feat(ai-review): add kya-peerreview mode with per-reviewer lenses#176
Merged
Conversation
New --mode kya-peerreview (4 reviewers) for critical whitepaper peer review where each reviewer gets its OWN prompt instead of one shared mode persona: - shared brief (KYC-analogy anchor, global-not-local, three-layer, steelman) - GPT-5 = logic/argument consistency, Gemini = standards/tech landscape, Perplexity = web/jurisdictions + sourced counter-positions, Mistral = EU law/sovereignty - resolve_system_prompt(mode, reviewer_key) routes per-reviewer prompts; standard modes unchanged (fall back to REVIEW_PROMPTS[mode]) - dedicated SYNTHESIS_PROMPT_KYA: ranked problems, divergence, fact-check, EU-nuance, concrete fixes, verdict on the central thesis Internal pre-review is deliberately NOT included (reviewers must judge independently). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Was
Neuer
--mode kya-peerreviewfür kritische Whitepaper-Peer-Reviews, bei denen jeder Reviewer seine eigene Linse bekommt statt einer geteilten Modus-Persona — exakt nach dem KYA-v4.0-Peer-Review-Kit (TEIL 2 + TEIL 3):resolve_system_prompt(mode, reviewer_key)routet die per-Reviewer-Prompts; Standard-Modi unverändert (Fallback aufREVIEW_PROMPTS[mode], nur 1 Vorkommen übrig).SYNTHESIS_PROMPT_KYA: ranked Probleme, Divergenz, Fact-Check, EU-Nuance, konkrete Fixes, Verdikt zur Kernthese.Das interne Pre-Review (TEIL 1) ist bewusst nicht enthalten — die Reviewer sollen unabhängig urteilen.
Test / erster Lauf
--mode kya-peerreviewauf dem v4.0-Draft: 4/4 Reviewer nicht-leer (GPT-5 16482, Gemini 14092, Perplexity 12559, Mistral 13248 Tokens), Synthese ✅, exit 0, 90 KB Output. Baut auf der #167-Härtung auf (GPT-5 liefert jetzt volle Reviews).🤖 Generated with Claude Code