feat(api): vertical slice POST /v1/agent/chat and the Celery ping path

One request exercises every layer: JWT auth, quota reservation, a versioned prompt through the LLM gateway, a cost row, quota commit or refund, and the unified envelope. The trivial ping task proves the queue routing and the tk_task transitions before any real long-running task is written. Routes are mounted at the /api/v1 base path of 架构文档 §9.1; /v1/* is rewritten to it at the ASGI layer so both spellings work from one route table.
2026-08-14 00:26:39 +08:00
parent 71204affab
commit 746b66da01
16 changed files with 822 additions and 0 deletions
@@ -0,0 +1,64 @@
+"""``POST /agent/chat`` — the vertical slice.
+
+One request exercises: JWT auth → quota reserve → LLM gateway (routing, prompt
+version, cache-prefix check, daily budget) → ``ob_ai_call`` cost row → quota
+commit/refund → unified envelope. Streaming (SSE, FR-AGT-01) is intentionally
+out of scope for the scaffold.
+"""
+
+from __future__ import annotations
+
+import uuid
+
+from fastapi import APIRouter
+
+from apps.api.deps import AgentServiceDep, CurrentUserId
+from apps.api.schemas import ChatRequest, ChatResponse, ChatUsage
+from packages.llm.errors import (
+    AllProvidersFailedError,
+    CachePrefixViolationError,
+    DailyBudgetExceededError,
+    StructuredOutputError,
+)
+from packages.shared.errors import AppError, ErrorCode
+from packages.shared.response import ok
+
+router = APIRouter(prefix="/agent", tags=["agent"])
+
+
+@router.post("/chat", summary="Single-turn styling chat (non-streaming)")
+async def chat(
+    payload: ChatRequest,
+    user_id: CurrentUserId,
+    agent: AgentServiceDep,
+) -> dict[str, object]:
+    request_key = payload.request_key or uuid.uuid4().hex
+    try:
+        result = await agent.chat(user_id=user_id, message=payload.message, request_key=request_key)
+    except DailyBudgetExceededError as exc:
+        raise AppError(ErrorCode.LLM_DAILY_BUDGET_EXCEEDED) from exc
+    except StructuredOutputError as exc:
+        raise AppError(ErrorCode.LLM_STRUCTURED_OUTPUT_FAILED) from exc
+    except AllProvidersFailedError as exc:
+        raise AppError(ErrorCode.LLM_ALL_PROVIDERS_FAILED) from exc
+    except CachePrefixViolationError as exc:
+        raise AppError(ErrorCode.LLM_PROMPT_CACHE_VIOLATION) from exc
+
+    return ok(
+        ChatResponse(
+            reply=result.reply,
+            provider=result.provider,
+            model=result.model,
+            prompt_id=result.prompt_id,
+            prompt_version=result.prompt_version,
+            call_id=str(result.call_id),
+            usage=ChatUsage(
+                tokens_in=result.tokens_in,
+                tokens_out=result.tokens_out,
+                tokens_cached=result.tokens_cached,
+                latency_ms=result.latency_ms,
+                cost_cents=str(result.cost_cents),
+            ),
+            quota_remaining=result.quota_remaining,
+        ).model_dump()
+    )