fix(chat): 持久化会话与消息

This commit is contained in:
2026-09-05 10:12:09 +08:00
parent d15ceafbe0
commit feb8cc651f
15 changed files with 726 additions and 125 deletions
+2 -2
View File
@@ -27,7 +27,7 @@ uv run uvicorn app.main:app --reload --host 127.0.0.1 --port 8000
| `app/extensions` | Skill、Plugin Host、MCP Registry 与 stdio/HTTP/SSE Bridge |
| `app/providers` | OpenAI Chat/Compatible、Responses、Anthropic Messages、Ollama 与能力路由 |
| `app/local_models` | 模型目录、固定 revision 下载、独立进程、设备回退和队列调度 |
| `app/services` | 索引、知识库上下文、转写、搜索历史、用量和诊断等应用服务 |
| `app/services` | 索引、知识库上下文、聊天记录、转写、搜索历史、用量和诊断等应用服务 |
| `app/benchmarks` | 版本化 RAG Dataset、异步评测、指标与报告 |
## 模型路由
@@ -82,7 +82,7 @@ API Key 可由前端设置页写入,也可通过 `OPENAI_API_KEY`、`DEEPSEEK_
uv run pytest
```
阶段 F 合并基线为 559 项测试通过,另有一条既有 Starlette/httpx 弃用提示。真实模型冒烟脚本:
当前基线为 562 项测试通过,另有一条既有 Starlette/httpx 弃用提示。真实模型冒烟脚本:
```powershell
.venv/Scripts/python scripts/local-model-smoke.py bekko --download
+47 -1
View File
@@ -255,11 +255,57 @@ class ModelRequest(Contract):
class ChatRequest(ModelRequest):
conversation_id: str | None = None
conversation_id: str | None = Field(default=None, min_length=1, max_length=128)
user_message_id: str | None = Field(default=None, min_length=1, max_length=128)
assistant_message_id: str | None = Field(default=None, min_length=1, max_length=128)
conversation_title: str | None = Field(default=None, max_length=120)
use_rag: bool = True
retrieval: SearchRequest | None = None
class ConversationCreateRequest(Contract):
conversation_id: str | None = Field(default=None, min_length=1, max_length=128)
title: str = Field(min_length=1, max_length=120)
@field_validator("title")
@classmethod
def title_must_not_be_blank(cls, value: str) -> str:
value = value.strip()
if not value:
raise ValueError("title must not be blank")
return value
class Conversation(Contract):
conversation_id: str
title: str
created_at: datetime
updated_at: datetime
message_count: int = 0
class ConversationListResponse(Contract):
items: list[Conversation] = Field(default_factory=list)
page: PageMeta = Field(default_factory=PageMeta)
class ChatMessage(Contract):
message_id: str
conversation_id: str
role: Literal["user", "assistant", "system"]
content: str
created_at: datetime
citations: list[dict[str, Any]] = Field(default_factory=list)
tool_calls: list[dict[str, Any]] = Field(default_factory=list)
thinking: str | None = None
usage: dict[str, Any] | None = None
class ChatMessageListResponse(Contract):
items: list[ChatMessage] = Field(default_factory=list)
page: PageMeta = Field(default_factory=PageMeta)
class ModelEventType(str, Enum):
citation = "Citation"
text_delta = "TextDelta"
+27
View File
@@ -132,6 +132,33 @@ MIGRATIONS: list[str] = [
"""
ALTER TABLE blocks ADD COLUMN embedding_local_only INTEGER NOT NULL DEFAULT 0;
""",
# v7: application-owned chat conversations and messages, shared by web and desktop clients.
"""
CREATE TABLE IF NOT EXISTS chat_conversations (
conversation_id TEXT PRIMARY KEY,
title TEXT NOT NULL,
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_chat_conversations_updated
ON chat_conversations(updated_at DESC);
CREATE TABLE IF NOT EXISTS chat_messages (
message_id TEXT PRIMARY KEY,
conversation_id TEXT NOT NULL REFERENCES chat_conversations(conversation_id) ON DELETE CASCADE,
sequence INTEGER NOT NULL,
role TEXT NOT NULL,
content TEXT NOT NULL DEFAULT '',
thinking TEXT,
citations_json TEXT NOT NULL DEFAULT '[]',
tool_calls_json TEXT NOT NULL DEFAULT '[]',
usage_json TEXT,
created_at TEXT NOT NULL,
UNIQUE(conversation_id, sequence)
);
CREATE INDEX IF NOT EXISTS idx_chat_messages_conversation
ON chat_messages(conversation_id, sequence);
""",
]
+123 -3
View File
@@ -1,4 +1,5 @@
import asyncio
import json
from collections.abc import AsyncIterator
from contextlib import aclosing
from datetime import datetime, timezone
@@ -15,6 +16,10 @@ from app.contracts import (
AgentRunListResponse,
AgentTraceResponse,
ChatRequest,
ChatMessageListResponse,
Conversation,
ConversationCreateRequest,
ConversationListResponse,
BenchmarkDatasetListResponse,
BenchmarkEventType,
BenchmarkKind,
@@ -321,6 +326,40 @@ async def clear_search_history() -> dict[str, list[str]]:
return {"queries": []}
@router.get("/chat/conversations", response_model=ConversationListResponse, tags=["Chat"])
async def list_chat_conversations(
limit: int = Query(default=50, ge=1, le=100), offset: int = Query(default=0, ge=0)
) -> ConversationListResponse:
from app.services import chat_history
items, total = chat_history.list_conversations(limit, offset)
return ConversationListResponse(items=items, page=PageMeta(total=total, limit=limit, offset=offset))
@router.post("/chat/conversations", response_model=Conversation, status_code=201, tags=["Chat"])
async def create_chat_conversation(request: ConversationCreateRequest) -> Conversation:
from app.services import chat_history
return chat_history.create(request.title, request.conversation_id)
@router.get("/chat/conversations/{conversation_id}/messages", response_model=ChatMessageListResponse, tags=["Chat"])
async def list_chat_messages(
conversation_id: str,
limit: int = Query(default=500, ge=1, le=1000),
offset: int = Query(default=0, ge=0),
) -> ChatMessageListResponse:
from app.services import chat_history
items, total = chat_history.list_messages(conversation_id, limit, offset)
return ChatMessageListResponse(items=items, page=PageMeta(total=total, limit=limit, offset=offset))
@router.delete("/chat/conversations/{conversation_id}", response_model=OperationResponse, tags=["Chat"])
async def delete_chat_conversation(conversation_id: str) -> OperationResponse:
from app.services import chat_history
if not chat_history.delete(conversation_id):
raise ApiError(404, "CONVERSATION_NOT_FOUND", "conversation not found", {"conversation_id": conversation_id})
return OperationResponse(status="completed", resource_id=conversation_id, message="deleted")
@router.post(
"/chat",
response_class=StreamingResponse,
@@ -333,14 +372,38 @@ async def clear_search_history() -> dict[str, list[str]]:
tags=["Chat"],
)
async def chat(request: ChatRequest) -> StreamingResponse:
from app.services import chat_history
conversation_id = request.conversation_id
assistant_message_id = request.assistant_message_id or f"message_{uuid4().hex}"
if conversation_id:
user_message = next(
(message for message in reversed(request.messages) if message.role.value == "user" and message.content.strip()),
None,
)
if user_message is not None:
chat_history.append_message(
conversation_id,
message_id=request.user_message_id or f"message_{uuid4().hex}",
role="user",
content=user_message.content,
title=request.conversation_title or user_message.content[:30],
)
provider = provider_or_404(request.provider_id)
async def stream() -> AsyncIterator[str]:
sequence = 0
assistant_content = ""
assistant_thinking = ""
citations: list[dict] = []
tool_calls: list[dict] = []
argument_buffers: dict[str, str] = {}
usage: dict | None = None
try:
from app.services.chat_context import prepare
grounded_request, citations = await prepare(request)
for citation in citations:
grounded_request, grounded_citations = await prepare(request)
for citation in grounded_citations:
citations.append(citation)
event = ModelEvent(event=ModelEventType.citation, sequence=sequence,
data=citation, timestamp=utc_now())
sequence += 1
@@ -349,13 +412,58 @@ async def chat(request: ChatRequest) -> StreamingResponse:
async for event in events:
event = event.model_copy(update={"sequence": sequence})
sequence += 1
if event.event == ModelEventType.text_delta:
assistant_content += str(event.data.get("text", ""))
elif event.event == ModelEventType.thinking_delta:
assistant_thinking += str(event.data.get("text", ""))
elif event.event == ModelEventType.tool_call_start:
tool_calls.append({
"tool_call_id": str(event.data.get("tool_call_id", "")),
"name": str(event.data.get("name", "unknown")),
"parameters": event.data.get("arguments") if isinstance(event.data.get("arguments"), dict) else {},
"status": "running",
})
elif event.event == ModelEventType.tool_call_delta:
call_id = str(event.data.get("tool_call_id", ""))
call = next((item for item in tool_calls if item["tool_call_id"] == call_id), None)
if call is not None:
delta = event.data.get("arguments_delta")
if isinstance(delta, str):
argument_buffers[call_id] = argument_buffers.get(call_id, "") + delta
try:
parsed_arguments = json.loads(argument_buffers[call_id])
if isinstance(parsed_arguments, dict):
call["parameters"] = parsed_arguments
except ValueError:
pass
arguments = event.data.get("arguments")
if isinstance(arguments, dict):
call["parameters"].update(arguments)
elif event.event == ModelEventType.tool_call_end:
call_id = str(event.data.get("tool_call_id", ""))
call = next((item for item in tool_calls if item["tool_call_id"] == call_id), None)
if call is not None:
call["status"] = "completed"
elif event.event == ModelEventType.usage:
input_tokens = int(event.data.get("input_tokens", 0))
output_tokens = int(event.data.get("output_tokens", 0))
usage = {"input_tokens": input_tokens, "output_tokens": output_tokens,
"total_tokens": input_tokens + output_tokens}
elif event.event == ModelEventType.error:
if assistant_content:
assistant_content += "\n\n"
assistant_content += str(event.data.get("message", "Model generation failed."))
yield as_sse(event.event.value, event.model_dump_json())
except Exception as exc:
failure_message = exc.message if isinstance(exc, ApiError) else "知识库检索或模型生成失败,请检查服务状态。"
if assistant_content:
assistant_content += "\n\n"
assistant_content += failure_message
error = ModelEvent(
event=ModelEventType.error,
sequence=sequence,
data={"code": exc.code if isinstance(exc, ApiError) else "CHAT_FAILED",
"message": exc.message if isinstance(exc, ApiError) else "知识库检索或模型生成失败,请检查服务状态。"},
"message": failure_message},
timestamp=utc_now(),
)
done = ModelEvent(
@@ -364,6 +472,18 @@ async def chat(request: ChatRequest) -> StreamingResponse:
)
yield as_sse(error.event.value, error.model_dump_json())
yield as_sse(done.event.value, done.model_dump_json())
finally:
if conversation_id and (assistant_content or assistant_thinking or citations or tool_calls):
chat_history.append_message(
conversation_id,
message_id=assistant_message_id,
role="assistant",
content=assistant_content,
thinking=assistant_thinking or None,
citations=citations,
tool_calls=tool_calls,
usage=usage,
)
return StreamingResponse(stream(), media_type="text/event-stream")
+183
View File
@@ -0,0 +1,183 @@
from __future__ import annotations
from contextlib import closing
from datetime import datetime, timezone
import json
import sqlite3
from typing import Any
from uuid import uuid4
from app.contracts import ChatMessage, Conversation
from app.database.db import connect, transaction
from app.errors import ApiError
def _now() -> datetime:
return datetime.now(timezone.utc)
def _conversation(row) -> Conversation:
return Conversation(
conversation_id=row["conversation_id"],
title=row["title"],
created_at=datetime.fromisoformat(row["created_at"]),
updated_at=datetime.fromisoformat(row["updated_at"]),
message_count=row["message_count"],
)
def _message(row) -> ChatMessage:
citations = json.loads(row["citations_json"])
for citation in citations:
if isinstance(citation.get("heading_path"), list):
citation["heading_path"] = " / ".join(str(part) for part in citation["heading_path"])
return ChatMessage(
message_id=row["message_id"],
conversation_id=row["conversation_id"],
role=row["role"],
content=row["content"],
thinking=row["thinking"],
citations=citations,
tool_calls=json.loads(row["tool_calls_json"]),
usage=json.loads(row["usage_json"]) if row["usage_json"] else None,
created_at=datetime.fromisoformat(row["created_at"]),
)
def create(title: str, conversation_id: str | None = None) -> Conversation:
conversation_id = conversation_id or f"conversation_{uuid4().hex}"
now = _now().isoformat()
with closing(connect()) as conn, transaction(conn):
try:
conn.execute(
"INSERT INTO chat_conversations(conversation_id,title,created_at,updated_at) VALUES(?,?,?,?)",
(conversation_id, title.strip(), now, now),
)
except sqlite3.IntegrityError as exc:
raise ApiError(409, "CONVERSATION_ALREADY_EXISTS", "conversation already exists", {"conversation_id": conversation_id}) from exc
result = get(conversation_id)
assert result is not None
return result
def get(conversation_id: str) -> Conversation | None:
with closing(connect()) as conn:
row = conn.execute(
"""SELECT c.*, COUNT(m.message_id) AS message_count
FROM chat_conversations c LEFT JOIN chat_messages m USING(conversation_id)
WHERE c.conversation_id=? GROUP BY c.conversation_id""",
(conversation_id,),
).fetchone()
return _conversation(row) if row else None
def list_conversations(limit: int, offset: int) -> tuple[list[Conversation], int]:
with closing(connect()) as conn:
total = conn.execute("SELECT COUNT(*) FROM chat_conversations").fetchone()[0]
rows = conn.execute(
"""SELECT c.*, COUNT(m.message_id) AS message_count
FROM chat_conversations c LEFT JOIN chat_messages m USING(conversation_id)
GROUP BY c.conversation_id ORDER BY c.updated_at DESC LIMIT ? OFFSET ?""",
(limit, offset),
).fetchall()
return [_conversation(row) for row in rows], total
def list_messages(conversation_id: str, limit: int, offset: int) -> tuple[list[ChatMessage], int]:
if get(conversation_id) is None:
raise ApiError(404, "CONVERSATION_NOT_FOUND", "conversation not found", {"conversation_id": conversation_id})
with closing(connect()) as conn:
total = conn.execute("SELECT COUNT(*) FROM chat_messages WHERE conversation_id=?", (conversation_id,)).fetchone()[0]
rows = conn.execute(
"SELECT * FROM chat_messages WHERE conversation_id=? ORDER BY sequence LIMIT ? OFFSET ?",
(conversation_id, limit, offset),
).fetchall()
return [_message(row) for row in rows], total
def delete(conversation_id: str) -> bool:
with closing(connect()) as conn, transaction(conn):
return conn.execute("DELETE FROM chat_conversations WHERE conversation_id=?", (conversation_id,)).rowcount > 0
def append_message(
conversation_id: str,
*,
message_id: str,
role: str,
content: str,
title: str | None = None,
thinking: str | None = None,
citations: list[dict[str, Any]] | None = None,
tool_calls: list[dict[str, Any]] | None = None,
usage: dict[str, Any] | None = None,
) -> None:
now = _now().isoformat()
clean_title = (title or "").strip() or content[:30].strip() or "New conversation"
with closing(connect()) as conn:
conn.execute("BEGIN IMMEDIATE")
try:
_append_message_in_transaction(
conn, conversation_id, message_id=message_id, role=role, content=content,
title=clean_title, thinking=thinking, citations=citations, tool_calls=tool_calls,
usage=usage, now=now,
)
conn.execute("COMMIT")
except BaseException:
if conn.in_transaction:
conn.execute("ROLLBACK")
raise
def _append_message_in_transaction(
conn,
conversation_id: str,
*,
message_id: str,
role: str,
content: str,
title: str,
thinking: str | None,
citations: list[dict[str, Any]] | None,
tool_calls: list[dict[str, Any]] | None,
usage: dict[str, Any] | None,
now: str,
) -> None:
conversation = conn.execute(
"SELECT 1 FROM chat_conversations WHERE conversation_id=?", (conversation_id,)
).fetchone()
if conversation is None:
conn.execute(
"INSERT INTO chat_conversations(conversation_id,title,created_at,updated_at) VALUES(?,?,?,?)",
(conversation_id, title, now, now),
)
count = conn.execute(
"SELECT COUNT(*) FROM chat_messages WHERE conversation_id=?", (conversation_id,)
).fetchone()[0]
if count == 0:
conn.execute(
"UPDATE chat_conversations SET title=? WHERE conversation_id=?",
(title, conversation_id),
)
existing = conn.execute(
"SELECT conversation_id FROM chat_messages WHERE message_id=?", (message_id,)
).fetchone()
if existing:
if existing["conversation_id"] != conversation_id:
raise ApiError(409, "MESSAGE_ID_CONFLICT", "message id belongs to another conversation")
return
sequence = conn.execute(
"SELECT COALESCE(MAX(sequence), -1) + 1 FROM chat_messages WHERE conversation_id=?",
(conversation_id,),
).fetchone()[0]
conn.execute(
"""INSERT INTO chat_messages(message_id,conversation_id,sequence,role,content,thinking,citations_json,tool_calls_json,usage_json,created_at)
VALUES(?,?,?,?,?,?,?,?,?,?)""",
(message_id, conversation_id, sequence, role, content, thinking,
json.dumps(citations or [], ensure_ascii=False), json.dumps(tool_calls or [], ensure_ascii=False),
json.dumps(usage, ensure_ascii=False) if usage is not None else None, now),
)
conn.execute(
"UPDATE chat_conversations SET updated_at=? WHERE conversation_id=?",
(now, conversation_id),
)
+82
View File
@@ -0,0 +1,82 @@
from datetime import datetime, timezone
from types import SimpleNamespace
from fastapi.testclient import TestClient
from app.contracts import ModelEvent, ModelEventType
from app.main import app
from app.services import chat_history
def test_chat_history_survives_new_connections_and_deletes_messages() -> None:
conversation = chat_history.create("Persistent chat", "conversation-1")
chat_history.append_message(
conversation.conversation_id,
message_id="user-1",
role="user",
content="question",
)
chat_history.append_message(
conversation.conversation_id,
message_id="assistant-1",
role="assistant",
content="answer",
citations=[{"note_id": "note-1", "heading_path": ["Heading"]}],
usage={"input_tokens": 2, "output_tokens": 1, "total_tokens": 3},
)
listed, total = chat_history.list_conversations(50, 0)
messages, message_total = chat_history.list_messages("conversation-1", 50, 0)
assert total == 1
assert listed[0].message_count == 2
assert message_total == 2
assert messages[1].citations[0]["note_id"] == "note-1"
assert messages[1].usage["total_tokens"] == 3
assert chat_history.delete("conversation-1") is True
assert chat_history.list_conversations(50, 0)[1] == 0
def test_chat_stream_persists_user_and_assistant_messages(monkeypatch) -> None:
from app import routes
class Adapter:
async def stream(self, _request):
now = datetime.now(timezone.utc)
yield ModelEvent(event=ModelEventType.text_delta, data={"text": "persisted answer"}, timestamp=now)
yield ModelEvent(event=ModelEventType.usage, data={"input_tokens": 4, "output_tokens": 2}, timestamp=now)
yield ModelEvent(event=ModelEventType.done, timestamp=now)
monkeypatch.setattr(routes, "provider_or_404", lambda _provider_id: SimpleNamespace(adapter=Adapter()))
payload = {
"provider_id": "configured",
"model": "model",
"conversation_id": "conversation-stream",
"user_message_id": "user-stream",
"assistant_message_id": "assistant-stream",
"conversation_title": "Persist this",
"use_rag": False,
"messages": [{"role": "user", "content": "question"}],
}
with TestClient(app) as client:
with client.stream("POST", "/api/chat", json=payload) as response:
assert response.status_code == 200
assert "persisted answer" in "".join(response.iter_text())
messages = client.get("/api/chat/conversations/conversation-stream/messages").json()["items"]
conversations = client.get("/api/chat/conversations").json()["items"]
assert [message["content"] for message in messages] == ["question", "persisted answer"]
assert messages[1]["usage"]["total_tokens"] == 6
assert conversations[0]["title"] == "Persist this"
assert conversations[0]["message_count"] == 2
def test_chat_conversation_crud_api() -> None:
with TestClient(app) as client:
created = client.post("/api/chat/conversations", json={"conversation_id": "crud", "title": "CRUD"})
assert created.status_code == 201
assert client.get("/api/chat/conversations").json()["page"]["total"] == 1
assert client.get("/api/chat/conversations/crud/messages").json()["items"] == []
assert client.delete("/api/chat/conversations/crud").status_code == 200
missing = client.get("/api/chat/conversations/crud/messages")
assert missing.status_code == 404
assert missing.json()["error"]["code"] == "CONVERSATION_NOT_FOUND"