mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-10 00:18:36 +00:00
ebc09ce130
* feat(mcp): auto-promote deferred MCP tools from routing hints
When tool_search.enabled=true defers MCP tool schemas, PR1 routing hints
still require the model to spend a tool_search discovery round trip before
it can call the tool the routing metadata already points at. This adds a
McpRoutingMiddleware that matches the latest user message against PR1
routing keywords and promotes the matching deferred schemas before the
model call, removing that round trip.
Design (soft routing, opt-in, additive):
- Matches only the latest real HumanMessage (shared is_real_user_message
helper, reused by SkillActivationMiddleware so the two cannot drift);
case-insensitive substring match, no tokenizer dependency.
- Ordering: priority desc, then tool name asc; capped by the new global
tool_search.auto_promote_top_k (default 3, clamped 1..5). Does not add or
consume a per-tool auto_promote_top_k (PR1 schema unchanged); a per-tool
value is ignored with a DEBUG note.
- Returns a plain {"promoted": ...} state update (not a Command) and relies
on ThreadState.merge_promoted for union/dedupe, so auto-promote and a
model-triggered tool_search converge on the same catalog hash.
- Installed before DeferredToolFilterMiddleware on every deferred-tool path
(lead agent, subagent, embedded client, webhook via shared builders);
a construction-time assert rejects the reversed order. catalog_hash is
None / no routing index is a complete no-op, so bootstrap and ACP skip it.
- Privacy: never executes tools, never promotes policy-filtered tools, adds
no routing keywords or matched tool names to trace metadata or INFO/WARN
logs.
No behavior change when tool_search.enabled=false.
Tests: index construction, matching semantics, middleware state updates,
same-cycle deferred-filter interaction, lead/subagent/embedded-client
builder wiring + order invariant, config clamping, config.example.yaml
parseability, and privacy assertions.
* refactor(mcp): address auto-promote review nits
- executor: access app_config.tool_search.auto_promote_top_k directly to match
the lead-agent and embedded-client paths (drop the over-defensive getattr that
masked missing config); update the subagent test mock to carry tool_search.
- tool_search / mcp_routing_middleware: cross-reference the duplicated routing
priority/keyword normalization between the builder and the middleware's
defensive _normalize_index so they cannot silently drift.
- MCP_SERVER.md: document that auto-promote keyword matching is a case-insensitive
substring test (not word-boundary), advising distinctive keywords.
|
||
|---|---|---|
| .. | ||
| API.md | ||
| APPLE_CONTAINER.md | ||
| ARCHITECTURE.md | ||
| AUTH_DESIGN.md | ||
| AUTH_TEST_DOCKER_GAP.md | ||
| AUTH_TEST_PLAN.md | ||
| AUTH_UPGRADE.md | ||
| AUTO_TITLE_GENERATION.md | ||
| BLOCKING_IO_DETECTION.md | ||
| CONFIGURATION.md | ||
| FILE_UPLOAD.md | ||
| GUARDRAILS.md | ||
| IM_CHANNEL_CONNECTIONS.md | ||
| MCP_SERVER.md | ||
| memory-settings-sample.json | ||
| MEMORY_IMPROVEMENTS.md | ||
| MEMORY_IMPROVEMENTS_SUMMARY.md | ||
| MEMORY_SETTINGS_REVIEW.md | ||
| middleware-execution-flow.md | ||
| PATH_EXAMPLES.md | ||
| plan_mode_usage.md | ||
| README.md | ||
| REPLAY_E2E.md | ||
| rfc-create-deerflow-agent.md | ||
| rfc-extract-shared-modules.md | ||
| rfc-grep-glob-tools.md | ||
| SANDBOX_MEMORY_PROFILING.md | ||
| SETUP.md | ||
| SSO.md | ||
| STREAMING.md | ||
| summarization.md | ||
| task_tool_improvements.md | ||
| TITLE_GENERATION_IMPLEMENTATION.md | ||
| TODO.md | ||
| TUI.md | ||
Documentation
This directory contains detailed documentation for the DeerFlow backend.
Quick Links
| Document | Description |
|---|---|
| ARCHITECTURE.md | System architecture overview |
| API.md | Complete API reference |
| AUTH_DESIGN.md | User authentication, CSRF, and per-user isolation design |
| CONFIGURATION.md | Configuration options |
| SETUP.md | Quick setup guide |
Feature Documentation
| Document | Description |
|---|---|
| STREAMING.md | Token-level streaming design: Gateway vs DeerFlowClient paths, stream_mode semantics, per-id dedup |
| FILE_UPLOAD.md | File upload functionality |
| PATH_EXAMPLES.md | Path types and usage examples |
| SANDBOX_MEMORY_PROFILING.md | Sandbox memory baseline and runtime comparison guide |
| summarization.md | Context summarization feature |
| plan_mode_usage.md | Plan mode with TodoList |
| AUTO_TITLE_GENERATION.md | Automatic title generation |
Development
| Document | Description |
|---|---|
| TODO.md | Planned features and known issues |
Getting Started
- New to DeerFlow? Start with SETUP.md for quick installation
- Configuring the system? See CONFIGURATION.md
- Understanding the architecture? Read ARCHITECTURE.md
- Building integrations? Check API.md for API reference
Document Organization
docs/
├── README.md # This file
├── ARCHITECTURE.md # System architecture
├── API.md # API reference
├── AUTH_DESIGN.md # User authentication and isolation design
├── CONFIGURATION.md # Configuration guide
├── SETUP.md # Setup instructions
├── FILE_UPLOAD.md # File upload feature
├── PATH_EXAMPLES.md # Path usage examples
├── summarization.md # Summarization feature
├── plan_mode_usage.md # Plan mode feature
├── STREAMING.md # Token-level streaming design
├── AUTO_TITLE_GENERATION.md # Title generation
├── TITLE_GENERATION_IMPLEMENTATION.md # Title implementation details
└── TODO.md # Roadmap and issues