rob thijssen
8f9e956d17
All checks were successful
build-prerelease / Resolve version stamps + change detection (push) Successful in 33s
build-prerelease / Build cortex binary (push) Has been skipped
build-prerelease / Build helexa-bench binary (push) Has been skipped
build-prerelease / Package cortex RPM (push) Has been skipped
build-prerelease / Package helexa-bench RPM (push) Has been skipped
build-prerelease / Build neuron-blackwell (push) Successful in 1m44s
build-prerelease / Build neuron-ada (push) Successful in 2m14s
build-prerelease / Lint (fmt + clippy) (push) Successful in 2m16s
build-prerelease / Build neuron-ampere (push) Successful in 2m55s
build-prerelease / Test (push) Successful in 4m24s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 1m41s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 1m43s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 1m45s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 53s
InferenceError responses were a flat `{"error": "..."}` string. OpenAI
clients (opencode, the openai SDK) reach into `error.type`/`error.code`
to drive behaviour — most importantly `code == "context_length_exceeded"`
triggers auto-compaction + retry instead of a hard failure. A flat string
is invisible to that logic.
Rewrite `inference_error_response` to emit the nested envelope
`{"error": {"message","type","code","param", ...diagnostics}}` and map:
- ModelNotLoaded → 404 invalid_request_error / model_not_found
- PromptTooLong → 400 invalid_request_error / context_length_exceeded
(message: "maximum context length is N tokens", + prompt_len/max)
- InsufficientVram → 503 api_error / insufficient_vram
- VisionUnsupported→ 400 invalid_request_error / vision_unsupported
- TemplateRenderFailed → 422 invalid_request_error / template_render_failed
- Other → 500 api_error / null code
Diagnostic extras ride inside the error object so the envelope shape is
stable. Both inline match blocks in the chat-completions handler
(streaming + non-streaming) now defer to the shared helper, which the
responses handler already used — one source of truth.
Adds 4 unit tests covering the envelope shape and codes. Also fixes a
pre-existing clippy lint (cloned_ref_to_slice_refs) in qwen3_5 snapshot
test surfaced by a newer clippy.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>