getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-19 06:01:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
co-mono/packages
History
Mario Zechner 8df22faedf fix(ai): ensure maxTokens > thinkingBudget for Claude thinking models 
Claude requires max_tokens > thinking.budget_tokens. When caller specifies
a small maxTokens (e.g. compaction with ~13k tokens) and reasoning is enabled
with high budget (16k tokens), the constraint was violated.

Fix: In mapOptionsForApi, add thinkingBudget on top of caller's maxTokens
(capped at model.maxTokens). If still not enough room, reduce thinkingBudget
to leave space for output.

Applied to both anthropic-messages and google-gemini-cli APIs.

Also adds test utilities for OAuth credential resolution and tests for
compaction with thinking models.

fixes #413
2026-01-03 02:45:30 +01:00
..
agent docs: update CHANGELOGs for steer()/followUp() API changes 2026-01-03 00:13:26 +01:00
ai fix(ai): ensure maxTokens > thinkingBudget for Claude thinking models 2026-01-03 02:45:30 +01:00
coding-agent fix(ai): ensure maxTokens > thinkingBudget for Claude thinking models 2026-01-03 02:45:30 +01:00
mom feat(coding-agent): complete steer()/followUp() migration 2026-01-03 00:13:25 +01:00
pods Release v0.31.1 2026-01-02 10:39:08 +01:00
tui Merge PR #382: word wrapping in Editor component 2026-01-03 00:48:28 +01:00
web-ui feat(coding-agent): complete steer()/followUp() migration 2026-01-03 00:13:25 +01:00