert sync_model == "claude-sonnet-4.6"
    +
    +    def test_provider_without_api_mode_still_uses_openai(self, tmp_path):
    +        """Named providers that don't declare api_mode should still go
    +        through the plain OpenAI-wire path (no regression)."""
    +        _write_config(tmp_path, {
    +            "providers": {
    +                "localchat": {
    +                    "name": "localchat",
    +                    "base_url": "http://127.0.0.1:1234/v1",
    +                    "api_key": "local-key",
    +                    "default_model": "llama-3",
    +                },
    +            },
    +        })
    +        from agent.auxiliary_client import resolve_provider_client
    +        from openai import OpenAI, AsyncOpenAI
    +        sync_client, _ = resolve_provider_client("localchat", async_mode=False)
    +        # sync returns the raw OpenAI client
    +        assert isinstance(sync_client, OpenAI)
    +        async_client, _ = resolve_provider_client("localchat", async_mode=True)
    +        assert isinstance(async_client, AsyncOpenAI)

• #85466 fix(auxiliary): keep /anthropic base_url for anthropic_messages custom endpoints (salvage #64891)

  merged to main

  files: agent/auxiliary_client.py, tests/agent/test_auxiliary_explicit_base_anthropic.py