open-multi-agent-kit 0.78.8 → 0.79.3

package/README.md

@@ -1,392 +1,111 @@
-<p align="center">
-  <img src="readmeasset/omk-control.webp" alt="OMK//CONTROL Night City Ops Console for routing agents, evidence gates, telemetry, MCP scope, and operator control" width="100%" />
-</p>
+# OMK
 
-<h1 align="center">OMK</h1>
+Run multiple coding agents safely in one repo.
 
-<p align="center">
-  <strong>OMK//CONTROL — provider-neutral multi-agent control plane for coding workflows.</strong>
-</p>
+OMK turns a coding task into a scoped DAG run: it routes the right model, limits tool access, requires evidence, and saves replayable artifacts before claiming success.
 
-<p align="center">
-  Models execute. OMK routes, verifies, measures, and controls.
-</p>
+Use it when one agent is too loose, too risky, or too hard to audit.
 
-<p align="center">
+<p>
   <a href="https://www.npmjs.com/package/open-multi-agent-kit"><img alt="npm version" src="https://img.shields.io/npm/v/open-multi-agent-kit?color=00D6FF"></a>
-  <a href="https://www.npmjs.com/package/open-multi-agent-kit"><img alt="npm package" src="https://img.shields.io/badge/package-open--multi--agent--kit-FF47B2"></a>
-  <a href="docs/versioning.md"><img alt="runtime contract" src="https://img.shields.io/badge/contract-v1.2_pre--1.0-9D4EDD"></a>
-  <a href="https://github.com/dmae97/open-multi-agent-kit/blob/main/proof/PROOF_INDEX.md"><img alt="proof check" src="https://img.shields.io/badge/proof--check-source-00FFC2"></a>
   <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue.svg"></a>
+  <a href="https://github.com/dmae97/open-multi-agent-kit/blob/main/proof/PROOF_INDEX.md"><img alt="proof check" src="https://img.shields.io/badge/proof--check-source-00FFC2"></a>
+  <a href="https://github.com/dmae97/open-multi-agent-kit/discussions"><img alt="discussions" src="https://img.shields.io/badge/discussions-open-9D4EDD"></a>
 </p>
 
-<p align="center">
-  <a href="#install">Install</a> ·
-  <a href="#quick-start">Quick start</a> ·
-  <a href="#who-is-this-for">Who is this for?</a> ·
-  <a href="#current-runtime-algorithm">Runtime algorithm</a> ·
-  <a href="docs/getting-started.md">Docs</a> ·
-  <a href="readmeasset/ASSET_INDEX.md">Visual assets</a>
-</p>
-
-`OMK` (`omk`) turns a coding goal into a bounded, evidence-gated agent run.
-
-Use OMK when one coding agent is not enough: route Codex, OpenCode, Kimi, DeepSeek, Qwen, OpenRouter, and local runtimes through one evidence-gated control loop.
-
-## Who is this for?
-
-- Developers running multiple coding agents from the terminal.
-- Teams that need MCP-scoped agent execution instead of unrestricted tool access.
-- Agent builders who want routing, fallback, evidence gates, telemetry, and replay.
-
-> Current package source target: `open-multi-agent-kit@0.78.8`.
-> Public package name: `open-multi-agent-kit` (`@omk/cli` is not the active npm package).
-> Runtime contract family: `v1.2` (contract family, not a stable npm `1.x` release).
-> Release channel: `pre-1.0`.
-> See [versioning](docs/versioning.md) and [provider maturity](docs/provider-maturity.md).
-
-## Quickstart (3 minutes)
-
-A beginner reads this, runs four commands, and reaches an initialized OMK chat/doctor flow.
+## 30-second demo
 
 ```bash
-npm i -g open-multi-agent-kit
-omk init
-omk doctor
-omk chat
+npx -y -p open-multi-agent-kit omk do "review this repo for release risk" --dry-run --json
 ```
 
-## Examples for agent tooling lists
-
-- [Codex MCP evidence run](https://github.com/dmae97/open-multi-agent-kit/tree/main/examples/codex-mcp-evidence-run): project-scoped MCP setup plus evidence-gated DAG dry run.
-- [Provider fallback](https://github.com/dmae97/open-multi-agent-kit/tree/main/examples/provider-fallback): `--provider auto` routing with parallel worker planning.
-
-## Current release reality
-
-- The public npm line is `open-multi-agent-kit@0.78.x`. The source target is `open-multi-agent-kit@0.78.8`;
-  treat npm `latest` as release-truthful only after the tagged release workflow and registry verification both pass.
-- The `v1.2` label in docs is a runtime contract family for the source tree, not a claim that
-  an npm `1.2.x` stable release exists.
-- Provider support is intentionally uneven: Kimi remains the most mature authority path;
-  Codex/OpenCode/CommandCode depend on local CLIs; MiMo/DeepSeek/Qwen/OpenRouter/local LLM
-  lanes are scoped by the provider-maturity contract.
-- Safety and evidence claims apply to the exact adapter, command, and verification gate that
-  produced them.
-- Regression Proof Matrix is a release-defense coverage gate, not a stable-release claim.
-  Stable promotion still requires full tests, live provider maturity data, and a minimal verified demo pass.
-
-## Why OMK
+OMK should produce a bounded plan before changing files:
 
-Most coding agents optimize for a single prompt/result loop. OMK wraps agent execution with a control-plane algorithm:
+```txt
+goal
+  review this repo for release risk
 
-- compile the user goal into a DAG coordinator turn;
-- inject only scoped MCP servers, skills, hooks, memory, and tools;
-- classify task intent and route to compatible runtime adapters;
-- execute with timeout, approval, sandbox, and fallback metadata;
-- require evidence before completion claims;
-- preserve run artifacts for replay, inspection, and audit.
+flow
+  goal -> input envelope -> DAG -> scoped lanes -> evidence -> verify
 
-## OMK//CONTROL visual console
-
-The GitHub visual set presents OMK as a Night City Ops Console: route status, DAG lanes, provider fallback, scoped MCP, evidence gates, replayable run telemetry, and publish-time assertions. Assets are provenance-covered in [`readmeasset/ASSET_PROVENANCE.md`](readmeasset/ASSET_PROVENANCE.md).
-
-<p align="center">
-  <img src="readmeasset/omk_tui.png" alt="OMK//CONTROL terminal dashboard — live DAG lanes, provider routing, MCP health, evidence gates, and telemetry in Night City Ops Console style" width="100%" />
-</p>
-
-| Operator TUI                                                                                                                                                                                            | Runtime flow                                                                                                                                                                                                                            |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| <img src="readmeasset/omk-tui-0.78.0.webp" alt="OMK//CONTROL TUI for OMK 0.78.0 showing Codex App OAuth routing, GPT Image 2 asset lane, DAG lanes, scoped MCP, and evidence gates" /> | <img src="readmeasset/omk-runtime-flow-0.78.0.webp" alt="OMK 0.78.0 runtime flow diagram: user goal, intent classifier, DAG compiler, runtime router, parallel workers, evidence bundle, verify gate, and merge replay inspect loop" /> |
-
-| Install lane                                                                     | Provider router                                                                       | Evidence gate                                                                     |
-| -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- |
-| <img src="readmeasset/omk-install-card.png" alt="OMK install quickstart card" /> | <img src="readmeasset/omk-provider-router-card.png" alt="OMK provider router card" /> | <img src="readmeasset/omk-evidence-gate-card.png" alt="OMK evidence gate card" /> |
-
-<p align="center">
-  <img src="readmeasset/omk-core-loop.svg" alt="OMK core loop: goal to DAG plan to evidence to verify to replay" width="100%" />
-</p>
-
-| Control surfaces | Release assertions |
-| ---------------- | ------------------ |
-| <img src="readmeasset/omk-control-surfaces.svg" alt="OMK control surfaces: CLI, provider router, MCP scope, evidence gate, replay ledger, and package audit" /> | <img src="readmeasset/omk-release-assertions.svg" alt="OMK release assertions: package name, CLI bins, release gates, package-safe exclusions, and registry verification" /> |
-
-## Install
-
-Requires Node.js `>=20` and npm `>=10`. The [3-minute route](#quickstart-3-minutes) uses the global install; these are the alternatives:
-
-Project/local install:
-
-```bash
-npm i open-multi-agent-kit
-npx omk --help
+artifacts (dry run)
+  .omk/runs/<run-id>/input-envelope.json
+  .omk/runs/<run-id>/dag.json
+  .omk/runs/<run-id>/dag-compile-report.json
 ```
 
-No install:
+Executing (not dry-run) adds loop artifacts such as `.omk/runs/<run-id>/loop-state.json` and `.omk/runs/<run-id>/loop-decisions.jsonl`. Artifact names can evolve with the runtime contract; the invariant is that OMK persists reviewable run state before a worker claims completion.
 
-```bash
-npx -p open-multi-agent-kit omk doctor
-```
-
-## Quick start
-
-The [3-minute route](#quickstart-3-minutes) is the canonical path. Beyond it, add provider auth and orchestration:
+## Install
 
 ```bash
-omk codex auth --choice plus-pro # optional; requires official Codex app/CLI login
-omk chat --provider auto --mode agent
-omk orchestrate "ship feature" --workers 4 --dry-run
-```
-
-## Current runtime algorithm
-
-The canonical algorithm definitions live in [Native Root Runtime Algorithms](docs/native-root-runtime-algorithms.md). README summary:
-
-### 1. Native root turn execution
-
-```text
-Read user input
-  → dispatch slash commands locally
-  → build scoped MCP/skills/hooks capability injection
-  → build prompt envelope
-  → materialize a DAG coordinator node
-  → run selected runtime with timeout/abort handling
-  → stream output, sync TODOs, attach evidence
-```
-
-This is the interactive root loop used by `omk chat`. It treats shell exits, slash commands, prompt envelopes, TODO sync, and recent output as controlled runtime state instead of loose chat text.
-
-### 2. Native root turn node construction
-
-```text
-User prompt
-  → infer risk: read | write | shell | merge
-  → normalize scoped capabilities
-  → choose provider-neutral routing policy
-  → attach approval/sandbox metadata
-  → produce coordinator DAG node
-```
-
-Read-only turns stay read-only. Write, shell, and merge turns get explicit capability metadata. DeepSeek-style advisory lanes are kept read/review when the risk is not safe for write authority.
-
-### 3. Runtime-backed task runner
-
-```text
-DAG node
-  → run state
-  → context capsule
-  → provider-neutral AgentTask
-  → RuntimeRouter.execute(task)
-  → TaskResult with selected runtime + fallback chain
-```
-
-OMK converts DAG context into an adapter-neutral task so Codex, MiMo, Kimi API/print lanes, DeepSeek, Qwen, OpenRouter, local adapters, or future runtimes can participate through the same contract when configured. That contract does not imply equal write/merge authority for every adapter.
-
-### 4. Intent-aware runtime routing and fallback
-
-```text
-Classify intent
-  → filter compatible runtimes
-  → score by quality, evidence pass rate, and recent failures
-  → execute best runtime
-  → fallback in ranked order when a runtime fails
-  → record selected runtime, intent, scores, and fallback chain
-```
-
-Provider routing is evidence-aware, not just provider-name matching. Failed or low-evidence lanes are penalized; compatible healthy lanes can take over.
-
-### 5. Secure worker transport and scoped environment
-
-```text
-Worker prompt
-  → stdin transport where supported, not process argv
-  → scoped agent file when needed
-  → sanitized child environment
-  → OMK_RUN_ID / OMK_NODE_ID / OMK_NODE_ROLE metadata
-```
-
-Kimi worker prompts use stdin with `--input-format text` where that adapter path applies. All worker environment claims are scoped to the exact adapter and evidence gates; private prompt envelopes and run artifacts remain trusted local data.
-
-## Core loop
-
-```text
-Goal → DAG plan → parallel lanes → evidence bundle → verify gate → merge / replay / inspect
+npm install -g open-multi-agent-kit
+omk init
+omk doctor
+omk chat
 ```
 
-## Goal lifecycle
-
-`omk goal` turns a raw goal into a planned, evidence-gated run. The **OMK Deep Interview** is an uncertainty reducer that clarifies the goal before planning, so the DAG is compiled from a structured spec instead of a vague prompt.
-
-Recommended flow:
+For local verification from a checkout:
 
 ```bash
-omk goal interview "<raw goal>" --depth deep --write-spec
-omk goal plan <goal-id>
-omk goal run <goal-id> --provider auto --approval-policy interactive
-omk goal verify <goal-id>
+npm ci
+npm run build
+node dist/cli.js do "explain this repo" --dry-run --json
+npm run verify:no-kimi
 ```
 
-### `omk goal interview [input]`
+## Use OMK if you
 
-Runs a deterministic deep interview that scores goal ambiguity (`0..1`), ranks targeted questions, assimilates answers into a structured spec delta, computes a completeness score, and (with `--write-spec`) creates or updates a `GoalSpec`. Question ranking is deterministic:
+- use Codex, Claude Code, OpenCode, DeepSeek, Qwen, OpenRouter, MiMo, or local models in the same repo;
+- want agents to produce evidence before saying “done”;
+- need read/write/shell authority separated by task;
+- want replayable `.omk/runs/` artifacts for review;
+- need project-scoped MCP, skills, hooks, and provider lanes instead of ambient global tool access.
 
-```text
-score = informationGain*0.35 + riskReduction*0.25 + dagImpact*0.20 + evidenceImpact*0.15 - userCost*0.05
-```
-
-| Option                     | Purpose                                                         |
-| -------------------------- | -------------------------------------------------------------- |
-| `--goal-id <id>`           | Target an existing goal.                                       |
-| `--mode <create\|refine>`  | Create a new spec or refine an existing one.                   |
-| `--depth <light\|standard\|deep>` | Interview depth; omit to auto-select by ambiguity.      |
-| `--max-questions <n>`      | Cap the number of ranked questions.                           |
-| `--answers <file>`         | Supply answers non-interactively.                             |
-| `--write-spec`             | Persist the spec delta into a `GoalSpec`.                     |
-| `--json`                   | Emit the `omk.interview.v1` JSON contract.                    |
-
-### `omk goal refine <goal-id>`
-
-Applies the latest interview spec delta to a goal and optionally replans.
-
-| Option                  | Purpose                                          |
-| ----------------------- | ------------------------------------------------ |
-| `--from-interview <id>` | Source interview session (default: latest).      |
-| `--plan`                | Replan the goal after applying the delta.         |
-| `--json`                | Emit machine-readable output.                     |
-
-Answers file format (`--answers answers.json`):
-
-```json
-{
-  "answers": [
-    { "questionId": "q-success-criteria", "answer": "..." }
-  ]
-}
-```
+## How OMK differs
 
-Session artifacts (`interview.json`, `spec-delta.json`, `questions.md`, `answers.jsonl`, `interview-report.md`) are written under `.omk/goals/<goalId>/interviews/<sessionId>/`, or `.omk/interviews/<sessionId>/` before `--write-spec`.
+| Tool type | Good at | Missing piece | OMK adds |
+| --- | --- | --- | --- |
+| Codex / Claude Code | Strong single-agent execution | Audit and routing layer | DAG, evidence, replay |
+| OpenCode | Terminal coding loop | Multi-provider governance | Provider authority + gates |
+| MCP servers | Tool access | Task-level control | Scoped MCP per lane |
+| CI | Post-hoc verification | Agent-time enforcement | Evidence before completion |
 
 ## What OMK controls
 
-| Surface            | What OMK does                                                                                           |
-| ------------------ | ------------------------------------------------------------------------------------------------------- |
-| DAG orchestration  | Plans, routes, executes, merges, replays, and inspects agent work.                                      |
-| Evidence gates     | Requires command output, diff, artifact, metric, or review proof before “done”.                         |
-| Provider routing   | Selects compatible runtimes with intent, capability, evidence, and fallback metadata.                   |
-| MCP scope          | Keeps project MCP, skills, hooks, and graph memory scoped instead of importing global secrets silently. |
-| Worktree isolation | Keeps parallel lanes bounded, reviewable, and recoverable.                                              |
-| Operator telemetry | Exposes route, status, blockers, TODOs, run health, and evidence state through CLI/HUD/TUI surfaces.    |
-| Security boundary  | Sanitizes child env, protects secrets, and makes workspace-write routes explicit.                       |
-
-## Provider lanes
-
-OMK is provider-neutral, but providers are not equally mature or equally authorized:
-
-- **Kimi API / print lanes**: most mature authority path and compatibility fallback when configured.
-- **MiMo**: default/read-review-thinking path when configured; direct workspace-write authority is not claimed for the API runtime.
-- **Codex app / CLI OAuth lanes**: compatibility path through the official Codex CLI/app login; local CLI availability and policy decide what can run.
-- **OpenCode / CommandCode CLI lanes**: compatibility paths when the local CLI and auth are present.
-- **DeepSeek, Qwen, OpenRouter, local LLM adapters**: advisory/read/review/QA/research lanes unless a tested contract grants more authority.
-- **GPT Image 2 asset lane**: visual asset workflow only when explicitly selected and separately configured.
-
-See [provider maturity](docs/provider-maturity.md) before treating any non-Kimi lane as an authority/write/merge path.
-
-## Codex app / OAuth first
-
-For Codex lanes, OMK delegates auth to the official Codex app/CLI and never reads or prints `~/.codex/auth.json` tokens.
-
-```bash
-codex login
-omk codex auth --choice plus-pro --run
-omk provider doctor codex --soft
-```
-
-Codex/ChatGPT OAuth is for Codex CLI sessions. `omk image generate/edit --model gpt-image-2` remains an OpenAI Images API call and requires a separate OpenAI Platform project API key. See [Codex OAuth setup](docs/codex-oauth-setup.md) and [OpenAI image keys](docs/openai-platform-image-keys.md).
-
-## CLI and package contract
-
-The npm package is intentionally package-safe:
-
-| Contract          | Value                                                                                                                                                                                                                          |
-| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| Package           | [`open-multi-agent-kit`](https://www.npmjs.com/package/open-multi-agent-kit)                                                                                                                                                   |
-| Version           | `0.78.8`                                                                                                                                                                                                                       |
-| Runtime contract family | `v1.2`                                                                                                                                                                                                                         |
-| Bins              | `omk`, `omk-project-mcp`, `omk-acp`, `omk-mcp-host`                                                                                                                                                                            |
-| Packaged docs     | `README.md`, `docs/`, `SECURITY.md`, `ROADMAP.md`, `MATURITY.md`, `DESIGN.md`                                                                                                                                                  |
-| Packaged branding | Canonical hero/social/TUI/runtime images plus the curated derivative gallery documented in [`readmeasset/ASSET_INDEX.md`](readmeasset/ASSET_INDEX.md) and [`readmeasset/ASSET_PROVENANCE.md`](readmeasset/ASSET_PROVENANCE.md) |
-| Release assertions | README and package audit assert package name/version, required CLI bins, package-safe file set, local-state exclusions, proof metadata, and registry-verification wording. |
-| Excluded          | source-only tests, scripts, local state, logs, secrets, private runtime directories                                                                                                                                            |
-
-Release checks:
-
-```bash
-npm run version:check
-npm run proof:check
-npm run pack:dry
-npm run audit:package
-```
-
-What those checks assert before publish:
-
-- `package.json` and `package-lock.json` agree on `open-multi-agent-kit` and the current package version.
-- The npm tarball exposes `omk`, `omk-project-mcp`, `omk-acp`, and `omk-mcp-host` from `dist/` with executable shebangs.
-- README/docs/changelog/release-truthfulness proof metadata mention the same package version and keep `v1.2` scoped to runtime contracts.
-- The packaged file set includes docs, templates, and provenance-covered README assets while excluding source, tests, local `.omk`/`.kimi` state, logs, tarballs, and secret-shaped files.
-- Published-version claims remain conditional until the tagged workflow and npm registry verification both pass.
-
-## Contract versions
-
-Machine-readable contracts currently include:
-
-- `omk.contract.v1`
-- `omk.evidence.v1`
-- `omk.decision.v1`
-- `omk.run-manifest.v1`
-- `omk.provider.v1`
-- `omk.version.v1`
-- `omk.proof-bundle.v1`
-
-Schemas live in the source-tree `schemas/` directory and are checked with:
-
-```bash
-npm run schema:check
+```text
+Goal → DAG plan → scoped lanes → evidence bundle → verify gate → replay / inspect
 ```
 
-## Known implementation caveats
-
-The runtime algorithms are the current contract target, with adapter-specific hardening still tracked in docs and tests:
+- **Routing**: choose a compatible provider/runtime for the task.
+- **Authority**: keep read, write, shell, and merge powers explicit.
+- **Evidence**: require command output, diff, artifact, metric, or review proof.
+- **Replay**: save run artifacts under `.omk/runs/<run-id>/` for review.
+- **Scope**: keep MCP servers, skills, hooks, and memory bounded per lane.
 
-- `/provider` is restart-only in the native root loop.
-- `/model` is UX debt until live mutation or restart-only behavior is enforced consistently.
-- Approval and sandbox metadata are preserved in task contracts; enforcement depends on the adapter path.
-- Provider health probes do not yet uniformly separate binary/API presence, auth, model support, and quota state across every adapter.
-- Safety claims are scoped to exact adapter, command, evidence, and package-audit results.
+## Examples
 
-## Brand system
-
-Public copy stays OMK-owned: **OMK//CONTROL**, **NEON GRID ONLINE**, route/evidence/loop/control language, and the **Night City Ops Console** palette. The README/NPM hero, social preview, TUI mock, runtime-flow diagram, and derivative gallery are package-safe brand assets with provenance in [`readmeasset/ASSET_PROVENANCE.md`](readmeasset/ASSET_PROVENANCE.md).
-
-## Docs
+- [Codex MCP evidence run](https://github.com/dmae97/open-multi-agent-kit/tree/main/examples/codex-mcp-evidence-run): project-scoped MCP setup plus evidence-gated DAG dry run.
+- [Provider fallback](https://github.com/dmae97/open-multi-agent-kit/tree/main/examples/provider-fallback): `--provider auto` routing with fallback planning.
+- [Proof index](https://github.com/dmae97/open-multi-agent-kit/blob/main/proof/PROOF_INDEX.md): source-controlled proof bundles checked by `npm run proof:check`.
 
-- [Getting started](docs/getting-started.md)
-- [Runtime versioning](docs/versioning.md)
-- [Provider maturity](docs/provider-maturity.md)
-- [Native root runtime algorithms](docs/native-root-runtime-algorithms.md)
-- [Codex OAuth setup](docs/codex-oauth-setup.md)
-- [Ouroboros integration](docs/integrations/ouroboros.md)
-- [Security policy](SECURITY.md)
+## Maturity and safety claims
 
-## Security
+Current source version: `open-multi-agent-kit@0.79.3`.
 
-Safe by default: child env is sanitized, ambient secrets are dropped, and workspace-write routes require approval. OS-level sandboxing is planned, not claimed; see [SECURITY.md](SECURITY.md).
+- Public package name: `open-multi-agent-kit`.
+- Runtime contract family: `v1.2` means contract family, not a stable npm `1.x` release.
+- Release channel: `pre-1.0`.
+- OS-level sandboxing is planned, not claimed; child env hardening and approval gates are adapter-specific.
+- registry verification: treat npm `latest` claims as valid only after tagged CI and registry checks pass.
 
-Safety checks run as pure TypeScript (no native/Rust build step). The former Rust `omk-safety` probe was retired; see [docs/adr/0001-no-native-rust-lane.md](docs/adr/0001-no-native-rust-lane.md).
+See [versioning](docs/versioning.md), [provider maturity](docs/provider-maturity.md), and [SECURITY.md](SECURITY.md).
 
-## Links
+## Community
 
-- GitHub: <https://github.com/dmae97/open-multi-agent-kit>
-- NPM: <https://www.npmjs.com/package/open-multi-agent-kit>
-- Releases: <https://github.com/dmae97/open-multi-agent-kit/releases>
+- Ask setup and provider questions in [Discussions](https://github.com/dmae97/open-multi-agent-kit/discussions).
+- File reproducible bugs in [Issues](https://github.com/dmae97/open-multi-agent-kit/issues).
+- If you want safer multi-agent coding runs, star the repo to follow the `v0.8` release line.
 
 ## License
 

package/ROADMAP.md

@@ -1,35 +1,27 @@
 # Roadmap
 
-Current source version: v0.78.1 (`v1.2` runtime contract family)
-Last updated: 2026-06-07
+Current source version: v1.1.18
+Last updated: 2026-05-24
 
-## 2026-06-07 release reality
+## 2026-05-24 runtime hardening status
 
-The public npm package line is `open-multi-agent-kit@0.78.x`. The `v1.2` label below is the source-tree runtime contract family, not a claim that a stable npm `1.2.x` package has shipped.
+Latest pushed source on `new-origin/main` is `6305e2b62185c11549f59e2340936769a3027cdd`. This supersedes the earlier native-root pivot commit in the same line. The architecture direction remains OMK-as-root with Kimi as the default coding adapter, but the current line is still hardening-gated:
 
-The v1.1.x/v1.2 rows in this file are historical source checkpoints and architecture milestones unless a row explicitly says it was npm-published. Current public-release work should be judged against the exact target commit, CI/smoke status, package audit, and npm dist-tag state.
+- GitHub Actions Smoke Test is green on `6305e2b`.
+- GitHub Actions CI is red on Windows jobs on `6305e2b`; do not publish/tag v1.1.18 until this is fixed.
+- The active architecture backlog is now tracked in `docs/native-root-runtime-hardening.md`, `docs/native-root-runtime-algorithms.md`, and `.omk/specs/native-orchestrator-phase1/`.
 
-## Historical 2026-05-31 v1.2 contract checkpoint
+## v1.1.9 reality
 
-At the 2026-05-31 checkpoint, the source tree was being aligned toward a `v1.2` runtime contract and an internal RC packaging target. That checkpoint is useful architectural history, but it is not the current public npm package line. The architecture direction is OMK-as-root with providers as adapters. Kimi remains the most mature authority path; other providers have narrower or advisory maturity unless tests and contracts say otherwise.
-
-- Version contract details: `docs/versioning.md`.
-- Provider status and limitations: `docs/provider-maturity.md`.
-- Public proof index: `proof/PROOF_INDEX.md`.
-- Active native-runtime backlog: `docs/native-root-runtime-hardening.md`, `docs/native-root-runtime-algorithms.md`, and `.omk/specs/native-orchestrator-phase1/`.
-- Do not claim stable npm `1.x` status until release gates pass on the exact target commit and the stable package/tag is published.
-
-## Historical v1.1.9 source reality
-
-Provider routing and graph viewing are no longer purely future work in the source tree, but these notes are historical and provider-dependent:
+Provider routing and graph viewing are no longer purely future work:
 
 - `omk run`, `omk parallel`, and DAG replay expose `--provider auto|kimi`.
 - `omk provider` / `omk deepseek` manage DeepSeek enablement, key setup, availability checks, and default fallback to the most mature adapter.
-- DeepSeek is an opportunistic read-only/advisory worker; Kimi remains the most mature authority adapter in this historical line, while v1.2 RC moves orchestration ownership into OMK.
+- DeepSeek is an opportunistic read-only/advisory worker; Kimi remains the most mature adapter, orchestrator, writer, merger, and final authority.
 - `omk graph view` generates an HTML view from `.omk/memory/graph-state.json`.
 - `omk goal` has a persisted lifecycle, continue loop, generated plan/evidence criteria, and verification flow.
 
-## v1.2 contract hardening — Native Orchestrator Decoupling
+## v1.2 — Native Orchestrator Decoupling
 
 ### Phase 0: Foundation & Spec
 
@@ -68,37 +60,34 @@ Provider routing and graph viewing are no longer purely future work in the sourc
 
 - Update `AGENTS.md`, `DESIGN.md`, init templates, and skill docs to reflect OMK-as-root narrative.
 - Deprecate Kimi-only subagent language where OMK `ParallelOrchestrator` is the actual spawn surface.
-- Mark v1.2.x stable only after provider fallback, evidence gates, DAG replay, version contracts, and provider-maturity docs are green across supported adapters.
+- Mark v1.2.x stable once provider fallback, evidence gates, and DAG replay are green across all supported adapters.
 
-## Post-0.78 hardening — current surface
+## v1.3 — Hardening the current surface
 
 ### P0: release and contract gates
 
-- Source implemented: YAML validation runs in local `verify` plus CI/smoke workflows.
-- Source verified in recent gates: package dry-pack, package audit, tarball smoke, native safety build, and release matrix coverage. Public publish/tag claims still depend on the exact target commit.
-- Required before a public npm publish/tag: regenerate the native safety binary if the target platform artifacts changed, pass package audit, pass smoke-pack/tarball install smoke, and pass `npm run release:check` or the documented CI equivalent on the exact intended release diff.
-- Required before a public npm publish/tag: CI and smoke checks must pass on the exact intended commit.
-- Source implemented: provider/deepseek and screenshot JSON command contracts have hermetic regression tests.
-- Source implemented: proof bundle schema/check/index scaffolding exists, with scoped hardening bundles covering no-Kimi smoke, doctor-provider, fallback-route, native-safety, contract-version, evidence-block, replay/inspect, graph-audit, deeper no-Kimi verification, and provider fallback-routing gates.
-- Source implemented: proof integrity enforces artifact linkage plus per-bundle `sha256sums.txt` hash validation.
-- Source implemented: current AGENTS/init templates and packaged workflow skills align with the active skills/MCP/agents/harness surface.
-- Still required: lock runtime safety gates for native turn risk, approval/sandbox propagation, authority-provider resolution, provider health probes, and DeepSeek read-only routing.
-- Still required: lock broader provider fallback metadata with tests for rate limit, timeout, and default fallback variants.
-- Still required: define minimum machine-readable CLI envelopes for the rest of the automation-critical commands.
-- Still required: promote additional proof bundles beyond the current baseline, especially provider fallback variants for rate limit, timeout, and default route behavior.
+- Done: YAML validation now runs in local `verify` plus CI/smoke workflows.
+- Done: package dry-pack, package audit, tarball smoke, native safety build, and release matrix gates were re-verified against v1.1.17 artifacts.
+- Required before v1.1.18 publish/tag: regenerate the native safety binary, pass package audit, pass smoke-pack/tarball install smoke, and pass `npm run release:check` on the exact intended release diff.
+- Required before v1.1.18 publish/tag: GitHub Actions CI and Smoke Test must both pass on the exact intended commit.
+- Done: provider/deepseek and screenshot JSON command contracts gained hermetic regression tests.
+- Done: current AGENTS/init templates and packaged workflow skills were aligned with the active skills/MCP/agents/harness surface, including all generated agent MCP/skills/hooks flags and parallel subagent orchestration guidance.
+- Remaining: lock runtime safety gates for native turn risk, approval/sandbox propagation, authority-provider resolution, provider health probes, and DeepSeek read-only routing.
+- Remaining: lock broader provider fallback metadata with tests for rate limit, timeout, and default fallback variants.
+- Remaining: define minimum machine-readable CLI envelopes for the rest of the automation-critical commands.
 
 ### P1: observability and diagnostics
 
-- Source implemented: provider route/fallback counts are emitted in run summaries/reports and summary terminal output.
-- Source implemented: invalid MCP JSON is reported as a visible diagnostic without leaking secret-like config values.
-- Source implemented: `omk mcp doctor --json` exposes structured server status, command resolution, timeout, permission, and config-source fields.
-- Expand JSON output for DAG, summary, and workflow commands where CI or agents consume results.
-- Link live graph nodes back to runs, goals, providers, and evidence so `omk graph audit` can validate real project graph memory, not only compact proof fixtures.
+- Done: provider route/fallback counts are now emitted in run summaries/reports and summary terminal output.
+- Done: invalid MCP JSON is reported as a visible diagnostic without leaking secret-like config values.
+- Done: `omk mcp doctor --json` exposes structured server status, command resolution, timeout, permission, and config-source fields.
+- Expand JSON output for graph, DAG, summary, and workflow commands where CI or agents consume results.
+- Link graph nodes back to runs, goals, providers, and evidence so `omk graph view` becomes audit evidence, not only visualization.
 
 ### P2: execution depth and planner quality
 
 - Deepen `omk team` runtime reporting: worker state, pane/session health, artifacts, and verification handoff.
-- Source implemented: replace the `omk goal plan` stub with a planner that emits steps, acceptance criteria, risks, and evidence gates.
+- Done: replace the `omk goal plan` stub with a planner that emits steps, acceptance criteria, risks, and evidence gates.
 - Add provider-quality gates before broader non-Kimi worker pools.
 - Keep Kimi execution as the safe fallback path for every run.
 
@@ -106,7 +95,7 @@ Provider routing and graph viewing are no longer purely future work in the sourc
 
 ### Provider routing maturity
 
-- Keep Kimi as the most mature authority adapter and default fallback until another provider has tested write/merge/MCP authority contracts.
+- Keep Kimi as the most mature adapter and main orchestrator, planner, merger, and final synthesis runtime.
 - Use provider hints for explorer, reviewer, QA, planner, and documentation roles only when preflight is healthy and task risk is low.
 - Record provider attempts, route confidence, fallback reason, and final authority in run evidence.
 
@@ -115,12 +104,10 @@ Provider routing and graph viewing are no longer purely future work in the sourc
 - Materialize provider routes, fallback events, goals, evidence gates, and run artifacts in the local graph/Kuzu ontology.
 - Keep `omk graph view` local-first and safe for private repositories.
 
-### Historical source milestones
-
-These are source/development checkpoints unless a release note explicitly says the version was npm-published.
+### Historical milestones
 
-| Source checkpoint | Focus |
-| --- | --- |
+| Version | Focus |
+|---------|-------|
 | v0.1 | init / doctor / chat, P0 skills, AGENTS.md / DESIGN.md generation, quality gate hooks |
 | v0.2 | wire controller, HUD, run state, worker logs |
 | v0.3 | worktree team, merge queue, reviewer / QA / integrator agents |
@@ -134,5 +121,4 @@ These are source/development checkpoints unless a release note explicitly says t
 | v1.1.15 | Isolated HOME MCP shell-profile hotfix and persistent fetch MCP entrypoint |
 | v1.1.16 | Deterministic IntentFrame/ActionAtom orchestration, chat schema preflight, MCP duplicate policy, agent capability propagation, and doctor/init/pack smoke fixes |
 | v1.1.17 | Full generated-agent MCP/skills/hooks enablement, parallel subagent orchestration emphasis, and v1.1.17 release docs |
-| v1.1.18 | Historical Kimi-wrapper dominant release-prep line: package source version alignment, native safety package gate, typed doctor repair plans, startup update prompt UX, and parallel subagent orchestration release-doc alignment |
-| v1.2.0-rc.0 | Internal RC target for the `v1.2` runtime contract family, provider-neutral docs alignment, version contract docs, and provider maturity limits |
+| v1.1.18 | **Last Kimi-wrapper dominant release.** Package source version alignment, latest-published v1.1.17 caveat, native safety package gate, typed doctor repair plans, startup update prompt UX, and parallel subagent orchestration release-doc alignment |

package/dist/adapters/kimi/runner.js

@@ -495,8 +495,8 @@ export async function runKimiInteractive(args, options) {
         throw new Error("[omk] Failed to load node-pty native module. " +
             `(${message})\n` +
             "This usually happens when installed with --ignore-scripts.\n" +
-            "Fix: npm rebuild -g @omk/cli\n" +
-            "Or reinstall: npm uninstall -g @omk/cli && npm install -g @omk/cli");
+            "Fix: npm rebuild -g open-multi-agent-kit\n" +
+            "Or reinstall: npm uninstall -g open-multi-agent-kit && npm install -g open-multi-agent-kit");
     }
     let ptyProcess;
     try {

package/dist/brand/theme.js

@@ -76,8 +76,8 @@ export const GREEN_RAIN_THEME = {
 export const NEON_GRID_THEME = {
     name: "neon-grid",
     label: "OMK//CONTROL",
-    tagline: "OMK control plane for coding agents.",
-    motto: "Route agents. Verify evidence. Control the loop.",
+    tagline: "Cyberpunk OMK control plane for routed agent work.",
+    motto: "Control the loop — route · verify · loop · control",
     symbols: {
         prompt: "›",
         active: "●",