deer-flow

mirror of https://github.com/bytedance/deer-flow.git synced 2026-10-28 22:20:35 +00:00

History

fix(channels): give DingTalk AI cards the channel token, not the SDK fetch (#7597 )

* fix(channels): give DingTalk AI cards the channel token, not the SDK fetch

AICardReplier's async card calls read dingtalk_client.get_access_token()
inline, and dingtalk-stream refreshes it with requests.post and no
timeout. Card creation and card streaming both run on the Gateway loop,
so the first card and every SDK refresh after it (about every two hours)
blocked the loop for the whole token request, without bound if DingTalk
stalled.

Hand the replier a _CardTokenClient that serves the channel's own
httpx token (10s timeout), set before card creation and before every
streamed update. A token failure while streaming now raises into send's
existing sampleMarkdown fallback instead of being skipped silently.

Pin it with a strict blocking-I/O anchor over a real DingTalkStreamClient
and AICardReplier, a gate meta-check, and unit tests for token rotation
and failure. LocalHttpServer also records each request's method, path
and headers.

* docs(changelog): reference #7597 for the DingTalk AI card token fetch

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-10-28 10:50:30 +08:00

channels

fix(channels): give DingTalk AI cards the channel token, not the SDK fetch (#7597 )

2026-10-28 10:50:30 +08:00

gateway

feat(plugins): add redacted administrator diagnostics (#7612 )

2026-10-27 21:29:21 +08:00

mcp_tasks

fix(mcp): retain durable control claims through slow calls and cancellation (#6780 )

2026-10-21 22:03:21 +08:00

scheduler

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588 )