fix(llm-pi-ai): classify usage-based context overflow

Pass each resolved catalog model capacity into pi-ai stream conversion so the upstream full-message classifier can recognize provider-specific, silent, and length-stop overflow signals. Retain the harness text fallback for legacy provider wording and cover the catalog-resolution path with a mock-provider regression.
2026-07-19 14:18:13 +08:00
parent 44d9fbcd6d
commit 4791b40b26
5 changed files with 81 additions and 11 deletions
@@ -43,7 +43,7 @@ If a listener rewrites assembled assistant content, the loop drops replay state
 ## Vocabulary differences

 - pi-ai tool-call arguments are parsed objects; the harness stores raw JSON strings. The adapter parses input and re-stringifies output.
- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted'}` chunks, with recognized context overflow normalized to `CONTEXT_WINDOW_EXCEEDED`.
+- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted'}` chunks. Provider-specific error text and usage signals evaluated against the resolved model's context window normalize overflow to `CONTEXT_WINDOW_EXCEEDED`.
 - pi-ai folds reasoning tokens into output usage; there is no separate reasoning count to map.
 - `GenerateOptions.stop` is rejected with `UNSUPPORTED_OPTION` because pi-ai's common streaming surface cannot guarantee it across providers.