open-multi-agent-kit 0.78.0

package/docs/2026-06-03/critical-issues.md

@@ -0,0 +1,20 @@
+# 2026-06-03 Critical Issues
+
+## Critical Init Status
+- No critical init artifacts were missing when this daily file was generated.
+### Missing critical artifacts
+- None detected.
+
+
+## Critical Artifacts Present
+- ✅ `AGENTS.md` — top-level operating contract
+- ✅ `.kimi/AGENTS.md` — Kimi-specific operating rules
+- ✅ `.omk/config.toml` — OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — root coordinator agent
+- ✅ `.kimi/mcp.json` — Kimi project MCP registry
+- ✅ `.omk/hooks/pre-shell-guard.sh` — destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — secret write guard
+- ✅ `.omk/memory/graph-state.json` — local ontology graph database
+
+## Escalation Rule
+- Treat missing shell/secret guards, root agent config, MCP registry, or ontology graph as critical until restored.

package/docs/2026-06-03/improvements.md

@@ -0,0 +1,14 @@
+# 2026-06-03 Improvements
+
+## Current Improvement Backlog
+### Optional init/support artifacts to add or refresh
+- None detected.
+
+### Critical init artifacts currently blocking reliable chat startup
+- None detected.
+
+
+## Suggested Focus
+- Keep `omk chat` startup idempotent and non-destructive.
+- Prefer local graph memory for default ontology state.
+- Keep generated daily docs small, dated, and safe to edit by hand.

package/docs/2026-06-03/init-checklist.md

@@ -0,0 +1,25 @@
+# 2026-06-03 Required Init Checklist
+
+**Run ID:** chat-2026-06-02T22-00-22-844Z-245004
+**Ontology graph:** `.omk/memory/graph-state.json`
+
+## Required Artifacts
+- ✅ `AGENTS.md` — critical; top-level operating contract
+- ✅ `.kimi/AGENTS.md` — critical; Kimi-specific operating rules
+- ✅ `DESIGN.md` — support; design/brand source of truth
+- ✅ `.omk/config.toml` — critical; OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — critical; root coordinator agent
+- ✅ `.kimi/mcp.json` — critical; Kimi project MCP registry
+- ✅ `.omk/mcp.json` — support; legacy OMK MCP fallback
+- ✅ `.omk/lsp.json` — support; TypeScript LSP config
+- ✅ `.omk/hooks/pre-shell-guard.sh` — critical; destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — critical; secret write guard
+- ✅ `.omk/memory/graph-state.json` — critical; local ontology graph database
+- ✅ `.kimi/skills` — support; Kimi skill directory
+- ✅ `.agents/skills` — support; portable skill directory
+
+## Recovery Command
+```bash
+omk init
+omk doctor
+```

package/docs/2026-06-03/plan.md

@@ -0,0 +1,20 @@
+# 2026-06-03 OMK Chat Plan
+
+**Run ID:** chat-2026-06-02T22-00-22-844Z-245004
+**Generated by:** omk chat bootstrap
+
+## Purpose
+- Start every chat with a dated workspace for planning, issue triage, and verification evidence.
+- Keep ontology-backed memory available before the root coordinator starts.
+- Make required init state visible without overwriting user-authored docs.
+
+## Today Plan
+1. Review `init-checklist.md` and resolve missing critical init artifacts first.
+2. Use `improvements.md` as the active improvement backlog.
+3. Use `critical-issues.md` for blocking defects, safety risks, and verification gaps.
+4. Record command evidence before claiming work is complete.
+
+## Stop Condition
+- Critical init artifacts are present.
+- Ontology graph exists at `.omk/memory/graph-state.json`.
+- Any new code/docs changes have explicit verification evidence.

package/docs/2026-06-04/critical-issues.md

@@ -0,0 +1,20 @@
+# 2026-06-04 Critical Issues
+
+## Critical Init Status
+- No critical init artifacts were missing when this daily file was generated.
+### Missing critical artifacts
+- None detected.
+
+
+## Critical Artifacts Present
+- ✅ `AGENTS.md` — top-level operating contract
+- ✅ `.kimi/AGENTS.md` — Kimi-specific operating rules
+- ✅ `.omk/config.toml` — OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — root coordinator agent
+- ✅ `.kimi/mcp.json` — Kimi project MCP registry
+- ✅ `.omk/hooks/pre-shell-guard.sh` — destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — secret write guard
+- ✅ `.omk/memory/graph-state.json` — local ontology graph database
+
+## Escalation Rule
+- Treat missing shell/secret guards, root agent config, MCP registry, or ontology graph as critical until restored.

package/docs/2026-06-04/improvements.md

@@ -0,0 +1,14 @@
+# 2026-06-04 Improvements
+
+## Current Improvement Backlog
+### Optional init/support artifacts to add or refresh
+- None detected.
+
+### Critical init artifacts currently blocking reliable chat startup
+- None detected.
+
+
+## Suggested Focus
+- Keep `omk chat` startup idempotent and non-destructive.
+- Prefer local graph memory for default ontology state.
+- Keep generated daily docs small, dated, and safe to edit by hand.

package/docs/2026-06-04/init-checklist.md

@@ -0,0 +1,25 @@
+# 2026-06-04 Required Init Checklist
+
+**Run ID:** chat-2026-06-03T20-11-10-268Z-411951
+**Ontology graph:** `.omk/memory/graph-state.json`
+
+## Required Artifacts
+- ✅ `AGENTS.md` — critical; top-level operating contract
+- ✅ `.kimi/AGENTS.md` — critical; Kimi-specific operating rules
+- ✅ `DESIGN.md` — support; design/brand source of truth
+- ✅ `.omk/config.toml` — critical; OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — critical; root coordinator agent
+- ✅ `.kimi/mcp.json` — critical; Kimi project MCP registry
+- ✅ `.omk/mcp.json` — support; legacy OMK MCP fallback
+- ✅ `.omk/lsp.json` — support; TypeScript LSP config
+- ✅ `.omk/hooks/pre-shell-guard.sh` — critical; destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — critical; secret write guard
+- ✅ `.omk/memory/graph-state.json` — critical; local ontology graph database
+- ✅ `.kimi/skills` — support; Kimi skill directory
+- ✅ `.agents/skills` — support; portable skill directory
+
+## Recovery Command
+```bash
+omk init
+omk doctor
+```

package/docs/2026-06-04/plan.md

@@ -0,0 +1,20 @@
+# 2026-06-04 OMK Chat Plan
+
+**Run ID:** chat-2026-06-03T20-11-10-268Z-411951
+**Generated by:** omk chat bootstrap
+
+## Purpose
+- Start every chat with a dated workspace for planning, issue triage, and verification evidence.
+- Keep ontology-backed memory available before the root coordinator starts.
+- Make required init state visible without overwriting user-authored docs.
+
+## Today Plan
+1. Review `init-checklist.md` and resolve missing critical init artifacts first.
+2. Use `improvements.md` as the active improvement backlog.
+3. Use `critical-issues.md` for blocking defects, safety risks, and verification gaps.
+4. Record command evidence before claiming work is complete.
+
+## Stop Condition
+- Critical init artifacts are present.
+- Ontology graph exists at `.omk/memory/graph-state.json`.
+- Any new code/docs changes have explicit verification evidence.

package/docs/2026-06-05/critical-issues.md

@@ -0,0 +1,20 @@
+# 2026-06-05 Critical Issues
+
+## Critical Init Status
+- No critical init artifacts were missing when this daily file was generated.
+### Missing critical artifacts
+- None detected.
+
+
+## Critical Artifacts Present
+- ✅ `AGENTS.md` — top-level operating contract
+- ✅ `.kimi/AGENTS.md` — Kimi-specific operating rules
+- ✅ `.omk/config.toml` — OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — root coordinator agent
+- ✅ `.kimi/mcp.json` — Kimi project MCP registry
+- ✅ `.omk/hooks/pre-shell-guard.sh` — destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — secret write guard
+- ✅ `.omk/memory/graph-state.json` — local ontology graph database
+
+## Escalation Rule
+- Treat missing shell/secret guards, root agent config, MCP registry, or ontology graph as critical until restored.

package/docs/2026-06-05/improvements.md

@@ -0,0 +1,14 @@
+# 2026-06-05 Improvements
+
+## Current Improvement Backlog
+### Optional init/support artifacts to add or refresh
+- None detected.
+
+### Critical init artifacts currently blocking reliable chat startup
+- None detected.
+
+
+## Suggested Focus
+- Keep `omk chat` startup idempotent and non-destructive.
+- Prefer local graph memory for default ontology state.
+- Keep generated daily docs small, dated, and safe to edit by hand.

package/docs/2026-06-05/init-checklist.md

@@ -0,0 +1,25 @@
+# 2026-06-05 Required Init Checklist
+
+**Run ID:** chat-2026-06-05T00-27-38-411Z-2417897
+**Ontology graph:** `.omk/memory/graph-state.json`
+
+## Required Artifacts
+- ✅ `AGENTS.md` — critical; top-level operating contract
+- ✅ `.kimi/AGENTS.md` — critical; Kimi-specific operating rules
+- ✅ `DESIGN.md` — support; design/brand source of truth
+- ✅ `.omk/config.toml` — critical; OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — critical; root coordinator agent
+- ✅ `.kimi/mcp.json` — critical; Kimi project MCP registry
+- ✅ `.omk/mcp.json` — support; legacy OMK MCP fallback
+- ✅ `.omk/lsp.json` — support; TypeScript LSP config
+- ✅ `.omk/hooks/pre-shell-guard.sh` — critical; destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — critical; secret write guard
+- ✅ `.omk/memory/graph-state.json` — critical; local ontology graph database
+- ✅ `.kimi/skills` — support; Kimi skill directory
+- ✅ `.agents/skills` — support; portable skill directory
+
+## Recovery Command
+```bash
+omk init
+omk doctor
+```

package/docs/2026-06-05/plan.md

@@ -0,0 +1,20 @@
+# 2026-06-05 OMK Chat Plan
+
+**Run ID:** chat-2026-06-05T00-27-38-411Z-2417897
+**Generated by:** omk chat bootstrap
+
+## Purpose
+- Start every chat with a dated workspace for planning, issue triage, and verification evidence.
+- Keep ontology-backed memory available before the root coordinator starts.
+- Make required init state visible without overwriting user-authored docs.
+
+## Today Plan
+1. Review `init-checklist.md` and resolve missing critical init artifacts first.
+2. Use `improvements.md` as the active improvement backlog.
+3. Use `critical-issues.md` for blocking defects, safety risks, and verification gaps.
+4. Record command evidence before claiming work is complete.
+
+## Stop Condition
+- Critical init artifacts are present.
+- Ontology graph exists at `.omk/memory/graph-state.json`.
+- Any new code/docs changes have explicit verification evidence.

package/docs/2026-06-06/critical-issues.md

@@ -0,0 +1,20 @@
+# 2026-06-06 Critical Issues
+
+## Critical Init Status
+- No critical init artifacts were missing when this daily file was generated.
+### Missing critical artifacts
+- None detected.
+
+
+## Critical Artifacts Present
+- ✅ `AGENTS.md` — top-level operating contract
+- ✅ `.kimi/AGENTS.md` — Kimi-specific operating rules
+- ✅ `.omk/config.toml` — OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — root coordinator agent
+- ✅ `.kimi/mcp.json` — Kimi project MCP registry
+- ✅ `.omk/hooks/pre-shell-guard.sh` — destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — secret write guard
+- ✅ `.omk/memory/graph-state.json` — local ontology graph database
+
+## Escalation Rule
+- Treat missing shell/secret guards, root agent config, MCP registry, or ontology graph as critical until restored.

package/docs/2026-06-06/improvements.md

@@ -0,0 +1,14 @@
+# 2026-06-06 Improvements
+
+## Current Improvement Backlog
+### Optional init/support artifacts to add or refresh
+- None detected.
+
+### Critical init artifacts currently blocking reliable chat startup
+- None detected.
+
+
+## Suggested Focus
+- Keep `omk chat` startup idempotent and non-destructive.
+- Prefer local graph memory for default ontology state.
+- Keep generated daily docs small, dated, and safe to edit by hand.

package/docs/2026-06-06/init-checklist.md

@@ -0,0 +1,25 @@
+# 2026-06-06 Required Init Checklist
+
+**Run ID:** chat-2026-06-06T00-20-33-098Z-13863
+**Ontology graph:** `.omk/memory/graph-state.json`
+
+## Required Artifacts
+- ✅ `AGENTS.md` — critical; top-level operating contract
+- ✅ `.kimi/AGENTS.md` — critical; Kimi-specific operating rules
+- ✅ `DESIGN.md` — support; design/brand source of truth
+- ✅ `.omk/config.toml` — critical; OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — critical; root coordinator agent
+- ✅ `.kimi/mcp.json` — critical; Kimi project MCP registry
+- ✅ `.omk/mcp.json` — support; legacy OMK MCP fallback
+- ✅ `.omk/lsp.json` — support; TypeScript LSP config
+- ✅ `.omk/hooks/pre-shell-guard.sh` — critical; destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — critical; secret write guard
+- ✅ `.omk/memory/graph-state.json` — critical; local ontology graph database
+- ✅ `.kimi/skills` — support; Kimi skill directory
+- ✅ `.agents/skills` — support; portable skill directory
+
+## Recovery Command
+```bash
+omk init
+omk doctor
+```

package/docs/2026-06-06/plan.md

@@ -0,0 +1,20 @@
+# 2026-06-06 OMK Chat Plan
+
+**Run ID:** chat-2026-06-06T00-20-33-098Z-13863
+**Generated by:** omk chat bootstrap
+
+## Purpose
+- Start every chat with a dated workspace for planning, issue triage, and verification evidence.
+- Keep ontology-backed memory available before the root coordinator starts.
+- Make required init state visible without overwriting user-authored docs.
+
+## Today Plan
+1. Review `init-checklist.md` and resolve missing critical init artifacts first.
+2. Use `improvements.md` as the active improvement backlog.
+3. Use `critical-issues.md` for blocking defects, safety risks, and verification gaps.
+4. Record command evidence before claiming work is complete.
+
+## Stop Condition
+- Critical init artifacts are present.
+- Ontology graph exists at `.omk/memory/graph-state.json`.
+- Any new code/docs changes have explicit verification evidence.

package/docs/2026-06-07/critical-issues.md

@@ -0,0 +1,20 @@
+# 2026-06-07 Critical Issues
+
+## Critical Init Status
+- No critical init artifacts were missing when this daily file was generated.
+### Missing critical artifacts
+- None detected.
+
+
+## Critical Artifacts Present
+- ✅ `AGENTS.md` — top-level operating contract
+- ✅ `.kimi/AGENTS.md` — Kimi-specific operating rules
+- ✅ `.omk/config.toml` — OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — root coordinator agent
+- ✅ `.kimi/mcp.json` — Kimi project MCP registry
+- ✅ `.omk/hooks/pre-shell-guard.sh` — destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — secret write guard
+- ✅ `.omk/memory/graph-state.json` — local ontology graph database
+
+## Escalation Rule
+- Treat missing shell/secret guards, root agent config, MCP registry, or ontology graph as critical until restored.

package/docs/2026-06-07/improvements.md

@@ -0,0 +1,14 @@
+# 2026-06-07 Improvements
+
+## Current Improvement Backlog
+### Optional init/support artifacts to add or refresh
+- None detected.
+
+### Critical init artifacts currently blocking reliable chat startup
+- None detected.
+
+
+## Suggested Focus
+- Keep `omk chat` startup idempotent and non-destructive.
+- Prefer local graph memory for default ontology state.
+- Keep generated daily docs small, dated, and safe to edit by hand.

package/docs/2026-06-07/init-checklist.md

@@ -0,0 +1,25 @@
+# 2026-06-07 Required Init Checklist
+
+**Run ID:** chat-2026-06-06T17-38-06-142Z-20997
+**Ontology graph:** `.omk/memory/graph-state.json`
+
+## Required Artifacts
+- ✅ `AGENTS.md` — critical; top-level operating contract
+- ✅ `.kimi/AGENTS.md` — critical; Kimi-specific operating rules
+- ✅ `DESIGN.md` — support; design/brand source of truth
+- ✅ `.omk/config.toml` — critical; OMK project runtime settings
+- ✅ `.omk/agents/root.yaml` — critical; root coordinator agent
+- ✅ `.kimi/mcp.json` — critical; Kimi project MCP registry
+- ✅ `.omk/mcp.json` — support; legacy OMK MCP fallback
+- ✅ `.omk/lsp.json` — support; TypeScript LSP config
+- ✅ `.omk/hooks/pre-shell-guard.sh` — critical; destructive shell guard
+- ✅ `.omk/hooks/protect-secrets.sh` — critical; secret write guard
+- ✅ `.omk/memory/graph-state.json` — critical; local ontology graph database
+- ✅ `.kimi/skills` — support; Kimi skill directory
+- ✅ `.agents/skills` — support; portable skill directory
+
+## Recovery Command
+```bash
+omk init
+omk doctor
+```

package/docs/2026-06-07/plan.md

@@ -0,0 +1,20 @@
+# 2026-06-07 OMK Chat Plan
+
+**Run ID:** chat-2026-06-06T17-38-06-142Z-20997
+**Generated by:** omk chat bootstrap
+
+## Purpose
+- Start every chat with a dated workspace for planning, issue triage, and verification evidence.
+- Keep ontology-backed memory available before the root coordinator starts.
+- Make required init state visible without overwriting user-authored docs.
+
+## Today Plan
+1. Review `init-checklist.md` and resolve missing critical init artifacts first.
+2. Use `improvements.md` as the active improvement backlog.
+3. Use `critical-issues.md` for blocking defects, safety risks, and verification gaps.
+4. Record command evidence before claiming work is complete.
+
+## Stop Condition
+- Critical init artifacts are present.
+- Ontology graph exists at `.omk/memory/graph-state.json`.
+- Any new code/docs changes have explicit verification evidence.

package/docs/GSTACK_MIGRATION.md

@@ -0,0 +1,169 @@
+# External Multi-Agent Stack → OMK Migration Guide
+
+> Generic migration path from any external multi-agent orchestration stack (e.g., gstack, custom frameworks) to OMK.
+> OMK v1.1.18+ with externalized skill presets.
+
+## Why Migrate to OMK
+
+| Feature | External Stack | OMK |
+|---------|---------------|-----|
+| DAG scheduling | Limited or none | Native DAG with evidence gates |
+| Skill assignment | Hard-coded | Runtime JSON presets + rules |
+| Worktree isolation | Manual | Automatic per-run isolation |
+| Decision trace | None | Built-in audit trail |
+| Provider routing | Single | Multi-provider with fallback |
+| MCP integration | Ad-hoc | First-class project-scoped MCP |
+
+## Phase 1: Inventory
+
+### 1.1 List your current agents/roles
+
+```bash
+# In your old stack, list all roles
+omk explore --list-roles > old-roles.json
+```
+
+Map each role to OMK's 15 built-in roles:
+- `explorer`, `researcher`, `planner`, `architect`, `coder`
+- `reviewer`, `security`, `qa`, `tester`, `integrator`
+- `aggregator`, `interviewer`, `vision-debugger`, `ontology`, `coordinator`
+
+### 1.2 Extract skill/tool/MCP assignments
+
+For each role, document:
+- Skills (reusable knowledge packs)
+- MCP servers (external tool interfaces)
+- Hooks (pre/post execution scripts)
+- Tools (allowed tool categories)
+
+## Phase 2: Convert to OMK Presets
+
+### 2.1 Create `src/config/skill-presets.json`
+
+```json
+{
+  "version": "1.0.0",
+  "presets": {
+    "your-old-role": {
+      "skills": ["your-skill-1", "your-skill-2"],
+      "mcpServers": ["your-mcp"],
+      "tools": ["search", "read"],
+      "hooks": ["your-hook.sh"]
+    }
+  }
+}
+```
+
+Validation rules (enforced at runtime):
+- All arrays must contain only strings
+- No undefined values allowed
+- Schema mismatch → automatic fallback to built-in defaults
+
+### 2.2 Add custom SKILL_RULES (optional)
+
+Edit `src/orchestration/skill-assigner.ts` to add intent-detection rules:
+
+```typescript
+{
+  id: "your-custom-rule",
+  match: (node, intent) => intent === "coding" && /your-keyword/.test(node.name),
+  assign: { skills: ["your-skill"] },
+  priority: 80,
+  rationale: "Your custom detection logic"
+}
+```
+
+## Phase 3: Hook Migration
+
+### 3.1 Convert pre-execution guards
+
+Old stack:
+```bash
+#!/bin/bash
+# old-pre-hook.sh
+echo "Running pre-check..."
+```
+
+OMK:
+```bash
+#!/bin/bash
+# .omk/hooks/pre-shell-guard.sh
+# Automatically injected by skill-assigner for coder/reviewer/security roles
+set -euo pipefail
+echo "[OMK] Pre-shell guard active"
+```
+
+### 3.2 Register hooks in presets
+
+```json
+{
+  "coder": {
+    "hooks": ["protect-secrets.sh", "pre-shell-guard.sh", "post-format.sh"]
+  }
+}
+```
+
+## Phase 4: Runtime Verification
+
+### 4.1 Test preset loading
+
+```typescript
+import { loadRoleDefaults } from "./orchestration/skill-assigner.js";
+
+const defaults = await loadRoleDefaults();
+console.log("Loaded presets:", Object.keys(defaults));
+```
+
+### 4.2 Force reload without restart
+
+```typescript
+await loadRoleDefaults(true); // force = true
+```
+
+### 4.3 Verify decision traces
+
+```bash
+omk trace --component skill-assigner --run-id <run-id>
+```
+
+## Phase 5: Memory-Injection Safety
+
+OMK's skill-assigner includes automatic schema validation:
+
+```typescript
+function validatePresets(data: unknown): boolean {
+  // Rejects:
+  // - Non-object root
+  // - Non-string version
+  // - Non-array skills/mcpServers/tools/hooks
+  // - Non-string array elements
+  // Falls back to hard-coded ROLE_DEFAULTS_FALLBACK on any error
+}
+```
+
+**Best practices:**
+1. Never trust external JSON → always validate
+2. Use fallback defaults for production safety
+3. Version your preset files
+4. Audit decision traces after rule changes
+
+## Appendix: Full Role Mapping
+
+| Old Role | OMK Role | Default Preset |
+|----------|----------|---------------|
+| Code Writer | `coder` | 8 skills, 3 hooks |
+| Code Reviewer | `reviewer` | 6 skills, 2 hooks |
+| Test Engineer | `tester` | 4 skills, 2 hooks |
+| DevOps | `integrator` | 3 skills, 3 hooks |
+| Architect | `architect` | 4 skills, 1 hook |
+| Researcher | `researcher` | 4 skills, 1 hook |
+| Explorer | `explorer` | 3 skills, 1 hook |
+| Security Auditor | `security` | 4 skills, 3 hooks |
+| QA Engineer | `qa` | 5 skills, 2 hooks |
+| Team Lead | `coordinator` | (add custom preset) |
+
+## See Also
+
+- `src/config/skill-presets.json` — editable runtime presets
+- `src/orchestration/skill-assigner.ts` — assignment engine with validation
+- `src/evidence/decision-trace.ts` — audit trail for all assignments