rob thijssen
d662fa20ef
All checks were successful
build-prerelease / Resolve version stamps + change detection (push) Successful in 30s
build-prerelease / Lint (fmt + clippy) (push) Successful in 2m20s
build-prerelease / Build helexa-bench binary (push) Successful in 2m6s
build-prerelease / Build cortex binary (push) Successful in 2m20s
build-prerelease / Test (push) Successful in 4m12s
build-prerelease / Build neuron-blackwell (push) Successful in 1m38s
build-prerelease / Build neuron-ada (push) Successful in 2m5s
build-prerelease / Build neuron-ampere (push) Successful in 4m44s
build-prerelease / Package helexa-bench RPM (push) Successful in 1m17s
build-prerelease / Package cortex RPM (push) Successful in 1m17s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 1m41s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 1m42s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 1m48s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 53s
Claude Code (ANTHROPIC_BASE_URL -> cortex) hits POST /v1/messages, but
anthropic_to_openai forwarded the request's `tools` array verbatim via
the flattened `extra`. neuron feeds that straight into the HF chat
template, which iterates the OpenAI shape (tool.function.name/.parameters).
Anthropic-shaped tools ({name, description, input_schema}) rendered as
broken/empty definitions, the model improvised an unparseable
<tool_use_name>...</tool_use_name> tool-call format, neuron's
<tool_call>{json}</tool_call> detector missed it, and the markup fell
through as plain assistant text — so CC never received a structured
tool_use and the agent loop died.
Request-side translation now reshapes:
- tool definitions: {name, description, input_schema}
-> {type:"function", function:{name, description, parameters}}
- tool_choice: auto->"auto", any->"required", none->"none",
tool->{type:"function",function:{name}}
- assistant tool_use blocks -> OpenAI assistant.tool_calls
(arguments JSON-stringified) — fixes multi-turn
- user tool_result blocks -> standalone role:"tool" messages keyed by
tool_call_id
- system content blocks flatten to text instead of being JSON-serialised
into the prompt; best-effort image-block -> image_url part
Wire-debug instrumentation (tracing levels only; cortex/neuron ship at
info, operator infra runs at debug):
- every handler emits a debug! "inbound request" line tagging the wire
surface (anthropic | openai-chat | openai-responses | openai-completions)
plus model/stream/tools and, for Anthropic, tool_history/system
- response side reports upstream_tool_calls + finish_reason, streaming
and non-streaming
- full inbound + translated-upstream bodies at trace! (UTF-8-safe, capped)
Tests: 8 request-side unit tests + an end-to-end gateway test asserting
the upstream neuron receives OpenAI-shaped tools and a
user->assistant(+tool_calls)->tool->user history.
Also tighten script/infra-log-verbosity.sh: independent cortex/neuron
RUST_LOG args, cortex-only by default (neuron restart behind
--with-neuron so we don't needlessly cold-reload models), mkdir -p the
drop-in dir, symmetric RUST_LOG cleanup, and set -euo pipefail.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>