github/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-09-25 22:16:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

doc(backend): Fixes the links of the backend documents (#5764)

Browse Source
This commit is contained in:
Willem Jiang 2026-09-23 15:24:13 +08:00 committed by GitHub
parent bafe7f0f40
commit c57d57ec63
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backend/docs/MEMORY_IMPROVEMENTS_SUMMARY.md
View File

@ -33,6 +33,6 @@ No `current_context` argument is currently available in `main`.
## Verification Pointers ## Verification Pointers
- Implementation: `packages/harness/deerflow/agents/memory/prompt.py` - Implementation: `packages/harness/deerflow/agents/memory/backends/deermem/deermem/core/prompt.py`
- Prompt assembly: `packages/harness/deerflow/agents/lead_agent/prompt.py` - Prompt assembly: `packages/harness/deerflow/agents/lead_agent/prompt.py`
- Regression tests: `backend/tests/test_memory_prompt_injection.py` - Regression tests: `backend/tests/test_memory_prompt_injection.py`

2
backend/docs/RUN_INTERACTION_POLICY.md
View File

@ -3,7 +3,7 @@
The harness resolves a `RunInteractionPolicy` from the run context and uses it The harness resolves a `RunInteractionPolicy` from the run context and uses it
as the single source for lead-agent tool visibility, clarification middleware as the single source for lead-agent tool visibility, clarification middleware
behavior, sandbox network approval eligibility, and system-prompt guidance. behavior, sandbox network approval eligibility, and system-prompt guidance.
The implementation lives in `deerflow/agents/interaction_policy.py`. The implementation lives in `../packages/harness/deerflow/agents/interaction_policy.py`.
## Modes and precedence ## Modes and precedence

4
backend/docs/TITLE_GENERATION_IMPLEMENTATION.md
View File

@ -42,7 +42,7 @@ title:
### 3. 文档 ### 3. 文档
#### [`docs/AUTO_TITLE_GENERATION.md`](../docs/AUTO_TITLE_GENERATION.md) (新建) #### [`docs/AUTO_TITLE_GENERATION.md`](AUTO_TITLE_GENERATION.md) (新建)
- ✅ 完整的功能说明文档 - ✅ 完整的功能说明文档
- ✅ 实现方式和架构设计 - ✅ 实现方式和架构设计
- ✅ 配置说明 - ✅ 配置说明
@ -220,7 +220,7 @@ pytest
## 📚 相关资源 ## 📚 相关资源
- [完整文档](../docs/AUTO_TITLE_GENERATION.md) - [完整文档](AUTO_TITLE_GENERATION.md)
- [LangGraph Middleware](https://langchain-ai.github.io/langgraph/concepts/middleware/) - [LangGraph Middleware](https://langchain-ai.github.io/langgraph/concepts/middleware/)
- [LangGraph State 管理](https://langchain-ai.github.io/langgraph/concepts/low_level/#state) - [LangGraph State 管理](https://langchain-ai.github.io/langgraph/concepts/low_level/#state)
- [LangGraph Checkpointer](https://langchain-ai.github.io/langgraph/concepts/persistence/) - [LangGraph Checkpointer](https://langchain-ai.github.io/langgraph/concepts/persistence/)

4
backend/docs/checkpoint-retention-contract.md
View File

@ -94,7 +94,7 @@ resume, (c) branch from an older visible turn, and (d) orphan row counts.
`parent_config` converts a cleanup into a thread-level outage (branch and `parent_config` converts a cleanup into a thread-level outage (branch and
regenerate fail loudly for every later turn). regenerate fail loudly for every later turn).
- Measurement first: proposals must include before/after numbers from - Measurement first: proposals must include before/after numbers from
`scripts/benchmark/checkpoint/bench_channels.py` (per-thread rows/bytes, `../scripts/benchmark/checkpoint/bench_channels.py` (per-thread rows/bytes,
SQLite and Postgres) plus the contract test suite passing. SQLite and Postgres) plus the contract test suite passing.
## History fast-path interaction (wiring requirement) ## History fast-path interaction (wiring requirement)
@ -138,7 +138,7 @@ alist path without re-implementing the writer's merge semantics.
reach state (preview + file reference under `.tool-results/`), so the reach state (preview + file reference under `.tool-results/`), so the
"50 KB result re-snapshotted every step" scenario from the original report "50 KB result re-snapshotted every step" scenario from the original report
depends on which tools/paths bypass it. The probe depends on which tools/paths bypass it. The probe
(`scripts/benchmark/checkpoint/bench_tool_result_probe.py`) measures the (`../scripts/benchmark/checkpoint/bench_tool_result_probe.py`) measures the
on-disk checkpoint delta for the wrapped vs unwrapped paths on the lead on-disk checkpoint delta for the wrapped vs unwrapped paths on the lead
graph; subagent chains instantiate the same middleware by default. Any PR graph; subagent chains instantiate the same middleware by default. Any PR
claiming a residual gap must name the concrete bypassing path and show its claiming a residual gap must name the concrete bypassing path and show its

2
backend/docs/plan_mode_usage.md
View File

@ -194,7 +194,7 @@ DeerFlow uses custom `system_prompt` and `tool_description` for the TodoListMidd
- Comprehensive best practices section - Comprehensive best practices section
- Task completion requirements to prevent premature marking - Task completion requirements to prevent premature marking
The custom prompts are defined in `_create_todo_list_middleware()` in `/Users/hetao/workspace/deer-flow/backend/packages/harness/deerflow/agents/lead_agent/agent.py:57`. The custom prompts are defined in `_create_todo_list_middleware()` in `../packages/harness/deerflow/agents/lead_agent/agent.py:57`.
## Notes ## Notes