mushuiyu_xydt 47112fc423 fix(memory): split header-too-large embedding batches ...

Route OpenAI/OpenAI-compatible request_headers_too_large embedding failures into the existing memory-core batch splitter instead of aborting bulk memory indexing.

Tighten the classifier to require header-too-large wording rather than a bare 431 status token, so unrelated provider errors do not fan out into recursive requests.

Fixes #92465.
Thanks @mushuiyu886 for the fix and @BrettHamlin for the report and proof.

2026-06-14 05:20:25 +08:00

..

src

fix(memory): split header-too-large embedding batches

2026-06-14 05:20:25 +08:00

api.ts

fix: store memory-core dreams state in sqlite (#91056)

2026-06-06 18:38:45 -07:00

cli-metadata.ts

docs: document large extension sources

2026-06-04 21:40:44 -04:00

cli.ts

docs: document large extension sources

2026-06-04 21:40:44 -04:00

doctor-contract-api.test.ts

refactor: store Zalo hosted media in plugin state

2026-06-06 22:56:48 -07:00

doctor-contract-api.ts

refactor: store Zalo hosted media in plugin state

2026-06-06 22:56:48 -07:00

index.test.ts

docs: document large extension sources

2026-06-04 21:40:44 -04:00

index.ts

fix(memory): keep memory_search in transient qmd mode (#92639)

2026-06-13 14:14:54 +00:00

manager-runtime.ts

docs: document large extension sources

2026-06-04 21:40:44 -04:00

openclaw.plugin.json

fix(memory): move local llama.cpp runtime to provider plugin

2026-06-09 14:30:35 +08:00

package.json

chore(release): prepare 2026.6.2 beta

2026-06-04 00:06:52 +01:00

runtime-api.ts

fix: store memory-core dreams state in sqlite (#91056)

2026-06-06 18:38:45 -07:00

tsconfig.json

…