open-multi-agent-kit 0.78.0

package/docs/cli-v2-migration.md

@@ -0,0 +1,87 @@
+# CLI v2 Migration Guide
+
+## Overview
+
+OMK CLI v2 migrates from Commander.js to Clipanion + Clack for a modern CLI experience matching opencode-style terminal UX.
+
+## Enabling CLI v2
+
+```bash
+OMK_CLI_V2=1 omk <command>
+```
+
+## Migrated Commands
+
+### Core Commands (cli-v2-skeleton.ts)
+| Command | Clipanion Class | Status |
+|---------|----------------|--------|
+| `omk chat` | ChatCommand | ✅ |
+| `omk run` | RunCommand | ✅ |
+| `omk status` | StatusCommand | ✅ |
+| `omk model` | ModelCommand | ✅ |
+| `omk doctor` | DoctorCommand | ✅ |
+| `omk memory` | MemoryCommand | ✅ |
+| `omk theme` | ThemeCommand | ✅ |
+
+### Provider Commands (provider-commands.ts)
+| Command | Clipanion Class | Status |
+|---------|----------------|--------|
+| `omk provider list` | ProviderListCommand | ✅ |
+| `omk provider use` | ProviderUseCommand | ✅ |
+| `omk provider set` | ProviderSetCommand | ✅ |
+| `omk provider enable` | ProviderEnableCommand | ✅ |
+| `omk provider disable` | ProviderDisableCommand | ✅ |
+| `omk provider doctor` | ProviderDoctorCommand | ✅ |
+| `omk provider profiles` | ProviderProfilesCommand | ✅ |
+| `omk model list` | ModelListCommand | ✅ |
+| `omk model aliases` | ModelAliasesCommand | ✅ |
+| `omk model resolve` | ModelResolveCommand | ✅ |
+| `omk model use` | ModelUseCommand | ✅ |
+
+### Workflow Commands (workflow-commands.ts)
+| Command | Clipanion Class | Status |
+|---------|----------------|--------|
+| `omk plan` | PlanCommand | ✅ |
+| `omk feature` | FeatureCommand | ✅ |
+| `omk bugfix` | BugfixCommand | ✅ |
+| `omk refactor` | RefactorCommand | ✅ |
+| `omk review` | ReviewCommand | ✅ |
+| `omk team` | TeamCommand | ✅ |
+| `omk orchestrate` | OrchestrateCommand | ✅ |
+| `omk consent` | ConsentCommand | ✅ |
+
+## Architecture
+
+All CLI v2 commands route through the full runtime pipeline:
+
+```
+User Input → Clipanion CLI → OmkCommand.executePipeline()
+  → CommandBus → IntentClassifier → CapabilitySelector
+  → RuntimeSidecar → OutputRouter → ThemeRenderer/NlpRenderer/JsonRenderer
+```
+
+## Key Files
+
+- `src/cli/v2/cli-v2-skeleton.ts`: Core commands + createCliV2()
+- `src/cli/v2/provider-commands.ts`: Provider + Model commands
+- `src/cli/v2/workflow-commands.ts`: Workflow + Consent commands
+- `src/cli/v2/chat-repl.ts`: Interactive REPL
+- `src/cli/v2/interactive-prompt.ts`: Clack prompts
+- `src/cli/v2/persistent-memory.ts`: Memory store
+- `src/cli/main.ts`: CLI v2 routing (isCliV2Enabled())
+
+## UI/UX Style
+
+CLI v2 uses opencode-style terminal output:
+- `> provider · model` one-line header
+- Spinner animation during processing
+- Compact error display with box drawing
+- Status bar at bottom
+- Bilingual (KO/EN) via i18n
+
+## Testing
+
+```bash
+node --test test/cli-v2-gating.test.mjs  # 7 tests
+node --test test/v2-regression.test.mjs   # 10 tests
+```

package/docs/codex-oauth-setup.md

@@ -0,0 +1,48 @@
+# Codex app / OAuth setup
+
+OMK uses the official Codex app/CLI for Codex authentication. OMK does not store Codex login data, read `~/.codex/auth.json`, or print OAuth/session tokens.
+
+## Recommended flow
+
+1. Install or expose the official Codex CLI/app on `PATH`.
+   ```bash
+   codex --version
+   ```
+2. Complete the official Codex OAuth login.
+   ```bash
+   codex login
+   ```
+3. Ask OMK to guide or run the official login flow.
+   ```bash
+   omk codex auth --choice plus-pro --run
+   omk provider doctor codex --soft
+   ```
+4. Import only safe Codex MCP server configuration when needed.
+   ```bash
+   omk mcp import-codex
+   ```
+
+## Policy
+
+- OMK project configuration lives under `.omk/`.
+- Codex-specific login state remains owned by the official Codex app/CLI.
+- OMK may inspect Codex MCP server configuration, but secret-bearing `headers`, `env`, bearer values, and token files are not copied into project MCP config.
+- Do not `cat` token/session files or paste OAuth values into logs.
+
+## OpenAI Images API is separate
+
+Codex/ChatGPT OAuth proves the Codex CLI login state only. It is not an OpenAI Platform API key.
+
+`omk image generate` and `omk image edit`, including `--model gpt-image-2`, require a separate OpenAI Platform project API key supplied only at runtime.
+
+```bash
+OPENAI_API_KEY=<platform-project-key> omk image generate "OMK control-plane hero" --model gpt-image-2
+```
+
+See [`openai-platform-image-keys.md`](openai-platform-image-keys.md) for the one-shot key flow.
+
+## Troubleshooting
+
+- If `codex` is not found, install the official Codex CLI/app or add it to `PATH`.
+- If login status is unclear, run `codex login`, then `omk provider doctor codex --soft`.
+- If MCP import finds nothing, check whether your Codex config has importable MCP servers.

package/docs/demo/verified-run/README.md

@@ -0,0 +1,32 @@
+# Verified-run demo evidence skeleton
+
+Status: **skeleton only**. This bundle defines TODO/capture slots for a future verified run; it does not contain real proof yet.
+
+## Story
+
+One prompt -> Kimi edits -> OMK blocks premature done -> evidence passes -> cockpit/replay shows proof.
+
+## Bundle map
+
+| Path | Purpose | Status |
+| --- | --- | --- |
+| `raw-prompt.md` | Exact prompt for the capture run | Ready to copy |
+| `generated-diff.md` | Diff capture rules and placeholder metadata | TODO/capture slot |
+| `capture-plan.md` | Commands and paths for verify, cockpit, and replay proof | TODO/capture slots |
+| `video-shot-list.md` | 60-90s recording outline | Ready storyboard |
+| `artifacts/README.md` | Expected raw evidence filenames | TODO/capture slots |
+
+## Acceptance criteria for filling this bundle
+
+- Use a disposable branch or worktree.
+- Capture Kimi's generated diff before manual cleanup.
+- Capture the premature-done block exactly as emitted; if no block occurs, mark the demo failed.
+- Capture `omk verify --json` to the documented JSON path and validate it parses.
+- Capture cockpit and replay proof from the same run id.
+- Do not commit secrets, tokens, private paths requiring redaction, or fabricated outputs.
+
+## Known limitation
+
+This skeleton cannot prove the verified-run story by itself.
+It becomes demo evidence only after TODO slots are filled from a real local run
+with matching run id, timestamps, and captured artifacts.

package/docs/demo/verified-run/artifacts/README.md

@@ -0,0 +1,18 @@
+# Artifact capture slots
+
+This directory is intentionally empty of real proof until a verified demo run is captured.
+
+Expected future files:
+
+- `command-log.txt` — exact run command and environment notes, no secrets
+- `generated-diff.patch` — real Kimi-generated diff
+- `generated-diff.stat.txt` — diff summary
+- `premature-done-block.txt` — exact evidence-gate rejection excerpt
+- `verify-result.json` — real `omk verify --run "$RUN_ID" --json` output
+- `cockpit-proof.png` — screenshot for the same run id
+- `cockpit-proof.txt` — optional text copy of cockpit state
+- `replay-proof.txt` — `omk replay "$RUN_ID" --evidence --decisions` output
+- `replay-proof.png` — screenshot of replay proof
+- `verified-run-demo.mp4` — final 60-90s video
+
+Do not add fabricated sample outputs. Leave absent files absent until captured.

package/docs/demo/verified-run/capture-plan.md

@@ -0,0 +1,51 @@
+# Evidence capture plan
+
+Use one real `RUN_ID` for every artifact below.
+
+```bash
+RUN_ID=<capture-run-id>
+CAPTURE_ROOT=docs/demo/verified-run/artifacts
+mkdir -p "$CAPTURE_ROOT"
+```
+
+## 1. Prompt and command log
+
+- Prompt source: `docs/demo/verified-run/raw-prompt.md`
+- Capture slot: `artifacts/command-log.txt`
+- TODO: record the exact OMK/Kimi command used for the run.
+
+## 2. Premature-done block
+
+- Capture slot: `artifacts/premature-done-block.txt`
+- TODO: save the exact terminal excerpt where OMK rejects completion because evidence is missing.
+- Failure rule: if no block occurs, write `DEMO FAILED: no premature-done block captured` in the slot.
+
+## 3. Verify JSON
+
+```bash
+omk verify --run "$RUN_ID" --json > "$CAPTURE_ROOT/verify-result.json"
+node -e 'JSON.parse(require("fs").readFileSync(process.argv[1], "utf8")); console.log("json ok")' "$CAPTURE_ROOT/verify-result.json"
+```
+
+- Capture slot: `artifacts/verify-result.json`
+- TODO: capture only real command output.
+
+## 4. Cockpit proof
+
+```bash
+omk cockpit --run-id "$RUN_ID" --height 24 --no-clear
+```
+
+- Screenshot capture slot: `artifacts/cockpit-proof.png`
+- Optional text slot: `artifacts/cockpit-proof.txt`
+- TODO: capture the cockpit view showing run state, TODO/evidence status, and changed files.
+
+## 5. Replay proof
+
+```bash
+omk replay "$RUN_ID" --evidence --decisions > "$CAPTURE_ROOT/replay-proof.txt"
+```
+
+- Transcript slot: `artifacts/replay-proof.txt`
+- Screenshot capture slot: `artifacts/replay-proof.png`
+- TODO: capture replay output showing evidence/decision history for the same run.

package/docs/demo/verified-run/generated-diff.md

@@ -0,0 +1,27 @@
+# Generated diff capture slot
+
+Expected future file: `artifacts/generated-diff.patch`
+
+## Capture rules
+
+1. Run the raw prompt in a disposable branch/worktree.
+2. Before manual cleanup, save Kimi's generated diff:
+
+```bash
+git diff --binary > docs/demo/verified-run/artifacts/generated-diff.patch
+git diff --stat > docs/demo/verified-run/artifacts/generated-diff.stat.txt
+```
+
+3. If the diff contains secrets or private data, discard the run and recapture with a safe fixture. Do not hand-edit a proof patch.
+4. Record metadata only after the real patch exists.
+
+## Metadata placeholder
+
+| Field | Value |
+| --- | --- |
+| Run id | TODO: capture |
+| Branch/worktree | TODO: capture |
+| Diff path | `docs/demo/verified-run/artifacts/generated-diff.patch` |
+| Diff stat path | `docs/demo/verified-run/artifacts/generated-diff.stat.txt` |
+| SHA-256 | TODO: capture after file exists |
+| Capture time | TODO: capture |

package/docs/demo/verified-run/raw-prompt.md

@@ -0,0 +1,21 @@
+# Raw prompt for verified-run capture
+
+Copy the block below into the future OMK/Kimi capture session.
+Replace bracketed placeholders before running.
+Do not edit the captured transcript afterward.
+
+```txt
+Goal: Make one tiny, reviewable change in the disposable demo fixture so the run has a real diff and evidence.
+Scope/write ownership: [DEMO_FIXTURE_PATH] only.
+Story requirement: show that OMK does not accept premature completion before evidence exists.
+Then show the run passing after evidence is captured.
+Constraints: no secrets, no production files, no package metadata, no unrelated refactor, no fabricated outputs.
+Required evidence:
+1. generated diff from Kimi's edit
+2. terminal excerpt where premature done is blocked by OMK evidence gate
+3. `omk verify --run [RUN_ID] --json` result
+4. cockpit proof for `[RUN_ID]`
+5. replay proof for `[RUN_ID]` with evidence/decision details
+Stop condition: report done only after evidence exists and `omk verify --json` passes.
+If evidence is missing, leave TODO/capture slots open instead of claiming completion.
+```

package/docs/demo/verified-run/video-shot-list.md

@@ -0,0 +1,14 @@
+# 60-90s verified-run video shot list
+
+| Time | Shot | Proof point |
+| --- | --- | --- |
+| 0-8s | Title card and clean terminal | Demo states: one prompt to verified proof |
+| 8-18s | Paste `raw-prompt.md` into OMK/Kimi | Single prompt starts the run |
+| 18-30s | Show Kimi edit and `git diff --stat` | Real file change exists |
+| 30-42s | Show premature completion blocked | OMK refuses done before evidence |
+| 42-55s | Run `omk verify --run "$RUN_ID" --json` | Machine-readable evidence gate passes |
+| 55-70s | Show cockpit for the same run id | Operator can inspect status and changed files |
+| 70-84s | Show replay evidence/decisions | Proof is reconstructable after the run |
+| 84-90s | End card with known limitation | Skeleton slots must be filled by real capture |
+
+Recording rule: if any TODO slot is missing, keep the video labeled `draft` and do not present it as verified evidence.

package/docs/design-md.md

@@ -0,0 +1,35 @@
+# DESIGN.md Integration
+
+open-multi-agent-kit supports Google DESIGN.md for visual identity.
+
+## Commands
+
+```bash
+omk design init          # Create DESIGN.md
+omk design list          # List awesome-design-md templates
+omk design search vercel # Search awesome-design-md templates
+omk design apply vercel  # Apply a template to DESIGN.md
+omk design lint          # Validate DESIGN.md
+omk design diff A B      # Compare two design files
+omk design export tailwind # Export tokens to Tailwind
+omk design open-design --open # Launch Open Design with OMK bridge + templates
+omk design open-design --doctor --json # Diagnose bridge readiness without side effects
+```
+
+## Skill
+
+The `omk-design-md`, `awesome-design-md`, and `open-design` skills are included in `.kimi/skills/`.
+
+## Open Design
+
+`omk design open-design` registers the **Awesome DESIGN.md Web UI Reference (OMK)** prompt template in Open Design. Use it when a prompt should borrow a named catalog style while preserving local product content and brand-safety guardrails.
+
+Bridge hardening:
+
+- Default public checkout remains `--branch main`; reproducible runs can pin `--ref <branch|tag|sha>` or `OMK_OPEN_DESIGN_REF`. OMK records tested upstream ref `3f7a05e7462f097bf38b7cbac0d4a4593deecd80`.
+- `--doctor --json` checks Node 24, Corepack/pnpm, git, ports, checkout layout compatibility, `OMK_BIN`, app-config, prompt template, and smoke path without clone/install/start side effects.
+- Open Design image/screenshot inputs are forwarded to `open-design-agent --image <path>` as local paths only; Kimi is instructed to use `ReadMediaFile` when available.
+- Timeout success only counts artifacts inside `.omk/open-design-artifacts/<run-id>/` or the explicit `--artifact-dir`; unrelated repo file changes do not mask failures.
+- The bridge filters secret-like child env vars by default. `OPENAI_API_KEY`, OAuth tokens, `*_TOKEN`, `*_SECRET`, and `*_KEY` are not passed to Kimi unless `OMK_OPEN_DESIGN_TRUST_SECRET_ENV=1` is explicitly set.
+
+Open Design outputs must prioritize the local `DESIGN.md` tokens and product constraints. Catalog styles are references, not replacement brand systems.

package/docs/getting-started.md

@@ -0,0 +1,37 @@
+# Getting Started
+
+Source release target: `@omk/cli@0.78.0`.
+
+## Prerequisites
+
+- Node.js 20+
+- Git
+- At least one supported provider or local runtime adapter (Codex CLI, Gemini CLI, Claude Code, OpenRouter, DeepSeek, Kimi, etc.)
+
+## Install
+
+```bash
+npm install -g @omk/cli
+```
+
+## Initialize a project
+
+```bash
+omk init
+```
+
+This creates:
+- `AGENTS.md`, `GEMINI.md`, `CLAUDE.md`, `DESIGN.md`
+- `.kimi/skills/` (runtime adapter skills used by the OMK control loop)
+- `.agents/skills/` (portable skills)
+- packaged workflow skills such as `agentmemory`, `react-doctor`, and `multica`
+- `.omk/` (config, hooks, memory, agents)
+
+## Run
+
+```bash
+omk doctor
+omk chat
+omk plan "refactor auth module"
+omk run feature-dev "add user dashboard"
+```

package/docs/hud-and-parallel-ux.md

@@ -0,0 +1,155 @@
+# HUD and Parallel UX
+
+This document covers the live terminal interfaces for monitoring and executing OMK runs.
+
+---
+
+## HUD (`omk hud`)
+
+The HUD is a **read-only dashboard** that gives you a real-time view of your project, system, and active runs without leaving the terminal.
+
+### Panels
+
+| Panel | Content |
+|-------|---------|
+| **System Usage** | CPU, memory, and disk utilization |
+| **Kimi Usage** | OAuth account badge, 5-hour quota, weekly quota (with optional bar gauges via `OMK_KIMI_STATUS_GAUGES=1`) |
+| **Project Status** | Git branch, changed files count, scaffold health |
+| **Latest Run** | Most recent run ID, goal, status, and health |
+| **TODO / Changed Files** | Sidebar list of open TODOs and uncommitted changes |
+
+### Top Summary Bar
+
+A compact header line shows:
+
+- **Goal** — current or most-recent run goal
+- **Run health** — `healthy` / `degraded` / `blocked` / `unknown`
+- **Next action** — suggested command or recovery step
+
+### Responsive Modes
+
+The HUD adapts to terminal width automatically:
+
+| Width | Layout |
+|-------|--------|
+| `>= 120 cols` | Full dashboard + right rail (all panels + sidebar) |
+| `90–119 cols` | Summary bar + latest run + TODO list |
+| `< 90 cols` | Compact single-column (summary bar + critical gauges only) |
+
+### Flags
+
+| Flag | Behavior |
+|------|----------|
+| `--watch` | Refresh every few seconds (default in TTY) |
+| `--compact` | Force compact layout regardless of width |
+| `--section <name>` | Show only one section: `run`, `project`, or `resources` |
+| `--no-clear` | Do not clear the terminal between refreshes |
+| `--alternate-screen` | Use the terminal alternate screen buffer (no scrollback pollution) |
+
+### Goal-aware Display
+
+The HUD resolves the current goal in this priority order:
+
+1. `.omk/goals/<id>/goal.json` — active goal file
+2. RunState snapshot — goal embedded in the latest persisted run
+3. `goal.md` — fallback project goal document
+
+### State Error UX
+
+If a run state file is corrupt, missing, or invalid, the HUD shows a **recovery suggestion** instead of crashing:
+
+- Missing state → prompt to run `omk parallel <goal>` or `omk run <flow> <goal>`
+- Corrupt JSON → suggest checking `.omk/runs/` or running `omk doctor`
+- Invalid schema → display the validation error and a link to relevant docs
+
+---
+
+## Parallel (`omk parallel`)
+
+Parallel is the **DAG executor with live UI**. It orchestrates coordinator → worker fan-out → reviewer runs and renders progress in real time.
+
+Runtime/provider UI fields should follow the canonical routing and worker-scope
+contracts in
+[`native-root-runtime-algorithms.md`](./native-root-runtime-algorithms.md):
+Algorithm 5 for selected runtime, fallback chain, and route evidence;
+Algorithm 7 for worker environment/capability scope.
+
+### Header
+
+The top of the parallel UI shows:
+
+- **Goal** — the task being executed
+- **Run ID** — unique timestamped identifier
+- **Workers** — number of active worker slots
+- **Approval policy** — `yolo`, `confirm`, or `reject`
+- **Mode** — `watch` or `no-watch`
+
+### Worker Grid
+
+Each worker is rendered as a labeled card:
+
+- **Role label** — e.g., `coder`, `reviewer`, `qa`
+- **Elapsed time** — since the worker started its current task
+- **Retry count** — number of retries for the current node
+
+### Blocker Panel
+
+Shown **only when a node fails or is blocked**:
+
+- Failed node name and role
+- Error summary
+- Suggested recovery action (e.g., `omk chat --run-id <id>`, `omk summary`)
+
+### Completion Panel
+
+When the run finishes, a completion panel appears with next steps:
+
+```txt
+Run complete. Next steps:
+  omk summary          → generate summary.md + report.md
+  omk verify           → run quality gates on the result
+  omk chat --run-id    → resume interactively
+```
+
+### Flags
+
+| Flag | Behavior |
+|------|----------|
+| `--watch` | Live UI refresh every 1.5 s (default in TTY) |
+| `--no-watch` | Static output, no refresh (default non-TTY) |
+| `--alternate-screen` | Full-screen alternate buffer (opt-in) |
+| `--no-pause` | Do not pause on completion; exit immediately |
+| `--compact` | Force compact worker grid layout |
+
+### Trust
+
+- Alternate screen is **opt-in** (`--alternate-screen`).
+- No forced scrollback loss: without the flag, output is appended to the main terminal buffer so you can scroll back through history.
+
+---
+
+## RunViewModel
+
+`RunViewModel` is the **shared abstraction** between HUD and parallel UI. It interprets raw run state into a consistent, display-ready model.
+
+### Inputs
+
+| Input | Source |
+|-------|--------|
+| `RunState` | `.omk/runs/<run-id>/run-state.json` |
+| Goal (optional) | `.omk/goals/<id>/goal.json` or `goal.md` |
+| Changed files | `git status --short` |
+
+### Outputs
+
+| Output | Description |
+|--------|-------------|
+| **Health** | `healthy` / `degraded` / `blocked` / `unknown` |
+| **Progress** | Completed nodes / total nodes |
+| **ETA** | Estimated time remaining (when enough data exists) |
+| **Active node** | Currently executing node + role |
+| **Blocker** | First blocking or failed node, if any |
+| **Workers** | Array of active workers with elapsed time and retry count |
+| **Runtime route** | Selected provider/runtime, fallback chain, risk, sandbox, and approval policy when available |
+
+Both HUD and parallel UI consume the same `RunViewModel`, so their interpretations of run health and progress are always consistent.

package/docs/kimi-oauth-usage-status.md

@@ -0,0 +1,33 @@
+# Kimi OAuth usage status line
+
+OMK augments the Kimi interactive context status line with a compact local usage badge:
+
+```txt
+context: 35.6% (93.2k/262.1k) | in:93.2k out:1.8k | omk:acct:de…r@example.com | 5h:70% left | wk:80% left
+```
+
+## What is shown
+
+- `acct`: the current `/login` OAuth identity from `~/.kimi/credentials/kimi-code.json`.
+  - Tokens are never printed.
+  - Emails/usernames are masked.
+  - If no safe identity claim exists, OMK shows a stable hashed `oauth:<hash>` id.
+- `5h`: Kimi Code 5-hour quota remaining when `/usages` is reachable.
+- `wk`: Kimi Code weekly quota remaining when `/usages` is reachable.
+- If the remote quota endpoint is unavailable, OMK falls back to local session-time estimates from `~/.kimi/sessions`.
+
+## Implementation
+
+The wrapper does not patch Kimi's installed Python package. Instead, `runKimiInteractive()` post-processes PTY output and appends the OMK badge whenever it sees Kimi's native `context:` status span.
+
+Disable the badge if needed:
+
+```bash
+OMK_KIMI_STATUS_USAGE=0 omk chat
+```
+
+The HUD also uses the same OAuth/usage reader:
+
+```bash
+omk hud
+```

package/docs/kimi-okabe-dmail.md

@@ -0,0 +1,44 @@
+# Kimi Okabe + D-Mail context recovery
+
+open-multi-agent-kit exposes a Kimi adapter lane. Generated root and role agents inherit an Okabe-compatible base agent that keeps the default tools and adds Kimi's `SendDMail` tool.
+
+## Why it matters
+
+Okabe/D-Mail is the fast context-safety layer:
+
+- use Okabe for smart context management instead of stuffing the main prompt with every detail;
+- send D-Mail before risky refactors, dependency migrations, long-running multi-agent handoffs, or `/compact`;
+- keep D-Mail notes short and future-facing so rollback/recovery knows the goal, changed files, tests, blockers, and next action.
+
+Project-local ontology graph memory is the durable project/session memory layer. D-Mail is for checkpoint recovery; graph memory is for long-term recall. Embedded Kuzu remains available when Cypher-style graph queries are needed.
+
+## Generated agent default
+
+Official Kimi docs expose built-in `okabe` via `kimi --agent okabe`, and note `--agent` / `--agent-file` are mutually exclusive. Because OMK uses custom `--agent-file` configs, it ships an `okabe.yaml` base that extends `default` and adds `kimi_cli.tools.dmail:SendDMail`.
+
+
+Generated `.omk/agents/*.yaml` files use:
+
+```yaml
+agent:
+  extend: ./okabe.yaml  # Okabe-compatible base adds SendDMail/D-Mail checkpoints
+```
+
+## Recommended D-Mail shape
+
+```txt
+Goal:
+Checkpoint reason:
+Changed files:
+Verification:
+Blockers:
+Next action:
+Rollback note:
+```
+
+Do not put secrets in D-Mail. Store durable, non-secret project facts through `omk_write_memory`; inspect ontology recall through `omk_memory_mindmap` or `omk_graph_query`.
+
+## References
+
+- Kimi Code CLI Agents and Subagents: https://moonshotai.github.io/kimi-cli/en/customization/agents.html
+- Kimi command agent flags: https://moonshotai.github.io/kimi-cli/en/reference/kimi-command.html