BrowserUse_and_ComputerUse_.../agent
Ahmad Ragab 3dc148ab6f fix: use adaptive thinking without budget_tokens for Claude 4.6 models
For Claude 4.6 models (Opus and Sonnet), the Anthropic API rejects
budget_tokens when thinking.type is 'adaptive'. This was causing a
400 error: 'thinking.adaptive.budget_tokens: Extra inputs are not
permitted'.

Changes:
- Send thinking: {type: 'adaptive'} without budget_tokens for 4.6
- Move effort control to output_config: {effort: ...} per Anthropic docs
- Map Hermes effort levels to Anthropic effort levels (xhigh->max, etc.)
- Narrow adaptive detection to 4.6 models only (4.5 still uses manual)
- Add tests for adaptive thinking on 4.6 and manual thinking on pre-4.6

Fixes #1126
2026-03-13 03:21:13 +01:00
..
__init__.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
anthropic_adapter.py fix: use adaptive thinking without budget_tokens for Claude 4.6 models 2026-03-13 03:21:13 +01:00
auxiliary_client.py merge: resolve conflicts with main (URL update to hermes-agent.nousresearch.com) 2026-03-12 17:49:26 -07:00
context_compressor.py chore: lower default compression threshold from 85% to 50% (#1096) 2026-03-12 15:51:50 -07:00
display.py Merge PR #736: feat(honcho): async writes, memory modes, session title integration, setup CLI 2026-03-12 19:05:11 -07:00
insights.py chore: add GLM/Kimi/MiniMax models to insights pricing (zero cost) 2026-03-06 19:12:14 -08:00
model_metadata.py fix(anthropic): live model fetching + adaptive thinking for 4.5+ models 2026-03-12 17:04:31 -07:00
prompt_builder.py Merge PR #785: feat: conditional skill activation based on tool availability 2026-03-11 08:43:30 -07:00
prompt_caching.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
redact.py Merge PR #713: docs: clarify Telegram token regex constraint 2026-03-10 16:59:54 -07:00
skill_commands.py feat: platform-conditional skill loading + Apple/macOS skills 2026-03-07 00:47:54 -08:00
trajectory.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00