mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-28 17:06:05 +00:00
5 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Ryker_Feng
|
20debf9cc7
|
feat(agents): per-agent model and generation settings (#4347)
* feat(agents): per-agent model and generation settings Let each custom agent choose its own model and sampling settings (temperature, max_tokens) plus thinking / reasoning_effort defaults, so agents sharing a model profile are no longer stuck with one shared temperature and output length (#4336). AgentConfig gains optional model_settings / thinking_enabled / reasoning_effort (None = inherit). create_chat_model applies per-caller model_overrides on top of the profile before the thinking/Codex transforms; the lead agent resolves each knob with precedence request > agent config > profile/default. The /api/agents create/update routes persist the fields and reject an unknown model. The default lead agent path is unchanged (no agent config -> overrides None). The agent chat composer also stops force-overriding an agent's configured default model with models[0]. * fix(agents): tri-state thinking control and default-model capability gating The model-settings dialog seeded the thinking switch to false, so opening it to tweak temperature and saving silently disabled thinking (the runtime default is on) with no way back to inherit. It also hid the thinking / reasoning controls whenever the agent inherited the global default model, since `__default__` never resolved through `models.find`. Give thinking an explicit Inherit / On / Off tri-state so an untouched save is a no-op, and resolve `__default__` to the effective default (models[0]) for the capability check. Logic lives in the tested helpers module. |
||
|
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>
|
||
|
Nan Gao
|
21b3510226
|
feat(agents): feature-gate the agents UI behind the agents_api flag (#3757) (#3769)
* feat(gateway): add GET /api/features for frontend feature gating (#3757) * feat(agents): add useAgentsApiEnabled feature-flag hook (#3757) * feat(agents): gate /workspace/agents segment on agents_api flag (#3757) * feat(sidebar): grey out Agents button with tooltip when agents_api disabled (#3757) * fix(sidebar): show disabled Agents tooltip on hover, harden a11y + e2e (#3757) - Wrap the disabled Agents button in a hoverable tooltip trigger so the 'feature not enabled' hint shows in the expanded sidebar, not only when collapsed (the SidebarMenuButton tooltip prop is hidden unless collapsed). - Add tabIndex={-1} and drop the redundant onClick preventDefault. - Add e2e coverage for the disabled state + a default /api/features mock. * style(sidebar): move cursor-not-allowed to the hoverable span (#3757) * test(agents): anchor e2e agents-API request filter with a path regex (#3757) * fix(agents): don't expose backend config in disabled message; tell user to contact admin (#3757) The disabled panel previously said 'Set agents_api.enabled: true in config.yaml', leaking backend configuration to end users. Replace with a generic 'not enabled on this server, contact your administrator' message (matching the existing nameStepApiDisabledError copy). e2e now asserts the contact-admin message and that no config.yaml/agents_api text is rendered. * make format * fix(agents): keep agents_api flag sticky during /api/features outage (#3757) Failing open re-mounted the agents UI and re-triggered the 403 storm when agents_api was genuinely disabled and /api/features was down. Persist the last definitive answer and fall back to it (sticky) before failing open, only failing open when nothing has ever been observed. Read the cached value after mount so the first client render matches the server (no hydration mismatch on the non-loading-gated sidebar). * fix(sidebar): make disabled Agents entry keyboard/SR accessible (#3757) The disabled-state explanation was hover-only: tabIndex={-1} removed the entry from the tab order and the reason lived only in a pointer-triggered tooltip. Keep it in the tab order and wire aria-describedby to a visually-hidden reason so keyboard and screen-reader users learn why it is disabled. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
Jiahan Chen
|
6fb22bb311
|
test(frontend): migrate unit tests to rstest (#3703)
* test(frontend): migrate unit tests to rstest * docs: updates AGENTS.md * test(frontend): fix rstest lint formatting |
||
|
Xinmin Zeng
|
2ace78d1e5
|
fix(frontend): surface backend detail when agent name check fails (#3048)
* fix(frontend): surface backend detail when agent name check fails The new-agent page caught AgentNameCheckError but only branched on reason === "backend_unreachable". Everything else (notably the 422 "Invalid agent name '...'. Must match ^[A-Za-z0-9-]+$" response from GET /api/agents/check when the user submits a name with disallowed characters — trailing space, dot, Chinese, invisible whitespace from copy-paste) fell through to the generic fallback "Could not verify name availability — please try again", swallowing the detail that already told the user exactly what to fix. Add a request_failed branch that surfaces err.message (which checkAgentName already populates from the backend's detail at core/agents/api.ts). The disabled / backend_unreachable / unknown- error paths are unchanged. Pin the contract with unit tests covering: 200 success, fetch rejection, 502/503/504 network errors, agents_api disabled detail, 422 validation detail carried verbatim, statusText fallback when detail is absent, and a regression guard against misclassifying a 422 as agents_api disabled. Closes #3041 * fix(frontend): localise the error prefix when surfacing backend detail The previous commit surfaced the backend's raw `err.message` on the new-agent page when the name check failed. The detail itself is English (backend's `_validate_agent_name` text, any 5xx business message, etc.) and dropping it bare into a zh-CN page produced a jarring English-among-Chinese line that didn't match neighbouring strings like "已存在同名智能体" / "无法验证名称可用性". Add `nameStepCheckErrorWithDetail` as a templated string ("Name check failed: {detail}" / "名称校验失败：{detail}"), mirroring the existing `nameStepBootstrapMessage` `{name}` template pattern. The page wraps `err.message` in it when present and falls back to the plain `nameStepCheckError` when the detail is empty. Rendered output (verified locally with a Console fetch mock that returns 500 + detail): zh-CN: 名称校验失败：Database connection lost: SQLAlchemy connection pool exhausted (max 5 connections, all in use) en-US: Name check failed: Database connection lost: SQLAlchemy connection pool exhausted (max 5 connections, all in use) The localised prefix tells the user *what operation* failed; the raw detail tells them *why*. Translating the detail itself would be lossy (any unbounded backend string would need a translation table) and would break the debuggability the previous commit delivered. Refs #3041 * fix(frontend): distinguish backend detail from generated fallback in AgentNameCheckError Addresses Copilot's review on #3048: the previous commits keyed off `err.message`, but `checkAgentName` substitutes a generated fallback string ("Failed to check agent name: ${statusText}") when the backend sent no detail. That guaranteed `err.message` was always truthy, made the `nameStepCheckError` fallback branch unreachable in practice, and could surface awkward strings like "名称校验失败：Failed to check agent name: Bad Gateway" in the UI. Add an explicit `detail: string | null` field to AgentNameCheckError. `checkAgentName` populates it only when the backend response actually carried a string `detail` (defensive guard against the dict-shaped detail that other deer-flow endpoints use for typed error codes). The new-agent page now selects on `err.detail` instead of `err.message` so the localised fallback wins when no real detail exists. Also fix the prettier formatting that broke lint-frontend CI on the previous push. Test changes: - The 422 carry-through test now asserts both `detail` and `message` hold the backend string verbatim. - A new "falls back to statusText in message but leaves detail null" test pins the contract that no real detail ⇒ no UI surface leak. - A new "treats non-string detail as null" test guards against future backend schema drift toward dict-shaped detail. Refs #3041 #3048 |