feat(provider): 完成阶段E协议适配、国内预设与模型路由

backend/app/providers/anthropic_messages.py

@@ -0,0 +1,163 @@
+"""Native Anthropic Messages protocol with incrementally decoded content blocks."""
+
+import json
+from contextlib import aclosing
+
+from app.contracts import MessageRole, ModelEventType, ModelRequest
+from app.providers.base import ProviderError, ProviderToolCall, ProviderTurn
+from app.providers.http_base import (
+    UsageTracker, check_error, decode_tool_arguments, invalid_response, list_value,
+    object_value, string_value, token_count, truncated_stream,
+)
+from app.providers.openai_compatible import OpenAICompatibleProvider
+from app.providers.tool_names import mapped_tool_names
+
+
+class AnthropicMessagesProvider(OpenAICompatibleProvider):
+    stream_path = "/messages"
+
+    def _headers(self) -> dict[str, str]:
+        headers = super()._headers()
+        authorization = headers.pop("Authorization", None)
+        if authorization:
+            headers["x-api-key"] = authorization.removeprefix("Bearer ")
+        headers["anthropic-version"] = "2023-06-01"
+        return headers
+
+    def _payload(self, request: ModelRequest, *, stream: bool) -> dict[str, object]:
+        systems = [request.system] if request.system else []
+        messages = []
+        for message in request.messages:
+            if message.role == MessageRole.system:
+                systems.append(message.content)
+                continue
+            if message.role == MessageRole.tool:
+                if not message.tool_call_id:
+                    raise ProviderError("PROVIDER_INVALID_REQUEST", "Tool result requires a call identifier.")
+                role = "user"
+                content = [{"type": "tool_result", "tool_use_id": message.tool_call_id, "content": message.content}]
+            else:
+                role = message.role.value
+                content = [{"type": "text", "text": message.content}] if message.content else []
+                content += [{"type": "tool_use", "id": call.tool_call_id, "name": call.name,
+                             "input": call.arguments} for call in message.tool_calls]
+            if not content:
+                continue
+            if messages and messages[-1]["role"] == role:
+                messages[-1]["content"].extend(content)
+            else:
+                messages.append({"role": role, "content": content})
+        payload: dict[str, object] = {"model": request.model, "messages": messages,
+                                     "max_tokens": request.max_tokens or 4096, "stream": stream}
+        if systems:
+            payload["system"] = "\n\n".join(systems)
+        if request.tools:
+            payload["tools"] = [{"name": tool.name, "description": tool.description,
+                                 "input_schema": tool.parameters} for tool in request.tools]
+        if request.temperature is not None:
+            payload["temperature"] = request.temperature
+        if request.response_format is not None:
+            format_ = request.response_format
+            if format_.get("type") != "json_schema":
+                raise ProviderError("PROVIDER_INVALID_REQUEST", "Messages requires a JSON schema response format.")
+            schema = object_value(format_.get("json_schema"))
+            payload["output_config"] = {"format": {"type": "json_schema", "schema": object_value(schema.get("schema"))}}
+        return payload
+
+    @mapped_tool_names
+    async def complete(self, request: ModelRequest) -> ProviderTurn:
+        data = await self._request("POST", self.stream_path, json=self._payload(request, stream=False))
+        texts = []
+        calls = []
+        for raw in list_value(data.get("content")):
+            block = object_value(raw)
+            if block.get("type") == "text":
+                texts.append(string_value(block.get("text")))
+            elif block.get("type") == "tool_use":
+                calls.append(ProviderToolCall(
+                    tool_call_id=string_value(block.get("id"), nonempty=True),
+                    name=string_value(block.get("name"), nonempty=True),
+                    arguments=decode_tool_arguments(block.get("input")),
+                ))
+        return ProviderTurn(text="".join(texts) or None, tool_calls=calls,
+                            **UsageTracker(cache_tokens=True).update(data.get("usage") or {}))
+
+    async def _events(self, request: ModelRequest):
+        blocks: dict[int, dict] = {}
+        usage = UsageTracker(cache_tokens=True)
+        started = False
+        async with aclosing(self._stream_json(self._payload(request, stream=True))) as chunks:
+            async for data in chunks:
+                kind = string_value(data.get("type"), nonempty=True)
+                if kind == "message_start":
+                    if started:
+                        raise invalid_response()
+                    started = True
+                    message = object_value(data.get("message"))
+                    check_error(message)
+                    if message.get("usage") is not None:
+                        yield ModelEventType.usage, usage.update(message["usage"])
+                elif kind == "content_block_start":
+                    index = token_count(data.get("index"))
+                    if not started or index in blocks:
+                        raise invalid_response()
+                    block = dict(object_value(data.get("content_block")))
+                    blocks[index] = block
+                    block["closed"] = False
+                    if block.get("type") == "tool_use":
+                        block["id"] = string_value(block.get("id"), nonempty=True)
+                        block["name"] = string_value(block.get("name"), nonempty=True)
+                        block["arguments"] = ""
+                        block["input"] = object_value(block.get("input", {}))
+                        yield ModelEventType.tool_call_start, {"tool_call_id": block["id"], "name": block["name"]}
+                    elif block.get("type") == "text" and block.get("text"):
+                        yield ModelEventType.text_delta, {"text": string_value(block["text"])}
+                    elif block.get("type") == "thinking" and block.get("thinking"):
+                        yield ModelEventType.thinking_delta, {"text": string_value(block["thinking"])}
+                elif kind == "content_block_delta":
+                    block = blocks.get(token_count(data.get("index")))
+                    if block is None or block["closed"]:
+                        raise invalid_response()
+                    delta = object_value(data.get("delta"))
+                    delta_type = delta.get("type")
+                    if delta_type == "text_delta":
+                        if block.get("type") != "text":
+                            raise invalid_response()
+                        yield ModelEventType.text_delta, {"text": string_value(delta.get("text"))}
+                    elif delta_type == "thinking_delta":
+                        if block.get("type") != "thinking":
+                            raise invalid_response()
+                        yield ModelEventType.thinking_delta, {"text": string_value(delta.get("thinking"))}
+                    elif delta_type == "input_json_delta" and block.get("type") == "tool_use":
+                        fragment = string_value(delta.get("partial_json"))
+                        block["arguments"] += fragment
+                        yield ModelEventType.tool_call_delta, {"tool_call_id": block["id"], "arguments_delta": fragment}
+                    # Signatures and future delta types have no representation in ModelEvent.
+                elif kind == "content_block_stop":
+                    block = blocks.get(token_count(data.get("index")))
+                    if block is None or block["closed"]:
+                        raise invalid_response()
+                    block["closed"] = True
+                    if block.get("type") == "tool_use":
+                        if block["arguments"]:
+                            decode_tool_arguments(block["arguments"])
+                        else:
+                            yield ModelEventType.tool_call_delta, {
+                                "tool_call_id": block["id"], "arguments_delta": json.dumps(block["input"]),
+                            }
+                        yield ModelEventType.tool_call_end, {"tool_call_id": block["id"]}
+                elif kind == "message_delta":
+                    if not started:
+                        raise invalid_response()
+                    object_value(data.get("delta"))
+                    if data.get("usage") is not None:
+                        yield ModelEventType.usage, usage.update(data["usage"])
+                elif kind == "message_stop":
+                    if not started:
+                        raise invalid_response()
+                    if any(not block["closed"] for block in blocks.values()):
+                        raise truncated_stream()
+                    return
+                elif kind == "[DONE]":
+                    raise truncated_stream()
+        raise truncated_stream()

backend/app/providers/factory.py

@@ -16,6 +16,18 @@ class ProviderFactory:
         self.credentials = ProviderCredentialResolver(credentials)
 
     def build(self, config: ProviderConfig) -> ModelProvider:
+        if config.provider_type == ProviderType.openai_responses:
+            from app.providers.openai_responses import OpenAIResponsesProvider
+            return OpenAIResponsesProvider(
+                base_url=config.base_url or "https://api.openai.com/v1",
+                credential_id=config.credential_id, credentials=self.credentials,
+            )
+        if config.provider_type == ProviderType.anthropic_messages:
+            from app.providers.anthropic_messages import AnthropicMessagesProvider
+            return AnthropicMessagesProvider(
+                base_url=config.base_url or "https://api.anthropic.com/v1",
+                credential_id=config.credential_id, credentials=self.credentials,
+            )
         if config.provider_type in {
             ProviderType.openai_chat,
             ProviderType.openai_compatible,
@@ -31,7 +43,7 @@ class ProviderFactory:
 
     @staticmethod
     def presets() -> list[ProviderPreset]:
-        return [
+        presets = [
             ProviderPreset(
                 preset_id="openai",
                 name="OpenAI",
@@ -54,12 +66,45 @@ class ProviderFactory:
                 requires_credential=False,
             ),
         ]
+        # General API endpoints. Coding-plan endpoints and keys are separate products.
+        domestic = [
+            ("kimi", "Kimi / 月之暗面", "https://api.moonshot.cn/v1", [], "长上下文对话；模型以账号权限为准。"),
+            ("qwen", "阿里云百炼", "https://dashscope.aliyuncs.com/compatible-mode/v1", [ModelCapability.embedding], "中国内地兼容接口；海外地域需修改地址。"),
+            ("zhipu", "智谱 GLM", "https://open.bigmodel.cn/api/paas/v4", [ModelCapability.embedding], "通用 API；Coding Plan 请使用其专用地址。"),
+            ("volcengine", "火山方舟 / 豆包", "https://ark.cn-beijing.volces.com/api/v3", [ModelCapability.embedding], "按账号填写模型 ID 或推理接入点 ID。"),
+            ("siliconflow", "硅基流动", "https://api.siliconflow.cn/v1", [ModelCapability.embedding, ModelCapability.transcription], "支持兼容 Embedding 和音频转写接口。"),
+            ("baidu", "百度千帆", "https://qianfan.baidubce.com/v2", [ModelCapability.embedding], "使用千帆 API Key；模型列表取决于账号。"),
+            ("hunyuan", "腾讯混元", "https://api.hunyuan.cloud.tencent.com/v1", [], "OpenAI 兼容对话接口。"),
+            ("minimax", "MiniMax", "https://api.minimaxi.com/v1", [], "文本对话兼容接口；其他媒体协议需独立适配。"),
+            ("stepfun", "阶跃星辰", "https://api.stepfun.com/v1", [], "通用 API；Step Plan 请使用其专用地址。"),
+        ]
+        for preset_id, name, url, extra, description in domestic:
+            presets.append(ProviderPreset(
+                preset_id=preset_id, name=name, provider_type=ProviderType.openai_compatible,
+                base_url=url, default_credential_id=preset_id, logo_id=preset_id,
+                capabilities=[ModelCapability.chat, *extra], description=description,
+            ))
+        presets.extend([
+            ProviderPreset(preset_id="openai-responses", name="OpenAI Responses", provider_type=ProviderType.openai_responses,
+                           base_url="https://api.openai.com/v1", default_credential_id="openai", logo_id="openai"),
+            ProviderPreset(preset_id="anthropic", name="Anthropic / Claude", provider_type=ProviderType.anthropic_messages,
+                           base_url="https://api.anthropic.com/v1", default_credential_id="anthropic", logo_id="anthropic"),
+        ])
+        for preset in presets:
+            if preset.logo_id == "custom":
+                preset.logo_id = preset.preset_id
+            if not preset.capabilities:
+                preset.capabilities = [ModelCapability.chat]
+        presets[0].capabilities += [ModelCapability.embedding, ModelCapability.transcription]
+        return presets
 
     @staticmethod
     def capabilities(provider_type: ProviderType) -> list[ModelCapability]:
         if provider_type in {
             ProviderType.openai_chat,
             ProviderType.openai_compatible,
+            ProviderType.openai_responses,
+            ProviderType.anthropic_messages,
         }:
             return [
                 ModelCapability.chat,

backend/app/providers/http_base.py

@@ -1,9 +1,13 @@
 import json
 from collections.abc import AsyncIterator
+from contextlib import aclosing
 from datetime import datetime, timezone
 
+import httpx
+
 from app.contracts import ModelEvent, ModelEventType, ModelRequest
 from app.providers.base import ProviderError, ProviderTurn
+from app.providers.tool_names import prepare_tool_names
 
 
 class TurnStreamingMixin:
@@ -80,3 +84,229 @@ def decode_tool_arguments(value: object) -> dict[str, object]:
     if not isinstance(decoded, dict):
         raise ProviderError("PROVIDER_INVALID_RESPONSE", "Tool arguments must be an object.")
     return decoded
+
+
+def invalid_response() -> ProviderError:
+    return ProviderError("PROVIDER_INVALID_RESPONSE", "Provider returned an invalid response.")
+
+
+def truncated_stream() -> ProviderError:
+    return ProviderError("PROVIDER_STREAM_TRUNCATED", "Provider stream ended before completion.")
+
+
+def object_value(value: object) -> dict:
+    if not isinstance(value, dict):
+        raise invalid_response()
+    return value
+
+
+def list_value(value: object) -> list:
+    if not isinstance(value, list):
+        raise invalid_response()
+    return value
+
+
+def string_value(value: object, *, nonempty: bool = False) -> str:
+    if not isinstance(value, str) or (nonempty and not value):
+        raise invalid_response()
+    return value
+
+
+def token_count(value: object) -> int:
+    if isinstance(value, bool) or not isinstance(value, int) or value < 0:
+        raise invalid_response()
+    return value
+
+
+def remote_error(value: object) -> ProviderError:
+    # Never reflect upstream messages, URLs, request bodies or credentials.
+    error = value if isinstance(value, dict) else {}
+    code = error.get("code") or error.get("type")
+    mapping = {
+        "authentication_error": "PROVIDER_AUTH_FAILED",
+        "invalid_api_key": "PROVIDER_AUTH_FAILED",
+        "permission_error": "PROVIDER_AUTH_FAILED",
+        "rate_limit_error": "PROVIDER_RATE_LIMITED",
+        "rate_limit_exceeded": "PROVIDER_RATE_LIMITED",
+        "insufficient_quota": "PROVIDER_RATE_LIMITED",
+        "not_found_error": "MODEL_NOT_FOUND",
+        "model_not_found": "MODEL_NOT_FOUND",
+        "invalid_request_error": "PROVIDER_INVALID_REQUEST",
+        "context_length_exceeded": "PROVIDER_INVALID_REQUEST",
+    }
+    mapped = mapping.get(code, "PROVIDER_UNAVAILABLE") if isinstance(code, str) else "PROVIDER_UNAVAILABLE"
+    return ProviderError(mapped, "Provider could not complete the request.")
+
+
+def check_error(data: dict) -> None:
+    if data.get("error") is not None or data.get("type") == "error":
+        raise remote_error(data.get("error") or data)
+
+
+class UsageTracker:
+    """Merge cumulative snapshots, including partial usage updates."""
+
+    def __init__(self, input_key: str = "input_tokens", output_key: str = "output_tokens",
+                 *, cache_tokens: bool = False) -> None:
+        self.input_key = input_key
+        self.output_key = output_key
+        self.cache_tokens = cache_tokens
+        self.counts: dict[str, int] = {}
+
+    def update(self, value: object) -> dict[str, int]:
+        usage = object_value(value)
+        keys = [self.input_key, self.output_key]
+        if self.cache_tokens:
+            keys += ["cache_creation_input_tokens", "cache_read_input_tokens"]
+        for key in keys:
+            if key in usage:
+                self.counts[key] = max(self.counts.get(key, 0), token_count(usage[key]))
+        inputs = self.counts.get(self.input_key, 0)
+        if self.cache_tokens:
+            inputs += sum(self.counts.get(key, 0) for key in keys[2:])
+        return {"input_tokens": inputs, "output_tokens": self.counts.get(self.output_key, 0)}
+
+
+class EventStreamingMixin:
+    async def stream(self, request: ModelRequest) -> AsyncIterator[ModelEvent]:
+        sequence = 0
+        status = "completed"
+        try:
+            request, originals = prepare_tool_names(request)
+            # Closing the public iterator must synchronously close every nested iterator.
+            async with aclosing(self._events(request)) as events:
+                async for kind, data in events:
+                    if kind == ModelEventType.tool_call_start and "name" in data:
+                        data = {**data, "name": originals.get(data["name"], data["name"])}
+                    if kind == ModelEventType.usage:
+                        data = {**data, "total_tokens": data["input_tokens"] + data["output_tokens"]}
+                    yield ModelEvent(event=kind, data=data, sequence=sequence,
+                                     timestamp=datetime.now(timezone.utc))
+                    sequence += 1
+        except ProviderError as exc:
+            status = "failed"
+            yield ModelEvent(event=ModelEventType.error, sequence=sequence,
+                             data={"code": exc.code, "message": exc.message},
+                             timestamp=datetime.now(timezone.utc))
+            sequence += 1
+        except (ValueError, TypeError, KeyError, IndexError, AttributeError, OverflowError):
+            status = "failed"
+            error = invalid_response()
+            yield ModelEvent(event=ModelEventType.error, sequence=sequence,
+                             data={"code": error.code, "message": error.message},
+                             timestamp=datetime.now(timezone.utc))
+            sequence += 1
+        # CancelledError and GeneratorExit deliberately propagate without a Done event.
+        yield ModelEvent(event=ModelEventType.done, sequence=sequence,
+                         data={"status": status},
+                         timestamp=datetime.now(timezone.utc))
+
+
+async def sse_objects(response: httpx.Response) -> AsyncIterator[dict]:
+    """Read SSE frames, accepting the adjacent data lines used by some gateways."""
+    parts: list[str] = []
+    event_name = ""
+
+    def decode() -> dict:
+        value = "\n".join(parts)
+        if value.strip() == "[DONE]":
+            return {"type": "[DONE]"}
+        try:
+            data = object_value(json.loads(value))
+        except (ValueError, TypeError) as exc:
+            raise invalid_response() from exc
+        if event_name and "type" not in data:
+            data["type"] = event_name
+        check_error(data)
+        return data
+
+    async for line in response.aiter_lines():
+        if not line:
+            if parts:
+                yield decode()
+            parts = []
+            event_name = ""
+        elif line.startswith(":"):
+            continue
+        elif line.startswith("event:"):
+            if parts:
+                yield decode()
+                parts = []
+            event_name = line[6:].strip()
+        elif line.startswith("data:"):
+            if parts:
+                # Legacy compatible endpoints sometimes omit blank separators.
+                try:
+                    json.loads("\n".join(parts))
+                except ValueError:
+                    pass
+                else:
+                    yield decode()
+                    parts = []
+                    event_name = ""
+            parts.append(line[5:].removeprefix(" "))
+    if parts:
+        yield decode()
+
+
+class HTTPProviderMixin:
+    stream_path = "/chat/completions"
+    stream_format = "sse"
+
+    def _headers(self) -> dict[str, str]:
+        return {"Content-Type": "application/json"}
+
+    @staticmethod
+    def _status_error(exc: httpx.HTTPStatusError) -> ProviderError:
+        status = exc.response.status_code
+        code = {400: "PROVIDER_INVALID_REQUEST", 401: "PROVIDER_AUTH_FAILED",
+                403: "PROVIDER_AUTH_FAILED", 404: "MODEL_NOT_FOUND",
+                408: "PROVIDER_TIMEOUT", 413: "PROVIDER_INVALID_REQUEST",
+                422: "PROVIDER_INVALID_REQUEST", 429: "PROVIDER_RATE_LIMITED"}.get(
+                    status, "PROVIDER_UNAVAILABLE")
+        return ProviderError(code, f"Provider returned HTTP {status}.")
+
+    async def _request(self, method: str, path: str, **kwargs) -> dict:
+        headers = self._headers()
+        try:
+            async with httpx.AsyncClient(timeout=self.timeout_seconds, transport=self.transport) as client:
+                response = await client.request(method, f"{self.base_url}{path}", headers=headers, **kwargs)
+                response.raise_for_status()
+                data = object_value(response.json())
+                check_error(data)
+                return data
+        except httpx.TimeoutException as exc:
+            raise ProviderError("PROVIDER_TIMEOUT", "Provider request timed out.") from exc
+        except httpx.HTTPStatusError as exc:
+            raise self._status_error(exc) from exc
+        except httpx.HTTPError as exc:
+            raise ProviderError("PROVIDER_UNAVAILABLE", "Provider is unavailable.") from exc
+        except (ValueError, TypeError) as exc:
+            raise invalid_response() from exc
+
+    async def _stream_json(self, payload: dict[str, object]) -> AsyncIterator[dict]:
+        headers = self._headers()
+        headers["Accept"] = "text/event-stream" if self.stream_format == "sse" else "application/x-ndjson"
+        try:
+            async with httpx.AsyncClient(timeout=self.timeout_seconds, transport=self.transport) as client:
+                async with client.stream("POST", f"{self.base_url}{self.stream_path}",
+                                         headers=headers, json=payload) as response:
+                    response.raise_for_status()
+                    if self.stream_format == "sse":
+                        async with aclosing(sse_objects(response)) as objects:
+                            async for data in objects:
+                                yield data
+                    else:
+                        async for line in response.aiter_lines():
+                            if line.strip():
+                                data = object_value(json.loads(line))
+                                check_error(data)
+                                yield data
+        except httpx.TimeoutException as exc:
+            raise ProviderError("PROVIDER_TIMEOUT", "Provider request timed out.") from exc
+        except httpx.HTTPStatusError as exc:
+            raise self._status_error(exc) from exc
+        except httpx.HTTPError as exc:
+            raise ProviderError("PROVIDER_UNAVAILABLE", "Provider is unavailable.") from exc
+        except (ValueError, TypeError) as exc:
+            raise invalid_response() from exc

backend/app/providers/ollama.py

@@ -1,16 +1,22 @@
-from uuid import uuid4
 import json
-from collections.abc import AsyncIterator
-from datetime import datetime, timezone
+from contextlib import aclosing
+from uuid import uuid4
 
 import httpx
 
-from app.contracts import ModelCapability, ModelEvent, ModelEventType, ModelInfo, ModelRequest
+from app.contracts import MessageRole, ModelCapability, ModelEventType, ModelInfo, ModelRequest
 from app.providers.base import ProviderError, ProviderToolCall, ProviderTurn
-from app.providers.http_base import TurnStreamingMixin, decode_tool_arguments
+from app.providers.tool_names import mapped_tool_names
+from app.providers.http_base import (
+    EventStreamingMixin, HTTPProviderMixin, UsageTracker, decode_tool_arguments,
+    invalid_response, list_value, object_value, string_value, truncated_stream,
+)
 
 
-class OllamaProvider(TurnStreamingMixin):
+class OllamaProvider(EventStreamingMixin, HTTPProviderMixin):
+    stream_path = "/api/chat"
+    stream_format = "jsonl"
+
     def __init__(
         self,
         base_url: str = "http://127.0.0.1:11434",
@@ -21,126 +27,55 @@ class OllamaProvider(TurnStreamingMixin):
         self.timeout_seconds = timeout_seconds
         self.transport = transport
 
+    @mapped_tool_names
     async def complete(self, request: ModelRequest) -> ProviderTurn:
-        messages = []
-        if request.system:
-            messages.append({"role": "system", "content": request.system})
-        for message in request.messages:
-            item: dict[str, object] = {
-                "role": message.role.value,
-                "content": message.content,
-            }
-            if message.tool_calls:
-                item["tool_calls"] = [
-                    {
-                        "function": {
-                            "name": call.name,
-                            "arguments": call.arguments,
-                        }
-                    }
-                    for call in message.tool_calls
-                ]
-            messages.append(item)
-        payload: dict[str, object] = {
-            "model": request.model,
-            "messages": messages,
-            "stream": False,
-        }
-        if request.tools:
-            payload["tools"] = [
-                {
-                    "type": "function",
-                    "function": {
-                        "name": tool.name,
-                        "description": tool.description,
-                        "parameters": tool.parameters,
-                    },
-                }
-                for tool in request.tools
-            ]
-        data = await self._request("POST", "/api/chat", json=payload)
-        message = data.get("message") or {}
-        tool_calls = []
-        for raw_call in message.get("tool_calls") or []:
-            function = raw_call.get("function") or {}
-            tool_calls.append(
-                ProviderToolCall(
-                    tool_call_id=raw_call.get("id") or f"call_{uuid4().hex}",
-                    name=function.get("name") or "",
-                    arguments=decode_tool_arguments(function.get("arguments", {})),
-                )
-            )
-        return ProviderTurn(
-            text=message.get("content") or None,
-            tool_calls=tool_calls,
-            input_tokens=int(data.get("prompt_eval_count") or 0),
-            output_tokens=int(data.get("eval_count") or 0),
+        data = await self._request("POST", self.stream_path, json=self._chat_payload(request, stream=False))
+        message = object_value(data.get("message"))
+        calls = [self._tool_call(raw) for raw in list_value(message.get("tool_calls", []))]
+        content = message.get("content")
+        if content is not None:
+            content = string_value(content)
+        return ProviderTurn(text=content or None, tool_calls=calls,
+                            **UsageTracker("prompt_eval_count", "eval_count").update(data))
+
+    @staticmethod
+    def _tool_call(raw: object) -> ProviderToolCall:
+        call = object_value(raw)
+        function = object_value(call.get("function"))
+        return ProviderToolCall(
+            tool_call_id=string_value(call.get("id") or f"call_{uuid4().hex}"),
+            name=string_value(function.get("name"), nonempty=True),
+            arguments=decode_tool_arguments(function.get("arguments", {})),
         )
 
-    async def list_models(self) -> list[ModelInfo]:
-        data = await self._request("GET", "/api/tags")
-        return [
-            ModelInfo(
-                model=item["name"],
-                display_name=item.get("name", ""),
-                capabilities=[ModelCapability.chat, ModelCapability.streaming],
-            )
-            for item in data.get("models", [])
-            if isinstance(item, dict) and item.get("name")
-        ]
-
-    async def stream(self, request: ModelRequest) -> AsyncIterator[ModelEvent]:
-        payload = self._chat_payload(request, stream=True)
-        sequence = 0
-
-        def event(kind: ModelEventType, data: dict | None = None) -> ModelEvent:
-            nonlocal sequence
-            item = ModelEvent(
-                event=kind, sequence=sequence, data=data or {},
-                timestamp=datetime.now(timezone.utc),
-            )
-            sequence += 1
-            return item
-
-        try:
-            async for data in self._stream_json(payload):
-                message = data.get("message") or {}
+    async def _events(self, request: ModelRequest):
+        usage = UsageTracker("prompt_eval_count", "eval_count")
+        async with aclosing(self._stream_json(self._chat_payload(request, stream=True))) as chunks:
+            async for data in chunks:
+                message = object_value(data.get("message", {}))
                 if message.get("thinking"):
-                    yield event(ModelEventType.thinking_delta, {"text": message["thinking"]})
+                    yield ModelEventType.thinking_delta, {"text": string_value(message["thinking"])}
                 if message.get("content"):
-                    yield event(ModelEventType.text_delta, {"text": message["content"]})
-                for raw_call in message.get("tool_calls") or []:
-                    function = raw_call.get("function") or {}
-                    call_id = raw_call.get("id") or f"call_{uuid4().hex}"
-                    yield event(
-                        ModelEventType.tool_call_start,
-                        {"tool_call_id": call_id, "name": function.get("name") or ""},
-                    )
-                    yield event(
-                        ModelEventType.tool_call_delta,
-                        {
-                            "tool_call_id": call_id,
-                            "arguments_delta": json.dumps(
-                                function.get("arguments") or {}, ensure_ascii=False
-                            ),
-                        },
-                    )
-                    yield event(ModelEventType.tool_call_end, {"tool_call_id": call_id})
-                if data.get("done"):
-                    yield event(
-                        ModelEventType.usage,
-                        {
-                            "input_tokens": int(data.get("prompt_eval_count") or 0),
-                            "output_tokens": int(data.get("eval_count") or 0),
-                        },
-                    )
-            yield event(ModelEventType.done)
-        except ProviderError as exc:
-            yield event(ModelEventType.error, {"code": exc.code, "message": exc.message})
-            yield event(ModelEventType.done)
+                    yield ModelEventType.text_delta, {"text": string_value(message["content"])}
+                for raw in list_value(message.get("tool_calls", [])):
+                    call = self._tool_call(raw)
+                    yield ModelEventType.tool_call_start, {"tool_call_id": call.tool_call_id, "name": call.name}
+                    yield ModelEventType.tool_call_delta, {
+                        "tool_call_id": call.tool_call_id,
+                        "arguments_delta": json.dumps(call.arguments, ensure_ascii=False),
+                    }
+                    yield ModelEventType.tool_call_end, {"tool_call_id": call.tool_call_id}
+                if "done" in data and not isinstance(data["done"], bool):
+                    raise invalid_response()
+                if "prompt_eval_count" in data or "eval_count" in data or data.get("done"):
+                    yield ModelEventType.usage, usage.update(data)
+                if data.get("done") is True:
+                    return
+        raise truncated_stream()
 
     def _chat_payload(self, request: ModelRequest, *, stream: bool) -> dict[str, object]:
         messages = []
+        names: dict[str, str] = {}
         if request.system:
             messages.append({"role": "system", "content": request.system})
         for message in request.messages:
@@ -150,53 +85,49 @@ class OllamaProvider(TurnStreamingMixin):
                     {"function": {"name": call.name, "arguments": call.arguments}}
                     for call in message.tool_calls
                 ]
+                names.update({call.tool_call_id: call.name for call in message.tool_calls})
+            if message.role == MessageRole.tool:
+                name = message.name or names.get(message.tool_call_id or "")
+                if name:
+                    item["tool_name"] = name
             messages.append(item)
         payload: dict[str, object] = {
-            "model": request.model, "messages": messages, "stream": stream
+            "model": request.model, "messages": messages, "stream": stream,
         }
         if request.tools:
             payload["tools"] = [
-                {
-                    "type": "function",
-                    "function": {
-                        "name": tool.name,
-                        "description": tool.description,
-                        "parameters": tool.parameters,
-                    },
-                }
-                for tool in request.tools
+                {"type": "function", "function": {
+                    "name": tool.name, "description": tool.description, "parameters": tool.parameters,
+                }} for tool in request.tools
             ]
+        options = {}
+        if request.temperature is not None:
+            options["temperature"] = request.temperature
+        if request.max_tokens is not None:
+            options["num_predict"] = request.max_tokens
+        if options:
+            payload["options"] = options
+        if request.response_format:
+            format_ = request.response_format
+            if format_.get("type") == "json_object":
+                payload["format"] = "json"
+            elif format_.get("type") == "json_schema":
+                payload["format"] = object_value(object_value(format_.get("json_schema")).get("schema"))
+            else:
+                payload["format"] = format_
         return payload
 
-    async def _stream_json(self, payload: dict[str, object]) -> AsyncIterator[dict]:
-        try:
-            async with httpx.AsyncClient(
-                timeout=self.timeout_seconds, transport=self.transport
-            ) as client:
-                async with client.stream(
-                    "POST", f"{self.base_url}/api/chat", json=payload
-                ) as response:
-                    response.raise_for_status()
-                    async for line in response.aiter_lines():
-                        if not line.strip():
-                            continue
-                        try:
-                            data = json.loads(line)
-                        except json.JSONDecodeError as exc:
-                            raise ProviderError(
-                                "PROVIDER_INVALID_RESPONSE", "Ollama returned invalid JSONL."
-                            ) from exc
-                        if isinstance(data, dict):
-                            yield data
-        except httpx.TimeoutException as exc:
-            raise ProviderError("PROVIDER_TIMEOUT", "Ollama request timed out.") from exc
-        except httpx.HTTPStatusError as exc:
-            raise ProviderError(
-                "MODEL_NOT_FOUND" if exc.response.status_code == 404 else "PROVIDER_UNAVAILABLE",
-                f"Ollama returned HTTP {exc.response.status_code}.",
-            ) from exc
-        except httpx.HTTPError as exc:
-            raise ProviderError("PROVIDER_UNAVAILABLE", "Ollama is unavailable.") from exc
+    async def list_models(self) -> list[ModelInfo]:
+        data = await self._request("GET", "/api/tags")
+        return [
+            ModelInfo(
+                model=string_value(item["name"]), display_name=item["name"],
+                capabilities=([ModelCapability.embedding] if "embed" in item["name"].lower()
+                              else [ModelCapability.chat, ModelCapability.streaming]),
+            )
+            for item in list_value(data.get("models"))
+            if isinstance(item, dict) and isinstance(item.get("name"), str) and item["name"]
+        ]
 
     async def test_connection(self, model: str | None = None) -> tuple[bool, str]:
         try:
@@ -206,24 +137,3 @@ class OllamaProvider(TurnStreamingMixin):
         if model and model not in {item.model for item in models}:
             return False, f"Model is not installed: {model}"
         return True, f"Connected; discovered {len(models)} local model(s)."
-
-    async def _request(self, method: str, path: str, **kwargs) -> dict:
-        try:
-            async with httpx.AsyncClient(
-                timeout=self.timeout_seconds, transport=self.transport
-            ) as client:
-                response = await client.request(method, f"{self.base_url}{path}", **kwargs)
-                response.raise_for_status()
-                data = response.json()
-        except httpx.TimeoutException as exc:
-            raise ProviderError("PROVIDER_TIMEOUT", "Ollama request timed out.") from exc
-        except httpx.HTTPStatusError as exc:
-            raise ProviderError(
-                "MODEL_NOT_FOUND" if exc.response.status_code == 404 else "PROVIDER_UNAVAILABLE",
-                f"Ollama returned HTTP {exc.response.status_code}.",
-            ) from exc
-        except (httpx.HTTPError, ValueError) as exc:
-            raise ProviderError("PROVIDER_UNAVAILABLE", "Ollama is unavailable.") from exc
-        if not isinstance(data, dict):
-            raise ProviderError("PROVIDER_INVALID_RESPONSE", "Ollama returned non-object JSON.")
-        return data

backend/app/providers/openai_compatible.py

@@ -1,24 +1,20 @@
 import json
-from collections.abc import AsyncIterator
-from datetime import datetime, timezone
+from contextlib import aclosing
 from uuid import uuid4
 
 import httpx
 
-from app.contracts import (
-    MessageRole,
-    ModelCapability,
-    ModelEvent,
-    ModelEventType,
-    ModelInfo,
-    ModelRequest,
-)
+from app.contracts import MessageRole, ModelCapability, ModelEventType, ModelInfo, ModelRequest
 from app.providers.base import ProviderError, ProviderToolCall, ProviderTurn
 from app.providers.credentials import CredentialResolver, CredentialStoreError
-from app.providers.http_base import TurnStreamingMixin, decode_tool_arguments
+from app.providers.tool_names import mapped_tool_names
+from app.providers.http_base import (
+    EventStreamingMixin, HTTPProviderMixin, UsageTracker, decode_tool_arguments,
+    invalid_response, list_value, object_value, string_value, token_count, truncated_stream,
+)
 
 
-class OpenAICompatibleProvider(TurnStreamingMixin):
+class OpenAICompatibleProvider(EventStreamingMixin, HTTPProviderMixin):
     def __init__(
         self,
         base_url: str,
@@ -33,50 +29,37 @@ class OpenAICompatibleProvider(TurnStreamingMixin):
         self.timeout_seconds = timeout_seconds
         self.transport = transport
 
+    @mapped_tool_names
     async def complete(self, request: ModelRequest) -> ProviderTurn:
-        payload = self._payload(request, stream=False)
-
-        data = await self._request("POST", "/chat/completions", json=payload)
-        try:
-            message = data["choices"][0]["message"]
-        except (KeyError, IndexError, TypeError) as exc:
-            raise ProviderError("PROVIDER_INVALID_RESPONSE", "Missing completion message.") from exc
-
-        tool_calls = []
-        for raw_call in message.get("tool_calls") or []:
-            function = raw_call.get("function") or {}
-            tool_calls.append(
-                ProviderToolCall(
-                    tool_call_id=raw_call.get("id") or f"call_{uuid4().hex}",
-                    name=function.get("name") or "",
-                    arguments=decode_tool_arguments(function.get("arguments", "{}")),
-                )
-            )
-        usage = data.get("usage") or {}
-        return ProviderTurn(
-            text=message.get("content"),
-            tool_calls=tool_calls,
-            input_tokens=int(usage.get("prompt_tokens") or 0),
-            output_tokens=int(usage.get("completion_tokens") or 0),
-        )
+        data = await self._request("POST", self.stream_path, json=self._payload(request, stream=False))
+        choices = list_value(data.get("choices"))
+        if not choices:
+            raise invalid_response()
+        message = object_value(object_value(choices[0]).get("message"))
+        calls = []
+        for raw in list_value(message.get("tool_calls", [])):
+            raw = object_value(raw)
+            function = object_value(raw.get("function"))
+            calls.append(ProviderToolCall(
+                tool_call_id=string_value(raw.get("id") or f"call_{uuid4().hex}"),
+                name=string_value(function.get("name"), nonempty=True),
+                arguments=decode_tool_arguments(function.get("arguments", "{}")),
+            ))
+        text = message.get("content")
+        if text is not None:
+            text = string_value(text)
+        usage = UsageTracker("prompt_tokens", "completion_tokens").update(data.get("usage") or {})
+        return ProviderTurn(text=text, tool_calls=calls, **usage)
 
     def _payload(self, request: ModelRequest, *, stream: bool) -> dict[str, object]:
         payload: dict[str, object] = {
-            "model": request.model,
-            "messages": self._messages(request),
-            "stream": stream,
+            "model": request.model, "messages": self._messages(request), "stream": stream,
         }
         if request.tools:
             payload["tools"] = [
-                {
-                    "type": "function",
-                    "function": {
-                        "name": tool.name,
-                        "description": tool.description,
-                        "parameters": tool.parameters,
-                    },
-                }
-                for tool in request.tools
+                {"type": "function", "function": {
+                    "name": tool.name, "description": tool.description, "parameters": tool.parameters,
+                }} for tool in request.tools
             ]
         if request.temperature is not None:
             payload["temperature"] = request.temperature
@@ -84,124 +67,81 @@ class OpenAICompatibleProvider(TurnStreamingMixin):
             payload["max_tokens"] = request.max_tokens
         if request.response_format is not None:
             payload["response_format"] = request.response_format
-
+        if stream:
+            payload["stream_options"] = {"include_usage": True}
         return payload
 
-    async def stream(self, request: ModelRequest) -> AsyncIterator[ModelEvent]:
-        sequence = 0
-        open_calls: dict[int, str] = {}
-
-        def event(kind: ModelEventType, data: dict | None = None) -> ModelEvent:
-            nonlocal sequence
-            item = ModelEvent(
-                event=kind,
-                sequence=sequence,
-                data=data or {},
-                timestamp=datetime.now(timezone.utc),
-            )
-            sequence += 1
-            return item
-
-        try:
-            async for data in self._stream_json(self._payload(request, stream=True)):
-                usage = data.get("usage") or {}
-                if usage:
-                    yield event(
-                        ModelEventType.usage,
-                        {
-                            "input_tokens": int(usage.get("prompt_tokens") or 0),
-                            "output_tokens": int(usage.get("completion_tokens") or 0),
-                        },
-                    )
-                choices = data.get("choices") or []
+    async def _events(self, request: ModelRequest):
+        calls: dict[int, dict] = {}
+        usage = UsageTracker("prompt_tokens", "completion_tokens")
+        finished = False
+        seen = False
+        async with aclosing(self._stream_json(self._payload(request, stream=True))) as chunks:
+            async for data in chunks:
+                if data.get("type") == "[DONE]":
+                    if not seen:
+                        raise invalid_response()
+                    finished = True
+                    break
+                if data.get("usage") is not None:
+                    yield ModelEventType.usage, usage.update(data["usage"])
+                choices = list_value(data.get("choices", []))
                 if not choices:
                     continue
-                choice = choices[0]
-                delta = choice.get("delta") or {}
+                seen = True
+                choice = object_value(choices[0])
+                delta = object_value(choice.get("delta") or {})
                 if delta.get("reasoning_content"):
-                    yield event(
-                        ModelEventType.thinking_delta,
-                        {"text": delta["reasoning_content"]},
-                    )
+                    yield ModelEventType.thinking_delta, {"text": string_value(delta["reasoning_content"])}
                 if delta.get("content"):
-                    yield event(ModelEventType.text_delta, {"text": delta["content"]})
-                for raw_call in delta.get("tool_calls") or []:
-                    index = int(raw_call.get("index") or 0)
-                    function = raw_call.get("function") or {}
-                    call_id = raw_call.get("id") or open_calls.get(index) or f"call_{uuid4().hex}"
-                    if index not in open_calls:
-                        open_calls[index] = call_id
-                        yield event(
-                            ModelEventType.tool_call_start,
-                            {"tool_call_id": call_id, "name": function.get("name") or ""},
-                        )
-                    if function.get("arguments"):
-                        yield event(
-                            ModelEventType.tool_call_delta,
-                            {
-                                "tool_call_id": open_calls[index],
-                                "arguments_delta": function["arguments"],
-                            },
-                        )
-                if choice.get("finish_reason") == "tool_calls":
-                    for call_id in open_calls.values():
-                        yield event(
-                            ModelEventType.tool_call_end, {"tool_call_id": call_id}
-                        )
-                    open_calls.clear()
-            for call_id in open_calls.values():
-                yield event(ModelEventType.tool_call_end, {"tool_call_id": call_id})
-            yield event(ModelEventType.done)
-        except ProviderError as exc:
-            yield event(ModelEventType.error, {"code": exc.code, "message": exc.message})
-            yield event(ModelEventType.done)
-
-    async def _stream_json(self, payload: dict[str, object]) -> AsyncIterator[dict]:
-        headers = self._headers()
-        try:
-            async with httpx.AsyncClient(
-                timeout=self.timeout_seconds, transport=self.transport
-            ) as client:
-                async with client.stream(
-                    "POST", f"{self.base_url}/chat/completions", headers=headers, json=payload
-                ) as response:
-                    response.raise_for_status()
-                    async for line in response.aiter_lines():
-                        if not line.startswith("data:"):
-                            continue
-                        value = line[5:].strip()
-                        if not value or value == "[DONE]":
-                            continue
-                        try:
-                            data = json.loads(value)
-                        except json.JSONDecodeError as exc:
-                            raise ProviderError(
-                                "PROVIDER_INVALID_RESPONSE", "Provider returned invalid SSE JSON."
-                            ) from exc
-                        if isinstance(data, dict):
-                            yield data
-        except httpx.TimeoutException as exc:
-            raise ProviderError("PROVIDER_TIMEOUT", "Provider request timed out.") from exc
-        except httpx.HTTPStatusError as exc:
-            raise self._status_error(exc) from exc
-        except httpx.HTTPError as exc:
-            raise ProviderError("PROVIDER_UNAVAILABLE", "Provider is unavailable.") from exc
+                    yield ModelEventType.text_delta, {"text": string_value(delta["content"])}
+                for raw in list_value(delta.get("tool_calls", [])):
+                    raw = object_value(raw)
+                    index = token_count(raw.get("index", 0))
+                    function = object_value(raw.get("function") or {})
+                    call = calls.setdefault(index, {"id": "", "name": "", "arguments": "", "started": False})
+                    if raw.get("id"):
+                        call["id"] = string_value(raw["id"])
+                    if function.get("name"):
+                        call["name"] += string_value(function["name"])
+                    fragment = string_value(function.get("arguments", ""))
+                    call["arguments"] += fragment
+                    if not call["started"] and call["name"]:
+                        call["id"] = call["id"] or f"call_{uuid4().hex}"
+                        call["started"] = True
+                        yield ModelEventType.tool_call_start, {"tool_call_id": call["id"], "name": call["name"]}
+                        fragment = call["arguments"]
+                    if call["started"] and fragment:
+                        yield ModelEventType.tool_call_delta, {"tool_call_id": call["id"], "arguments_delta": fragment}
+                if choice.get("finish_reason"):
+                    finished = True
+        if not finished:
+            raise truncated_stream()
+        for call in calls.values():
+            if not call["started"]:
+                raise invalid_response()
+            decode_tool_arguments(call["arguments"] or "{}")
+            yield ModelEventType.tool_call_end, {"tool_call_id": call["id"]}
 
     async def list_models(self) -> list[ModelInfo]:
         data = await self._request("GET", "/models")
-        return [
-            ModelInfo(
-                model=item["id"],
-                display_name=item["id"],
-                capabilities=[
-                    ModelCapability.chat,
-                    ModelCapability.tool_calling,
-                    ModelCapability.streaming,
-                ],
-            )
-            for item in data.get("data", [])
-            if isinstance(item, dict) and item.get("id")
-        ]
+        return [ModelInfo(model=string_value(item["id"]), display_name=item["id"],
+                          capabilities=self._model_capabilities(string_value(item["id"])))
+                for item in list_value(data.get("data"))
+                if isinstance(item, dict) and item.get("id")]
+
+    @staticmethod
+    def _model_capabilities(model: str) -> list[ModelCapability]:
+        # /models does not advertise capabilities. Avoid known non-chat families;
+        # these are discovery hints, not a guarantee of support by a gateway.
+        name = model.lower()
+        if "embed" in name or name.startswith(("bge-", "bge/")):
+            return [ModelCapability.embedding]
+        if any(marker in name for marker in (
+            "whisper", "tts", "transcri", "audio", "realtime", "dall-e", "image", "moderation", "rerank",
+        )):
+            return []
+        return [ModelCapability.chat]
 
     async def test_connection(self, model: str | None = None) -> tuple[bool, str]:
         try:
@@ -217,73 +157,30 @@ class OpenAICompatibleProvider(TurnStreamingMixin):
         if request.system:
             result.append({"role": "system", "content": request.system})
         for message in request.messages:
-            item: dict[str, object] = {
-                "role": message.role.value,
-                "content": message.content,
-            }
+            item: dict[str, object] = {"role": message.role.value, "content": message.content}
             if message.name:
                 item["name"] = message.name
             if message.role == MessageRole.tool and message.tool_call_id:
                 item["tool_call_id"] = message.tool_call_id
             if message.tool_calls:
                 item["tool_calls"] = [
-                    {
-                        "id": call.tool_call_id,
-                        "type": "function",
-                        "function": {
-                            "name": call.name,
-                            "arguments": json.dumps(call.arguments),
-                        },
-                    }
-                    for call in message.tool_calls
+                    {"id": call.tool_call_id, "type": "function", "function": {
+                        "name": call.name, "arguments": json.dumps(call.arguments),
+                    }} for call in message.tool_calls
                 ]
             result.append(item)
         return result
 
-    async def _request(self, method: str, path: str, **kwargs) -> dict:
-        headers = self._headers()
-        try:
-            async with httpx.AsyncClient(
-                timeout=self.timeout_seconds, transport=self.transport
-            ) as client:
-                response = await client.request(
-                    method, f"{self.base_url}{path}", headers=headers, **kwargs
-                )
-                response.raise_for_status()
-                data = response.json()
-        except httpx.TimeoutException as exc:
-            raise ProviderError("PROVIDER_TIMEOUT", "Provider request timed out.") from exc
-        except httpx.HTTPStatusError as exc:
-            raise self._status_error(exc) from exc
-        except (httpx.HTTPError, ValueError) as exc:
-            raise ProviderError("PROVIDER_UNAVAILABLE", "Provider is unavailable.") from exc
-        if not isinstance(data, dict):
-            raise ProviderError("PROVIDER_INVALID_RESPONSE", "Provider returned non-object JSON.")
-        return data
-
     def _headers(self) -> dict[str, str]:
         headers = {"Content-Type": "application/json"}
         try:
             api_key = self.credentials.resolve(self.credential_id)
         except CredentialStoreError as exc:
-            raise ProviderError(
-                "PROVIDER_CREDENTIAL_UNAVAILABLE",
-                "Credential could not be decrypted by the AI Core.",
-            ) from exc
+            raise ProviderError("PROVIDER_CREDENTIAL_UNAVAILABLE",
+                                "Credential could not be decrypted by the AI Core.") from exc
         if self.credential_id and not api_key:
-            raise ProviderError(
-                "PROVIDER_CREDENTIAL_MISSING",
-                f'Credential "{self.credential_id}" is not available in the AI Core process.',
-            )
+            raise ProviderError("PROVIDER_CREDENTIAL_MISSING",
+                                "Credential is not available in the AI Core process.")
         if api_key:
             headers["Authorization"] = f"Bearer {api_key}"
         return headers
-
-    @staticmethod
-    def _status_error(exc: httpx.HTTPStatusError) -> ProviderError:
-        code = {
-            401: "PROVIDER_AUTH_FAILED",
-            404: "MODEL_NOT_FOUND",
-            429: "PROVIDER_RATE_LIMITED",
-        }.get(exc.response.status_code, "PROVIDER_UNAVAILABLE")
-        return ProviderError(code, f"Provider returned HTTP {exc.response.status_code}.")

backend/app/providers/openai_responses.py

@@ -0,0 +1,168 @@
+"""Native /responses adapter; stateless history uses function_call/output items."""
+
+import json
+from contextlib import aclosing
+
+from app.contracts import MessageRole, ModelEventType, ModelRequest
+from app.providers.base import ProviderError, ProviderToolCall, ProviderTurn
+from app.providers.http_base import (
+    UsageTracker, check_error, decode_tool_arguments, invalid_response, list_value,
+    object_value, remote_error, string_value, token_count, truncated_stream,
+)
+from app.providers.openai_compatible import OpenAICompatibleProvider
+from app.providers.tool_names import mapped_tool_names
+
+
+class OpenAIResponsesProvider(OpenAICompatibleProvider):
+    stream_path = "/responses"
+
+    def _payload(self, request: ModelRequest, *, stream: bool) -> dict[str, object]:
+        inputs = []
+        for message in request.messages:
+            if message.role == MessageRole.tool:
+                if not message.tool_call_id:
+                    raise ProviderError("PROVIDER_INVALID_REQUEST", "Tool result requires a call identifier.")
+                inputs.append({"type": "function_call_output", "call_id": message.tool_call_id,
+                               "output": message.content})
+                continue
+            if message.content or not message.tool_calls:
+                inputs.append({"role": message.role.value, "content": message.content})
+            for call in message.tool_calls:
+                inputs.append({"type": "function_call", "call_id": call.tool_call_id,
+                               "name": call.name, "arguments": json.dumps(call.arguments)})
+        payload: dict[str, object] = {"model": request.model, "input": inputs, "stream": stream}
+        if request.system:
+            payload["instructions"] = request.system
+        if request.tools:
+            payload["tools"] = [{"type": "function", "name": tool.name,
+                                 "description": tool.description, "parameters": tool.parameters}
+                                for tool in request.tools]
+        if request.temperature is not None:
+            payload["temperature"] = request.temperature
+        if request.max_tokens is not None:
+            payload["max_output_tokens"] = request.max_tokens
+        if request.response_format is not None:
+            format_ = dict(request.response_format)
+            if format_.get("type") == "json_schema":
+                format_ = {"type": "json_schema", **object_value(format_.get("json_schema"))}
+            payload["text"] = {"format": format_}
+        return payload
+
+    @staticmethod
+    def _check_response(data: dict) -> None:
+        check_error(data)
+        status = data.get("status")
+        if status == "incomplete":
+            raise ProviderError("PROVIDER_INCOMPLETE_RESPONSE", "Provider response is incomplete.")
+        if status == "failed":
+            raise remote_error(data.get("error"))
+        if status is not None and status != "completed":
+            raise invalid_response()
+
+    @mapped_tool_names
+    async def complete(self, request: ModelRequest) -> ProviderTurn:
+        data = await self._request("POST", self.stream_path, json=self._payload(request, stream=False))
+        self._check_response(data)
+        texts = []
+        calls = []
+        for raw in list_value(data.get("output")):
+            item = object_value(raw)
+            if item.get("type") == "message":
+                for raw_part in list_value(item.get("content")):
+                    part = object_value(raw_part)
+                    if part.get("type") == "output_text":
+                        texts.append(string_value(part.get("text")))
+                    elif part.get("type") == "refusal":
+                        texts.append(string_value(part.get("refusal")))
+            elif item.get("type") == "function_call":
+                calls.append(ProviderToolCall(
+                    tool_call_id=string_value(item.get("call_id"), nonempty=True),
+                    name=string_value(item.get("name"), nonempty=True),
+                    arguments=decode_tool_arguments(item.get("arguments")),
+                ))
+        return ProviderTurn(text="".join(texts) or None, tool_calls=calls,
+                            **UsageTracker().update(data.get("usage") or {}))
+
+    async def _events(self, request: ModelRequest):
+        calls: dict[int, dict] = {}
+        usage = UsageTracker()
+
+        def finish_call(index: int, final: object = None):
+            call = calls[index]
+            if call["ended"]:
+                return []
+            events = []
+            if final is not None:
+                arguments = string_value(final)
+                if not arguments.startswith(call["arguments"]):
+                    raise invalid_response()
+                remainder = arguments[len(call["arguments"]):]
+                if remainder:
+                    events.append((ModelEventType.tool_call_delta,
+                                   {"tool_call_id": call["id"], "arguments_delta": remainder}))
+                call["arguments"] = arguments
+            decode_tool_arguments(call["arguments"])
+            call["ended"] = True
+            events.append((ModelEventType.tool_call_end, {"tool_call_id": call["id"]}))
+            return events
+
+        async with aclosing(self._stream_json(self._payload(request, stream=True))) as chunks:
+            async for data in chunks:
+                kind = string_value(data.get("type"), nonempty=True)
+                if kind in {"response.failed", "response.incomplete"}:
+                    response = object_value(data.get("response"))
+                    self._check_response({**response, "status": kind.split(".")[1]})
+                elif kind in {"response.output_text.delta", "response.refusal.delta"}:
+                    yield ModelEventType.text_delta, {"text": string_value(data.get("delta"))}
+                elif kind in {"response.reasoning_summary_text.delta", "response.reasoning_text.delta"}:
+                    yield ModelEventType.thinking_delta, {"text": string_value(data.get("delta"))}
+                elif kind in {"response.output_item.added", "response.output_item.done"}:
+                    item = object_value(data.get("item"))
+                    if item.get("type") != "function_call":
+                        continue
+                    index = token_count(data.get("output_index"))
+                    call_id = string_value(item.get("call_id"), nonempty=True)
+                    name = string_value(item.get("name"), nonempty=True)
+                    if index not in calls:
+                        calls[index] = {"id": call_id, "name": name, "arguments": "", "ended": False,
+                                        "item_id": item.get("id")}
+                        yield ModelEventType.tool_call_start, {"tool_call_id": call_id, "name": name}
+                    elif calls[index]["id"] != call_id or calls[index]["name"] != name:
+                        raise invalid_response()
+                    if kind == "response.output_item.done":
+                        for event in finish_call(index, item.get("arguments")):
+                            yield event
+                    elif item.get("arguments"):
+                        arguments = string_value(item["arguments"])
+                        calls[index]["arguments"] += arguments
+                        yield ModelEventType.tool_call_delta, {"tool_call_id": call_id, "arguments_delta": arguments}
+                elif kind in {"response.function_call_arguments.delta", "response.function_call_arguments.done"}:
+                    index = token_count(data.get("output_index"))
+                    call = calls.get(index)
+                    if call is None or (data.get("item_id") and call["item_id"] != data["item_id"]):
+                        raise invalid_response()
+                    if kind.endswith(".done"):
+                        for event in finish_call(index, data.get("arguments")):
+                            yield event
+                    else:
+                        if call["ended"]:
+                            raise invalid_response()
+                        fragment = string_value(data.get("delta"))
+                        call["arguments"] += fragment
+                        yield ModelEventType.tool_call_delta, {"tool_call_id": call["id"], "arguments_delta": fragment}
+                elif kind == "response.completed":
+                    response = object_value(data.get("response"))
+                    self._check_response(response)
+                    if any(not call["ended"] for call in calls.values()):
+                        raise truncated_stream()
+                    if response.get("usage") is not None:
+                        yield ModelEventType.usage, usage.update(response["usage"])
+                    return
+                elif kind == "[DONE]":
+                    raise truncated_stream()
+                elif kind in {"response.created", "response.in_progress"}:
+                    response = object_value(data.get("response"))
+                    check_error(response)
+                    if response.get("usage") is not None:
+                        yield ModelEventType.usage, usage.update(response["usage"])
+        raise truncated_stream()

backend/app/providers/registry.py

@@ -1,5 +1,10 @@
 from dataclasses import dataclass
 from time import perf_counter
+from pathlib import Path
+
+from app.config import get_settings
+from app.database.db import connect
+from app.errors import ApiError
 
 from app.contracts import ModelInfo, ProviderConfig, ProviderTestResponse
 from app.providers.base import ModelProvider
@@ -16,20 +21,64 @@ class RegisteredProvider:
 
 
 class ProviderRegistry:
-    def __init__(self) -> None:
+    def __init__(self, factory=None) -> None:
         self._providers: dict[str, RegisteredProvider] = {}
+        self._factory = factory
+        self._loaded_path: Path | None = None
+
+    def _restore(self) -> None:
+        if self._factory is None or self._loaded_path == get_settings().db_path:
+            return
+        conn = connect()
+        try:
+            conn.execute("CREATE TABLE IF NOT EXISTS provider_configs (provider_id TEXT PRIMARY KEY, config_json TEXT NOT NULL)")
+            restored = {}
+            for row in conn.execute("SELECT config_json FROM provider_configs"):
+                config = ProviderConfig.model_validate_json(row["config_json"])
+                if config.provider_id == "mock":
+                    raise ValueError("reserved provider")
+                restored[config.provider_id] = RegisteredProvider(config, self._factory.build(config))
+            if "mock" in self._providers:
+                restored["mock"] = self._providers["mock"]
+            self._providers = restored
+            self._loaded_path = get_settings().db_path
+        except (ValueError, TypeError) as exc:
+            raise ApiError(500, "PROVIDER_STORAGE_INVALID", "Saved provider configuration could not be loaded.") from exc
+        finally:
+            conn.close()
+
+    def _save(self, config: ProviderConfig) -> None:
+        if self._factory is None or config.provider_id == "mock":
+            return
+        conn = connect()
+        try:
+            conn.execute("INSERT OR REPLACE INTO provider_configs VALUES (?, ?)", (config.provider_id, config.model_dump_json()))
+        finally:
+            conn.close()
 
     def register(self, config: ProviderConfig, adapter: ModelProvider) -> None:
+        if config.provider_id != "mock":
+            self._restore()
         if config.provider_id in self._providers:
             raise ValueError(f"Provider already registered: {config.provider_id}")
+        self._save(config)
         self._providers[config.provider_id] = RegisteredProvider(config=config, adapter=adapter)
 
     def unregister(self, provider_id: str) -> None:
+        self._restore()
+        if self._factory is not None:
+            conn = connect()
+            try:
+                conn.execute("DELETE FROM provider_configs WHERE provider_id = ?", (provider_id,))
+            finally:
+                conn.close()
         self._providers.pop(provider_id, None)
 
     def replace(self, config: ProviderConfig, adapter: ModelProvider) -> None:
+        self._restore()
         if config.provider_id not in self._providers:
             raise ProviderNotFoundError(config.provider_id)
+        self._save(config)
         self._providers[config.provider_id] = RegisteredProvider(config=config, adapter=adapter)
 
     def get(self, provider_id: str) -> RegisteredProvider:
@@ -39,12 +88,14 @@ class ProviderRegistry:
         return provider
 
     def get_any(self, provider_id: str) -> RegisteredProvider:
+        self._restore()
         try:
             return self._providers[provider_id]
         except KeyError as exc:
             raise ProviderNotFoundError(provider_id) from exc
 
     def list_configs(self) -> list[ProviderConfig]:
+        self._restore()
         return [item.config.model_copy(deep=True) for item in self._providers.values()]
 
     async def list_models(self, provider_id: str) -> list[ModelInfo]:

backend/app/providers/routing.py

@@ -0,0 +1,287 @@
+"""Capability routing: validated remote results, then an explicit local backend.
+
+Phase E supplies HTTP adapters and injectable local contracts. Hash embeddings are
+still a development placeholder; speech models are installed in phase F.
+"""
+from __future__ import annotations
+
+import hashlib
+import json
+import math
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Protocol
+
+import httpx
+
+from app.contracts import (
+    EmbeddingResult, LocalBackendStatus, ModelBinding, ModelRoutingConfig,
+    ModelRoutingResponse, ProviderType, SpeakerMatchResult,
+)
+from app.database.db import connect, transaction
+from app.errors import ApiError
+from app.providers.base import ProviderError
+from app.providers.credentials import CredentialResolver, CredentialStoreError
+from app.providers.registry import ProviderNotFoundError, ProviderRegistry
+from app.retrieval.embedding import EmbeddingProvider, HashEmbeddingProvider
+
+CAPABILITIES = ("embedding", "transcription", "speaker_matching")
+HTTP_TYPES = {ProviderType.openai_chat, ProviderType.openai_compatible}
+MAX_MEDIA_BYTES = 25 * 1024 * 1024
+MAX_RESPONSE_BYTES = 16 * 1024 * 1024
+
+
+class LocalSpeechBackend(Protocol):
+    available: bool
+
+    async def transcribe(self, source: Path, language: str | None) -> str: ...
+
+    async def match(self, source: Path, reference: Path) -> float: ...
+
+
+class PendingSpeechBackend:
+    available = False
+
+    async def transcribe(self, source: Path, language: str | None) -> str:
+        raise ProviderError("LOCAL_MODEL_NOT_INSTALLED", "本地音频转写模型尚未安装，将在阶段 F 接入。")
+
+    async def match(self, source: Path, reference: Path) -> float:
+        raise ProviderError("LOCAL_MODEL_NOT_INSTALLED", "本地声纹模型尚未安装，将在阶段 F 接入。")
+
+
+@dataclass(frozen=True)
+class RoutedTranscript:
+    text: str
+    source: str
+    fallback_reason: str | None = None
+
+
+def invalid_response() -> ProviderError:
+    return ProviderError("PROVIDER_INVALID_RESPONSE", "Model API returned an invalid result.")
+
+
+def finite_number(value: object) -> bool:
+    if type(value) not in (int, float):
+        return False
+    try:
+        return math.isfinite(value)
+    except (OverflowError, ValueError):
+        return False
+
+
+class ModelRoutingService:
+    def __init__(self, providers: ProviderRegistry, credentials: CredentialResolver, *,
+                 local_embedding: EmbeddingProvider | None = None,
+                 local_speech: LocalSpeechBackend | None = None,
+                 transport: httpx.AsyncBaseTransport | None = None) -> None:
+        self.providers = providers
+        self.credentials = credentials
+        self.local_embedding = local_embedding or HashEmbeddingProvider()
+        self.local_speech = local_speech or PendingSpeechBackend()
+        self.transport = transport
+
+    @staticmethod
+    def _connection():
+        conn = connect()
+        conn.execute("CREATE TABLE IF NOT EXISTS model_routing (id INTEGER PRIMARY KEY CHECK(id=1), config_json TEXT NOT NULL)")
+        return conn
+
+    def configuration(self) -> ModelRoutingConfig:
+        conn = self._connection()
+        try:
+            row = conn.execute("SELECT config_json FROM model_routing WHERE id=1").fetchone()
+            return ModelRoutingConfig.model_validate_json(row[0]) if row else ModelRoutingConfig()
+        except ValueError as exc:
+            raise ApiError(500, "MODEL_ROUTING_STORAGE_INVALID", "Saved model routing could not be loaded.") from exc
+        finally:
+            conn.close()
+
+    def describe(self) -> ModelRoutingResponse:
+        return ModelRoutingResponse(config=self.configuration(), local_backends=[
+            LocalBackendStatus(capability="embedding", status="placeholder" if isinstance(self.local_embedding, HashEmbeddingProvider) else "ready",
+                               message="当前为 hash-v1 确定性占位向量，真实本地语义模型尚未集成。" if isinstance(self.local_embedding, HashEmbeddingProvider) else "本地 Embedding 模型已就绪。"),
+            *[LocalBackendStatus(capability=capability, status="ready" if self.local_speech.available else "not_installed",
+                                 message="本地模型已就绪。" if self.local_speech.available else "阶段 F 接入本地模型；当前保留回退接口。")
+              for capability in ("transcription", "speaker_matching")],
+        ])
+
+    def update(self, config: ModelRoutingConfig) -> ModelRoutingResponse:
+        for capability in CAPABILITIES:
+            binding = getattr(config, capability)
+            if binding:
+                try:
+                    provider = self.providers.get_any(binding.provider_id).config
+                except ProviderNotFoundError as exc:
+                    raise ApiError(422, "PROVIDER_NOT_FOUND", "请选择已保存的提供商。") from exc
+                if provider.provider_type not in HTTP_TYPES:
+                    raise ApiError(422, "MODEL_ROUTING_PROTOCOL_UNSUPPORTED", "该能力当前需要 OpenAI Compatible HTTP 接口。")
+        conn = self._connection()
+        try:
+            with transaction(conn):
+                row = conn.execute("SELECT config_json FROM model_routing WHERE id=1").fetchone()
+                current = ModelRoutingConfig.model_validate_json(row[0]) if row else ModelRoutingConfig()
+                if current.version != config.version:
+                    raise ApiError(409, "MODEL_ROUTING_VERSION_CONFLICT", "配置已更新，请重新加载后再保存。")
+                saved = config.model_copy(update={"version": config.version + 1})
+                conn.execute("INSERT OR REPLACE INTO model_routing VALUES (1, ?)", (saved.model_dump_json(),))
+        finally:
+            conn.close()
+        return self.describe()
+
+    def uses_provider(self, provider_id: str) -> bool:
+        config = self.configuration()
+        return any(binding and binding.provider_id == provider_id for binding in
+                   (getattr(config, name) for name in CAPABILITIES))
+
+    def _remote(self, binding: ModelBinding) -> tuple[str, dict[str, str]]:
+        try:
+            provider = self.providers.get(binding.provider_id).config
+        except ProviderNotFoundError as exc:
+            raise ProviderError("PROVIDER_UNAVAILABLE", "Configured provider is unavailable.") from exc
+        if provider.provider_type not in HTTP_TYPES:
+            raise ProviderError("PROVIDER_CAPABILITY_UNSUPPORTED", "Provider does not support this HTTP capability.")
+        try:
+            key = self.credentials.resolve(provider.credential_id)
+        except CredentialStoreError as exc:
+            raise ProviderError("PROVIDER_CREDENTIAL_UNAVAILABLE", "Provider credential is unavailable.") from exc
+        if provider.credential_id and not key:
+            raise ProviderError("PROVIDER_CREDENTIAL_MISSING", "Provider credential is not configured.")
+        url = (provider.base_url or "https://api.openai.com/v1").rstrip("/") + binding.endpoint
+        return url, {"Authorization": f"Bearer {key}"} if key else {}
+
+    async def _request(self, binding: ModelBinding, *, remote: tuple[str, dict[str, str]] | None = None, **kwargs) -> tuple[dict, str]:
+        url, headers = remote or self._remote(binding)
+        try:
+            async with httpx.AsyncClient(timeout=30, transport=self.transport) as client:
+                async with client.stream("POST", url, headers=headers, **kwargs) as response:
+                    response.raise_for_status()
+                    body = bytearray()
+                    async for chunk in response.aiter_bytes():
+                        body.extend(chunk)
+                        if len(body) > MAX_RESPONSE_BYTES:
+                            raise invalid_response()
+                    data = json.loads(body)
+        except httpx.TimeoutException as exc:
+            raise ProviderError("PROVIDER_TIMEOUT", "Model API timed out.") from exc
+        except httpx.HTTPStatusError as exc:
+            code = {401: "PROVIDER_AUTH_FAILED", 403: "PROVIDER_AUTH_FAILED", 404: "MODEL_NOT_FOUND", 429: "PROVIDER_RATE_LIMITED"}.get(exc.response.status_code, "PROVIDER_UNAVAILABLE")
+            raise ProviderError(code, f"Model API returned HTTP {exc.response.status_code}.") from exc
+        except (httpx.HTTPError, httpx.InvalidURL) as exc:
+            raise ProviderError("PROVIDER_UNAVAILABLE", "Model API is unavailable.") from exc
+        except (ValueError, UnicodeError) as exc:
+            raise invalid_response() from exc
+        if not isinstance(data, dict) or data.get("error"):
+            raise invalid_response()
+        return data, url
+
+    async def embed(self, texts: list[str]) -> EmbeddingResult:
+        binding = self.configuration().embedding
+        reason = None
+        if binding and texts:
+            try:
+                vectors = []
+                dimension = binding.dimensions
+                # Freeze the origin across batches, even if the user edits the provider.
+                remote = self._remote(binding)
+                for start in range(0, len(texts), 32):
+                    batch = texts[start:start + 32]
+                    payload = {"model": binding.model, "input": batch, "encoding_format": "float"}
+                    if binding.dimensions is not None:
+                        payload["dimensions"] = binding.dimensions
+                    data, url = await self._request(binding, remote=remote, json=payload)
+                    items = data.get("data")
+                    if not isinstance(items, list) or len(items) != len(batch):
+                        raise invalid_response()
+                    indexed = {}
+                    for item in items:
+                        if not isinstance(item, dict):
+                            raise invalid_response()
+                        index, vector = item.get("index"), item.get("embedding")
+                        if type(index) is not int or index in indexed or not 0 <= index < len(batch):
+                            raise invalid_response()
+                        if not isinstance(vector, list) or not 1 <= len(vector) <= 16384:
+                            raise invalid_response()
+                        if any(not finite_number(value) for value in vector):
+                            raise invalid_response()
+                        dimension = dimension or len(vector)
+                        norm = math.hypot(*vector)
+                        if len(vector) != dimension or not norm or not math.isfinite(norm):
+                            raise invalid_response()
+                        indexed[index] = [value / norm for value in vector]
+                    vectors.extend(indexed[index] for index in range(len(batch)))
+                identity = json.dumps([url, binding.model, dimension], separators=(",", ":"))
+                return EmbeddingResult(vectors=vectors, source="api", dimensions=dimension,
+                                       model_id="api-" + hashlib.sha256(identity.encode()).hexdigest())
+            except ProviderError as exc:
+                reason = exc.code
+        vectors = await self.local_embedding.embed_documents(texts)
+        return EmbeddingResult(vectors=vectors, source="local", model_id=self.local_embedding.model_id,
+                               dimensions=self.local_embedding.dim, fallback_reason=reason)
+
+    @staticmethod
+    def _media_file(path: Path):
+        try:
+            handle = path.open("rb")
+        except OSError as exc:
+            raise ApiError(404, "ATTACHMENT_NOT_FOUND", "Audio attachment was not found.") from exc
+        import os
+        if not 0 < os.fstat(handle.fileno()).st_size <= MAX_MEDIA_BYTES:
+            handle.close()
+            raise ApiError(413, "ATTACHMENT_TOO_LARGE", "Audio attachment must be between 1 byte and 25 MiB.")
+        return handle
+
+    async def transcribe(self, source: Path, language: str | None) -> RoutedTranscript:
+        binding = self.configuration().transcription
+        if binding is None:
+            with self._media_file(source):
+                pass
+        reason = None
+        if binding:
+            try:
+                fields = {"model": binding.model}
+                if language:
+                    fields["language"] = language
+                with self._media_file(source) as handle:
+                    data, _ = await self._request(binding, data=fields,
+                        files={"file": (source.name, handle, "application/octet-stream")})
+                text = data.get("text")
+                if not isinstance(text, str) or not text.strip():
+                    raise invalid_response()
+                return RoutedTranscript(text=text, source="api")
+            except ProviderError as exc:
+                reason = exc.code
+        try:
+            text = await self.local_speech.transcribe(source, language)
+            if not isinstance(text, str) or not text.strip():
+                raise ProviderError("LOCAL_MODEL_INVALID_RESPONSE", "Local transcription was empty.")
+            return RoutedTranscript(text=text, source="local", fallback_reason=reason)
+        except ProviderError as exc:
+            raise ApiError(503, exc.code, exc.message, {"fallback_reason": reason}) from exc
+
+    async def match_speakers(self, source: Path, reference: Path) -> SpeakerMatchResult:
+        binding = self.configuration().speaker_matching
+        if binding is None:
+            with self._media_file(source), self._media_file(reference):
+                pass
+        reason = None
+        if binding:
+            try:
+                # Explicit application contract, not an OpenAI-standard endpoint.
+                with self._media_file(source) as audio, self._media_file(reference) as sample:
+                    data, _ = await self._request(binding, data={"model": binding.model}, files={
+                        "file": (source.name, audio, "application/octet-stream"),
+                        "reference_file": (reference.name, sample, "application/octet-stream"),
+                    })
+                score = data.get("score")
+                if not finite_number(score) or not 0 <= score <= 1:
+                    raise invalid_response()
+                return SpeakerMatchResult(score=score, source="api")
+            except ProviderError as exc:
+                reason = exc.code
+        try:
+            score = await self.local_speech.match(source, reference)
+            if not finite_number(score) or not 0 <= score <= 1:
+                raise ProviderError("LOCAL_MODEL_INVALID_RESPONSE", "Local speaker matching was invalid.")
+            return SpeakerMatchResult(score=score, source="local", fallback_reason=reason)
+        except ProviderError as exc:
+            raise ApiError(503, exc.code, exc.message, {"fallback_reason": reason}) from exc

backend/app/providers/tool_names.py

@@ -0,0 +1,47 @@
+"""Keep internal namespaced tools compatible with providers' 64-character names."""
+import hashlib
+import re
+from functools import wraps
+
+from app.contracts import MessageRole, ModelRequest
+
+
+def prepare_tool_names(request: ModelRequest) -> tuple[ModelRequest, dict[str, str]]:
+    names = {tool.name for tool in request.tools}
+    for message in request.messages:
+        names.update(call.name for call in message.tool_calls)
+        if message.role == MessageRole.tool and message.name:
+            names.add(message.name)
+    mapping = {name: name for name in names if re.fullmatch(r"[A-Za-z0-9_-]{1,64}", name)}
+    used = set(mapping)
+    for name in sorted(names - mapping.keys()):
+        salt = 0
+        while True:
+            alias = "tool_" + hashlib.sha256(f"{name}:{salt}".encode()).hexdigest()[:56]
+            if alias not in used:
+                break
+            salt += 1
+        mapping[name] = alias
+        used.add(alias)
+    if all(name == alias for name, alias in mapping.items()):
+        return request, {}
+    wire = request.model_copy(deep=True)
+    for tool in wire.tools:
+        tool.name = mapping[tool.name]
+    for message in wire.messages:
+        for call in message.tool_calls:
+            call.name = mapping[call.name]
+        if message.role == MessageRole.tool and message.name:
+            message.name = mapping[message.name]
+    return wire, {alias: name for name, alias in mapping.items()}
+
+
+def mapped_tool_names(complete):
+    @wraps(complete)
+    async def wrapped(self, request: ModelRequest):
+        wire, originals = prepare_tool_names(request)
+        turn = await complete(self, wire)
+        for call in turn.tool_calls:
+            call.name = originals.get(call.name, call.name)
+        return turn
+    return wrapped