Files
compounding-intelligence/metrics/dashboard.md
Timmy bf003cd944 feat: measurer.py — compounding intelligence metrics engine
Implements issue #14: 7 metrics that prove knowledge compounding.

Metrics:
- Knowledge velocity: new facts/day (from index.json)
- Knowledge coverage: % domains with 10+ facts (from YAML files)
- Hit rate: % sessions referencing bootstrap knowledge
- Error recurrence: same errors across sessions (should decrease)
- Task completion: % sessions with successful end_reason
- First-try success: actions without backtracking (tool/msg ratio)
- Knowledge age: staleness of facts (freshness score)

Data sources:
- knowledge/index.json + YAML files for fact metrics
- ~/.hermes/state.db sessions + messages tables

Features:
- JSON and markdown output formats
- --since, --repo, --format flags
- 7-day trend tracking via snapshot persistence
- Runs in 33ms on 11.9K sessions / 192K messages
- Dashboard auto-generation with --save-snapshot

Closes #14
2026-04-14 14:16:31 -04:00

62 lines
1.3 KiB
Markdown

# Compounding Intelligence Metrics
**Generated:** 2026-04-14T18:12:26.469085+00:00
## knowledge_velocity
New facts extracted per day. Higher = compounding loop working.
**Value:** 1.61 | **7d trend:** N/A --- (unknown)
- total_facts: 29
- period_days: 18
- new_facts: 29
## knowledge_coverage
Percentage of domains/repos with 10+ facts. Measures breadth.
**Value:** 0.333 | **7d trend:** N/A --- (unknown)
- covered_domains: 1
- total_domains: 3
## hit_rate
Percentage of sessions referencing bootstrapped knowledge.
**Value:** 0.676 | **7d trend:** N/A --- (unknown)
- hit_sessions: 8058
- total_sessions: 11922
## error_recurrence
Ratio of recurring errors. Lower = fleet learning from mistakes.
**Value:** 0.17 | **7d trend:** N/A --- (unknown)
- unique_errors: 53615
- recurring_errors: 9093
## task_completion
Percentage of sessions ending with successful completion.
**Value:** 0.452 | **7d trend:** N/A --- (unknown)
- normal_end_rate: 0.56
- completed: 5385
- total: 11922
## first_try_success
Percentage of sessions completed without backtracking.
**Value:** 0.818 | **7d trend:** N/A --- (unknown)
- avg_tool_msg_ratio: 0.392
- sampled: 5923
## knowledge_age
Freshness of knowledge store. 1.0 = all fresh, 0.0 = all stale.
**Value:** 0.973 | **7d trend:** N/A --- (unknown)
- avg_age_days: 2.4
- stale_facts: 0
- total_facts: 29