deerflow2/backend/packages/harness/deerflow
IECspace f394c0d8c8
feat(mcp): support custom tool interceptors via extensions_config.json (#2451)
* feat(mcp): support custom tool interceptors via extensions_config.json

Add a generic extension point for registering custom MCP tool
interceptors through `extensions_config.json`. This allows downstream
projects to inject per-request header manipulation, auth context
propagation, or other cross-cutting concerns without modifying
DeerFlow source code.

Interceptors are declared as Python callable paths in a new
`mcpInterceptors` array field and loaded via the existing
`resolve_variable` reflection mechanism:

```json
{
  "mcpInterceptors": [
    "my_package.mcp.auth:build_auth_interceptor"
  ]
}
```

Each entry must resolve to a no-arg builder function that returns an
async interceptor compatible with `MultiServerMCPClient`'s
`tool_interceptors` interface.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test(mcp): add unit tests for custom tool interceptors

Cover all branches of the mcpInterceptors loading logic:

- valid interceptor loaded and appended to tool_interceptors
- multiple interceptors loaded in declaration order
- builder returning None is skipped
- resolve_variable ImportError logged and skipped
- builder raising exception logged and skipped
- absent mcpInterceptors field is safe (no-op)
- custom interceptors coexist with OAuth interceptor

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* fix(mcp): validate mcpInterceptors type and fix lint warnings

Address review feedback:

1. Validate mcpInterceptors config value before iterating:
   - Accept a single string and normalize to [string]
   - Ignore None silently
   - Log warning and skip for non-list/non-string types

2. Fix ruff F841 lint errors in tests:
   - Rename _make_mock_env to _make_patches, embed mock_client
   - Remove unused `as mock_cls` bindings where not needed
   - Extract _get_interceptors() helper to reduce repetition

3. Add two new test cases for type validation:
   - test_mcp_interceptors_single_string_is_normalized
   - test_mcp_interceptors_invalid_type_logs_warning

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(mcp): validate interceptor return type and fix import mock path

Address review feedback:

1. Validate builder return type with callable() check:
   - callable interceptor → append to tool_interceptors
   - None → silently skip (builder opted out)
   - non-callable → log warning with type name and skip

2. Fix test mock path: resolve_variable is a top-level import in
   tools.py, so mock deerflow.mcp.tools.resolve_variable instead of
   deerflow.reflection.resolve_variable to correctly intercept calls.

3. Add test_custom_interceptor_non_callable_return_logs_warning to
   cover the new non-callable validation branch.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(mcp): add mcpInterceptors example and documentation

- Add mcpInterceptors field to extensions_config.example.json
- Add "Custom Tool Interceptors" section to MCP_SERVER.md with
  configuration format, example interceptor code, and edge case
  behavior notes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: IECspace <IECspace@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-04-25 09:18:13 +08:00
..
agents fix: read lead agent options from context (#2515) 2026-04-24 22:46:51 +08:00
community fix(jina): log transient failures at WARNING without traceback (#2484) (#2485) 2026-04-24 16:00:14 +08:00
config fix(middleware): avoid rescuing non-skill tool outputs during summarization (#2458) 2026-04-24 21:19:46 +08:00
guardrails feat(guardrails): add pre-tool-call authorization middleware with pluggable providers (#1240) 2026-03-23 18:07:33 +08:00
mcp feat(mcp): support custom tool interceptors via extensions_config.json (#2451) 2026-04-25 09:18:13 +08:00
models feat(models): Provider for MindIE model engine (#2483) 2026-04-25 08:59:03 +08:00
reflection refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) 2026-03-14 22:55:52 +08:00
runtime feat: implement full checkpoint rollback on user cancellation (#1867) 2026-04-09 17:56:36 +08:00
sandbox fix: use subprocess instead of os.system in local_backend.py (#2494) 2026-04-25 08:59:31 +08:00
skills feat(trace):Add run_name to the trace info for system agents. (#2492) 2026-04-24 17:06:55 +08:00
subagents feat(subagents): support per-subagent skill loading and custom subagent types (#2253) 2026-04-23 23:59:47 +08:00
tools fix: gate deferred MCP tool execution (#2513) 2026-04-24 22:45:41 +08:00
tracing feat(tracing): add optional Langfuse support (#1717) 2026-04-02 13:06:10 +08:00
uploads feat(harness): integration ACP agent tool (#1344) 2026-03-26 14:20:18 +08:00
utils [security] fix(uploads): require explicit opt-in for host-side document conversion (#2332) 2026-04-18 22:47:42 +08:00
__init__.py refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) 2026-03-14 22:55:52 +08:00
client.py feat: show token usage per assistant response (#2270) 2026-04-16 08:56:49 +08:00