Yichen Jiang 1d2ea70e9b feat(llm-deepseek): per-model output cap in the advisory catalog ...

A catalog entry may now carry its own `maxTokens`, matching the shape the
pi-ai adapter already exposes. Exact-model resolution prefers it over the
profile value, so capping one model no longer means capping the route.

Defaults are unchanged: an entry without a cap, and any unlisted
pass-through id, still resolve to the profile `maxTokens` (256,000), and the
shipped catalog keeps its context windows.

2026-08-04 14:53:02 +08:00

..

adapter.ts

feat(llm-deepseek): per-model output cap in the advisory catalog

2026-08-04 14:53:02 +08:00

index.ts

feat(llm-deepseek): per-model output cap in the advisory catalog

2026-08-04 14:53:02 +08:00

invariant.ts

fix(invariants): assert runtime relationships, not API shapes

2026-07-20 19:34:19 +08:00

serialize.ts

fix(agent-loop): rematerialize adapter defaults

2026-07-30 21:49:58 +08:00

sse.ts

refactor(llm-deepseek): replace hand-rolled SSE parser with eventsource-parser

2026-07-26 22:45:33 +08:00

translate.ts

fix(llm): classify empty model completions as retryable EMPTY_RESPONSE

2026-07-24 19:23:12 +08:00

types.ts

Gate JSDoc completeness on every package export

2026-07-06 22:09:30 +08:00