mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-16 01:28:38 +00:00
7 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
lllyfff
|
99c926b7bb
|
fix(mcp): bring-up has no timeout and externalized tool outputs are counted as undelivered artifacts (#4657)
* fix: bound MCP server bring-up timeouts and exclude externalized tool outputs from delivery verification Two related robustness fixes: 1. MCP server bring-up was unbounded. tool_call_timeout only covered session.call_tool(); tool discovery (subprocess spawn + initialize + tools/list) and persistent stdio session initialization could hang forever, blocking agent construction (and on the Gateway event loop, the whole process). Add a per-server session_init_timeout (default DEFAULT_MCP_SESSION_INIT_TIMEOUT = 60s, null disables) that bounds both discovery and pooled-session initialization. The session pool's existing cancellation handling tears down a session stuck mid-creation in its own task. 2. ToolOutputBudgetMiddleware externalizes oversized tool outputs into outputs/.tool-results/ (configurable tool_output.storage_subdir). The workspace-change scanner and run delivery verification counted those files as produced artifacts, so any run that externalized a tool output without also presenting a real artifact failed with "Artifact delivery incomplete". Exclude TOOL_RESULTS_DIRNAME via a shared constant (mirroring BROWSER_FRAMES_DIRNAME) and thread the configured storage_subdir through snapshot capture so both workspace-changes events and delivery verification stay clean. * review: enforce single-segment tool_output.storage_subdir; document discovery-timeout cleanup Address review feedback: 1. A custom tool_output.storage_subdir with a path separator (e.g. cache/tool-results) silently no-oped the workspace-scanner exclusion: os.walk yields one-segment dirnames, so a nested value never matched and its files were counted as produced artifacts again. ToolOutputConfig now validates storage_subdir as a single directory name (rejects separators, .., absolute, empty) with tests, so the exclusion is always sound. 2. The discovery-timeout path now documents why cancellation is safe, mirroring the session-init note: discovery runs inside the adapter's nested async context managers, and stdio_client's finally terminates the process tree (SIGTERM->SIGKILL on POSIX, process-tree on Windows), so a timed-out npx subprocess and its children are reaped rather than accumulating. * review: log session-init timeouts and align API response model default with runtime config Address second-round review feedback: 1. A session-init timeout raised TimeoutError without any log, unlike the discovery timeout which logs a WARNING. Wrap the bounded get_session in a try/except that logs the timeout (server name + seconds) and re-raises, so operators can diagnose tool-call failures caused by hung MCP sessions. 2. McpServerConfigResponse.session_init_timeout defaulted to None while McpServerConfig defaults to 60s: a server created via PUT /api/mcp/config without the field was persisted with null (no timeout) while the same server created in the config file got 60s. Align the response-model default to DEFAULT_MCP_SESSION_INIT_TIMEOUT so API-created and file-created servers behave the same; an explicit null still opts out. * review: narrow the discovery-timeout handler to the bounded wait_for path The except TimeoutError clause covered both the bounded wait_for branch and the bare discovery branch. With session_init_timeout opted out (None), a TimeoutError raised by discovery itself would hit the %.1f format with None: logging raises TypeError internally, the WARNING is silently dropped, and a --- Logging error --- traceback goes to stderr. Narrow the handler to wrap only the wait_for call, where the branch condition guarantees the timeout value is not None. A discovery-internal TimeoutError on the opted-out path now falls through to the generic failure handler and is reported as 'tool discovery failed' with exc_info. Covered by a regression test that asserts the skip is reported without any broken format. |
||
|
Vanzeren
|
6f53fd5e99
|
feat(runtime): enforce artifact delivery from workspace snapshots (#4494) | ||
|
Andrew Chen
|
f113f10f36
|
fix(workspace-changes): count diff body lines starting with "-- "/"++ " (#4303)
`_count_diff_lines` skipped every line starting with "+++ "/"--- " to drop difflib's two file headers. But a deleted hunk-body line whose content begins with "-- " (e.g. a SQL comment `-- get users`) becomes the diff line `--- get users`, and an added `++ ...` line becomes `+++ ...`, so those were dropped too — undercounting the user-visible +N/-M change summary (WorkspaceChangeSummary, per-file WorkspaceFileChange, and the run-event string in recorder.py). `difflib.unified_diff` always emits the two headers first, so skip them by position (`lines[2:]`) instead. Hunk `@@` lines start with `@` and are still ignored. Numeric/plain diffs are unaffected. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Ryker_Feng
|
fa496c0c8d
|
feat(browser): add agentic browser control (#4187)
* feat(browser): add agentic browser control
* fix(frontend): format browser view changes
* fix(browser): keep browser optional and isolate sidecar layout
* fix(browser): address PR review security and IME findings
- Nginx: add a browser-stream WebSocket location before the generic
/api/threads regex so Live upgrades instead of downgrading to HTTP
(both nginx.conf and nginx.local.conf).
- Ownership: require an existing owned thread for the WS stream and REST
navigate, and tear down the browser session on thread deletion so a
later caller cannot reuse a retained page/cookies by guessing the id.
- SSRF: enforce the URL policy at the browser request boundary via a
context-level route guard covering redirects, popups, iframes, and
subresources (skipped for CDP-attached Chrome).
- IME: skip key forwarding while a composition is active so confirming a
CJK candidate with Enter no longer submits the remote page form.
Adds regression tests for the request guard, session teardown on delete,
and the composing-Enter key decision.
* fix(frontend): smooth streaming in long tool threads
* Revert "fix(frontend): smooth streaming in long tool threads"
This reverts commit f0462516eabe77f138d4027ea1c714fb226683cf.
* fix(browser): address review security and lifecycle findings
- Reject cross-origin WebSocket upgrades on the live browser stream
(Origin allow-list reuse of CORS/same-origin helpers) to close a
WS-CSRF hole, and fail closed when the ownership store is absent.
- Warn when a CDP-attached session runs with the SSRF request guard
off, and drop the unreachable CDP screencast teardown dead code.
- Read browser session launch config from a single canonical source
(browser_navigate) so it is deterministic regardless of call order.
- Bound per-thread Chromium accumulation with idle-timeout eviction
and an LRU max-sessions cap.
- Reset the Live reconnect counter on a successful open so the stream
can't permanently stall after the cumulative attempt cap.
* fix(frontend): reduce long tool thread render stalls
Reuse stable historical message groups during streaming, defer heavy Markdown and browser previews, and lazy-decode message images.
* fix(browser): keep live control responsive during continuous input
Why: Manual browser control felt laggy — a physical click ran the remote
Playwright click three times and each non-move input synchronously awaited a
JPEG screenshot, so events queued behind capture (queue wait up to ~237ms).
The first async attempt used a trailing-edge debounce, which froze the visible
page until a wheel/keyboard gesture stopped ("scroll finishes, then it jumps").
What:
- Frontend forwards one `click` per physical click instead of also emitting
`down`/`up`, so the remote page is not clicked twice per gesture.
- Backend detaches live-frame capture from input dispatch: non-move actions
start a rate-limited background refresh loop (leading frame + bounded cadence)
that keeps emitting frames while input continues and never blocks dispatch.
- Add regression tests: input dispatch no longer awaits the screenshot, rapid
inputs coalesce, and continuous input keeps refreshing before it stops.
Scenarios: Verified in the live Browser panel — a single click completes in
~57ms (was blocked behind a 171ms capture), and a 1.14s sustained wheel gesture
renders ~7 frames throughout the scroll instead of one frame after it ends.
* fix(browser): harden worker and session lifecycle
* fix(browser): address latest review feedback
* fix(frontend): preserve optimistic new-chat message
* test(e2e): preserve mocked message run ids
* fix(browser): address capability review feedback
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
|
||
|
Daoyuan Li
|
b565e6c0f0
|
fix(workspace-changes): classify a symlink replacing a file distinctly from deleted (#4170)
* fix(workspace-changes): classify a symlink replacing a file distinctly from deleted scan_workspace_roots() skipped every symlinked path entirely (host_file.is_symlink() -> continue), so the path was completely absent from a snapshot instead of being recorded as a metadata-only stub the way binary/large/sensitive-looking files already are. When an agent run replaces a tracked file with a symlink (e.g. rm config.txt && ln -s /some/other/path config.txt), the after-snapshot never contained that path at all, so compare_snapshots()'s _status() saw after_file=None and reported plain "deleted" -- silently hiding that the path is still alive on disk, now as a symlink that can point anywhere on the host, including outside the workspace root. Add a "symlink" classification mirroring the existing binary/large/ sensitive pattern: scan_workspace_roots() now records a symlink as a metadata-only FileSnapshot stub (symlink=True, symlink_target from os.readlink(), lstat'd without ever following the link) instead of omitting it. _status() reports "symlink_created" whenever a symlink newly occupies a path that was not already a symlink (brand new or replacing a prior file), so the security-relevant fact surfaces distinctly instead of collapsing into "deleted". A symlink genuinely removed with nothing replacing it is unchanged: still "deleted". Verified against a real POSIX symlink (WSL; native Windows symlink creation needs elevated privilege) driving the unmodified scan_workspace_roots()/compare_snapshots() functions, and via a patch-file revert/reapply cycle on this same fix to confirm the added regression tests fail before and pass after. * fix(workspace-changes): count symlink_created in the changed-file badge getChangedFileCount summed only created + modified + deleted, so a run whose only change was a symlink replacing a file (reported as the new symlink_created status, not deleted) produced a count of 0 and WorkspaceChangeBadge hid the badge entirely -- the exact scenario this PR targets, with the opposite of the intended result. Add symlink_created to the frontend WorkspaceChangeSummary interface (already emitted by the backend) and include it in the count. The per-file StatusIcon/statusLabel "modified" fallthrough is unaffected and left as a follow-up, per review. Regression test reverts cleanly to reproduce a count of 0 pre-fix. * fix(workspace-changes): rank symlink_created in file sort and complete the type contract sortWorkspaceChanges's statusRank had no entry for the new symlink_created status, so statusRank[left.status] - statusRank[right.status] evaluated to NaN for any comparison involving a symlink-created file, violating Array#sort's ordering contract instead of producing a deterministic order. The frontend WorkspaceChangeStatus and DiffUnavailableReason unions, and the WorkspaceFileChange symlink fields, also stayed narrower than what the backend now emits, so TypeScript's satisfies Record<...> guard on statusRank could not catch the gap. Widen WorkspaceChangeStatus to include "symlink_created" and DiffUnavailableReason to include "symlink", add the matching symlink/symlink_target_before/symlink_target_after fields to WorkspaceFileChange, and give symlink_created a rank alongside modified in statusRank -- restoring the satisfies guard's ability to catch a future unranked status. unavailableLabel now has an explicit "symlink" branch (new symlinkUnavailable i18n string, en-US + zh-CN) instead of falling through to the generic label. Also fixes the failing e2e-tests CI check: the existing workspace-changes.spec.ts mock summary predates the symlink_created field, so getChangedFileCount computed 1 + 1 + 0 + undefined = NaN and the badge rendered "Edited NaN files" instead of "Edited 2 files". Added symlink_created: 0 to the mock to match the real backend contract. New sortWorkspaceChanges unit tests revert cleanly against the unranked statusRank to reproduce the NaN-driven misordering. pnpm test (626 tests), pnpm check, and pnpm format are clean, and the previously-failing e2e spec plus the full e2e suite (94 tests) pass. |
||
|
Vanzeren
|
823c47bcc2
|
fix(backend): stop classifying UTF-16 markdown files as binary (#3966)
* fix: detect utf16 markdown workspace diffs * fix: tighten binary detection in workspace diff scanner * fix: decode utf-8-sig before utf-8 to strip bom from diff content |
||
|
Ryker_Feng
|
00161811bd
|
feat: add workspace change review for agent runs (#3945)
* feat: add workspace change review * chore: format workspace change files * fix: optimize workspace change summaries * style: refine workspace change badge scale * fix: restore workspace change user context import * fix(frontend): gate workspace change badge to assistant messages Only pass run_id to assistant MessageListItems so the workspace-change badge can never render under a user's prompt, which carries the same run_id. Assert single badge render in the E2E flow. * fix(workspace-changes): address review feedback on diff parsing and badge - Restrict unified-diff header detection to "+++ "/"--- " (trailing space) in both backend _count_diff_lines and frontend getWorkspaceChangeLineClass so content lines beginning with +++/--- are counted/styled correctly - Gate WorkspaceChangeBadge to ai messages so tool messages folded into an assistant group don't render a duplicate badge - Add regression tests for both diff-classification fixes - Apply prettier formatting to workspace-changes files flagged by CI --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |