open-multi-agent-kit 0.90.9 → 0.92.0

package/CHANGELOG.md

@@ -2,9 +2,44 @@
 
 ## [Unreleased]
 
+## [0.92.0] - 2026-07-23
+
+### Added
+
+- Subagent managed-process runtime under `examples/extensions/subagent`: a deadline-budgeted, checkpointed, adaptive subagent executor with process-group lifecycle management (SIGTERM→SIGKILL escalation and resistant-descendant reaping) plus an extension smoke path that runs a registered tool through the managed-process boundary without a provider API.
+- Print mode now reports a clear usage message and exits with code 2 when invoked with no prompt (bare `omk -p`) instead of exiting silently.
+
+### Changed
+
+- Simplified the built-in loadout authority model: every loadout (`inspect`, `plan`, `architect`, `review`, `critic`, `security`, `test`, `visual-qa`) now resolves to `write-scoped` authority with a unified `read/grep/find/ls/edit/write/bash` tool grant and `scoped-shell` command mode, replacing the previous per-loadout read-only / advisory / review-only tiers and their filesystem-MCP downgrade and write-skill stripping. Lane write scope remains gated by the scheduler write-set.
+- Removed the headless credential/secret-file command-safety guard: `classifySecretAccess` and the `secret.read_path` confirm tier are gone, and the agent session no longer applies the safety-floor block for `secret.*` verdicts before spawning a shell. Commands referencing `.env`, `.npmrc`, `.netrc`, `.aws/credentials`, `auth.json`, SSH private keys, `*.pem`/`*.key`, and similar are no longer gated for headless/RPC/LLM bash callers.
+
+### Notes
+
+- Local-only scratch scripts and operator protocol notes are now gitignored and excluded from the release surface.
+
+## [0.91.0] - 2026-07-21
+
+### Added
+
+- **System-wide resource metrics in the footer** — the footer CPU/MEM segment now reports whole-machine utilization (aggregate `os.cpus()` busy percentage and `totalmem - freemem`) instead of process-scoped usage. Wide terminals show `CPU 42% MEM 35% (18.0GB/50.5GB)`; thresholds are percentage-based (warning ≥70% CPU or ≥85% MEM, error ≥90%/95%). Process-scoped getters remain available on the sampler for diagnostics.
+- **Aurora theme pair** — new built-in `omk-aurora-dark` and `omk-aurora-light` themes with WCAG-verified contrast (body text ≥14:1, muted ≥5.7:1, semantic colors ≥4.5:1), a full 51-token color map, and a stepped thinking-level color ramp. Aliases: `aurora`, `aurora-dark`, `aurora-light`.
+- **AdaptOrch advisory bridge wiring** — opt-in, global-only `adaptorchBridge` settings block (`enabled`, `ttlMs`, `timeoutMs`, `maxConsultsPerSession`, `failureThreshold`). When enabled, the v4 auto thinking-level resolver consults the circuit-breaker-protected, TTL-cached advisory bridge and fuses the returned hint as a bounded ±2-step nudge; the resolver's own confidence escalation still applies on top. Default remains fully off, and a project-scope settings file can never enable it.
+
+### Changed
+
+- **`omk-adaptorch-wpl` promoted to stable** and added as a runtime dependency of `open-multi-agent-kit` (lockstep `0.91.0`). The Work Packet Loop state machine, outcome adjudicator, and verification-wall modules now ship with the CLI package.
+- Repository hygiene: local-only research corpora and audit artifacts are no longer tracked in git (they remain on disk, with a local SHA-256 integrity manifest for the project-owned subset).
+
 ### Fixed
 
 - Masked API-key-like values in newly submitted user chat before extensions, models, event streams, and session persistence.
+- Restored `omk-adaptorch-wpl` handling in the coding-agent shrinkwrap generator so internal workspace packaging stays reproducible.
+
+### Notes
+
+- Published to npm as `open-multi-agent-kit@0.91.0` (lockstep with `omk-ai`, `omk-agent-core`, `omk-tui`, and `omk-adaptorch-wpl` at `0.91.0`).
+- Verification boundary: `tsgo --noEmit` clean; adaptorch-wpl suite 73/73, coding-agent regression suite 784/784, theme suites green. Live-provider coverage remains outside this release.
 
 ## [0.90.9] - 2026-07-19
 
@@ -17,17 +52,17 @@
 - Added typed termination, incomplete-run recovery, and `omk session doctor`, including dry-run repair for unambiguous recoverable state only.
 - Added provider-origin-aware `omk provider doctor` diagnostics with sanitized Level 0–2 probes for native, custom OpenAI-compatible, and local-proxy endpoints.
 
-### Local freeze
+### Notes
 
-- The `0.90.9` workspace snapshot is locally frozen and unpublished. Local build/check, keyless workspace tests, npm packs, isolated npm/Bun installs, and the Linux x64 Bun binary/archive passed; live-provider and other-OS coverage remain outside this freeze.
-- Publication, push, tag, dist-tag, and trusted-publisher mutations remain blocked pending authoritative WORM release infrastructure.
+- Published to npm as `open-multi-agent-kit@0.90.9` (lockstep with `omk-ai`, `omk-agent-core`, and `omk-tui` at `0.90.9`); prebuilt binaries are attached to the GitHub release.
+- Verification boundary: build/check and the keyless workspace suite passed; live-provider and other-OS coverage remain outside this release. Validate existing integrations against your workload.
 
 ## [0.90.8] - 2026-07-13
 
 ### New Features
 
 - **GPT-5.6 MoA virtual model** — `openai-codex/gpt-5.6-moa` combines bounded concurrent Sol and Terra analysis into one Sol-synthesized response. See [provider setup](docs/providers.md).
-- **Path-safe parallel tool-batch waves** — independent tool calls run in ordered waves while conflicts and unknown operations remain sequential. See [the agent runtime](../../agent/README.md).
+- **Path-safe parallel tool-batch waves** — independent tool calls run in ordered waves while conflicts and unknown operations remain sequential. See [the agent runtime](../agent/README.md).
 - **Context-budget v2 controls** — enable the global budget with `contextBudget.enabled` and select an authenticated compaction model with `compaction.model`. See [settings](docs/settings.md) and [compaction](docs/compaction.md).
 - **Evidence-gated Correctness Wall** — fixtureless live OA uses a bound MCP handler only and otherwise remains preview-only. See the [Correctness Wall example](examples/extensions/correctness-wall/README.md).
 - **Project-local computer use** — the Stagehand extension and `omk-computeruse` skill add bounded, approval-gated browser workflows. See [the extension](../../.omk/extensions/omk-computeruse-stagehand/README.md).

package/README.md

@@ -15,7 +15,7 @@
 <p align="center">
   <a href="https://discord.com/invite/3cU7Bz4UPx"><img alt="Discord" src="https://img.shields.io/badge/discord-community-5865F2?style=flat-square&logo=discord&logoColor=white" /></a>
   <a href="https://www.npmjs.com/package/open-multi-agent-kit"><img alt="npm" src="https://img.shields.io/npm/v/open-multi-agent-kit?style=flat-square" /></a>
-  <a href="https://github.com/dmae97/omk/releases/tag/v0.90.8"><img alt="Release" src="https://img.shields.io/badge/release-v0.90.8-00d7ff?style=flat-square" /></a>
+  <a href="https://github.com/dmae97/omk/releases/tag/v0.92.0"><img alt="Release" src="https://img.shields.io/badge/release-v0.92.0-00d7ff?style=flat-square" /></a>
 </p>
 
 > New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See [CONTRIBUTING.md](https://github.com/dmae97/open-multi-agent-kit/blob/v0.90.4/CONTRIBUTING.md).
@@ -32,6 +32,19 @@ The OMK//CONTROL startup surface is the default operator view. The header reads
 
 The default dark TUI theme uses the `omk-control-grid-dark` Night City palette and keeps the control sidebar focused on route, evidence, loop, MCP, runtime, skills, and context budget state.
 
+## Release v0.91.0
+
+This feature release moves footer resource metrics to whole-machine telemetry, ships the WCAG-verified Aurora theme pair, stabilizes the AdaptOrch Work Packet Loop package as a CLI runtime dependency, and adds two built-in subscription providers (Qwen, Grok).
+
+| Area | What changed |
+|------|--------------|
+| Footer metrics | CPU/MEM now reflect the whole machine (`os.cpus()` busy %, `totalmem - freemem`) instead of the OMK process, with percentage-based warning/error thresholds. |
+| Themes | `omk-aurora-dark` / `omk-aurora-light`: WCAG-verified contrast (body ≥14:1, semantic ≥4.5:1), stepped thinking-level ramp, aliases `aurora` / `aurora-dark` / `aurora-light`. |
+| AdaptOrch | `omk-adaptorch-wpl` promoted to stable as a CLI runtime dependency; opt-in global-only `adaptorchBridge` advisory hints for the auto thinking-level resolver (default off). |
+| Providers | New built-in subscription providers under `/login`: Qwen (Qwen Code Subscription) and Grok (xAI OAuth Proxy). |
+
+GitHub-focused release notes live in [RELEASE_NOTES_v0.92.0.md](https://github.com/dmae97/omk/blob/v0.92.0/.github/RELEASE_NOTES_v0.92.0.md). The GitHub release workflow also extracts the canonical release body from [packages/coding-agent/CHANGELOG.md](https://github.com/dmae97/omk/blob/v0.92.0/packages/coding-agent/CHANGELOG.md).
+
 ## Release v0.90.8
 
 This patch release adds the tool-free GPT-5.6 MoA model, ordered path-safe tool-batch waves, global context-budget controls, and evidence-gated computer-use integrations.

package/dist/core/agent-session.d.ts

@@ -242,6 +242,15 @@ export declare class AgentSession {
      */
     private _reasoningRouterBiasSnapshot;
     private _reasoningRouterBiasSnapshotLoaded;
+    /**
+     * AdaptOrch advisory bridge (default-off, global-only opt-in via
+     * `adaptorchBridge.enabled` in ~/.omk/agent/settings.json). Lazily
+     * constructed on the first v4 auto-turn when enabled; stays `null`
+     * otherwise. The bridge is advisory-only: its hint is fused into the
+     * resolver as a bounded ±2 step nudge, never as an override.
+     */
+    private _adaptorchBridge;
+    private _adaptorchBridgeInitAttempted;
     private _unsubscribeAgent?;
     private _eventListeners;
     private _messageEndReplacements;
@@ -649,6 +658,22 @@ export declare class AgentSession {
      * coefficient); computed for future calibrated weight presets.
      */
     private _computePressureBucket;
+    /**
+     * AdaptOrch advisory bridge hint accessor (default-off, global-only).
+     * Lazily constructs the bridge on first call when enabled; returns `null`
+     * (no hint) otherwise. The bridge's `getFreshHint` is synchronous and
+     * cache-read-only, so this never blocks the turn-start path. A fire-and-
+     * forget `requestRefresh` is issued for the NEXT turn's benefit.
+     *
+     * The returned hint is shaped as `{ level, confidence }` for the resolver's
+     * hint-fusion slot: confidence is mapped from the bridge's closed
+     * `confidenceBand` enum (low=0.5, medium=0.75, high=0.95) and the level is
+     * derived from the bridge's `taskClass` via the same static rule table the
+     * resolver uses. The resolver's own HINT_CONFIDENCE_THRESHOLD (0.7) gates
+     * whether the hint actually fuses, so a "low" band hint is structurally
+     * inert.
+     */
+    private _getAdaptorchHint;
     /**
      * Cycle to next thinking level.
      * @returns New level, or undefined if model doesn't support thinking
@@ -730,6 +755,8 @@ export declare class AgentSession {
      * Context overflow errors are NOT retryable (handled by compaction instead).
      */
     private _isRetryableError;
+    private _ejectStickySafetyModelIfNeeded;
+    private _maybeFailoverFromSafetyStop;
     private _prepareRetry;
     /**
      * Cancel in-progress retry.