mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* [25aa5b24] Implement rate-limit Zustand store, Axios interceptor, WebSocket hook, banner component, and page-load sync (#99) (#101) * [25aa5b24] feat(rate-limits): add types, Zustand store, Axios 429 interceptor, WS hook, sync hook, and banner component - panel/src/types/rate-limits.ts: RateLimitEntry, RateLimitHitEvent, RateLimitLiftedEvent, RateLimitApiResponse - panel/src/store/rate-limit-store.ts: useRateLimitStore with Map state, hitRateLimit/liftRateLimit/syncFromApi - panel/src/lib/api/rate-limits.ts: GET /api/system/rate-limits with isMockMode guard - panel/src/lib/api/client.ts: 429 interceptor dispatches to store first, Sonner toast on retry exhaustion - panel/src/hooks/use-rate-limit-websocket.ts: RATE_LIMIT_HIT/LIFTED events + onReconnect callback - panel/src/hooks/use-rate-limit-sync.ts: mount sync + no-op with console.warn when endpoint unavailable - panel/src/components/rate-limit/rate-limit-banner.tsx: amber rows with countdown, no dismiss button - panel/src/app/(dashboard)/layout.tsx: RateLimitBanner mounted below Header - store/index.ts, hooks/index.ts: export new store and hooks * [25aa5b24] fix(rate-limit-banner): use lint-clean countdown pattern (computeSecondsLeft outside render) * [25aa5b24] fix(client): add real retry loop to 429 interceptor so Sonner toast fires on exhaustion - Increment error.config._retryCount and return api(error.config) when retryCount < RATE_LIMIT_MAX_RETRIES, actually retrying the request. - Toast fires only when retryCount >= RATE_LIMIT_MAX_RETRIES (3 attempts). - Fixes AC4: toast was dead code because without return api(error.config) every 429 saw retryCount=1, permanently below the threshold of 3. --------- Co-authored-by: Frontend Developer 1 <fe-dev-1@agents.roboco.dev> * [4112cd34] feat(rate-limit): add RateLimitError with 5-retry exponential backoff at all LLM call sites (#102) (#103) - Create roboco/services/exceptions.py with RateLimitError(provider, retry_after), HTTP_TOO_MANY_REQUESTS, MAX_RATE_LIMIT_RETRIES constants, and parse_retry_after_header() helper - extraction.py: extract _call_anthropic_with_retry() helper; retry Anthropic call 5x on 429 with exponential backoff; re-raise RateLimitError from outer except instead of swallowing it - ollama_embedder.py: 5-retry outer loop (429) wrapping existing 3-retry inner loop (ConnectError/Timeout) for all 4 call sites; two concerns kept isolated - indexes/base.py, mentor.py, validator.py: replace magic 429 literals with HTTP_TOO_MANY_REQUESTS; 5-retry loop on 429 for LLM calls - middleware.py: add rate_limit_exception_handler returning HTTP 429 with Retry-After response header - tests/unit/services/test_rate_limit_retry.py: 28 tests covering exhaustion, Retry-After header sleep, partial retries then success, ConnectError isolation Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> * [18107054] feat(rate-limit): Redis rate-limit state tracker + i_am_blocked rate_limited path (#105) (#106) - Add RateLimitStateTracker in roboco/services/gateway/rate_limit_tracker.py with activate(), clear(), is_rate_limited(), get_state(), increment_probe_failures(), reset_probe_failures() backed by redis.asyncio - Add RATE_LIMIT_HIT = "rate_limit.hit" to EventType StrEnum in events.py - Add _handle_rate_limited_parking() to Choreographer: intercepts i_am_blocked(reason='rate_limited') before block state transition, parks all active agents sharing affected provider via mark_waiting_long, publishes RATE_LIMIT_HIT event to StreamEventBus, task stays in_progress - Add get_provider_for_agent() and get_active_agent_slugs_for_provider() helper methods to AgentOrchestrator - Wire orchestrator and stream_bus into ChoreographerDeps via deps.py - Add test_rate_limit_tracker.py (basic ops, probe failures, cross-reconnection persistence, provider isolation) and test_i_am_blocked_rate_limited.py (AC3/AC4/AC5 coverage: task stays in_progress, mark_waiting_long call count equals active agent count, RATE_LIMIT_HIT event payload structure) Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> * [5501e4b4] Wire RateLimitStateTracker into live orchestrator paths — 4 CEO-identified integration gaps (#109) * [8451ca50] feat(gateway): wire RateLimitStateTracker.activate() into i_am_blocked rate-limited path and add provider-rate-limit gate to decide_spawn() (#107) - Add provider/provider_rate_limited optional fields to TriggerContext (backward-compatible defaults) - Insert rule 2 in decide_spawn(): QUEUE when trigger.provider_rate_limited is True with reason 'provider X rate-limited' - Call RateLimitStateTracker(provider).activate() in _handle_rate_limited_parking() after mark_waiting_long loop (wrapped in contextlib.suppress for Redis fault tolerance) - Extend gateway_pre_spawn_check() with optional provider param; check RateLimitStateTracker.is_rate_limited() when provider is known - Pass provider=self.get_provider_for_agent(agent_id) from orchestrator call site - Add TestProviderRateLimitGate (6 tests) to test_trigger_filter.py - Add TestRateLimitTrackerActivateOnParking (6 tests) to test_i_am_blocked_rate_limited.py - All 38 unit tests pass; ruff and mypy clean on changed files Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> * [e9cef0f0] feat(rate-limits): sweeper probe loop, CEO notification, and GET /api/system/rate-limits endpoint (AC4, AC8, AC9) (#108) - Add RATE_LIMIT_LIFTED event type to EventType enum in models/events.py - Add RateLimitStateTracker.list_rate_limited_providers() classmethod to scan Redis for all currently rate-limited providers (used by the new endpoint) - Add orchestrator._rate_limit_probe_loop(): background task started/stopped in start()/stop(), runs _sweep_rate_limit_probes() every 30s - Add orchestrator._probe_one_provider(): checks estimated_lift_at gate, calls _do_probe(); on success: tracker.clear(), resolve_wait() for all parked agents with waiting_for='rate_limit_lifted' matching the provider, publishes RATE_LIMIT_LIFTED event; on failure: increments probe_failures counter, sends CEO notification at threshold 10 (once per episode via _rate_limit_ceo_notified) - Add orchestrator._make_tracker(): injectable factory for RateLimitStateTracker - Add orchestrator._do_probe(): overridable async bool probe (default: True) - Add orchestrator._notify_rate_limit_ceo(): high-priority notification to CEO containing provider name, duration since activation, and paused agent count - Add roboco/api/routes/system.py with GET /rate-limits endpoint (AC9) - Register system_router in app.py under /api/system prefix - Add 17 unit tests in tests/unit/runtime/test_rate_limit_sweep.py covering all AC4/AC8/AC9 paths: probe success/failure, CEO threshold, endpoint schema Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> --------- Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> --------- Co-authored-by: Frontend Developer 1 <fe-dev-1@agents.roboco.dev> Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> Co-authored-by: Renn F <rennf93@users.noreply.github.com>
422 lines
13 KiB
Python
422 lines
13 KiB
Python
"""
|
|
API Middleware
|
|
|
|
Request/response middleware for logging, error handling, and correlation IDs.
|
|
"""
|
|
|
|
import time
|
|
import uuid
|
|
from collections.abc import Callable, Sequence
|
|
from typing import Any, cast
|
|
|
|
import structlog
|
|
from fastapi import FastAPI, HTTPException, Request, Response
|
|
from fastapi import status as http_status
|
|
from fastapi.exceptions import RequestValidationError
|
|
from fastapi.responses import JSONResponse
|
|
from starlette.middleware.base import BaseHTTPMiddleware
|
|
|
|
from roboco.api.schemas.common import ErrorCode
|
|
from roboco.exceptions import (
|
|
AuthenticationError,
|
|
InvalidStateError,
|
|
NotFoundError,
|
|
PermissionDeniedError,
|
|
RobocoError,
|
|
ValidationError,
|
|
)
|
|
from roboco.services.base import (
|
|
ConflictError as ServiceConflictError,
|
|
)
|
|
from roboco.services.base import (
|
|
NotFoundError as ServiceNotFoundError,
|
|
)
|
|
from roboco.services.base import (
|
|
ServiceError,
|
|
ServiceUnavailableError,
|
|
)
|
|
from roboco.services.base import (
|
|
UnauthorizedError as ServiceUnauthorizedError,
|
|
)
|
|
from roboco.services.base import (
|
|
ValidationError as ServiceValidationError,
|
|
)
|
|
from roboco.services.exceptions import RateLimitError
|
|
|
|
logger = structlog.get_logger()
|
|
|
|
|
|
# =============================================================================
|
|
# CORRELATION ID MIDDLEWARE
|
|
# =============================================================================
|
|
|
|
|
|
class CorrelationIdMiddleware(BaseHTTPMiddleware):
|
|
"""
|
|
Adds a correlation ID to each request for tracing.
|
|
|
|
The correlation ID is:
|
|
- Extracted from X-Correlation-ID header if present
|
|
- Generated if not present
|
|
- Added to response headers
|
|
- Bound to the logger context
|
|
"""
|
|
|
|
async def dispatch(self, request: Request, call_next: Callable) -> Response:
|
|
# Get or generate correlation ID
|
|
correlation_id = request.headers.get("X-Correlation-ID")
|
|
if not correlation_id:
|
|
correlation_id = str(uuid.uuid4())
|
|
|
|
# Store in request state for access in handlers
|
|
request.state.correlation_id = correlation_id
|
|
|
|
# Bind to structlog context
|
|
structlog.contextvars.clear_contextvars()
|
|
structlog.contextvars.bind_contextvars(
|
|
correlation_id=correlation_id,
|
|
path=request.url.path,
|
|
method=request.method,
|
|
)
|
|
|
|
# Process request
|
|
response = cast("Response", await call_next(request))
|
|
|
|
# Add correlation ID to response
|
|
response.headers["X-Correlation-ID"] = correlation_id
|
|
|
|
return response
|
|
|
|
|
|
# =============================================================================
|
|
# REQUEST LOGGING MIDDLEWARE
|
|
# =============================================================================
|
|
|
|
|
|
class RequestLoggingMiddleware(BaseHTTPMiddleware):
|
|
"""
|
|
Logs request/response details with timing.
|
|
"""
|
|
|
|
async def dispatch(self, request: Request, call_next: Callable) -> Response:
|
|
start_time = time.perf_counter()
|
|
|
|
# Log request
|
|
logger.info(
|
|
"Request started",
|
|
path=request.url.path,
|
|
method=request.method,
|
|
query_params=dict(request.query_params),
|
|
)
|
|
|
|
try:
|
|
response = cast("Response", await call_next(request))
|
|
duration_ms = (time.perf_counter() - start_time) * 1000
|
|
|
|
# Log response
|
|
logger.info(
|
|
"Request completed",
|
|
status_code=response.status_code,
|
|
duration_ms=round(duration_ms, 2),
|
|
)
|
|
|
|
# Add timing header
|
|
response.headers["X-Response-Time-Ms"] = str(round(duration_ms, 2))
|
|
|
|
return response
|
|
|
|
except Exception as e:
|
|
duration_ms = (time.perf_counter() - start_time) * 1000
|
|
logger.exception(
|
|
"Request failed",
|
|
duration_ms=round(duration_ms, 2),
|
|
error=str(e),
|
|
)
|
|
raise
|
|
|
|
|
|
# =============================================================================
|
|
# EXCEPTION HANDLERS
|
|
# =============================================================================
|
|
|
|
|
|
def get_status_code(exc: RobocoError) -> int:
|
|
"""Map exception type to HTTP status code."""
|
|
status_map = {
|
|
NotFoundError: 404,
|
|
ValidationError: 422,
|
|
InvalidStateError: 409,
|
|
PermissionDeniedError: 403,
|
|
AuthenticationError: 401,
|
|
}
|
|
|
|
for exc_type, status in status_map.items():
|
|
if isinstance(exc, exc_type):
|
|
return status
|
|
|
|
# Default for other RobocoError subclasses
|
|
return 400
|
|
|
|
|
|
async def roboco_exception_handler(request: Request, exc: Exception) -> JSONResponse:
|
|
"""Handle RobocoError exceptions."""
|
|
roboco_exc = cast("RobocoError", exc)
|
|
status_code = get_status_code(roboco_exc)
|
|
|
|
# Add correlation ID to error details
|
|
correlation_id = getattr(request.state, "correlation_id", None)
|
|
if correlation_id:
|
|
roboco_exc.details["correlation_id"] = correlation_id
|
|
|
|
logger.warning(
|
|
"Handled exception",
|
|
error_code=roboco_exc.code,
|
|
error_message=roboco_exc.message,
|
|
status_code=status_code,
|
|
)
|
|
|
|
return JSONResponse(
|
|
status_code=status_code,
|
|
content=roboco_exc.to_dict(),
|
|
)
|
|
|
|
|
|
# `roboco.services.base.ServiceError` is a parallel exception hierarchy that
|
|
# does NOT inherit from `RobocoError` (it extends `Exception` directly), so
|
|
# `roboco_exception_handler` never sees it and the requests fall through to
|
|
# `generic_exception_handler` as 500s. Map its subclasses to the same status
|
|
# codes used in the RobocoError handler so route-layer try/except blocks can
|
|
# surface clean 4xx codes whether the service raises from `roboco.exceptions`
|
|
# or `roboco.services.base`.
|
|
_SERVICE_ERROR_STATUS: dict[type[ServiceError], int] = {
|
|
ServiceNotFoundError: 404,
|
|
ServiceValidationError: 422,
|
|
ServiceConflictError: 409,
|
|
ServiceUnauthorizedError: 403,
|
|
ServiceUnavailableError: 503,
|
|
}
|
|
|
|
|
|
async def service_exception_handler(request: Request, exc: Exception) -> JSONResponse:
|
|
"""Handle `roboco.services.base.ServiceError` and subclasses."""
|
|
svc_exc = cast("ServiceError", exc)
|
|
status_code = 500
|
|
for exc_type, mapped_status in _SERVICE_ERROR_STATUS.items():
|
|
if isinstance(svc_exc, exc_type):
|
|
status_code = mapped_status
|
|
break
|
|
|
|
correlation_id = getattr(request.state, "correlation_id", None)
|
|
details = dict(svc_exc.details)
|
|
if correlation_id:
|
|
details["correlation_id"] = correlation_id
|
|
|
|
logger.warning(
|
|
"Handled exception",
|
|
error_type=type(svc_exc).__name__,
|
|
error_message=svc_exc.message,
|
|
status_code=status_code,
|
|
)
|
|
|
|
return JSONResponse(
|
|
status_code=status_code,
|
|
content={
|
|
"error": type(svc_exc).__name__,
|
|
"message": svc_exc.message,
|
|
"details": details,
|
|
},
|
|
)
|
|
|
|
|
|
async def rate_limit_exception_handler(
|
|
request: Request, exc: Exception
|
|
) -> JSONResponse:
|
|
"""Handle :class:`~roboco.services.exceptions.RateLimitError`.
|
|
|
|
Returns HTTP 429 with a ``Retry-After`` response header (when available)
|
|
and a structured JSON body so API consumers can back off gracefully.
|
|
"""
|
|
rl_exc = cast("RateLimitError", exc)
|
|
correlation_id = getattr(request.state, "correlation_id", None)
|
|
|
|
logger.warning(
|
|
"LLM rate limit exhausted",
|
|
provider=rl_exc.provider,
|
|
retry_after=rl_exc.retry_after,
|
|
)
|
|
|
|
content: dict = {
|
|
"error": "rate_limit_exceeded",
|
|
"provider": rl_exc.provider,
|
|
"message": str(rl_exc),
|
|
}
|
|
if correlation_id:
|
|
content["correlation_id"] = correlation_id
|
|
|
|
headers: dict[str, str] = {}
|
|
if rl_exc.retry_after is not None:
|
|
headers["Retry-After"] = str(int(rl_exc.retry_after))
|
|
|
|
return JSONResponse(
|
|
status_code=429,
|
|
content=content,
|
|
headers=headers,
|
|
)
|
|
|
|
|
|
async def generic_exception_handler(request: Request, exc: Exception) -> JSONResponse:
|
|
"""Handle unexpected exceptions."""
|
|
correlation_id = getattr(request.state, "correlation_id", None)
|
|
|
|
logger.exception(
|
|
"Unhandled exception",
|
|
error=str(exc),
|
|
error_type=type(exc).__name__,
|
|
)
|
|
|
|
return JSONResponse(
|
|
status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
|
|
content={
|
|
"error": {
|
|
"code": ErrorCode.INTERNAL_ERROR,
|
|
"message": "An internal error occurred",
|
|
"details": {
|
|
"correlation_id": correlation_id,
|
|
},
|
|
}
|
|
},
|
|
)
|
|
|
|
|
|
# Map HTTP status codes to string error codes
|
|
_HTTP_TO_ERROR_CODE: dict[int, str] = {
|
|
400: ErrorCode.INVALID_INPUT,
|
|
401: ErrorCode.NOT_AUTHORIZED,
|
|
403: ErrorCode.ACCESS_DENIED,
|
|
404: ErrorCode.NOT_FOUND,
|
|
409: ErrorCode.INVALID_INPUT, # Conflict
|
|
422: ErrorCode.INVALID_INPUT, # Validation error
|
|
500: ErrorCode.INTERNAL_ERROR,
|
|
}
|
|
|
|
|
|
async def http_exception_handler(request: Request, exc: Exception) -> JSONResponse:
|
|
"""
|
|
Handle FastAPI HTTPException with standardized error format.
|
|
|
|
Converts HTTP status codes to string error codes for consistency with MCP.
|
|
"""
|
|
http_exc = cast("HTTPException", exc)
|
|
correlation_id = getattr(request.state, "correlation_id", None)
|
|
|
|
# Map status code to error code
|
|
error_code = _HTTP_TO_ERROR_CODE.get(http_exc.status_code, ErrorCode.INTERNAL_ERROR)
|
|
|
|
logger.warning(
|
|
"HTTP exception",
|
|
status_code=http_exc.status_code,
|
|
error_code=error_code,
|
|
detail=http_exc.detail,
|
|
)
|
|
|
|
response_content: dict = {
|
|
"error": {
|
|
"code": error_code,
|
|
"message": str(http_exc.detail),
|
|
}
|
|
}
|
|
|
|
if correlation_id:
|
|
response_content["error"]["details"] = {"correlation_id": correlation_id}
|
|
|
|
return JSONResponse(
|
|
status_code=http_exc.status_code,
|
|
content=response_content,
|
|
)
|
|
|
|
|
|
# =============================================================================
|
|
# SETUP FUNCTION
|
|
# =============================================================================
|
|
|
|
|
|
def _uuid_field_remediation(errors: Sequence[Any]) -> str | None:
|
|
"""Spell out the fix when a truncated id is sent where a UUID is required.
|
|
|
|
Agents routinely copy the 8-character task prefix the system shows them
|
|
(e.g. the ``[cee99ecc]`` commit prefix) and send it as ``task_id``, which
|
|
fails UUID validation with an opaque "invalid length" message and wastes a
|
|
call. Detect that case and hand back an actionable remediation instead.
|
|
"""
|
|
for err in errors:
|
|
if not isinstance(err, dict):
|
|
continue
|
|
loc = err.get("loc") or ()
|
|
field = loc[-1] if loc else None
|
|
if field == "task_id" and "uuid" in str(err.get("type", "")).lower():
|
|
return (
|
|
"Use the FULL 36-character task UUID, not the 8-character short "
|
|
"form shown in commit prefixes or summaries. The full id is in "
|
|
"the `task_id` field of the envelope returned by give_me_work "
|
|
"or your most recent verb."
|
|
)
|
|
return None
|
|
|
|
|
|
async def request_validation_handler(request: Request, exc: Exception) -> JSONResponse:
|
|
"""Log the rejected body before returning the standard 422 response.
|
|
|
|
FastAPI's default 422 returns validation details to the client but
|
|
nothing lands in server logs. During smoke tests this leaves us
|
|
blind to which field actually broke. Log the body + the per-field
|
|
errors so the next 422 is debuggable in one log scan.
|
|
|
|
When the failure is a truncated ``task_id`` (the recurring agent mistake),
|
|
add a ``remediate`` hint so the agent knows to retry with the full UUID.
|
|
"""
|
|
rve = cast("RequestValidationError", exc)
|
|
body = rve.body if isinstance(rve.body, str | bytes | dict | list) else None
|
|
errors = rve.errors()
|
|
logger.warning(
|
|
"Request validation failed",
|
|
path=request.url.path,
|
|
method=request.method,
|
|
body=body,
|
|
errors=errors,
|
|
)
|
|
content: dict[str, Any] = {"detail": errors, "body": body}
|
|
remediate = _uuid_field_remediation(errors)
|
|
if remediate is not None:
|
|
content["remediate"] = remediate
|
|
return JSONResponse(
|
|
status_code=http_status.HTTP_422_UNPROCESSABLE_ENTITY,
|
|
content=content,
|
|
)
|
|
|
|
|
|
def setup_middleware(app: FastAPI) -> None:
|
|
"""
|
|
Setup all middleware for the application.
|
|
|
|
Order matters:
|
|
1. CorrelationIdMiddleware - first to set correlation ID
|
|
2. RequestLoggingMiddleware - logs with correlation ID
|
|
|
|
Exception handler priority:
|
|
1. RequestValidationError - 422s; log body + per-field errors
|
|
2. HTTPException - most common, converts to string error codes
|
|
3. RobocoError - custom domain exceptions
|
|
4. Exception - catch-all for unexpected errors
|
|
"""
|
|
# Exception handlers (order: specific to general)
|
|
app.add_exception_handler(RequestValidationError, request_validation_handler)
|
|
app.add_exception_handler(HTTPException, http_exception_handler)
|
|
app.add_exception_handler(RobocoError, roboco_exception_handler)
|
|
app.add_exception_handler(ServiceError, service_exception_handler)
|
|
app.add_exception_handler(RateLimitError, rate_limit_exception_handler)
|
|
app.add_exception_handler(Exception, generic_exception_handler)
|
|
|
|
# Middleware (added in reverse order due to LIFO)
|
|
app.add_middleware(RequestLoggingMiddleware)
|
|
app.add_middleware(CorrelationIdMiddleware)
|