Skip to content

v1.1.0 — The Auditable Council

Latest

Choose a tag to compare

@ernestprovo23 ernestprovo23 released this 21 Jun 18:10

The auditable council. Every run can now produce a structured, agreement-scored, fully auditable verdict plus a redacted execution manifest — on top of the existing synthesize / raw / debate / adversarial modes.

conclave ask "<decision>" now returns a verdict: a headline + recommendation, a consensus score computed by reproducible arithmetic over the models' own clustering (never an LLM-emitted number), conflicts citing which providers disagreed (with evidence), and minority reports — alongside a manifest recording which providers were called and how the verdict was made. Streaming and --json carry it too.

Highlights

  • CouncilResult v2verdict, consensus_score/method/label, conflicts, provider_votes, minority_reports, manifest (all additive, backward-compatible).
  • ModelHarnessManifest with verdict-extraction provenance — no secrets, ever.
  • Deterministic consensus (position_cluster_ratio_v1) — the auditability fix: the number is arithmetic over the model's clustering, not an LLM figure.
  • Native structured output across OpenAI / Anthropic / Gemini, threaded through call_model.
  • Static provider capability catalog; CLI verdict rendering + --json manifest; streaming verdict parity.

The verdict is optional — open-ended prompts, single-member councils, and extraction failures degrade gracefully to synthesis-only. Default-on; opt out with Council(extract_verdict=False).

Full notes in CHANGELOG.md. Install: pip install -U conclave-cli