Apply the highest-confidence findings from the Phase 0→42 forensic sweep
after four scrum-master iterations under the adversarial prompt. Each fix
is independently validated by a later scrum iteration scoring the same
file higher under the same bar.
Code changes
────────────
P5-001 — crates/gateway/src/auth.rs + main.rs
api_key_auth was marked #[allow(dead_code)] and never wrapped around
the router, so `[auth] enabled=true` logged a green message and
enforced nothing. Now wired via from_fn_with_state, with constant-time
header compare and /health exempted for LB probes.
P42-001 — crates/truth/src/lib.rs
TruthStore::check() ignored RuleCondition entirely — signature looked
like enforcement, body returned every action unconditionally. Added
evaluate(task_class, ctx) that actually walks FieldEquals / FieldEmpty /
FieldGreater / Always against a serde_json::Value via dot-path lookup.
check() kept for back-compat. Tests 14 → 24 (10 new exercising real
pass/fail semantics). serde_json moved to [dependencies].
P9-001 (partial) — crates/ingestd/src/service.rs
Added Optional<Journal> to IngestState + a journal.record_ingest() call
on /ingest/file success. Gateway wires it with `journal.clone()` before
the /journal nest consumes the original. First-ever internal mutation
journal event verified live (total_events_created 0→1 after probe).
Iter-4 scrum scored these files higher under same prompt:
ingestd/src/service.rs 3 → 6 (P9-001 visible)
truth/src/lib.rs 3 → 4 (P42-001 visible)
gateway/src/auth.rs 3 → 4 (P5-001 visible)
gateway/src/execution_loop 4 → 6 (indirect)
storaged/src/federation 3 → 4 (indirect)
Infrastructure additions
────────────────────────
* tests/real-world/scrum_master_pipeline.ts
- cloud-first ladder: kimi-k2:1t → deepseek-v3.1:671b → mistral-large-3:675b
→ gpt-oss:120b → devstral-2:123b → qwen3.5:397b (deep final thinker)
- LH_SCRUM_FORENSIC env: injects SCRUM_FORENSIC_PROMPT.md as adversarial preamble
- LH_SCRUM_PROPOSAL env: per-iter fix-wave doc override
- Confidence extraction (markdown + JSON), schema v4 KB rows with:
verdict, critical_failures_count, verified_components_count,
missing_components_count, output_format, gradient_tier
- Model trust profile written per file-accept to data/_kb/model_trust.jsonl
- Fire-and-forget POST to observer /event so by_source.scrum appears in /stats
* mcp-server/observer.ts — unchanged in shape, confirmed receiving scrum events
* ui/ — new Visual Control Plane on :3950
- Bun.serve with /data/{services,reviews,metrics,trust,overrides,findings,file,refactor_signals,search,logs/:svc,scrum_log}
- Views: MAP (D3 graph, 5 overlays) / TRACE (per-file iter timeline) /
TRAJECTORY (refactor signals + reverse index search) / METRICS (explainers
with SOURCE + GOOD lines) / KB (card grid with tooltips) / CONSOLE (per-service
journalctl tail, tabs for gateway/sidecar/observer/mcp/ctx7/auditor/langfuse)
- tryFetch always attempts JSON.parse (fix for observer returning JSON without content-type)
- renderNodeContext primitive-vs-object guard (fix for gateway /health string)
* docs/SCRUM_FIX_WAVE.md — iter-specific scope directing the scrum
* docs/SCRUM_FORENSIC_PROMPT.md — adversarial audit prompt (verdict/critical/verified schema)
* docs/SCRUM_LOOP_NOTES.md — iteration observations + fix-next-loop queue
* docs/SYSTEM_EVOLUTION_LAYERS.md — Layers 1-10 roadmap (trust profiling, execution DNA, drift sentinel, etc)
Measurements across iterations
──────────────────────────────
iter 1 (soft prompt, gpt-oss:120b): mean score 5.00/10
iter 3 (forensic, kimi-k2:1t): mean score 3.56/10 (−1.44 — bar raised)
iter 4 (same bar, post fixes): mean score 4.00/10 (+0.44 — fixes landed)
Score movement iter3→iter4: ↑5 ↓1 =12
21/21 first-attempt accept by kimi-k2:1t in iter 4
20/21 emitted forensic JSON (richer signal than markdown)
16 verified_components captured (proof-of-life, new metric)
Permission Gradient distribution: 0 auto · 16 dry_run · 4 sim · 1 block
Observer loop: by_source {scrum: 21, langfuse: 1985, phase24_audit: 1}
v1/usage: 224 requests, 477K tokens, all tracked
Signal classes per file (iter 3 → iter 4):
CONVERGING: 1 (ingestd/service.rs — fix clearly landed)
LOOPING: 4 (catalogd/registry, main, queryd/service, vectord/index_registry)
ORBITING: 1 (truth — novel findings surfacing as surface ones fix)
PLATEAU: 9 (scores flat with high confidence — diminishing returns)
MIXED: 6
Loop thesis status
──────────────────
A file's score rises only when the scrum confirms a real fix landed.
No false positives yet across 3 iterations. Fixes applied to 3 files all
raised their independent scores under the same adversarial prompt. Loop
is measurable, not hand-wavy.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Second provider wired. /v1/chat now routes by optional `provider`
field: default "ollama" hits local via sidecar, "ollama_cloud"
(or "cloud") hits ollama.com/api/generate directly with Bearer auth.
Key sourced at gateway startup from OLLAMA_CLOUD_KEY env, then
/root/llm_team_config.json (providers.ollama_cloud.api_key), then
OLLAMA_CLOUD_API_KEY env. Config source matches LLM Team convention.
Shape-identical to scenario.ts::generateCloud — same endpoint, same
body, same Bearer auth. Cloud path bypasses sidecar entirely (sidecar
is local-only by design, mirrors TS agent.ts).
Changes:
- crates/gateway/src/v1/ollama_cloud.rs (new, 130 LOC) — reqwest
client, resolve_cloud_key(), chat() adapter, CloudGenerateBody /
CloudGenerateResponse wire shapes
- crates/gateway/src/v1/ollama.rs — flatten_messages_public()
re-export so sibling adapters reuse the shape collapse
- crates/gateway/src/v1/mod.rs — provider field on ChatRequest,
dispatch match in chat() handler, ollama_cloud_key on V1State
- crates/gateway/src/main.rs — resolves cloud key at startup,
logs which source provided it
- crates/gateway/Cargo.toml — reqwest 0.12 with rustls-tls
Verified end-to-end after restart:
- provider=ollama → qwen3.5:latest local (~400ms, Phase 38 unchanged)
- provider=ollama_cloud + model=gpt-oss:120b → real 225-word
technical response in 5.4s, 313 tokens
Tests: 9/9 green (7 from Phase 38 + 2 new for cloud body serialization
and key resolver shape).
Not in this slice: trait extraction (full Phase 39 scope adds
ProviderAdapter trait + OpenRouter adapter + fallback chain logic).
These land next with Phase 40 routing engine on top.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- ToolRegistry: named tools with parameter validation and audit logging
- 6 built-in staffing tools:
search_candidates (skills, city, state, experience, availability)
get_candidate (by ID)
revenue_by_client (top N by billed revenue)
recruiter_performance (placements, revenue per recruiter)
cold_leads (called N+ times, never placed)
open_jobs (by vertical, city)
- Each tool: name, description, params, permission level (read/write/admin)
- SQL template with validated parameter substitution
- Full audit trail: every invocation logged with agent, params, result
- Endpoints: GET /tools (list), GET /tools/{name} (schema),
POST /tools/{name}/call (execute), GET /tools/audit (log)
- Per ADR-015: governed interface before raw SQL for agents
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- journald crate: immutable event log for every data mutation
- Events: entity_type, entity_id, field, action, old_value, new_value,
actor, source, workspace_id, timestamp
- In-memory buffer with configurable flush threshold (default 100 events)
- Flush writes events as Parquet to journal/ directory
- Query: GET /journal/history/{entity_id} — full history of any record
- Query: GET /journal/recent?limit=50 — latest events across all entities
- Convenience methods: record_insert, record_update, record_ingest
- Stats: GET /journal/stats — buffer size, persisted file count
- Manual flush: POST /journal/flush
- Per ADR-012: events are never modified or deleted
This is the single most important future-proofing decision.
Once history is lost, it's gone forever.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
