@dzhechkov/keysarium 1.1.2 → 1.2.0

package/templates/lib/worker-templates/consolidate.md

@@ -0,0 +1,180 @@
+# Worker Template: Pattern Consolidation
+
+> This file is loaded by the background worker agent. It contains the complete
+> instructions for executing the consolidation task.
+
+## Worker Identity
+
+- **Type:** consolidate
+- **Model:** sonnet
+- **Purpose:** Scan completed researches for universal patterns and generate a harvest delta
+
+## Instructions
+
+You are a background worker agent. Your job is to analyze completed research cases
+and extract reusable patterns. You operate in ISOLATION -- you must not modify any
+files outside your output directory.
+
+### Input Parameters
+
+These will be injected by the orchestrator:
+
+- `WORKER_ID`: Your unique worker identifier
+- `OUTPUT_DIR`: Your output directory path (`.keysarium/workers/{WORKER_ID}/`)
+
+### Execution Steps
+
+#### Step 1: Initialize
+
+Write your status file:
+
+```json
+// Write to {OUTPUT_DIR}/status.json
+{
+  "worker_id": "{WORKER_ID}",
+  "type": "consolidate",
+  "status": "running",
+  "started_at": "{current ISO8601 timestamp}",
+  "completed_at": null,
+  "progress": {
+    "phase": "initializing",
+    "items_processed": 0
+  },
+  "error": null
+}
+```
+
+#### Step 2: Scan Researches
+
+1. List all directories under `researches/`
+2. For each research directory, check for completion markers:
+   - File `08_executive_summary.md` exists (indicates completed case)
+   - File `README.md` exists (indicates packaging done)
+3. Build a list of completed research slugs
+4. Update status: `"phase": "scanning researches", "items_processed": {count}`
+
+**IMPORTANT:** Check for `{OUTPUT_DIR}/stop-requested` file. If it exists, write
+status as `stopped` and exit immediately.
+
+#### Step 3: Analyze Patterns
+
+For each completed research:
+
+1. Read `00_product_discovery.md` -- extract domain, JTBD segments
+2. Read `02_research_findings.md` -- extract key findings, technologies
+3. Read `03_solution_strategy.md` -- extract solution patterns
+4. Read `05_presentation_content.md` -- extract storytelling patterns
+
+Look for:
+- **Domain patterns**: Which domains appear most? What works in each?
+- **Technology patterns**: Which technologies are recommended repeatedly?
+- **Solution patterns**: Which problem-solving frameworks yield best results?
+- **Anti-patterns**: Which approaches were rejected and why?
+- **Time patterns**: Which phases tend to take longer than budgeted?
+
+Update status: `"phase": "analyzing patterns", "items_processed": {count}`
+
+**IMPORTANT:** Check for `stop-requested` file between each research analysis.
+
+#### Step 4: Generate Output
+
+Write the following files to `{OUTPUT_DIR}/output/`:
+
+**patterns.json:**
+```json
+{
+  "generated_at": "{timestamp}",
+  "worker_id": "{WORKER_ID}",
+  "cases_analyzed": 5,
+  "patterns": [
+    {
+      "type": "domain",
+      "name": "Banking cases need on-premise LLM",
+      "frequency": 3,
+      "confidence": "high",
+      "source_cases": ["bank_kc_automation", "bank_risk_scoring"]
+    },
+    {
+      "type": "technology",
+      "name": "GigaChat preferred for Russian-language banking",
+      "frequency": 2,
+      "confidence": "medium",
+      "source_cases": ["bank_kc_automation"]
+    }
+  ],
+  "anti_patterns": [
+    {
+      "name": "Generic GPT without architecture",
+      "occurrences": 1,
+      "fix": "Always specify concrete model + pipeline"
+    }
+  ],
+  "recommendations": [
+    "Consider increasing Phase 2 time budget for banking domain (observed 2x overrun)",
+    "TRIZ framework shows higher success rate than Game Theory for retail cases"
+  ]
+}
+```
+
+**harvest-delta.md:**
+```markdown
+# Harvest Delta — {timestamp}
+
+## New Patterns Discovered
+
+### Domain Patterns
+- [pattern description with source cases]
+
+### Technology Patterns
+- [pattern description with source cases]
+
+### Solution Patterns
+- [pattern description with source cases]
+
+## Recommendations
+
+- [actionable recommendation]
+
+## Application Instructions
+
+To apply these findings to TOOLKIT_HARVEST.md, review the patterns above and
+manually merge the relevant ones. This worker does NOT modify TOOLKIT_HARVEST.md
+directly to preserve isolation.
+```
+
+#### Step 5: Complete
+
+1. Read `TOOLKIT_HARVEST.md` if it exists -- note its current content for context
+   (do NOT modify it)
+2. Write final status:
+
+```json
+{
+  "worker_id": "{WORKER_ID}",
+  "type": "consolidate",
+  "status": "completed",
+  "started_at": "{start timestamp}",
+  "completed_at": "{current timestamp}",
+  "progress": {
+    "phase": "completed",
+    "items_processed": "{total cases analyzed}"
+  },
+  "error": null
+}
+```
+
+### Error Handling
+
+If any step fails:
+
+1. Write error details to `{OUTPUT_DIR}/error.log`
+2. Update status.json with status `failed` and error message
+3. Exit
+
+### Isolation Rules
+
+- You MUST only write files to `{OUTPUT_DIR}/`
+- You MUST NOT modify any file in `researches/`, `features/`, `.claude/`, or project root
+- You MUST NOT modify `TOOLKIT_HARVEST.md` (write delta to your output dir instead)
+- You MUST NOT spawn sub-agents
+- You MAY read any file in the project for analysis purposes

package/templates/lib/worker-templates/dream-cycle.md

@@ -0,0 +1,154 @@
+# Worker Template: Dream Cycle
+
+> This file is loaded by the background worker agent. It contains the complete
+> instructions for executing a dream cycle using the DreamEngine protocol.
+
+## Worker Identity
+
+- **Type:** dream-cycle
+- **Model:** sonnet
+- **Purpose:** Build concept graph from reward records, detect cross-domain associations, generate actionable insights
+
+## Instructions
+
+You are a background worker agent. Your job is to analyze accumulated reward records
+and generate higher-order insights using the DreamEngine protocol defined in
+`lib/dream-engine.md`. You operate in ISOLATION -- you must not modify any files
+outside your output directory and `.keysarium/insights/`.
+
+### Input Parameters
+
+These will be injected by the orchestrator:
+
+- `WORKER_ID`: Your unique worker identifier
+- `OUTPUT_DIR`: Your output directory path (`.keysarium/workers/{WORKER_ID}/`)
+- `TRIGGER_REASON`: Why this dream was triggered (`time` | `volume` | `event` | `manual`)
+
+### Execution Steps
+
+#### Step 1: Initialize
+
+Write your status file:
+
+```json
+// Write to {OUTPUT_DIR}/status.json
+{
+  "worker_id": "{WORKER_ID}",
+  "type": "dream-cycle",
+  "status": "running",
+  "started_at": "{current ISO8601 timestamp}",
+  "completed_at": null,
+  "progress": {
+    "phase": "initializing",
+    "items_processed": 0
+  },
+  "error": null
+}
+```
+
+#### Step 2: Load Data
+
+Follow the DreamEngine Step 1 (Load Data) protocol from `lib/dream-engine.md`:
+
+1. Check if `.keysarium/memory/` exists. If not, write status `completed` with `"phase": "no_data"` and exit.
+2. Read `.keysarium/memory/_stats/reward-summary.json` (optional).
+3. Read `.keysarium/memory/_patterns/domain-patterns.json` (optional).
+4. Scan and parse all reward record JSON files under `.keysarium/memory/`.
+5. Exclude expired records, sort by reward DESC, take top 200.
+6. If fewer than 5 records: write status `completed` with `"phase": "insufficient_data"` and exit.
+
+Update status: `"phase": "loading data", "items_processed": {record_count}`
+
+**IMPORTANT:** Check for `{OUTPUT_DIR}/stop-requested` file. If it exists, write status as `stopped` and exit immediately.
+
+#### Step 3: Build Concept Graph
+
+Follow the DreamEngine Step 2 (Build Concept Graph) protocol:
+
+1. Initialize empty graph.
+2. For each record, create/update domain, phase, skill, and outcome nodes.
+3. Create/update edges with reward weights.
+4. Compute per-node aggregates (avg_reward, record_count, trend).
+5. Compute per-edge aggregates (weight, record_count).
+
+Update status: `"phase": "building concept graph", "items_processed": {node_count}`
+
+**IMPORTANT:** Check for `stop-requested` file.
+
+#### Step 4: Detect Associations
+
+Follow the DreamEngine Step 3 (Detect Associations) protocol:
+
+1. Cross-domain phase comparison (reward gap > 0.15).
+2. Skill-domain mismatch detection (reward gap > 0.15).
+3. Phase correlation analysis (co-occurring low rewards).
+4. Temporal trend detection (systematic changes over time).
+
+Update status: `"phase": "detecting associations", "items_processed": {association_count}`
+
+**IMPORTANT:** Check for `stop-requested` file.
+
+#### Step 5: Generate Insights
+
+Follow the DreamEngine Step 4 (Generate Insights) protocol:
+
+1. Convert each association to an Insight object.
+2. Map association types to insight types.
+3. Score confidence and impact.
+4. Add actionable advice to descriptions.
+5. Promote high-confidence domain patterns to insights.
+6. Deduplicate against recent dreams (last 3 files in `.keysarium/insights/`).
+7. Sort by rank_score DESC, take top 20.
+
+Update status: `"phase": "generating insights", "items_processed": {insight_count}`
+
+#### Step 6: Store Results
+
+Follow the DreamEngine Step 5 (Store and Clean) protocol:
+
+1. Ensure `.keysarium/insights/` directory exists.
+2. Write dream result JSON to `.keysarium/insights/dream-{YYYYMMDD}-{HHmmss}.json`.
+3. Apply retention: list dream files, keep newest 10, delete older.
+4. Reset trigger state in `.keysarium/insights/trigger-state.json`.
+5. Copy dream result to `{OUTPUT_DIR}/output/dream-{timestamp}.json`.
+
+#### Step 7: Complete
+
+Write final status:
+
+```json
+{
+  "worker_id": "{WORKER_ID}",
+  "type": "dream-cycle",
+  "status": "completed",
+  "started_at": "{start timestamp}",
+  "completed_at": "{current timestamp}",
+  "progress": {
+    "phase": "completed",
+    "records_analyzed": "{count}",
+    "insights_generated": "{count}",
+    "associations_found": "{count}"
+  },
+  "error": null
+}
+```
+
+### Error Handling
+
+If any step fails:
+
+1. Write error details to `{OUTPUT_DIR}/error.log`
+2. Update status.json with status `failed` and error message in the `error` field
+3. Do NOT modify trigger-state.json on failure (preserve current trigger state)
+4. Exit
+
+### Isolation Rules
+
+- You MUST only write files to `{OUTPUT_DIR}/` and `.keysarium/insights/`
+- You MUST NOT modify any file in `researches/`, `features/`, `.claude/`, or project root
+- You MUST NOT modify files in `.keysarium/memory/` (read-only access)
+- You MUST NOT modify `TOOLKIT_HARVEST.md` or `CLAUDE.md`
+- You MUST NOT spawn sub-agents
+- You MAY read any file in the project for analysis purposes
+- Exception: `.keysarium/insights/trigger-state.json` is writable (for reset on completion)
+- Exception: `.keysarium/insights/dream-*.json` is writable (for new dream results and retention cleanup)

package/templates/lib/worker-templates/health-check.md

@@ -0,0 +1,255 @@
+# Worker Template: Health Check
+
+> This file is loaded by the background worker agent. It contains the complete
+> instructions for executing the health check task.
+
+## Worker Identity
+
+- **Type:** health-check
+- **Model:** haiku
+- **Purpose:** Verify system health: skill trust tiers, data freshness, structural integrity
+
+## Instructions
+
+You are a background worker agent. Your job is to perform health checks on the
+Keysarium system and produce a structured health report. You operate in ISOLATION --
+you must not modify any files outside your output directory.
+
+### Input Parameters
+
+These will be injected by the orchestrator:
+
+- `WORKER_ID`: Your unique worker identifier
+- `OUTPUT_DIR`: Your output directory path (`.keysarium/workers/{WORKER_ID}/`)
+
+### Execution Steps
+
+#### Step 1: Initialize
+
+Write your status file:
+
+```json
+{
+  "worker_id": "{WORKER_ID}",
+  "type": "health-check",
+  "status": "running",
+  "started_at": "{current ISO8601 timestamp}",
+  "completed_at": null,
+  "progress": { "phase": "initializing", "items_processed": 0 },
+  "error": null
+}
+```
+
+#### Step 2: Check Skill Trust Tiers
+
+For each skill directory in `.claude/skills/`:
+
+1. Read `SKILL.md` -- check for `trust_tier` in frontmatter
+2. Check if `references/` directory exists
+3. Check if `modules/` directory exists
+4. Check if `examples/` directory exists
+5. Determine actual tier based on contents:
+   - Tier 0 (Advisory): Only SKILL.md
+   - Tier 1 (Structured): SKILL.md + references/ or modules/
+   - Tier 2 (Validated): Tier 1 + BTO test score >= 7.0 in metadata
+   - Tier 3 (Verified): Tier 2 + eval test suites
+6. Compare claimed tier vs actual tier
+7. Flag mismatches (claimed higher than actual)
+
+Record results for each skill:
+```json
+{
+  "name": "skill-trust-tiers",
+  "status": "warn",
+  "message": "frontend-design claims Tier 0 but could be promoted to Tier 1",
+  "details": {
+    "skills": [
+      { "name": "explore", "claimed": 1, "actual": 1, "match": true },
+      { "name": "frontend-design", "claimed": 0, "actual": 0, "match": true, "promotion_hint": "Add references/ to reach Tier 1" }
+    ]
+  }
+}
+```
+
+Update status: `"phase": "checking skill tiers", "items_processed": 1`
+
+**Check for `stop-requested` file.**
+
+#### Step 3: Check Governance Integrity
+
+1. Verify all governance shards exist in `.claude/shards/`:
+   - `phase-0-discovery.shard.md`
+   - `phase-1-explore.shard.md`
+   - `phase-2-research.shard.md`
+   - `phase-25-cjm.shard.md`
+   - `phase-3-solve.shard.md`
+   - `phase-4-architecture.shard.md`
+   - `phase-5-presentation.shard.md`
+   - `bto-evaluation.shard.md`
+   - `feature-adr.shard.md`
+2. Verify all rule files exist in `.claude/rules/`
+3. Verify all commands exist in `.claude/commands/`
+4. Check for any orphaned files (files not referenced in CLAUDE.md)
+
+Record results:
+```json
+{
+  "name": "governance-integrity",
+  "status": "pass",
+  "message": "All 9 shards, 13 rules, and 20 commands present",
+  "details": { "shards": 9, "rules": 13, "commands": 20, "orphaned": 0 }
+}
+```
+
+Update status: `"phase": "checking governance", "items_processed": 2`
+
+**Check for `stop-requested` file.**
+
+#### Step 4: Check Research Data Freshness
+
+1. List all research directories in `researches/`
+2. For each: check last modification date of files
+3. Flag researches with incomplete artifact sets (missing required files)
+4. Check if TOOLKIT_HARVEST.md has been updated recently
+
+Record results:
+```json
+{
+  "name": "data-freshness",
+  "status": "pass",
+  "message": "3 completed researches, 0 stale, TOOLKIT_HARVEST.md current",
+  "details": {
+    "total_researches": 3,
+    "completed": 3,
+    "incomplete": 0,
+    "harvest_stale": false
+  }
+}
+```
+
+Update status: `"phase": "checking data freshness", "items_processed": 3`
+
+**Check for `stop-requested` file.**
+
+#### Step 5: Check Witness Chain (if exists)
+
+1. Check if `.keysarium/witness-chain/` exists
+2. If yes, verify chain integrity (each hash links to previous)
+3. Report any broken links
+
+Record results:
+```json
+{
+  "name": "witness-chain",
+  "status": "pass",
+  "message": "Witness chain intact (12 entries, no breaks)",
+  "details": { "entries": 12, "broken_links": 0 }
+}
+```
+
+If witness chain does not exist:
+```json
+{
+  "name": "witness-chain",
+  "status": "warn",
+  "message": "Witness chain not initialized (optional feature)",
+  "details": null
+}
+```
+
+Update status: `"phase": "checking witness chain", "items_processed": 4`
+
+#### Step 6: Check Worker System Health
+
+1. Read `.keysarium/workers/registry.json` if it exists
+2. Count stale entries (running but no status.json update in > 15 minutes)
+3. Check for orphaned worker directories (no registry entry)
+4. Report disk usage of `.keysarium/workers/` directory
+
+Record results:
+```json
+{
+  "name": "worker-system",
+  "status": "pass",
+  "message": "Worker registry clean, 0 stale entries",
+  "details": { "total_entries": 5, "stale": 0, "orphaned": 0 }
+}
+```
+
+Update status: `"phase": "checking worker system", "items_processed": 5`
+
+#### Step 7: Check Brain/Memory State
+
+1. Check if `keysarium-brain.json` or `.keysarium/exports/` exists
+2. Verify brain file structure if present
+3. Check for reward data (`.keysarium/rewards/` if exists)
+
+Record results:
+```json
+{
+  "name": "brain-state",
+  "status": "pass",
+  "message": "Brain export available, last exported 2026-02-28",
+  "details": { "brain_exists": true, "last_export": "2026-02-28" }
+}
+```
+
+Update status: `"phase": "checking brain state", "items_processed": 6`
+
+#### Step 8: Generate Health Report
+
+Write `{OUTPUT_DIR}/output/health-report.json`:
+
+```json
+{
+  "generated_at": "{timestamp}",
+  "worker_id": "{WORKER_ID}",
+  "summary": {
+    "total_checks": 6,
+    "passed": 5,
+    "warnings": 1,
+    "failures": 0,
+    "overall_status": "healthy"
+  },
+  "checks": [ /* all check results from steps 2-7 */ ],
+  "recommendations": [
+    "Run /bto-test on 'explore' skill to promote from Tier 1 to Tier 2",
+    "Consider initializing witness chain for audit trail"
+  ]
+}
+```
+
+Overall status logic:
+- `healthy`: 0 failures, 0-2 warnings
+- `degraded`: 0 failures, 3+ warnings
+- `unhealthy`: 1+ failures
+
+#### Step 9: Complete
+
+Write final status:
+
+```json
+{
+  "worker_id": "{WORKER_ID}",
+  "type": "health-check",
+  "status": "completed",
+  "started_at": "{start timestamp}",
+  "completed_at": "{current timestamp}",
+  "progress": { "phase": "completed", "items_processed": 6 },
+  "error": null
+}
+```
+
+### Error Handling
+
+If any check step fails:
+1. Record the failed check with status `fail` and error message
+2. Continue to the next check (do not abort on individual check failure)
+3. Only write `error.log` and set status `failed` if the entire worker crashes
+
+### Isolation Rules
+
+- You MUST only write files to `{OUTPUT_DIR}/`
+- You MUST NOT modify any file in the project
+- You MUST NOT spawn sub-agents
+- You MAY read any file in the project for analysis purposes