release: 0.26.0 — source authority, a second trust axis (#111)#115
Merged
Conversation
Ships the source-authority layer (#112/#113/#114): deterministic, no-LLM domain scoring (scoreAuthority), keep-stage ranking that gives authoritative sources the limited fetch slots (--source-authority prefer|strict|off), and a source-trust signal in the footer + --json — orthogonal to citation support, so a fully-cited answer built on content farms is flagged instead of silently confident. Version bump + CHANGELOG + README doctor sample only.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Release 0.26.0 — source authority
Cuts the release that ships the source-authority layer (#111), already merged to
masteracross #112 / #113 / #114 but not yet published. Latest npm isv0.25.3; theSource trust:footer and keep-stage ranking are unreleased, sonpm i -g @askalf/deepdivedoesn't yet have them.Why now
deepdive verifies that each cited claim appears in its source (lexical citation support) — but that's silent on whether the source itself was worth citing. On recency/trending topics, where AI content farms outrank primary sources, an answer can be fully cited, score perfect support, and rest entirely on fabricable spam (the 2026-06-15 dogfood: "latest open-weight LLMs" → 100% content farms at 1.00 citation support). 0.26.0 surfaces the missing axis — source authority — measured deterministically (no LLM) and reported separately so the two signals can disagree.
What's in it (already on master)
scoreAuthority— pure, no-network domain scoring →primary | reputable | unknown | low; boost-led, unknown stays neutral, low is a small curated content-farm denylist (feat(sources): source-authority scorer — P1 foundation (#111) #112).--source-authority/DEEPDIVE_SOURCE_AUTHORITY=prefer(default, reorder-only) |strict(drop farms, min-keep floor) |off; authoritative sources win the limited fetch slots (feat(sources): keep-stage authority ranking (P1 of #111) #113).Source trust: high|mixed|lowin the citation-health footer + per-sourceauthorityand top-levelsourceTrustin--json; clean runs stay silent (feat(sources): source-trust signal in output + --json (P2 of #111) #114).This PR
Version bump + CHANGELOG
[0.26.0]section + README doctor sample (2 spots) only — no source changes. On merge,auto-release.ymltagsv0.26.0, builds/tests, creates the GitHub release from the CHANGELOG section, andnpm publish --provenance.