can1357 a60e492fba feat(agent): enabled dynamic reasoning override per model call ...

- Added an optional `getReasoning` callback to `AgentLoopConfig` to resolve reasoning effort dynamically for each LLM call.
- Updated the agent loop to resolve reasoning via `getReasoning` and use it in place of static `reasoning` when provided.
- Added a test confirming a run re-reads the thinking level between consecutive model calls when it changes mid-run.

2026-05-03 07:39:52 +02:00

..

utils

refactor: consolidated module import paths

2026-01-23 21:01:13 +01:00

agent-loop.test.ts

fix(ai): corrected AI abort precedence and provider stream normalization

2026-05-02 01:06:53 +02:00

agent.test.ts

feat(agent): enabled dynamic reasoning override per model call

2026-05-03 07:39:52 +02:00

helpers.ts

fix: resolved AI/OAuth helper duplication via shared modules

2026-04-23 21:02:14 +02:00