picoclaw

mirror of https://github.com/sipeed/picoclaw.git synced 2026-06-12 18:08:54 +00:00

Files

T

yinwm 09a0d19119 fix: add VLLM default API base and implement MaxTokensField support

1. Add VLLM default API base (http://localhost:8000/v1)
   - Previously returned empty string, causing provider creation to fail

2. Implement MaxTokensField configuration
   - Add maxTokensField field to HTTPProvider
   - Add NewHTTPProviderWithMaxTokensField constructor
   - Use configured field name for max_tokens parameter
   - Fallback to model-based detection for backward compatibility

3. Add tests for VLLM, deepseek, ollama default API bases

Example config usage:
{
  "model_name": "glm-4",
  "model": "openai/glm-4",
  "max_tokens_field": "max_completion_tokens"
}

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-19 01:43:24 +08:00

agent

fix(antigravity): sanitize invalid tool-call history ordering

2026-02-17 20:05:41 +05:30

auth

feat: add manual callback URL entry for headless OAuth flow

2026-02-17 20:05:10 +05:30

bus

Prevent panic on publish after MessageBus is closed (#223 )

2026-02-16 15:04:25 +08:00

channels

feat: Add the Qwen provider