feat(ai-review): kit-driven per-reviewer prompts (--kit) + raise synthesis token cap#177
Merged
Merged
Conversation
…hesis token cap
--kit <json> generalizes per-reviewer prompts (shared_brief + reviewers{} + optional
synthesis_prompt) so each peer-review round supplies a data kit instead of hardcoding
paper-version prompts in the pipeline. resolve_system_prompt precedence: KIT > kya-peerreview
> mode persona; synthesis uses KIT.synthesis_prompt when present. Standard modes unchanged.
Also: CLAUDE_MAX_TOKENS 4000 -> 16000 — 4-reviewer syntheses (eu-compliance / kya-peerreview /
--kit) truncated at 4000 (stop_reason=max_tokens, verdict cut off). Ceiling only; small
syntheses cost nothing extra.
First use: KYA v4.1 delta-verification pass (4/4 reviewers full, synthesis complete to verdict).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
--kit <json>macht die per-Reviewer-Prompts datengetrieben: ein Kit liefertshared_brief+reviewers{openai,gemini,perplexity,mistral}(+ optionalsynthesis_prompt). Damit braucht jede Peer-Review-Runde nur ein Kit-File statt paper-spezifischer Prompts im Code.KIT>kya-peerreview(v4.0 hardcoded) > Modus-Persona. Standard-Modi unverändert.KIT.synthesis_prompt, wenn vorhanden.CLAUDE_MAX_TOKENS4000 → 16000: 4-Reviewer-Synthesen (eu-compliance / kya-peerreview / --kit) wurden bei 4000 abgeschnitten (stop_reason=max_tokens, Verdikt fehlte). Ceiling — kein Mehrpreis für kleine Synthesen.Erster Einsatz: KYA v4.1 Delta-Verification-Pass
Kit = Delta-Brief + 4 re-fokussierte Lenses + Delta-Synthese (Per-Fix-Verdikt-Tabelle + „extern zirkulierbar?"). 4/4 Reviewer voll (GPT-5 13675, Gemini 16029, Perplexity 15318, Mistral 13901 Tok), Synthese vollständig bis zum Gesamturteil (nicht mehr abgeschnitten).
🤖 Generated with Claude Code