mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00

Files

T

dulikaifazr de1768d3ba Fix: Claude models return incomplete responses due to empty finish_reason handling (#6728 )

## Summary
Fixes streaming issue where Claude models return only 1-4 characters
instead of full responses when used through certain API
providers/proxies.

## Environment
- **OS**: Windows
- **Models affected**: Claude models (e.g., claude-haiku-4-5-20251001)
- **API Provider**: AAAI API proxy (https://api.aaai.vip/v1)
- **Working models**: GLM, Google models work correctly

## Problem
When using Claude models in both TUI and exec modes, only 1-4 characters
are displayed despite the backend receiving the full response. Debug
logs revealed that some API providers send SSE chunks with an empty
string finish_reason during active streaming, rather than null or
omitting the field entirely.

The current code treats any non-null finish_reason as a termination
signal, causing the stream to exit prematurely after the first chunk.
The problematic chunks contain finish_reason with an empty string
instead of null.

## Solution
Fix empty finish_reason handling in chat_completions.rs by adding a
check to only process non-empty finish_reason values. This ensures empty
strings are ignored and streaming continues normally.

## Testing
- Tested on Windows with Claude Haiku model via AAAI API proxy
- Full responses now received and displayed correctly in both TUI and
exec modes
- Other models (GLM, Google) continue to work as expected
- No regression in existing functionality

## Impact
- Improves compatibility with API providers that send empty
finish_reason during streaming
- Enables Claude models to work correctly in Windows environment
- No breaking changes to existing functionality

## Related Issues
This fix resolves the issue where Claude models appeared to return
incomplete responses. The root cause was identified as a compatibility
issue in parsing SSE responses from certain API providers/proxies,
rather than a model-specific problem. This change improves overall
robustness when working with various API endpoints.

---------

Co-authored-by: Eric Traut <etraut@openai.com>

de1768d3ba · 2025-11-16 19:50:36 -08:00

History

src

Fix: Claude models return incomplete responses due to empty finish_reason handling (#6728 )

2025-11-16 19:50:36 -08:00

templates

Improve compact (#6692 )

2025-11-15 07:17:51 +00:00

tests

Improve compact (#6692 )

2025-11-15 07:17:51 +00:00

Cargo.toml

chore(core) Consolidate apply_patch tests (#6545 )

2025-11-13 15:52:39 -08:00

gpt_5_1_prompt.md

chore(core) Update prompt for gpt-5.1 (#6588 )

2025-11-13 07:51:28 -08:00

gpt_5_codex_prompt.md

feat: clarify that gpt-5-codex should not amend commits unless requested (#6333 )

2025-11-06 11:42:47 -08:00

prompt.md

Add file reference guidelines to gpt-5 prompt (#3651 )

2025-09-15 08:35:30 -07:00

README.md

docs: align sandbox defaults, dedupe sections and improve getting started guide (#5357 )

2025-10-19 16:41:10 -07:00

review_prompt.md

docs: Fix markdown list item spacing in codex-rs/core/review_prompt.md (#4144 )

2025-10-30 17:39:21 -07:00

README.md

codex-core

This crate implements the business logic for Codex. It is designed to be used by the various Codex UIs written in Rust.

Dependencies

Note that codex-core makes some assumptions about certain helper utilities being available in the environment. Currently, this support matrix is:

macOS

Expects /usr/bin/sandbox-exec to be present.

Linux

Expects the binary containing codex-core to run the equivalent of codex sandbox linux (legacy alias: codex debug landlock) when arg0 is codex-linux-sandbox. See the codex-arg0 crate for details.

All Platforms

Expects the binary containing codex-core to simulate the virtual apply_patch CLI when arg1 is --codex-run-as-apply-patch. See the codex-arg0 crate for details.