Commit Graph

10 Commits

Author SHA1 Message Date
Paul O'Reilly
7244e0ec5f fix(minimax-m3-max, fable-low-effort): H-SECRET-4 rejected MAX_THINKING_TOKENS in env
The validator pattern-matches *TOKEN* as credential-shaped and rejected
both contexts, failing every task on the new harnesses. The env var name
is fixed by Claude Code, so deliver the thinking budget via the
settings.json env map in init.sh instead (jq-merge preserves apiKeyHelper
from the minimax/oauth layer).

Claude-Session: https://claude.ai/code/session_019tJk7P8tZzJ24PvtgoGhLN
2026-09-03 00:39:59 +12:00
Paul O'Reilly
f5968cfab5 feat: migrate missing harnesses, templates, and workflows from agent-runtimes
Brings the framework CRS repo up to date with all content that was
living in agent-runtimes (local-dev fallback) but hadn't been promoted.

New composites: feature-delivery-loop, integration-direct, scaffolding-repo,
sonnet-impl-narrow, sonnet-manager, test-writing-repo

New contexts: integration/v1, scaffolding/v1, sonnet-manager/v1, z-ai/v1,
airouter/v1/bin (anthropic-compat-wrapper.sh), cp-harness/v1/init.sh

New task-templates: sonnet-integrator.yaml, workflow/* (17 typed workflow
task templates for the Epic 1 pipeline)

Updated: agent-repo/v1/finalize.sh — adds AR-38/F97 empty-deliverable audit
(SKIP_BRANCH_PUSH support, boilerplate-path filtering, ci_metadata.json flag)

Also adds MEMORY.md index and memory/ topic files for the framework repo.
2026-06-23 08:59:01 +12:00
Paul O'Reilly
415118434c debug(agent-repo): expose reference_branches clone failure mode
Probes 7-9 (2026-05-08) all "succeeded" but with empty diffs because
AR-14a fell back to fork main: "WARNING: /workspace/reference/main/.git
not found; using fork main (may be stale)". The reference clone python
loop printed "Cloning git@..." but never "Cloned main successfully" —
no error visible either.

Most likely cause: full-history clone (post-3087ad7) is hitting some
silent failure mode (auth, fs perms, OOM, timeout). With capture_output=True
the git clone's own output was hidden.

Add explicit logging:
- python3 -u (unbuffered stdout)
- pre-loop "reference_branches loop: N entries"
- post-clone "clone returncode=N"
- always-print stdout (last 1KB) and stderr (last 1KB) from subprocess
- explicit chmod return code check
- post-clone .git existence assertion

Next probe will tell us EXACTLY what's failing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 17:24:10 +12:00
Paul O'Reilly
3087ad7de1 fix(agent-repo): full-history clone for reference + upstream-ref fetch
Probe 7 (2026-05-08) finally surfaced the actual push error:

  ! [remote rejected] HEAD -> task-9dc266b5 (shallow update not allowed)

Cause: REFERENCE_BRANCHES handler clones with --depth 1, AR-14a then
fetches upstream-ref --depth 1. The agent's task branch is a single
commit on top of a single shallow commit — no ancestry visible. Gitea
rejects shallow pushes server-side.

Fix:
- Reference clone drops --depth 1 (full history)
- AR-14a fetch upstream-ref drops --depth 1 (full fetch from local-path)
- Cost: a few extra MB per task on tmpfs/PVC. Acceptable.

This unblocks AR-14a's upstream-seeding for the dogfood pipeline. The
agent's branch now has the full upstream history visible to gitea.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 17:09:53 +12:00
Paul O'Reilly
bf18ca3ef5 fix(agent-repo): capture git push output explicitly for diagnosis
Probe 6 (2026-05-08) showed git push failing twice with exit 1 and
zero visible output — the previous form `if cmd 2>&1; then` redirected
git's stderr to stdout where the entrypoint's stderr-only log capture
missed it. CP-side log showed only the bash `set -x` trace, not the
actual git error message (e.g., "Permission denied (publickey)" or
"remote: pre-receive hook rejected").

Refactor the push retry loop:
- Capture output to PUSH_OUT via $() with `2>&1`
- Wrap in set +e/set -e to detect non-zero without aborting
- echo PUSH_OUT to stderr (where set -x trace also goes) so the
  entrypoint's stderr capture sees it

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 17:03:12 +12:00
Paul O'Reilly
9cf016fa1c fix(agent-repo): harden AR-21 diff-verify against set-e/pipefail abort
The 2026-05-08 attempt-2 dogfood batch had 8/8 tasks "succeed" with
zero branches pushed. Root cause: my AR-21 diff-verification block was
running under set -euo pipefail without explicit error handling. A
single non-zero exit anywhere in the `git diff | tr | sed` pipeline
killed finalize.sh before the metadata write or push ran.

Specific risk: `git diff <REF_HEAD>..HEAD` returns non-zero when the
SHA is unreachable (e.g., shallow clone with init.sh fork-fallback
where upstream-ref wasn't fetched). pipefail then kills the pipeline,
set -e kills the script.

Fix: wrap the entire AR-21 block in `set +eo pipefail` (with explicit
`set -eo pipefail` restore at the end). Also:
- Use `${arr[@]:-}` instead of `${arr[@]}` for set -u safety on empty
  arrays
- Add `|| true` to git command substitutions (belt-and-braces)
- Use `printf` instead of `echo` for the comma-wrap (more portable)

Verified locally: when `/workspace/reference/main/.git` is absent the
block correctly skips with the existing fallback; when present and
upstream-ref is reachable, the block runs and reports DIFF_VERIFIED.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 16:31:33 +12:00
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