mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
fix: prod triage 2026-07-08 — MCP auth residue, gateway envelopes, verb-loop cap, A2A interjection, manual spawn UX (#334)
* fix(auth): pass agent UUID to CLI-arg MCP servers (optimal/docs/search) The container token is HMAC-signed over the agent UUID (#314), but the optimal/docs/search MCP servers received the slug as their CLI arg and sent X-Agent-ID=<slug>, so every research/RAG/docs call 401ed with signature mismatch under enforced auth. Pass the already-computed agent_uuid in the three args lists instead. * fix(gateway): include remediate in gateway.rejected audit details Conventions-gate rejections carry the offending file:line listing only in the envelope's remediate field, which the audit row dropped -- ops logs showed just the violation count with no way to see what blocked. * fix(gateway): return envelope on do/commit git failure A GitError from the commit verb propagated to the generic middleware handler, so agents got a raw error blob with no remediate/next. Catch it and return an error envelope; 'no changes added to commit' with an explicit files list now names the mismatch and the omit-files fallback. * fix(agent-sdk): absolute rejection cap breaks slow-drip verb loops The verb circuit breaker only counted rejections inside a 60s sliding window, so an agent retrying i_am_done every 3-4 minutes looped for 30+ minutes without tripping it. Add a session-scoped cumulative per-(verb, task) cap at 3x the windowed limit that trips regardless of pacing. * feat(a2a): CEO chime-in interjects into the viewed conversation Previously reply_as_ceo re-homed the message into a canonical CEO<->target conversation with no panel surface, so a chime-in reported success but was invisible and only opportunistically delivered. interject_as_ceo now inserts the message into the conversation being viewed (from_agent=ceo, directed via an @target content prefix), bumps that conversation's counters with the unread ping keyed to the addressed participant, and both participants see it in transcript and read_a2a. * feat(panel): manual spawn carries task + message, surfaces refusals The agent detail page spawned with no request body (task/message impossible), the spawn button could double-fire (2.5ms double-POST seen live), and refusal reasons never reached the UI: readiness refusals were generic 500s and the already-running no-op looked like success. Detail page now uses SpawnAgentDialog, a synchronous ref guard blocks re-entry, AgentReadinessError maps to 409 with its reason shown, already_running is signalled and toasted, and a task_id builds a task-aware prompt instructing the claim (task_id alone never did), with the CEO's message appended as a note. * test(panel): align a2a page test with the interjection footer copy The chime-in rebuild changed the composer footer; the page-level test asserting the old copy was outside the rebuild's scoped vitest run. * fix(api): commit the request DB session before the response is sent FastAPI unwinds yield-dependencies after the response bytes go out, so get_db's post-yield commit raced the client's next request -- a verb could return ok while its claim/status write was still uncommitted (the e2e ok-without-effect flake family), and a failed commit was silently lost behind an already-sent 200. DbCommitMiddleware (innermost, pure ASGI) commits the session stashed by get_db_committed before forwarding http.response.start; commit failure now surfaces as a 5xx. get_db is untouched for its direct non-request callers. * fix(db): invalidate, not rollback, the session on request cancellation With the commit moved into the send path, the flow-verb timeout can cancel mid-commit; rolling back then issues another command over an asyncpg connection stranded mid-wire-protocol, and the poisoned connection segfaults uvloop/asyncpg when a later checkout recycles it (3/3 identical CI faulthandler dumps). On CancelledError discard the connection via session.invalidate() -- SQLAlchemy's documented handling for a timeout during commit -- and keep rollback for plain exceptions. --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
This commit is contained in:
@@ -20,7 +20,11 @@ from unittest.mock import patch
|
||||
import pytest
|
||||
import roboco.agent_sdk.server as srv
|
||||
from fastapi.testclient import TestClient
|
||||
from roboco.foundation.policy.agent_loop import VERB_RETRY_LIMITS, retry_limit_for
|
||||
from roboco.foundation.policy.agent_loop import (
|
||||
VERB_RETRY_LIMITS,
|
||||
absolute_retry_limit_for,
|
||||
retry_limit_for,
|
||||
)
|
||||
from roboco.services.gateway.envelope import Envelope
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -428,3 +432,168 @@ def test_qa_handoff_retry_keys_match_mcp_verb_names() -> None:
|
||||
assert "fail" in VERB_RETRY_LIMITS
|
||||
assert retry_limit_for("pass") == VERB_RETRY_LIMITS["pass"]
|
||||
assert retry_limit_for("fail") == VERB_RETRY_LIMITS["fail"]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# ABSOLUTE (session-scoped, never-pruned) breaker — the slow-drip fix
|
||||
#
|
||||
# Production, 2026-07-08: an agent's i_am_done was rejected once every 3-4
|
||||
# minutes for 30+ minutes. Each rejection arrived alone in an empty 60s
|
||||
# window, so `_check_verb_circuit` never saw more than 1 attempt at a time
|
||||
# and never tripped. `_verb_absolute_attempts` counts cumulatively across
|
||||
# the whole container session (never pruned) so pacing can't defeat it.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_I_AM_DONE_ABSOLUTE_CAP = 9 # VERB_RETRY_LIMITS["i_am_done"] * multiplier(3)
|
||||
|
||||
|
||||
def test_i_am_done_absolute_cap_matches_foundation() -> None:
|
||||
"""Pin the effective absolute cap so a foundation change is caught here too."""
|
||||
assert absolute_retry_limit_for("i_am_done") == _I_AM_DONE_ABSOLUTE_CAP
|
||||
|
||||
|
||||
def test_absolute_tracker_keys_per_verb_task_pair() -> None:
|
||||
"""Different tasks accumulate independent absolute counts."""
|
||||
a_count = 5
|
||||
b_count = 2
|
||||
for _ in range(a_count):
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
for _ in range(b_count):
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-B")
|
||||
|
||||
assert srv._verb_absolute_attempt_count("i_am_done", "task-A") == a_count
|
||||
assert srv._verb_absolute_attempt_count("i_am_done", "task-B") == b_count
|
||||
|
||||
|
||||
def test_absolute_tracker_keys_per_verb_independent_of_task() -> None:
|
||||
"""Different verbs on the same task don't share the cumulative counter."""
|
||||
done_count = 4
|
||||
submit_count = 1
|
||||
for _ in range(done_count):
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
for _ in range(submit_count):
|
||||
srv._record_verb_attempt_absolute("submit_up", "task-A")
|
||||
|
||||
assert srv._verb_absolute_attempt_count("i_am_done", "task-A") == done_count
|
||||
assert srv._verb_absolute_attempt_count("submit_up", "task-A") == submit_count
|
||||
|
||||
|
||||
def test_absolute_counter_never_prunes_with_time() -> None:
|
||||
"""Unlike the windowed deque, a huge time jump does not reset the count."""
|
||||
base = 1000.0
|
||||
expected = 2
|
||||
with patch("roboco.agent_sdk.server.time.monotonic") as mock_time:
|
||||
mock_time.return_value = base
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
mock_time.return_value = base + 10_000.0 # far past any sliding window
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
assert srv._verb_absolute_attempt_count("i_am_done", "task-A") == expected
|
||||
|
||||
|
||||
def test_slow_drip_never_trips_window_but_trips_absolute_cap() -> None:
|
||||
"""Rejections spaced > 60s apart never trip `_check_verb_circuit`, but
|
||||
the absolute cap still trips once the cumulative count reaches it —
|
||||
the exact production scenario this breaker was added to close.
|
||||
"""
|
||||
cap = absolute_retry_limit_for("i_am_done")
|
||||
assert cap is not None
|
||||
base = 1000.0
|
||||
with patch("roboco.agent_sdk.server.time.monotonic") as mock_time:
|
||||
for i in range(cap):
|
||||
mock_time.return_value = base + i * 200.0 # always > 60s apart
|
||||
srv._record_verb_attempt("i_am_done", "task-A")
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
# The sliding window is always empty when this attempt lands.
|
||||
assert srv._check_verb_circuit("i_am_done", "task-A") is None
|
||||
|
||||
result = srv._check_verb_absolute_circuit("i_am_done", "task-A")
|
||||
assert result is not None
|
||||
assert result["error"] == "circuit_open"
|
||||
assert "absolute cap" in result["message"]
|
||||
assert "i_am_blocked" in result["remediate"]
|
||||
|
||||
|
||||
def test_absolute_check_returns_none_below_cap() -> None:
|
||||
"""One rejection short of the cap, the absolute breaker stays closed."""
|
||||
cap = absolute_retry_limit_for("i_am_done")
|
||||
assert cap is not None
|
||||
for _ in range(cap - 1):
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
assert srv._check_verb_absolute_circuit("i_am_done", "task-A") is None
|
||||
|
||||
|
||||
def test_absolute_check_returns_none_for_unlimited_retry_verbs() -> None:
|
||||
"""give_me_work stays exempt from the absolute cap too."""
|
||||
assert absolute_retry_limit_for("give_me_work") is None
|
||||
for _ in range(50):
|
||||
srv._record_verb_attempt_absolute("give_me_work", None)
|
||||
assert srv._check_verb_absolute_circuit("give_me_work", None) is None
|
||||
|
||||
|
||||
def test_combined_check_still_trips_fast_storm_via_window() -> None:
|
||||
"""Windowed behavior is unchanged: 3 fast rejections (the existing
|
||||
i_am_done cap) still trip via the combined check, well below the
|
||||
absolute cap of 9 — and the message reads as a windowed trip, not a
|
||||
session one.
|
||||
"""
|
||||
limit = retry_limit_for("i_am_done")
|
||||
assert limit is not None
|
||||
for _ in range(limit):
|
||||
srv._record_verb_attempt("i_am_done", "task-A")
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
|
||||
result = srv._check_any_verb_circuit("i_am_done", "task-A")
|
||||
assert result is not None
|
||||
assert result["error"] == "circuit_open"
|
||||
assert "this session" not in result["message"]
|
||||
assert "in last" in result["message"]
|
||||
|
||||
|
||||
def test_verb_attempted_endpoint_trips_absolute_cap_on_slow_drip() -> None:
|
||||
"""End-to-end repro through the real /verb/attempted endpoint: rejections
|
||||
paced far past 60s apart never open the windowed breaker but do open the
|
||||
absolute one once the cumulative count reaches the cap.
|
||||
"""
|
||||
client = TestClient(srv.app)
|
||||
cap = absolute_retry_limit_for("i_am_done")
|
||||
assert cap is not None
|
||||
last_body: dict[str, object] | None = None
|
||||
with patch("roboco.agent_sdk.server.time.monotonic") as mock_time:
|
||||
for i in range(cap):
|
||||
mock_time.return_value = 1000.0 + i * 200.0
|
||||
resp = client.post(
|
||||
"/verb/attempted",
|
||||
json={
|
||||
"verb": "i_am_done",
|
||||
"task_id": "task-A",
|
||||
"rejection_kind": "tracing_gap",
|
||||
},
|
||||
)
|
||||
assert resp.status_code == _OK
|
||||
last_body = resp.json()
|
||||
if i < cap - 1:
|
||||
assert last_body["open"] is False
|
||||
|
||||
assert last_body is not None
|
||||
assert last_body["open"] is True
|
||||
env = last_body["circuit_envelope"]
|
||||
assert isinstance(env, dict)
|
||||
assert env["error"] == "circuit_open"
|
||||
assert "absolute cap" in env["message"]
|
||||
|
||||
|
||||
def test_state_reset_clears_verb_absolute_attempts() -> None:
|
||||
"""_state.reset() (a fresh container spawn) wipes the absolute tracker too."""
|
||||
expected = 3
|
||||
for _ in range(expected):
|
||||
srv._record_verb_attempt_absolute("i_am_done", "task-A")
|
||||
assert srv._verb_absolute_attempt_count("i_am_done", "task-A") == expected
|
||||
|
||||
srv._state.reset()
|
||||
assert srv._verb_absolute_attempt_count("i_am_done", "task-A") == 0
|
||||
|
||||
|
||||
def test_verb_absolute_attempts_default_is_zero() -> None:
|
||||
"""defaultdict yields 0 for unseen keys — sanity check."""
|
||||
fresh = srv._SessionState()
|
||||
assert fresh.verb_absolute_attempts[("never_seen", None)] == 0
|
||||
|
||||
Reference in New Issue
Block a user