dongarandClaude Opus 5 886cb80583 Count only mutating tools as evidence of work ...

The previous fix challenged a completion claim made before any tool
call, but treated every tool as work — so a model that ran one
list_dir and then declared the milestone done was believed, and CI
caught the same empty milestone again.

Reading a file or listing a directory is the model orienting itself.
Only write_file and run_command now count, so a completion claim must
be backed by something that changed or verified the tree.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

2026-09-07 22:53:20 +00:00

..

test_approvals.py

Externalise plans to Gitea and accept approvals there (A4, Part H)

2026-09-07 22:15:08 +00:00

test_canonical.py

Add canonical event log and renderer skeleton (A10)

2026-09-06 19:51:58 +00:00

test_control.py

Add control loop, gating primitives, and transport interface (A4/B1)

2026-09-05 21:28:07 +00:00

test_dev_main.py

Scaffold hello-world apps, test frameworks, and Gitea CI

2026-09-05 18:48:51 +00:00

test_executor.py

Count only mutating tools as evidence of work

2026-09-07 22:53:20 +00:00

test_gates.py

Add control loop, gating primitives, and transport interface (A4/B1)

2026-09-05 21:28:07 +00:00

test_git.py

Add Gitea client and git operations (B2) — step 6a, part 1

2026-09-07 20:27:34 +00:00

test_gitea.py

Page to the end when searching for an existing PR

2026-09-07 20:31:31 +00:00

test_llm.py

Add LLM-backed planning agent (A4/A11/A13) — step 5a

2026-09-07 14:47:12 +00:00

test_matrix.py

Add MatrixTransport (A1) — step-2 PR B

2026-09-06 23:52:45 +00:00

test_oplog.py

Add literal-format test showing exact log lines

2026-09-05 21:20:41 +00:00

test_planner.py

Fix AWAIT_INPUT deadlock and make the live milestone test robust

2026-09-07 16:46:07 +00:00

test_poller.py

Add PR comment intake and the review loop (B2) — step 6b

2026-09-07 21:59:50 +00:00

test_pr_open.py

Publish finished milestones as PRs (B2/A3) — step 6a, part 2

2026-09-07 20:43:20 +00:00

test_publish.py

Publish finished milestones as PRs (B2/A3) — step 6a, part 2

2026-09-07 20:43:20 +00:00

test_reconcile.py

Implement A9 state-change logging in the state store

2026-09-05 21:13:36 +00:00

test_render.py

Add executor tool loop (A12/A15) — step 5b

2026-09-07 16:35:39 +00:00

test_review_loop.py

Add PR comment intake and the review loop (B2) — step 6b

2026-09-07 21:59:50 +00:00

test_state.py

Implement A9 state-change logging in the state store

2026-09-05 21:13:36 +00:00

test_tools.py

Externalise plans to Gitea and accept approvals there (A4, Part H)

2026-09-07 22:15:08 +00:00