dev_agentandClaude Opus 5.5 cb93134f3e Fix reasoning-model temperature quirk matching and validation ...

- Omit temperature for OpenRouter's namespaced OpenAI reasoning models
  (openai/o1, openai/o1-mini, openai/o3-mini, openai/o1:online).
- Match o1/o3 only as the bare family name or with a "-" variant, so
  o123 and o3custom keep their temperature.
- Validate the caller's request before clearing temperature, so a
  negative temperature is still a validation error, not a sent request.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-04 08:58:43 -04:00

..

anthropic

Anthropic Messages adapter (#40)

2026-10-04 08:09:20 -04:00

ollama

Ollama native adapter (#41)

2026-10-04 08:47:05 -04:00

openai

Anthropic Messages adapter (#40)

2026-10-04 08:09:20 -04:00

presets

Fix reasoning-model temperature quirk matching and validation

2026-10-04 08:58:43 -04:00

errors_test.go

Feature 08 task 2: OpenAI-compatible adapter (#35)

2026-10-04 07:41:45 -04:00

errors.go

Anthropic Messages adapter (#40)

2026-10-04 08:09:20 -04:00

fake_test.go

Feature 08 task 1: Provider interface, typed errors and Fake provider (#33)

2026-10-03 16:14:12 -04:00

fake.go

Feature 08 task 1: Provider interface, typed errors and Fake provider (#33)

2026-10-03 16:14:12 -04:00

llm_test.go

Feature 08 task 1: Provider interface, typed errors and Fake provider (#33)

2026-10-03 16:14:12 -04:00

llm.go

Feature 08 task 2: OpenAI-compatible adapter (#35)

2026-10-04 07:41:45 -04:00

settings.go

Add provider presets and FromSettings factory

2026-10-04 08:51:19 -04:00