Repository navigation
Conversation
Castiron custom codeEvaluated main: Trusted main policy: ✅ No new custom-code files detected. 0 mixed files remain; 0 existing customizations changed. Compared A changed generated baseline means this report cannot reliably identify which handwritten lines changed. Inspect the custom-code diffDownload the exact patch produced by this run (requires repository access): gh run download 40029002619 --repo openai/openai-python \
--name castiron-custom-code-40029002619-1 --dir /tmp/castiron-custom-code-40029002619-1
git apply --stat /tmp/castiron-custom-code-40029002619-1/custom-code.patch
cat /tmp/castiron-custom-code-40029002619-1/custom-code.patchOr reproduce it from an SDK checkout containing the vendored reporter: git fetch --no-tags origin 43045fcaf91aec08571e54c57706597cefd32d45 fc44b250a21b3c18fd86c7490c5d2872ab60f9d5
python3 scripts/castiron/custom_code_report.py report \
--base 43045fcaf91aec08571e54c57706597cefd32d45 \
--head fc44b250a21b3c18fd86c7490c5d2872ab60f9d5 --target-branch main --fetch --require-head-hash --public \
--out /tmp/castiron-custom-code-fc44b250a21b
cat /tmp/castiron-custom-code-fc44b250a21b/custom-code.patchThis is the current full custom patch for mixed files, not an attribution of only the handwritten lines changed by this PR. |
marcuswood-oai
left a comment
There was a problem hiding this comment.
LGTM 👍 No changes requested.
The focused cache-state probe passed. The draft CI run skipped test and lint jobs; I did not independently rerun the SDK tests.
Reviewed: fc44b250a21b · Base: 43045fcaf91a · sdk-pr-review
markstuart-oai
left a comment
There was a problem hiding this comment.
Reviewed fc44b250a21b3c18fd86c7490c5d2872ab60f9d5. No blocking findings. The reduced event count still exceeds the actual cache capacity. Both client modes now explicitly verify tool-event eviction and replay while retaining duplicate suppression, one tool invocation, cache bounds, and stream cleanup.
Source-only review; I did not run candidate code or tests. Hosted checks: 13 skipped, 22 success.
The agent-session stream cache test delivers 5,000 distinct text deltas twice to exercise a 1,024-event cache. Use 1,026 deltas and explicitly verify that the original tool event is delivered after eviction while its handler still runs once. Both client modes retain duplicate-delta, cache-bound, input-count, and closure checks. This reduces sustained eviction churn from 3,978 to four evictions before the tool replay.
Validation: Python 3.10.16 / Pydantic 1.10.26, three serial local trials per revision (
DEFER_PYDANTIC_BUILD=false,pytest -n 0): median call time 2.67s → 1.24s sync and 2.56s → 0.68s async. Python 3.10.16 / Pydantic 2.12.5: modified test file 90 passed, 4 skipped; Ruff lint and format checks passed. Whole-gate savings have not been measured.