mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* feat(metrics): capture per-session turns + tool_calls (phase 1)
Persist LLM iterations (turns) and tool invocations per agent spawn session,
the raw signal the granular per-member performance metrics build on (real
effort/iterations vs wall-clock).
- sum_transcript_usage returns a 5-tuple adding turns = unique assistant
message-id count; _usage_from_transcript + _resolve_active_tokens updated to
the 5-tuple (active-tokens keeps its 4-tuple contract by slicing).
- SDK: _SessionState.turns, set by /usage/sync; /usage/status (TokenUsageStatus)
now carries turns + tool_calls (= total_calls).
- orchestrator: new _resolve_final_turns_tools (SDK primary, transcript fallback
for turns only; Grok -> 0/0) wired into _finalize_spawn_session, which writes
turns + tool_calls to agent_spawn_sessions.
- migration 055 adds turns + tool_calls (BigInteger DEFAULT 0 -> historical/Grok
rows read 0, surfaced as n/a). Verified real alembic upgrade/downgrade.
Part of metrics-granularity (v0.15.0); recon-adjusted plan on disk.
* feat(metrics): pure compute_stage_effort helper (phase 2, part 1)
Foundation-layer overlap math (no DB): split each task status window into
active (merged wall-clock overlap of spawn stints — concurrent stints counted
once, so active <= window) vs wait (queue/review idle). Distinct from summed
effort. The per-task metrics service will feed it audit-log windows + spawn
stints. 9 unit tests (disjoint/nested/partial/merged/clamped/zero/multi-window).
* feat(metrics): per-task live metrics + GET /metrics/task/{id} (phase 2)
TaskMetrics dataclass + MetricsService.get_task_metrics: summed spawn effort
(vs wall-clock), turns/tool_calls/tokens/cost, per-stage active-vs-wait
(compute_stage_effort over audit windows x spawn stints), and who-caused-rework
(revision_count + named qa/pr fail events). Open stints and the open final
stage window close at completed_at for a terminal task (else now), so stages
don't grow past completion. Exposed at GET /dashboard/metrics/task/{task_id}
(404 if absent). Real-PG tests (compose/none/in-flight) + route tests (200/404).
* feat(metrics): CEO-as-member scorecard + ceo_reject audit regression (phase 3)
The human CEO is a measured member, read purely from audit_log (agent_role='ceo'
serializes from the CEO StrEnum): approval dwell (awaiting_ceo_approval -> a CEO
decision, incl. the coordination-root reject that lands in pending), unblock
dwell (blocked -> a CEO revive), and god-mode action count (every CEO-attributed
transition). CeoScorecard + MetricsService.get_ceo_scorecard (p50/p90 via
PERCENTILE_CONT, expanding IN for the decision sets) + GET
/dashboard/metrics/member/ceo (declared before any future member/{id} route).
The ceo_reject coordination-root audit gap the plan meant to close was already
closed by the gap-sweep (routes through admin_set_status -> agent_role='ceo'
audit); locked with a regression assertion in the existing coordination-reject
test. Real-PG tests: approval/unblock/godmode, non-ceo exclusion, empty->zeros.
* feat(metrics): audit instrumentation for escalations/blocked-others/idle (phase 4a)
The three extra per-member metrics that had no data source get durable,
in-session audit events (additive; never gate the underlying action):
- apply_escalation -> task.escalated (details.escalator_slug) on both the
normal block path and the pool-divert path -> escalations count.
- _unblock_dependents -> task.unblocked_dependents (details.count) on the
completed BLOCKER task, captured before the dependency edges are pruned ->
blocked-others count (sweeper attributes to the blocker's owner).
- mark_agent_idle -> agent.idle (details.agent_slug) -> idle/utilization (the
sweeper pairs an idle mark to the member's next spawn for idle duration).
(QA pass-rate needs no new event — reuses task.awaiting_documentation[qa] +
task.qa_fail.) Real-PG tests for each; 111 transition tests still green.
* feat(metrics): member_performance_daily rollup table + migration 056 (phase 4b)
The per-member scorecard rollup: one row per (date, member_kind, agent_slug),
CEO as a first-class member_kind='ceo' row (agent_slug='' NOT NULL so the
NULL-distinct UNIQUE keeps it unique). Full column set + the four CEO-approved
extras (qa_reviews_total/passed, escalations, blocked_others, idle_seconds) plus
blocked_seconds. Overwrite-upsert on (date, member_kind, agent_slug) for an
idempotent sweep. Migration 056 verified real up/down (24 cols, 4 indexes).
* feat(metrics): _sweep_member_performance rollup sweeper (phase 4c)
The daily per-member rollup sweep (mirrors _sweep_daily_rollup): a trailing
7-day, idempotent overwrite-upsert wired into _run_sweep. One focused query per
metric merges into a (date, agent_slug) accumulator — spawn effort/turns/tokens/
cost, completed/first-pass/revisions-received, revisions-caused (qa/pr fails),
QA pass-rate (passed + total), escalations (by escalator_slug), blocked-others
(unblocked_dependents by blocker owner), idle_seconds (idle mark -> next spawn),
blocked_seconds (blocked dwell) — plus one CEO row/day (approval/unblock dwell +
god-mode). Real-PG test asserts every facet + idempotency (a 2nd sweep
overwrites, never doubles); spawn-day != completion-day split is by-design.
* feat(metrics): member/org rollup scorecards + endpoints + live overlay (phase 5)
MemberScorecard + OrgScorecard with derived rates (FPY, effort-throughput,
turns/tool-calls per task, QA pass-rate, utilization) — all division-guarded to
None. get_member_scorecard reads member_performance_daily by slug and overlays
the member's live in-flight (non-terminal) tasks' effort via get_task_metrics
(disjoint by status: completion counts stay rollup-only, overlay only enriches
effort/turns/cost; includes_live_inflight flags it). get_org_scorecard
aggregates the cell (?team=) or whole org. Routes: GET /metrics/member/{agent_id}
(404 if absent, after the ceo literal route) + GET /metrics/org?team=. Real-PG
tests (derived rates, overlay no double-count, guards, org) + route tests.
* feat(metrics): granular CEO completion notification (phase 6)
There was no CEO completion notification at all (EventType.TASK_COMPLETED was
defined but never emitted). Add notify_ceo_of_completion in
NotificationDeliveryService — a granular body (real effort vs wall-clock +
stints/turns/tool-calls/revisions[QA/PR]/cost from get_task_metrics; degrades to
wall-clock-only, turns 'n/a', when there are no spawn sessions). Reuses the
existing ALERT type (no enum migration; the notificationtype PG enum is fixed at
001). ceo_approve now emits TASK_COMPLETED + fires the notification (best-effort
via _notify_completion — never blocks completion); complete() emits
TASK_COMPLETED too (closes the dead-code gap; the WS bridge can forward it).
Pure formatter tests + real-PG notification test.
* [metrics-granularity] Phase 7: panel Scorecards tab + dashboard overview
Add the CEO-facing metrics surfaces for the granularity feature:
- New "Scorecards" tab on the Metrics page: org rollup headline, the
CEO-as-member card (approval/unblock dwell + god-mode count), and a
per-member table (completed, first-pass yield, active effort, turns/task,
QA pass-rate, escalations, blocked-others, utilization). Each member row
self-fetches its rollup scorecard; live in-flight rows carry a "live" badge.
- New dashboard overview card (ScorecardOverviewPanel): org-wide 30-day
headline (completed, FPY, throughput/hr, active effort, cost) deep-linking
into the Scorecards tab.
- Plumbing: TaskMetrics/MemberScorecard/OrgScorecard/CeoScorecard types,
observability API client methods + empty fallbacks, and the four
useCeoScorecard/useMemberScorecard/useOrgScorecard/useTaskMetrics hooks.
Panel gate green: tsc, eslint, prettier, vitest (175 tests, +6 new).
* [metrics-granularity] test: make completion-notification robust to shared-DB CEO
test_notify_ceo_of_completion_creates_alert errored in the full suite (passed
in isolation): the session-scoped test DB is shared across the run, and the
sibling real-DB board-gate test commits a role=CEO agent (slug="ceo") without
cleanup — so my env fixture's hardcoded slug="ceo" insert hit a unique-constraint
violation, and a second role=CEO row would also make _get_ceo_agent()'s
scalar_one_or_none() raise. Reuse an existing CEO when present (the singleton the
production system actually has), else create one with a unique slug. Order-
independent. Also reflow test_metrics_instrumentation.py to ruff format.
* chore(release): 0.15.0
Metrics granularity: per-member/per-task/org + CEO-as-member scorecards,
turn/tool-call capture (migration 055), member_performance_daily rollup
(migration 056) with QA pass-rate / escalations / blocked-others / utilization,
per-task active-vs-wait metrics, granular completion notification, panel
Scorecards tab + dashboard Performance card, and the ceo_reject audit fix.
Version bump across the canonical set + CHANGELOG.
* [metrics-granularity] fix pre-tag audit findings (overlay double-count + panel error states)
Adversarial review before the v0.15.0 tag surfaced two real logical gaps:
- MAJOR (backend): the live in-flight overlay re-summed ALL sessions of every
non-terminal task via get_task_metrics, but _msweep_spawn already rolls up
every CLOSED session regardless of task status — so a closed session on a
still-open task was counted twice (rollup + overlay), permanently inflating a
member's effort/turns/tokens/cost on the common reap/respawn path. The overlay
now sums only OPEN sessions (ended_at IS NULL), which the closed-only rollup
can never contain — disjoint by construction. A just-closed session lands in
the rollup on the next ~60s sweep (no gap of note). Aggregated in SQL to mirror
_msweep_spawn. Regression test reproduces the double-count (turns 10→5).
- MAJOR (panel): the four new scorecard surfaces used `isLoading || !data` with
no isError branch, so a failed query span forever on a skeleton. They now
surface a load error. Tests added.
Also: OrgSummary active-effort formatting no longer round-trips hours→seconds→
hours; dashboard grid uses xl:grid-cols-4 (was 2xl) so 4 panels show at 1280px;
corrected the inaccurate "NULL distinct" CEO-row uniqueness comment (agent_slug
is NOT NULL; the '' tuple is simply distinct from agent rows).
make quality GREEN (cov 95.31%); panel GREEN (vitest 178).
* [metrics-granularity] fix: decode bytes stream message-id before XCLAIM
StreamEventBus._recover_stream passed the pending message id to XCLAIM via
str() on the raw bytes the client returns (redis client has no
decode_responses), producing "b'1782066556728-0'". Redis rejects that with
"Unrecognized XCLAIM option", so pending-message recovery threw on every
reclaim tick and unacked messages from crashed/slow consumers were never
reclaimed (leaking in the PEL on every stream, spamming the error log). Decode
via the existing _to_str helper — the fix the sibling claim path already uses.
Pre-existing in v0.14.0 (unrelated to metrics granularity); folded into this
release per CEO. TDD regression test + CHANGELOG entry. make quality GREEN.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
245 lines
6.9 KiB
Python
245 lines
6.9 KiB
Python
"""get_task_metrics — granular per-task effort against a real Postgres.
|
|
|
|
Seeds a task's audit-log journey + agent spawn stints (with turns/tool_calls/
|
|
tokens/cost) + named qa/pr fail events, then asserts the composed metrics:
|
|
summed effort vs wall-clock, turns/tool_calls/tokens/cost, per-stage
|
|
active-vs-wait, and who-caused-rework.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime, timedelta
|
|
from typing import TYPE_CHECKING, Any, NamedTuple
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
import pytest_asyncio
|
|
from roboco.db.tables import (
|
|
AgentSpawnSessionTable,
|
|
AgentTable,
|
|
AuditLogTable,
|
|
ProjectTable,
|
|
TaskTable,
|
|
)
|
|
from roboco.models.base import (
|
|
AgentRole,
|
|
AgentStatus,
|
|
Complexity,
|
|
TaskNature,
|
|
TaskStatus,
|
|
TaskType,
|
|
Team,
|
|
)
|
|
from roboco.services.metrics import MetricsService
|
|
|
|
if TYPE_CHECKING:
|
|
from collections.abc import AsyncIterator
|
|
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
_T0 = datetime(2026, 6, 20, 12, 0, 0, tzinfo=UTC)
|
|
|
|
|
|
def _sec(n: int) -> datetime:
|
|
return _T0 + timedelta(seconds=n)
|
|
|
|
|
|
def _agent(role: AgentRole, slug: str) -> AgentTable:
|
|
return AgentTable(
|
|
id=uuid4(),
|
|
name=slug,
|
|
slug=slug,
|
|
role=role,
|
|
team=Team.BACKEND,
|
|
status=AgentStatus.ACTIVE,
|
|
model_config={},
|
|
system_prompt="x",
|
|
capabilities=[],
|
|
permissions={},
|
|
metrics={},
|
|
)
|
|
|
|
|
|
def _audit(
|
|
task_id: Any,
|
|
status: str,
|
|
ts: datetime,
|
|
*,
|
|
agent_id: Any = None,
|
|
event_type: str | None = None,
|
|
) -> AuditLogTable:
|
|
return AuditLogTable(
|
|
id=uuid4(),
|
|
event_type=event_type or f"task.{status}",
|
|
agent_id=agent_id,
|
|
target_type="task",
|
|
target_id=task_id,
|
|
severity="info",
|
|
details={"to_status": status, "from_status": "prev", "team": "backend"},
|
|
timestamp=ts,
|
|
)
|
|
|
|
|
|
class _Usage(NamedTuple):
|
|
turns: int
|
|
tool_calls: int
|
|
tokens_in: int
|
|
tokens_out: int
|
|
cost: float
|
|
|
|
|
|
def _spawn(
|
|
task_id: str,
|
|
started: datetime,
|
|
ended: datetime | None,
|
|
usage: _Usage,
|
|
) -> AgentSpawnSessionTable:
|
|
return AgentSpawnSessionTable(
|
|
id=uuid4(),
|
|
agent_slug="be-dev-1",
|
|
team="backend",
|
|
role="developer",
|
|
model="claude",
|
|
task_id=task_id,
|
|
started_at=started,
|
|
ended_at=ended,
|
|
turns=usage.turns,
|
|
tool_calls=usage.tool_calls,
|
|
tokens_input=usage.tokens_in,
|
|
tokens_output=usage.tokens_out,
|
|
estimated_cost_usd=usage.cost,
|
|
)
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
async def setup(db_session: AsyncSession) -> AsyncIterator[dict]:
|
|
dev = _agent(AgentRole.DEVELOPER, f"be-dev-{uuid4().hex[:6]}")
|
|
qa = _agent(AgentRole.QA, f"be-qa-{uuid4().hex[:6]}")
|
|
db_session.add_all([dev, qa])
|
|
await db_session.flush()
|
|
project = ProjectTable(
|
|
id=uuid4(),
|
|
name="P",
|
|
slug=f"p-{uuid4().hex[:6]}",
|
|
git_url="https://example.com/r.git",
|
|
assigned_cell=Team.BACKEND,
|
|
created_by=dev.id,
|
|
)
|
|
db_session.add(project)
|
|
await db_session.flush()
|
|
yield {
|
|
"svc": MetricsService(db_session),
|
|
"db": db_session,
|
|
"project_id": project.id,
|
|
"dev_id": dev.id,
|
|
"qa_id": qa.id,
|
|
}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_returns_none_for_missing_task(setup: dict) -> None:
|
|
assert await setup["svc"].get_task_metrics(uuid4()) is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_composes_effort_turns_stages_and_rework(setup: dict) -> None:
|
|
db = setup["db"]
|
|
tid = uuid4()
|
|
db.add(
|
|
TaskTable(
|
|
id=tid,
|
|
title="t",
|
|
description="d",
|
|
acceptance_criteria=["ac"],
|
|
task_type=TaskType.CODE,
|
|
nature=TaskNature.TECHNICAL,
|
|
status=TaskStatus.COMPLETED,
|
|
team=Team.BACKEND,
|
|
project_id=setup["project_id"],
|
|
created_by=setup["dev_id"],
|
|
assigned_to=setup["dev_id"],
|
|
revision_count=2,
|
|
estimated_complexity=Complexity.MEDIUM,
|
|
started_at=_T0,
|
|
completed_at=_sec(7200),
|
|
)
|
|
)
|
|
db.add_all(
|
|
[
|
|
_audit(tid, "claimed", _T0),
|
|
_audit(tid, "in_progress", _sec(60)),
|
|
_audit(tid, "awaiting_qa", _sec(3660)),
|
|
_audit(tid, "completed", _sec(7200)),
|
|
_audit(tid, "needs_revision", _sec(3660), event_type="task.qa_fail"),
|
|
_audit(tid, "needs_revision", _sec(3000), event_type="task.pr_fail"),
|
|
]
|
|
)
|
|
db.add_all(
|
|
[
|
|
_spawn(str(tid), _T0, _sec(600), _Usage(5, 10, 100, 50, 1.0)),
|
|
_spawn(str(tid), _sec(3600), _sec(3660), _Usage(3, 4, 20, 10, 0.5)),
|
|
]
|
|
)
|
|
await db.flush()
|
|
|
|
m = await setup["svc"].get_task_metrics(tid)
|
|
assert m is not None
|
|
# summed effort (600 + 60) vs wall-clock (2h).
|
|
expected_active_s = 660
|
|
expected_wall_s = 7200
|
|
assert m.active_runtime_seconds == expected_active_s
|
|
assert m.wall_clock_seconds == expected_wall_s
|
|
assert (m.turns, m.tool_calls, m.tokens) == (8, 14, 180)
|
|
assert m.cost_usd == pytest.approx(1.5)
|
|
assert (m.revision_count, m.qa_fails, m.pr_fails, m.stints) == (2, 1, 1, 2)
|
|
|
|
stages = {s.status: s for s in m.stages}
|
|
# claimed [0,60): stint1 covers it fully.
|
|
assert (stages["claimed"].active_seconds, stages["claimed"].wait_seconds) == (60, 0)
|
|
# in_progress [60,3660): stint1 60..600 (540) + stint2 3600..3660 (60) = 600 active.
|
|
assert (
|
|
stages["in_progress"].active_seconds,
|
|
stages["in_progress"].wait_seconds,
|
|
) == (600, 3000)
|
|
# awaiting_qa [3660,7200): no stint running -> all wait.
|
|
assert (
|
|
stages["awaiting_qa"].active_seconds,
|
|
stages["awaiting_qa"].wait_seconds,
|
|
) == (0, 3540)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_in_flight_open_stint_and_open_window_decompose(setup: dict) -> None:
|
|
db = setup["db"]
|
|
tid = uuid4()
|
|
db.add(
|
|
TaskTable(
|
|
id=tid,
|
|
title="t",
|
|
description="d",
|
|
acceptance_criteria=["ac"],
|
|
task_type=TaskType.CODE,
|
|
nature=TaskNature.TECHNICAL,
|
|
status=TaskStatus.IN_PROGRESS,
|
|
team=Team.BACKEND,
|
|
project_id=setup["project_id"],
|
|
created_by=setup["dev_id"],
|
|
assigned_to=setup["dev_id"],
|
|
estimated_complexity=Complexity.MEDIUM,
|
|
started_at=_T0,
|
|
completed_at=None,
|
|
)
|
|
)
|
|
db.add_all([_audit(tid, "claimed", _T0), _audit(tid, "in_progress", _sec(60))])
|
|
# An OPEN stint (ended_at=None) -> runs to now.
|
|
db.add(_spawn(str(tid), _T0, None, _Usage(2, 3, 1, 1, 0.1)))
|
|
await db.flush()
|
|
|
|
m = await setup["svc"].get_task_metrics(tid)
|
|
assert m is not None
|
|
assert m.stints == 1
|
|
assert m.active_runtime_seconds > 0 # open stint ran to now
|
|
assert m.wall_clock_seconds > 0 # open task -> now
|
|
# The open final window (in_progress) still decomposes.
|
|
assert "in_progress" in {s.status for s in m.stages}
|