mathiasandClaude Opus 4.8 c40b46b661 fix(llm): send generous max_tokens on every request ...

The copied OpenAI-compatible client sent no max_tokens. Thinking models
(qwen3, deepseek-r1) spend their budget on the reasoning trace and return
EMPTY content when max_tokens is unset, which the summarizer treats as an
error. ADR-004 says change Tapir's copy rather than the hyperguild upstream,
so set a generous default (8192) leaving room for both reasoning and output.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-02 20:55:49 +02:00

..

client_test.go

fix(llm): send generous max_tokens on every request

2026-06-02 20:55:49 +02:00

client.go

fix(llm): send generous max_tokens on every request

2026-06-02 20:55:49 +02:00

router_test.go

feat(adapters): copy stdlib llm package (Client + Router) per ADR-004

2026-06-02 17:01:56 +02:00

router.go

feat(adapters): copy stdlib llm package (Client + Router) per ADR-004

2026-06-02 17:01:56 +02:00