@goondocks/myco 0.20.1 → 0.21.0

package/dist/src/agent/definitions/tasks/skill-evolve.yaml

@@ -10,7 +10,7 @@ prompt: >-
   overlap. The instruction contains pre-filtered skills with their
   content, new spore IDs, and pre-computed similarity analysis.
 isDefault: false
-model: claude-sonnet-4-6
+reasoningLevel: default
 maxTurns: 48
 timeoutSeconds: 1800
 schedule:
@@ -18,13 +18,14 @@ schedule:
   intervalSeconds: 900
   runIn:
     - idle
+    - sleep
   preCondition: has-active-skills
 params:
   assess_interval_hours: 24
   max_skills_per_run: 8
 phases:
   - name: inventory
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     prompt: |
       The instruction contains pre-computed structural analysis of
       all active skills. Two mechanical signals are provided:
@@ -81,7 +82,7 @@ phases:
     readOnly: true
 
   - name: assess
-    model: claude-sonnet-4-6
+    reasoningLevel: default
     prompt: |
       Read the inventory analysis from vault_state
       (key: skill-evolve-inventory).
@@ -156,7 +157,7 @@ phases:
       - inventory
 
   - name: act
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     prompt: |
       Read classifications from vault_state
       (key: skill-evolve-classifications). Parse the JSON.

package/dist/src/agent/definitions/tasks/skill-generate.yaml

@@ -10,7 +10,7 @@ prompt: >-
   The instruction contains the candidate metadata and pre-assembled
   source material. Stage the skill, validate it, then finalize it.
 isDefault: false
-model: claude-sonnet-4-6
+reasoningLevel: default
 maxTurns: 30
 timeoutSeconds: 900
 schedule:
@@ -18,6 +18,7 @@ schedule:
   intervalSeconds: 600
   runIn:
     - idle
+    - sleep
   preCondition: has-approved-candidates
 phases:
   - name: draft

package/dist/src/agent/definitions/tasks/skill-survey.yaml

@@ -9,14 +9,16 @@ prompt: >-
   Survey the vault knowledge graph for procedural domain candidates.
   The instruction contains pre-assembled vault context.
 isDefault: false
-model: claude-sonnet-4-6
+reasoningLevel: default
 maxTurns: 35
 timeoutSeconds: 1800
 schedule:
   enabled: true
-  intervalSeconds: 600
+  intervalSeconds: 21600
   runIn:
     - idle
+    - sleep
+  preCondition: has-skill-survey-evidence
 phases:
   - name: explore
     prompt: |
@@ -57,6 +59,9 @@ phases:
       ## Process
 
       1. Read the pre-assembled context for orientation.
+         It already excludes active-session data and only exists when
+         the vault has enough settled knowledge to support a serious
+         candidate review.
 
       2. Use vault tools for TARGETED follow-up on promising
          clusters. The baseline gives you direction — follow threads
@@ -67,8 +72,6 @@ phases:
            a domain you spotted in the digest
          - vault_spores to read full content of high-signal spores
            summarized in the baseline
-         - vault_entities for components with high mention counts
-           that might anchor a domain
 
          Do NOT exhaustively paginate or search every keyword.
          You have ~12 tool calls — use them purposefully.
@@ -77,11 +80,13 @@ phases:
          note: the core theme, which procedures it covers, and
          which source items provide evidence.
 
+      4. Reject generic engineering domains even if they are common.
+         A valid candidate must be specific to this project's named
+         components, files, commands, or conventions.
+
       Store your domain clusters in working notes for the next phase.
     tools:
       - vault_spores
-      - vault_entities
-      - vault_edges
       - vault_sessions
       - vault_search_fts
       - vault_search_semantic
@@ -90,7 +95,7 @@ phases:
     readOnly: true
 
   - name: synthesize-evaluate
-    model: claude-sonnet-4-6
+    reasoningLevel: default
     prompt: |
       The explore phase identified procedural domain clusters from
       the vault. Now evaluate each and create candidates for domains
@@ -103,27 +108,34 @@ phases:
 
       ## Evaluation criteria
 
-      Each candidate must pass ALL of these at the DOMAIN level:
+      Each candidate must pass ALL of these at the DOMAIN level.
+      If any required criterion fails, reject the domain and do not
+      create or update a candidate.
 
       1. PROCEDURE TEST: Does this domain describe "how to do a
          family of related tasks in this project"? A domain about
          "what X is" or "X exists" is knowledge, not a skill.
 
-      2. REPEATABILITY TEST: Will developers need these procedures
+      2. PROJECT-SPECIFICITY TEST: Is this domain meaningfully tied
+         to THIS repository? It must be anchored to named project
+         components, files, commands, or conventions. Generic
+         engineering topics FAIL.
+
+      3. REPEATABILITY TEST: Will developers need these procedures
          again as the project grows? Domains covering extension
          points (adding new X, extending Y) are strong candidates.
          One-time fixes and bug patches are NOT skills.
 
-      3. BREADTH TEST: Does this domain cover 2+ distinct procedures
+      4. BREADTH TEST: Does this domain cover 2+ distinct procedures
          that share prerequisite knowledge? A single procedure is
          too narrow — it should be a section within a broader domain.
          If you can't imagine 3+ major section headings, it's not
          broad enough.
 
-      4. CROSS-SESSION EVIDENCE: Knowledge from 2+ sessions and 3+
+      5. CROSS-SESSION EVIDENCE: Knowledge from 2+ sessions and 3+
          source items (spores, sessions, plans).
 
-      5. DEDUPLICATION: Check BOTH lists from step 0.
+      6. DEDUPLICATION: Check BOTH lists from step 0.
          - If an active skill already covers this domain, skip.
          - If the domain SUBSUMES existing narrow skills (the domain
            is broader and the narrow skills are sections within it),
@@ -136,7 +148,7 @@ phases:
            warning. If the dismissed topic is a narrow subset of
            your broader domain, proceed.
 
-      6. CONFIDENCE SCORE (0.0-1.0):
+      7. CONFIDENCE SCORE (0.0-1.0):
          - Domain breadth (more procedures covered = higher)
          - Cross-session evidence (wider = higher)
          - Wisdom spore presence (higher quality signal)

package/dist/src/agent/definitions/tasks/supersession-sweep.yaml

@@ -13,7 +13,7 @@ description: >
   Records resolution events for audit trail.
 agent: myco-agent
 isDefault: false
-model: claude-haiku-4-5-20251001
+reasoningLevel: low
 maxTurns: 30
 timeoutSeconds: 300
 

package/dist/src/agent/definitions/tasks/title-summary.yaml

@@ -13,9 +13,9 @@ description: >
   title and informative summary.
 agent: myco-agent
 isDefault: false
-model: claude-haiku-4-5-20251001
+reasoningLevel: low
 maxTurns: 15
-timeoutSeconds: 120
+timeoutSeconds: 300
 
 prompt: |
   Generate or update session titles and summaries. Budget: ~12 turns.
@@ -28,27 +28,24 @@ prompt: |
 
   **If a target session ID is specified above:**
   Always process it — the user explicitly requested regeneration.
-  Call `vault_sessions` with `include_active: true` to get its current
-  title/summary (the session may still be active). Call `vault_search_fts`
-  with the session ID to find ALL its prompt batches (processed and
-  unprocessed). Do NOT skip even if there are no new unprocessed batches.
+  Call `vault_session_summary_material` with `session_id: <target session>`
+  to get the current title/summary plus the compact ordered prompt-batch arc.
+  Do NOT skip even if there are no new unprocessed batches.
 
   **If no target session specified (automatic run):**
   Call `vault_unprocessed` with `include_active: true` — titles are needed
   mid-flight, not just after a session completes. Group by session_id —
-  each session with unprocessed batches needs its summary updated. Call
-  `vault_sessions` with `include_active: true` for those sessions. If no
-  sessions have unprocessed batches, report "skip" and finish.
+  each session with unprocessed batches needs its summary updated. For each
+  session, call `vault_session_summary_material`. If no sessions have
+  unprocessed batches, report "skip" and finish.
 
   ## Phase 2 — Update Each Session (budget: 8 turns)
 
   For each session to process:
   1. Read the EXISTING title and summary — context from prior runs.
-  2. Read the session's prompt batches — user_prompt + response_summary.
-     For targeted sessions, use `vault_search_fts` results from Phase 1.
-     For automatic runs, use `vault_unprocessed` results.
-     This is your PRIMARY source — read through the full set to understand
-     the complete arc of work.
+  2. Read the session's compact prompt-batch arc — user_prompt +
+     response_summary. This is your PRIMARY source — read through the full
+     set to understand the complete arc of work.
   3. Generate a title and summary from the full session content.
   4. Call `vault_update_session` with BOTH title and summary.
 
@@ -81,10 +78,6 @@ prompt: |
 
 toolOverrides:
   - vault_unprocessed
-  - vault_sessions
-  - vault_spores
-  - vault_search_fts
-  - vault_state
+  - vault_session_summary_material
   - vault_update_session
-  - vault_set_state
   - vault_report

package/dist/src/agent/definitions/tasks/{full-intelligence.yaml → vault-evolve.yaml}

@@ -1,5 +1,5 @@
 # =============================================================================
-# Built-in Task: Full Intelligence (Phased)
+# Built-in Task: Vault Evolve (Phased)
 # =============================================================================
 # Default task for: myco-agent
 #
@@ -8,30 +8,30 @@
 # controls the loop — the LLM cannot skip phases.
 # =============================================================================
 
-name: full-intelligence
-displayName: Full Intelligence
+name: vault-evolve
+displayName: Vault Evolve
 description: >
   Complete intelligence pass over all unprocessed session data. Extracts
   observations as spores, updates session summaries, consolidates related
-  spores into wisdom, builds knowledge graph entities and edges, and
-  regenerates digest extracts.
+  spores into wisdom, and regenerates digest extracts. Runs automatically
+  on a schedule once sessions have settled.
 agent: myco-agent
 isDefault: true
 maxTurns: 150
 timeoutSeconds: 1800
-model: claude-sonnet-4-6
+reasoningLevel: default
 
 schedule:
   enabled: true
   intervalSeconds: 300
   runIn:
-    - active
     - idle
+    - sleep
   preCondition: has-unprocessed-batches
 
 orchestrator:
   enabled: true
-  model: claude-sonnet-4-6
+  reasoningLevel: default
   maxTurns: 3
 
 contextQueries:
@@ -61,7 +61,7 @@ prompt: >
 
 phases:
   - name: read-state
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     # Root phase — no dependsOn
     prompt: |
       Read the current vault state to determine what needs processing.
@@ -81,7 +81,7 @@ phases:
     readOnly: true
 
   - name: extract
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     dependsOn: [read-state]
     prompt: |
       Extract observations from unprocessed batches as spores.
@@ -134,7 +134,7 @@ phases:
     required: true
 
   - name: summarize
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     dependsOn: [read-state]
     prompt: |
       Update session titles and summaries for sessions touched during extraction.
@@ -189,7 +189,7 @@ phases:
     required: false
 
   - name: consolidate
-    model: claude-sonnet-4-6
+    reasoningLevel: default
     dependsOn: [extract]
     prompt: |
       Consolidate related spores into wisdom and clean up redundancy.
@@ -254,76 +254,12 @@ phases:
     maxTurns: 25
     required: false
 
-  - name: graph
-    model: claude-sonnet-4-6
-    dependsOn: [extract]
-    prompt: |
-      Build the knowledge graph: create entities, then link spores to them.
-
-      New graph work may still be warranted even when extract skipped, because
-      spores and entities can be created by coding agents or manual curation.
-      Focus on recent or high-signal active spores and obvious entity gaps.
-      If a quick review shows no meaningful new graph work, report "skip".
-
-      The graph has two layers:
-      - Lineage (automatic): spore→session, spore→batch — already done
-      - Semantic (your job): spore→entity, entity→entity — you create these
-
-      ## Step 1: Review spores and existing entities (2 turns)
-
-      1. Call `vault_spores` with status "active" to see current spores
-      2. Call `vault_entities` to see existing graph entities
-      3. Call `vault_edges` to see existing relationships
-
-      ## Step 2: Create entities (budget: 6 turns)
-
-      For components/concepts/people that appear across multiple spores:
-      - Call `vault_create_entity` with type: component | concept | person
-      - Focus on entities that help understand the system architecture
-      - Prefer fewer well-defined entities over many vague ones
-
-      ## Step 3: Link spores to entities (budget: 12 turns) — CRITICAL
-
-      For EACH entity (newly created AND existing unlinked ones):
-      1. Call `vault_search_semantic` with the entity name to find related spores
-      2. Before creating an edge, call `vault_edges` with `source_id` and
-         `target_id` to verify it does not already exist
-      3. For each relevant search result, call `vault_create_edge`:
-         - type: REFERENCES
-         - source_id: the spore ID, source_type: spore
-         - target_id: the entity ID, target_type: entity
-      4. Entities without edges are invisible — always link after creating
-
-      ## Step 4: Structural edges between entities (remaining turns)
-
-      For architectural dependencies between entities:
-      - DEPENDS_ON (entity→entity): "daemon" depends on "SQLite"
-      - AFFECTS (spore→entity): a gotcha that impacts a component
-
-      Do NOT create lineage edges (FROM_SESSION, EXTRACTED_FROM, etc.)
-
-      Call `vault_report` with action "graph" reporting:
-      - Entities created: N
-      - Spore→entity REFERENCES edges: N
-      - Entity→entity structural edges: N
-    tools:
-      - vault_spores
-      - vault_sessions
-      - vault_search_semantic
-      - vault_entities
-      - vault_edges
-      - vault_create_entity
-      - vault_create_edge
-      - vault_report
-    maxTurns: 35
-    required: false
-
   # ---- Digest: assess + 3 parallel tier writes ----
   # The assess phase gathers context, then each tier runs independently
   # in the same wave via Promise.allSettled().
 
   - name: digest-assess
-    model: claude-sonnet-4-6
+    reasoningLevel: default
     dependsOn: [consolidate]
     prompt: |
       Assess current digest state and gather material for tier updates.
@@ -390,7 +326,7 @@ phases:
     required: true
 
   - name: digest-10000
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     dependsOn: [digest-assess]
     prompt: |
       Update digest tier 10000 — Full institutional knowledge.
@@ -427,7 +363,7 @@ phases:
     required: false
 
   - name: digest-5000
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     dependsOn: [digest-assess]
     prompt: |
       Update digest tier 5000 — Deep onboarding.
@@ -463,7 +399,7 @@ phases:
     required: false
 
   - name: digest-1500
-    model: claude-haiku-4-5-20251001
+    reasoningLevel: low
     dependsOn: [digest-assess]
     prompt: |
       Update digest tier 1500 — Executive briefing.
@@ -499,8 +435,8 @@ phases:
     required: false
 
   - name: report
-    model: claude-haiku-4-5-20251001
-    dependsOn: [extract, summarize, consolidate, graph, digest-assess, digest-10000, digest-5000, digest-1500]
+    reasoningLevel: low
+    dependsOn: [extract, summarize, consolidate, digest-assess, digest-10000, digest-5000, digest-1500]
     prompt: |
       Summarize what was done across all phases.
 
@@ -509,7 +445,6 @@ phases:
       - Spores created: N (by type)
       - Sessions updated: N
       - Wisdom created: N
-      - Entities created: N, edges created: N
       - Digest tiers written: N
 
       This report MUST be the last tool call of the run.