v4.4.0: streaming perf + Gemini thinking + DSML parser hardening#408
Merged
Conversation
修复了使用Zeabur部署会失败的问题
feat(openai): retrieve uploaded file metadata
Core changes: - stream.go: New accumulation buffer architecture with scanner goroutine + select loop, MinChars=16, MaxWait=10ms, first-flush-immediate - dedupe.go: Add TrimContinuationOverlapFromBuilder to avoid string copies - claude/stream_runtime_core.go: Integrate toolstream for incremental text - claude/stream_runtime_finalize.go: toolstream flush support - stream_emitter.js: Reduce DeltaCoalescer thresholds (160->16 chars, 80->20ms) - empty_retry: Add thinking-aware empty output detection - Fix reasoning_content leak and finish_reason=null in edge cases - Fix tail content truncation when max_tokens exceeded Tests: sync test expectations with upstream for thinking content
…tion perf(streaming): optimize TTFT and reduce buffering latency
…rom thinking and response streams
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: eccd8c957b
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
… into new assistantturn and completionruntime packages
…ing and track emitted text to prevent redundant output blocks
…thinking by default for supported models
…rent input file handling into the completion runtime pipeline.
…tecture docs Fill gaps identified in architecture audit: add artifacts/ and static/ to directory tree, and document 7 auxiliary internal/ packages (textclean, claudeconv, compat, rawsample, devcapture, util, version) in Section 3. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add compatibility for <dsml-tool-calls>/<dsml-invoke>/<dsml-parameter> tag forms alongside the canonical pipe-prefixed DSML shell. Hyphenated forms only activate when a DSML prefix is detected, preventing false matches on bare XML lookalikes. Go and Node parsers aligned, with tests covering here-doc CDATA, streaming sieve, and negative lookalike cases. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…tripping - ValidateTurn no longer errors on thinking-only responses, deferring to ShouldRetryEmptyOutput which now also covers thinking-only outputs. - Empty output retry uses multi-turn follow-up with a regeneration prompt suffix and parent_message_id in the same DeepSeek session. - Centralize StripReferenceMarkersEnabled into textclean package to eliminate duplicated hardcoded booleans across 4 protocol handlers. - Log a deprecation warning when the legacy "compat" config key is used. - Document thinking-only retry and reference marker stripping in API.md. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This was
linked to
issues
May 2, 2026
Open
…ariants Support `<dsml_tool_calls>`, `<dsml_invoke>`, `<dsml_parameter>` in addition to the existing pipe, space, hyphen, and collapsed forms. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…inside markdown fences within tool calls
…ompact tool call content
…to enforce stricter completion requirements
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
CJackHwang
changed the title
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
3 participants
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
bufio.Scanner→Reader migration, keep-alive heartbeat, assistant turn refactor
line-offset tracking fixes, Node + Go parser alignment
reference marker stripping
Change Type
Test plan