jay77721 d7682b5b92 fix(agent): fit LLM prompts to model content_length (#18093) ...

Use the chat model's context window (`content_length`) as the message-fitting budget instead of the canvas `max_tokens` parameter.

2026-08-12 17:23:43 +08:00

..

audio

Go: fix context and warnings (#18097)

2026-08-11 16:18:49 +08:00

canvas

Go: fix context and warnings (#18097)

2026-08-11 16:18:49 +08:00

chat

Port Python agentic search to Go (nav service, harness, tools) (#17702)

2026-08-03 11:16:16 +08:00

component

fix(agent): fit LLM prompts to model content_length (#18093)

2026-08-12 17:23:43 +08:00

dsl

fix(go-agent): use session IDs for cancellation and context flow (#17462)

2026-07-28 14:59:34 +08:00

harness

Go: fix context and warnings (#18097)

2026-08-11 16:18:49 +08:00

retrievalbridge

fix(go-agent): finish retrieval component (#17845)

2026-08-05 15:48:54 +08:00

runtime

Go: fix warnings (#17738)

2026-08-03 21:30:01 +08:00

sandbox

Go: fix context (#18118)

2026-08-11 19:19:29 +08:00

tool

Go: fix context, part2 (#18133)

2026-08-11 20:12:29 +08:00

workflowx

refactor: use the built-in max/min to simplify the code (#17059)

2026-07-24 15:33:02 +08:00