docs: checkpoint-and-continue — supervised runs park and advance - #43
Merged
Conversation
AUTONOMY.md gains the operational mechanics generalised from register_and_iterate: trigger (judgment gates only), one batched answerable-cold question per pause, awaiting-input parking with a question: pointer in active.md, continue policy (next independent step -> next task -> clean end), resume from active.md in any environment; hard blockers park as blocked, never as questions. start_dev supervised line links the section; register_and_iterate's contract now references the general pattern (single source). Ship sign-off/merge park the task, never bypass the gate. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013UptUDNTYiB7izaQJBAKgS
There was a problem hiding this comment.
Pull request overview
Adds the canonical “checkpoint-and-continue” operational doctrine for supervised --auto runs to AUTONOMY.md, and updates consuming skills to reference that single source rather than duplicating mechanics. This fits the repo’s role as the reasoning/doctrine layer by tightening the autonomy contract documentation and its cross-skill linkage.
Changes:
- Define a dedicated “Checkpoint-and-continue (
supervised)" section inAUTONOMY.mdand update the levels text to point to it. - Update
/start_devdocs to describe (and reference) the checkpoint-and-continue flow. - Update
/register_and_iteratedocs to treat its contract as an instance of the generalized checkpoint-and-continue mechanics.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| skills/start_dev/start_dev.md | Expands the supervised --auto description to reference checkpoint-and-continue behavior. |
| skills/register_and_iterate/register_and_iterate.md | Reframes the skill’s autonomy contract as an instance of the generalized checkpoint-and-continue doctrine. |
| AUTONOMY.md | Introduces a canonical checkpoint-and-continue section and adjusts surrounding autonomy prose/consumer list accordingly. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+28
to
+32
| This contract is the origin of, and now an instance of, the general | ||
| **checkpoint-and-continue** mechanics in | ||
| [`../../AUTONOMY.md`](../../AUTONOMY.md) — question format, `awaiting-input` | ||
| parking and resume are defined there, once. Runs without intervention | ||
| **except** at these gates, where it writes a clear question and stops: |
Comment on lines
+43
to
+46
| 3. **`supervised`** → judgment gates become batched issue questions and the | ||
| run advances (the contract's "Checkpoint-and-continue" section: question → | ||
| `awaiting-input` park → next independent step or task → resume from | ||
| `active.md`); mechanical stretches proceed. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Task 5 of the autonomy series.
AUTONOMY.mdgains the operational mechanics of checkpoint-and-continue forsupervised--autoruns, generalised fromregister_and_iterate's production-proven contract: judgment-gate trigger, one batched answerable-cold question per pause,awaiting-inputparking with aquestion:pointer inactive.md, continue policy (next independent step → next queued task → clean end with a parked-question summary), resume fromactive.mdin any environment, and hard blockers parking as blocked rather than as questions.start_dev's supervised line links the section;register_and_iterate's contract references the general pattern (single source). Ship sign-off and merge park the task — the human's session is freed, never the checkpoint.Closes #42.
API Changes
None — documentation/doctrine only. Mind-side schema addition (
awaiting-inputstatus + optionalquestion:key in theactive.mdschema) ships as amind:commit alongside this PR.Test Plan
Full API Changes (for automation & release notes)
None — internal documentation/doctrine only.
🤖 Generated with Claude Code
https://claude.ai/code/session_013UptUDNTYiB7izaQJBAKgS