nestharus e73cdf5cff fix(claude): ensure max_tokens exceeds thinking budget for thinking models ...

Fixes an issue where Claude thinking models would return 400 errors when
the thinking.budget_tokens was greater than or equal to max_tokens.

Changes:
- Add MaxCompletionTokens: 128000 to all Claude thinking model definitions
- Add ensureMaxTokensForThinking() function in claude_executor.go that:
  - Checks if thinking is enabled with a budget_tokens value
  - Looks up the model's MaxCompletionTokens from the registry
  - Ensures max_tokens is set to at least the model's MaxCompletionTokens
  - Falls back to budget_tokens + 4000 buffer if registry lookup fails

This ensures Anthropic API constraint (max_tokens > thinking.budget_tokens)
is always satisfied when using extended thinking features.

Fixes: #339

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

2025-11-26 22:31:05 -08:00

..

executor

fix(claude): ensure max_tokens exceeds thinking budget for thinking models

2025-11-26 22:31:05 -08:00

geminicli

feat(gemini-cli): add multi-project support and enhance credential handling

2025-11-13 02:55:32 +08:00