Run a context-asymmetric debate in a single call.

One canonical entry point. Pick a mode:

• auto (default): Ploidy generates both sides via the configured OpenAI-compatible API endpoint and returns the convergence result. Requires non-empty context_documents plus a configured API endpoint. HITL pause/resume is available via pause_at; resume with the legacy debate_review tool.

• solo: you supply both positions (and optionally both challenges) and Ploidy persists + converges them. No external API key needed — the recommended single-terminal flow when the caller (e.g. Claude Code itself) writes both sides locally.

The older 12-tool surface (debate_start / debate_join / debate_position / ...) remains available for two-terminal and HITL workflows but is now deprecated; new integrations should use this tool.

Args: prompt: The decision question to debate. mode: "auto" or "solo". deep_position: (solo only) Deep side's stance. fresh_position: (solo only) Fresh side's stance. deep_challenge: (solo only) Optional deep-side critique. fresh_challenge: (solo only) Optional fresh-side critique. deep_label / fresh_label: (solo) display labels for roles. fresh_role: (auto) "fresh" or "semi_fresh". delivery_mode: (auto + semi_fresh) "passive", "active", or "selective". pause_at: (auto) Optional "challenge" or "convergence" HITL pause point. deep_n / fresh_n: (auto) Ploidy level per side. effort: (auto) "low", "medium", "high", "max". injection_mode: (auto) Context formatting mode. context_pct: (auto) Percentage of context to retain. language: (auto) Output language code. deep_model / fresh_model: (auto) Model override. Supplying either applies it to both sides; if both are supplied they must match. context_documents: Documents attached only to the Deep side. Required and non-empty in auto mode; optional provenance in solo mode. context_sources: Optional provenance labels, one per context document. blocked_sources: Optional strings that must not appear in source labels or context documents. target_lease: Optional target identifier that pins this debate's scope. allowed_sources: Optional source-label allowlist; defaults to target_lease when a target lease is set.

Returns: Convergence result dict, or paused state (auto + pause_at).

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Begin a new debate session with a decision prompt.

Creates a debate and a Deep (full-context) session. Share the returned debate_id with the fresh session so it can join.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Join an existing debate as a fresh or semi-fresh session.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Submit a position from a session.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Submit a challenge to another session's position.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Trigger convergence analysis for a debate.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Cancel a debate in progress.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Permanently delete a debate and all its data.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Get current state of a debate.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Retrieve past debates and their outcomes.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Run a complete debate from caller-supplied positions in one call.

Single-terminal entry point: the caller generates both sides locally and submits the texts here. No external API key required.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Run a complete debate automatically in a single command.

Requires non-empty context_documents and a configured API endpoint. Generates positions and one independent challenge per seat with one resolved model, runs the protocol, and returns the convergence result.

DEPRECATED (v0.4) — prefer debate(prompt, mode=...).

Review and resume a paused auto-debate (HITL).

Call after debate_auto with pause_at paused the run. Action is one of 'approve', 'override', or 'reject'.