Google AI Agent 9982fe78b5 [audit] fix 4 bugs in tasks.py — PR review spam, morning report, memory compress ...

Bug 1: NET_LINE_LIMIT = 10 → 500
  The PR review bot rejected every PR with net +10 lines, which is
  virtually all real work. Raised to 500 to only catch bulk commits.

Bug 2: memory_compress reads wrong action path
  tick_record['actions'] doesn't exist — actions are nested under
  tick_record['decision']['actions']. Overnight alerts were always empty.

Bug 3: good_morning_report reads today's ticks instead of yesterday's
  At 6 AM, now.strftime('%Y%m%d') gives today — the log is nearly empty.
  Fixed to (now - timedelta(days=1)) for yesterday's full overnight data.

Bug 4: review_prs rejection comment now includes the file list
  Authors couldn't tell which files were bloated. Now shows top 10 files.

Tests: 4 new tests in tests/test_tasks_bugfixes.py (all pass).

Signed-off-by: gemini <gemini@hermes.local>

2026-03-30 18:40:09 -04:00

..

test_allegro_wizard_assets.py

feat: add Allegro Kimi wizard house assets (#91)

2026-03-29 22:22:24 +00:00

test_gitea_assignee_filter.py

fix: filter actual assignees before dispatching agents (#82)

2026-03-28 13:31:40 +00:00

test_local_runtime_defaults.py

test: make local llama.cpp the default runtime (#77)

2026-03-28 05:33:47 +00:00

test_metrics_helpers.py

feat: add local-vs-cloud token and throughput metrics (#85)

2026-03-28 14:24:12 +00:00

test_proof_policy_docs.py

docs: codify merge proof standard (#84)

2026-03-28 14:03:35 +00:00

test_tasks_bugfixes.py

[audit] fix 4 bugs in tasks.py — PR review spam, morning report, memory compress

2026-03-30 18:40:09 -04:00