@linimin/pi-letscook 0.1.36 → 0.1.39

package/CHANGELOG.md

@@ -1,9 +1,29 @@
 # Changelog
 
-## 0.1.36
+## 0.1.39
 
 ### Changed
 
+- aligned public docs and packaged release-gate parity around bare `/cook` as the only supported workflow entrypoint
+- updated operator-facing fail-closed guidance to send users back to the main chat to clarify the mission before rerunning bare `/cook`
+- refreshed `scripts/release-check.sh` so packaged parity now fails closed on the bare-only contract while still covering the supported startup, refocus, and context flows
+
+## 0.1.38
+
+### Changed
+
+- normalized discussion-derived `/cook` missions through shared proposal finalization so planning-phrased startup, next-round, and bare active-refocus discussions now resolve to implementation-result missions only when scope or acceptance clearly point to shipped code/test/doc/runtime changes
+- preserved genuine planning missions for explicit plan/spec/design-doc/migration-plan/proposal and support-docs-only discussions, while keeping ambiguous generic scope fail-closed instead of promoting it into a new mission
+- aligned analyst-derived and strict structured-fallback `/cook` proposal paths behind the same mission-normalization rules, added deterministic regressions for planning-only preservation and ambiguous-scope fail-closed behavior, and kept the existing approval-only Start/Cancel rewrite gate intact
+
+## 0.1.37
+
+### Changed
+
+- documented `/cook` as the single public discussion-first workflow command for startup, active-workflow continue/refocus, and done-workflow next-round flows
+- reframed the public docs/help copy around `/cook` as the discussion-first workflow entrypoint and documented the conservative fail-closed clarification path before the later runtime removal
+- documented the fail-closed ambiguous-discussion behavior and approval-only Start/Cancel gate before canonical-state writes
+- added release-gated public-parity assertions for README/help/changelog `/cook` single-command copy so docs drift fails closed before packaging
 - simplified the README opening so first-time users can understand the problem `/cook` solves, what the extension provides, and how to start using it without reading the full control-plane details first
 
 ## 0.1.35
@@ -92,7 +112,7 @@
 ### Changed
 
 - `/cook` with no goal can now propose a context-derived startup plan for confirmation when no active workflow exists, including starting a fresh next round after the previous workflow already reached `done`
-- `/cook <goal>` now builds a goal-anchored, context-enriched startup proposal before writing canonical state, uses more explicit active-workflow replacement wording, and starts the next round directly from the explicit goal after a completed workflow instead of reopening continue/refocus choices
+- historically added goal-anchored startup proposals from inline `/cook` arguments before canonical writes, plus more explicit active-workflow replacement wording and direct next-round startup after a completed workflow; that old inline-argument path is no longer supported now that bare `/cook` is the only public entrypoint
 
 ## 0.1.24
 

package/README.md

@@ -1,6 +1,6 @@
 # @linimin/pi-letscook
 
-A Pi extension that turns `/cook` into a repo-local workflow command for long-running coding work.
+A Pi extension that turns `/cook` into a discussion-driven repo-local workflow command for long-running coding work.
 
 ## Why this exists
 
@@ -11,14 +11,15 @@ Normal chat is good for one-off tasks. It is much worse for work that needs to:
 - resume from repo state instead of chat memory
 - keep review, audit, and verification tied to the repo
 
-`@linimin/pi-letscook` solves that by storing canonical workflow state in `.agent/**` and using `/cook` to start, resume, or refocus the workflow.
+`@linimin/pi-letscook` solves that by storing canonical workflow state in `.agent/**` and using `/cook` as one discussion-first command to start, continue, refocus, or advance the workflow.
 
 ## What you get
 
 - one command: `/cook`
 - repo-local canonical state in `.agent/**`
 - resumable long-running workflows
-- startup proposals from an explicit goal or recent discussion
+- discussion-first startup, continue, refocus, and next-round routing
+- fail-closed guidance that sends you back to the main chat when the mission still needs clarification
 - deterministic verification, review, audit, and stop checks
 
 ## Install
@@ -31,49 +32,48 @@ Then run `/reload` in Pi.
 
 ## Quick start
 
-Start from an explicit goal:
-
-```text
-/cook build feature X end-to-end with tests and docs
-```
-
-Resume an active workflow:
+Primary entrypoint:
 
 ```text
 /cook
 ```
 
-Replace the active workflow with a different goal:
+Use bare `/cook` after you discuss the mission in the main chat. The same command can:
 
-```text
-/cook fix onboarding crash first, with regression tests
-```
+- start a brand-new workflow from recent discussion
+- continue the current workflow when recent discussion still matches it, or when discussion is too weak or ambiguous to justify a refocus
+- surface a conservative refocus chooser when recent discussion clearly points to a different workflow
+- start the next workflow round after the previous one is `done`
+
+On startup and next-round flows, if recent discussion is missing, weak, or ambiguous, bare `/cook` fails closed, leaves canonical `.agent/**` state unchanged, and tells you to clarify the mission in the main chat before rerunning bare `/cook`.
 
 ## How `/cook` works
 
-`/cook` is the only public workflow command, but it reacts to canonical workflow state:
+Bare `/cook` is the only supported workflow entrypoint.
 
-| Repo state | `/cook` | `/cook <goal>` |
-|---|---|---|
-| No workflow yet | Summarizes recent discussion into a startup proposal, then asks for approval | Builds a proposal anchored on the explicit goal, then asks for approval |
-| Active workflow exists | Resumes from canonical `.agent/**` state | First asks whether to continue or replace the current workflow |
-| Previous workflow is `done` | Starts the next round from recent discussion | Starts the next round from the explicit goal |
+| Repo state | Bare `/cook` |
+|---|---|
+| No workflow yet | Summarizes recent discussion into a startup proposal, then asks for approval with **Start** or **Cancel**. If the discussion is weak or ambiguous, `/cook` fails closed without writing `.agent/**` state and tells you to clarify the mission in the main chat before rerunning bare `/cook`. |
+| Active workflow exists | Reads the current mission plus recent non-command discussion. Matching or unclear discussion resumes from canonical `.agent/**` state. Clear replacement discussion opens a chooser first, then only rewrites canonical state after the follow-on **Start** confirmation. |
+| Previous workflow is `done` | Starts the next round from recent discussion, then asks for approval with **Start** or **Cancel**. Ambiguous discussion fails closed without rewriting canonical state and tells you to clarify the mission in the main chat before rerunning bare `/cook`. |
 
-## Startup confirmation
+## Approval-only confirmation and fail-closed behavior
 
-Startup and replacement proposals are **approval-only**:
+All startup, next-round, and replacement proposals are **approval-only**:
 
 - the proposal body is shown separately from actions
 - actions are only **Start** and **Cancel**
-- if the proposal needs changes, **Cancel**, discuss them in the main chat, and rerun `/cook`
+- **Cancel** is side-effect free: discuss changes in the main chat and rerun `/cook`
+
+When bare `/cook` cannot derive a clear startup, next-round, or replacement proposal from recent discussion, it fails closed instead of guessing. That means no canonical `.agent/**` state is created or rewritten until the discussion is clarified in the main chat and you rerun bare `/cook`.
 
-When an active workflow already exists and you run `/cook <goal>`, `/cook` still shows a separate chooser first:
+When an active workflow already exists and recent discussion clearly suggests a different workflow, `/cook` shows a separate chooser first:
 
 - **Continue current workflow**
-- **Abandon current workflow and start this new one**
+- **Start new workflow from recent discussion**
 - **Cancel**
 
-Only the follow-on startup/replacement proposal uses the approval-only Start/Cancel gate.
+Only the follow-on startup/replacement proposal uses the approval-only Start/Cancel gate, and canonical `.agent/**` state changes happen only after **Start** is accepted.
 
 When you accept startup or refocus from that flow, `/cook` persists the chosen `task_type` and `evaluation_profile` across `.agent/profile.json`, `.agent/state.json`, `.agent/plan.json`, and `.agent/active-slice.json`, and records the accepted critique outcome in canonical continuation state before the re-ground round begins.
 
@@ -218,7 +218,7 @@ npm run rubric-contract-test
 npm run release-check
 ```
 
-`npm run release-check` is the broad packaged-release verifier. It begins with `bash .agent/verify_completion_control_plane.sh`, so missing or stale `.agent/verification-evidence.json` parity fails closed before the broader suite runs, then reruns the startup/refocus/context checks — including the critique-aware `/cook` confirmation regression and the smoke auto-resume prompt path — includes deterministic canonical evidence artifact coverage and includes deterministic active-slice contract coverage plus observability coverage, evaluator calibration, and the rubric-contract regression, and finishes with `npm pack --dry-run`.
+`npm run release-check` is the broad packaged-release verifier. It begins with `bash .agent/verify_completion_control_plane.sh`, so missing or stale `.agent/verification-evidence.json` parity fails closed before the broader suite runs, then asserts the shipped single-command `/cook` public parity surfaces in `README.md`, `CHANGELOG.md`, and the `/cook` help/fail-closed copy in `extensions/completion/index.ts`, reruns the startup/refocus/context checks — including the critique-aware `/cook` confirmation regression and the smoke auto-resume prompt path — includes deterministic canonical evidence artifact coverage and includes deterministic active-slice contract coverage plus observability coverage, evaluator calibration, and the rubric-contract regression, and finishes with `npm pack --dry-run`.
 
 ## Release