rob thijssen
ec2b6450b2
Some checks are pending
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Blocked by required conditions
build-prerelease / Resolve version stamps (push) Successful in 33s
CI / Format (push) Successful in 36s
CI / Clippy (push) Successful in 2m33s
build-prerelease / Build cortex binary (push) Successful in 4m20s
CI / Test (push) Successful in 5m4s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Build neuron-blackwell (push) Successful in 5m40s
build-prerelease / Build neuron-ampere (push) Successful in 7m53s
build-prerelease / Build neuron-ada (push) Successful in 5m33s
build-prerelease / Package cortex RPM (push) Successful in 8m20s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 2m56s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 2m57s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m46s
Qwen3.6-27B occasionally emits a <tool_call> body with the right
arguments but no top-level `name` field — observed in the field as
mkdir-style bash calls like
{"arguments":{"command":"mkdir -p .../doc/plan/{01-discovery,...}"}}
with no `name`. The agent had no tool to dispatch and surfaced a
Failed card; the model would then hang or retry the same shape.
Add a shape-based inference layer:
- tools::infer_tool_name(arguments) — given an `arguments` object
alone, return Some(name) when the key set uniquely identifies one
tool: `{command}` or `{command,cwd}` → bash, `{path,content}` →
write_file, `{path,old_text,new_text}` → edit_file. Ambiguous
shapes (`{path}` alone — could be read_file or list_dir) return
None so the agent still emits a Failed card rather than guessing.
- agent::try_repair_missing_name(raw) — parses a malformed body,
applies infer_tool_name, returns (name, args_json) on success.
- drive_prompt sweeps malformed_calls through this repair before
the Failed-card path. Recovered calls go into tool_buckets at
the next free index and dispatch through the normal tool loop.
10 new unit tests in tools::tests cover the inference table plus
the verbatim mkdir failure from the field log.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>