Oleks 105e9f5bae Phase 7 acceptance: two FR-5.4/S3 fidelity fixes found by running the real pipeline
S1-S3 and S5-S8 pass; S4 is prepared but deliberately unfiled pending user
sign-off (tasks.md 7.4 stays unchecked).

Two bugs surfaced by running the composed pipeline against real data rather
than synthetic fixtures, both in load-bearing places:

audit-snapshot: cost_per_invocation folded to 0 when a candidate had zero
invocations in a window, so a step that simply did not run reported -100% and
direction() called it `shrunk`. That is the quiet-window artefact FR-5.4 exists
to prevent, one level up from absolute tokens, and it contradicted direction()'s
own docstring. It is now None, metric_delta marks the pair `unmeasured`,
direction returns a new `unmeasured` status, and the pages render "not run".

tests/calibration/mask-worktree-audit.py: recomputed script_loc from scripts
alone, silently dropping all 1051 LOC of worktree-discipline's hooks. Masking
one 272-LOC script appeared to remove 1323, taking script_coverage 0.353 -> 0.083
instead of 0.297, which let S3 pass partly on an artefact of the mask. The mask
now matches build_aggregate. S3 still flags the known cut `high` /
llm-over-script-digest on the corrected, harder input.

Both fixes carry regression tests; suite is 156 assertions, exit 0.
2026-07-29 18:15:47 +03:00

inference-arbitrage

Audits a Claude Code plugin — its skill/agent definitions and its real usage transcripts — to find steps that are being done by raw LLM inference but pass every test of a deterministic script, and files the well-evidenced ones as issues on the target plugin's own repo. Runs on demand; each run accumulates into a snapshot history so cost and candidate status can be tracked over time.

The name echoes builder-arbitrage: route each unit of work to the cheapest executor that can do it correctly — here, "script vs. model" instead of "which build node."

Status: scaffolding, pre-implementation. See design/ for the full specification:

Tracked as issues on this repo under the v0.1.0 milestone.

S
Description
Claude Code plugin — optimize Claude model selection by routing inference requests to the best model per query, balancing cost, latency, and accuracy.
Readme MIT
688 KiB
Languages
Python 66%
Shell 34%