cool-workflow 0.2.1 → 0.2.3

package/docs/end-to-end-golden-path.7.md

@@ -36,26 +36,26 @@ needs evidence, with the `readonly` sandbox profile.
 The runner runs the same public commands that an operator would use:
 
 ```bash
-node scripts/cw.js app validate end-to-end-golden-path
-node scripts/cw.js plan end-to-end-golden-path --repo <tmp> --question "..."
-node scripts/cw.js dispatch <run-id> --limit 1 --sandbox readonly
-node scripts/cw.js worker manifest <run-id> <worker-id>
-node scripts/cw.js worker output <run-id> <worker-id> <result.md>
-node scripts/cw.js candidate register <run-id> --worker <worker-id> --id golden-candidate
-node scripts/cw.js candidate score <run-id> golden-candidate \
+cw app validate end-to-end-golden-path
+cw plan end-to-end-golden-path --repo <tmp> --question "..."
+cw dispatch <run-id> --limit 1 --sandbox readonly
+cw worker manifest <run-id> <worker-id>
+cw worker output <run-id> <worker-id> <result.md>
+cw candidate register <run-id> --worker <worker-id> --id golden-candidate
+cw candidate score <run-id> golden-candidate \
   --criterion correctness=4 \
   --criterion evidence=4 \
   --criterion fit=2 \
   --maxTotal 10 \
   --evidence <file:line>
-node scripts/cw.js candidate rank <run-id>
-node scripts/cw.js candidate select <run-id> golden-candidate --reason "golden path verified"
-node scripts/cw.js commit <run-id> --selection <selection-id> \
+cw candidate rank <run-id>
+cw candidate select <run-id> golden-candidate --reason "golden path verified"
+cw commit <run-id> --selection <selection-id> \
   --reason "golden path verifier-gated commit"
-node scripts/cw.js report <run-id>
-node scripts/cw.js status <run-id>
-node scripts/cw.js graph <run-id>
-node scripts/cw.js report <run-id> --show
+cw report <run-id>
+cw status <run-id>
+cw graph <run-id>
+cw report <run-id> --show
 ```
 
 After dispatch, the script reads the worker manifest it made, and writes a

package/docs/evidence-adoption-reasoning-chain.7.md

@@ -321,3 +321,7 @@ _No behavioral change in v0.1.89 (CLI-surface golden-path + help-output fixes on
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3

package/docs/execution-backends.7.md

@@ -351,3 +351,7 @@ _No behavioral change in v0.1.89 (CLI-surface golden-path + help-output fixes on
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3

package/docs/getting-started.md

@@ -6,7 +6,7 @@ Start from a new clone:
 cd plugins/cool-workflow
 npm install
 npm run build
-node scripts/cw.js app list
+cw app list
 ```
 
 ## Check your setup first (`cw doctor`)
@@ -15,10 +15,10 @@ Like `brew doctor`, this names any setup problem and the fix for it before you
 start a run:
 
 ```bash
-node scripts/cw.js doctor          # human-readable
-node scripts/cw.js doctor --json   # stable payload for scripts
-node scripts/cw.js doctor --onramp # short path for users and code work
-node scripts/cw.js doctor --onramp --changed-from origin/main
+cw doctor          # human-readable
+cw doctor --json   # stable payload for scripts
+cw doctor --onramp # short path for users and code work
+cw doctor --onramp --changed-from origin/main
 ```
 
 It checks the Node version (v18+), whether an agent backend is set up (and its
@@ -47,7 +47,7 @@ tests and guard checks for your current change.
 Make a run with a canonical workflow app:
 
 ```bash
-node scripts/cw.js plan release-cut \
+cw plan release-cut \
   --repo "$PWD" \
   --version 0.1.25 \
   --previousVersion 0.1.24 \
@@ -58,37 +58,37 @@ node scripts/cw.js plan release-cut \
 Use the run id you get back:
 
 ```bash
-node scripts/cw.js status <run-id>
-node scripts/cw.js graph <run-id>
-node scripts/cw.js dispatch <run-id> --limit 1 --sandbox readonly
-node scripts/cw.js worker summary <run-id>
-node scripts/cw.js topology list
-node scripts/cw.js topology apply <run-id> map-reduce --task <task-id>
-node scripts/cw.js topology summary <run-id>
-node scripts/cw.js multi-agent run <run-id> --topology judge-panel --task <task-id>
-node scripts/cw.js multi-agent status <run-id>
-node scripts/cw.js multi-agent graph <run-id>
-node scripts/cw.js multi-agent dependencies <run-id>
-node scripts/cw.js multi-agent failures <run-id>
-node scripts/cw.js multi-agent evidence <run-id>
-node scripts/cw.js multi-agent step <run-id> --sandbox readonly
-node scripts/cw.js multi-agent blackboard <run-id> summary
-node scripts/cw.js multi-agent score <run-id> <candidate-id> --criterion correctness=1 --evidence <ref>
-node scripts/cw.js multi-agent select <run-id> <candidate-id> --reason "verified winner"
-node scripts/cw.js multi-agent summary <run-id>
-node scripts/cw.js blackboard summary <run-id>
-node scripts/cw.js audit summary <run-id>
-node scripts/cw.js audit multi-agent <run-id>
-node scripts/cw.js audit policy <run-id>
-node scripts/cw.js audit blackboard <run-id>
-node scripts/cw.js audit judge <run-id>
-node scripts/cw.js eval snapshot <run-id> --id <suite-id>
-node scripts/cw.js eval replay .cw/evals/<suite-id>/snapshot.json
-node scripts/cw.js eval compare .cw/evals/<suite-id>/snapshot.json .cw/evals/<suite-id>/replay-run.json
-node scripts/cw.js eval score .cw/evals/<suite-id>/replay-run.json
-node scripts/cw.js eval gate .cw/evals/<suite-id>
-node scripts/cw.js eval report .cw/evals/<suite-id>/replay-run.json
-node scripts/cw.js report <run-id> --show
+cw status <run-id>
+cw graph <run-id>
+cw dispatch <run-id> --limit 1 --sandbox readonly
+cw worker summary <run-id>
+cw topology list
+cw topology apply <run-id> map-reduce --task <task-id>
+cw topology summary <run-id>
+cw multi-agent run <run-id> --topology judge-panel --task <task-id>
+cw multi-agent status <run-id>
+cw multi-agent graph <run-id>
+cw multi-agent dependencies <run-id>
+cw multi-agent failures <run-id>
+cw multi-agent evidence <run-id>
+cw multi-agent step <run-id> --sandbox readonly
+cw multi-agent blackboard <run-id> summary
+cw multi-agent score <run-id> <candidate-id> --criterion correctness=1 --evidence <ref>
+cw multi-agent select <run-id> <candidate-id> --reason "verified winner"
+cw multi-agent summary <run-id>
+cw blackboard summary <run-id>
+cw audit summary <run-id>
+cw audit multi-agent <run-id>
+cw audit policy <run-id>
+cw audit blackboard <run-id>
+cw audit judge <run-id>
+cw eval snapshot <run-id> --id <suite-id>
+cw eval replay .cw/evals/<suite-id>/snapshot.json
+cw eval compare .cw/evals/<suite-id>/snapshot.json .cw/evals/<suite-id>/replay-run.json
+cw eval score .cw/evals/<suite-id>/replay-run.json
+cw eval gate .cw/evals/<suite-id>
+cw eval report .cw/evals/<suite-id>/replay-run.json
+cw report <run-id> --show
 ```
 
 Run the smallest check that fits the change:

package/docs/index.md

@@ -49,6 +49,7 @@ advanced pages only when you need those parts.
 - [Durable State & Locking](durable-state-and-locking.7.md) - atomic writes, fsync durability, and portable file locks.
 - [Source Context Profiles](source-context-profiles.7.md) - opt-in JSONL source exports for context slimming.
 - [Security / Trust Hardening](security-trust-hardening.7.md) - audit records, provenance, sandbox attestations, and acceptance rationale.
+- [Trust Audit Anchor](trust-audit-anchor.7.md) - head anchor that makes a cut-off audit-log tail visible.
 - [State Explosion Management](state-explosion-management.7.md) - summaries, compact graph views, blackboard digests, and stale-aware compaction.
 - [Evidence Adoption Reasoning Chain](evidence-adoption-reasoning-chain.7.md) - why evidence was adopted or rejected.
 

package/docs/multi-agent-cli-mcp-surface.7.md

@@ -30,21 +30,21 @@ drive a run.
 Make or join a topology-backed run without starting up workers:
 
 ```bash
-node scripts/cw.js multi-agent run <run-id> --topology judge-panel --task <task-id>
-node scripts/cw.js multi-agent run --app architecture-review --repo /path/to/repo --question "Review this" --topology map-reduce
+cw multi-agent run <run-id> --topology judge-panel --task <task-id>
+cw multi-agent run --app architecture-review --repo /path/to/repo --question "Review this" --topology map-reduce
 ```
 
 Read the joined host status:
 
 ```bash
-node scripts/cw.js multi-agent status <run-id>
-node scripts/cw.js multi-agent status <run-id> --json
+cw multi-agent status <run-id>
+cw multi-agent status <run-id> --json
 ```
 
 Do one deterministic step at a time:
 
 ```bash
-node scripts/cw.js multi-agent step <run-id> --sandbox readonly
+cw multi-agent step <run-id> --sandbox readonly
 ```
 
 `step` may make a dispatch manifest, get fanin, snapshot the blackboard,
@@ -55,19 +55,19 @@ command. It never starts up agents on its own.
 Work with the active blackboard when it is clear which one it is:
 
 ```bash
-node scripts/cw.js multi-agent blackboard <run-id> summary
-node scripts/cw.js multi-agent blackboard <run-id> topics
-node scripts/cw.js multi-agent blackboard <run-id> post --topic <topic-id> --body "finding" --evidence <ref>
-node scripts/cw.js multi-agent blackboard <run-id> add-artifact --topic <topic-id> --kind worker-result --path result.md
-node scripts/cw.js multi-agent blackboard <run-id> snapshot
+cw multi-agent blackboard <run-id> summary
+cw multi-agent blackboard <run-id> topics
+cw multi-agent blackboard <run-id> post --topic <topic-id> --body "finding" --evidence <ref>
+cw multi-agent blackboard <run-id> add-artifact --topic <topic-id> --kind worker-result --path result.md
+cw multi-agent blackboard <run-id> snapshot
 ```
 
 Score and select in a clear way:
 
 ```bash
-node scripts/cw.js multi-agent score <run-id> <candidate-id> --criterion correctness=1 --criterion evidence=1 --evidence <ref>
-node scripts/cw.js multi-agent select <run-id> <candidate-id> --score <score-id> --reason "verifier-backed candidate"
-node scripts/cw.js commit <run-id> --selection <selection-id> --reason "verified winner"
+cw multi-agent score <run-id> <candidate-id> --criterion correctness=1 --criterion evidence=1 --evidence <ref>
+cw multi-agent select <run-id> <candidate-id> --score <score-id> --reason "verifier-backed candidate"
+cw commit <run-id> --selection <selection-id> --reason "verified winner"
 ```
 
 ## Operator Inspection
@@ -75,10 +75,10 @@ node scripts/cw.js commit <run-id> --selection <selection-id> --reason "verified
 v0.1.21 adds to the host loop these pointed operator commands:
 
 ```bash
-node scripts/cw.js multi-agent graph <run-id>
-node scripts/cw.js multi-agent dependencies <run-id>
-node scripts/cw.js multi-agent failures <run-id>
-node scripts/cw.js multi-agent evidence <run-id>
+cw multi-agent graph <run-id>
+cw multi-agent dependencies <run-id>
+cw multi-agent failures <run-id>
+cw multi-agent evidence <run-id>
 ```
 
 The human output is short and ready to use: agent graph, dependencies, failed
@@ -327,3 +327,7 @@ The host-facing surface tracks the CLI golden-path fixes (`cw -q` routing + repo
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3

package/docs/multi-agent-eval-replay-harness.7.md

@@ -33,26 +33,26 @@ The harness is file-first by design:
 Create a snapshot from a multi-agent run:
 
 ```bash
-node scripts/cw.js eval snapshot <run-id> --id <suite-id>
-node scripts/cw.js eval snapshot <run-id> --id <suite-id> --json
+cw eval snapshot <run-id> --id <suite-id>
+cw eval snapshot <run-id> --id <suite-id> --json
 ```
 
 Replay without live agents:
 
 ```bash
-node scripts/cw.js eval replay .cw/evals/<suite-id>/snapshot.json
+cw eval replay .cw/evals/<suite-id>/snapshot.json
 ```
 
 Compare, score, gate, and report:
 
 ```bash
-node scripts/cw.js eval compare \
+cw eval compare \
   .cw/evals/<suite-id>/snapshot.json \
   .cw/evals/<suite-id>/replay-run.json
 
-node scripts/cw.js eval score .cw/evals/<suite-id>/replay-run.json
-node scripts/cw.js eval gate .cw/evals/<suite-id>
-node scripts/cw.js eval report .cw/evals/<suite-id>/replay-run.json
+cw eval score .cw/evals/<suite-id>/replay-run.json
+cw eval gate .cw/evals/<suite-id>
+cw eval report .cw/evals/<suite-id>/replay-run.json
 ```
 
 `npm run eval:replay` runs the deterministic smoke suite. It is part of
@@ -172,12 +172,12 @@ Use this harness after a topology-backed run gets a score, a selection, and a
 verifier-gated commit:
 
 ```bash
-node scripts/cw.js eval snapshot <run-id> --id release-replay
-node scripts/cw.js eval replay .cw/evals/release-replay/snapshot.json
-node scripts/cw.js eval compare .cw/evals/release-replay/snapshot.json .cw/evals/release-replay/replay-run.json
-node scripts/cw.js eval score .cw/evals/release-replay/replay-run.json
-node scripts/cw.js eval gate .cw/evals/release-replay
-node scripts/cw.js eval report .cw/evals/release-replay/replay-run.json
+cw eval snapshot <run-id> --id release-replay
+cw eval replay .cw/evals/release-replay/snapshot.json
+cw eval compare .cw/evals/release-replay/snapshot.json .cw/evals/release-replay/replay-run.json
+cw eval score .cw/evals/release-replay/replay-run.json
+cw eval gate .cw/evals/release-replay
+cw eval report .cw/evals/release-replay/replay-run.json
 ```
 
 The gate proves the replay finished, graph/dependencies stayed stable,
@@ -353,3 +353,7 @@ _No behavioral change in v0.1.89 (CLI-surface golden-path + help-output fixes on
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3

package/docs/multi-agent-operator-ux.7.md

@@ -50,28 +50,28 @@ The model is derived from:
 Use the normal status and report commands for the wide view:
 
 ```bash
-node scripts/cw.js status <run-id>
-node scripts/cw.js graph <run-id>
-node scripts/cw.js report <run-id> --show
+cw status <run-id>
+cw graph <run-id>
+cw report <run-id> --show
 ```
 
 Use the focused multi-agent views when the operator needs the process table.
 
 ```bash
-node scripts/cw.js multi-agent status <run-id>
-node scripts/cw.js multi-agent graph <run-id>
-node scripts/cw.js multi-agent dependencies <run-id>
-node scripts/cw.js multi-agent failures <run-id>
-node scripts/cw.js multi-agent evidence <run-id>
+cw multi-agent status <run-id>
+cw multi-agent graph <run-id>
+cw multi-agent dependencies <run-id>
+cw multi-agent failures <run-id>
+cw multi-agent evidence <run-id>
 ```
 
 Every focused command can give deterministic JSON:
 
 ```bash
-node scripts/cw.js multi-agent status <run-id> --json
-node scripts/cw.js multi-agent dependencies <run-id> --json
-node scripts/cw.js multi-agent failures <run-id> --format json
-node scripts/cw.js multi-agent evidence <run-id> --json
+cw multi-agent status <run-id> --json
+cw multi-agent dependencies <run-id> --json
+cw multi-agent failures <run-id> --format json
+cw multi-agent evidence <run-id> --json
 ```
 
 The compact human output uses six stable panels:
@@ -175,13 +175,13 @@ derived operator model under `summaries.multiAgentOperator`.
 ## Example Trace
 
 ```bash
-node scripts/cw.js multi-agent graph "$RUN"
-node scripts/cw.js multi-agent dependencies "$RUN" --json
-node scripts/cw.js multi-agent failures "$RUN"
-node scripts/cw.js multi-agent evidence "$RUN"
-node scripts/cw.js audit provenance "$RUN" --candidate "$CANDIDATE"
-node scripts/cw.js commit "$RUN" --selection "$SELECTION" --reason "verified winner"
-node scripts/cw.js report "$RUN" --show
+cw multi-agent graph "$RUN"
+cw multi-agent dependencies "$RUN" --json
+cw multi-agent failures "$RUN"
+cw multi-agent evidence "$RUN"
+cw audit provenance "$RUN" --candidate "$CANDIDATE"
+cw commit "$RUN" --selection "$SELECTION" --reason "verified winner"
+cw report "$RUN" --show
 ```
 
 The operator can start at an agent membership, follow `depends-on` to its task
@@ -365,3 +365,7 @@ _No behavioral change in v0.1.89 (CLI-surface golden-path + help-output fixes on
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3

package/docs/multi-agent-runtime-core.7.md

@@ -83,29 +83,29 @@ Fanin does not quietly take missing evidence for required roles.
 Present dispatch and worker flows are still valid:
 
 ```bash
-node scripts/cw.js dispatch <run-id> --limit 1 --sandbox readonly
+cw dispatch <run-id> --limit 1 --sandbox readonly
 ```
 
 To tie dispatch to clear multi-agent state:
 
 ```bash
-node scripts/cw.js multi-agent run <run-id> --id ma-release --objective "release verification"
-node scripts/cw.js multi-agent role <run-id> verifier \
+cw multi-agent run <run-id> --id ma-release --objective "release verification"
+cw multi-agent role <run-id> verifier \
   --multi-agent-run ma-release \
   --responsibility "verify release evidence" \
   --required-evidence "release-check log"
-node scripts/cw.js multi-agent group <run-id> release-group \
+cw multi-agent group <run-id> release-group \
   --multi-agent-run ma-release \
   --phase "Verify" \
   --task verify:package
-node scripts/cw.js multi-agent fanout <run-id> release-fanout \
+cw multi-agent fanout <run-id> release-fanout \
   --group release-group \
   --reason "split release verification" \
   --role verifier \
   --task verify:package \
   --limit 1 \
   --sandbox-choice verifier=readonly
-node scripts/cw.js dispatch <run-id> \
+cw dispatch <run-id> \
   --limit 1 \
   --sandbox readonly \
   --multi-agent-run ma-release \
@@ -136,7 +136,7 @@ multi-agent trust audit events.
 Gather fanin after worker output:
 
 ```bash
-node scripts/cw.js multi-agent fanin <run-id> release-fanin \
+cw multi-agent fanin <run-id> release-fanin \
   --group release-group \
   --fanout release-fanout \
   --required-role verifier
@@ -151,26 +151,26 @@ missing evidence is a state error, not a quiet success.
 Use the everyday operator commands:
 
 ```bash
-node scripts/cw.js status <run-id>
-node scripts/cw.js graph <run-id>
-node scripts/cw.js report <run-id> --show
-node scripts/cw.js audit summary <run-id>
-node scripts/cw.js audit provenance <run-id>
+cw status <run-id>
+cw graph <run-id>
+cw report <run-id> --show
+cw audit summary <run-id>
+cw audit provenance <run-id>
 ```
 
 Use the more pointed multi-agent commands:
 
 ```bash
-node scripts/cw.js multi-agent summary <run-id>
-node scripts/cw.js multi-agent summary <run-id> --json
-node scripts/cw.js multi-agent graph <run-id>
-node scripts/cw.js multi-agent graph <run-id> --json
-node scripts/cw.js multi-agent show <run-id> <multi-agent-run-id>
-node scripts/cw.js multi-agent role <run-id> <role-id>
-node scripts/cw.js multi-agent group <run-id> <group-id>
-node scripts/cw.js multi-agent membership <run-id> <membership-id>
-node scripts/cw.js multi-agent fanout <run-id> <fanout-id>
-node scripts/cw.js multi-agent fanin <run-id> <fanin-id>
+cw multi-agent summary <run-id>
+cw multi-agent summary <run-id> --json
+cw multi-agent graph <run-id>
+cw multi-agent graph <run-id> --json
+cw multi-agent show <run-id> <multi-agent-run-id>
+cw multi-agent role <run-id> <role-id>
+cw multi-agent group <run-id> <group-id>
+cw multi-agent membership <run-id> <membership-id>
+cw multi-agent fanout <run-id> <fanout-id>
+cw multi-agent fanin <run-id> <fanin-id>
 ```
 
 The status and report Multi-Agent panel shows group status, role coverage,

package/docs/multi-agent-topologies.7.md

@@ -44,12 +44,12 @@ candidates, selections, commits, and trust audit events.
 ## CLI
 
 ```bash
-node scripts/cw.js topology list
-node scripts/cw.js topology show map-reduce
-node scripts/cw.js topology validate map-reduce
-node scripts/cw.js topology apply <run-id> map-reduce --task map:server-api --mapper-count 2
-node scripts/cw.js topology summary <run-id>
-node scripts/cw.js topology graph <run-id>
+cw topology list
+cw topology show map-reduce
+cw topology validate map-reduce
+cw topology apply <run-id> map-reduce --task map:server-api --mapper-count 2
+cw topology summary <run-id>
+cw topology graph <run-id>
 ```
 
 Apply commands are JSON-first. `summary` and `graph` also give human output

package/docs/multi-agent-trust-policy-audit.7.md

@@ -86,20 +86,20 @@ verifier-gated commit readiness where those gates lean on judge evidence.
 The commands that are already there still work the same way:
 
 ```bash
-node scripts/cw.js audit summary <run-id>
-node scripts/cw.js audit provenance <run-id>
-node scripts/cw.js multi-agent status <run-id>
-node scripts/cw.js multi-agent evidence <run-id>
+cw audit summary <run-id>
+cw audit provenance <run-id>
+cw multi-agent status <run-id>
+cw multi-agent evidence <run-id>
 ```
 
 Focused views:
 
 ```bash
-node scripts/cw.js audit multi-agent <run-id>
-node scripts/cw.js audit policy <run-id>
-node scripts/cw.js audit role <run-id> <role-id>
-node scripts/cw.js audit blackboard <run-id>
-node scripts/cw.js audit judge <run-id>
+cw audit multi-agent <run-id>
+cw audit policy <run-id>
+cw audit role <run-id> <role-id>
+cw audit blackboard <run-id>
+cw audit judge <run-id>
 ```
 
 Use `--json` or `--format json` for deterministic machine output.
@@ -121,8 +121,8 @@ Human output has stable panels:
 so it cannot gate a script. `audit verify` is the gate:
 
 ```bash
-node scripts/cw.js audit verify <run-id>        # exit 1 if the chain is forged
-node scripts/cw.js audit verify <run-id> --json
+cw audit verify <run-id>        # exit 1 if the chain is forged
+cw audit verify <run-id> --json
 ```
 
 It proves the run's trust-audit hash chain again offline: it works out every event

package/docs/node-snapshot-diff-replay.7.md

@@ -186,3 +186,7 @@ _No behavioral change in v0.1.89 (CLI-surface golden-path + help-output fixes on
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3

package/docs/observability-cost-accounting.7.md

@@ -246,3 +246,7 @@ _No behavioral change in v0.1.89 (CLI-surface golden-path + help-output fixes on
 0.2.0
 
 0.2.1
+
+0.2.2
+
+0.2.3