test: cover #25957 production regressions#26039
Conversation
|
Heads up for review: this PR is still the #25957 follow-up with the production regression tests, but its current e2e red is inherited from shared CI state, not from this branch. I opened #26048 as the narrow unblocker for that shared post-#25957 fallout. It fixes the Discord e2e mock surface plus the Nous provider-parity fixture issue, and it is green/clean now. Once #26048 lands, I’ll refresh/rerun this PR against main. |
462ee53 to
63eaf60
Compare
|
@ethernet8023 quick routing update: #26039 is refreshed after #26048 and the old e2e blocker is gone. The remaining red is inherited
Once those land on main, I’ll refresh/rerun #26039 again. |
…-prod-regressions # Conflicts: # run_agent.py
|
@ethernet8023 bump on #26039: refreshed onto current main, conflicts resolved, CI is green, mergeState CLEAN, and the PR body was rechecked against the live diff. This is still the narrow #25957 follow-up: one bg-review snapshot fix plus the two focused regression tests. Current diff is just Could you re-review/merge when you get a minute? |
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR #26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions.
|
Merged via PR #33661. Your commit |
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR NousResearch#26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions.
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR NousResearch#26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions. #AI commit#
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR NousResearch#26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions.
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR NousResearch#26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions.
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR NousResearch#26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions.
Snapshot review_agent._session_messages before teardown so close() can clean per-session state without dropping the user-visible self-improvement summary. Adds two regressions: - bg-review summarizer receives captured review-agent tool messages after review_agent.close() runs - context-compressor protected-head handoff rehydration populates _previous_summary and keeps the old handoff out of newly summarized turns Salvaged from PR NousResearch#26039 onto current main after agent/background_review.py extraction. Original commit 63eaf60; bg-review test updated to patch the module-level summarize_background_review_actions in agent.background_review instead of the now-forwarder AIAgent._summarize_background_review_actions.
What does this PR do?
Adds the follow-up regressions requested on #25957 for the two production behavior fixes that were merged as part of the CI unblocker.
This keeps the follow-up narrow:
_previous_summarybefore the next summary updatereview_agentis closedRelated Issue
Follow-up to #25957. Does not close a separate issue.
Type of Change
Changes Made
agent/background_review.pyreview_agent._session_messagesbefore memory-provider shutdown andreview_agent.close()so cleanup cannot drop bg-review action reportingtests/agent/test_context_compressor_summary_continuity.pyContextCompressor._previous_summaryand keeps the old handoff out of newly summarized turnstests/run_agent/test_background_review.pysummarize_background_review_actionsreceives captured review-agent tool messages afterreview_agent.close()runsagent.background_reviewrefactorHow to Test
./scripts/run_tests.sh tests/run_agent/test_background_review.py tests/agent/test_context_compressor_summary_continuity.py -- -q --tb=shortpython -m py_compile agent/background_review.py run_agent.py tests/run_agent/test_background_review.py tests/agent/test_context_compressor_summary_continuity.pypython -m ruff check agent/background_review.py tests/run_agent/test_background_review.py tests/agent/test_context_compressor_summary_continuity.pygit diff --check origin/mainValidation Status
mainbaseba9964ff0d68002d9440f6b8a64276d7c34a77a4.08967f6d5c9b259b9627debe12e01cb8feafd998.origin/main: 3 files changed,agent/background_review.py,tests/agent/test_context_compressor_summary_continuity.py,tests/run_agent/test_background_review.py.8 passed, 0 failed in 1.5s.python -m py_compile ...passed for touched files plusrun_agent.py.python -m ruff check ...passed for touched files.git diff --check origin/mainpassed.test,e2e, lint, Nix, Docker builds, attribution, history, and supply-chain checks are green on head08967f6d5c9b259b9627debe12e01cb8feafd998.merge,move-main, andmove-latestskipped as expected for PR CI.pytest tests/ -qis not claimed here. This is intentionally a narrow follow-up to fix(ci): stabilize shared test state after 21012 #25957.Checklist
Code
fix(scope):,feat(scope):, etc.)pytest tests/ -qand all tests passscripts/run_tests.shDocumentation & Housekeeping
docs/, docstrings) - N/Acli-config.yaml.exampleif I added/changed config keys - N/ACONTRIBUTING.mdorAGENTS.mdif I changed architecture or workflows - N/AFor New Skills
N/A
Screenshots / Logs