Adds bench/cross_model_selfplay.py + `make bench-cross-model` target.
For each question in a fixture, runs `arborist query` once per
configured model (default: Hermes + Qwen) and tabulates:
* audit_mode per model (EVIDENCE-WARRANTED → POINTER-LINKED → UNGROUNDED)
* agreement on primary source URI
* grounding rate per model
* estimated $/grounded-answer (per-call prices configurable)
* cheap-first cascade analysis (try cheapest, escalate on UNGROUNDED)
This is the "ask twice for two options" pattern from the agent
perspective — bakes it in as a benchmark so we can measure whether
the cascade beats always-using-the-stronger-model on $/grounded.
First live run (2 questions × 2 models, $0.41):
- Hermes: 1/1 grounded (1 timeout — operational issue)
- Qwen: 2/2 grounded STRICT
- Cascade: 2/2 grounded for $0.25 — beats always-Qwen ($0.32)
when Hermes succeeds on its first call.
Output: bench/cross_model_results/<utc-iso>.{jsonl,md} (gitignored).
Adds a Sphinx extension at docs/_source/_ext/makefile_targets.py that
parses the project Makefile's '## description' annotations and writes
docs/_source/api/makefile.rst at build time. Same convention 'make help'
uses, so the reference stays in sync with the source.
Generated page is grouped by target prefix (fetch-, ingest-, distill-,
docs-, etc.) and rendered as a list-table. Shows on RTD alongside the
autodoc API modules.
Generated file is gitignored — RTD regenerates on every build.
The previous commit (588aa45) accidentally git-added four
.claude/worktrees/agent-* gitlinks via `git add -A`. Those are
session-local Claude Code worktree pointers (a tooling artifact),
not source. Removing them from the index and adding `.claude/` to
.gitignore so future sessions don't trip the same way.
Adds bench/qa_sweep.py + bench/qa_questions.txt + `make bench-qa` target.
Sweeps a fixed question set through quote and claim_lattice_pointer modes,
N samples per cell (default 3), each sample burns the cached record so
Hermes nondeterminism becomes the variance source.
Outputs:
bench/qa_results/<utc>.jsonl one row per (mode, question, sample)
bench/qa_results/<utc>.md summary + per-question vote counts
Question set spans the failure-mode shapes the verifier needs to handle:
narrow factoid, broad descriptive ("tell me about X"), entity list,
relationship, and out-of-corpus (should land UNGROUNDED honestly).
Methodology gap this closes: at n=1 the strict-rate swings ±20pp on a
fixed prompt purely from sampling noise. n=3 makes 5pp deltas legible.
