Repository navigation
ai-memory consolidation: dated note on GPT-6 models and upstream #852 - #313
Merged
seathatflowsinourveins merged 1 commit intoSep 26, 2026
Merged
Conversation
With llm_provider = "codex", ai-memory 2.3.2/2.4.0 send temperature and gpt-6-luna, gpt-6-sol and gpt-6-astra reject it (400). Upstream #852 (f7ec2eda) omits it; it ships in v2.4.1 and release/2.5. Records the laptop's 2.3.2 build carrying the #859 and #852 backports, running gpt-6-sol (keep-but-compare) since 2026-09-26. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
seathatflowsinourveins
added
the
lane:foundation
seathatflowsinourveins
enabled auto-merge (squash)
September 26, 2026 02:31
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
seathatflowsinourveins
deleted the
claude/gpt6-consolidation-note-20260926
branch
September 26, 2026 02:42
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Scope
docs/native-memory-consolidation.mdfor hosts running ai-memory with Codex-provider consolidation. It explains why GPT-6 models fail on 2.3.2 and 2.4.0, and which upstream fix and release carry the fix.lane:foundation.docs/native-memory-consolidation.mdandmanifests/evidence.json(hash re-registration only).SOTA sources
f7ec2eda6e6579cbcb5dfa9b8343d6b81932716c, issue #851. The changes are incrates/ai-memory-llm/src/{openai_oauth.rs,openai.rs,copilot.rs}.433a19f3) andrelease/2.5(dde5806b). v2.3.2 (353841d9) and v2.4.0 (b1b25219) lack it; their request predicates skip temperature only forgpt-5/o*.Evidence-class table
400 Unsupported parameter: temperaturethrough a 2.3.2 build (6 of 6 runs)native_provenon the WSL authoring laptopsource_review: the three request files are the same blobs as 2.3.2f7ec2eda; the live service runs it withgpt-6-solsource_reviewandnative_proven. Two independent reviews: a Claude evidence-reviewer and a Codex gpt-6-astra/ultra cross-review (SAFE_TO_DEPLOY). After restart, a live structured gpt-6-sol call succeeded.source_reviewonlyChecks:
scripts/validate.py: passed.evidence_manifest.py --check: passed.python3 -m unittest(before the wording-only revision): 5784 tests, OK.origin/main..HEAD: no leaks.🤖 Generated with Claude Code