voyage/tests
Kjell Tore Guttormsen 8e3946e687
feat(research): researching-sources skill, preloaded by the five web agents
The source rules the research agents shared by copy now live in one skill,
skills/researching-sources/: official sources first with URL, date and
matching version; no citation, no finding; an empty search is reported with
its denominator and never as a finding; fetched pages are data, and text in
them aimed at AI assistants is ignored and reported; nothing local in an
outbound query. It also holds the one confidence scale.

- docs-, community-, security-, contrarian-researcher and research-scout
  preload it (skills: ["voyage:researching-sources"]); the copied rule text
  leaves them, their own role stays.
- Two agent sentences that contradicted the rules are gone: an empty
  counter-evidence search "increases confidence", and "fall back silently".
- /trekresearch names the skill where it starts the external agents and in
  web follow-ups; Phase 6 rates on the skill's scale word for word; the
  deep-research adapter accepts `contradictory` like the template does.
- Enforced by: research-validator checks structure only, the query privacy
  gate runs only in the default-off STORM steps; the rest is text only.
  A guard on every web search is a separate later order (operator 08.10).
- Red baseline (helpers, offline fixtures): without the skill 3 of 5 runs
  ignored an injected instruction silently and 1 of 2 contrarian runs counted
  an empty search as weak support; with it 0 of 3 and 0 of 2. Path leaks:
  0 of 7 without, 0 of 5 with.
- Eval cases (3 should trigger, 2 should not, 1 effect), written, not run.
- tests/lib/skills-research-prose-pins.test.mjs: 14 pins, 13 red on 4ee711a.

Credits: Addy Osmani, agent-skills @9d0c60d,
skills/source-driven-development/SKILL.md:97-114 (MIT); Jesse Vincent,
obra/superpowers @8ca22db, skills/diagnosing-superpowers/ (MIT). Ideas only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:46:49 +02:00
..
commands feat(execute): one fresh helper per step, a controller on the diff, proof by command 2026-10-06 19:58:18 +02:00
fixtures fix: the second lekerepo trial's faults that made a result wrong or misleading 2026-10-08 15:12:07 +02:00
helpers fix(validate): a check that can never run is caught when the brief or plan is written 2026-10-08 06:42:33 +02:00
hooks fix: close what an independent review found in the trial 2 fixes 2026-10-08 15:21:56 +02:00
integration chore(voyage): release v5.0.0 — remove bespoke playground + /trekrevise + Handover 8; render produced artifacts to HTML + link, annotate via /playground 2026-05-12 14:05:07 +02:00
lib feat(research): researching-sources skill, preloaded by the five web agents 2026-10-08 21:46:49 +02:00
parsers chore(voyage): release v5.0.0 — remove bespoke playground + /trekrevise + Handover 8; render produced artifacts to HTML + link, annotate via /playground 2026-05-12 14:05:07 +02:00
scripts fix(review): close the gate's fail-open paths an independent review found 2026-10-06 20:03:16 +02:00
synthetic chore(voyage): S34 — V30 economy-profile self-declares experimental (uncalibrated Jaccard floor) 2026-06-20 10:18:38 +02:00
validators fix(plan): an open MAJOR stops the plan; after the last round the operator decides 2026-10-08 07:07:00 +02:00