Start a new Elenchus verification session. Collects initial context, builds dependency graph, and initializes mediator.

Get current verification context including files, issues summary, and session state.

Submit the output of a verification round. Analyzes for new issues, context expansion, convergence, and mediator interventions.

End the verification session with a final verdict.

Get issues from the current session with optional filtering.

Create a checkpoint for potential rollback.

Rollback session to a previous checkpoint.

Apply a fix for an issue within the current session. Creates checkpoint, updates issue status, refreshes file context, and optionally triggers re-verification. Use this to maintain fix-verify continuity without starting new sessions.

Analyze ripple effect of a code change. Shows which files and functions will be affected by modifying a specific file.

Get mediator summary including dependency graph stats, verification coverage, and intervention history.

Get detailed role prompt and guidelines for Verifier or Critic. Includes mustDo/mustNotDo rules, output templates, and checklists.

Get role enforcement summary including compliance history, average scores, violations, and current expected role.

Update role enforcement configuration. Can enable strict mode, change minimum compliance score, or toggle role alternation requirement.

Start a re-verification session for resolved issues. Links to a previous verification session and focuses on verifying that fixes are correct and complete. Returns focused verification context with target issues.

Save verification baseline after a successful session. This baseline is used for differential analysis in future verifications to only check changed code.

Get differential analysis summary for a project. Shows what has changed since the last verification and estimates token savings.

Get verification history for a project including past sessions and baselines.

Get cache statistics including hit rate, total entries, and token savings.

Clear all cached verification results. Requires confirm: true.

Get current tier pipeline status including completed tiers, escalations, and token usage.

Manually escalate to a higher verification tier (screen → focused → exhaustive).

Mark the current tier as complete and check for auto-escalation based on issues found.

Get quality safeguards status including periodic verification, confidence, and sampling stats.

Update confidence scores for files based on verification method (cache, chunk, tiered, etc.).

Record results from random sampling verification of a skipped file.

Check if session convergence is allowed based on quality safeguards.

Set the response compression mode for token optimization. Use "compact" for moderate savings or "minimal" for aggressive savings.

Get current token optimization statistics and recommendations.

Configure token optimization settings including compression, context management, and semantic caching.

Estimate potential token savings for a verification session.

Generate customized Verifier/Critic role prompts based on user requirements. This is a 3-step process:

1. detect_domain - Detects the verification domain from requirements

2. generate_verifier - Generates Verifier role (needs domain result)

3. generate_critic - Generates Critic role (needs verifier role)

Each step returns a prompt to send to an LLM. After all 3 steps, call elenchus_set_dynamic_roles with the results.

Set dynamically generated roles for a session. Call this after completing all 3 steps of elenchus_generate_roles. The roles will be used automatically by getRolePrompt when sessionId is provided.

Get LLM evaluation prompt for convergence quality assessment. Returns a prompt to send to an LLM.

Get LLM evaluation prompt for issue severity assessment. Returns a prompt to send to an LLM.

Get LLM evaluation prompt for edge case coverage. Returns a prompt to send to an LLM.

Submit LLM evaluation response. Call this after receiving an LLM response to an evaluation prompt.