AIFactory API Reference

Home
851 endpoints
67 blueprints
app 91
GET / Serve the main web interface
GET /api/actions/palette Redirect to correct quick-actions palette endpoint
GET /api/agents Redirect to correct agents/list endpoint
GET /api/cache/metrics Get comprehensive cache and optimization metrics
GET /api/cache/metrics/prometheus Get metrics in Prometheus format
POST /api/cache/metrics/reset Reset all cache metrics
POST /api/cache/semantic/clear Clear the semantic cache
GET /api/cache/semantic/stats Get semantic cache statistics
POST /api/chart/save Save chart as PNG
GET POST /api/charts Redirect to correct analytics/charts endpoint
DELETE GET /api/charts/<chart_id> Redirect to correct analytics/charts detail endpoint
GET /api/config Get current configuration (excluding sensitive keys)
GET /api/config/default-credentials Get default credentials status
POST /api/config/save Save current configuration to .env file (explicit save endpoint)
GET /api/config/summary Get configuration summary
POST /api/config/update Update configuration settings
GET /api/config/validate Validate application configuration
GET /api/context/budget/status Get context budget status for current model
GET /api/context/memory List global facts via LangGraph Store (semantic namespace).
POST /api/context/memory Add a fact to global memory via LangGraph Store.
GET /api/context/session/<session_id> Get thread info via Platform Threads API.
DELETE /api/context/session/<session_id> Delete thread via Platform Threads API.
POST /api/context/session/<session_id>/summarize Auto-summarization is handled by Platform / LangMem tools (agents
POST /api/context/session/<session_id>/sync Update thread metadata (session name, message count) via Platform.
GET /api/context/sessions List threads via Platform Threads API.
GET POST /api/dashboards Redirect to correct analytics/dashboards endpoint
GET /api/dashboards/<dashboard_id> Redirect to correct analytics/dashboards detail endpoint
GET POST /api/feature-sets Feature sets - return empty list since not fully implemented
GET POST /api/features Redirect to correct nim/features endpoint
GET /api/features/<feature_id> Redirect to correct nim/features detail endpoint
GET /api/health/connections Get health status of all managed connections (Redis, MCP, Database)
GET /api/health/ocr Report the chat-attachment OCR cascade's active engine + endpoint health.
GET /api/health/platform Probe LangGraph Platform readiness.
GET /api/health/teradata-mcp Probe the Teradata MCP server's reachability (used by status bar's DB chip).
GET /api/llm/health Check LLM provider health (global / fallback layer).
GET /api/llm/health/agent/<agent_id> Check a specific agent's LLM health (used in solo mode for the pinned
GET /api/llm/health/supervisor Check the SUPERVISOR (routing) layer's LLM health.
GET /api/mcp/deployment-mode Get current MCP deployment mode (read-only at runtime)
GET /api/mcp/docker-env Get Docker MCP configuration from .env
POST /api/mcp/docker-env Update Docker MCP configuration in .env
GET /api/mcp/docker/image-info Get Docker image information
GET /api/mcp/docker/logs Get Docker container logs.
POST /api/mcp/docker/rebuild Rebuild Docker MCP image
POST /api/mcp/docker/restart Restart Docker MCP container
POST /api/mcp/docker/start Start Docker MCP container
GET /api/mcp/docker/status Get Docker MCP server status
POST /api/mcp/docker/stop Stop Docker MCP container
GET /api/mcp/env Get .env configuration from teradata-mcp-server/.env
POST /api/mcp/env Update .env configuration
POST /api/mcp/env/delete Delete a key from .env configuration
GET /api/mcp/health Perform health check - returns format expected by frontend
GET /api/mcp/health-summary Get comprehensive health summary for main app display
GET /api/mcp/logs Get recent logs
GET /api/mcp/logs/stream Stream logs via SSE
GET /api/mcp/modules Get status of all MCP server modules
GET /api/mcp/profiles Get available profiles
GET /api/mcp/prompts Get available MCP prompts via MCP API with fallback to filesystem
GET /api/mcp/prompts/<prompt_id> Get a specific MCP prompt's content via MCP API.
GET /api/mcp/prompts/metadata Get metadata for all MCP prompts including module status
POST /api/mcp/refresh-tools Refresh MCP tools cache based on current deployment mode
POST /api/mcp/restart Restart MCP server (Local mode only)
POST /api/mcp/start Start MCP server (Local mode only)
GET /api/mcp/status Get MCP server status (Local MCP only)
POST /api/mcp/stop Stop MCP server (Local mode only)
GET /api/mcp/tool/<tool_name> Get schema for a specific MCP tool
GET /api/mcp/tools Get available MCP tools
GET /api/neural-circuit/data Neural circuit visualization - return placeholder data
GET /api/optimization/tools/stats Get tool optimizer statistics
GET /api/prompts/all Get both MCP prompts and user prompts combined
POST /api/prompts/copy-mcp Alias for POST /api/user/prompts/copy-mcp - matches UnifiedPromptManager expectations
GET /api/prompts/user Alias for GET /api/user/prompts - matches UnifiedPromptManager expectations
POST /api/prompts/user Alias for POST /api/user/prompts - matches UnifiedPromptManager expectations
GET /api/prompts/user/<prompt_id> Alias for GET /api/user/prompts/<id> - matches UnifiedPromptManager expectations
PUT /api/prompts/user/<prompt_id> Alias for PUT /api/user/prompts/<id> - matches UnifiedPromptManager expectations
DELETE /api/prompts/user/<prompt_id> Alias for DELETE /api/user/prompts/<id> - matches UnifiedPromptManager expectations
POST /api/prompts/user/<prompt_id>/use Track prompt usage (optional analytics endpoint for UnifiedPromptManager)
GET /api/status Get current configuration status
POST /api/tokens/count Count tokens in provided text
POST /api/tokens/estimate-cost Estimate cost for given token counts
GET /api/user/prompts Get all user-saved prompts
POST /api/user/prompts Create a new user prompt (from scratch or with specific data)
GET /api/user/prompts/<prompt_id> Get a specific user prompt by ID
PUT /api/user/prompts/<prompt_id> Update an existing user prompt
DELETE /api/user/prompts/<prompt_id> Delete a user prompt
POST /api/user/prompts/copy-mcp Create a user copy of an MCP prompt for customization
GET /app Serve the React SPA from static/dist/
GET /app/ Serve the React SPA from static/dist/
GET /app/<path:path> Serve the React SPA from static/dist/
GET /favicon.ico Serve favicon to prevent 404 errors
GET /metrics Expose Prometheus metrics for scraping.
GET /test/layers Serve the layer performance test page
agent_card 4
GET /.well-known/agent-card.json Top-level organisational card — a directory of every discoverable agent.
GET /.well-known/agent-card/<agent_id> Per-agent A2A card. 404s for unknown / non-discoverable agents.
GET /.well-known/agent-card/<agent_id>.json Per-agent A2A card. 404s for unknown / non-discoverable agents.
GET /api/agents/cards Internal endpoint: lists every agent with status/source/runtime/enabled
api_docs_bp 2
GET /api-docs Render the API documentation page.
GET /api/docs/json JSON export of all registered endpoints.
accuracy 11
GET /api/accuracy/benchmarks List all available benchmarks
POST /api/accuracy/benchmarks Add a new benchmark
DELETE /api/accuracy/benchmarks/<benchmark_id> Delete a benchmark
GET /api/accuracy/export Export accuracy data in various formats
GET /api/accuracy/query-types Get available query types with descriptions
POST /api/accuracy/scores Record an accuracy score for an LLM response
POST /api/accuracy/scores/evaluate Evaluate a response without recording it
GET /api/accuracy/scores/recent Get recent accuracy scores
GET /api/accuracy/status Get accuracy scoring system status
GET /api/accuracy/summary Get accuracy summary statistics
GET /api/accuracy/trends Get daily accuracy trends
error_handler 8
GET /api/actions/mission-status Mission status endpoint
GET /api/health Health check endpoint
GET /api/local-models/list List local models
GET /api/local-models/status Local models status
POST /api/log/error Log frontend errors - prevents infinite error loop
GET /api/memory/status Memory status endpoint
GET /api/nim/performance/summary NIM performance summary endpoint
GET /api/security/quantum-shield/data Quantum shield visualization data
admin 8
POST /api/admin/ai/analyze-audit POST /api/admin/ai/analyze-audit - AI-powered audit log analysis
POST /api/admin/ai/nl-to-sql POST /api/admin/ai/nl-to-sql - Convert natural language to SQL
POST /api/admin/ai/optimize-sql POST /api/admin/ai/optimize-sql - AI-powered SQL optimization
POST /api/admin/connect Connect to Teradata as DBC admin.
POST /api/admin/execute-sql Execute arbitrary SQL (for advanced users).
POST /api/admin/grant-role Grant TD_AIAdmin role to a user.
POST /api/admin/revoke-role Revoke TD_AIAdmin role from a user.
GET /api/admin/users List users and their TD_AIAdmin role status.
agent_layers 7
POST /api/agent-layers/circuit/gate Apply quantum gate to circuit
GET /api/agent-layers/circuit/state Get current quantum circuit state
GET /api/agent-layers/metrics Get performance metrics for all layers
GET /api/agent-layers/result/<task_id> Get result for a specific task
GET /api/agent-layers/status Get agent layers system status
GET /api/agent-layers/stream SSE stream for real-time quantum circuit updates
POST /api/agent-layers/submit Submit task to agent layers
agents_factory 8
POST /api/agents-factory/chat Synchronous chat — returns the full response in one shot.
POST /api/agents-factory/chat/reset Reset conversation state for a session.
POST /api/agents-factory/chat/stream SSE streaming chat with the ReAct Agent Builder.
GET /api/agents-factory/chat/working-draft Return the current working AgentDefinition draft for live preview.
POST /api/agents-factory/compose-preview Stateless: given an AgentDefinition (or partial), return the composed prompt
POST /api/agents-factory/describe/stream One-shot LLM → canonical v2 AgentDefinition JSON draft.
POST /api/agents-factory/improve/stream One-shot LLM refinement of an existing AgentDefinition.
GET /api/agents-factory/status
agents 70
GET /api/agents/<agent_name> Get detailed configuration for a specific agent
PUT /api/agents/<agent_name> Update an existing agent configuration.
DELETE /api/agents/<agent_name> Delete an agent (only custom agents can be deleted)
POST /api/agents/<agent_name>/clone Clone an existing agent with a new name.
PUT /api/agents/<agent_name>/llm Update LLM configuration for a specific agent
GET /api/agents/<agent_name>/prompt Get the full generated system prompt for an agent.
PUT /api/agents/<agent_name>/prompt Update the agent's additional_instructions (custom prompt additions).
POST /api/agents/<agent_name>/prompt/regenerate Regenerate the system prompt from current skill fields.
GET /api/agents/<agent_name>/routing Get per-agent routing config.
PUT /api/agents/<agent_name>/routing Update per-agent routing config.
GET /api/agents/<agent_name>/skills Get full skills data for an agent from agents.yml.
PUT /api/agents/<agent_name>/skills Update skills for an agent in agents.yml.
POST /api/agents/<agent_name>/skills/<skill_name>/toggle Enable/disable a specific skill for an agent.
POST /api/agents/<agent_name>/skills/attach Integration I5 — reverse CTA: attach a skill to an existing agent.
POST /api/agents/<agent_name>/skills/attach/undo Consume the 10-s undo token and revert the ``knowledge_skills`` mutation.
POST /api/agents/<agent_name>/toggle Toggle agent enabled/disabled status
PUT /api/agents/<agent_name>/tools Update tool access configuration for a specific agent
GET /api/agents/active-layer Phase 10.9: Get the currently active orchestration layer based on settings.
GET /api/agents/config Get multi-agent configuration
POST /api/agents/create Create a new agent configuration
POST /api/agents/describe/stream Conversational "describe-your-agent" fast path — Phase 2.5.
GET /api/agents/dispatch/config Get the dispatch configuration from orchestration.yml.
PUT /api/agents/dispatch/config Update the dispatch configuration in orchestration.yml.
GET /api/agents/export Export all agent configurations
GET /api/agents/foundational-tools Return the foundational-tool tiers intersected with the live MCP catalog.
GET /api/agents/handoffs Get recent agent handoff history
POST /api/agents/import Import agent configurations
GET /api/agents/info Get information about available agents and multi-agent configuration.
GET /api/agents/layer-info Phase 10.9: Get layer-specific runtime information for all agents.
GET /api/agents/list List all agents with summary info
GET /api/agents/models/<path:pattern> Get a single model entry.
PUT /api/agents/models/<path:pattern> Add or update a single model entry.
DELETE /api/agents/models/<path:pattern> Delete a model from registry.
GET /api/agents/models/providers Get provider defaults.
PUT /api/agents/models/providers Update provider defaults.
GET /api/agents/models/registry Get full model registry.
PUT /api/agents/models/registry Bulk update model registry.
POST /api/agents/models/resolve Resolve capabilities for a model name.
GET /api/agents/providers Get available LLM providers for agent configuration
POST /api/agents/reload Phase 5A/6B: Hot-reload agent configs and rebuild supervisor graph.
GET /api/agents/routing/analytics Get routing analytics: success rates by tier and agent.
GET /api/agents/routing/collaboration Get full collaboration map.
PUT /api/agents/routing/collaboration Update collaboration map.
GET PUT /api/agents/routing/compound-detection GET/PUT compound detection configuration from orchestration.yml.
GET /api/agents/routing/config Get full routing configuration.
PUT /api/agents/routing/config Update global routing_config.yml and reload.
POST /api/agents/routing/diagnose Run the full routing cascade on a query and return diagnostic trace.
GET /api/agents/routing/disambiguation Get all disambiguation rules.
PUT /api/agents/routing/disambiguation Bulk update disambiguation rules.
POST /api/agents/routing/feedback Record routing feedback (success/failure) for analytics and auto-tuning.
GET /api/agents/routing/hints Get all agents' routing configs in bulk, plus global routing hint settings.
PUT /api/agents/routing/hints/global Update global routing hint settings (enabled, threshold, margin).
GET /api/agents/routing/llm-config Get LLM routing intelligence configuration.
PUT /api/agents/routing/llm-config Update LLM routing intelligence configuration.
GET /api/agents/routing/model-prompts Get model prompt variants.
PUT /api/agents/routing/model-prompts Update model prompts.
POST /api/agents/routing/preview-prompt Preview supervisor prompt with current config.
GET /api/agents/routing/stats Get routing telemetry stats from ConfigDrivenRouter.
DELETE /api/agents/routing/stats Reset routing telemetry counters.
GET /api/agents/routing/thresholds Get collaboration thresholds.
PUT /api/agents/routing/thresholds Update collaboration thresholds.
GET /api/agents/routing/tool-categories Get tool categorization rules.
PUT /api/agents/routing/tool-categories Update tool categorization rules.
GET /api/agents/supervisor Get supervisor configuration
PUT /api/agents/supervisor Update supervisor configuration
POST /api/agents/sync Force a full bi-directional sync between Flask and LangGraph Platform.
GET /api/agents/sync-status Get bi-directional sync status between Flask and LangGraph Platform.
POST /api/agents/test-routing Test agent routing for a given query without executing
POST /api/agents/validate Validate an agent configuration without saving
GET /api/agents/visualization Get agent handoff visualization data for current session.
ai_assistant 5
POST /api/ai/assist POST /api/ai/assist - Unified AI task handler
POST /api/ai/batch POST /api/ai/batch - Process multiple AI tasks in batch
GET /api/ai/health GET /api/ai/health - Check AI service health and availability
GET /api/ai/models GET /api/ai/models - List available AI models and their status
POST /api/ai/stream POST /api/ai/stream - Streaming AI response (Server-Sent Events)
analytics_charts 15
GET /api/analytics/alerts Get all alerts
POST /api/analytics/alerts Create new alert
GET /api/analytics/analytics/performance Get performance analytics
GET /api/analytics/analytics/wave/data Get quantum wave visualization data
GET /api/analytics/charts Get all chart configurations
POST /api/analytics/charts Create new chart configuration
GET /api/analytics/charts/<chart_id> Get specific chart configuration
DELETE /api/analytics/charts/<chart_id> Delete chart configuration
GET /api/analytics/charts/<chart_id>/data Get chart data
GET /api/analytics/dashboards Get all dashboards
POST /api/analytics/dashboards Create new dashboard
GET /api/analytics/dashboards/<dashboard_id> Get specific dashboard
GET /api/analytics/reports Get all reports
POST /api/analytics/reports/generate Generate analytics report
GET /api/analytics/tokens Get token usage analytics
artifact 14
GET /api/artifacts/<artifact_id> Get a previously generated artifact by ID.
DELETE /api/artifacts/<artifact_id> Delete a stored artifact.
GET /api/artifacts/<artifact_id>/download Download artifact as standalone HTML file.
GET /api/artifacts/<artifact_id>/html Get just the HTML content for rendering in iframe.
POST /api/artifacts/clear Clear all stored artifacts (admin endpoint).
POST /api/artifacts/dashboard Generate a single dashboard artifact with multiple charts in CSS Grid layout.
GET /api/artifacts/dashboards List all saved dashboard configurations. [Future implementation]
GET /api/artifacts/dashboards/<dashboard_id> Retrieve a saved dashboard configuration. [Future implementation]
POST /api/artifacts/dashboards/save Save a named dashboard configuration. [Future implementation]
POST /api/artifacts/from-chart-data Generate artifacts from chat response chart_data format.
POST /api/artifacts/generate Generate a self-contained HTML artifact from chart data.
POST /api/artifacts/preview Generate and return artifact HTML directly for immediate preview.
GET /api/artifacts/status Get artifact system status.
GET /api/artifacts/themes/<theme_name> Get theme configuration by name.
registration 5
POST /api/auth/login Login with username and password.
POST /api/auth/logout Clear session.
GET /api/auth/me Get current user info from session.
PUT /api/auth/profile Update user profile fields.
POST /api/auth/register Register a new user account.
cache 15
GET /api/cache/alerts Get current cache performance alerts.
POST /api/cache/batch/group Preview how queries would be grouped without processing them.
POST /api/cache/batch/process Process multiple queries using batch processing.
GET /api/cache/batch/status Get batch processing status and configuration.
POST /api/cache/clear Clear cache entries.
GET /api/cache/config Get current cache configuration.
POST /api/cache/config Update cache configuration.
GET /api/cache/health Get cache system health status.
GET /api/cache/metrics Export cache metrics in Prometheus format.
GET /api/cache/prompt-stats Get Anthropic prompt cache statistics.
POST /api/cache/similar Find similar cached queries for debugging/analysis.
GET /api/cache/stats Get detailed cache hit/miss statistics.
GET /api/cache/status Get comprehensive status of all cache subsystems.
POST /api/cache/toggle Enable or disable semantic caching.
POST /api/cache/warmup Trigger cache warmup with common queries.
chat 13
POST /api/chat Process chat request with multi-step execution, optional document context, and enhanced context memory
POST /api/chat/clear Clear chat history for the current session
POST /api/chat/context Set document context for a chat session
DELETE /api/chat/context Clear document context for a chat session
POST /api/chat/generate-title Generate a concise title for a chat session based on conversation content
GET /api/chat/history Get chat history for the current session
GET /api/chat/memory/langchain/status Get LangChain/LangGraph memory integration status
GET /api/chat/memory/pipeline/stats Get memory extraction pipeline statistics
GET /api/chat/memory/status Get status of all enhanced memory systems (Phase 2.2 & 2.6)
POST /api/chat/solo/reset Reset a solo-mode agent-run session.
POST /api/chat/stream Process chat request with real-time progress updates and optional document context
POST /api/chat/stream/tokens Stream LLM response token-by-token for low first-token latency.
GET /api/chat/viz/<request_id> PERF Phase 5: Fetch async viz result for a POST /api/chat request.
chat_enhancements 4
POST /api/chat-enhancements/clear Clear chat history and temporary files
GET /api/chat-enhancements/export Export chat history
GET /api/chat-enhancements/status Get chat system status
POST /api/chat-enhancements/stream Enhanced streaming chat endpoint with file support
chat_attach 5
POST /api/chat/attach Upload a file and kick off a Platform ingest run.
DELETE /api/chat/attach/<doc_id> Remove all chunks + the temp file for this attachment.
GET /api/chat/attach/<doc_id>/preview Return the attachment's metadata blob (filename + first 500 chars + page count).
GET /api/chat/attach/<doc_id>/status Return the last-known phase/status for this doc_id (in-memory mirror).
GET /api/chat/attach/<doc_id>/stream SSE stream of the Platform ingest run's progress.
chat_voice 1
POST /api/chat/transcribe Transcribe a single audio blob. Returns {text, provider}.
circuit_breaker 11
GET /api/circuit-breakers Get status of all circuit breakers.
POST /api/circuit-breakers Create a new circuit breaker with custom configuration.
GET /api/circuit-breakers/<name> Get status of a specific circuit breaker.
DELETE /api/circuit-breakers/<name> Remove a circuit breaker from the registry.
GET /api/circuit-breakers/<name>/metrics Get detailed metrics for a circuit breaker.
POST /api/circuit-breakers/<name>/open Force a circuit breaker to open state.
POST /api/circuit-breakers/<name>/reset Reset a circuit breaker to closed state.
GET /api/circuit-breakers/health Get health summary of all circuit breakers.
POST /api/circuit-breakers/mcp/auto-reset Auto-reset the MCP circuit breaker if the MCP health check reports healthy.
POST /api/circuit-breakers/reset-all Reset all circuit breakers to closed state.
GET /api/circuit-breakers/status FE-facing alias of /health that returns the breaker list directly.
claude_code 7
GET /api/claude-code/context Gather live health/cache/error context for injection.
GET /api/claude-code/session/history Return past session metadata.
POST /api/claude-code/session/start Start a new diagnostic/repair session.
POST /api/claude-code/session/stop Stop the running session.
GET /api/claude-code/session/stream/<session_id> SSE stream of session output.
GET /api/claude-code/status Check backend availability and provider info.
GET /api/claude-code/tasks List predefined diagnostic tasks.
copilot 7
GET /api/copilot/agents List active agents (for Copilot discovery).
GET /api/copilot/declarative-agent.json Track E: Serve the Copilot Studio declarative-agent manifest (v1.0 schema).
GET /api/copilot/plugin.json Serve the Copilot plugin manifest.
POST /api/copilot/query Copilot-optimized query endpoint.
GET /api/copilot/skills/<name>.yaml Track E: Serve a narrowed OpenAPI slice used as a skill by the declarative
GET /api/copilot/tools List available MCP tools (for Copilot discovery).
GET /api/openapi.yaml Serve the OpenAPI specification.
debug_urls 2
GET /api/debug/external-urls
GET /api/debug/langfuse-auto-login
direct_llm 11
POST /api/direct-llm/direct-llm/generate Generate text using selected model
POST /api/direct-llm/direct-llm/optimize-prompt Optimize a prompt for a specific model
GET /api/direct-llm/direct-llm/plasma/metrics Get Plasma Core metrics for visualization
POST /api/direct-llm/direct-llm/prompt-chains Create a new prompt chain
POST /api/direct-llm/direct-llm/prompt-chains/<chain_id>/execute Execute a prompt chain
GET /api/direct-llm/direct-llm/prompt-templates Get available prompt templates
GET /api/direct-llm/direct-llm/samples Get sample prompts and chains
GET /api/direct-llm/direct-llm/stream/plasma-state Stream plasma core state updates
GET /api/direct-llm/direct-llm/token-usage Get token usage statistics
GET /api/direct-llm/models Get available LLM models - returns REAL configured models
GET /api/direct-llm/models/<model_id> Get detailed information about a specific model
grafana_embed 6
GET /api/grafana/dashboard/<dashboard_uid> Get dashboard details with all panel embed URLs.
GET /api/grafana/dashboards List available dashboards with metadata.
GET /api/grafana/embed/<dashboard_uid> Get embed URL for a dashboard or panel.
GET /api/grafana/health Check Grafana connectivity.
GET /api/grafana/page/<dashboard_uid> Render a full monitoring page with embedded panels.
GET /api/grafana/panels/<dashboard_uid> Get all panels for a dashboard with their embed URLs.
health 8
GET /api/health Main health check endpoint.
GET /api/health/database Check database connection health
GET /api/health/live Kubernetes-style liveness probe
GET /api/health/mcp Check MCP server connection health (all registered servers)
GET /api/health/metrics Basic metrics endpoint
GET /api/health/ready Kubernetes-style readiness probe
GET /api/health/redis Check Redis connection health
GET /api/health/warmup Orchestrator warmup status endpoint.
platform_health 6
GET POST /api/health/chromadb Transitional stub. ChromaDB was retired in W1 of the 2026-03 reinnovation.
GET POST /api/health/langgraph Probe the self-hosted LangGraph Platform runtime at `LANGGRAPH_API_URL`.
GET POST /api/health/mcp Delegate to `/api/mcp/status` — the canonical Teradata MCP server probe.
GET POST /api/health/modelops Delegate to `/api/modelops/test-connection` — the canonical ModelOps probe.
GET POST /api/health/teradata Probe Teradata DB by asking for its version via the MCP server.
GET POST /api/health/teradata_vs Delegate to `/api/tdvs/health` — the canonical VS health check.
jwt 12
POST /api/jwt/ai/analyze-login POST /api/jwt/ai/analyze-login - AI-powered login anomaly detection
POST /api/jwt/auto-login Auto-login using default credentials from configuration.
GET /api/jwt/config Get JWT configuration.
POST /api/jwt/device-flow-start Initiate OAuth device flow.
POST /api/jwt/device-flow/init Initiate OAuth device flow.
POST /api/jwt/device-flow/poll Poll for device flow token completion.
GET /api/jwt/ensure-valid Ensure a valid token exists (load existing or auto-login).
GET /api/jwt/load Load JWT token from file.
POST /api/jwt/password-flow Generate JWT token using password flow.
POST /api/jwt/refresh Refresh JWT token using refresh token.
POST /api/jwt/save Save JWT token to file.
POST /api/jwt/validate Validate a JWT token.
api_keys 3
POST /api/keys Create a new API key.
GET /api/keys List all active API keys (metadata only, never raw keys).
DELETE /api/keys/<key_hash> Revoke an API key by its hash.
langflow_inventory 3
GET /api/langflow/flows List Langflow flows annotated with AIFactory mapping + sync status.
GET /api/langflow/mcp-servers Return the MCP servers currently registered in Langflow — for the
POST /api/langflow/register-mcp/<name> Register a known MCP server (teradata / neo4j-cypher / all) inside
langgraph 9
GET /api/langgraph/neural/metrics Get neural network metrics
GET /api/langgraph/samples Get sample workflow templates
GET /api/langgraph/stream/events SSE endpoint for real-time graph events
GET /api/langgraph/workflows Get all workflows
POST /api/langgraph/workflows Create a new workflow
GET /api/langgraph/workflows/<workflow_id> Get specific workflow details
POST /api/langgraph/workflows/<workflow_id>/edges Add an edge to a workflow
POST /api/langgraph/workflows/<workflow_id>/execute Execute a workflow
POST /api/langgraph/workflows/<workflow_id>/nodes Add a node to a workflow
langsmith 14
GET /api/langsmith/agents/<name>/metrics
GET /api/langsmith/agents/<name>/runs Recent runs for a given agent (by graph_id/run-name filter).
GET /api/langsmith/datasets
POST /api/langsmith/datasets
POST /api/langsmith/datasets/<dataset_id>/examples
POST /api/langsmith/evaluate Run an evaluation experiment against a dataset.
GET /api/langsmith/info
GET /api/langsmith/link/agent/<name>
GET /api/langsmith/link/project
GET /api/langsmith/link/run/<run_id>
GET /api/langsmith/link/workflow/<workflow_id>
GET /api/langsmith/projects
GET /api/langsmith/workflows/<workflow_id>/metrics
GET /api/langsmith/workflows/<workflow_id>/runs Recent runs for a given workflow (by metadata.workflow_id filter).
llm_analysis 10
GET /api/llm-analysis/benchmarks Get all benchmark definitions
POST /api/llm-analysis/benchmarks Create a new benchmark definition
DELETE /api/llm-analysis/benchmarks/<benchmark_id> Delete a benchmark
GET /api/llm-analysis/export Export accuracy data as JSON or CSV
POST /api/llm-analysis/run-benchmarks Run benchmark suite and record results
GET /api/llm-analysis/scores Get accuracy scores with optional filtering
POST /api/llm-analysis/scores Record a new accuracy score
GET /api/llm-analysis/session/<session_id>/summary Get summary for a specific session
GET /api/llm-analysis/summary Get dashboard summary metrics
GET /api/llm-analysis/trends Get trend data for charts
local_models 20
GET /api/local-models/ Get all local models
POST /api/local-models/ Add a new local model
GET /api/local-models/<model_id> Get specific local model details
DELETE /api/local-models/<model_id> Delete a local model
POST /api/local-models/<model_id>/benchmark Run performance benchmark on model
POST /api/local-models/<model_id>/download Start model download
POST /api/local-models/<model_id>/inference Run inference on local model
POST /api/local-models/<model_id>/load Load model into memory
GET /api/local-models/benchmarks Get all benchmarks
GET /api/local-models/cache Get all cache entries
POST /api/local-models/cache/<model_id>/evict Evict model from cache
GET /api/local-models/cache/stats Get cache statistics
GET /api/local-models/downloads Get all download tasks
GET /api/local-models/downloads/<task_id> Get download task status
GET /api/local-models/huggingface/model-info Get HuggingFace model information
GET /api/local-models/huggingface/search Search HuggingFace model hub
GET /api/local-models/inference/<request_id> Get inference request result
GET /api/local-models/neural-circuit/data Get neural circuit visualization data
GET /api/local-models/offline/config Get offline mode configuration
PUT /api/local-models/offline/config Update offline mode configuration
mcp_docker 13
GET /api/mcp-docker/container Get Docker container information
GET /api/mcp-docker/env Get Docker environment variables
POST /api/mcp-docker/env Update Docker environment variable
GET /api/mcp-docker/health Health check for Docker MCP container
GET /api/mcp-docker/health/summary Get comprehensive health summary for Docker deployment
GET /api/mcp-docker/image Get Docker image information
GET /api/mcp-docker/logs Get Docker container logs
GET /api/mcp-docker/logs/stream Stream Docker container logs via SSE
POST /api/mcp-docker/rebuild Rebuild Docker MCP image
POST /api/mcp-docker/restart Restart Docker MCP container
POST /api/mcp-docker/start Start Docker MCP container
GET /api/mcp-docker/status Get Docker MCP container status
POST /api/mcp-docker/stop Stop Docker MCP container
mcp 9
POST /api/mcp-legacy/call Execute an MCP tool with provided parameters
POST /api/mcp-legacy/execute Execute an MCP tool with provided parameters
GET /api/mcp-legacy/modules/status Get MCP modules status
GET /api/mcp-legacy/prompts Get available MCP prompts/templates using async client
GET /api/mcp-legacy/prompts/<prompt_id> Get a specific MCP prompt's content via MCP API.
GET /api/mcp-legacy/resources Get available MCP resources (not yet implemented)
GET /api/mcp-legacy/status Get MCP connection status and statistics
GET /api/mcp-legacy/tool/<tool_name> Get detailed information about a specific MCP tool
GET /api/mcp-legacy/tools Get list of available MCP tools using async MCP client (cached for 5 min)
mcp_local 13
GET /api/mcp-local/env Get .env configuration
POST /api/mcp-local/env Update .env configuration
POST /api/mcp-local/env/delete Delete a key from .env configuration
GET /api/mcp-local/health Perform health check
GET /api/mcp-local/logs Get recent logs
GET /api/mcp-local/logs/stream Stream logs via SSE with heartbeat for connection keepalive
GET /api/mcp-local/modules Get status of all MCP server modules
GET /api/mcp-local/profiles Get available profiles
GET /api/mcp-local/prompts/metadata Get metadata for all MCP prompts
POST /api/mcp-local/restart Restart Local MCP server
POST /api/mcp-local/start Start Local MCP server
GET /api/mcp-local/status Get Local MCP server status
POST /api/mcp-local/stop Stop Local MCP server
mcp_factory 28
GET /api/mcp/actual-mode Get what MCP server mode is ACTUALLY running (not just configured).
POST /api/mcp/call Execute an MCP tool with provided parameters.
GET /api/mcp/compare Compare status of both Local and Docker deployments
GET /api/mcp/container Get Docker container info (Docker mode only)
GET /api/mcp/db-status Check database connectivity via MCP with timeout.
GET /api/mcp/env Get environment variables (auto-routes based on deployment mode)
POST /api/mcp/env Update environment variable (auto-routes based on deployment mode)
POST /api/mcp/env/check-restart-type Check if environment changes require restart or rebuild.
POST /api/mcp/execute Execute an MCP tool with provided parameters.
GET /api/mcp/health Health check based on ACTUAL running mode (not just configured)
GET /api/mcp/health/summary Get comprehensive health summary (auto-routes based on deployment mode)
GET /api/mcp/image Get Docker image info (Docker mode only)
GET /api/mcp/info Get comprehensive MCP deployment information
GET /api/mcp/logs Get MCP server logs (auto-routes based on deployment mode)
GET /api/mcp/logs/stream Stream MCP server logs via SSE (auto-routes based on deployment mode)
GET /api/mcp/mode Get current MCP deployment mode (configured AND actual running state)
POST /api/mcp/mode Switch MCP deployment mode with mutual exclusion.
GET /api/mcp/modules Get MCP module status (works in both Local and Docker modes)
GET /api/mcp/modules/status Get MCP module status (works in both Local and Docker modes)
GET /api/mcp/profiles Get available MCP profiles (Local mode only)
GET /api/mcp/prompts Get list of available MCP prompts.
POST /api/mcp/rebuild Rebuild Docker image (Docker mode only)
POST /api/mcp/restart Restart MCP server (auto-routes based on deployment mode)
POST /api/mcp/start Start MCP server (auto-routes based on deployment mode)
GET /api/mcp/status Get MCP server status based on ACTUAL running mode (not just configured).
POST /api/mcp/stop Stop MCP server (auto-routes based on deployment mode)
GET /api/mcp/tool/<tool_name> Get details for a specific MCP tool by name.
GET /api/mcp/tools Get list of available MCP tools.
memory_inspector 21
POST /api/memory/cleanup No-op stub — Platform-native cleanup (Z7 / 2026-04-26).
GET /api/memory/connections Get neural connection map
POST /api/memory/context Add new context to memory
GET /api/memory/context/history Get context history
GET /api/memory/episodic Get episodic memory summaries with drill-down
GET /api/memory/facts Get key facts from procedural memory
GET /api/memory/graph/entities E2: Paginated entity listing with optional type filter.
GET /api/memory/graph/entity/<path:name> E4: Entity detail with properties and neighborhood.
GET /api/memory/graph/relationships E5: Paginated relationship listing with optional type filter.
GET /api/memory/graph/search E3: Entity search delegating to graph.search_entities().
GET /api/memory/graph/stats E1: Graph stats — entity/relationship type counts.
GET /api/memory/layers Get detailed layer information
GET /api/memory/metrics Memory metrics — Platform-native (Z7 / 2026-04-26).
GET /api/memory/procedural Get procedural memory patterns and tool stats
GET /api/memory/procedural/context Get procedural patterns relevant to a context query
GET /api/memory/real-stats Get detailed statistics from real 4-layer memory system
GET /api/memory/retention Retention policy — Platform-managed (Z7 / 2026-04-26).
GET /api/memory/session/<session_id> Get session-specific memory information
GET /api/memory/sessions Get all sessions from real memory system
GET /api/memory/status Get current memory system status
GET /api/memory/stream Stream real-time memory updates via SSE
memory_management 18
POST /api/memory/manage/cleanup No-op stub: cleanup is now Platform-native (TTL sweeper + checkpoint pruner).
GET /api/memory/manage/config Get current memory configuration.
GET /api/memory/manage/facts/<session_id> Get extracted key facts for a session.
GET /api/memory/manage/facts/global List global facts via PostgresStore (Z4 / 2026-04-26).
POST /api/memory/manage/facts/global Add a fact to global memory via PostgresStore (Z4 / 2026-04-26).
POST /api/memory/manage/facts/global/clear Clear all global facts.
GET /api/memory/manage/graph-memory/status Get graph memory / extraction status for info bar.
GET /api/memory/manage/health Get memory system health status.
GET /api/memory/manage/pipeline/health Get memory pipeline enhancement status (2.2-2.8).
GET /api/memory/manage/session/<session_id> Get detailed information about a specific session.
DELETE /api/memory/manage/session/<session_id> Delete a session completely.
POST /api/memory/manage/session/<session_id>/clear Clear a session's memory.
GET /api/memory/manage/session/<session_id>/messages Get messages from a session.
POST /api/memory/manage/session/<session_id>/rename Rename a session.
GET /api/memory/manage/sessions List sessions via Platform Threads API (Z4 / 2026-04-26).
GET /api/memory/manage/status Get comprehensive status of all memory subsystems.
POST /api/memory/manage/vector/search Semantic search across vector memories.
GET /api/memory/manage/vector/status Get vector memory status.
modelops 5
GET /api/modelops/discover Full discovery: projects + categorized deployed models.
GET /api/modelops/projects List ModelOps projects the JWT user has access to.
GET /api/modelops/projects/<project_id>/deployments List all active deployments in a project.
GET /api/modelops/projects/<project_id>/trained-models List trained models in a project (pagination handled inside the service).
POST /api/modelops/test-connection Health-check a ModelOps / NIM endpoint.
nim_models 18
POST /api/nim/ai/optimize-allocation POST /api/nim/ai/optimize-allocation - AI-powered GPU allocation optimization
POST /api/nim/ai/predict-scaling POST /api/nim/ai/predict-scaling - AI-powered scaling prediction
POST /api/nim/ai/recommend-model POST /api/nim/ai/recommend-model - AI-powered model recommendation
GET POST /api/nim/discover Discover and refresh NIM models from ModelOps API.
GET /api/nim/gpu-status Get GPU allocation status from ModelOps deployments.
GET /api/nim/llm-config Get current NIM LLM configuration
GET /api/nim/llm-models Get discovered NIM completion models for LLM provider selection.
POST /api/nim/llm-models/select Select a NIM model for chat completion.
POST /api/nim/llm-models/test Test connection to a NIM completion model.
GET /api/nim/model/<model_id>/config Get client configuration (endpoint/model name) for a deployed model
POST /api/nim/model/<model_id>/deploy Deploy a NIM model
GET /api/nim/model/<model_id>/details Get detailed information about a NIM model including metadata
POST /api/nim/model/<model_id>/retire Retire a deployed NIM model
GET /api/nim/models List all NIM models from ModelOps - NO HARDCODED MODELS.
GET /api/nim/projects List all ModelOps projects
GET /api/nim/test-connection Test connection to Teradata Database and ModelOps API - Two step test
POST /api/nim/test-endpoint Test a specific NIM endpoint for connectivity and model availability
POST /api/nim/validate Validate a NIM model endpoint
nim 4
GET /api/nim/config Get NIM configuration (without sensitive data).
GET /api/nim/models Get available NIM models.
GET /api/nim/status Get NIM service status.
POST /api/nim/test Test NIM connection with a simple completion.
nim_feature 15
GET /api/nim/deployments List all model deployments
GET /api/nim/feature-sets List all feature sets
POST /api/nim/feature-sets Create a new feature set
POST /api/nim/feature-sets/<fset_id>/retrieve Retrieve feature values for a feature set
GET /api/nim/features List all features in the feature store
POST /api/nim/features Create a new feature in the feature store
GET /api/nim/features/<feature_id> Get specific feature details
GET /api/nim/features/<feature_id>/values Get feature values (simulated)
GET /api/nim/grid/data Get data for cyber grid visualization
GET /api/nim/models List all NVIDIA NIM models, split by type for frontend compatibility
GET /api/nim/models/<model_id> Get specific model details
POST /api/nim/models/<model_id>/deploy Deploy a model to NVIDIA NIM
POST /api/nim/models/<model_id>/inference Run inference on a deployed model
GET /api/nim/models/<model_id>/metrics Get real-time model metrics
GET /api/nim/performance/summary Get overall performance summary
ocr 11
POST /api/ocr/ai/classify Document classification. Reuses ai_classify_document helper.
POST /api/ocr/ai/extract-fields Structured field extraction. Reuses ai_extract_fields helper.
POST /api/ocr/ai/summarize Brief or detailed text summarization via the central LLM provider.
POST /api/ocr/batch/<bid>/process
GET /api/ocr/batch/<bid>/results
GET /api/ocr/batch/<bid>/status
POST /api/ocr/batch/upload
POST /api/ocr/format LLM-based OCR error correction. Reuses ai_correct_ocr_errors helper.
POST /api/ocr/process-direct Forward an already-uploaded file path to the configured OCR engine.
GET /api/ocr/services Return available OCR services with availability status.
POST /api/ocr/upload Save the uploaded file to a temp slot and return the path.
performance_metrics 11
GET /api/performance/alerts Get performance alerts
POST /api/performance/alerts/<alert_id>/acknowledge Acknowledge an alert
GET /api/performance/export Export metrics data
GET /api/performance/forecast Get performance forecast
GET /api/performance/health Get overall system health status
GET /api/performance/hologram/data Get data for holographic visualization
GET /api/performance/metrics/current Get current performance metrics
GET /api/performance/metrics/historical Get historical performance metrics
GET /api/performance/metrics/prometheus Export metrics in Prometheus format for scraping
GET /api/performance/metrics/stream Stream live performance metrics via SSE
GET /api/performance/optimization/suggestions Get optimization suggestions
platform_runs 4
GET /api/platform/agents/<name>/metrics
GET /api/platform/agents/<name>/runs
GET /api/platform/link/agent/<name>
GET /api/platform/link/thread/<thread_id>
preferences 5
GET /api/preferences Get current user's preferences.
PUT /api/preferences Save/update user preferences.
DELETE /api/preferences Clear all preferences (revert to system defaults).
GET /api/preferences/api-keys Get masked API keys for display.
PUT /api/preferences/api-keys Save encrypted API keys. Send null to clear a key.
quick_actions 6
GET /api/quick-actions/command/<command_id> Get details for a specific command
POST /api/quick-actions/execute Execute a tactical command
GET /api/quick-actions/history Get command execution history
GET /api/quick-actions/mission-status Get current mission status
GET /api/quick-actions/palette Get the full command palette
POST /api/quick-actions/suggestions Get context-aware action suggestions
scratchpad 8
POST /api/scratchpad/cleanup Clean up expired entries based on TTL.
POST /api/scratchpad/clear Clear all scratchpad entries.
GET /api/scratchpad/context Get context injection data (summaries for all entries).
GET /api/scratchpad/entries List all scratchpad entries with optional filtering.
POST /api/scratchpad/entries Create a new scratchpad entry.
GET /api/scratchpad/entries/<entry_id> Get a specific scratchpad entry with full content.
DELETE /api/scratchpad/entries/<entry_id> Delete a scratchpad entry.
GET /api/scratchpad/stats Get scratchpad statistics.
security_hardening 14
GET /api/security/api-keys List user's API keys
POST /api/security/api-keys Create new API key
DELETE /api/security/api-keys/<key_id> Revoke API key
GET /api/security/audit/events Get security event types
GET /api/security/audit/logs Get audit logs
POST /api/security/auth/login User login
POST /api/security/auth/logout User logout
POST /api/security/auth/register Register new user
GET /api/security/auth/verify Verify authentication status
GET /api/security/config Get security configuration
PUT /api/security/config Update security configuration
GET /api/security/quantum-shield/data Get quantum shield visualization data
GET /api/security/users List all users (admin only)
PUT /api/security/users/<user_id>/role Update user role (admin only)
settings 83
GET /api/settings/ Get all application settings from .env file
GET /api/settings/advanced Get advanced settings
PUT /api/settings/advanced Update advanced settings including orchestration layer override
GET /api/settings/context_enrichment Get context enrichment settings
PUT /api/settings/context_enrichment Update context enrichment settings
GET /api/settings/cost Get cost management and budget settings
POST /api/settings/cost Save cost management settings
POST /api/settings/cost/reset-month Reset monthly cost tracking counters
GET /api/settings/display Return display filter configuration for frontend rendering.
GET /api/settings/env-values Get current configuration values from Config class.
GET /api/settings/export Export all settings for backup
GET /api/settings/extended-thinking Get extended thinking (chain-of-thought) settings
POST PUT /api/settings/extended-thinking Save extended thinking settings
GET /api/settings/general Get general application settings
PUT /api/settings/general Update general application settings
GET /api/settings/health Check consistency between .env, JSON, and Config runtime.
POST /api/settings/import Import settings from backup
GET POST /api/settings/layer Get or set orchestration layer override.
GET /api/settings/llm Get LLM provider settings
PUT /api/settings/llm Update LLM provider settings
GET /api/settings/memory Get context memory settings — inject runtime Config values for UI field names
PUT /api/settings/memory Update context memory settings
GET /api/settings/modelops Return the 3 ModelOps config fields plus JWT token presence.
PUT /api/settings/modelops Save ModelOps settings to .env via the same path as /save-to-env.
GET /api/settings/models Get model capabilities registry with execution profiles.
PUT /api/settings/models Update per-model capability overrides.
GET /api/settings/monitoring Get monitoring and observability settings
POST /api/settings/monitoring Save monitoring settings
POST /api/settings/monitoring/deploy-prometheus Deploy Prometheus monitoring stack via Docker
GET /api/settings/multi-agent Get multi-agent layer configuration.
POST /api/settings/multi-agent Save multi-agent layer configuration.
GET /api/settings/multi-agent/export Export multi-agent configuration as YAML
POST /api/settings/multi-agent/import Import multi-agent configuration from YAML or JSON
GET /api/settings/nim-defaults Get NIM default model selections
POST /api/settings/nim-defaults Save NIM default model selections
GET /api/settings/performance Get performance and connection pool settings
POST PUT /api/settings/performance Save performance settings
POST /api/settings/performance/test Test performance configuration validity
GET /api/settings/platforms Get platform connection settings (Redis, Postgres, Teradata, etc.).
POST PUT /api/settings/platforms Save platform connection settings
POST /api/settings/platforms/chroma-collections List ChromaDB collections using the Python client (preferred) or REST API.
GET /api/settings/platforms/docker-logs View Docker logs - redirects to docker_blueprint
POST /api/settings/platforms/docker-start Start Docker services - redirects to docker_blueprint
GET /api/settings/platforms/docker-status Check Docker status - redirects to docker_blueprint
POST /api/settings/platforms/docker-stop Stop Docker services - redirects to docker_blueprint
GET /api/settings/platforms/export Export platform configuration
POST /api/settings/platforms/import Import platform configuration
POST /api/settings/platforms/init-checkpoint-tables Initialize LangGraph checkpoint tables in PostgreSQL
POST /api/settings/platforms/ollama-models List available Ollama models
POST /api/settings/platforms/test-chroma Test ChromaDB connection using Python client with heartbeat.
POST /api/settings/platforms/test-grafana Test Grafana connection
POST /api/settings/platforms/test-ollama Test Ollama connection
POST /api/settings/platforms/test-postgres Test PostgreSQL connection
POST /api/settings/platforms/test-prometheus Test Prometheus connection
POST /api/settings/platforms/test-redis Test Redis connection
GET /api/settings/prompts Get all saved prompts
POST /api/settings/prompts Save prompts
GET /api/settings/prompts/export Export all prompts
POST /api/settings/prompts/import Import prompts
GET /api/settings/rag Get RAG (Retrieval Augmented Generation) settings
POST /api/settings/rag Save RAG settings
POST /api/settings/rag/test Test RAG query with current settings
POST /api/settings/reload-env Reload all configuration from .env file into runtime Config.
POST /api/settings/reset Reset all settings to defaults
POST /api/settings/reset/<category> Reset settings to defaults for a specific category
POST /api/settings/save-to-env Save settings to .env file and update runtime Config.
GET /api/settings/security Get security configuration
POST PUT /api/settings/security Save security configuration
POST /api/settings/security/audit Run security audit on current configuration
GET /api/settings/skills Get skills-related settings
PUT /api/settings/skills Update skills-related settings
GET /api/settings/smart_viz Get smart visualization settings
PUT /api/settings/smart_viz Update smart visualization settings
POST /api/settings/sync Force synchronization from .env to JSON and Config runtime.
POST /api/settings/system-prompts/<agent> Save system prompt for a specific agent
GET /api/settings/teradata Get Teradata connection settings — inject runtime Config values for UI field names
PUT /api/settings/teradata Update Teradata connection settings
POST /api/settings/test-connection Test connection for various services
GET /api/settings/ui Get UI preference settings
POST /api/settings/ui Save UI preference settings
POST /api/settings/update Update a single Config value by key.
GET /api/settings/vectorstore Get vector store settings
PUT /api/settings/vectorstore Update vector store settings
skills 23
GET /api/skills/ List all skills (SKILL.md catalog, post-v4 migration).
GET /api/skills/<skill_type>/<category>/<name> Return a single SKILL.md bundle as {frontmatter, body_markdown, structured_blocks}.
POST /api/skills/<skill_type>/<category>/<name> Create or update a skill as a SKILL.md bundle.
DELETE /api/skills/<skill_type>/<category>/<name> Delete a SKILL.md directory.
GET /api/skills/<skill_type>/<category>/<name>/export Phase 3.11 — download the full skill directory as a .zip.
GET /api/skills/<skill_type>/<category>/<name>/references Return the agents currently binding this skill by name.
GET /api/skills/<skill_type>/<category>/<name>/revisions Return the revision history of a SKILL.md, newest first.
GET /api/skills/<skill_type>/<category>/<name>/revisions/<int:revision_id> Return a single revision's full frontmatter + body_markdown.
GET /api/skills/<skill_type>/<category>/<topic>/wizard-payload Convert a skill file to wizard-compatible format.
GET /api/skills/categories List available categories with counts.
POST /api/skills/chat Sync chat — returns full response.
POST /api/skills/chat/reset Reset conversation state for a session.
POST /api/skills/chat/stream SSE streaming chat with Skills Factory agent.
GET /api/skills/chat/working-skill Get current working skill drafts for live preview.
POST /api/skills/describe/stream Phase 2.5 (skill side) — conversational skill draft.
POST /api/skills/impact Preview which agents would be regenerated by saving/deleting a skill.
POST /api/skills/import Phase 3.11 — upload a .zip bundle; writes SKILL.md + adjunct dirs
POST /api/skills/improve/stream AI "improve this skill" — given the current SKILL.md + a user goal,
POST /api/skills/lint Health check: detect stale, contradictory, or low-coverage skills.
POST /api/skills/parse Parse + validate a skill YAML text payload and return a normalised dict.
GET /api/skills/routing Get the full skills routing config.
GET /api/skills/routing/<agent_name> Get skill categories for a specific agent.
GET /api/skills/status Summary stats.
supervisor 10
GET /api/supervisor/config Get current supervisor configuration
POST /api/supervisor/config Update supervisor configuration
POST /api/supervisor/memory/clear Clear all vector memory
GET /api/supervisor/memory/stats Get vector memory statistics
POST /api/supervisor/rebuild Rebuild supervisor with current settings
POST /api/supervisor/reset-l1 Reset L1 supervisor in chat_handler to force re-initialization.
POST /api/supervisor/stats/reset Reset all routing statistics
GET /api/supervisor/status Get comprehensive orchestrator status
POST /api/supervisor/tools/reindex Reindex all tools in semantic selector
POST /api/supervisor/tools/test-selection Test semantic tool selection with a query
bisync 21
POST /api/sync/agents/<name>/pull
POST /api/sync/agents/<name>/push
GET /api/sync/diff/<entity_type>/<entity_id> Return both app + cloud versions of an entity + diff summary.
POST /api/sync/fleet/deploy-now Manually trigger a new Fleet revision from the current filesystem state.
GET /api/sync/fleet/revisions Return recent revisions with build/deploy status for the Fleet panel.
GET /api/sync/fleet/status Return Fleet deployment health + latest revision + api_url + ui_url.
POST /api/sync/langflow/agents/<agent_name>/pull Pull a single Flask agent from Langflow using its lineage.platform_flow_id.
POST /api/sync/langflow/agents/<agent_name>/push Push a single Flask agent into Langflow as a flow (create-or-update).
POST /api/sync/langflow/pull Force an immediate pull of agent-tagged Langflow flows → AIFactory
POST /api/sync/resolve Resolve a conflict by picking a winner.
POST /api/sync/retry/<entity_type>/<entity_id> Reset an entity's retry state (lifts it out of dead-letter).
GET /api/sync/scheduler/status
POST /api/sync/skills/<path:skill>/push
GET /api/sync/status
GET /api/sync/status/<entity_type>
POST /api/sync/tick
GET /api/sync/webhook-info Return the exact URL + secret fingerprint to register on LangSmith.
POST /api/sync/webhooks/langflow Receive flow change events from Langflow.
POST /api/sync/webhooks/langsmith
DELETE /api/sync/workflows/<workflow_id>
POST /api/sync/workflows/<workflow_id>/push
tdvs 16
POST /api/tdvs/ai/enhance-question POST /api/tdvs/ai/enhance-question - AI-powered question enhancement
POST /api/tdvs/ai/rerank POST /api/tdvs/ai/rerank - AI-powered search result reranking
POST /api/tdvs/ai/suggest-followup POST /api/tdvs/ai/suggest-followup - AI-powered follow-up question suggestions
POST /api/tdvs/ask Ask a question using RAG via MCP - manual LLM integration
POST /api/tdvs/chat Chat with documents using RAG - uses app's LLM settings with conversation history
POST /api/tdvs/create Create vector store via MCP with full parameters
DELETE /api/tdvs/delete/<vs_name> Delete vector store via MCP
GET /api/tdvs/details/<vs_name> Get vector store details via MCP
POST /api/tdvs/grant Grant user permission on vector store via MCP
GET /api/tdvs/health Check TDVS service health via MCP
GET /api/tdvs/list List all vector stores via MCP - optionally filter by database (cached for 30s)
GET /api/tdvs/models Get available embedding models
POST /api/tdvs/revoke Revoke user permission on vector store via MCP
POST /api/tdvs/search Perform similarity search via MCP
POST /api/tdvs/update Update vector store via MCP
POST /api/tdvs/upload Upload document file(s) for vector store creation
teams_link 3
POST /api/teams/link/claim Claim an existing AIFactory account for the current Teams session.
GET /api/teams/link/status Report whether the current session is linked to an AIFactory user.
POST /api/teams/link/unlink Remove the link between the current Teams session and its AIFactory user.
teams_bot 2
POST /api/teams/messages Bot Framework webhook — receives all bot activities from Teams.
GET /api/teams/token-check Diagnostic endpoint — acquire a Bot Connector token and inspect its JWT claims.
teams_notify 1
POST /api/teams/notify Proactively push a message or Adaptive Card to a Teams user.
vectorstore 13
GET /api/vectorstore/config Get Vector Store configuration.
POST /api/vectorstore/create Create a new Vector Store (async job).
POST /api/vectorstore/delete Delete a Vector Store.
POST /api/vectorstore/grant-permission Grant permission to a user on a vector store.
POST /api/vectorstore/info Get Vector Store info.
GET /api/vectorstore/job/<job_id> Get status of a Vector Store creation job.
POST /api/vectorstore/job/<job_id>/cancel Cancel a Vector Store creation job.
GET /api/vectorstore/jobs List all Vector Store jobs.
POST /api/vectorstore/jobs/clear Clear completed and failed jobs.
POST /api/vectorstore/list List all Vector Stores.
GET /api/vectorstore/permissions Get permissions for a specific vector store.
POST /api/vectorstore/revoke-permission Revoke permission from a user on a vector store.
POST /api/vectorstore/test Test Vector Store connection.
visualization 14
POST /api/visualization/analyze Analyze data and return chart recommendations.
GET /api/visualization/charts Get all charts across all sessions.
GET /api/visualization/charts/<session_id> Get all charts for a specific session.
GET /api/visualization/charts/<session_id>/<chart_id> Get a specific chart by ID.
DELETE /api/visualization/charts/<session_id>/<chart_id> Delete a specific chart.
DELETE /api/visualization/clear/<session_id> Clear all charts for a session.
GET /api/visualization/config Get ECharts configuration including Teradata theme colors.
POST /api/visualization/dashboard Create multi-chart dashboard from multiple data sources.
GET /api/visualization/format-config Get LLM configuration for data formatting.
POST /api/visualization/format-llm LLM-powered data formatting for charts.
GET /api/visualization/health Health check for visualization service.
POST /api/visualization/parse-mcp-result Parse MCP plot tool result into chart format.
POST /api/visualization/render Render a chart from provided data.
GET /api/visualization/types Get available chart types and their descriptions.
wizard 14
GET /api/wizard/databases List all user databases (excludes system databases).
POST /api/wizard/discover Run MCP tools to discover database metadata.
GET /api/wizard/display-rules/<category>/<topic> Return display_rules block from a documentation skill YAML file.
PUT /api/wizard/display-rules/<category>/<topic> Update display_rules block in a documentation skill YAML file.
POST /api/wizard/enhance-metadata Use LLM to generate semantic descriptions for tables and columns.
POST /api/wizard/generate-display-instructions Use LLM to suggest display instructions based on agent skills/description.
POST /api/wizard/generate-skill-pack Generate the full 3-skill pack for a database in ONE LLM call.
POST /api/wizard/parse-prompt Extract structured skills from a free-form agent system prompt.
POST /api/wizard/preview-prompt Generate a preview of the system prompt from wizard state without saving.
POST /api/wizard/recommend-skills Generate LLM-powered skill recommendations from discovery payload.
GET /api/wizard/templates List available agent templates.
GET /api/wizard/templates/<template_id> Get full template configuration.
POST /api/wizard/templates/<template_id>/instantiate Create an agent from a template with variable substitution.
POST /api/wizard/validate-skill Validate a single skill against discovery metadata.
workflows 15
GET /api/workflows List all available workflows. Supports ?limit=N&offset=M pagination.
POST /api/workflows Create a new workflow + register it as a Platform assistant.
GET /api/workflows/<workflow_id> Get a specific workflow by ID.
PUT /api/workflows/<workflow_id> Update an existing workflow + refresh its Platform assistant.
DELETE /api/workflows/<workflow_id> Delete a workflow + its Platform assistants.
POST /api/workflows/execute Execute a workflow synchronously (JSON response).
POST /api/workflows/execute/stream SSE streaming execution — same event taxonomy `useWorkflowStream.ts` expects.
GET /api/workflows/executions List workflow execution history (from PostgreSQL).
GET /api/workflows/executions/<execution_id> Get a specific workflow execution detail.
POST /api/workflows/match Find matching workflow for a query without executing.
POST /api/workflows/reload Reload workflow configurations from disk.
GET /api/workflows/status Get workflow system status.
GET /api/workflows/templates List available workflow templates.
POST /api/workflows/templates/<template_id>/instantiate Create a new workflow from a template.
POST /api/workflows/validate Validate a workflow definition (cycles, reachability).
help_bp 1
GET /help Render the help & documentation page.
langflow_proxy 4
DELETE GET PATCH POST PUT /langflow
DELETE GET PATCH POST PUT /langflow/
DELETE GET PATCH POST PUT /langflow/<path:path>
GET /langflow/__health__ Cheap health probe for the admin SyncStatusPanel.
login_bp 6
GET /login Render the landing page (login form + service links).
POST /login Handle login form submission.
GET /login/demo/<username> Quick-login for demo tenants.
GET /login/guest Continue as anonymous guest.
GET /logout Clear session and redirect to React UI or legacy login.
GET /ocr Render the standalone OCR processing page.
monitoring 2
GET /monitoring/ Redirect to default dashboard (only `agent-token-usage` remains after
GET /monitoring/dashboard/<dashboard_uid> Render monitoring page for specific dashboard.
teams_tab 5
GET /static/<path:filename> The view function used to serve files from
GET /teams/tab Main Teams tab page — auto-login and render AIFactory UI.
GET /teams/tab/artifact/<artifact_id> Direct artifact view for Task Module popups (Step 2 bot integration).
POST /teams/tab/auth Exchange a Teams SSO token for an AIFactory session.
GET /teams/tab/config Tab configuration page (called by Teams when user first adds the tab).
No endpoints match your search.