justinmclean opened a new pull request, #467:
URL: https://github.com/apache/airflow-steward/pull/467

   ## Summary
   
   The update beat re-audited every skill, tool, and modes.md row on every
   run, which was the bulk of the streaming volume on a slow link. This adds
   a tools/spec-loop/.last-sync marker holding the BASE SHA the specs were
   last synced against, and an update_scope_context step that tells the agent
   to diff only the paths changed since that SHA and skip everything else. If
   the diff is empty the run exits without creating a branch or commit.
   
   loop.sh owns the marker: after a successful sync it advances .last-sync to
   the current BASE HEAD, amending it into the agent's sync commit when there
   is one, or making a marker-only branch off BASE when there was nothing to
   sync. PROMPT_update.md is updated to honor the incremental scope and to
   leave the marker file alone, since loop.sh maintains it.
   
   Also skip the open-PR context (a gh network round-trip) in update mode,
   which never picks a work item, and add SPEC_LOOP_OUTPUT_FORMAT (default
   text) to switch the agent to stream-json with --verbose when debugging a
   wedged run.
   
   ## Type of change
   
   - [ ] Skill change (`.claude/skills/<name>/`) — eval fixtures updated below
   - [ ] Tool / bridge contract (`tools/<system>/*.md`)
   - [ ] Python package (`tools/*/` with `pyproject.toml`)
   - [ ] Groovy reference impl
   - [ ] Cross-cutting (RFC, AGENTS.md, sandbox, privacy-LLM)
   - [ ] Documentation (`docs/`, `README.md`, `CONTRIBUTING.md`)
   - [ ] Project template (`projects/_template/`)
   - [ ] CI / dev loop (`prek`, workflows, validators)
   - [X] Other: tool update
   
   ## Test plan
   
   - [X] `prek run --all-files` passes
   - [X] For Python packages touched: `uv run pytest` / `ruff check` / `mypy` 
passes
   - [ ] For Groovy bridges touched: command-line invocation tested end-to-end
   - [ ] For skill changes: eval suite passes for the affected skill
         (`PYTHONPATH=tools/skill-evals/src python3 -m skill_evals.runner 
tools/skill-evals/evals/<skill>/`)
   - [ ] For skill *behaviour* changes: a new or updated eval fixture is 
included in this PR
         (a regression test for the bug fixed / the behaviour added — see 
CONTRIBUTING.md)
   - [ ] Other:


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to