proxysql

Commit Graph

Author	SHA1	Message	Date
Rene Cannao	9ffc3f8d71	mcp tests: add phase-B TAP coverage and optional real Claude CLI E2E runner Add two complementary TAP tests for phase-B validation and an optional real Claude CLI E2E helper, so we can validate both 'without Claude credentials' and 'with real Claude CLI' workflows. What was added: 1) CI-safe deterministic phase-B TAP - New: test/tap/tests/test_mcp_llm_discovery_phaseb-t.sh - Validates MCP phase-B primitives end-to-end without external LLM API: - list_targets - discovery.run_static (target_id-scoped setup) - catalog.list_objects - agent.run_start / agent.run_finish - llm.summary_upsert / llm.summary_get - llm.domain_upsert / llm.domain_set_members - llm.metric_upsert - llm.question_template_add - llm.search - Uses unique per-run markers to assert persisted artifacts are retrievable 2) Claude headless flow TAP smoke - New: test/tap/tests/test_mcp_claude_headless_flow-t.sh - Always validates integration path without external dependencies: - static_harvest.sh wrapper executes and yields run_id - two_phase_discovery.py --dry-run executes with target_id/run_id context - Optional real Claude execution: - enabled via TAP_RUN_REAL_CLAUDE=1 - skipped by default to keep CI deterministic 3) Manual real-CLI E2E runner - New: scripts/mcp/DiscoveryAgent/ClaudeCode_Headless/run_real_claude_e2e.sh - Runs full two-step flow manually when credentials/CLI are available: - phase-A static harvest (or --skip-phase-a + --run-id) - phase-B real Claude run via two_phase_discovery.py 4) Documentation updates - scripts/mcp/DiscoveryAgent/ClaudeCode_Headless/README.md: - documents run_real_claude_e2e.sh usage - test/tap/groups/ai/README.md: - adds manual run instructions for: - phase-A static harvest test - phase-B deterministic TAP test - Claude headless smoke (with optional real mode) Validation run: - bash -n: - test_mcp_llm_discovery_phaseb-t.sh - test_mcp_claude_headless_flow-t.sh - run_real_claude_e2e.sh - static_harvest.sh - python3 -m py_compile: - two_phase_discovery.py	2 months ago
Rene Cannao	ade0130e67	discoveryagent: update Claude Code headless flow for target_id-scoped MCP tools Enhance the existing Claude Code custom-prompt discovery examples to match the new MCP contract introduced by multi-target routing and target-scoped catalog semantics. Changes included: - static_harvest.sh - added required --target-id argument (with MCP_TARGET_ID env fallback) - always sends target_id in discovery.run_static arguments - updated usage/help/examples to include target_id - two_phase_discovery.py - added required --target-id argument - static-harvest bootstrap call now passes target_id - improved run_id error guidance with target_id-aware commands - injects <TARGET_ID> placeholder into user prompt template - improved runtime logging to display target_id - Prompt templates - two_phase_discovery_prompt.md: - catalog/agent/llm tool signatures updated to include target_id - Stage 0 and workflow text updated to use provided target_id + run_id - removed contradictory instruction that asked to call discovery.run_static in Phase 2 - two_phase_user_prompt.md: - added target_id input section - all example calls updated to pass target_id - start instructions now require target_id + run_id - README and utility example - README quick-start curl and script examples now include target_id - test_catalog.sh now accepts/prints target_id and passes it to catalog/llm calls Validation: - bash -n passed for updated shell scripts - python3 -m py_compile passed for two_phase_discovery.py	2 months ago
Rene Cannao	1b7335acfe	Fix two-phase discovery documentation and scripts - Add mcp_config.example.json for Claude Code MCP configuration - Fix MCP bridge path in example config (../../proxysql_mcp_stdio_bridge.py) - Update Two_Phase_Discovery_Implementation.md with correct Phase 1/Phase 2 usage - Fix Two_Phase_Discovery_Implementation.md DELETE FROM fts_objects to scope to run_id - Update README.md with two-phase discovery section and multi-agent legacy note - Create static_harvest.sh bash wrapper for Phase 1 - Create two_phase_discovery.py orchestration script with prompts - Add --run-id parameter to skip auto-fetch - Fix RUN_ID placeholder mismatch (<USE_THE_PROVIDED_RUN_ID>) - Fix catalog path default to mcp_catalog.db - Add test_catalog.sh to verify catalog tools work - Fix Discovery_Schema.cpp FTS5 syntax (missing space) - Remove invalid CREATE INDEX on FTS virtual tables - Add MCP tool call logging to track tool usage - Fix Static_Harvester::get_harvest_stats() to accept run_id parameter - Fix DELETE FROM fts_objects to only delete for specific run_id - Update system prompts to say DO NOT call discovery.run_static - Update user prompts to say Phase 1 is already complete - Add --mcp-only flag to restrict Claude Code to MCP tools only - Make FTS table failures non-fatal (check if table exists first) - Add comprehensive documentation for both discovery approaches	3 months ago
Rene Cannao	6fd58a6fd4	docs: Update README for v1.3 improvements Updated README to reflect new capabilities: 1. Statistical Analysis section: - Added Statistical Significance Testing subsection - Listed 5 required statistical tests (normality, correlation, chi-square, outliers, group comparisons) - Mentioned p-values and effect sizes 2. Query Analysis section: - Added Performance Baseline Measurement subsection - Listed 6 required query types with timing - Mentioned efficiency scoring (EXPLAIN vs actual) 3. Question Catalogs section: - Updated to reflect 15+ cross-domain questions (enhanced in v1.3) - Added 5 cross-domain categories with question counts 4. Cross-Domain Questions section: - Expanded from 3 examples to 15 specific questions - Organized by 5 categories with question counts - Matched new v1.3 requirements	3 months ago
Rene Cannao	39b9ce6d58	feat: Add Question Catalog generation to all agents Each agent now generates a comprehensive catalog of questions they can answer about the database, with executable answer plans using MCP tools. Question Catalog Features: - 90+ questions across all agents (minimum 15-20 per agent) - Executable answer plans with specific MCP tools for each question - Answer templates with structured output formats - Complexity ratings (LOW/MEDIUM/HIGH) and time estimates - Cross-domain questions requiring multiple agents New Output Locations: - kind="question_catalog", key="structural_questions" - kind="question_catalog", key="statistical_questions" - kind="question_catalog", key="semantic_questions" - kind="question_catalog", key="query_questions" - kind="question_catalog", key="security_questions" - kind="question_catalog", key="cross_domain_questions" Benefits: 1. Fast Answers: Pre-validated plans skip analysis phase 2. Consistent Quality: All answers follow proven templates 3. Tool Reuse: Efficient MCP tool usage patterns 4. Comprehensive Coverage: 90+ questions cover most user needs Example Question Catalog Entry: - Question: "What sensitive data exists in table X?" - Answer Plan: sample_rows + column_profile on table X - Answer Template: Structured list with sensitivity classification - Complexity: MEDIUM - Estimated Time: 30 seconds This creates a reusable knowledge base for future LLM interactions, enabling quick, accurate responses to common database questions.	3 months ago
Rene Cannao	130981d1be	feat: Add SECURITY and META agents to multi-agent discovery Expand the 4-agent system to 6 agents (5 analysis + 1 meta) with enhanced security analysis and self-improving prompt optimization. New Agents: - SECURITY: Identifies sensitive data (PII, credentials, financial), assesses access patterns, identifies vulnerabilities, and provides compliance assessment (GDPR, PCI-DSS) - META: Analyzes report quality by section, identifies gaps, suggests specific prompt improvements for future runs Protocol Changes: - Expanded from 4 rounds to 5 rounds - Round 5 is Meta Analysis (META agent only) - META agent does not participate in rounds 1-4 New Report Sections: - 5. SECURITY ANALYSIS with data classification (PUBLIC/INTERNAL/ CONFIDENTIAL/RESTRICTED) - E. Security data classification appendix New Output: - Separate META ANALYSIS document with: - Section quality ratings (depth, completeness) - Specific prompt improvement suggestions - Gap identification - Evolution history tracking This enables continuous prompt optimization through multiple discovery iterations, with each run informing improvements for the next.	3 months ago
Rene Cannao	aed042ba0d	feat: Replace single-agent with multi-agent database discovery Replace the old single-agent discovery approach with a new 4-agent collaborative system that provides more comprehensive analysis. Changes: - Add prompts/ directory with multi-agent system prompts - Replace README.md with multi-agent discovery documentation - Replace headless_db_discovery.py to use 4-agent prompt - Replace headless_db_discovery.sh to use 4-agent prompt - Remove HEADLESS_DISCOVERY_README.md (replaced by README.md) The new system uses 4 collaborating agents (STRUCTURAL, STATISTICAL, SEMANTIC, QUERY) that communicate via MCP catalog across 4 rounds: 1. Blind Exploration (parallel independent discovery) 2. Pattern Recognition (cross-agent collaboration) 3. Hypothesis Testing (validation with evidence) 4. Final Synthesis (comprehensive report) This provides deeper analysis with 15+ hypothesis validations, health scores, and prioritized recommendations.	3 months ago

7 Commits (f88dddaefb4e9067f5e1562e78e7e1ad1e6b7e00)