Preserve Claude native context management - #2
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
context_managementtool-result and thinking edits at the Codex protocol boundary without changing saved transcriptsPrompt is too longerrors for JSON and SSE so Claude Code can run its own compaction recoveryclaude-apipayload rewrite with Claude Code's nativeskillOverridessettingRoot cause
gptCode discarded Claude's context-management field and classified streaming context overflow as a generic API failure. A mis-selected bundled provider skill could then consume the GPT context without Claude's normal cleanup and recovery path.
Validation
npm run check: 100/100 tests, package verification, isolated install smokegptcode doctor: Claude 2.1.211, Codex CLI 0.144.4, Codex OAuth accepted, 270k native auto-compact windowgptcode -presponse