feat(reflection): add cross-model review between claude-opus and gpt-codex#119
Merged
feat(reflection): add cross-model review between claude-opus and gpt-codex#119
Conversation
…codex When self-assessment completes with 'complete' verdict, the plugin now invokes the opposite frontier model (claude-opus-4.6 ↔ gpt-5.2-codex) in an ephemeral session to independently review the changes. The cross- review result is saved alongside the reflection artifact. Also adds: - Detailed ASCII state graph to docs/reflection.md and README.md - Missing INTERNAL_SESSION_MARKERS for SELF-ASSESS and REVIEW prefixes in tts.ts, telegram.ts, and telegram.test-helpers.ts - Unit tests for parseModelSpec and getCrossReviewModelSpec - Telegram filter tests for the new session markers
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
complete, the plugin now invokes the opposite frontier model (claude-opus-4.6 ↔ gpt-5.2-codex) in an ephemeral session to independently review the changes. The cross-review result is saved in the.reflection/<session>_<timestamp>.jsonartifact.docs/reflection.mdandREADME.md.INTERNAL_SESSION_MARKERSentries (SELF-ASSESS REFLECTION-3,REVIEW REFLECTION-3 COMPLETION) totts.ts,telegram.ts, andtelegram.test-helpers.tsso those plugins correctly skip all reflection-internal sessions.Changes
reflection-3.tsparseModelSpec(),getCrossReviewModelSpec(),runCrossModelReview(), wired into completion path, updatedisJudgeSession()reflection-3.test-helpers.tsparseModelSpecandgetCrossReviewModelSpectts.ts/telegram.ts/telegram.test-helpers.tsINTERNAL_SESSION_MARKERStest/reflection-3.unit.test.tstest/telegram-session-filter.test.tsdocs/reflection.md/README.mdTesting
npm test— 326 passed, 5 skipped, 8 suites greennpm run eval:judge— 23/23 passednpm run eval:stuck— 12/13 passed (1 pre-existing borderline case)npm run eval:compression— 12/12 passed