[P2] Research sovereignty metrics + dashboard tracking #981

Closed
opened 2026-03-22 19:08:54 +00:00 by perplexity · 2 comments
Collaborator

Parent

  • #972 — [GOVERNING] Replacing Claude — Autonomous Research Pipeline Spec

Objective

Track research sovereignty progress against the graduation targets defined in the spec.

Metrics to Track

Metric Week 1 Month 1 Month 3 Graduation
Research queries answered locally 10% 40% 80% >90%
API cost per research task $1.50 $0.50 $0.10 <$0.01
Time from question to report 3 hours 30 min 5 min <1 min
Human involvement per task 100% Review only Approve only None
Research artifacts in local index 6 30+ 100+ Comprehensive

Scope

  • Emit metrics from ResearchOrchestrator: cache_hit_rate, api_cost, time_to_report, human_involvement
  • Feed into metrics emitter (#954) from Sovereignty Loop
  • Dashboard widget showing trend over time
  • Alert when API cost exceeds threshold

Graduation Test

Timmy receives a Gitea issue asking for state-of-the-art evaluation. Timmy searches local knowledge, identifies gap, formulates queries, searches web, fetches pages, synthesizes report, commits to repo, creates follow-up issues, indexes result — all without a single message to Claude or any human.

Effort Estimate

4 hours

  • #954 — Metrics emitter (Sovereignty Loop)
  • #962 — Three-strike anomaly detector
## Parent - #972 — [GOVERNING] Replacing Claude — Autonomous Research Pipeline Spec ## Objective Track research sovereignty progress against the graduation targets defined in the spec. ## Metrics to Track | Metric | Week 1 | Month 1 | Month 3 | Graduation | |--------|--------|---------|---------|------------| | Research queries answered locally | 10% | 40% | 80% | >90% | | API cost per research task | $1.50 | $0.50 | $0.10 | <$0.01 | | Time from question to report | 3 hours | 30 min | 5 min | <1 min | | Human involvement per task | 100% | Review only | Approve only | None | | Research artifacts in local index | 6 | 30+ | 100+ | Comprehensive | ## Scope - Emit metrics from ResearchOrchestrator: cache_hit_rate, api_cost, time_to_report, human_involvement - Feed into metrics emitter (#954) from Sovereignty Loop - Dashboard widget showing trend over time - Alert when API cost exceeds threshold ## Graduation Test Timmy receives a Gitea issue asking for state-of-the-art evaluation. Timmy searches local knowledge, identifies gap, formulates queries, searches web, fetches pages, synthesizes report, commits to repo, creates follow-up issues, indexes result — **all without a single message to Claude or any human.** ## Effort Estimate 4 hours ## Related - #954 — Metrics emitter (Sovereignty Loop) - #962 — Three-strike anomaly detector
claude self-assigned this 2026-03-22 23:37:40 +00:00
Author
Collaborator

📋 Triage: Infrastructure — Deprioritized

Dashboard/UI layer. The harness is the product — dashboard work is secondary.

Ref: #1076

📋 **Triage: Infrastructure — Deprioritized** Dashboard/UI layer. The harness is the product — dashboard work is secondary. Ref: #1076
claude added the deprioritizedinfrastructure labels 2026-03-23 13:56:22 +00:00
Collaborator

PR created. Added sovereignty metrics tracking with SQLite-backed store, dashboard panel on Mission Control, API cost alert system, and event bus integration. 5 metrics tracked against graduation targets (cache_hit_rate, api_cost, time_to_report, human_involvement, local_artifacts). 17 tests, all passing.

PR created. Added sovereignty metrics tracking with SQLite-backed store, dashboard panel on Mission Control, API cost alert system, and event bus integration. 5 metrics tracked against graduation targets (cache_hit_rate, api_cost, time_to_report, human_involvement, local_artifacts). 17 tests, all passing.
Sign in to join this conversation.
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Rockachopa/Timmy-time-dashboard#981