Skip to content

README: plainer flags section, and why the crop matters - #7

Merged
defraction0 merged 1 commit into
mainfrom
claude/tender-meitner-wpy400
Sep 13, 2026
Merged

defraction0 merged 1 commit into
mainfrom
claude/tender-meitner-wpy400

Conversation

@defraction0

Copy link
Copy Markdown
Owner

Three wording changes to the README, nothing else.

  • The pitch line drops "legally" and says why the evidence is a page crop: it is cut from the PDF by code, not written by the model, so a verdict cannot rest on a hallucinated source. The resolver is still described as using legal open-access routes where it is described.
  • The limits, case-folder and model paragraphs are rewritten shorter and plainer, with the same facts. The extract stage and out/claims.json stay in the pipeline diagram; the cherry-pick route stays on the roadmap.

The README-reading tests pass (tests/test_report_viewer.py, tests/test_brand_mark.py).

🤖 Generated with Claude Code

https://claude.ai/code/session_01Fp8Cq2FEpunJx29st3MDyb


Generated by Claude Code

The pitch says why the evidence is a page crop: it is cut from the PDF by
code, not written by the model, so a verdict cannot rest on a hallucinated
source. "Legally" is dropped from the pitch line; the routes are still named
as legal open-access routes where the resolver is described. The limits,
case-folder and model paragraphs are rewritten shorter and plainer, with the
same facts and none of the machinery — the extract stage and claims.json are
in the pipeline diagram, and the cherry-pick route is on the roadmap.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fp8Cq2FEpunJx29st3MDyb
@defraction0
defraction0 merged commit 6e87fb1 into main Sep 13, 2026
10 checks passed
defraction0 added a commit that referenced this pull request Sep 19, 2026
… side

`limits` (--max-claims, --max-sources) and this branch's per-label agreement
both decide whether a cited source is judged, so the merge had to keep three
reasons a source yields no verdict apart, not two:

  not obtainable      retrieval failed          fix access, or accept the gap
  skipped on request  you asked for a slice     raise the limit and re-run
  withheld            the readings disagree     check that citation by hand

Verified end to end: paywalled reports `not available (paywalled)`, a capped
source `not available (skipped on request)`, and a disputed label `unchecked`
with the label named. Each says which happened; none is summarised into
another.

They compose by construction: `skipped` is not in ("retrieved", "provided"),
so a skipped entry never reaches the partition that withholding splits, and a
source can never be both.

Resolutions worth knowing. cli.py took both features' flags on `refs` and
`run`, and the stage order `limits` introduced survives —
ingest → extract → refs → scout → check → highlight → report — with extraction
before references so a claims limit retrieves only what the selected claims
cite, and the escalation still inside `_refs_pipeline`. check.py kept this
branch's withheld branch with `limits`' skipped-aware reasons inside it.
CLAUDE.md kept this branch's `ask.py` seam rule and dropped the old "check.py
is the only module that calls a model", which is now false, while taking
`limits`' paragraph on how limits reach `resolve_all`. README took the shorter
rewrite from #6/#7 as the base and swapped in the four-readings bullet, since
theirs still described two. One 0.7.0 section in the changelog carries both.

Two tests needed the merged shape rather than either side's: the wizard's cost
estimate, because the reference-list call survives every limit and `apply_limits`
already accounted for it; and the flag-forwarding test, which had to stub the
new extract stage.

1170 passed, ruff clean.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants