System

Runtime Contracts

Contract-based status, no fragile UI or hard patch-version checks.

Debates22 transcripts

Runs75 real · 2 fake

Judgements2119 artifacts

Cost$0.000328ledger-based

Version

{'app': 'disputatio', 'app_version': '0.5.5', 'schema_version': '0.2.0', 'env': 'production'}

DB

{'status': 'ok', 'driver': 'psycopg', 'migration_status': 'ok', 'schema_version': '0.2.0', 'db_schema_version': '0.2.0', 'alembic_revision': '0001_core_schema', 'missing_tables': [], 'seed_status': 'ok'}

Queue

{'status': 'ok', 'backend': 'valkey', 'queued': 0, 'running': 0, 'failed': 0, 'worker_seen_recently': True}

Storage

{'status': 'ok', 'root': '/app/storage/files', 'writable': True, 'used_percent': 70.36, 'free_bytes': 11849433088, 'artifact_count': 19}

Schema Contract

{'app': 'disputatio', 'status': 'ok', 'schema_version': '0.2.0', 'db_schema_version': '0.2.0', 'required_tables': ['system_schema_versions', 'system_settings', 'users', 'jobs', 'events', 'audit_events', 'budgets', 'cost_ledger', 'artifacts', 'debates', 'debate_sources', 'transcripts', 'speakers', 'segments', 'llm_providers', 'llm_models', 'model_profiles', 'model_snapshots', 'rubric_versions', 'prompt_versions', 'experiment_conditions', 'jury_runs', 'run_manifests', 'model_judgements', 'score_dimensions', 'metric_definitions', 'metric_results', 'performance_metrics', 'aggregation_profiles', 'aggregation_results'], 'missing_tables': [], 'table_count': 31, 'alembic_revision': '0001_core_schema', 'migration_status': 'ok', 'seed_status': 'ok', 'seed_checks': {'schema_version': True, 'provider_openrouter': True, 'model_a_budget': True, 'model_b_reasoning': True, 'model_c_contrast': True, 'rubric_neutral': True, 'prompt_neutral': True, 'aggregation_median': True, 'metric_latency': True}}

Real Jury Readiness

{'status': 'ok', 'ready': True, 'openrouter_key_present': True, 'app_attribution': {'HTTP-Referer': 'https://disputatio.itservice-braun.de', 'X-OpenRouter-Title': 'Disputatio', 'X-OpenRouter-Categories': 'research,education'}, 'models': ['qwen/qwen3-next-80b-a3b-instruct:free', 'google/gemini-2.5-flash-lite', 'mistralai/mistral-small-3.2-24b-instruct'], 'model_count': 3, 'limits': {'max_models_per_run': 3, 'max_input_chars_per_run': 12000, 'max_cost_per_run_usd': 0.1, 'max_tokens': 3000, 'temperature': 0.0, 'json_mode': True, 'structured_schema': True, 'require_parameters': True, 'disable_reasoning': True}, 'recommended_first_run_models': ['qwen/qwen3-next-80b-a3b-instruct:free', 'google/gemini-2.5-flash-lite', 'mistralai/mistral-small-3.2-24b-instruct'], 'cost_estimate': {'estimated_known_max_cost_usd': 0.002325, 'unknown_price_models': [], 'models': [{'model': 'qwen/qwen3-next-80b-a3b-instruct:free', 'estimated_max_cost_usd': 0.0}, {'model': 'google/gemini-2.5-flash-lite', 'estimated_max_cost_usd': 0.0015}, {'model': 'mistralai/mistral-small-3.2-24b-instruct', 'estimated_max_cost_usd': 0.000825}]}, 'first_real_run_ready': True, 'diagnostic_policy': {'max_models': 3, 'max_retry_per_model': 1, 'aggregation_uses_only_schema_valid': True, 'strict_json_schema_first': True}}

Fake E2E Readiness

{'status': 'ok', 'ready': True, 'readiness': {'active_rubrics': 1, 'active_prompts': 1, 'active_aggregation_profiles': 1, 'fake_models': 3}, 'external_calls': False}

Run via ./scripts/e2e_fake_jury.sh.