mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* feat(gateway): claim-scoped context briefing — heavy sections only on context-acquisition verbs
* feat(gateway): cap unbounded LLM-facing payloads — embedded diffs, notification bodies, handoff journal content, north star
* feat(mcp): role-scope the optimal server's tool groups; index management becomes dev/test-only
* feat(mcp): cap per-result content on kb/error/learning search, mentor sources, rag citations
* refactor(gateway): extract heavy-briefing sections + clip helper to keep xenon ranks
* feat(orchestrator): cross-tick cooldown for notification-triggered spawns
* feat(usage,orchestrator): scope spawn-waste to anthropic sessions; cap agent Bash output via settings env
* docs: claim-scoped briefing, payload caps, optimal role-scoping, notification-spawn cooldown
* test(mcp): type the mixed-item cap fixture explicitly
* fix(orchestrator): lazy-init the notification-spawn cooldown store
* fix(lifecycle): admin-override claim reconciliation + PM request_changes verb (S6 postmortem B3+B4)
B3 — admin_set_status now reconciles claim ownership when leaving BLOCKED:
review/queue targets clear claimed_by/claimed_at/active_claimant_id and
consume the pre-block snapshot (a stale escalation claim was stranding the
next claimant: give_me_work handed the task out while note() bounced
not_authorized — the live b8fe0494 wedge). The pending/in_progress restore
path also syncs active_claimant_id, and a REST PATCH unassign releases the
claim with it.
B4 — new PM verb request_changes: awaiting_pm_review -> needs_revision with
concrete issues. The PM previously had no reject at merge review (only
complete/escalate), so an AC/scope violation looped i_am_blocked->escalate
4x live. Full vertical: lifecycle transition + ActionSpec + IntentSpec,
TaskService.request_changes (routes like a QA fail — original dev for a
leaf, revision PM for assembled; issues appended to dev_notes), verb-runner
compose, choreographer verb (spec gate + non-empty issues + soup check +
a2a delivery of the reject reason), HTTP routes on both PM flows, MCP tool,
journal:decision tracing, PM prompts, regenerated lifecycle artifacts.
* fix(panel): stop scorecard fetches for fallback-roster placeholder ids
useAgents() serves the static AGENT_ROSTER (ids "1".."22") while agent
definitions load; the Scorecards tab fetched a member scorecard per row
immediately, firing 22 guaranteed-422 requests per refetch cycle. Through
the browser's per-origin connection limit those queued every metrics-page
query behind them (~10s of skeletons on every tab). Gate the fetch on a
real member id (agent UUID or the "ceo" alias).
* Upgraded uv.lock
* fix(sequencing): declared deps become real edges + full loop-breaker coverage + assembled-branch freshness (S6 postmortem B1/B2/B6 + breaker)
B1a — code delegations REQUIRE a collision surface: new TASK_AT_DELEGATE
completeness spec (conditional FieldRequirement, when=('task_type','code'))
enforced at the gateway delegate gate. A no-surface code sibling is
'parallel to everything' by analyzer design, which is how two devs ran the
CEO's explicitly-ordered work out of order (f3e1afc5: seq#1 started before
seq#0, zero dependency edges). PM prompts updated; REST/manual creation
(TASK_AT_CREATE) unchanged.
B1b — the CEO's declared 'Depends on' lists become real edges: DraftSurface
gains declared_depends_on; SequencingService.analyze unions declared edges
(validated: self/out-of-range rejected) with the derived collision rules,
cycle-checked by the existing toposort. confirm_live_batch/preview_batch
map each draft's depends_on through (string indices coerced); intake tool
doc + prompter role prompt instruct verbatim copying. The live S6 root got
1 of its 3 declared in-batch edges and started alongside still-running R3.
Breaker coverage — the progress-aware respawn circuit breaker
(_pm_respawn_should_gate: strike counting, status-advance reset,
tracing-gap budget, DB durability, one-shot CEO notification) was consulted
by only 3 spawn paths; the doc/QA/dev/PR-review/PR-gate/revision/board
paths spawned unguarded at fixed cadence (the 26-respawn fe-doc loop,
~$7.20). Now consulted at every task-keyed spawn site (14 total).
B2 — assembled-branch freshness: submit_up/submit_root auto-sync the
assembled branch when it has fallen behind its base (children are terminal
at submit time, so the rebase is safe; master is never written). A rebase
conflict is a hard reject naming the files instead of a blind re-review —
kills the needs_revision↔awaiting_pr_review ping-pong of re-submitting a
stale head. Leaf i_am_done already had the behind-base gate; claim-time
fetch-fresh cut already existed.
B6 — documenter revision-pass loop: the awaiting_documentation bail
rejections (i_am_blocked/unclaim) now name the actual exit (i_documented
re-affirm) and the documenter prompt gets an explicit revision-pass rule.
* fix(orchestration): assembly-integrity gate + dispatcher heartbeat (incidents #11, #1)
Assembly integrity — submit_up/submit_root refuse when a completed child's
commits are not patch-present in the assembled branch (git cherry —
rebase-safe; branch pruned after merge or any git error fails open). Live
incident #11: a completed revert subtask's merge was lost from the cell
branch and the review gate re-flagged the exact violation the revert fixed,
spawning another revision cycle.
Dispatcher heartbeat — a dispatcher.alive audit row every 5 minutes from
the dispatch loop. The 2026-07-01 outage was 4h25m of fleet-wide silence
with no way to distinguish 'loop dead' from 'no work'; the loop's stdout
died with the container while audit_log survives. CHANGELOG for tonight's
full sweep included.
* style: ruff format for the orchestration sweep
* refactor(gateway): fold the assembled-submit guards + trim complexity under the xenon gate
_assembled_submit_guards combines the #11 integrity check and B2 freshen for
submit_up/submit_root; lifecycle's invalid-source remediate and git's
per-child cherry probe extracted into helpers. Test harnesses built via
__new__ stub the respawn tracker (the breaker now runs on their paths).
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
109 lines
3.8 KiB
Python
109 lines
3.8 KiB
Python
"""The respawn circuit breaker guards EVERY task-keyed spawn path.
|
|
|
|
Live break (2026-07-02, b8fe0494): fe-doc respawned 26 times in ~100 min
|
|
(~$7.20) on an awaiting_documentation task with no valid verb — because
|
|
``_pm_respawn_should_gate`` (progress-aware strikes, DB-durable, one-shot CEO
|
|
notification) was consulted by only 3 of the ~10 task-keyed dispatch paths.
|
|
The doc/QA/PR-gate/dev paths spawned unguarded at fixed cadence.
|
|
|
|
These tests pin the gate consultation on the previously-unguarded helpers:
|
|
gate says skip → no spawn; gate says go → spawn proceeds.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any, cast
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.runtime.orchestrator import AgentOrchestrator
|
|
|
|
|
|
def _orch(gate_result: bool) -> AgentOrchestrator:
|
|
"""Orchestrator via __new__ with the gate + spawn stubbed."""
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
o = cast("Any", orch)
|
|
o._pm_respawn_should_gate = AsyncMock(return_value=gate_result)
|
|
o.spawn_agent = AsyncMock()
|
|
o._resolve_agent_slug = lambda x: x
|
|
o._is_agent_active = lambda _slug: False
|
|
o._task_git_context = lambda _t: None
|
|
o._build_doc_prompt = lambda _t: "doc prompt"
|
|
o._build_qa_prompt = lambda _t: "qa prompt"
|
|
o._build_pr_gate_prompt = lambda _t: "gate prompt"
|
|
o._select_agent_for_cell = lambda _team, _role: "fe-pr-reviewer"
|
|
o._is_task_handled_this_tick = lambda _tid: False
|
|
return orch
|
|
|
|
|
|
def _task(**overrides: Any) -> dict[str, Any]:
|
|
base: dict[str, Any] = {
|
|
"id": str(uuid4()),
|
|
"status": "awaiting_documentation",
|
|
"team": "frontend",
|
|
"assigned_to": "fe-doc",
|
|
}
|
|
base.update(overrides)
|
|
return base
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_doc_respawn_consults_gate_and_skips_when_tripped() -> None:
|
|
# The exact fe-doc loop path: assigned documenter, inactive, respawned
|
|
# every tick. With the gate tripped, the spawn must be skipped.
|
|
orch = _orch(gate_result=True)
|
|
handled = await orch._respawn_doc_if_assigned(_task())
|
|
assert handled is True # task stays handled (no auto-assign fallthrough)
|
|
cast("Any", orch).spawn_agent.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_doc_respawn_spawns_when_gate_clear() -> None:
|
|
orch = _orch(gate_result=False)
|
|
handled = await orch._respawn_doc_if_assigned(_task())
|
|
assert handled is True
|
|
cast("Any", orch).spawn_agent.assert_awaited_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_assigned_qa_consults_gate_and_skips_when_tripped() -> None:
|
|
orch = _orch(gate_result=True)
|
|
handled = await orch._spawn_assigned_qa(
|
|
_task(status="awaiting_qa"), assigned_to="fe-qa"
|
|
)
|
|
assert handled is True
|
|
cast("Any", orch).spawn_agent.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_assigned_qa_spawns_when_gate_clear() -> None:
|
|
orch = _orch(gate_result=False)
|
|
handled = await orch._spawn_assigned_qa(
|
|
_task(status="awaiting_qa"), assigned_to="fe-qa"
|
|
)
|
|
assert handled is True
|
|
cast("Any", orch).spawn_agent.assert_awaited_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_pr_gate_dispatch_consults_gate_and_skips_when_tripped() -> None:
|
|
orch = _orch(gate_result=True)
|
|
o = cast("Any", orch)
|
|
o._fetch_tasks = AsyncMock(
|
|
return_value=[_task(status="awaiting_pr_review", team="frontend")]
|
|
)
|
|
await orch._dispatch_pr_gate_work(MagicMock())
|
|
o.spawn_agent.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_pr_gate_dispatch_spawns_when_gate_clear() -> None:
|
|
orch = _orch(gate_result=False)
|
|
o = cast("Any", orch)
|
|
o._fetch_tasks = AsyncMock(
|
|
return_value=[_task(status="awaiting_pr_review", team="frontend")]
|
|
)
|
|
await orch._dispatch_pr_gate_work(MagicMock())
|
|
o.spawn_agent.assert_awaited_once()
|