Joao 6b074653f2 fix: prevent system prompt re-injection on subsequent turns
When tool results are sent back to the model, the system prompt was being
re-injected into the user message content, causing the model to think the
user had pasted the system prompt again. This was especially noticeable
after multiple tool uses.

The fix checks if there is conversation history (len(history) > 0). If so,
it's a subsequent turn and we skip system prompt injection. The system
prompt is only injected on the first turn (len(history) == 0).

This ensures:
- First turn: system prompt is injected
- Tool result turns: system prompt is NOT re-injected
- New conversations: system prompt is injected fresh
2026-01-16 20:16:44 +00:00
2025-12-23 23:30:57 +08:00
2025-09-25 10:32:48 +08:00
2026-01-15 03:30:56 +08:00
2025-10-15 11:47:35 +08:00
2025-09-25 10:32:48 +08:00
2025-12-16 13:19:32 +08:00
2026-01-07 20:07:01 -05:00
2026-01-07 20:06:55 -05:00

CLIProxyAPI Plus

English | Chinese

This is the Plus version of CLIProxyAPI, adding support for third-party providers on top of the mainline project.

All third-party provider support is maintained by community contributors; CLIProxyAPI does not provide technical support. Please contact the corresponding community maintainer if you need assistance.

The Plus release stays in lockstep with the mainline features.

Differences from the Mainline

  • Added GitHub Copilot support (OAuth login), provided by em4go
  • Added Kiro (AWS CodeWhisperer) support (OAuth login), provided by fuko2935, Ravens2121

Contributing

This project only accepts pull requests that relate to third-party provider support. Any pull requests unrelated to third-party provider support will be rejected.

If you need to submit any non-third-party provider changes, please open them against the mainline repository.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Description
No description provided
Readme MIT 266 MiB
Languages
Go 99.8%
Shell 0.1%