fix(agent): skip tools for models without tool-call capability and parse image output

- Add SupportsToolCall to RunConfig; only inject tools into SDK when set
- Update twilight-ai to 497ad09 which adds SSE scanner 10MB buffer
  (fixes token-too-long on large image payloads) and parses the images
  array from OpenAI-compatible chat completions into StreamFilePart
This commit is contained in:
Acbox
2026-04-03 00:01:14 +08:00
parent 574bc1fb59
commit fc2b603018
7 changed files with 18 additions and 8 deletions
+1 -1
View File
@@ -26,7 +26,7 @@ require (
github.com/larksuite/oapi-sdk-go/v3 v3.5.3
github.com/mailgun/mailgun-go/v5 v5.14.0
github.com/memohai/acgo v0.0.0-20260221232113-babac0d6acd7
github.com/memohai/twilight-ai v0.3.4-0.20260329101319-3ebcc563f5d9
github.com/memohai/twilight-ai v0.3.4-0.20260402155501-497ad09c6724
github.com/modelcontextprotocol/go-sdk v1.4.1
github.com/opencontainers/image-spec v1.1.1
github.com/opencontainers/runtime-spec v1.3.0