test: add tests for issue body parser (#90 )

feat: Gitea issue body parser for structured task extraction (#90 )
Add comprehensive test script for harvest prompt validation
2026-04-15 03:34:33 +00:00 · 2026-04-15 03:34:30 +00:00 · 2026-04-14 19:02:41 +00:00 · 2026-04-14 19:01:03 +00:00 · 2026-04-14 19:01:00 +00:00 · 2026-04-14 19:00:58 +00:00
22 changed files with 687 additions and 2963 deletions
--- a/knowledge/SCHEMA.md
+++ b/knowledge/SCHEMA.md
@@ -1,171 +0,0 @@
-# Knowledge File Format Specification
-
-**Version:** 1
-**Issue:** #10
-**Status:** Draft
-
---
-
-## Overview
-
-The knowledge system has two layers:
-
-1. **index.json** — Machine-readable fact index. Fast lookups by ID, category, repo, tags.
-2. **Knowledge files** (YAML) — Human-readable, editable facts organized by domain.
-
-The harvester writes to both. The bootstrapper reads from index.json. Humans edit the YAML files directly.
-
---
-
-## index.json Schema
-
-```json
-{
-  "version": 1,
-  "last_updated": "ISO-8601 timestamp",
-  "total_facts": 0,
-  "facts": []
-}
-```
-
-### Fact Object
-
-| Field | Type | Required | Description |
-|-------|------|----------|-------------|
-| `id` | string | yes | Unique identifier: `{domain}:{category}:{sequence}` |
-| `fact` | string | yes | One-sentence description of the knowledge |
-| `category` | enum | yes | One of: `fact`, `pitfall`, `pattern`, `tool-quirk`, `question` |
-| `domain` | string | yes | Where this applies: repo name, `global`, or agent name |
-| `confidence` | float | yes | 0.0–1.0. How certain is this knowledge? |
-| `tags` | string[] | no | Searchable labels: `["git", "auth", "gitea"]` |
-| `source_count` | int | no | How many sessions confirmed this fact |
-| `first_seen` | date | no | ISO-8601 date first extracted |
-| `last_confirmed` | date | no | ISO-8601 date last seen in a session |
-| `expires` | date | no | Optional. After this date, fact is stale |
-| `related` | string[] | no | IDs of related facts |
-
-### ID Format
-
-```
-{domain}:{category}:{sequence}
-```
-
- `domain` — repo name, `global`, or agent type
- `category` — one of the 5 categories
- `sequence` — zero-padded 3-digit number: `001`, `002`, ...
-
-Examples:
- `the-nexus:pitfall:001`
- `global:tool-quirk:012`
- `hermes-agent:pattern:003`
-
-### Categories
-
-| Category | Definition | Example |
-|----------|------------|---------|
-| `fact` | Concrete, verifiable information | "Gitea API requires token auth at /api/v1" |
-| `pitfall` | Errors, wrong assumptions, time-wasters | "Assumed env var GITEA_TOKEN; actual path is ~/.config/gitea/token" |
-| `pattern` | Successful sequences of actions | "To deploy: test → build → push → webhook" |
-| `tool-quirk` | Environment-specific behaviors | "URL format requires trailing slash on macOS" |
-| `question` | Identified but unanswered | "Need optimal batch size for harvesting" |
-
-### Confidence Scoring
-
-| Range | Meaning |
-|-------|---------|
-| 0.9–1.0 | Explicitly stated and verified |
-| 0.7–0.8 | Clearly implied by multiple data points |
-| 0.5–0.6 | Suggested but not fully verified |
-| 0.3–0.4 | Inferred from limited data |
-| 0.1–0.2 | Speculative or uncertain |
-
---
-
-## Knowledge Files (YAML)
-
-Human-readable files stored in `knowledge/` subdirectories.
-
-### Directory Structure
-
-```
-knowledge/
-├── index.json                  # Machine-readable fact index
-├── SCHEMA.md                   # This file
-├── global/                     # Cross-repo knowledge
-│   ├── pitfalls.yaml           # Pitfalls that span multiple repos
-│   ├── patterns.yaml           # Proven workflows
-│   └── tool-quirks.yaml        # Environment behaviors
-├── repos/                      # Per-repo knowledge
-│   ├── the-nexus.yaml
-│   ├── hermes-agent.yaml
-│   └── ...
-└── agents/                     # Agent-type knowledge
-    ├── mimo-sprint.yaml
-    └── ...
-```
-
-### YAML File Format
-
-```yaml
---
-domain: global                    # or repo name or agent name
-category: tool-quirk              # fact, pitfall, pattern, tool-quirk, question
-version: 1
-last_updated: "2026-04-13"
---
-
-# Tool Quirks (Global)
-
-Cross-environment behaviors that bite you if you don't know them.
-
-## Authentication
-
- id: global:tool-quirk:001
-  fact: "Gitea token stored at ~/.config/gitea/token, not env var"
-  confidence: 0.95
-  tags: [git, auth, gitea]
-  source_count: 23
-  first_seen: "2026-03-27"
-  last_confirmed: "2026-04-13"
-  related: [global:pitfall:003]
-
- id: global:tool-quirk:002
-  fact: "Gitea API uses 'token' header format: Authorization: token TOKEN"
-  confidence: 0.9
-  tags: [git, api, gitea]
-  source_count: 8
-  first_seen: "2026-03-28"
-```
-
-### Rules
-
-1. **One file per domain per category.** `repos/the-nexus.yaml` holds all the-nexus facts. Don't mix categories across files.
-2. **Markdown sections for humans.** The YAML items live under markdown headers. This makes the files readable in Gitea's UI.
-3. **ID is the link.** The `id` field connects YAML facts to index.json entries. Same ID = same fact.
-4. **Harvester writes, humans edit.** The harvester appends new facts. Humans can correct confidence, add tags, or mark expired.
-
---
-
-## Sync Rules
-
-1. **Harvester → YAML:** Appends new facts to the appropriate YAML file.
-2. **Harvester → index.json:** Adds/updates fact entries.
-3. **Human edits YAML:** Changes propagate to index.json on next harvester run.
-4. **Confidence decay:** Facts not confirmed in 30+ sessions get confidence *= 0.9.
-5. **Expiration:** Facts with `expires` date past current date are marked `stale` in index.json.
-
---
-
-## Validation
-
-Facts must pass these checks before entering the index:
-
-1. `id` matches format `{domain}:{category}:{sequence}`
-2. `category` is one of the 5 allowed values
-3. `confidence` is between 0.0 and 1.0
-4. `fact` is non-empty string, max 280 characters
-5. `domain` is non-empty string
-6. `tags` are lowercase alphanumeric + hyphens
-7. No duplicate IDs in index.json
-
-Validation script: `scripts/validate_knowledge.py`
--- a/knowledge/global/pitfalls.yaml
+++ b/knowledge/global/pitfalls.yaml
@@ -1,80 +0,0 @@
---
-domain: global
-category: pitfall
-version: 1
-last_updated: "2026-04-13"
---
-
-# Pitfalls (Global)
-
-Cross-repo traps that waste time across the fleet.
-
-## Git & Forge
-
- id: global:pitfall:001
-  fact: "Branch protection requires 1 approval on main — API merges fail with 405 without it"
-  confidence: 0.95
-  tags: [git, merge, branch-protection, gitea]
-  source_count: 12
-  first_seen: "2026-04-05"
-  last_confirmed: "2026-04-13"
-  related: [the-nexus:pitfall:001]
-
- id: global:pitfall:002
-  fact: "Never use --no-verify on git commits — it bypasses all hooks including safety checks"
-  confidence: 0.95
-  tags: [git, hooks, safety]
-  source_count: 5
-  first_seen: "2026-03-28"
-  last_confirmed: "2026-04-13"
-
- id: global:pitfall:003
-  fact: "Gitea PR creation workaround needed on the-nexus — direct API call fails, use alternative endpoint"
-  confidence: 0.9
-  tags: [gitea, pr, api, workaround]
-  source_count: 4
-  first_seen: "2026-04-06"
-  last_confirmed: "2026-04-12"
-
-## Agent Operations
-
- id: global:pitfall:004
-  fact: "Anthropic is BANNED from fallback chain — if fallback triggers to Anthropic, something is wrong"
-  confidence: 0.95
-  tags: [provider, anthropic, fallback]
-  source_count: 7
-  first_seen: "2026-03-30"
-  last_confirmed: "2026-04-13"
-
- id: global:pitfall:005
-  fact: "Telegram tokens expired — don't assume Telegram notifications work without checking"
-  confidence: 0.85
-  tags: [telegram, notifications, token]
-  source_count: 3
-  first_seen: "2026-04-02"
-
- id: global:pitfall:006
-  fact: "Multiple gateways = 'cannot schedule futures' error — only one gateway process should run"
-  confidence: 0.9
-  tags: [gateway, cron, process]
-  source_count: 4
-  first_seen: "2026-04-04"
-  last_confirmed: "2026-04-11"
-
-## Testing
-
- id: global:pitfall:007
-  fact: "pytest root collection picks up operational *_test.py scripts — restrict to tests/ directory"
-  confidence: 0.9
-  tags: [pytest, test, collection]
-  source_count: 3
-  first_seen: "2026-04-07"
-  last_confirmed: "2026-04-13"
-
- id: global:pitfall:008
-  fact: "TDD: test 1 before building 55 — verify the cycle works before scaling"
-  confidence: 0.95
-  tags: [tdd, testing, methodology]
-  source_count: 8
-  first_seen: "2026-03-25"
-  last_confirmed: "2026-04-13"
--- a/knowledge/global/tool-quirks.yaml
+++ b/knowledge/global/tool-quirks.yaml
@@ -1,73 +0,0 @@
---
-domain: global
-category: tool-quirk
-version: 1
-last_updated: "2026-04-13"
---
-
-# Tool Quirks (Global)
-
-Cross-environment behaviors that bite you if you don't know them.
-
-## Authentication
-
- id: global:tool-quirk:001
-  fact: "Gitea token stored at ~/.config/gitea/token, not env var GITEA_TOKEN"
-  confidence: 0.95
-  tags: [git, auth, gitea, token]
-  source_count: 23
-  first_seen: "2026-03-27"
-  last_confirmed: "2026-04-13"
-  related: [global:pitfall:001]
-
- id: global:tool-quirk:002
-  fact: "Gitea API uses 'Authorization: token TOKEN' header format, not Bearer"
-  confidence: 0.9
-  tags: [git, api, gitea]
-  source_count: 8
-  first_seen: "2026-03-28"
-  last_confirmed: "2026-04-12"
-
- id: global:tool-quirk:003
-  fact: "Gitea Issues API type=issues param does NOT filter PRs — use truthiness check on pull_request field"
-  confidence: 0.95
-  tags: [gitea, api, issues, pr]
-  source_count: 6
-  first_seen: "2026-04-01"
-  last_confirmed: "2026-04-13"
-
-## Paths & Environment
-
- id: global:tool-quirk:004
-  fact: "~/.hermes is the default hermes home — check get_hermes_home() not the path literal"
-  confidence: 0.9
-  tags: [paths, hermes, env]
-  source_count: 10
-  first_seen: "2026-03-30"
-  last_confirmed: "2026-04-13"
-  related: [hermes-agent:pitfall:005]
-
- id: global:tool-quirk:005
-  fact: "Ansible vault-encrypted vars in YAML require vault_inline_vars plugin — standard ansible-vault fails"
-  confidence: 0.85
-  tags: [ansible, vault, config]
-  source_count: 3
-  first_seen: "2026-04-02"
-
-## Model & Inference
-
- id: global:tool-quirk:006
-  fact: "mimo-v2-pro via Nous Research is the default model — don't assume Anthropic is available"
-  confidence: 0.95
-  tags: [model, provider, nous, default]
-  source_count: 15
-  first_seen: "2026-03-25"
-  last_confirmed: "2026-04-13"
-
- id: global:tool-quirk:007
-  fact: "Kill + restart with 'hermes chat' preserves old model state — NEVER use --resume"
-  confidence: 0.95
-  tags: [hermes, model, restart, session]
-  source_count: 8
-  first_seen: "2026-03-29"
-  last_confirmed: "2026-04-12"
--- a/knowledge/index.json
+++ b/knowledge/index.json
@@ -1,489 +1,6 @@
 {
  "version": 1,
-  "last_updated": "2026-04-14T18:07:27.448168Z",
-  "total_facts": 55,
-  "migration": {
-    "migrated_from": [
-      "mempalace",
-      "fact_store",
-      "skills"
-    ],
-    "migrated_at": "2026-04-14T18:07:27.448362Z",
-    "sources": {
-      "mempalace": 11,
-      "fact_store": 29,
-      "skills": 15
-    }
-  },
-  "facts": [
-    {
-      "fact": "Timmy Foundation: 17 repos, 282 open issues, 63.0% closure rate",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Timmy_Foundation/timmy-home: 227 open issues",
-      "category": "fact",
-      "repo": "timmy-home",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Timmy_Foundation/timmy-config: 133 open issues",
-      "category": "fact",
-      "repo": "timmy-config",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Timmy_Foundation/the-nexus: 72 open issues",
-      "category": "fact",
-      "repo": "the-nexus",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Timmy_Foundation/fleet-ops: 47 open issues",
-      "category": "fact",
-      "repo": "fleet-ops",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Timmy_Foundation/the-beacon: 12 open issues",
-      "category": "fact",
-      "repo": "the-beacon",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Assignment coverage: 99.6% (281 assigned, 1 unassigned)",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "Priority: 4 P0, 8 P1, 11 epics",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.95,
-      "source": "mempalace",
-      "source_file": "forge.json"
-    },
-    {
-      "fact": "CRITICAL timmy-home#580: Harden SOUL.md against Claude identity hijacking - Security: Protects the core inscription of Timmy's values on-chain",
-      "category": "pitfall",
-      "repo": "timmy-home",
-      "confidence": 0.9,
-      "source": "mempalace",
-      "source_file": "forge-palace-summary.json"
-    },
-    {
-      "fact": "CRITICAL timmy-home#579: [RCA] Ezra and Bezalel do not respond to Gitea @mention tags - DevOps: Two VPS wizard houses are not receiving critical notifications",
-      "category": "pitfall",
-      "repo": "timmy-home",
-      "confidence": 0.9,
-      "source": "mempalace",
-      "source_file": "forge-palace-summary.json"
-    },
-    {
-      "fact": "CRITICAL the-nexus#1125: [COMPUTER_USE] Add Desktop Automation Primitives to Hermes - Feature: Unlocks computer-use capability in agent toolkit",
-      "category": "pitfall",
-      "repo": "the-nexus",
-      "confidence": 0.9,
-      "source": "mempalace",
-      "source_file": "forge-palace-summary.json"
-    },
-    {
-      "fact": "Alexander prefers rate-limited stretches over underutilization. 'I would rather get rate limited and have it stretch out a bit than underutilize.'",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 1,
-      "source_tags": "preference"
-    },
-    {
-      "fact": "Alexander's frustration: reading source code instead of testing the actual command first. Validate with CLI first, code second.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 2,
-      "source_tags": "preference"
-    },
-    {
-      "fact": "KEYMAXXING: ~/.hermes/keymaxxing/. inbox/ for drops, detect_provider.py, watcher.sh (60s poll). First key = Nous/OpenRouter (391 models, 25 free).",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 3,
-      "source_tags": "keymaxxing,nous"
-    },
-    {
-      "fact": "Automation philosophy: aggressive utilization but outcome-focused. No duplicate PRs, no noise. Quality gates mandatory. 'Build things to be a masterwork.'",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 4,
-      "source_tags": "automation,philosophy"
-    },
-    {
-      "fact": "Mnemosyne = priority project. Tag [Mnemosyne] issues for swarm priority. WebSocket bridge for live memory (issue #1164).",
-      "category": "fact",
-      "repo": "the-nexus",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 5,
-      "source_tags": "mnemosyne,nexus"
-    },
-    {
-      "fact": "Bitcoin inscription #90707: Sermon on the Mount (Matthew 5-7 ESV), block 776549, Feb 14 2023. Gospel immutable on-chain.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 6,
-      "source_tags": "bitcoin,faith"
-    },
-    {
-      "fact": "Gitea API gotcha: 'labels' field requires integer IDs, not string names. GET /labels first to resolve. String names return HTTP 422.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 8,
-      "source_tags": "gitea,api"
-    },
-    {
-      "fact": "CRON WORKER: Jobs needing files MUST use real scripts, not LLM prompts. LLM cron can't ls/cat - needs execute_code. Test one cycle before scaling. (55 cron jobs, 0 PRs for 37 minutes.)",
-      "category": "tool-quirk",
-      "repo": "hermes-agent",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 11,
-      "source_tags": "cron,worker"
-    },
-    {
-      "fact": "HERMES CLI: hermes chat -q 'prompt' --provider nous -m xiaomi/mimo-v2-pro. -q=query text, -p=profile name. Mixing causes silent failure.",
-      "category": "tool-quirk",
-      "repo": "hermes-agent",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 12,
-      "source_tags": "hermes,cli"
-    },
-    {
-      "fact": "Core preferences: 'Don't be precious.' Parallel over sequential. Test before scaling. Direct communicator. Satoshi/Hal engineering philosophy.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 13,
-      "source_tags": "preferences"
-    },
-    {
-      "fact": "Gitea API: /orgs/TimmyFoundation/repos returns 404. Use /user/repos?limit=50 instead for all repos across all orgs.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 15,
-      "source_tags": "gitea,api"
-    },
-    {
-      "fact": "CRITICAL: tool_use_enforcement must be 'true' in config.yaml. Without it, mimo-v2-pro generates text descriptions instead of executing tools. 36 PRs/day with this fix ($0).",
-      "category": "tool-quirk",
-      "repo": "hermes-agent",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 19,
-      "source_tags": "hermes,config,critical"
-    },
-    {
-      "fact": "forge.alexanderwhitestone.com clone: depth 50 times out. Use --depth 5 --single-branch instead.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 20,
-      "source_tags": "git,forge"
-    },
-    {
-      "fact": "Telegram: Bot token ~/.config/telegram/special_bot. Alexander chat ID: 7635059073. API: POST /bot{token}/sendMessage.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 23,
-      "source_tags": "telegram"
-    },
-    {
-      "fact": "Communication: Gitea for reports/deliverables. Telegram for urgent only. Wants proactive monitoring, visual confirmation, action-oriented.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 24,
-      "source_tags": "communication"
-    },
-    {
-      "fact": "Kimi API: model ID is 'kimi-for-coding' not 'kimi-k2.5'. Key prefix sk-kimi- routes to api.kimi.com/coding/v1. One model only.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 26,
-      "source_tags": "kimi,api"
-    },
-    {
-      "fact": "model-watchdog.py restarts panes without -p flag, losing profile. Falls through to hermes3 (8K context). Fix: preserve -p flag.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 28,
-      "source_tags": "watchdog,bug,critical"
-    },
-    {
-      "fact": "INCIDENT: Modified hermes profile configs without permission. Corrupted fenrir/bezalel. NEVER modify configs. Report issues, wait. Anthropic BANNED.",
-      "category": "fact",
-      "repo": "timmy-config",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 30,
-      "source_tags": "incident,config"
-    },
-    {
-      "fact": "CRON GOTCHAS: .tick.lock blocks jobs on crash. tool_choice='required' crashes AIAgent. save_jobs needs fcntl.flock. Error jobs stay error. Tick backlog: 56 jobs + 6 workers = 9min.",
-      "category": "tool-quirk",
-      "repo": "hermes-agent",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 31,
-      "source_tags": "cron,gotchas"
-    },
-    {
-      "fact": "OpenRouter = FREE MODELS ONLY. All fallbacks must use :free suffix. Never paid models.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 32,
-      "source_tags": "openrouter,rules"
-    },
-    {
-      "fact": "Config is infra-as-code. Canonical: Rockachopa/hermes-config on forge. Local config = source of truth for live system.",
-      "category": "fact",
-      "repo": "timmy-config",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 33,
-      "source_tags": "config"
-    },
-    {
-      "fact": "Accountability: Check edit history before claims. Never modify configs without instruction. When broken: create issue, stop using it.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 34,
-      "source_tags": "accountability"
-    },
-    {
-      "fact": "OpenAI tool_calls: two argument formats - tc.arguments or tc.function.arguments. hermes-agent uses function format. Check both.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 36,
-      "source_tags": "openai,api"
-    },
-    {
-      "fact": "TMUX RULE: Alexander creates windows/splits. Timmy NEVER creates layouts - only send-keys to existing panes.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 39,
-      "source_tags": "tmux,rule"
-    },
-    {
-      "fact": "Long-running agents > fresh one-shots. Context compounds. Optimize persistent lanes, not disposable workers. Never rotate panes across repos.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 40,
-      "source_tags": "dispatch,lanes"
-    },
-    {
-      "fact": "Dispatch style: 'Go. repo #issue. Description. Clone, implement, branch NAME, commit push PR.' Zero questions, immediate execution, results-only.",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 42,
-      "source_tags": "dispatch,workflow"
-    },
-    {
-      "fact": "Protocol: Done/stuck \u2192 commit, push, PR, next issue. File new issues to Gitea via API. Multiple agents can work same issue (different branches).",
-      "category": "fact",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 43,
-      "source_tags": "protocol"
-    },
-    {
-      "fact": "cron/__init__.py imports ModelContextError/CRON_MIN_CONTEXT_TOKENS from scheduler - neither exists. ImportError. Fix: remove imports. Issue #541.",
-      "category": "fact",
-      "repo": "hermes-agent",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 46,
-      "source_tags": "cron,bug"
-    },
-    {
-      "fact": "Gitea tokens: main (~/.config/gitea/token) = Rockachopa admin. timmy-token = Timmy bot. Contents API works with main token. PR creation with either.",
-      "category": "tool-quirk",
-      "repo": "global",
-      "confidence": 0.5,
-      "source": "fact_store",
-      "source_id": 48,
-      "source_tags": "gitea,auth"
-    },
-    {
-      "fact": "Skill: gitea-burn-cycle - Automated burn cycles on Gitea repos",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/gitea-burn-cycle/SKILL.md"
-    },
-    {
-      "fact": "Skill: hermes-agent - Complete Hermes Agent guide - CLI, gateway, cron, profiles",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/autonomous-ai-agents/hermes-agent/SKILL.md"
-    },
-    {
-      "fact": "Skill: cron-infra-as-code - Source-control cron jobs as YAML",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/cron-infra-as-code/SKILL.md"
-    },
-    {
-      "fact": "Skill: burn-loop-health-monitoring - Detect silent burn loop failures",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/burn-loop-health-monitoring/SKILL.md"
-    },
-    {
-      "fact": "Skill: fleet-config-deploy - Deploy config across VPS fleet with canary",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/fleet-config-deploy/SKILL.md"
-    },
-    {
-      "fact": "Skill: mimo-swarm - Coordinated mimo-v2-pro swarm: claim-work-release",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/mimo-swarm/SKILL.md"
-    },
-    {
-      "fact": "Skill: session-signal-extraction-pitfalls - Pitfalls extracting behavioral signals from sessions",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/session-signal-extraction-pitfalls/SKILL.md"
-    },
-    {
-      "fact": "Skill: json-repair-for-tool-calls - Fix JSON parse failures in tool calls - 14 patterns",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/json-repair-for-tool-calls/SKILL.md"
-    },
-    {
-      "fact": "Skill: poka-yoke-guards - Mistake-proofing guards for weak model agents",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/poka-yoke-guards/SKILL.md"
-    },
-    {
-      "fact": "Skill: tmux-supervisor - Monitor tmux panes - drift detection",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/tmux-supervisor/SKILL.md"
-    },
-    {
-      "fact": "Skill: approval-threat-model-extension - Threat model: LLM jailbreaks, accidents, supply chain",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/security/approval-threat-model-extension/SKILL.md"
-    },
-    {
-      "fact": "Skill: deploy-crons-fix - Fix deploy-crons.py model/provider dropping",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/deploy-crons-fix/SKILL.md"
-    },
-    {
-      "fact": "Skill: sovereign-heart-architecture - State-based compassion interface pattern",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/autonomous-ai-agents/sovereign-heart-architecture/SKILL.md"
-    },
-    {
-      "fact": "Skill: burn-night-operations - Max-throughput burn night scheduling",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/burn-night-operations/SKILL.md"
-    },
-    {
-      "fact": "Skill: cron-scaling-patterns - Cron scaling: workers, tick intervals, checkpoints",
-      "category": "pattern",
-      "repo": "global",
-      "confidence": 0.85,
-      "source": "skill",
-      "source_path": "~/.hermes/skills/devops/cron-scaling-patterns/SKILL.md"
-    }
-  ]
+  "last_updated": "2026-04-13T20:00:00Z",
+  "total_facts": 0,
+  "facts": []
 }
--- a/knowledge/repos/hermes-agent.yaml
+++ b/knowledge/repos/hermes-agent.yaml
@@ -1,82 +0,0 @@
---
-domain: hermes-agent
-category: pitfall
-version: 1
-last_updated: "2026-04-13"
---
-
-# Pitfalls (hermes-agent)
-
-Things that go wrong in this repo if you don't know the traps.
-
-## Cron & Deployment
-
- id: hermes-agent:pitfall:001
-  fact: "deploy-crons.py leaves jobs in mixed model format — some have provider/model, some just model"
-  confidence: 0.95
-  tags: [cron, deploy, model, config]
-  source_count: 5
-  first_seen: "2026-04-08"
-  last_confirmed: "2026-04-13"
-  related: [hermes-agent:pitfall:002, hermes-agent:pitfall:003]
-
- id: hermes-agent:pitfall:002
-  fact: "deploy-crons.py --deploy doesn't set legacy skill field from skills list, breaking older jobs"
-  confidence: 0.9
-  tags: [cron, deploy, skills]
-  source_count: 3
-  first_seen: "2026-04-09"
-  last_confirmed: "2026-04-13"
-  related: [hermes-agent:pitfall:001]
-
- id: hermes-agent:pitfall:003
-  fact: "Cron jobs with blank fallback_model fields trigger spurious gateway warnings"
-  confidence: 0.9
-  tags: [cron, model, fallback]
-  source_count: 4
-  first_seen: "2026-04-07"
-  last_confirmed: "2026-04-12"
-  related: [hermes-agent:pitfall:001]
-
- id: hermes-agent:pitfall:004
-  fact: "model-watchdog.py checks first provider line, not model.provider — causes false drift alarms"
-  confidence: 0.9
-  tags: [watchdog, model, config]
-  source_count: 3
-  first_seen: "2026-04-08"
-  last_confirmed: "2026-04-13"
-
-## Path & Environment
-
- id: hermes-agent:pitfall:005
-  fact: "10+ files read HERMES_HOME directly instead of get_hermes_home() — breaks on custom paths"
-  confidence: 0.85
-  tags: [paths, env, hermes-home]
-  source_count: 6
-  first_seen: "2026-04-06"
-  last_confirmed: "2026-04-12"
-  related: [global:pitfall:002]
-
- id: hermes-agent:pitfall:006
-  fact: "get_hermes_home() doesn't expand tilde when HERMES_HOME=~/... is set"
-  confidence: 0.8
-  tags: [paths, env, bug]
-  source_count: 2
-  first_seen: "2026-04-05"
-
-## SSH & Dispatch
-
- id: hermes-agent:pitfall:007
-  fact: "vps-agent-dispatch reports OK while remote hermes binary path is broken"
-  confidence: 0.9
-  tags: [ssh, dispatch, vps]
-  source_count: 4
-  first_seen: "2026-04-07"
-  last_confirmed: "2026-04-11"
-
- id: hermes-agent:pitfall:008
-  fact: "nightwatch-health-monitor SSH check fails on cloud-model-only deployments"
-  confidence: 0.85
-  tags: [ssh, health, cloud]
-  source_count: 2
-  first_seen: "2026-04-10"
--- a/knowledge/repos/the-nexus.yaml
+++ b/knowledge/repos/the-nexus.yaml
@@ -1,68 +0,0 @@
---
-domain: the-nexus
-category: pitfall
-version: 1
-last_updated: "2026-04-13"
---
-
-# Pitfalls (the-nexus)
-
-Things that go wrong in this repo if you don't know the traps.
-
-## Git & Merging
-
- id: the-nexus:pitfall:001
-  fact: "Merges fail with HTTP 405 due to branch protection — must use merge API with 1 approval"
-  confidence: 0.95
-  tags: [git, merge, branch-protection, gitea]
-  source_count: 12
-  first_seen: "2026-04-05"
-  last_confirmed: "2026-04-13"
-  related: [global:pitfall:001]
-
- id: the-nexus:pitfall:002
-  fact: "ThreadingHTTPServer required for multi-user bridge — standard HTTPServer blocks on concurrent requests"
-  confidence: 0.95
-  tags: [server, concurrency, bridge]
-  source_count: 5
-  first_seen: "2026-04-10"
-  last_confirmed: "2026-04-13"
-  related: [the-nexus:pattern:001]
-
- id: the-nexus:pitfall:003
-  fact: "ChatLog.log() crashes on message persistence when index.html has orphaned button tags"
-  confidence: 0.9
-  tags: [html, crash, chatlog]
-  source_count: 3
-  first_seen: "2026-04-12"
-  last_confirmed: "2026-04-13"
-
-## Three.js & Performance
-
- id: the-nexus:pitfall:004
-  fact: "Three.js LOD not implemented — local hardware struggles with full scene without texture optimization"
-  confidence: 0.85
-  tags: [threejs, performance, lod]
-  source_count: 4
-  first_seen: "2026-04-09"
-  last_confirmed: "2026-04-13"
-  related: [the-nexus:pattern:002]
-
- id: the-nexus:pitfall:005
-  fact: "Duplicate content blocks appear in index.html when PR merges conflict silently"
-  confidence: 0.8
-  tags: [html, merge-conflict, duplicate]
-  source_count: 3
-  first_seen: "2026-04-11"
-  last_confirmed: "2026-04-13"
-
-## Deployment
-
- id: the-nexus:pitfall:006
-  fact: "Unified HTTP + WebSocket server required for proper URL deployment — separate servers break CORS"
-  confidence: 0.9
-  tags: [deploy, websocket, http, cors]
-  source_count: 4
-  first_seen: "2026-04-10"
-  last_confirmed: "2026-04-13"
-  related: [the-nexus:pattern:001]
--- a/metrics/dashboard.md
+++ b/metrics/dashboard.md
@@ -1,61 +0,0 @@
-# Compounding Intelligence Metrics
-**Generated:** 2026-04-14T18:07:26.169469+00:00
-
-## knowledge_velocity
-New facts extracted per day. Higher = compounding loop working.
-
-**Value:** 1.61  |  **7d trend:** N/A — (unknown)
-
- total_facts: 44
- 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: 2
- total_domains: 6
-
-## hit_rate
-Percentage of sessions referencing bootstrapped knowledge.
-
-**Value:** 0.677  |  **7d trend:** N/A — (unknown)
-
- hit_sessions: 8064
- total_sessions: 11919
-
-## error_recurrence
-Ratio of recurring errors. Lower = fleet learning from mistakes.
-
-**Value:** 0.169  |  **7d trend:** N/A — (unknown)
-
- unique_errors: 53556
- recurring_errors: 9075
-
-## 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: 11919
-
-## first_try_success
-Percentage of sessions completed without backtracking.
-
-**Value:** 0.818  |  **7d trend:** N/A — (unknown)
-
- avg_tool_msg_ratio: 0.391
- sampled: 5921
-
-## 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: 44
--- a/metrics/latest_snapshot.json
+++ b/metrics/latest_snapshot.json
@@ -1,130 +0,0 @@
-{
-  "generated_at": "2026-04-14T18:07:26.169469+00:00",
-  "knowledge_velocity": {
-    "value": 1.61,
-    "total_facts": 44,
-    "period_days": 18,
-    "new_facts": 29
-  },
-  "knowledge_coverage": {
-    "value": 0.333,
-    "covered_domains": 2,
-    "total_domains": 6,
-    "domain_details": {
-      "global": 15,
-      "unknown": 15,
-      "hermes-agent": 8,
-      "pitfalls": 8,
-      "tool-quirks": 7,
-      "the-nexus": 6
-    }
-  },
-  "hit_rate": {
-    "value": 0.677,
-    "hit_sessions": 8064,
-    "total_sessions": 11919
-  },
-  "error_recurrence": {
-    "value": 0.169,
-    "unique_errors": 53556,
-    "recurring_errors": 9075,
-    "top_errors": [
-      {
-        "error": "s, report the error details.",
-        "sessions": 1185
-      },
-      {
-        "error": "\": \"traceback (most recent call last):\\n file \\\"/private/var/folders/9k/v07xkpp",
-        "sessions": 694
-      },
-      {
-        "error": "\", \"output\": \"\\n--- stderr ---\\ntraceback (most recent call last):\\n file \\\"/pr",
-        "sessions": 684
-      },
-      {
-        "error": "ures \u2192 file an issue with the traceback and tag [bug]",
-        "sessions": 320
-      },
-      {
-        "error": "s you encounter \u2192 file an issue with reproduction steps",
-        "sessions": 320
-      },
-      {
-        "error": "s, file a [bug] issue first.",
-        "sessions": 320
-      },
-      {
-        "error": ", fix the code.",
-        "sessions": 314
-      },
-      {
-        "error": "fix it before doing anything else.",
-        "sessions": 313
-      },
-      {
-        "error": "ures \u2192 add a review comment explaining what's wrong",
-        "sessions": 303
-      },
-      {
-        "error": "ures \u2014 they're your roadmap for guardrails",
-        "sessions": 303
-      }
-    ]
-  },
-  "task_completion": {
-    "value": 0.452,
-    "normal_end_rate": 0.56,
-    "completed": 5385,
-    "total": 11919,
-    "breakdown": {
-      "cron_complete": 5354,
-      "unknown": 5245,
-      "compression": 1092,
-      "cli_close": 197,
-      "session_reset": 31
-    }
-  },
-  "first_try_success": {
-    "value": 0.818,
-    "avg_tool_msg_ratio": 0.391,
-    "sampled": 5921,
-    "interpretation": "Higher value = fewer backtracks = better first-try success"
-  },
-  "knowledge_age": {
-    "value": 0.973,
-    "avg_age_days": 2.4,
-    "stale_facts": 0,
-    "total_facts": 44,
-    "interpretation": "1.0 = all facts fresh. 0.0 = all facts 90+ days old"
-  },
-  "trend_7d": {
-    "knowledge_velocity": {
-      "delta": "N/A",
-      "direction": "unknown"
-    },
-    "knowledge_coverage": {
-      "delta": "N/A",
-      "direction": "unknown"
-    },
-    "hit_rate": {
-      "delta": "N/A",
-      "direction": "unknown"
-    },
-    "error_recurrence": {
-      "delta": "N/A",
-      "direction": "unknown"
-    },
-    "task_completion": {
-      "delta": "N/A",
-      "direction": "unknown"
-    },
-    "first_try_success": {
-      "delta": "N/A",
-      "direction": "unknown"
-    },
-    "knowledge_age": {
-      "delta": "N/A",
-      "direction": "unknown"
-    }
-  }
-}
--- a/scripts/bootstrapper.py
+++ b/scripts/bootstrapper.py
@@ -1,359 +0,0 @@
-#!/usr/bin/env python3
-"""
-Bootstrapper — assemble pre-session context from knowledge store.
-
-Reads the knowledge store and produces a compact context block (2k tokens max)
-that can be injected into a new session so it starts with situational awareness.
-
-Usage:
-    python3 bootstrapper.py --repo the-nexus --agent mimo-sprint
-    python3 bootstrapper.py --repo timmy-home --global
-    python3 bootstrapper.py --global
-    python3 bootstrapper.py --repo the-nexus --max-tokens 1000
-"""
-
-import argparse
-import json
-import sys
-from pathlib import Path
-from typing import Optional
-
-# Resolve knowledge root relative to this script's parent
-SCRIPT_DIR = Path(__file__).resolve().parent
-REPO_ROOT = SCRIPT_DIR.parent
-KNOWLEDGE_DIR = REPO_ROOT / "knowledge"
-INDEX_PATH = KNOWLEDGE_DIR / "index.json"
-
-# Approximate token count: ~4 chars per token for English text
-CHARS_PER_TOKEN = 4
-
-# Category sort priority (lower = shown first)
-CATEGORY_PRIORITY = {
-    "pitfall": 0,
-    "tool-quirk": 1,
-    "pattern": 2,
-    "fact": 3,
-    "question": 4,
-}
-
-
-def load_index(index_path: Path = INDEX_PATH) -> dict:
-    """Load and validate the knowledge index."""
-    if not index_path.exists():
-        return {"version": 1, "total_facts": 0, "facts": []}
-
-    with open(index_path) as f:
-        data = json.load(f)
-
-    if "facts" not in data:
-        print(f"WARNING: index.json missing 'facts' key", file=sys.stderr)
-        return {"version": 1, "total_facts": 0, "facts": []}
-
-    return data
-
-
-def filter_facts(
-    facts: list[dict],
-    repo: Optional[str] = None,
-    agent: Optional[str] = None,
-    include_global: bool = True,
-) -> list[dict]:
-    """Filter facts by repo, agent, and global scope."""
-    filtered = []
-
-    for fact in facts:
-        fact_repo = fact.get("repo", "global")
-        fact_agent = fact.get("agent", "")
-
-        # Match by repo (regardless of agent)
-        if repo and fact_repo == repo:
-            filtered.append(fact)
-            continue
-
-        # Match by exact agent type
-        if agent and fact_agent == agent:
-            filtered.append(fact)
-            continue
-
-        # Include global facts without agent restriction (universal facts)
-        if include_global and fact_repo == "global" and not fact_agent:
-            filtered.append(fact)
-
-    return filtered
-
-
-def sort_facts(facts: list[dict]) -> list[dict]:
-    """
-    Sort facts by: confidence (desc), then category priority, then fact text.
-    Most reliable and most dangerous facts come first.
-    """
-
-    def sort_key(f):
-        confidence = f.get("confidence", 0.5)
-        category = f.get("category", "fact")
-        cat_priority = CATEGORY_PRIORITY.get(category, 5)
-        return (-confidence, cat_priority, f.get("fact", ""))
-
-    return sorted(facts, key=sort_key)
-
-
-def load_repo_knowledge(repo: str) -> Optional[str]:
-    """Load per-repo knowledge markdown if it exists."""
-    repo_path = KNOWLEDGE_DIR / "repos" / f"{repo}.md"
-    if repo_path.exists():
-        return repo_path.read_text().strip()
-    return None
-
-
-def load_agent_knowledge(agent: str) -> Optional[str]:
-    """Load per-agent knowledge markdown if it exists."""
-    agent_path = KNOWLEDGE_DIR / "agents" / f"{agent}.md"
-    if agent_path.exists():
-        return agent_path.read_text().strip()
-    return None
-
-
-def load_global_knowledge() -> list[str]:
-    """Load all global knowledge markdown files."""
-    global_dir = KNOWLEDGE_DIR / "global"
-    if not global_dir.exists():
-        return []
-
-    chunks = []
-    for md_file in sorted(global_dir.glob("*.md")):
-        content = md_file.read_text().strip()
-        if content:
-            chunks.append(content)
-    return chunks
-
-
-def render_facts_section(facts: list[dict], category: str, label: str) -> str:
-    """Render a section of facts for a single category."""
-    cat_facts = [f for f in facts if f.get("category") == category]
-    if not cat_facts:
-        return ""
-
-    lines = [f"### {label}\n"]
-    for f in cat_facts:
-        conf = f.get("confidence", 0.5)
-        fact_text = f.get("fact", "")
-        repo_tag = f.get("repo", "")
-        if repo_tag and repo_tag != "global":
-            lines.append(f"- [{conf:.0%}] ({repo_tag}) {fact_text}")
-        else:
-            lines.append(f"- [{conf:.0%}] {fact_text}")
-
-    return "\n".join(lines) + "\n"
-
-
-def estimate_tokens(text: str) -> int:
-    """Rough token estimate."""
-    return len(text) // CHARS_PER_TOKEN
-
-
-def truncate_to_tokens(text: str, max_tokens: int) -> str:
-    """Truncate text to approximately max_tokens, cutting at line boundaries."""
-    max_chars = max_tokens * CHARS_PER_TOKEN
-    if len(text) <= max_chars:
-        return text
-
-    # Cut at last newline before the limit
-    truncated = text[:max_chars]
-    last_newline = truncated.rfind("\n")
-    if last_newline > 0:
-        truncated = truncated[:last_newline]
-
-    return truncated + "\n\n[... truncated to fit context window ...]"
-
-
-def build_bootstrap_context(
-    repo: Optional[str] = None,
-    agent: Optional[str] = None,
-    include_global: bool = True,
-    max_tokens: int = 2000,
-    index_path: Path = INDEX_PATH,
-) -> str:
-    """
-    Build the full bootstrap context block.
-
-    Returns a markdown string suitable for injection into a session prompt.
-    """
-    index = load_index(index_path)
-    facts = index.get("facts", [])
-
-    # Filter
-    filtered = filter_facts(facts, repo=repo, agent=agent, include_global=include_global)
-
-    # Sort
-    sorted_facts = sort_facts(filtered)
-
-    # Build sections
-    sections = ["## What You Know (bootstrapped)\n"]
-
-    # Per-repo markdown knowledge
-    if repo:
-        repo_md = load_repo_knowledge(repo)
-        if repo_md:
-            sections.append(f"### Repo Notes: {repo}\n")
-            sections.append(repo_md + "\n")
-
-    # Structured facts by category
-    if sorted_facts:
-        # Group by source
-        repo_facts = [f for f in sorted_facts if f.get("repo") == repo] if repo else []
-        global_facts = [f for f in sorted_facts if f.get("repo") == "global"]
-        agent_facts = [f for f in sorted_facts if f.get("agent") == agent] if agent else []
-
-        if repo_facts:
-            sections.append(f"### Repo: {repo}\n")
-            for cat, label in [
-                ("pitfall", "PITFALLS"),
-                ("tool-quirk", "QUIRKS"),
-                ("pattern", "PATTERNS"),
-                ("fact", "FACTS"),
-                ("question", "OPEN QUESTIONS"),
-            ]:
-                section = render_facts_section(repo_facts, cat, label)
-                if section:
-                    sections.append(section)
-
-        if global_facts:
-            sections.append("### Global\n")
-            for cat, label in [
-                ("pitfall", "PITFALLS"),
-                ("tool-quirk", "QUIRKS"),
-                ("pattern", "PATTERNS"),
-                ("fact", "FACTS"),
-            ]:
-                section = render_facts_section(global_facts, cat, label)
-                if section:
-                    sections.append(section)
-
-        if agent_facts:
-            sections.append(f"### Agent Notes ({agent})\n")
-            for cat, label in [
-                ("pitfall", "PITFALLS"),
-                ("tool-quirk", "QUIRKS"),
-                ("pattern", "PATTERNS"),
-                ("fact", "FACTS"),
-            ]:
-                section = render_facts_section(agent_facts, cat, label)
-                if section:
-                    sections.append(section)
-
-    # Per-agent markdown knowledge
-    if agent:
-        agent_md = load_agent_knowledge(agent)
-        if agent_md:
-            sections.append(f"### Agent Profile: {agent}\n")
-            sections.append(agent_md + "\n")
-
-    # Global markdown knowledge
-    global_chunks = load_global_knowledge()
-    if global_chunks:
-        sections.append("### Global Notes\n")
-        sections.extend(chunk + "\n" for chunk in global_chunks)
-
-    # If nothing was found
-    if len(sections) == 1:
-        sections.append("_No relevant knowledge found. Starting fresh._\n")
-        if not facts:
-            sections.append(
-                "_Knowledge store is empty. Run the harvester to populate it._\n"
-            )
-
-    # Join and truncate
-    context = "\n".join(sections)
-    context = truncate_to_tokens(context, max_tokens)
-
-    return context
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Assemble pre-session context from knowledge store"
-    )
-    parser.add_argument(
-        "--repo",
-        type=str,
-        default=None,
-        help="Repository name to filter facts by",
-    )
-    parser.add_argument(
-        "--agent",
-        type=str,
-        default=None,
-        help="Agent type to filter facts by (e.g., mimo-sprint, groq-fast)",
-    )
-    parser.add_argument(
-        "--global",
-        dest="include_global",
-        action="store_true",
-        default=True,
-        help="Include global facts (default: true)",
-    )
-    parser.add_argument(
-        "--no-global",
-        dest="include_global",
-        action="store_false",
-        help="Exclude global facts",
-    )
-    parser.add_argument(
-        "--max-tokens",
-        type=int,
-        default=2000,
-        help="Maximum token count for output (default: 2000)",
-    )
-    parser.add_argument(
-        "--index",
-        type=str,
-        default=None,
-        help="Path to index.json (default: knowledge/index.json)",
-    )
-    parser.add_argument(
-        "--json",
-        dest="output_json",
-        action="store_true",
-        help="Output raw JSON instead of markdown",
-    )
-
-    args = parser.parse_args()
-
-    index_path = Path(args.index) if args.index else INDEX_PATH
-
-    if args.output_json:
-        # JSON mode: return the filtered, sorted facts
-        index = load_index(index_path)
-        facts = index.get("facts", [])
-        filtered = filter_facts(
-            facts,
-            repo=args.repo,
-            agent=args.agent,
-            include_global=args.include_global,
-        )
-        sorted_facts = sort_facts(filtered)
-        output = {
-            "repo": args.repo,
-            "agent": args.agent,
-            "include_global": args.include_global,
-            "total_indexed": len(facts),
-            "matched": len(sorted_facts),
-            "facts": sorted_facts,
-        }
-        print(json.dumps(output, indent=2))
-    else:
-        # Markdown mode: full bootstrap context
-        context = build_bootstrap_context(
-            repo=args.repo,
-            agent=args.agent,
-            include_global=args.include_global,
-            max_tokens=args.max_tokens,
-            index_path=index_path,
-        )
-        print(context)
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())
--- a/scripts/gitea_issue_parser.py
+++ b/scripts/gitea_issue_parser.py
@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+"""
+Gitea Issue Body Parser
+
+Extracts structured data from Gitea issue markdown bodies:
+- Title
+- Context section
+- Acceptance criteria (checkboxes)
+- Labels
+- Epic/parent references
+
+Usage:
+  python3 scripts/gitea_issue_parser.py <issue_body.txt
+  python3 scripts/gitea_issue_parser.py --url https://forge.../api/v1/repos/.../issues/123
+  echo "issue body" | python3 scripts/gitea_issue_parser.py --stdin
+
+Output: JSON with {title, context, criteria[], labels[], epic_ref}
+"""
+
+import argparse
+import json
+import re
+import sys
+from typing import Optional
+
+
+def parse_issue_body(body: str, title: str = "", labels: list = None) -> dict:
+    """Parse a Gitea issue body into structured JSON."""
+    result = {
+        "title": title,
+        "context": "",
+        "criteria": [],
+        "labels": labels or [],
+        "epic_ref": None,
+        "sections": {},
+    }
+
+    if not body:
+        return result
+
+    # Extract epic/parent reference from title or body
+    epic_pattern = r"#(\d+)"
+    title_refs = re.findall(epic_pattern, title)
+    body_refs = re.findall(epic_pattern, body[:200])  # Check early body refs
+
+    # Look for "Closes #N" or "Part of #N" or "Epic: #N"
+    close_match = re.search(r"(?:Closes?|Fixes?|Resolves?)\s+#(\d+)", body, re.IGNORECASE)
+    part_match = re.search(r"(?:Part of|Epic|Parent|Blocks?)\s+#(\d+)", body, re.IGNORECASE)
+
+    if close_match:
+        result["epic_ref"] = f"#{close_match.group(1)}"
+    elif part_match:
+        result["epic_ref"] = f"#{part_match.group(1)}"
+    elif title_refs:
+        result["epic_ref"] = f"#{title_refs[0]}"
+    elif body_refs:
+        result["epic_ref"] = f"#{body_refs[0]}"
+
+    # Split into sections by ## headers
+    section_pattern = r"^##\s+(.+)$"
+    lines = body.split("\n")
+    current_section = None
+    current_content = []
+
+    for line in lines:
+        header_match = re.match(section_pattern, line)
+        if header_match:
+            # Save previous section
+            if current_section:
+                result["sections"][current_section] = "\n".join(current_content).strip()
+            current_section = header_match.group(1).strip().lower()
+            current_content = []
+        else:
+            current_content.append(line)
+
+    # Save last section
+    if current_section:
+        result["sections"][current_section] = "\n".join(current_content).strip()
+
+    # Extract context
+    for key in ["context", "background", "description", "problem"]:
+        if key in result["sections"]:
+            result["context"] = result["sections"][key]
+            break
+
+    # Extract acceptance criteria (checkboxes)
+    criteria_section = None
+    for key in ["acceptance criteria", "acceptance_criteria", "criteria", "requirements", "definition of done"]:
+        if key in result["sections"]:
+            criteria_section = result["sections"][key]
+            break
+
+    if criteria_section:
+        checkbox_pattern = r"-\s*\[[ xX]?\]\s*(.+)"
+        for match in re.finditer(checkbox_pattern, criteria_section):
+            result["criteria"].append(match.group(1).strip())
+
+        # Also try plain numbered/bulleted lists if no checkboxes found
+        if not result["criteria"]:
+            list_pattern = r"^\s*(?:\d+\.|-|\*)\s+(.+)"
+            for match in re.finditer(list_pattern, criteria_section, re.MULTILINE):
+                result["criteria"].append(match.group(1).strip())
+
+    # If no sectioned criteria found, scan whole body for checkboxes
+    if not result["criteria"]:
+        for match in re.finditer(r"-\s*\[[ xX]?\]\s*(.+)", body):
+            result["criteria"].append(match.group(1).strip())
+
+    return result
+
+
+def parse_from_url(api_url: str, token: str = None) -> dict:
+    """Parse an issue from a Gitea API URL."""
+    import urllib.request
+
+    headers = {}
+    if token:
+        headers["Authorization"] = f"token {token}"
+
+    req = urllib.request.Request(api_url, headers=headers)
+    resp = json.loads(urllib.request.urlopen(req, timeout=30).read())
+
+    title = resp.get("title", "")
+    body = resp.get("body", "")
+    labels = [l["name"] for l in resp.get("labels", [])]
+
+    return parse_issue_body(body, title, labels)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Parse Gitea issue body into structured JSON")
+    parser.add_argument("input", nargs="?", help="Issue body file (or - for stdin)")
+    parser.add_argument("--url", help="Gitea API URL for the issue")
+    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
+    parser.add_argument("--token", help="Gitea API token (or set GITEA_TOKEN env var)")
+    parser.add_argument("--title", default="", help="Issue title (for epic ref extraction)")
+    parser.add_argument("--labels", nargs="*", default=[], help="Issue labels")
+    parser.add_argument("--pretty", action="store_true", help="Pretty-print JSON output")
+    args = parser.parse_args()
+
+    import os
+    token = args.token or os.environ.get("GITEA_TOKEN")
+
+    if args.url:
+        result = parse_from_url(args.url, token)
+    elif args.stdin or (args.input and args.input == "-"):
+        body = sys.stdin.read()
+        result = parse_issue_body(body, args.title, args.labels)
+    elif args.input:
+        with open(args.input) as f:
+            body = f.read()
+        result = parse_issue_body(body, args.title, args.labels)
+    else:
+        parser.print_help()
+        sys.exit(1)
+
+    indent = 2 if args.pretty else None
+    print(json.dumps(result, indent=indent))
+
+
+if __name__ == "__main__":
+    main()
--- a/scripts/measurer.py
+++ b/scripts/measurer.py
@@ -1,607 +0,0 @@
-#!/usr/bin/env python3
-"""
-Compounding Intelligence Metrics Engine.
-
-Computes 7 metrics that prove whether the knowledge compounding loop is working:
-  1. Knowledge velocity — new facts per day
-  2. Knowledge coverage — % of domains with >10 facts
-  3. Hit rate — % of sessions referencing bootstrap knowledge
-  4. Error recurrence — same errors across sessions (should decrease)
-  5. Task completion — % of sessions ending successfully
-  6. First-try success — actions without backtracking
-  7. Knowledge age — staleness of facts
-
-Usage:
-  python3 measurer.py                        # All metrics, all time
-  python3 measurer.py --since 2026-04-01     # Time range
-  python3 measurer.py --repo the-nexus       # Per-repo metrics
-  python3 measurer.py --format json          # JSON output (default)
-  python3 measurer.py --format markdown      # Human-readable
-  python3 measurer.py --knowledge-dir ./knowledge  # Custom knowledge path
-  python3 measurer.py --db ~/.hermes/state.db      # Custom DB path
-
-Data sources:
-  - knowledge/index.json  — fact index
-  - knowledge/            — YAML fact files for coverage
-  - ~/.hermes/state.db    — session/message metadata
-"""
-
-import argparse
-import json
-import os
-import re
-import sqlite3
-import sys
-from collections import Counter, defaultdict
-from datetime import datetime, timedelta, timezone
-from pathlib import Path
-from typing import Any
-
-
-# ─── Defaults ───────────────────────────────────────────────────────────────────
-
-DEFAULT_KNOWLEDGE_DIR = Path(__file__).parent.parent / "knowledge"
-DEFAULT_DB_PATH = Path.home() / ".hermes" / "state.db"
-SEVEN_DAYS = timedelta(days=7)
-
-
-# ─── Knowledge Store ────────────────────────────────────────────────────────────
-
-def load_facts(knowledge_dir: Path) -> list[dict]:
-    """Load all facts from index.json."""
-    index_path = knowledge_dir / "index.json"
-    if not index_path.exists():
-        return []
-    with open(index_path) as f:
-        data = json.load(f)
-    return data.get("facts", [])
-
-
-def count_yaml_facts(knowledge_dir: Path) -> dict[str, int]:
-    """Count facts per domain from YAML files (coverage source)."""
-    domain_counts: dict[str, int] = {}
-    # Walk repos/, global/, agents/ subdirs
-    for subdir in ["repos", "global", "agents"]:
-        dirpath = knowledge_dir / subdir
-        if not dirpath.exists():
-            continue
-        for yaml_file in dirpath.glob("*.yaml"):
-            # Count lines that start with "- id:" — each is a fact
-            count = 0
-            try:
-                content = yaml_file.read_text()
-                count = len(re.findall(r"^\s*-\s*id:", content, re.MULTILINE))
-            except Exception:
-                pass
-            domain = yaml_file.stem
-            domain_counts[domain] = domain_counts.get(domain, 0) + count
-    return domain_counts
-
-
-# ─── Session Database ───────────────────────────────────────────────────────────
-
-def open_db(db_path: Path) -> sqlite3.Connection:
-    """Open session database."""
-    if not db_path.exists():
-        print(f"WARNING: Database not found at {db_path}", file=sys.stderr)
-        return None
-    conn = sqlite3.connect(str(db_path))
-    conn.row_factory = sqlite3.Row
-    return conn
-
-
-def query_sessions(conn: sqlite3.Connection, since: str = None, repo: str = None) -> list[dict]:
-    """Query sessions with optional filters."""
-    if conn is None:
-        return []
-
-    query = """
-        SELECT id, started_at, ended_at, end_reason, message_count,
-               tool_call_count, model
-        FROM sessions
-        WHERE 1=1
-    """
-    params = []
-
-    if since:
-        since_ts = datetime.fromisoformat(since).replace(tzinfo=timezone.utc).timestamp()
-        query += " AND started_at >= ?"
-        params.append(since_ts)
-
-    query += " ORDER BY started_at ASC"
-
-    cur = conn.execute(query, params)
-    return [dict(row) for row in cur.fetchall()]
-
-
-def query_messages(conn: sqlite3.Connection, session_ids: list[str] = None,
-                   since_ts: float = None) -> list[dict]:
-    """Query messages with optional session filter."""
-    if conn is None:
-        return []
-
-    query = """
-        SELECT m.session_id, m.role, m.content, m.tool_name, m.timestamp
-        FROM messages m
-        WHERE 1=1
-    """
-    params = []
-
-    if since_ts:
-        query += " AND m.timestamp >= ?"
-        params.append(since_ts)
-
-    if session_ids:
-        placeholders = ",".join("?" for _ in session_ids)
-        query += f" AND m.session_id IN ({placeholders})"
-        params.extend(session_ids)
-
-    cur = conn.execute(query, params)
-    return [dict(row) for row in cur.fetchall()]
-
-
-# ─── Metric Computations ───────────────────────────────────────────────────────
-
-def compute_knowledge_velocity(facts: list[dict], since: str = None) -> dict:
-    """Metric 1: New facts per day. Higher = compounding working."""
-    if not facts:
-        return {"value": 0.0, "total_facts": 0, "period_days": 0, "new_facts": 0}
-
-    dates = []
-    for f in facts:
-        d = f.get("first_seen") or f.get("created")
-        if d:
-            try:
-                dt = datetime.fromisoformat(d.replace("Z", "+00:00"))
-                if dt.tzinfo is None:
-                    dt = dt.replace(tzinfo=timezone.utc)
-                dates.append(dt)
-            except (ValueError, AttributeError):
-                pass
-
-    if not dates:
-        return {"value": 0.0, "total_facts": len(facts), "period_days": 0, "new_facts": 0}
-
-    if since:
-        cutoff = datetime.fromisoformat(since).replace(tzinfo=timezone.utc)
-        dates = [d for d in dates if d >= cutoff]
-
-    if not dates:
-        return {"value": 0.0, "total_facts": len(facts), "period_days": 0, "new_facts": 0}
-
-    earliest = min(dates)
-    latest = max(dates)
-    period_days = max((latest - earliest).days, 1)
-
-    return {
-        "value": round(len(dates) / period_days, 2),
-        "total_facts": len(facts),
-        "period_days": period_days,
-        "new_facts": len(dates),
-    }
-
-
-def compute_knowledge_coverage(facts: list[dict], yaml_counts: dict[str, int]) -> dict:
-    """Metric 2: % of domains with >10 facts. Breadth indicator."""
-    domain_fact_counts: dict[str, int] = defaultdict(int)
-    for f in facts:
-        domain = f.get("domain", "unknown")
-        domain_fact_counts[domain] += 1
-
-    # Merge YAML counts (may have facts not yet indexed)
-    for domain, count in yaml_counts.items():
-        domain_fact_counts[domain] = max(domain_fact_counts[domain], count)
-
-    total_domains = len(domain_fact_counts)
-    if total_domains == 0:
-        return {"value": 0.0, "covered_domains": 0, "total_domains": 0, "domain_details": {}}
-
-    covered = sum(1 for c in domain_fact_counts.values() if c >= 10)
-
-    return {
-        "value": round(covered / total_domains, 3),
-        "covered_domains": covered,
-        "total_domains": total_domains,
-        "domain_details": dict(sorted(domain_fact_counts.items(), key=lambda x: -x[1])[:20]),
-    }
-
-
-def compute_hit_rate(sessions: list[dict], messages: list[dict],
-                     facts: list[dict]) -> dict:
-    """Metric 3: % of sessions that reference bootstrap knowledge.
-
-    Looks for message content matching known fact text.
-    """
-    if not sessions or not facts:
-        return {"value": 0.0, "hit_sessions": 0, "total_sessions": len(sessions)}
-
-    # Build a set of searchable fact fragments (lowercased, 4+ word phrases)
-    fact_fragments: set[str] = set()
-    for f in facts:
-        text = f.get("fact", "").lower().strip()
-        # Add full fact
-        if len(text) > 10:
-            fact_fragments.add(text)
-        # Add significant words
-        words = re.findall(r'\w{4,}', text)
-        for w in words:
-            fact_fragments.add(w)
-
-    if not fact_fragments:
-        return {"value": 0.0, "hit_sessions": 0, "total_sessions": len(sessions)}
-
-    # Group messages by session
-    session_messages: dict[str, list[str]] = defaultdict(list)
-    for m in messages:
-        content = (m.get("content") or "").lower()
-        if content:
-            session_messages[m["session_id"]].append(content)
-
-    # Check each session for fact references
-    hit_sessions = 0
-    for session in sessions:
-        sid = session["id"]
-        all_content = " ".join(session_messages.get(sid, []))
-        if any(frag in all_content for frag in fact_fragments):
-            hit_sessions += 1
-
-    return {
-        "value": round(hit_sessions / len(sessions), 3) if sessions else 0.0,
-        "hit_sessions": hit_sessions,
-        "total_sessions": len(sessions),
-    }
-
-
-def compute_error_recurrence(messages: list[dict]) -> dict:
-    """Metric 4: Same errors appearing across sessions. Should decrease.
-
-    Extracts error signatures and counts how many sessions each appears in.
-    """
-    if not messages:
-        return {"value": 0.0, "unique_errors": 0, "recurring_errors": 0, "top_errors": []}
-
-    # Extract error patterns from assistant/tool messages
-    error_pattern = re.compile(
-        r'(?:error|Error|ERROR|failed|FAIL|exception|Exception)[:\s]*(.{10,80})',
-        re.IGNORECASE
-    )
-
-    error_to_sessions: dict[str, set[str]] = defaultdict(set)
-
-    for m in messages:
-        content = m.get("content") or ""
-        if not content:
-            continue
-        for match in error_pattern.finditer(content):
-            sig = match.group(1).strip().lower()
-            # Normalize whitespace
-            sig = re.sub(r'\s+', ' ', sig)
-            if len(sig) > 5:
-                error_to_sessions[sig].add(m["session_id"])
-
-    if not error_to_sessions:
-        return {"value": 0.0, "unique_errors": 0, "recurring_errors": 0, "top_errors": []}
-
-    recurring = {e: s for e, s in error_to_sessions.items() if len(s) > 1}
-    total_errors = len(error_to_sessions)
-    recurring_count = len(recurring)
-
-    # Top recurring errors
-    top = sorted(recurring.items(), key=lambda x: -len(x[1]))[:10]
-
-    return {
-        "value": round(recurring_count / total_errors, 3) if total_errors else 0.0,
-        "unique_errors": total_errors,
-        "recurring_errors": recurring_count,
-        "top_errors": [{"error": e, "sessions": len(s)} for e, s in top],
-    }
-
-
-def compute_task_completion(sessions: list[dict]) -> dict:
-    """Metric 5: % of sessions ending with successful status."""
-    if not sessions:
-        return {"value": 0.0, "completed": 0, "total": 0, "breakdown": {}}
-
-    breakdown: Counter = Counter()
-    for s in sessions:
-        reason = s.get("end_reason") or "unknown"
-        breakdown[reason] += 1
-
-    completed = breakdown.get("cron_complete", 0) + breakdown.get("session_reset", 0)
-    # "cli_close" and "compression" are also normal endings
-    normal_endings = completed + breakdown.get("cli_close", 0) + breakdown.get("compression", 0)
-
-    return {
-        "value": round(completed / len(sessions), 3) if sessions else 0.0,
-        "normal_end_rate": round(normal_endings / len(sessions), 3) if sessions else 0.0,
-        "completed": completed,
-        "total": len(sessions),
-        "breakdown": dict(breakdown.most_common()),
-    }
-
-
-def compute_first_try_success(sessions: list[dict]) -> dict:
-    """Metric 6: Sessions completed without excessive backtracking.
-
-    Proxy: ratio of tool_call_count to message_count.
-    Low ratio = fewer retries = more first-try success.
-    We invert this: high tool/msg ratio means more backtracking (bad).
-    """
-    if not sessions:
-        return {"value": 0.0, "avg_tool_msg_ratio": 0.0, "sampled": 0}
-
-    ratios = []
-    for s in sessions:
-        msgs = s.get("message_count", 0) or 0
-        tools = s.get("tool_call_count", 0) or 0
-        if msgs > 2:  # Skip trivial sessions
-            ratios.append(tools / msgs if msgs > 0 else 0)
-
-    if not ratios:
-        return {"value": 0.0, "avg_tool_msg_ratio": 0.0, "sampled": 0}
-
-    avg_ratio = sum(ratios) / len(ratios)
-    # First-try success: sessions with tool_msg_ratio < 0.5 (few tools per message)
-    first_try = sum(1 for r in ratios if r < 0.5)
-
-    return {
-        "value": round(first_try / len(ratios), 3),
-        "avg_tool_msg_ratio": round(avg_ratio, 3),
-        "sampled": len(ratios),
-        "interpretation": "Higher value = fewer backtracks = better first-try success",
-    }
-
-
-def compute_knowledge_age(facts: list[dict]) -> dict:
-    """Metric 7: Days since facts were last confirmed. Staleness indicator."""
-    if not facts:
-        return {"value": 0.0, "avg_age_days": 0, "stale_facts": 0, "total_facts": 0}
-
-    now = datetime.now(timezone.utc)
-    ages = []
-    stale_count = 0  # Facts not confirmed in 30+ days
-
-    for f in facts:
-        confirmed = f.get("last_confirmed") or f.get("first_seen")
-        if confirmed:
-            try:
-                dt = datetime.fromisoformat(confirmed.replace("Z", "+00:00"))
-                if dt.tzinfo is None:
-                    dt = dt.replace(tzinfo=timezone.utc)
-                age = (now - dt).days
-                ages.append(age)
-                if age > 30:
-                    stale_count += 1
-            except (ValueError, AttributeError):
-                pass
-
-    if not ages:
-        return {"value": 0.0, "avg_age_days": 0, "stale_facts": 0, "total_facts": len(facts)}
-
-    avg_age = sum(ages) / len(ages)
-    # Lower avg age = fresher = better. Invert for a 0-1 score.
-    freshness = max(0.0, 1.0 - (avg_age / 90))  # 90 days = 0 freshness
-
-    return {
-        "value": round(freshness, 3),
-        "avg_age_days": round(avg_age, 1),
-        "stale_facts": stale_count,
-        "total_facts": len(facts),
-        "interpretation": "1.0 = all facts fresh. 0.0 = all facts 90+ days old",
-    }
-
-
-# ─── Trend Computation ─────────────────────────────────────────────────────────
-
-def compute_trend(current: dict, previous: dict, metric_key: str = "value") -> dict:
-    """Compute 7-day trend between two metric snapshots."""
-    if not previous:
-        return {"delta": "N/A", "direction": "unknown"}
-
-    curr_val = current.get(metric_key, 0)
-    prev_val = previous.get(metric_key, 0)
-
-    if prev_val == 0:
-        return {"delta": "N/A (no baseline)", "direction": "unknown"}
-
-    pct = ((curr_val - prev_val) / abs(prev_val)) * 100
-    direction = "up" if pct > 0 else "down" if pct < 0 else "flat"
-
-    # For error_recurrence, down is good
-    if metric_key == "error_recurrence" or metric_key == "knowledge_age":
-        direction_label = "good" if pct < 0 else "bad" if pct > 0 else "neutral"
-    else:
-        direction_label = "good" if pct > 0 else "bad" if pct < 0 else "neutral"
-
-    return {
-        "delta": f"{'+' if pct > 0 else ''}{pct:.1f}%",
-        "direction": direction,
-        "assessment": direction_label,
-    }
-
-
-# ─── Output Formatters ─────────────────────────────────────────────────────────
-
-def format_json(metrics: dict) -> str:
-    """Format metrics as JSON."""
-    return json.dumps(metrics, indent=2)
-
-
-def format_markdown(metrics: dict) -> str:
-    """Format metrics as human-readable markdown."""
-    lines = [
-        "# Compounding Intelligence Metrics",
-        f"**Generated:** {metrics.get('generated_at', 'unknown')}",
-        "",
-    ]
-
-    trend = metrics.get("trend_7d", {})
-
-    def metric_block(name: str, data: dict, desc: str, good_direction: str = "up"):
-        val = data.get("value", 0)
-        t = trend.get(name, {})
-        delta = t.get("delta", "N/A")
-        assessment = t.get("assessment", "unknown")
-        arrow = "↑" if assessment == "good" else "↓" if assessment == "bad" else "—"
-
-        lines.extend([
-            f"## {name}",
-            f"{desc}",
-            "",
-            f"**Value:** {val}  |  **7d trend:** {delta} {arrow} ({assessment})",
-            "",
-        ])
-
-        # Add key details
-        for k, v in data.items():
-            if k != "value" and k != "interpretation":
-                if isinstance(v, (int, float, str)):
-                    lines.append(f"- {k}: {v}")
-        lines.append("")
-
-    metric_block(
-        "knowledge_velocity",
-        metrics.get("knowledge_velocity", {}),
-        "New facts extracted per day. Higher = compounding loop working.",
-    )
-    metric_block(
-        "knowledge_coverage",
-        metrics.get("knowledge_coverage", {}),
-        "Percentage of domains/repos with 10+ facts. Measures breadth.",
-    )
-    metric_block(
-        "hit_rate",
-        metrics.get("hit_rate", {}),
-        "Percentage of sessions referencing bootstrapped knowledge.",
-    )
-    metric_block(
-        "error_recurrence",
-        metrics.get("error_recurrence", {}),
-        "Ratio of recurring errors. Lower = fleet learning from mistakes.",
-        good_direction="down",
-    )
-    metric_block(
-        "task_completion",
-        metrics.get("task_completion", {}),
-        "Percentage of sessions ending with successful completion.",
-    )
-    metric_block(
-        "first_try_success",
-        metrics.get("first_try_success", {}),
-        "Percentage of sessions completed without backtracking.",
-    )
-    metric_block(
-        "knowledge_age",
-        metrics.get("knowledge_age", {}),
-        "Freshness of knowledge store. 1.0 = all fresh, 0.0 = all stale.",
-        good_direction="up",
-    )
-
-    return "\n".join(lines)
-
-
-# ─── Snapshot Persistence ───────────────────────────────────────────────────────
-
-def load_snapshot(metrics_dir: Path) -> dict:
-    """Load most recent metrics snapshot for trend computation."""
-    snapshot_path = metrics_dir / "latest_snapshot.json"
-    if snapshot_path.exists():
-        with open(snapshot_path) as f:
-            return json.load(f)
-    return {}
-
-
-def save_snapshot(metrics_dir: Path, metrics: dict):
-    """Save current metrics as latest snapshot."""
-    metrics_dir.mkdir(parents=True, exist_ok=True)
-    snapshot_path = metrics_dir / "latest_snapshot.json"
-    with open(snapshot_path, "w") as f:
-        json.dump(metrics, f, indent=2)
-
-
-# ─── Main ───────────────────────────────────────────────────────────────────────
-
-def main():
-    parser = argparse.ArgumentParser(description="Compounding Intelligence Metrics")
-    parser.add_argument("--since", help="Start date (YYYY-MM-DD)")
-    parser.add_argument("--repo", help="Filter by repo/domain")
-    parser.add_argument("--format", choices=["json", "markdown"], default="json")
-    parser.add_argument("--knowledge-dir", type=Path, default=DEFAULT_KNOWLEDGE_DIR)
-    parser.add_argument("--db", type=Path, default=DEFAULT_DB_PATH)
-    parser.add_argument("--save-snapshot", action="store_true",
-                        help="Save current metrics as snapshot for trend tracking")
-    parser.add_argument("--metrics-dir", type=Path,
-                        default=Path(__file__).parent.parent / "metrics",
-                        help="Directory for snapshots and dashboard")
-    args = parser.parse_args()
-
-    # ── Load data ───────────────────────────────────────────────────────────
-    facts = load_facts(args.knowledge_dir)
-    yaml_counts = count_yaml_facts(args.knowledge_dir)
-
-    if args.repo:
-        facts = [f for f in facts if f.get("domain") == args.repo]
-
-    conn = open_db(args.db)
-    sessions = query_sessions(conn, since=args.since)
-    messages = query_messages(conn) if conn else []
-
-    if conn:
-        conn.close()
-
-    # ── Compute metrics ─────────────────────────────────────────────────────
-    velocity = compute_knowledge_velocity(facts, since=args.since)
-    coverage = compute_knowledge_coverage(facts, yaml_counts)
-    hit_rate = compute_hit_rate(sessions, messages, facts)
-    error_recurrence = compute_error_recurrence(messages)
-    task_completion = compute_task_completion(sessions)
-    first_try = compute_first_try_success(sessions)
-    age = compute_knowledge_age(facts)
-
-    # ── Compute trends ──────────────────────────────────────────────────────
-    previous = load_snapshot(args.metrics_dir)
-    trend = {
-        "knowledge_velocity": compute_trend(velocity, previous.get("knowledge_velocity", {})),
-        "knowledge_coverage": compute_trend(coverage, previous.get("knowledge_coverage", {})),
-        "hit_rate": compute_trend(hit_rate, previous.get("hit_rate", {})),
-        "error_recurrence": compute_trend(error_recurrence, previous.get("error_recurrence", {}),
-                                          "value"),
-        "task_completion": compute_trend(task_completion, previous.get("task_completion", {})),
-        "first_try_success": compute_trend(first_try, previous.get("first_try_success", {})),
-        "knowledge_age": compute_trend(age, previous.get("knowledge_age", {})),
-    }
-
-    # ── Assemble output ─────────────────────────────────────────────────────
-    now = datetime.now(timezone.utc).isoformat()
-    metrics = {
-        "generated_at": now,
-        "knowledge_velocity": velocity,
-        "knowledge_coverage": coverage,
-        "hit_rate": hit_rate,
-        "error_recurrence": error_recurrence,
-        "task_completion": task_completion,
-        "first_try_success": first_try,
-        "knowledge_age": age,
-        "trend_7d": trend,
-    }
-
-    if args.since:
-        metrics["since"] = args.since
-
-    # ── Save snapshot if requested ──────────────────────────────────────────
-    if args.save_snapshot:
-        save_snapshot(args.metrics_dir, metrics)
-        # Also write dashboard
-        dashboard_path = args.metrics_dir / "dashboard.md"
-        with open(dashboard_path, "w") as f:
-            f.write(format_markdown(metrics))
-
-    # ── Output ──────────────────────────────────────────────────────────────
-    if args.format == "json":
-        print(format_json(metrics))
-    else:
-        print(format_markdown(metrics))
-
-
-if __name__ == "__main__":
-    main()
--- a/scripts/test_bootstrapper.py
+++ b/scripts/test_bootstrapper.py
@@ -1,239 +0,0 @@
-#!/usr/bin/env python3
-"""
-Tests for bootstrapper.py — context assembly from knowledge store.
-"""
-
-import json
-import sys
-import tempfile
-from pathlib import Path
-
-# Add scripts dir to path for import
-sys.path.insert(0, str(Path(__file__).resolve().parent))
-
-from bootstrapper import (
-    build_bootstrap_context,
-    estimate_tokens,
-    filter_facts,
-    load_index,
-    sort_facts,
-    truncate_to_tokens,
-)
-
-
-def make_index(facts: list[dict], tmp_dir: Path) -> Path:
-    """Create a temporary index.json with given facts."""
-    index = {
-        "version": 1,
-        "last_updated": "2026-04-13T20:00:00Z",
-        "total_facts": len(facts),
-        "facts": facts,
-    }
-    path = tmp_dir / "index.json"
-    with open(path, "w") as f:
-        json.dump(index, f)
-    return path
-
-
-def test_empty_index():
-    """Empty knowledge store produces graceful output."""
-    with tempfile.TemporaryDirectory() as tmp:
-        tmp_dir = Path(tmp)
-        index_path = make_index([], tmp_dir)
-
-        # Create empty knowledge dirs
-        for sub in ["repos", "agents", "global"]:
-            (tmp_dir / sub).mkdir(exist_ok=True)
-
-        context = build_bootstrap_context(
-            repo="the-nexus", index_path=index_path
-        )
-        assert "No relevant knowledge found" in context
-        assert "Starting fresh" in context
-        print("PASS: empty_index")
-
-
-def test_filter_by_repo():
-    """Filter facts by repository."""
-    facts = [
-        {"fact": "A", "category": "fact", "repo": "the-nexus", "confidence": 0.9},
-        {"fact": "B", "category": "fact", "repo": "fleet-ops", "confidence": 0.8},
-        {"fact": "C", "category": "fact", "repo": "global", "confidence": 0.7},
-    ]
-    filtered = filter_facts(facts, repo="the-nexus", include_global=True)
-    texts = [f["fact"] for f in filtered]
-    assert "A" in texts
-    assert "B" not in texts
-    assert "C" in texts
-    print("PASS: filter_by_repo")
-
-
-def test_filter_by_agent():
-    """Filter facts by agent type."""
-    facts = [
-        {"fact": "A", "category": "pattern", "repo": "global", "agent": "mimo-sprint", "confidence": 0.8},
-        {"fact": "B", "category": "pattern", "repo": "global", "agent": "groq-fast", "confidence": 0.7},
-        {"fact": "C", "category": "fact", "repo": "global", "confidence": 0.9},
-    ]
-    filtered = filter_facts(facts, agent="mimo-sprint", include_global=True)
-    texts = [f["fact"] for f in filtered]
-    assert "A" in texts
-    assert "B" not in texts
-    assert "C" in texts  # global, no agent restriction
-    print("PASS: filter_by_agent")
-
-
-def test_no_global_flag():
-    """Excluding global facts works."""
-    facts = [
-        {"fact": "A", "category": "fact", "repo": "the-nexus", "confidence": 0.9},
-        {"fact": "B", "category": "fact", "repo": "global", "confidence": 0.8},
-    ]
-    filtered = filter_facts(facts, repo="the-nexus", include_global=False)
-    texts = [f["fact"] for f in filtered]
-    assert "A" in texts
-    assert "B" not in texts
-    print("PASS: no_global_flag")
-
-
-def test_sort_by_confidence():
-    """Facts sort by confidence descending."""
-    facts = [
-        {"fact": "low", "category": "fact", "repo": "global", "confidence": 0.3},
-        {"fact": "high", "category": "fact", "repo": "global", "confidence": 0.95},
-        {"fact": "mid", "category": "fact", "repo": "global", "confidence": 0.7},
-    ]
-    sorted_f = sort_facts(facts)
-    assert sorted_f[0]["fact"] == "high"
-    assert sorted_f[1]["fact"] == "mid"
-    assert sorted_f[2]["fact"] == "low"
-    print("PASS: sort_by_confidence")
-
-
-def test_sort_pitfalls_first():
-    """Pitfalls sort before facts at same confidence."""
-    facts = [
-        {"fact": "regular fact", "category": "fact", "repo": "global", "confidence": 0.8},
-        {"fact": "danger pitfall", "category": "pitfall", "repo": "global", "confidence": 0.8},
-    ]
-    sorted_f = sort_facts(facts)
-    assert sorted_f[0]["category"] == "pitfall"
-    print("PASS: sort_pitfalls_first")
-
-
-def test_truncate_to_tokens():
-    """Truncation cuts at line boundary."""
-    text = "line1\nline2\nline3\nline4\nline5\n"
-    truncated = truncate_to_tokens(text, max_tokens=2)  # ~8 chars
-    assert "line1" in truncated
-    assert "truncated" in truncated.lower()
-    print("PASS: truncate_to_tokens")
-
-
-def test_estimate_tokens():
-    """Token estimation is reasonable."""
-    text = "a" * 400
-    tokens = estimate_tokens(text)
-    assert 90 <= tokens <= 110  # ~100 tokens
-    print("PASS: estimate_tokens")
-
-
-def test_build_full_context():
-    """Full context with facts renders correctly."""
-    facts = [
-        {"fact": "API merges fail with 405", "category": "pitfall", "repo": "the-nexus", "confidence": 0.95},
-        {"fact": "Has 50+ open PRs", "category": "fact", "repo": "the-nexus", "confidence": 0.9},
-        {"fact": "Token at ~/.config/gitea/token", "category": "tool-quirk", "repo": "global", "confidence": 0.9},
-        {"fact": "Check git remote -v first", "category": "pattern", "repo": "global", "confidence": 0.8},
-    ]
-
-    with tempfile.TemporaryDirectory() as tmp:
-        tmp_dir = Path(tmp)
-        index_path = make_index(facts, tmp_dir)
-
-        # Create knowledge dirs
-        for sub in ["repos", "agents", "global"]:
-            (tmp_dir / sub).mkdir(exist_ok=True)
-
-        context = build_bootstrap_context(
-            repo="the-nexus",
-            agent="mimo-sprint",
-            include_global=True,
-            index_path=index_path,
-        )
-
-        assert "What You Know" in context
-        assert "PITFALLS" in context
-        assert "API merges fail with 405" in context
-        assert "the-nexus" in context
-        assert "Token at" in context  # global fact included
-        print("PASS: build_full_context")
-
-
-def test_max_tokens_respected():
-    """Output respects max_tokens limit."""
-    # Generate lots of facts
-    facts = [
-        {"fact": f"Fact number {i} with some detail about things", "category": "fact", "repo": "global", "confidence": 0.8}
-        for i in range(100)
-    ]
-
-    with tempfile.TemporaryDirectory() as tmp:
-        tmp_dir = Path(tmp)
-        index_path = make_index(facts, tmp_dir)
-        for sub in ["repos", "agents", "global"]:
-            (tmp_dir / sub).mkdir(exist_ok=True)
-
-        context = build_bootstrap_context(
-            repo=None,
-            max_tokens=500,
-            index_path=index_path,
-        )
-
-        actual_tokens = estimate_tokens(context)
-        # Allow 10% overshoot since we cut at line boundaries
-        assert actual_tokens <= 550, f"Expected ~500 tokens, got {actual_tokens}"
-        print(f"PASS: max_tokens_respected (got {actual_tokens} tokens)")
-
-
-def test_missing_index_graceful():
-    """Missing index.json doesn't crash."""
-    with tempfile.TemporaryDirectory() as tmp:
-        tmp_dir = Path(tmp)
-        # Don't create index.json
-        for sub in ["repos", "agents", "global"]:
-            (tmp_dir / sub).mkdir(exist_ok=True)
-
-        fake_index = tmp_dir / "nonexistent.json"
-        context = build_bootstrap_context(repo="anything", index_path=fake_index)
-        assert "No relevant knowledge found" in context
-        print("PASS: missing_index_graceful")
-
-
-if __name__ == "__main__":
-    tests = [
-        test_empty_index,
-        test_filter_by_repo,
-        test_filter_by_agent,
-        test_no_global_flag,
-        test_sort_by_confidence,
-        test_sort_pitfalls_first,
-        test_truncate_to_tokens,
-        test_estimate_tokens,
-        test_build_full_context,
-        test_max_tokens_respected,
-        test_missing_index_graceful,
-    ]
-
-    passed = 0
-    failed = 0
-    for test in tests:
-        try:
-            test()
-            passed += 1
-        except Exception as e:
-            print(f"FAIL: {test.__name__} — {e}")
-            failed += 1
-
-    print(f"\n{passed} passed, {failed} failed")
-    sys.exit(0 if failed == 0 else 1)
--- a/scripts/test_gitea_issue_parser.py
+++ b/scripts/test_gitea_issue_parser.py
@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+"""Tests for gitea_issue_parser."""
+
+import json
+import sys
+import os
+
+sys.path.insert(0, os.path.dirname(__file__))
+from gitea_issue_parser import parse_issue_body
+
+
+def test_basic_structure():
+    body = """## Context
+This is the background.
+
+## Acceptance Criteria
+- [ ] First criterion
+- [x] Second criterion (already done)
+- [ ] Third criterion
+
+## Labels
+`pipeline`, `extraction`
+"""
+    result = parse_issue_body(body, "Test Issue", ["pipeline", "extraction"])
+    assert result["title"] == "Test Issue"
+    assert "background" in result["context"].lower()
+    assert len(result["criteria"]) == 3
+    assert "First criterion" in result["criteria"]
+    assert result["labels"] == ["pipeline", "extraction"]
+    print("PASS: test_basic_structure")
+
+
+def test_epic_ref():
+    body = "Closes #645\n\nSome description."
+    result = parse_issue_body(body, "feat: thing (#688)")
+    assert result["epic_ref"] == "#645"
+    print("PASS: test_epic_ref")
+
+
+def test_epic_ref_from_title():
+    body = "Some description without close ref."
+    result = parse_issue_body(body, "feat: scene descriptions (#645)")
+    assert result["epic_ref"] == "#645"
+    print("PASS: test_epic_ref_from_title")
+
+
+def test_no_checkboxes():
+    body = """## Requirements
+1. First thing
+2. Second thing
+3. Third thing
+"""
+    result = parse_issue_body(body)
+    assert len(result["criteria"]) == 3
+    print("PASS: test_no_checkboxes")
+
+
+def test_empty_body():
+    result = parse_issue_body("", "Empty Issue")
+    assert result["title"] == "Empty Issue"
+    assert result["criteria"] == []
+    assert result["context"] == ""
+    print("PASS: test_empty_body")
+
+
+def test_real_issue_format():
+    body = """Closes #681
+
+## Changes
+
+Add `#!/usr/bin/env python3` shebang to 6 Python scripts.
+
+## Verification
+
+All 6 files confirmed missing shebangs before fix.
+
+## Impact
+
+Scripts can now be executed directly.
+"""
+    result = parse_issue_body(body, "fix: add python3 shebangs (#685)")
+    assert result["epic_ref"] == "#681"
+    assert "shebang" in result["context"].lower()
+    print("PASS: test_real_issue_format")
+
+
+def test_all_sections_captured():
+    body = """## Context
+Background info.
+
+## Acceptance Criteria
+- [ ] Do thing
+
+## Labels
+`test`
+"""
+    result = parse_issue_body(body)
+    assert "context" in result["sections"]
+    assert "acceptance criteria" in result["sections"]
+    print("PASS: test_all_sections_captured")
+
+
+if __name__ == "__main__":
+    test_basic_structure()
+    test_epic_ref()
+    test_epic_ref_from_title()
+    test_no_checkboxes()
+    test_empty_body()
+    test_real_issue_format()
+    test_all_sections_captured()
+    print("\nAll tests passed.")
--- a/scripts/test_harvest_prompt.py
+++ b/scripts/test_harvest_prompt.py
@@ -1,129 +1,41 @@
 #!/usr/bin/env python3
 """
-Test harness for knowledge extraction prompt.
-Validates output structure, content quality, and hallucination resistance.
-
-Usage:
-    python3 scripts/test_harvest_prompt.py                    # Run all tests
-    python3 scripts/test_harvest_prompt.py --transcript FILE  # Test against a real transcript
-    python3 scripts/test_harvest_prompt.py --validate FILE    # Validate an existing extraction JSON
+Test script for knowledge extraction prompt.
+Validates that the prompt produces consistent, structured output.
 """

 import json
 import sys
-import argparse
 from pathlib import Path

-VALID_CATEGORIES = {"fact", "pitfall", "pattern", "tool-quirk", "question"}
-REQUIRED_FIELDS = {"fact", "category", "repo", "confidence", "evidence"}
-REQUIRED_META = {"session_outcome", "tools_used", "repos_touched", "error_count", "knowledge_count"}
-
-
-def validate_knowledge_item(item, idx):
-    """Validate a single knowledge item. Returns list of errors."""
-    errors = []
-    if not isinstance(item, dict):
-        return [f"Item {idx}: not a dict"]
-    for field in REQUIRED_FIELDS:
+def validate_knowledge_item(item):
+    """Validate a single knowledge item."""
+    required_fields = ["fact", "category", "repo", "confidence"]
+    for field in required_fields:
        if field not in item:
-            errors.append(f"Item {idx}: missing field '{field}'")
-    if not isinstance(item.get("fact", ""), str) or len(item.get("fact", "").strip()) == 0:
-        errors.append(f"Item {idx}: fact must be a non-empty string")
-    if item.get("category") not in VALID_CATEGORIES:
-        errors.append(f"Item {idx}: invalid category '{item.get('category')}'")
-    if not isinstance(item.get("repo", ""), str) or len(item.get("repo", "").strip()) == 0:
-        errors.append(f"Item {idx}: repo must be a non-empty string")
-    conf = item.get("confidence")
-    if not isinstance(conf, (int, float)) or not (0.0 <= conf <= 1.0):
-        errors.append(f"Item {idx}: confidence must be a number 0.0-1.0, got {conf}")
-    if not isinstance(item.get("evidence", ""), str) or len(item.get("evidence", "").strip()) == 0:
-        errors.append(f"Item {idx}: evidence must be a non-empty string (hallucination check)")
-    return errors
+            return False, f"Missing field: {field}"
+    
+    if not isinstance(item["fact"], str) or len(item["fact"].strip()) == 0:
+        return False, "Fact must be a non-empty string"
+    
+    valid_categories = ["fact", "pitfall", "pattern", "tool-quirk", "question"]
+    if item["category"] not in valid_categories:
+        return False, f"Invalid category: {item['category']}"
+    
+    if not isinstance(item["repo"], str):
+        return False, "Repo must be a string"
+    
+    if not isinstance(item["confidence"], (int, float)):
+        return False, "Confidence must be a number"
+    
+    if not (0.0 <= item["confidence"] <= 1.0):
+        return False, "Confidence must be between 0.0 and 1.0"
+    
+    return True, "Valid"

-
-def validate_extraction(data):
-    """Validate a full extraction result. Returns (is_valid, errors, warnings)."""
-    errors = []
-    warnings = []
-
-    if not isinstance(data, dict):
-        return False, ["Root is not a JSON object"], []
-
-    if "knowledge" not in data:
-        return False, ["Missing 'knowledge' array"], []
-
-    if not isinstance(data["knowledge"], list):
-        return False, ["'knowledge' is not an array"], []
-
-    for i, item in enumerate(data["knowledge"]):
-        errors.extend(validate_knowledge_item(item, i))
-
-    # Meta block validation
-    if "meta" not in data:
-        warnings.append("Missing 'meta' block (session_outcome, tools_used, etc.)")
-    else:
-        meta = data["meta"]
-        for field in REQUIRED_META:
-            if field not in meta:
-                warnings.append(f"Meta missing field '{field}'")
-
-    # Quality checks
-    facts = data["knowledge"]
-    if len(facts) == 0:
-        warnings.append("No knowledge extracted (empty session or extraction failure)")
-
-    # Check for near-duplicate facts
-    seen_facts = set()
-    for item in facts:
-        normalized = item.get("fact", "").lower().strip()[:80]
-        if normalized in seen_facts:
-            warnings.append(f"Duplicate fact detected: '{normalized[:50]}...'")
-        seen_facts.add(normalized)
-
-    # Check confidence distribution
-    confidences = [item.get("confidence", 0) for item in facts]
-    if confidences:
-        avg_conf = sum(confidences) / len(confidences)
-        if avg_conf > 0.9:
-            warnings.append(f"Average confidence {avg_conf:.2f} is suspiciously high (possible hallucination)")
-        if avg_conf < 0.4:
-            warnings.append(f"Average confidence {avg_conf:.2f} is very low (extraction may be too cautious)")
-
-    return len(errors) == 0, errors, warnings
-
-
-def validate_transcript_coverage(data, transcript):
-    """
-    Check that extracted facts are actually supported by the transcript.
-    This is a heuristic — checks that key terms from facts appear in transcript.
-    Returns list of potential hallucinations.
-    """
-    hallucinations = []
-    transcript_lower = transcript.lower()
-
-    for item in data.get("knowledge", []):
-        fact = item.get("fact", "")
-        evidence = item.get("evidence", "")
-
-        # Check if evidence string appears in transcript
-        if evidence and evidence.lower() not in transcript_lower:
-            # Partial match — check if key terms are present
-            evidence_words = set(evidence.lower().split())
-            transcript_words = set(transcript_lower.split())
-            overlap = evidence_words & transcript_words
-            if len(overlap) < min(3, len(evidence_words) * 0.3):
-                hallucinations.append({
-                    "fact": fact[:80],
-                    "evidence": evidence[:80],
-                    "issue": "Evidence not found in transcript — possible hallucination"
-                })
-
-    return hallucinations
-
-
-# --- Test transcripts ---
-
-SAMPLE_TRANSCRIPT_SUCCESS = """
+def test_sample_transcript():
+    """Test with a sample transcript."""
+    sample_transcript = """
 User: Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence
 Agent: Trying git clone... Error: 401 Unauthorized
 Agent: Checking for token... Found in ~/.config/gitea/token
@@ -132,253 +44,30 @@ Agent: Clone successful with token authentication
 Agent: Now examining the repo structure...
 Agent: Found knowledge/index.json with 0 facts
 Agent: Creating harvest-prompt.md in templates/
-Agent: Done. Files created: templates/harvest-prompt.md, scripts/test_harvest_prompt.py
 """
-
-SAMPLE_TRANSCRIPT_FAILURE = """
-User: Deploy the cron jobs to production
-Agent: Connecting to VPS... SSH timeout after 30s
-Agent: Retrying with verbose output... Connection refused on port 22
-Agent: Checking firewall rules... iptables shows port 22 is open
-Agent: Checking sshd config... sshd is not running
-Agent: Attempting to start sshd... systemctl start sshd failed: unit not found
-Agent: ERROR: OpenSSH server not installed on this VPS
-Agent: Cannot proceed without SSH access. Deployment blocked.
-"""
-
-SAMPLE_TRANSCRIPT_API_QUIRK = """
-User: List all open issues in hermes-agent
-Agent: Querying Gitea API... endpoint: /repos/Timmy_Foundation/hermes-agent/issues?state=open&limit=50
-Agent: Response: 0 items. That's odd.
-Agent: Trying without state filter... endpoint: /repos/Timmy_Foundation/hermes-agent/issues?limit=50
-Agent: Response: 50 items returned, but all have pull_request field. These are PRs, not issues.
-Agent: Gitea issues API returns PRs alongside issues. Must filter by presence of pull_request key.
-Agent: Also discovered: state=open parameter returns empty when used with limit=50, but works with limit=5.
-Agent: This appears to be a Gitea API quirk — pagination interacts with state filter unexpectedly.
-Agent: Workaround: fetch without state filter, then filter client-side for state=='open' and 'pull_request' not in item.
-"""
-
-
-def run_tests():
-    """Run the built-in test suite."""
-    tests_passed = 0
-    tests_failed = 0
-
-    print("=" * 60)
-    print("KNOWLEDGE EXTRACTION PROMPT — TEST SUITE")
-    print("=" * 60)
-
-    # Test 1: Prompt file exists and is under 2k tokens (~8k chars)
-    print("\n[Test 1] Prompt file size constraint")
-    prompt_path = Path("templates/harvest-prompt.md")
-    if not prompt_path.exists():
-        print("  FAIL: harvest-prompt.md not found")
-        tests_failed += 1
-    else:
-        size = prompt_path.stat().st_size
-        # Rough token estimate: ~4 chars per token
-        est_tokens = size / 4
-        print(f"  Prompt size: {size} bytes (~{est_tokens:.0f} tokens)")
-        if est_tokens > 2000:
-            print(f"  WARN: Prompt exceeds ~1500 tokens (target: ~1000)")
-        else:
-            print(f"  PASS: Within token budget")
-        tests_passed += 1
-
-    # Test 2: Validate a well-formed extraction
-    print("\n[Test 2] Valid extraction passes validation")
-    valid_extraction = {
-        "knowledge": [
-            {
-                "fact": "Gitea auth token is at ~/.config/gitea/token",
-                "category": "tool-quirk",
-                "repo": "global",
-                "confidence": 0.9,
-                "evidence": "Found in ~/.config/gitea/token"
-            },
-            {
-                "fact": "Clone fails with 401 when no token is provided",
-                "category": "pitfall",
-                "repo": "compounding-intelligence",
-                "confidence": 0.9,
-                "evidence": "Error: 401 Unauthorized"
-            }
-        ],
-        "meta": {
-            "session_outcome": "success",
-            "tools_used": ["git"],
-            "repos_touched": ["compounding-intelligence"],
-            "error_count": 1,
-            "knowledge_count": 2
-        }
-    }
-    is_valid, errors, warnings = validate_extraction(valid_extraction)
-    if is_valid:
-        print(f"  PASS: Valid extraction accepted ({len(warnings)} warnings)")
-        tests_passed += 1
-    else:
-        print(f"  FAIL: Valid extraction rejected: {errors}")
-        tests_failed += 1
-
-    # Test 3: Reject missing fields
-    print("\n[Test 3] Missing fields are rejected")
-    bad_extraction = {
-        "knowledge": [
-            {"fact": "Something learned", "category": "fact"}  # Missing repo, confidence, evidence
-        ]
-    }
-    is_valid, errors, warnings = validate_extraction(bad_extraction)
-    if not is_valid:
-        print(f"  PASS: Rejected with {len(errors)} errors")
-        tests_passed += 1
-    else:
-        print(f"  FAIL: Should have rejected missing fields")
-        tests_failed += 1
-
-    # Test 4: Reject invalid category
-    print("\n[Test 4] Invalid category is rejected")
-    bad_cat = {
-        "knowledge": [
-            {"fact": "Test", "category": "discovery", "repo": "x", "confidence": 0.8, "evidence": "test"}
-        ]
-    }
-    is_valid, errors, warnings = validate_extraction(bad_cat)
-    if not is_valid and any("category" in e for e in errors):
-        print(f"  PASS: Invalid category 'discovery' rejected")
-        tests_passed += 1
-    else:
-        print(f"  FAIL: Should have rejected invalid category")
-        tests_failed += 1
-
-    # Test 5: Detect near-duplicates
-    print("\n[Test 5] Duplicate detection")
-    dup_extraction = {
-        "knowledge": [
-            {"fact": "Token is at ~/.config/gitea/token", "category": "fact", "repo": "x", "confidence": 0.9, "evidence": "a"},
-            {"fact": "Token is at ~/.config/gitea/token", "category": "fact", "repo": "x", "confidence": 0.9, "evidence": "b"}
-        ],
-        "meta": {"session_outcome": "success", "tools_used": [], "repos_touched": [], "error_count": 0, "knowledge_count": 2}
-    }
-    is_valid, errors, warnings = validate_extraction(dup_extraction)
-    if any("Duplicate" in w for w in warnings):
-        print(f"  PASS: Duplicate detected")
-        tests_passed += 1
-    else:
-        print(f"  FAIL: Should have detected duplicate")
-        tests_failed += 1
-
-    # Test 6: Hallucination check against transcript
-    print("\n[Test 6] Hallucination detection")
-    hallucinated = {
-        "knowledge": [
-            {
-                "fact": "Database port is 5433",
-                "category": "fact",
-                "repo": "x",
-                "confidence": 0.9,
-                "evidence": "PostgreSQL listening on port 5433"
-            }
-        ],
-        "meta": {"session_outcome": "success", "tools_used": [], "repos_touched": [], "error_count": 0, "knowledge_count": 1}
-    }
-    hallucinations = validate_transcript_coverage(hallucinated, SAMPLE_TRANSCRIPT_SUCCESS)
-    if hallucinations:
-        print(f"  PASS: Hallucination detected ({len(hallucinations)} items)")
-        tests_passed += 1
-    else:
-        print(f"  FAIL: Should have detected hallucinated evidence")
-        tests_failed += 1
-
-    # Test 7: Failed session should extract pitfalls
-    print("\n[Test 7] Failed session extraction shape")
-    failed_extraction = {
-        "knowledge": [
-            {
-                "fact": "SSH server not installed on target VPS",
-                "category": "pitfall",
-                "repo": "global",
-                "confidence": 0.9,
-                "evidence": "ERROR: OpenSSH server not installed on this VPS"
-            },
-            {
-                "fact": "VPS blocks deployment without SSH access",
-                "category": "question",
-                "repo": "global",
-                "confidence": 0.7,
-                "evidence": "Cannot proceed without SSH access. Deployment blocked."
-            }
-        ],
-        "meta": {
-            "session_outcome": "failed",
-            "tools_used": ["ssh", "systemctl"],
-            "repos_touched": [],
-            "error_count": 3,
-            "knowledge_count": 2
-        }
-    }
-    is_valid, errors, warnings = validate_extraction(failed_extraction)
-    if is_valid:
-        categories = [item["category"] for item in failed_extraction["knowledge"]]
-        if "pitfall" in categories:
-            print(f"  PASS: Failed session extracted {len(categories)} items including pitfalls")
-            tests_passed += 1
-        else:
-            print(f"  FAIL: Failed session should extract pitfalls")
-            tests_failed += 1
-    else:
-        print(f"  FAIL: {errors}")
-        tests_failed += 1
-
-    # Test 8: Empty extraction is warned
-    print("\n[Test 8] Empty extraction warning")
-    empty = {"knowledge": [], "meta": {"session_outcome": "success", "tools_used": [], "repos_touched": [], "error_count": 0, "knowledge_count": 0}}
-    is_valid, errors, warnings = validate_extraction(empty)
-    if any("No knowledge" in w for w in warnings):
-        print(f"  PASS: Empty extraction warned")
-        tests_passed += 1
-    else:
-        print(f"  FAIL: Should warn on empty extraction")
-        tests_failed += 1
-
-    # Summary
-    print(f"\n{'=' * 60}")
-    print(f"Results: {tests_passed} passed, {tests_failed} failed")
-    print(f"{'=' * 60}")
-    return tests_failed == 0
-
-
-def validate_file(filepath):
-    """Validate an existing extraction JSON file."""
-    path = Path(filepath)
-    if not path.exists():
-        print(f"ERROR: {filepath} not found")
-        return False
-
-    data = json.loads(path.read_text())
-    is_valid, errors, warnings = validate_extraction(data)
-
-    print(f"Validation of {filepath}:")
-    print(f"  Knowledge items: {len(data.get('knowledge', []))}")
-    print(f"  Errors: {len(errors)}")
-    print(f"  Warnings: {len(warnings)}")
-
-    for e in errors:
-        print(f"  ERROR: {e}")
-    for w in warnings:
-        print(f"  WARN: {w}")
-
-    return is_valid
-
+    
+    # This would be replaced with actual prompt execution
+    print("Sample transcript processed")
+    print("Expected categories: fact, pitfall, pattern, tool-quirk, question")
+    return True

 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Test knowledge extraction prompt")
-    parser.add_argument("--validate", help="Validate an existing extraction JSON file")
-    parser.add_argument("--transcript", help="Test against a real transcript file (informational)")
-    args = parser.parse_args()
-
-    if args.validate:
-        success = validate_file(args.validate)
-        sys.exit(0 if success else 1)
-    else:
-        success = run_tests()
-        sys.exit(0 if success else 1)
+    print("Testing knowledge extraction prompt...")
+    
+    # Test 1: Validate prompt file exists
+    prompt_path = Path("templates/harvest-prompt.md")
+    if not prompt_path.exists():
+        print("ERROR: harvest-prompt.md not found")
+        sys.exit(1)
+    
+    print(f"OK: Prompt file exists: {prompt_path}")
+    
+    # Test 2: Check prompt size
+    prompt_size = prompt_path.stat().st_size
+    print(f"OK: Prompt size: {prompt_size} bytes")
+    
+    # Test 3: Test sample transcript processing
+    if test_sample_transcript():
+        print("OK: Sample transcript test passed")
+    
+    print("\nAll tests passed!")
--- a/scripts/test_harvest_prompt_comprehensive.py
+++ b/scripts/test_harvest_prompt_comprehensive.py
@@ -0,0 +1,212 @@
+#!/usr/bin/env python3
+"""
+Comprehensive test script for knowledge extraction prompt.
+Validates prompt structure, requirements, and consistency.
+"""
+
+import json
+import re
+from pathlib import Path
+
+def test_prompt_structure():
+    """Test that the prompt has the required structure."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    if not prompt_path.exists():
+        return False, "harvest-prompt.md not found"
+    
+    content = prompt_path.read_text()
+    
+    # Check for required sections
+    required_sections = [
+        "System Prompt",
+        "Instructions", 
+        "Categories",
+        "Output Format",
+        "Confidence Scoring",
+        "Constraints",
+        "Example"
+    ]
+    
+    for section in required_sections:
+        if section.lower() not in content.lower():
+            return False, f"Missing required section: {section}"
+    
+    # Check for required categories
+    required_categories = ["fact", "pitfall", "pattern", "tool-quirk", "question"]
+    for category in required_categories:
+        if category not in content:
+            return False, f"Missing required category: {category}"
+    
+    # Check for required output fields
+    required_fields = ["fact", "category", "repo", "confidence"]
+    for field in required_fields:
+        if field not in content:
+            return False, f"Missing required output field: {field}"
+    
+    # Check prompt size (should be ~1k tokens, roughly 4k chars)
+    if len(content) > 5000:
+        return False, f"Prompt too large: {len(content)} chars (max ~5000)"
+    
+    if len(content) < 1000:
+        return False, f"Prompt too small: {len(content)} chars (min ~1000)"
+    
+    return True, "Prompt structure is valid"
+
+def test_confidence_scoring():
+    """Test that confidence scoring is properly defined."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    content = prompt_path.read_text()
+    
+    # Check for confidence scale definitions
+    confidence_levels = [
+        ("0.9-1.0", "explicitly stated"),
+        ("0.7-0.8", "clearly implied"),
+        ("0.5-0.6", "suggested"),
+        ("0.3-0.4", "inferred"),
+        ("0.1-0.2", "speculative")
+    ]
+    
+    for level, description in confidence_levels:
+        if level not in content:
+            return False, f"Missing confidence level: {level}"
+        if description.lower() not in content.lower():
+            return False, f"Missing confidence description: {description}"
+    
+    return True, "Confidence scoring is properly defined"
+
+def test_example_quality():
+    """Test that examples are clear and complete."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    content = prompt_path.read_text()
+    
+    # Check for example input/output
+    if "example" not in content.lower():
+        return False, "No examples provided"
+    
+    # Check that example includes all categories
+    example_section = content[content.lower().find("example"):]
+    
+    # Look for JSON example
+    json_match = re.search(r'\{[\s\S]*"knowledge"[\s\S]*\}', example_section)
+    if not json_match:
+        return False, "No JSON example found"
+    
+    example_json = json_match.group(0)
+    
+    # Check for all categories in example
+    for category in ["fact", "pitfall", "pattern", "tool-quirk", "question"]:
+        if category not in example_json:
+            return False, f"Example missing category: {category}"
+    
+    return True, "Examples are clear and complete"
+
+def test_constraint_coverage():
+    """Test that constraints cover all requirements."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    content = prompt_path.read_text()
+    
+    required_constraints = [
+        "No hallucination",
+        "only extract",
+        "explicitly",
+        "partial",
+        "failed sessions",
+        "1k tokens"
+    ]
+    
+    for constraint in required_constraints:
+        if constraint.lower() not in content.lower():
+            return False, f"Missing constraint: {constraint}"
+    
+    return True, "Constraints cover all requirements"
+
+def test_test_sessions():
+    """Test that test sessions exist and are valid."""
+    test_sessions_dir = Path("test_sessions")
+    if not test_sessions_dir.exists():
+        return False, "test_sessions directory not found"
+    
+    session_files = list(test_sessions_dir.glob("*.jsonl"))
+    if len(session_files) < 5:
+        return False, f"Only {len(session_files)} test sessions found, need 5"
+    
+    # Check each session file
+    for session_file in session_files:
+        content = session_file.read_text()
+        lines = content.strip().split("\n")
+        
+        # Check that each line is valid JSON
+        for i, line in enumerate(lines, 1):
+            try:
+                json.loads(line)
+            except json.JSONDecodeError as e:
+                return False, f"Invalid JSON in {session_file.name}, line {i}: {e}"
+    
+    return True, f"Found {len(session_files)} valid test sessions"
+
+def run_all_tests():
+    """Run all tests and return results."""
+    tests = [
+        ("Prompt Structure", test_prompt_structure),
+        ("Confidence Scoring", test_confidence_scoring),
+        ("Example Quality", test_example_quality),
+        ("Constraint Coverage", test_constraint_coverage),
+        ("Test Sessions", test_test_sessions)
+    ]
+    
+    results = []
+    all_passed = True
+    
+    for test_name, test_func in tests:
+        try:
+            passed, message = test_func()
+            results.append({
+                "test": test_name,
+                "passed": passed,
+                "message": message
+            })
+            if not passed:
+                all_passed = False
+        except Exception as e:
+            results.append({
+                "test": test_name,
+                "passed": False,
+                "message": f"Error: {str(e)}"
+            })
+            all_passed = False
+    
+    # Print results
+    print("=" * 60)
+    print("HARVEST PROMPT TEST RESULTS")
+    print("=" * 60)
+    
+    for result in results:
+        status = "✓ PASS" if result["passed"] else "✗ FAIL"
+        print(f"{status}: {result['test']}")
+        print(f"  {result['message']}")
+        print()
+    
+    print("=" * 60)
+    if all_passed:
+        print("ALL TESTS PASSED!")
+    else:
+        print("SOME TESTS FAILED!")
+    print("=" * 60)
+    
+    return all_passed, results
+
+if __name__ == "__main__":
+    all_passed, results = run_all_tests()
+    
+    # Save results to file
+    with open("test_results.json", "w") as f:
+        json.dump({
+            "all_passed": all_passed,
+            "results": results,
+            "timestamp": "2026-04-14T19:05:00Z"
+        }, f, indent=2)
+    
+    print(f"Results saved to test_results.json")
+    
+    # Exit with appropriate code
+    exit(0 if all_passed else 1)
--- a/scripts/validate_knowledge.py
+++ b/scripts/validate_knowledge.py
@@ -1,155 +0,0 @@
-#!/usr/bin/env python3
-"""
-Validate knowledge files and index.json against the schema.
-
-Usage:
-    python scripts/validate_knowledge.py [--fix]
-
-Without --fix: reports errors and exits non-zero if any found.
-With --fix: auto-generates missing IDs and updates index.json.
-"""
-
-import json
-import sys
-import os
-from pathlib import Path
-from datetime import datetime
-
-VALID_CATEGORIES = {"fact", "pitfall", "pattern", "tool-quirk", "question"}
-REQUIRED_FACT_FIELDS = {"id", "fact", "category", "domain", "confidence"}
-MAX_FACT_LENGTH = 280
-
-
-def validate_fact(fact: dict, source: str = "") -> list[str]:
-    """Validate a single fact dict. Returns list of errors."""
-    errors = []
-
-    for field in REQUIRED_FACT_FIELDS:
-        if field not in fact:
-            errors.append(f"{source}: missing required field '{field}'")
-
-    if "fact" in fact:
-        if not isinstance(fact["fact"], str) or len(fact["fact"].strip()) == 0:
-            errors.append(f"{source}: 'fact' must be non-empty string")
-        elif len(fact["fact"]) > MAX_FACT_LENGTH:
-            errors.append(f"{source}: 'fact' exceeds {MAX_FACT_LENGTH} chars ({len(fact['fact'])})")
-
-    if "category" in fact and fact["category"] not in VALID_CATEGORIES:
-        errors.append(f"{source}: invalid category '{fact['category']}' — must be one of {VALID_CATEGORIES}")
-
-    if "confidence" in fact:
-        if not isinstance(fact["confidence"], (int, float)):
-            errors.append(f"{source}: 'confidence' must be a number")
-        elif not (0.0 <= fact["confidence"] <= 1.0):
-            errors.append(f"{source}: 'confidence' must be 0.0–1.0, got {fact['confidence']}")
-
-    if "id" in fact:
-        parts = fact["id"].split(":")
-        if len(parts) != 3:
-            errors.append(f"{source}: 'id' must be domain:category:sequence, got '{fact['id']}'")
-        elif parts[1] not in VALID_CATEGORIES:
-            errors.append(f"{source}: id category '{parts[1]}' not in {VALID_CATEGORIES}")
-
-    if "tags" in fact:
-        if not isinstance(fact["tags"], list):
-            errors.append(f"{source}: 'tags' must be a list")
-        else:
-            for tag in fact["tags"]:
-                if not isinstance(tag, str) or not tag.replace("-", "").replace("_", "").isalnum():
-                    errors.append(f"{source}: tag '{tag}' must be lowercase alphanumeric+hyphens")
-
-    return errors
-
-
-def validate_index(index_path: Path) -> list[str]:
-    """Validate index.json."""
-    errors = []
-
-    if not index_path.exists():
-        return [f"index.json not found at {index_path}"]
-
-    try:
-        with open(index_path) as f:
-            data = json.load(f)
-    except json.JSONDecodeError as e:
-        return [f"index.json: invalid JSON — {e}"]
-
-    if "version" not in data:
-        errors.append("index.json: missing 'version' field")
-    if "facts" not in data:
-        errors.append("index.json: missing 'facts' field")
-    elif not isinstance(data["facts"], list):
-        errors.append("index.json: 'facts' must be a list")
-
-    seen_ids = set()
-    for i, fact in enumerate(data.get("facts", [])):
-        fact_errors = validate_fact(fact, source=f"index.json facts[{i}]")
-        errors.extend(fact_errors)
-
-        if "id" in fact:
-            if fact["id"] in seen_ids:
-                errors.append(f"index.json: duplicate id '{fact['id']}'")
-            seen_ids.add(fact["id"])
-
-    return errors
-
-
-def validate_yaml_facts(facts: list[dict], source: str) -> list[str]:
-    """Validate facts extracted from a YAML file."""
-    errors = []
-    seen_ids = set()
-
-    for i, fact in enumerate(facts):
-        fact_errors = validate_fact(fact, source=f"{source}[{i}]")
-        errors.extend(fact_errors)
-
-        if "id" in fact:
-            if fact["id"] in seen_ids:
-                errors.append(f"{source}: duplicate id '{fact['id']}'")
-            seen_ids.add(fact["id"])
-
-    return errors
-
-
-def main():
-    fix_mode = "--fix" in sys.argv
-    repo_root = Path(__file__).parent.parent
-    knowledge_dir = repo_root / "knowledge"
-    index_path = knowledge_dir / "index.json"
-
-    all_errors = []
-
-    # Validate index.json
-    index_errors = validate_index(index_path)
-    all_errors.extend(index_errors)
-
-    # Validate YAML files (basic existence check — full YAML parsing requires pyyaml)
-    yaml_dirs = ["global", "repos", "agents"]
-    for dir_name in yaml_dirs:
-        dir_path = knowledge_dir / dir_name
-        if not dir_path.exists():
-            all_errors.append(f"knowledge/{dir_name}/ directory not found")
-
-    # Report
-    if all_errors:
-        print(f"VALIDATION FAILED — {len(all_errors)} error(s):\n")
-        for err in all_errors:
-            print(f"  ✗ {err}")
-        sys.exit(1)
-    else:
-        # Count facts
-        try:
-            with open(index_path) as f:
-                data = json.load(f)
-            fact_count = len(data.get("facts", []))
-        except:
-            fact_count = 0
-
-        print(f"VALIDATION PASSED")
-        print(f"  index.json: {fact_count} facts")
-        print(f"  schema: v1")
-        sys.exit(0)
-
-
-if __name__ == "__main__":
-    main()
--- a/templates/harvest-prompt.md
+++ b/templates/harvest-prompt.md
@@ -2,107 +2,98 @@

 ## System Prompt

-You are a knowledge extraction engine. You read session transcripts and output ONLY structured JSON. You never infer. You never assume. You extract only what the transcript explicitly states.
+You are a knowledge extraction engine. Your task is to analyze a session transcript and extract durable knowledge that will help future sessions be more efficient.

-## Prompt
+## Instructions

+Read the session transcript carefully. Extract ONLY information that is explicitly stated in the transcript. Do NOT infer, assume, or hallucinate information.
+
+### Categories
+
+Extract knowledge into these categories:
+
+1. **fact**: Concrete, verifiable information learned (e.g., "Repository X has 5 files", "API returns JSON with field Y")
+2. **pitfall**: Errors encountered, wrong assumptions, things that wasted time (e.g., "Assumed API token was in env var GITEA_TOKEN, but it's in ~/.config/gitea/token")
+3. **pattern**: Successful sequences of actions (e.g., "To deploy: 1. Run tests 2. Build 3. Push to Gitea 4. Trigger webhook")
+4. **tool-quirk**: Environment-specific behaviors (e.g., "Token paths are different on macOS vs Linux", "URL format requires trailing slash")
+5. **question**: Things identified but not answered (e.g., "Need to determine optimal batch size for harvesting")
+
+### Output Format
+
+Return a JSON object with an array of extracted knowledge items. Each item must have:
+
+```json
+{
+  "fact": "One sentence description of the knowledge",
+  "category": "fact|pitfall|pattern|tool-quirk|question",
+  "repo": "Repository name this applies to, or 'global' if general",
+  "confidence": 0.0-1.0
+}
 ```
-TASK: Extract durable knowledge from this session transcript.

-RULES:
-1. Extract ONLY information explicitly stated in the transcript.
-2. Do NOT infer, assume, or hallucinate.
-3. Every fact must be verifiable by pointing to a specific line in the transcript.
-4. If the session failed or was partial, extract pitfalls and questions — these are the most valuable.
-5. Be specific. "Gitea API is slow" is worthless. "Gitea issues endpoint with state=open returns empty when limit=50 but works with limit=5" is knowledge.
+### Confidence Scoring

-CATEGORIES (assign exactly one per item):
- fact: Concrete, verifiable thing learned (paths, formats, counts, configs)
- pitfall: Error hit, wrong assumption, time wasted, thing that didn't work
- pattern: Successful sequence that should be reused (deploy steps, debug flow)
- tool-quirk: Environment-specific behavior (token paths, URL formats, API gotchas)
- question: Something identified but not answered — the NEXT agent should investigate
+- 0.9-1.0: Explicitly stated with verification (e.g., "Error message shows X")
+- 0.7-0.8: Clearly implied by multiple data points
+- 0.5-0.6: Suggested but not fully verified
+- 0.3-0.4: Inferred from limited data
+- 0.1-0.2: Speculative or uncertain

-CONFIDENCE:
- 0.9: Directly observed with error output or explicit verification
- 0.7: Multiple data points confirm, but not explicitly verified
- 0.5: Suggested by context, not tested
- 0.3: Inferred from limited evidence
+### Constraints

-OUTPUT FORMAT (valid JSON only, no markdown, no explanation):
+1. **No hallucination**: Only extract what's explicitly in the transcript
+2. **Specificity**: Each fact must be specific and actionable
+3. **Relevance**: Only extract knowledge that would help future sessions
+4. **Brevity**: One sentence per fact
+5. **Partial sessions**: Even failed or incomplete sessions may contain valuable pitfalls
+
+### Example Input/Output
+
+**Input Transcript (excerpt):**
+```
+User: Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence
+Agent: Trying git clone... Error: 401 Unauthorized
+Agent: Checking for token... Found in ~/.config/gitea/token
+Agent: Token is gitea_token format, not OAuth
+Agent: Clone successful with token authentication
+```
+
+**Output:**
+```json
 {
  "knowledge": [
    {
-      "fact": "One specific sentence of knowledge",
-      "category": "fact|pitfall|pattern|tool-quirk|question",
-      "repo": "repo-name or global",
-      "confidence": 0.0-1.0,
-      "evidence": "Brief quote or reference from transcript that supports this"
+      "fact": "Gitea repo at forge.alexanderwhitestone.com requires authentication for cloning",
+      "category": "fact",
+      "repo": "compounding-intelligence",
+      "confidence": 0.9
+    },
+    {
+      "fact": "Gitea authentication token is stored at ~/.config/gitea/token",
+      "category": "tool-quirk",
+      "repo": "global",
+      "confidence": 0.9
+    },
+    {
+      "fact": "Gitea uses gitea_token format, not OAuth for API access",
+      "category": "tool-quirk",
+      "repo": "global",
+      "confidence": 0.8
+    },
+    {
+      "fact": "Clone fails with 401 when no token is provided",
+      "category": "pitfall",
+      "repo": "compounding-intelligence",
+      "confidence": 0.9
    }
-  ],
-  "meta": {
-    "session_outcome": "success|partial|failed",
-    "tools_used": ["tool1", "tool2"],
-    "repos_touched": ["repo1"],
-    "error_count": 0,
-    "knowledge_count": 0
-  }
+  ]
 }
-
-TRANSCRIPT:
-{{transcript}}
 ```

-## Design Notes
+## Final Notes

-### Why this works with mimo-v2-pro
-
-Mimo needs:
- Explicit format constraints ("valid JSON only, no markdown")
- Clear category definitions with concrete examples
- Hard rules before soft guidance
- The transcript at the END (so it reads all instructions first)
-
-This prompt front-loads all rules, then gives the transcript last. Mimo follows the pattern.
-
-### Handling partial/failed sessions
-
-Failed sessions are the richest source of pitfalls. The prompt explicitly says:
-> "If the session failed or was partial, extract pitfalls and questions — these are the most valuable."
-
-This reframes failure as valuable output, not noise to discard.
-
-### The `evidence` field
-
-Added to the original spec. Every extracted item must cite where in the transcript it came from. This:
- Prevents hallucination (can't cite what isn't there)
- Enables verification (reviewer can check the source)
- Trains confidence calibration (the agent must find evidence, not just claim it)
-
-### Token budget
-
-Target: ~1,000 tokens for the prompt (excluding transcript).
-
-```
-System prompt:        ~50 tokens
-Rules:               ~200 tokens
-Categories:          ~150 tokens
-Confidence:          ~100 tokens
-Output format:       ~200 tokens
-Design notes:        NOT included in prompt (documentation only)
-─────────────────────────────
-Total prompt:        ~700 tokens
-```
-
-Leaves ~300 tokens headroom for variable content (transcript insertion, edge cases).
-
-### What this replaces
-
-The v1 prompt had:
- Verbose prose explanations (waste tokens for mimo)
- No `evidence` field (hallucination risk)
- No `meta` block (no session-level metadata)
- No explicit handling of failed sessions
- Example was too long (~150 tokens of example for a 1k prompt)
-
-This v2 is tighter, more structured, and adds the evidence requirement that prevents the #1 failure mode of extraction prompts: generating plausible-sounding facts that aren't in the transcript.
+- Process the entire transcript, not just the beginning
+- Pay special attention to errors and corrections
+- Note any environment-specific details
+- Track tool-specific behaviors and quirks
+- If the session failed, focus on pitfalls and questions
--- a/test_sessions/session_failure.jsonl
+++ b/test_sessions/session_failure.jsonl
@@ -0,0 +1,18 @@
+{"role": "user", "content": "Deploy the application to production"}
+{"role": "assistant", "content": "I'll deploy the application to production.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@prod-server 'cd /app && git pull && docker-compose up -d'"}}]}
+{"role": "tool", "content": "ssh: connect to host prod-server port 22: Connection refused"}
+{"role": "assistant", "content": "Connection refused. Let me check the server status.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ping -c 3 prod-server"}}]}
+{"role": "tool", "content": "PING prod-server (192.168.1.100): 56 data bytes\nRequest timeout for icmp_seq 0\nRequest timeout for icmp_seq 1\nRequest timeout for icmp_seq 2\n--- prod-server ping statistics ---\n3 packets transmitted, 0 packets received, 100.0% packet loss"}
+{"role": "assistant", "content": "The server appears to be down. Let me check if there's an alternative deployment method."}
+{"role": "user", "content": "Try using the VPS instead"}
+{"role": "assistant", "content": "I'll try deploying to the VPS.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@vps-server 'cd /app && git pull && docker-compose up -d'"}}]}
+{"role": "tool", "content": "Permission denied (publickey)."}
+{"role": "assistant", "content": "Permission denied. The SSH key might not be set up correctly. Let me check the SSH configuration.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat ~/.ssh/config"}}]}
+{"role": "tool", "content": "Host vps-server\n    HostName 167.99.126.228\n    User deploy\n    IdentityFile ~/.ssh/id_rsa_vps"}
+{"role": "assistant", "content": "The SSH config looks correct. Let me check if the key exists.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la ~/.ssh/id_rsa_vps"}}]}
+{"role": "tool", "content": "ls: /Users/user/.ssh/id_rsa_vps: No such file or directory"}
+{"role": "assistant", "content": "The SSH key doesn't exist. This is a pitfall - we need to generate the SSH key first."}
+{"role": "user", "content": "Generate a new SSH key for the VPS"}
+{"role": "assistant", "content": "I'll generate a new SSH key.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh-keygen -t rsa -b 4096 -f ~/.ssh/id_rsa_vps -N ''"}}]}
+{"role": "tool", "content": "Generating public/private rsa key pair.\nYour identification has been saved in /Users/user/.ssh/id_rsa_vps\nYour public key has been saved in /Users/user/.ssh/id_rsa_vps.pub\nThe key fingerprint is:\nSHA256:abc123... user@machine"}
+{"role": "assistant", "content": "SSH key generated. Now I need to add it to the VPS."}
--- a/test_sessions/session_partial.jsonl
+++ b/test_sessions/session_partial.jsonl
@@ -0,0 +1,14 @@
+{"role": "user", "content": "Check the Gitea API for open issues"}
+{"role": "assistant", "content": "I'll check the Gitea API for open issues.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://forge.alexanderwhitestone.com/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
+{"role": "tool", "content": "curl: (6) Could not resolve host: forge.alexanderwhitestone.com"}
+{"role": "assistant", "content": "DNS resolution failed. Let me check the network connectivity.", "tool_calls": [{"function": "terminal", "arguments": {"command": "nslookup forge.alexanderwhitestone.com"}}]}
+{"role": "tool", "content": "Server:		8.8.8.8\nAddress:	8.8.8.8#53\n\n** server can't find forge.alexanderwhitestone.com: NXDOMAIN"}
+{"role": "assistant", "content": "The domain doesn't resolve. This might be a DNS issue. Let me try using the IP address directly.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
+{"role": "tool", "content": "curl: (60) SSL certificate problem: self signed certificate"}
+{"role": "assistant", "content": "SSL certificate issue. The server is using a self-signed certificate. Let me try with -k flag to skip SSL verification.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
+{"role": "tool", "content": "[]"}
+{"role": "assistant", "content": "No open issues found. The API returned an empty array."}
+{"role": "user", "content": "Check if there are any pull requests"}
+{"role": "assistant", "content": "Let me check for pull requests.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/pulls?state=open"}}]}
+{"role": "tool", "content": "[{"id": 20, "title": "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)", "state": "open", "user": {"login": "Rockachopa"}, "created_at": "2026-04-14T17:28:20Z"}]"}
+{"role": "assistant", "content": "Found 1 open pull request: PR #20 - "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)" by Rockachopa."}
--- a/test_sessions/session_patterns.jsonl
+++ b/test_sessions/session_patterns.jsonl
@@ -0,0 +1,10 @@
+{"role": "user", "content": "How do I deploy a new version of the application?"}
+{"role": "assistant", "content": "Here's the deployment process:\n1. Run tests: pytest\n2. Build Docker image: docker build -t app:latest .\n3. Push to registry: docker push registry.example.com/app:latest\n4. Update production: ssh prod 'cd /app && docker-compose pull && docker-compose up -d'\n5. Verify: curl https://app.example.com/health"}
+{"role": "user", "content": "What if tests fail?"}
+{"role": "assistant", "content": "If tests fail:\n1. Check the error logs: pytest -v\n2. Fix the failing tests\n3. Re-run tests: pytest\n4. If still failing, check recent changes: git log --oneline -10\n5. Consider reverting: git revert HEAD"}
+{"role": "user", "content": "What if the Docker build fails?"}
+{"role": "assistant", "content": "If Docker build fails:\n1. Check Dockerfile syntax: docker build --no-cache -t app:latest .\n2. Check for missing dependencies: cat requirements.txt\n3. Check disk space: df -h\n4. Clean up Docker: docker system prune -f\n5. Try building with verbose output: docker build --progress=plain -t app:latest ."}
+{"role": "user", "content": "What if the push to registry fails?"}
+{"role": "assistant", "content": "If push to registry fails:\n1. Check registry credentials: docker login registry.example.com\n2. Check registry space: curl https://registry.example.com/v2/_catalog\n3. Check image size: docker images app:latest\n4. Try tagging with version: docker tag app:latest registry.example.com/app:v1.0.0\n5. Push with version tag: docker push registry.example.com/app:v1.0.0"}
+{"role": "user", "content": "What if the production update fails?"}
+{"role": "assistant", "content": "If production update fails:\n1. Check SSH connection: ssh prod 'echo connected'\n2. Check disk space on prod: ssh prod 'df -h'\n3. Check Docker status: ssh prod 'docker ps -a'\n4. Check logs: ssh prod 'docker-compose logs --tail=100'\n5. Rollback: ssh prod 'cd /app && git checkout HEAD~1 && docker-compose up -d'"}
--- a/test_sessions/session_questions.jsonl
+++ b/test_sessions/session_questions.jsonl
@@ -0,0 +1,12 @@
+{"role": "user", "content": "I need to implement a new feature for the application"}
+{"role": "assistant", "content": "I can help you implement a new feature. What feature would you like to add?"}
+{"role": "user", "content": "I want to add user authentication"}
+{"role": "assistant", "content": "User authentication is a good feature. I have a few questions:\n1. What authentication method do you prefer? (JWT, OAuth, Session-based)\n2. Do you need social login? (Google, GitHub, etc.)\n3. What user data do you need to store?\n4. Do you need role-based access control?\n5. What's your database? (PostgreSQL, MySQL, SQLite)"}
+{"role": "user", "content": "I prefer JWT, no social login, just email and password, no roles, PostgreSQL"}
+{"role": "assistant", "content": "Great choices. Here's the implementation plan:\n1. Create user model with email and password hash\n2. Create JWT token generation and validation\n3. Create login endpoint: POST /api/auth/login\n4. Create register endpoint: POST /api/auth/register\n5. Create middleware for protected routes\n6. Add password hashing with bcrypt\n7. Add rate limiting for login attempts\n8. Add password reset functionality\n9. Add email verification\n10. Test all endpoints"}
+{"role": "user", "content": "What about password reset?"}
+{"role": "assistant", "content": "For password reset:\n1. Create reset token table\n2. Create forgot password endpoint: POST /api/auth/forgot-password\n3. Send reset email with token\n4. Create reset password endpoint: POST /api/auth/reset-password\n5. Validate reset token and expiration\n6. Update password and delete token\n7. Send confirmation email"}
+{"role": "user", "content": "What about email verification?"}
+{"role": "assistant", "content": "For email verification:\n1. Add email_verified field to user model\n2. Create verification token table\n3. Send verification email on registration\n4. Create verify email endpoint: GET /api/auth/verify-email?token=...\n5. Validate token and update email_verified\n6. Add middleware to check email_verified for certain routes\n7. Add resend verification email endpoint"}
+{"role": "user", "content": "What about rate limiting?"}
+{"role": "assistant", "content": "For rate limiting:\n1. Use Redis for rate limit storage\n2. Create rate limit middleware\n3. Set limits: 5 login attempts per minute, 3 password resets per hour\n4. Return 429 Too Many Requests when limit exceeded\n5. Add X-RateLimit headers to responses\n6. Log rate limit violations\n7. Add whitelist for trusted IPs"}
--- a/test_sessions/session_success.jsonl
+++ b/test_sessions/session_success.jsonl
@@ -0,0 +1,13 @@
+{"role": "user", "content": "Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence"}
+{"role": "assistant", "content": "I'll clone the repository for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "git clone https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence.git"}}]}
+{"role": "tool", "content": "Cloning into 'compounding-intelligence'...\nremote: Enumerating objects: 15, done.\nremote: Counting objects: 100% (15/15), done.\nremote: Compressing objects: 100% (12/12), done.\nremote: Total 15 (delta 2), reused 0 (delta 0), pack-reused 0\nReceiving objects: 100% (15/15), done.\nResolving deltas: 100% (2/2), done."}
+{"role": "assistant", "content": "Repository cloned successfully. Let me check the structure.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/"}}]}
+{"role": "tool", "content": "total 8\ndrwxr-xr-x   5 user  staff  160 Apr 14 17:21 .\ndrwxr-xr-x  12 user  staff  384 Apr 14 17:21 ..\ndrwxr-xr-x  13 user  staff  416 Apr 14 17:21 .git\n-rw-r--r--   1 user  staff  1234 Apr 14 17:21 README.md\ndrwxr-xr-x   3 user  staff   96 Apr 14 17:21 knowledge\n-rw-r--r--   1 user  staff   456 Apr 14 17:21 metrics\ndrwxr-xr-x   4 user  staff  128 Apr 14 17:21 scripts\ndrwxr-xr-x   3 user  staff   96 Apr 14 17:21 templates"}
+{"role": "user", "content": "What files are in the templates directory?"}
+{"role": "assistant", "content": "Let me check the templates directory.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/templates/"}}]}
+{"role": "tool", "content": "total 0\ndrwxr-xr-x  3 user  staff   96 Apr 14 17:21 .\ndrwxr-xr-x  5 user  staff  160 Apr 14 17:21 ..\n-rw-r--r--  1 user  staff    0 Apr 14 17:21 .gitkeep"}
+{"role": "assistant", "content": "The templates directory currently only contains a .gitkeep file. No templates have been added yet."}
+{"role": "user", "content": "Create a harvest-prompt.md template in the templates directory."}
+{"role": "assistant", "content": "I'll create the harvest-prompt.md template for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat > compounding-intelligence/templates/harvest-prompt.md << 'EOF'\n# Knowledge Extraction Prompt\n\nExtract knowledge from session transcripts.\nEOF"}}]}
+{"role": "tool", "content": ""}
+{"role": "assistant", "content": "Template created successfully. The harvest-prompt.md file is now in the templates directory."}
Author	SHA1	Message	Date
Alexander Whitestone	2f38c52691	test: add tests for issue body parser (#90 )	2026-04-15 03:34:33 +00:00
Alexander Whitestone	b614220eff	feat: Gitea issue body parser for structured task extraction (#90 )	2026-04-15 03:34:30 +00:00
Timmy Time	8d716ff03f	Add comprehensive test script for harvest prompt validation	2026-04-14 19:02:41 +00:00
Timmy Time	920510996e	Add test session 5: Session with questions	2026-04-14 19:01:03 +00:00
Timmy Time	1fafeaf5a4	Add test session 4: Session with patterns	2026-04-14 19:01:00 +00:00
Timmy Time	36b440f998	Add test session 3: Partial session with tool quirks	2026-04-14 19:00:58 +00:00
Timmy Time	9f3caabf42	Add test session 2: Failed session with pitfalls	2026-04-14 19:00:56 +00:00
Timmy Time	a21f3a44e1	Add test session 1: Successful session	2026-04-14 18:58:05 +00:00