Repository navigation
README: plainer flags section, and why the crop matters - #7
Merged
Merged
Conversation
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
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.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Three wording changes to the README, nothing else.
out/claims.jsonstay 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