Commit Graph

4 Commits

Author SHA1 Message Date
Paul O'Reilly
07309567d5 feat(agent-repo,airouter): seed from upstream + label-gate + diff verify
Three load-bearing fixes for the airouter dogfood pipeline, derived from
the 2026-05-08 batch-3 dogfood postmortem (gotchas-airouter.md items 27-30):

1. agent-repo/v1/init.sh — seed fresh task branches from
   /workspace/reference/main/ (the upstream clone) rather than the agent
   repo's stale main. This was THE killer for batch 3: the
   agent-runtimes-agents fork has been frozen at 2026-05-04 since the
   "Fork cleanup" PR, so every agent started from old state, missing
   recent test files and the M16/M22 scripts to delete. The fork remains
   the push remote (so finalize.sh works); only the working-tree seed
   moves to the upstream reference. Falls back to fork main when the
   reference clone isn't available (preserves legacy behavior). Tagged
   AR-14a.

2. requires_labels on contexts/composites — airouter context + both
   airouter composites declare requires_labels: [airouter] so the
   dispatcher's _collect_supported_harnesses (with the matching agent-
   runtimes change) advertises them only on dispatchers carrying the
   airouter label. Stops the main dispatcher from claiming airouter-
   labeled tasks and dying at init time. Composites that wrap label-
   restricted contexts MUST redeclare their own requires_labels — no
   auto-traversal of layers (kept simple).

3. agent-repo/v1/finalize.sh — AR-21 diff-against-upstream verification.
   New env-var protocol:
     - AGENT_EXPECTED_CHANGED_FILES (comma-separated paths that MUST
       appear in `git diff <ref/main>..HEAD`)
     - AGENT_FORBIDDEN_CHANGED_FILES (paths that MUST NOT appear)
   finalize.sh fails the task (exit 1) if either invariant is violated;
   the branch is still pushed for forensics so the operator can inspect.
   Catches BOTH the false-success mode (item 30 — agent reports succeeded
   but never changed the target file) AND the destructive-Write mode
   (item 21 — task 4a2f2988 stripped 9 unrelated functions). Also writes
   diff_verified, diff_mismatch, diff_changed_files into ci_metadata.json.

CRS pulls all three on next CP poll — no agent-runtimes image rebuild
needed for the framework parts. The matching dispatcher poller filter
ships in agent-runtimes (separate commit).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 15:45:41 +12:00
Paul O'Reilly
8bbf6cbb2f BUG-5/BUG-20 fixes: pre_test.sh, output validation, push retry, workflow output tags
- pre_test.sh: harness-level test folder revert script, replaces inline
  _revert_test_folders() in entrypoint. Writes {"reverted": N} atomically.
- finalize.sh: set -x debug tracing; push retry (AGENT_PUSH_RETRIES, default 1
  retry after 5s); output validation (AGENT_EXPECTED_OUTPUT env var); wrong-path
  detection moves .agent-output/ files to working dir and writes
  .correction-prompt.txt for entrypoint re-invoke
- harness.yaml: add scripts.pre_test
- spec-planning.yaml: all 17 nodes tagged with output:{path,min_bytes}

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-04 18:29:47 +12:00
Paul O'Reilly
0272e3df1e chore: sync framework content from agent-runtimes main (2026-04-28)
- Hardens qwen-code-methodology rules (no code deletion, pre-commit diff)
- Fixes test-writing CLAUDE.md workspace path
- Adds best-practices-opus-repo/v1 composite harness
- Adds opus-best-practices-review task template
- Adds max_turns support to airouter task template defaults
- Updates agent-repo finalize.sh

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-28 10:58:01 +12:00
Paul O'Reilly
37a5165dfb init: seed framework reference content from agent-runtimes main repo 2026-04-26 12:17:42 +12:00