cool-workflow 0.1.79 → 0.1.80

package/docs/project-index.md

@@ -1,15 +1,15 @@
 # Cool Workflow Project Index
 
-Generated from the current repository code on 2026-06-11 by `npm run sync:project-index`.
+Generated from the current repository code on 2026-06-13 by `npm run sync:project-index`.
 
 ## Snapshot
 
 - Package: `cool-workflow`
-- Version: `0.1.79`
+- Version: `0.1.80`
 - Source modules: `58`
-- Workflow apps: `6`
-- Docs: `46`
-- Smoke tests: `69`
+- Workflow apps: `7`
+- Docs: `47`
+- Smoke tests: `75`
 - Repository: https://github.com/coo1white/cool-workflow
 
 ## Architecture
@@ -116,6 +116,7 @@ multi-agent host -> topology -> blackboard/coordinator
 | App | Type | Inputs | Sandbox | Source |
 | --- | --- | --- | --- | --- |
 | `architecture-review` - Map a repository architecture, assess risks, verify important findings, and synthesize an evidence-backed verdict. | canonical | `repo`, `question`, `invariant`, `focus` | `readonly` | [manifest](../apps/architecture-review/app.json) / [workflow](../apps/architecture-review/workflow.js) |
+| `architecture-review-fast` - Run a shorter architecture review with parallel map and assess phases for faster first results. | canonical | `repo`, `question`, `invariant`, `focus`, `sourceContext`, `sourceContextDigest` | `readonly` | [manifest](../apps/architecture-review-fast/app.json) / [workflow](../apps/architecture-review-fast/workflow.js) |
 | `end-to-end-golden-path` - Deterministic one-worker workflow app for proving the CW integration chain. | userland | `question` | `readonly` | [manifest](../apps/end-to-end-golden-path/app.json) / [workflow](../apps/end-to-end-golden-path/workflow.js) |
 | `pr-review-fix-ci` - Review a pull request or branch, inspect CI failures, diagnose actionable issues, optionally patch, verify, and summarize with evidence. | canonical | `repo`, `pr`, `branch`, `base`, `ci`, `mode` | `readonly`, `workspace-write` | [manifest](../apps/pr-review-fix-ci/app.json) / [workflow](../apps/pr-review-fix-ci/workflow.js) |
 | `release-cut` - Prepare a release with checklist discipline: version checks, changelog, tests, packaging, release notes, and final verification. | canonical | `repo`, `version`, `previousVersion`, `releaseBranch`, `dryRun` | `readonly`, `workspace-write` | [manifest](../apps/release-cut/app.json) / [workflow](../apps/release-cut/workflow.js) |
@@ -162,6 +163,7 @@ multi-agent host -> topology -> blackboard/coordinator
 - [SANDBOX-PROFILES(7)](sandbox-profiles.7.md)
 - [Scheduled Tasks](scheduled-tasks.md)
 - [Security / Trust Hardening](security-trust-hardening.7.md)
+- [Source Context Profiles](source-context-profiles.7.md)
 - [State Explosion Management](state-explosion-management.7.md)
 - [STATE-NODE(7)](state-node.7.md)
 - [Team Collaboration](team-collaboration.7.md)
@@ -176,6 +178,8 @@ multi-agent host -> topology -> blackboard/coordinator
 Smoke tests mirror the public contracts. The high-signal suites are:
 
 - [agent-delegation-drive-smoke.js](../test/agent-delegation-drive-smoke.js)
+- [architecture-review-fast-automation-smoke.js](../test/architecture-review-fast-automation-smoke.js)
+- [architecture-review-fast-smoke.js](../test/architecture-review-fast-smoke.js)
 - [artifact-integrity-smoke.js](../test/artifact-integrity-smoke.js)
 - [backend-registry-smoke.js](../test/backend-registry-smoke.js)
 - [block-unapproved-tag-smoke.js](../test/block-unapproved-tag-smoke.js)
@@ -222,13 +226,17 @@ Smoke tests mirror the public contracts. The high-signal suites are:
 - [result-normalize-smoke.js](../test/result-normalize-smoke.js)
 - [robustness-hardening-smoke.js](../test/robustness-hardening-smoke.js)
 - [run-export-import-smoke.js](../test/run-export-import-smoke.js)
+- [run-export-restore-rerun-smoke.js](../test/run-export-restore-rerun-smoke.js)
+- [run-export-restore-resume-smoke.js](../test/run-export-restore-resume-smoke.js)
 - [run-fixture-compat-smoke.js](../test/run-fixture-compat-smoke.js)
 - [run-registry-control-plane-smoke.js](../test/run-registry-control-plane-smoke.js)
 - [run-retention-reclamation-smoke.js](../test/run-retention-reclamation-smoke.js)
 - [sandbox-profile-smoke.js](../test/sandbox-profile-smoke.js)
+- [schedule-routine-daemon-smoke.js](../test/schedule-routine-daemon-smoke.js)
 - [schema-validation-smoke.js](../test/schema-validation-smoke.js)
 - [security-trust-hardening-smoke.js](../test/security-trust-hardening-smoke.js)
 - [self-audit-hardening-smoke.js](../test/self-audit-hardening-smoke.js)
+- [source-context-profile-smoke.js](../test/source-context-profile-smoke.js)
 - [state-explosion-management-smoke.js](../test/state-explosion-management-smoke.js)
 - [state-node-smoke.js](../test/state-node-smoke.js)
 - [tamper-evidence-demo-smoke.js](../test/tamper-evidence-demo-smoke.js)

package/docs/real-execution-backends.7.md

@@ -142,3 +142,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/release-and-migration.7.md

@@ -280,3 +280,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/release-tooling.7.md

@@ -159,3 +159,7 @@ also get generated MCP manifests (`.gemini-plugin/`, `.opencode-plugin/`) so the
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/routines.md

@@ -41,6 +41,29 @@ Inspect events:
 node scripts/cw.js routine events
 ```
 
+## Long Architecture Reviews
+
+Use `architecture-review-fast` for the foreground user path, then schedule the
+full `architecture-review` app as background work when a deep audit should not
+block an interactive session:
+
+```bash
+node scripts/architecture-review-fast.js \
+  --repo /path/to/repo \
+  --question "Is this architecture sound?" \
+  --metrics \
+  --schedule-full
+```
+
+The wrapper creates a one-shot reminder schedule whose `workflowId` is
+`architecture-review`. The schedule prompt is policy. CW stores the schedule and
+records due events; the external agent host decides how to run the long review.
+The prompt includes the foreground fast run id, fast report path, source-context
+digest/profile, and asks the background agent to return the full review report
+path and digest.
+The `--metrics` flag is optional and reports foreground elapsed time plus
+agent-spawn and result-cache-hit counts for the fast run.
+
 ## Boundary
 
 CW v0.1.1 does not provide managed cloud infrastructure. It provides a local

package/docs/run-registry-control-plane.7.md

@@ -49,6 +49,13 @@ own `sourceFingerprint`, the covered `repos`, the `queue`, and lifecycle
 a `nextAction`. Every read re-derives records from source; the persisted index is
 only compared against, never trusted as the live status.
 
+During one index build, repo-level overlays (`archive.json` and
+`provenance.json`) are read once per repo and passed as an in-memory scan
+snapshot to each run record. This is a short-lived mechanism, not a persistent
+cache: the next registry command re-reads source state and overlays from disk, so
+freshness, fail-closed behavior, and output shape stay unchanged while large
+repos avoid repeated identical overlay reads.
+
 ## Lifecycle state machine
 
 Lifecycle is CLASSIFIED from existing state, never invented. `deriveLifecycle`
@@ -136,6 +143,32 @@ in the repo's `registry/provenance.json`. The original failed run is PRESERVED
 for audit — the past is never overwritten. Rerunning a rerun increments
 `generation` and keeps `originRunId` pinned to the chain root.
 
+## Portable export, import, and restore verification
+
+`run export <run-id> --output PATH` writes a portable JSON archive for a run. The
+archive includes the run state plus run-local files, committed artifacts, audit
+overlays, telemetry ledger files, per-file sha256 digests, file sizes, and a
+manifest digest. External repo-local artifact paths referenced by the run are
+copied into the archive under `external-artifacts/` and recorded with their
+original `sourcePath`; the source run is never mutated.
+
+`run import PATH --target DIR` restores the archive under
+`DIR/.cw/runs/<run-id>/`, rebases paths to the target repo, writes an
+`import-manifest.json`, refreshes the target repo registry, and immediately runs
+the same verification used by `run verify-import`. Restored partial runs can be
+resumed from the target repo; restored failed runs remain discoverable from the
+home registry and can be rerun as new linked runs. The import does not alter the
+source repository or the source run.
+
+`run verify-import <run-id> [--cwd DIR]` re-reads the restore manifest, recomputes
+every restored file digest, checks the manifest digest, and verifies the
+telemetry ledger when one was restored. Missing manifests, digest mismatches,
+path escapes, unsupported archive schemas, unreadable files, or telemetry-chain
+failures return explicit failed checks instead of a fabricated success.
+
+MCP exposes the same mechanisms as `cw_run_export`, `cw_run_import`, and
+`cw_run_verify_import`; the CLI and MCP paths share the same runtime functions.
+
 ## Cross-repo history
 
 `history` reads a unified timeline of runs across all registered repos
@@ -155,6 +188,9 @@ node scripts/cw.js run resume <run-id> [--limit N] [--json]
 node scripts/cw.js run archive <run-id> [--reason TEXT] [--unarchive]
 node scripts/cw.js run archive --older-than-days N [--state completed --state failed]
 node scripts/cw.js run rerun <run-id> [--reason TEXT]
+node scripts/cw.js run export <run-id> --output PATH
+node scripts/cw.js run import PATH --target DIR
+node scripts/cw.js run verify-import <run-id> [--cwd DIR]
 node scripts/cw.js queue add [--app ID|--workflow ID|--runId ID] [--repo PATH] [--priority N] [--note TEXT]
 node scripts/cw.js queue list [--status STATE] [--repo PATH] [--json]
 node scripts/cw.js queue show <queue-id>
@@ -174,7 +210,8 @@ passes `npm run parity:check`:
 
 - `cw_registry_refresh`, `cw_registry_show`
 - `cw_run_search`, `cw_run_list`, `cw_run_show`, `cw_run_resume`,
-  `cw_run_archive`, `cw_run_rerun`
+  `cw_run_archive`, `cw_run_rerun`, `cw_run_export`, `cw_run_import`,
+  `cw_run_verify_import`
 - `cw_queue_add`, `cw_queue_list`, `cw_queue_drain`, `cw_queue_show`
 - `cw_history`
 
@@ -312,3 +349,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/run-retention-reclamation.7.md

@@ -191,3 +191,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/source-context-profiles.7.md

@@ -0,0 +1,119 @@
+# Source Context Profiles
+
+CW keeps source-context slimming out of the runtime kernel. The profile is policy
+data in `manifest/source-context-profiles.json`; `scripts/source-context.js` is a
+small mechanism that reads a git ref and writes JSONL to stdout.
+
+## Core Profile
+
+The default `core` profile is the project memory for AI source imports. It keeps
+runtime source and app/userland entrypoints, and leaves generated artifacts,
+tests, docs, release records, and long logs as manifest-only records.
+
+Included:
+
+- `plugins/cool-workflow/src/**`
+- `plugins/cool-workflow/apps/**`
+- `plugins/cool-workflow/package.json`
+- `plugins/cool-workflow/tsconfig.json`
+- `plugins/cool-workflow/scripts/cw.js`
+- `plugins/cool-workflow/scripts/mcp-server.js`
+- `plugins/cool-workflow/scripts/agents/**`
+
+Excluded from exported content:
+
+- `plugins/cool-workflow/dist/**`
+- `plugins/cool-workflow/test/**`
+- `plugins/cool-workflow/docs/**`
+- `docs/assets/**`
+- `.cw-release/**`
+- `CHANGELOG.md`
+- `ITERATION_LOG.md`
+
+Exclusion does not delete files and does not change release behavior. `dist/`
+remains a committed release artifact until the release contract is explicitly
+changed.
+
+## Narrow Profiles
+
+Use a narrower opt-in profile when the question is already scoped:
+
+- `runtime`: the full `src/**` runtime kernel plus package and TypeScript
+  metadata.
+- `mcp`: capability core/registry, CLI routing, MCP server, MCP launcher scripts,
+  and shared types.
+- `workflow-apps`: canonical apps plus the Workflow App framework and app
+  planning/orchestration surface.
+- `release`: release flow, gates, manifest/version tooling, package metadata, and
+  release-tooling docs.
+- `agent-wrappers`: external agent wrappers, agent config, execution backend,
+  drive loop, and agent-delegation docs.
+
+The narrow profiles are policy data only. Selecting one changes only the JSONL
+context pack; it does not change runtime behavior, release contents, or the
+default `core` profile.
+
+## Commands
+
+```bash
+node scripts/source-context.js profiles
+node scripts/source-context.js manifest --profile core --ref HEAD --repo-root /path/to/repo > manifest.jsonl
+node scripts/source-context.js export --profile core --ref HEAD --repo-root /path/to/repo > core-source.jsonl
+node scripts/source-context.js export --profile mcp --ref HEAD --repo-root /path/to/repo > mcp-source.jsonl
+node scripts/source-context.js export --profile mcp --changed-from origin/main --ref HEAD --repo-root /path/to/repo > mcp-changed.jsonl
+node scripts/source-context.js export --profile core --ref HEAD --repo-root /path/to/repo --cache-dir .cw/cache/source-context > core-source.jsonl
+```
+
+`manifest` emits one JSON object per tracked file at the selected ref:
+
+```json
+{"path":"plugins/cool-workflow/src/state.ts","included":true,"reason":"included:plugins/cool-workflow/src/**","sha256":"..."}
+```
+
+`export` emits only included text files and adds `content`. Both commands use
+stdout for JSONL data only. Diagnostics and refusal messages go to stderr.
+
+`--changed-from REF` is opt-in diff-aware mode. It filters `manifest` and
+`export` to paths changed between the resolved base commit and `--ref`, then
+applies the selected profile include/exclude rules. Deleted files are omitted
+because there is no blob at the target ref. Records include `changedFrom` with
+the resolved base commit. Empty diffs are valid and emit empty JSONL.
+
+`export --cache-dir DIR` is opt-in. The cache key is the resolved git commit SHA
+plus a digest of the selected source profile, so changing either the ref or the
+include/exclude policy produces a different JSONL cache file. Cache hits write the
+same JSONL bytes to stdout and stay silent on stderr. Corrupt or mismatched cache
+records fail closed instead of falling back silently. Diff-aware exports include
+the resolved `--changed-from` commit in the cache key, so full and changed exports
+do not share cache files.
+
+`--repo-root DIR` is also opt-in; when omitted, the script keeps its historical
+default and reads the Cool Workflow repository root.
+
+## Verification
+
+The smoke test checks that:
+
+- the profile includes and excludes exactly the remembered paths;
+- `dist/`, tests, docs, release records, and long logs are manifest-only;
+- exported records are parseable JSONL with content and sha256;
+- narrow profiles are slimmer than `core` and include/exclude their intended
+  surfaces;
+- `--changed-from` emits only changed current-ref files, still honors excludes,
+  and caches separately from full exports;
+- cached exports are byte-identical to uncached exports and corrupt cache hits
+  fail closed;
+- the `core` profile stays under its `maxLines` guard.
+
+Run:
+
+```bash
+node test/source-context-profile-smoke.js
+```
+
+## FreeBSD Discipline
+
+This feature is opt-in and does not alter existing CLI output. It is mechanism,
+not policy: profile selection lives in data, and vendor prompt/stream behavior
+stays in wrappers. It fails closed on invalid profiles, unknown refs, binary
+included files, and line-count drift past the configured guard.

package/docs/state-explosion-management.7.md

@@ -45,6 +45,13 @@ Summaries are written under `.cw/runs/<run-id>/summaries/` as plain JSON. Raw
 blackboard messages, graph nodes, graph edges, audit events, evidence refs, and
 eval artifacts are never deleted or overwritten.
 
+Within a single summary build, CW shares the derived full operator graph,
+operator status, blackboard digest, state-size record, and graph view records
+through a short-lived in-memory context. This avoids rebuilding the same graph
+for `summary refresh`, `summary show`, and the top-level state-explosion report.
+It is not a daemon or persistent cache: the next command re-reads run state from
+disk, recomputes source fingerprints, and still fails closed on stale summaries.
+
 ## Blackboard summarization
 
 `blackboard summarize <run-id>` (MCP: `cw_blackboard_summarize`) returns a
@@ -264,3 +271,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/team-collaboration.7.md

@@ -207,3 +207,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/docs/unix-principles.md

@@ -1,7 +1,10 @@
 # Unix-Inspired Workflow Principles
 
 CW borrows a small set of durable systems ideas and applies them to agent
-workflow engineering. These are design principles, not platform claims.
+workflow engineering. These are design principles, not platform claims — but
+they are not optional: this project strictly follows the FreeBSD programming
+philosophy, and §7 below states the binding rules every change is reviewed
+against (mirrored as hard constraints in the repository's `AGENTS.md`).
 
 ## 1. Everything Is State
 
@@ -190,3 +193,48 @@ Hosts enforce runtime sandbox policy.
 ```
 
 This keeps CW small, inspectable, and extensible.
+
+## 7. FreeBSD Discipline (Binding Rules)
+
+The principles above descend from one tradition — the FreeBSD school of
+systems engineering — and CW adheres to it strictly. Concretely:
+
+**POLA — Principle of Least Astonishment.** An existing output, file layout,
+exit code, or flag never changes meaning or bytes underneath an operator. New
+behavior ships behind a new verb/flag or an env toggle, with the prior
+behavior byte-identical by default. (Example: live drive output is additive —
+stderr only, TTY-gated, `CW_NO_STREAM=1` opt-out; the stdout payload and
+evidence digest are unchanged.)
+
+**Mechanism, not policy.** The kernel provides mechanisms; policy is data in
+userland. WHICH agent runs is config (`CW_AGENT_COMMAND` / agent-config), not
+code; vendor-specific rendering lives in wrappers under `scripts/agents/`,
+never in core. Core may forward a vendor's stream; it never parses one.
+
+**Rule of Silence.** stdout is data, stderr is diagnostics, and a
+non-interactive run is silent on success. Anything human-friendly is TTY-gated
+and can be disabled; `--json` output is stable and undecorated so it composes
+in pipes.
+
+**Fail closed, conservative defaults.** Unconfigured backends probe as
+`unverified`, unverifiable telemetry is surfaced loudly (or refused in strict
+mode), invalid results park the hop. CW never fabricates a success and never
+falls back silently. Boring correctness beats clever features.
+
+**Tools, not frameworks.** Zero runtime dependencies is a red line. Verbs do
+one thing; composition happens through durable files (`.cw/`) and pipes, not
+hidden in-process coupling.
+
+**Man pages are the contract.** Every shipped capability has a `docs/*.7.md`
+page updated in the same change, and doc-drift guards in the test suite keep
+the documented commands honest. Undocumented behavior is unfinished behavior.
+
+**style(9) spirit.** One consistent style per layer; a diff matches the file
+it touches and never reformats code it does not change.
+
+**Release engineering.** Main is -CURRENT; a tag is -RELEASE: it exists only
+after the deterministic gate and an independent review pass, and cadence never
+overrides the gate.
+
+A change that violates any rule in this section is rejected in review even if
+the capability it ships is otherwise desirable.

package/docs/web-desktop-workbench.7.md

@@ -215,3 +215,7 @@ Migration DAG with reversible edges (v0.1.45), capability auto-discovery (v0.1.4
 0.1.78
 
 0.1.79
+
+## Fast Architecture Review (v0.1.80)
+
+Adds the opt-in fast architecture-review lane: scoped JSONL source contexts, diff-aware exports, reusable Map and Assess results, measurable wrapper metrics, actionable background full-review handoff, and userland model policy flags for routing fast/strong workers without changing the full review contract.

package/manifest/plugin.manifest.json

@@ -2,7 +2,7 @@
   "_comment": "SINGLE SOURCE OF TRUTH for every vendor manifest. Edit THIS file, then run `npm run gen:manifests`. Do NOT hand-edit the generated vendor manifests (.claude-plugin/, .codex-plugin/, .agents/, .mcp.json) — `npm run gen:manifests -- --check` (run by release:check) will fail if they drift from this source.",
   "identity": {
     "name": "cool-workflow",
-    "version": "0.1.79",
+    "version": "0.1.80",
     "license": "BSD-2-Clause",
     "homepage": "https://github.com/coo1white/cool-workflow",
     "author": {

package/manifest/source-context-profiles.json

@@ -0,0 +1,142 @@
+{
+  "schemaVersion": 1,
+  "profiles": {
+    "core": {
+      "description": "Default AI source context: runtime source, apps, package metadata, and agent wrappers; generated artifacts, tests, docs, release records, and long logs are manifest-only.",
+      "maxLines": 50000,
+      "include": [
+        "plugins/cool-workflow/src/**",
+        "plugins/cool-workflow/apps/**",
+        "plugins/cool-workflow/package.json",
+        "plugins/cool-workflow/tsconfig.json",
+        "plugins/cool-workflow/scripts/cw.js",
+        "plugins/cool-workflow/scripts/mcp-server.js",
+        "plugins/cool-workflow/scripts/agents/**"
+      ],
+      "exclude": [
+        "plugins/cool-workflow/dist/**",
+        "plugins/cool-workflow/test/**",
+        "plugins/cool-workflow/docs/**",
+        "docs/assets/**",
+        ".cw-release/**",
+        "CHANGELOG.md",
+        "ITERATION_LOG.md"
+      ]
+    },
+    "runtime": {
+      "description": "Runtime-kernel source context for state, orchestration, scheduling, execution, and shared types.",
+      "maxLines": 40000,
+      "include": [
+        "plugins/cool-workflow/src/**",
+        "plugins/cool-workflow/package.json",
+        "plugins/cool-workflow/tsconfig.json"
+      ],
+      "exclude": [
+        "plugins/cool-workflow/dist/**",
+        "plugins/cool-workflow/test/**",
+        "plugins/cool-workflow/docs/**",
+        "plugins/cool-workflow/apps/**",
+        "plugins/cool-workflow/scripts/**",
+        "docs/assets/**",
+        ".cw-release/**",
+        "CHANGELOG.md",
+        "ITERATION_LOG.md"
+      ]
+    },
+    "mcp": {
+      "description": "MCP and CLI surface context for capability registry, MCP server, CLI routing, and MCP launcher wrappers.",
+      "maxLines": 18000,
+      "include": [
+        "plugins/cool-workflow/src/capability-core.ts",
+        "plugins/cool-workflow/src/capability-registry.ts",
+        "plugins/cool-workflow/src/cli.ts",
+        "plugins/cool-workflow/src/mcp-server.ts",
+        "plugins/cool-workflow/src/types/**",
+        "plugins/cool-workflow/scripts/cw.js",
+        "plugins/cool-workflow/scripts/mcp-server.js",
+        "plugins/cool-workflow/package.json",
+        "plugins/cool-workflow/tsconfig.json"
+      ],
+      "exclude": [
+        "plugins/cool-workflow/dist/**",
+        "plugins/cool-workflow/test/**",
+        "plugins/cool-workflow/docs/**",
+        "docs/assets/**",
+        ".cw-release/**",
+        "CHANGELOG.md",
+        "ITERATION_LOG.md"
+      ]
+    },
+    "workflow-apps": {
+      "description": "Workflow App framework and canonical app context without the full runtime kernel.",
+      "maxLines": 18000,
+      "include": [
+        "plugins/cool-workflow/apps/**",
+        "plugins/cool-workflow/src/workflow-app-framework.ts",
+        "plugins/cool-workflow/src/orchestrator.ts",
+        "plugins/cool-workflow/src/orchestrator/**",
+        "plugins/cool-workflow/src/types/workflow-app.ts",
+        "plugins/cool-workflow/src/types/run.ts",
+        "plugins/cool-workflow/scripts/canonical-apps.js",
+        "plugins/cool-workflow/package.json",
+        "plugins/cool-workflow/tsconfig.json"
+      ],
+      "exclude": [
+        "plugins/cool-workflow/dist/**",
+        "plugins/cool-workflow/test/**",
+        "plugins/cool-workflow/docs/**",
+        "docs/assets/**",
+        ".cw-release/**",
+        "CHANGELOG.md",
+        "ITERATION_LOG.md"
+      ]
+    },
+    "release": {
+      "description": "Release-engineering context for gates, release flow, version sync, manifests, and package metadata.",
+      "maxLines": 12000,
+      "include": [
+        "AGENTS.md",
+        "plugins/cool-workflow/scripts/release-flow.js",
+        "plugins/cool-workflow/scripts/release-gate.sh",
+        "plugins/cool-workflow/scripts/dogfood-release.js",
+        "plugins/cool-workflow/scripts/gen-manifests.js",
+        "plugins/cool-workflow/scripts/version-sync-check.js",
+        "plugins/cool-workflow/scripts/bump-version.js",
+        "plugins/cool-workflow/package.json",
+        "plugins/cool-workflow/manifest/**",
+        "plugins/cool-workflow/docs/release-tooling.7.md"
+      ],
+      "exclude": [
+        "plugins/cool-workflow/dist/**",
+        "plugins/cool-workflow/test/**",
+        "docs/assets/**",
+        ".cw-release/**",
+        "CHANGELOG.md",
+        "ITERATION_LOG.md"
+      ]
+    },
+    "agent-wrappers": {
+      "description": "External agent delegation wrappers and neutral backend configuration context.",
+      "maxLines": 14000,
+      "include": [
+        "plugins/cool-workflow/scripts/agents/**",
+        "plugins/cool-workflow/scripts/architecture-review-fast.js",
+        "plugins/cool-workflow/src/agent-config.ts",
+        "plugins/cool-workflow/src/execution-backend.ts",
+        "plugins/cool-workflow/src/drive.ts",
+        "plugins/cool-workflow/src/types/execution-backend.ts",
+        "plugins/cool-workflow/src/types/drive.ts",
+        "plugins/cool-workflow/package.json",
+        "plugins/cool-workflow/docs/agent-delegation-drive.7.md"
+      ],
+      "exclude": [
+        "plugins/cool-workflow/dist/**",
+        "plugins/cool-workflow/test/**",
+        "docs/assets/**",
+        ".cw-release/**",
+        "CHANGELOG.md",
+        "ITERATION_LOG.md"
+      ]
+    }
+  }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cool-workflow",
-  "version": "0.1.79",
+  "version": "0.1.80",
   "bin": {
     "cool-workflow": "scripts/cw.js",
     "cw": "scripts/cw.js"
@@ -56,6 +56,7 @@
     "release:check": "node scripts/release-check.js",
     "test": "node dist/cli.js list && node test/run-all.js",
     "test:fast": "npm run build --if-present && node dist/cli.js list && node test/run-all.js --concurrency auto",
+    "test:coverage": "node dist/cli.js list && node scripts/coverage-gate.js",
     "eval:replay": "tsc -p tsconfig.json && node test/multi-agent-eval-replay-harness-smoke.js",
     "ci": "npm run build && npm run check && npm run test && npm run release:check",
     "validate:schema": "node scripts/validate-run-state-schema.js"