Surfaced by today's untracked-files audit. None of these are accidents —
multiple are referenced by name in CLAUDE.md and memory files but were
never added.
Categories:
- docs/PHASE_AUDIT_GUIDE.md (106 LOC) — Claude Code phase audit guidance
- ops/systemd/lakehouse-langfuse-bridge.service — Langfuse bridge unit
- package.json — top-level npm manifest
- scripts/e2e_pipeline_check.sh + production_smoke.sh — real test scripts
- reports/kimi/audit-last-week*.md — the "Two reports live" CLAUDE.md cites
- tests/multi-agent/scenarios/ — 44 staffing scenarios (cutover decision A)
- tests/multi-agent/playbooks/ — 102 playbook records
- tests/battery/, tests/agent_test/PRD.md, tests/real-world/* — real tests
- sidecar/sidecar/{lab_ui,pipeline_lab}.py — 888 LOC dev-only UIs that
remain in service post-sidecar-drop (commit ba928b1 explicitly kept them)
Sensitivity check: scenarios use synthetic company names ("Heritage Foods",
"Cornerstone Fabrication"); audit reports describe code findings only;
no PII or secrets surfaced.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Staffer.tool_level now controls which subsystems a specific run gets:
full — qwen3.5 + qwen3 + cloud T3 + cloud rescue
local — qwen3.5 + qwen3 + local gpt-oss:20b T3 + rescue
basic — qwen2.5 + qwen2.5 + local T3, no rescue
minimal — qwen2.5 + qwen2.5, NO T3, NO rescue. Playbook
inheritance only.
applyToolLevel() mutates module-scoped ACTIVE_* slots each run from the
env defaults, so prior staffer's overrides never leak. Hot-path code
reads ACTIVE_EXECUTOR / ACTIVE_REVIEWER / ACTIVE_T3_DISABLED /
ACTIVE_OVERVIEW_CLOUD / ACTIVE_RETRY_ON_FAIL instead of the baked
constants.
The architectural question this answers: does playbook_memory
inheritance carry enough knowledge to let a weakly-tooled coordinator
still produce usable outcomes? "Minimal" Alex runs qwen2.5 exec + no
reviewer overseer + no cloud rescue. If Alex still fills events at a
reasonable rate, the playbook system is the real knowledge carrier —
the senior stack is nice-to-have, not the sine qua non.
Demo personas mapped:
Maria (senior, 48mo, full)
James (mid, 14mo, local)
Sam (junior, 4mo, basic)
Alex (trainee, 1mo, minimal)
Same 3 contracts (Nashville downtown, Joliet warehouse, Indianapolis
assembly) across all four → 12 runs. KB + kb_staffer_report.py
leaderboard already wired; competence_score will now reflect real tool
asymmetry instead of LLM sampling variance.
Matrix-index the "who handled this" dimension so top staffers become
the training signal and juniors inherit their playbooks automatically
via the boost pipeline. Auto-discovered indicators emerge from
comparing trajectories across staffers on similar contracts — that was
always the architectural point; this wires the last piece.
ContractTerms:
- deadline, budget_total_usd, budget_per_hour_max, local_bonus_per_hour,
local_bonus_radius_mi, fill_requirement ("paramount" | "preferred")
- Attached to ScenarioSpec, propagated into T3 checkpoint + cloud
rescue prompts so cloud reasons about trade-offs (pivot within bonus
radius first; respect per-hour cap; split across cities when
fill_requirement=paramount).
Staffer:
- {id, name, tenure_months, role: senior|mid|junior|trainee}
- On ScenarioSpec; logged at scenario start; attached to KB outcome
- Recomputed StafferStats written to data/_kb/staffers.jsonl after
every run: total_runs, fill_rate, avg_turns, avg_citations,
rescue_rate, competence_score.
- Competence formula: 0.45*fill_rate + 0.20*turn_efficiency +
0.20*citation_density + 0.15*rescue_rate. Normalized to 0..1.
findNeighbors now returns weighted_score = cosine × best_staffer_competence
(floored at 0.3 so high-similarity low-competence neighbors still
surface). pathway_recommender prompt shows the top staffer's identity
so cloud knows WHOSE playbook it's synthesizing from.
Demo infrastructure:
- tests/multi-agent/gen_staffer_demo.ts: 4 personas (Maria senior,
James mid, Sam junior, Alex trainee) × 3 contracts (Nashville Welder,
Joliet Warehouse, Indianapolis Assembly). 12 scenarios total.
- scripts/run_staffer_demo.sh: runs the 12 sequentially with
LH_OVERVIEW_CLOUD=1. Post-run calls kb_staffer_report.py.
- scripts/kb_staffer_report.py: leaderboard + cross-staffer worker
overlap (names endorsed by ≥2 staffers → auto-discovered high-value
workers). Top vs bottom differential.
gen_scenarios.ts (Phase 22 generator) also now emits contract terms
on 70% of generated specs — future KB batches populate with realistic
constraint patterns instead of bare role+city+count.
Stress scenario from item A intentionally NOT the production test.
Real staffing has constraints; Nashville contract + staffer demo is
the honest test of whether the architecture produces measurable
differential between coordinator skill levels.
Demo batch launched — 12 runs × ~3min each ≈ 40min unattended. Report
emitted after batch.
Proves cloud passthrough works end-to-end AND fixes the diagnostic
quality problem that first run surfaced.
STRESS SCENARIO (tests/multi-agent/scenarios/stress_01.json):
Five genuinely hard events with varied failure modes:
- Gary, IN 5× Electrician: ZERO supply (city not in workers_500k)
- Peoria, IL 8× Safety Coordinator: scarce role, initial pool only 5
- Flint, MI 3× Welder: ZERO supply
- Grand Rapids, MI 4× Tool & Die Maker: scarce but solvable
- Gary, IN 1× Electrician misplacement: repeats event 1's impossibility
FIRST RUN (stress v1) — cloud passthrough works, diagnosis vague:
T3 checkpoint: "Potential drift flags for upcoming role"
Lesson: "Before dispatching, query pool status. Update turn counter..."
Generic tactical advice that doesn't address the real problem.
Root cause: T3 prompt only saw outcome summary, not the raw
SQL/pool/drift signals the executor had in its log.
DIAGNOSTIC FIX:
- Added LogEntry[] `sharedLog` parameter to runAgentFill so the caller
retains the trace even when runAgentFill throws drift-abort.
- EventResult gained `diagnostic_log` field populated on both OK and
FAIL paths.
- extractDiagnostics() pulls SQL filters, hybrid_search row counts,
SQL errors, and reviewer drift notes from the log.
- Checkpoint prompt now includes FAILURE FORENSICS block for failed
events: SQL filters attempted, row counts, errors, drift reasons,
and an explicit teaching note about zero-supply detection.
- Cross-day lesson prompt flags each event with [ZERO-SUPPLY: pivot
city needed] tag when drift reasons mention "no match"/"no
candidates"/"0 rows". PRIORITY clause in the prompt tells the model
its lesson MUST name alternate cities when that tag appears.
SECOND RUN (stress v2 with enriched prompt) — cloud diagnosis sharp:
T3 after Flint: risk="Zero candidate supply for Welder in Flint"
hint="search Welder×3 in Saginaw, MI (≈30 mi) or
expand role to Metal Fabricator"
T3 after Gary: risk="Zero supply for Electrician in Gary, IN"
hint="Pivot to Chicago, IL (≈40 min); broaden to
Electrical Technician within 60 min radius"
Lesson: specific, per-city, with distances, role-broadening
fallback, and pre-loading strategy — actionable for item B retry.
Cloud 120b call latencies consistent: 4.8-8.0s per prompt. Cloud
passthrough proven under stress.
Fill outcomes unchanged (1/5 — correct rejection of three impossible
events + one propagating JSON emission edge case on retry pivot
reasoning). The knowledge to rescue them now exists in the lesson;
item B wires the retry.
