@soleri/forge 5.5.0 → 5.6.0

package/src/skills/verification-before-completion.md

@@ -45,37 +45,43 @@ Skip any step = lying, not verifying
 After passing all verification commands, run system diagnostics:
 
 ### Health Check
+
 ```
 YOUR_AGENT_core op:admin_health
 ```
+
 Catches issues tests might miss — vault corruption, stale caches, configuration drift.
 
 ### Full Diagnostic
+
 ```
 YOUR_AGENT_core op:admin_diagnostic
 ```
+
 Comprehensive system check — module status, database integrity, cache health, configuration validity.
 
 ### Vault Analytics
+
 ```
 YOUR_AGENT_core op:admin_vault_analytics
 ```
+
 Verify knowledge quality metrics — are capture rates healthy? Any degradation?
 
 If any check reports problems, address them before claiming completion.
 
 ## Common Failures
 
-| Claim | Requires | Not Sufficient |
-|-------|----------|----------------|
-| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
-| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
-| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
-| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
-| Regression test works | Red-green cycle verified | Test passes once |
-| Agent completed | VCS diff shows changes | Agent reports "success" |
-| Requirements met | Line-by-line checklist | Tests passing |
-| Agent healthy | `admin_diagnostic` clean | "No errors in logs" |
+| Claim                 | Requires                        | Not Sufficient                 |
+| --------------------- | ------------------------------- | ------------------------------ |
+| Tests pass            | Test command output: 0 failures | Previous run, "should pass"    |
+| Linter clean          | Linter output: 0 errors         | Partial check, extrapolation   |
+| Build succeeds        | Build command: exit 0           | Linter passing, logs look good |
+| Bug fixed             | Test original symptom: passes   | Code changed, assumed fixed    |
+| Regression test works | Red-green cycle verified        | Test passes once               |
+| Agent completed       | VCS diff shows changes          | Agent reports "success"        |
+| Requirements met      | Line-by-line checklist          | Tests passing                  |
+| Agent healthy         | `admin_diagnostic` clean        | "No errors in logs"            |
 
 ## Red Flags - STOP
 
@@ -90,44 +96,49 @@ If any check reports problems, address them before claiming completion.
 
 ## Rationalization Prevention
 
-| Excuse | Reality |
-|--------|---------|
-| "Should work now" | RUN the verification |
-| "I'm confident" | Confidence ≠ evidence |
-| "Just this once" | No exceptions |
-| "Linter passed" | Linter ≠ compiler |
-| "Agent said success" | Verify independently |
-| "I'm tired" | Exhaustion ≠ excuse |
-| "Partial check is enough" | Partial proves nothing |
-| "Different words so rule doesn't apply" | Spirit over letter |
+| Excuse                                  | Reality                |
+| --------------------------------------- | ---------------------- |
+| "Should work now"                       | RUN the verification   |
+| "I'm confident"                         | Confidence ≠ evidence  |
+| "Just this once"                        | No exceptions          |
+| "Linter passed"                         | Linter ≠ compiler      |
+| "Agent said success"                    | Verify independently   |
+| "I'm tired"                             | Exhaustion ≠ excuse    |
+| "Partial check is enough"               | Partial proves nothing |
+| "Different words so rule doesn't apply" | Spirit over letter     |
 
 ## Key Patterns
 
 **Tests:**
+
 ```
 [Run test command] [See: 34/34 pass] "All tests pass"
 NOT: "Should pass now" / "Looks correct"
 ```
 
 **Regression tests (TDD Red-Green):**
+
 ```
 Write -> Run (pass) -> Revert fix -> Run (MUST FAIL) -> Restore -> Run (pass)
 NOT: "I've written a regression test" (without red-green verification)
 ```
 
 **Build:**
+
 ```
 [Run build] [See: exit 0] "Build passes"
 NOT: "Linter passed" (linter doesn't check compilation)
 ```
 
 **Requirements:**
+
 ```
 Re-read plan -> Create checklist -> Verify each -> Report gaps or completion
 NOT: "Tests pass, phase complete"
 ```
 
 **Agent delegation:**
+
 ```
 Agent reports success -> Check VCS diff -> Verify changes -> Report actual state
 NOT: Trust agent report
@@ -149,6 +160,7 @@ This ensures the next session has context about what was verified and completed.
 ## When To Apply
 
 **ALWAYS before:**
+
 - ANY variation of success/completion claims
 - ANY expression of satisfaction
 - ANY positive statement about work state
@@ -162,9 +174,9 @@ Run the command. Read the output. THEN claim the result. This is non-negotiable.
 
 ## Agent Tools Reference
 
-| Op | When to Use |
-|----|-------------|
-| `admin_health` | Quick system health check |
-| `admin_diagnostic` | Comprehensive system diagnostic |
-| `admin_vault_analytics` | Knowledge quality metrics |
-| `session_capture` | Persist verified completion context |
+| Op                      | When to Use                         |
+| ----------------------- | ----------------------------------- |
+| `admin_health`          | Quick system health check           |
+| `admin_diagnostic`      | Comprehensive system diagnostic     |
+| `admin_vault_analytics` | Knowledge quality metrics           |
+| `session_capture`       | Persist verified completion context |

package/src/skills/writing-plans.md

@@ -22,6 +22,7 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 **Never write a plan from scratch.** Always search for existing knowledge first.
 
 ### 1. Vault First
+
 Check the vault for relevant implementation patterns:
 
 ```
@@ -30,6 +31,7 @@ YOUR_AGENT_core op:search_intelligent
 ```
 
 Look for:
+
 - **Implementation patterns** — proven approaches for similar features
 - **Anti-patterns** — approaches that failed and should be avoided
 - **Testing patterns** — how similar features were tested
@@ -48,13 +50,16 @@ YOUR_AGENT_core op:vault_tags
 ```
 
 ### 2. Web Search Second
+
 If the vault doesn't have implementation guidance, search the web:
+
 - **Libraries and tools** — is there a package that does this already?
 - **Reference implementations** — how did other projects solve this?
 - **API documentation** — official docs for libraries you'll use
 - **Known issues** — pitfalls others ran into
 
 ### 3. Then Write the Plan
+
 Incorporate vault insights and web findings into the plan. Reference specific vault entries and documentation links when they inform a step. A plan informed by existing knowledge is dramatically better than one written from first principles.
 
 ## Create a Tracked Plan
@@ -123,6 +128,7 @@ This generates individual tasks from the plan steps, ready for execution trackin
 ## Bite-Sized Task Granularity
 
 **Each step is one action (2-5 minutes):**
+
 - "Write the failing test" - step
 - "Run it to make sure it fails" - step
 - "Implement the minimal code to make the test pass" - step
@@ -150,6 +156,7 @@ This generates individual tasks from the plan steps, ready for execution trackin
 ## Task Structure
 
 Each task uses this format:
+
 - Files: Create / Modify / Test paths
 - Step 1: Write the failing test (with code)
 - Step 2: Run test to verify it fails (with expected output)
@@ -158,6 +165,7 @@ Each task uses this format:
 - Step 5: Commit (with exact git commands)
 
 ## Remember
+
 - Exact file paths always
 - Complete code in plan (not "add validation")
 - Exact commands with expected output
@@ -192,16 +200,16 @@ Which approach?"
 
 ## Agent Tools Reference
 
-| Op | When to Use |
-|----|-------------|
-| `search_intelligent` | Find relevant patterns before planning |
-| `brain_strengths` | Check proven approaches |
-| `vault_domains` / `vault_tags` | Browse knowledge landscape |
-| `create_plan` | Create tracked, persistent plan |
-| `plan_grade` | Grade plan quality |
-| `plan_auto_improve` | Auto-fix plan weaknesses |
-| `plan_meets_grade` | Verify grade target reached |
-| `plan_iterate` | Iterate on draft with feedback |
-| `plan_split` | Split plan into trackable tasks |
-| `approve_plan` | Lock in approved plan |
-| `plan_stats` | Overview of plan metrics |
+| Op                             | When to Use                            |
+| ------------------------------ | -------------------------------------- |
+| `search_intelligent`           | Find relevant patterns before planning |
+| `brain_strengths`              | Check proven approaches                |
+| `vault_domains` / `vault_tags` | Browse knowledge landscape             |
+| `create_plan`                  | Create tracked, persistent plan        |
+| `plan_grade`                   | Grade plan quality                     |
+| `plan_auto_improve`            | Auto-fix plan weaknesses               |
+| `plan_meets_grade`             | Verify grade target reached            |
+| `plan_iterate`                 | Iterate on draft with feedback         |
+| `plan_split`                   | Split plan into trackable tasks        |
+| `approve_plan`                 | Lock in approved plan                  |
+| `plan_stats`                   | Overview of plan metrics               |

package/src/templates/entry-point.ts

@@ -22,6 +22,7 @@ import {
   createCoreOps,
   createDomainFacades,
   registerAllFacades,
+  seedDefaultPlaybooks,
 } from '@soleri/core';
 import type { OpDefinition } from '@soleri/core';
 import { z } from 'zod';
@@ -39,6 +40,13 @@ async function main(): Promise<void> {
   });
 
   const tag = PERSONA.name.toLowerCase();
+
+  // Seed built-in playbooks (idempotent)
+  const seedResult = seedDefaultPlaybooks(runtime.vault);
+  if (seedResult.seeded > 0) {
+    console.error(\`[\${tag}] Seeded \${seedResult.seeded} built-in playbooks\`);
+  }
+
   const stats = runtime.vault.stats();
   console.error(\`[\${tag}] Vault: \${stats.totalEntries} entries, Brain: \${runtime.brain.getVocabularySize()} terms\`);
 

package/src/templates/test-facades.ts

@@ -200,6 +200,8 @@ ${domainDescribes}
       expect(opNames).toContain('brain_feedback');
       expect(opNames).toContain('brain_feedback_stats');
       expect(opNames).toContain('brain_reset_extracted');
+      // Brain decay report (#89)
+      expect(opNames).toContain('brain_decay_report');
       // Agent-specific ops (5)
       expect(opNames).toContain('health');
       expect(opNames).toContain('identity');
@@ -230,7 +232,7 @@ ${domainDescribes}
       expect(opNames).toContain('governance_stats');
       expect(opNames).toContain('governance_expire');
       expect(opNames).toContain('governance_dashboard');
-      // Planning Extra ops (9)
+      // Planning Extra ops (13)
       expect(opNames).toContain('plan_iterate');
       expect(opNames).toContain('plan_split');
       expect(opNames).toContain('plan_reconcile');
@@ -240,6 +242,10 @@ ${domainDescribes}
       expect(opNames).toContain('plan_archive');
       expect(opNames).toContain('plan_list_tasks');
       expect(opNames).toContain('plan_stats');
+      expect(opNames).toContain('plan_execution_metrics');
+      expect(opNames).toContain('plan_record_task_metrics');
+      expect(opNames).toContain('plan_submit_deliverable');
+      expect(opNames).toContain('plan_verify_deliverables');
       // Memory Extra ops (8)
       expect(opNames).toContain('memory_delete');
       expect(opNames).toContain('memory_stats');
@@ -262,6 +268,10 @@ ${domainDescribes}
       expect(opNames).toContain('vault_seed');
       expect(opNames).toContain('vault_backup');
       expect(opNames).toContain('vault_age_report');
+      // #89: Bi-temporal
+      expect(opNames).toContain('vault_set_temporal');
+      expect(opNames).toContain('vault_find_expiring');
+      expect(opNames).toContain('vault_find_expired');
       // Admin ops (8)
       expect(opNames).toContain('admin_health');
       expect(opNames).toContain('admin_tool_list');
@@ -271,7 +281,7 @@ ${domainDescribes}
       expect(opNames).toContain('admin_version');
       expect(opNames).toContain('admin_reset_cache');
       expect(opNames).toContain('admin_diagnostic');
-      // Loop ops (7)
+      // Loop ops (8)
       expect(opNames).toContain('loop_start');
       expect(opNames).toContain('loop_iterate');
       expect(opNames).toContain('loop_status');
@@ -279,6 +289,7 @@ ${domainDescribes}
       expect(opNames).toContain('loop_history');
       expect(opNames).toContain('loop_is_active');
       expect(opNames).toContain('loop_complete');
+      expect(opNames).toContain('loop_anomaly_check');
       // Orchestrate ops (5)
       expect(opNames).toContain('orchestrate_plan');
       expect(opNames).toContain('orchestrate_execute');
@@ -296,7 +307,7 @@ ${domainDescribes}
       expect(opNames).toContain('plan_latest_check');
       expect(opNames).toContain('plan_meets_grade');
       expect(opNames).toContain('plan_auto_improve');
-      // Admin Extra ops (10)
+      // Admin Extra ops (11)
       expect(opNames).toContain('admin_telemetry');
       expect(opNames).toContain('admin_telemetry_recent');
       expect(opNames).toContain('admin_telemetry_reset');
@@ -307,11 +318,14 @@ ${domainDescribes}
       expect(opNames).toContain('admin_env');
       expect(opNames).toContain('admin_gc');
       expect(opNames).toContain('admin_export_config');
-      // Curator Extra ops (4)
+      expect(opNames).toContain('admin_hot_reload');
+      // Curator Extra ops (4 + 1 hybrid)
       expect(opNames).toContain('curator_entry_history');
       expect(opNames).toContain('curator_record_snapshot');
       expect(opNames).toContain('curator_queue_stats');
       expect(opNames).toContain('curator_enrich');
+      // #36: Hybrid contradiction detection
+      expect(opNames).toContain('curator_hybrid_contradictions');
       // Project ops (12)
       expect(opNames).toContain('project_get');
       expect(opNames).toContain('project_list');
@@ -329,8 +343,23 @@ ${domainDescribes}
       expect(opNames).toContain('memory_promote_to_global');
       expect(opNames).toContain('memory_configure');
       expect(opNames).toContain('memory_cross_project_search');
-      // Total: 152 (147 core + 5 agent-specific)
-      expect(facade.ops.length).toBe(152);
+      // Playbook ops (5)
+      expect(opNames).toContain('playbook_list');
+      expect(opNames).toContain('playbook_get');
+      expect(opNames).toContain('playbook_create');
+      expect(opNames).toContain('playbook_match');
+      expect(opNames).toContain('playbook_seed');
+      // Cognee Sync ops (3)
+      expect(opNames).toContain('cognee_sync_status');
+      expect(opNames).toContain('cognee_sync_drain');
+      expect(opNames).toContain('cognee_sync_reconcile');
+      // Intake ops (4)
+      expect(opNames).toContain('intake_ingest_book');
+      expect(opNames).toContain('intake_process');
+      expect(opNames).toContain('intake_status');
+      expect(opNames).toContain('intake_preview');
+      // Total: 208 (203 core + 5 agent-specific)
+      expect(facade.ops.length).toBe(208);
     });
 
     it('search should query across all domains with ranked results', async () => {