* feat(agents): persist tool artifacts as resolvable handles (#4676)
MCP and sandbox tools return file paths, URLs, and task ids that are
lost when context compaction summarizes the conversation. This adds a
per-thread artifact handle registry so the model can reference
artifacts by short deterministic handles (art_xxxxxxxx) that survive
compaction and resolve to real references at the tool-call boundary.
- ThreadState.tool_artifacts: reducer channel capped at 100 entries,
same-handle latest-wins, survives summarization compaction
- artifact_registry: deterministic handle derivation from
(thread_id, tool_call_id, call_index); extraction precedence
structured_content -> file/image blocks -> conservative text scan;
HTML-escaped model-context rendering with char budget
- ArtifactCaptureMiddleware: before_model hook captures lightweight
metadata (never content) and tracks handle consumption
- ArtifactResolutionMiddleware: rewrites handles in tool-call args to
real references before execution; unknown handles untouched
- DurableContextMiddleware: projects the registry into the hidden
durable-context data block ([available]/[consumed] status)
- config: new tool_artifacts section (all switches default on)
- frontend: artifact badges on tool-call steps keyed by tool_call_id
Fixes#4676
* fix(agents): harden artifact registry after review (#4676)
Review findings on #4929:
- capture/consumption updates emitted in the same before_model call are
now concatenated instead of dict-merged; dict-merging clobbered the
shared tool_artifacts key and permanently dropped fresh captures
- handles embed a per-result ordinal so multiple references inside one
tool result never collide (two paths in one text block previously
collapsed into one handle)
- structured_content extraction pulls concrete refs from known keys
(file/path/url/task_id/..., string or list-of-string values) instead
of storing a truncated JSON preview, falls back to an untruncated
whole-object data entry, and no longer skips file/image content blocks
- plain-string tool results (e.g. bash/write_file output) are scanned
for sandbox paths / remote URLs too, gated by detect_refs_in_text
- wire max_entries through configure_tool_artifact_max_entries at
assembly (clamped 10..1000) and gate detect_refs_in_text scans
- resolution requires both enabled and resolve_handles_in_args,
matching its docs
- add real ToolCallRequest.override coverage and the spec 14.4
integration cycle (capture -> inject -> resolve -> consumption)
* fix(agents): address second-round artifact registry review (#4676)
Follow-up findings on #4929:
- drop generic `output`/`outputs` from structured ref keys: prose under
those keys no longer becomes a bogus file entry (falls back to the
whole-object data entry; path-shaped refs are still caught by the
free-text scan)
- strip closing quotes, brackets, and backticks from detected refs so
markdown- and JSON-wrapped paths resolve to clean real references
- remove the process-wide cap setter: the reducer enforces only an
absolute ceiling (1000) and ArtifactCaptureMiddleware applies the
configured max_entries per agent when emitting updates, so agents
with different configs in one process never share or flap a cap
- skip extraction for tool messages whose tool_call_id already has
registry entries and memoize known-empty results (bounded FIFO), so
steady-state capture cost drops to the new message tail instead of a
full-history rescan per model call
- correct the inverted ordering claim: capture is position-independent
in the wrap chain because it is a before_model hook reading state
messages; fixed the assembly comment, AGENTS.md item 15, and the
ordering test docstring
CI parity verified locally: ruff check + format --check, full offline
suite, blocking-io suite, collect-only, uv lock --check,
check_agent_guidance, frontend format/lint/typecheck/build/tests.
* fix(agents): sliding-window cap and URI gates for artifact registry (#4676)
Third-round review findings on #4929:
- max_entries is now a sliding retention window: fresh captures are
always registered, and when the projection exceeds the configured
cap the middleware appends a trailing {"op": "trim_to", "keep": N}
directive that the reducer applies by evicting the oldest entries.
The previous remaining-budget emission froze the registry at the cap,
permanently dropping post-compaction artifacts — the exact failure
mode #4676 targets — and silently disabled the round-2 rescan
optimizations at the point threads grew longest
- _track_consumption memoizes settled tool-call args in a bounded FIFO
alongside the existing empty-result memo, so historical AIMessage
args are not regex-rescanned every model call
- file/image content-block URLs must be http(s) or path-shaped;
data:/blob: URIs (MCP embedded resources carrying base64 payloads)
can no longer enter thread state, tool args, or crowd out the render
budget; protocol-relative //host forms are rejected as well
- structured-content ref values go through the same URI-shape gate as
content blocks, closing the embedded-payload hole via known keys such
as url/urls
- tool_artifacts.enabled now gates the whole middleware including
consumption tracking via an early return in before_model
Docs updated to describe the sliding window, URI gates, enabled scope,
and both bounded memos.
* fix(agents): final evictions and pending-aware consumption for artifact registry (#4676)
Fourth-round review findings on #4929:
- the sliding window interacted with the seen_call_ids skip to
resurrect evicted entries every round: once an entry was trimmed, its
tool_call_id left the seen set while its ToolMessage stayed in
context, so the next model call re-extracted it, re-registered it as
newest, and evicted something else — a never-converging rotation.
The empty-result memo is now a unified _processed_results memo that
records every extraction regardless of outcome, making evictions
final; steady state over a saturated thread is quiescent (pinned by
a multi-round test asserting no updates and zero extractions)
- the consumption scan built its handle map from pre-capture state, so
a call referencing a handle captured in the same before_model call
missed, got settled as quiet, and its consumption mark was lost
forever. _track_consumption now receives the pending capture entries
and resolves against state + pending; a call settles as quiet only
after every referenced handle resolved, so transient misses retry
next round instead of permanently suppressing the mark
AGENTS.md entry 15 updated to describe both memos and the
eviction-is-final semantics.
* fix(artifacts): address occurrence identity, PII and URL review findings
* fix(artifacts): enforce resolved policy checks and bounded registry handling
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* feat(knowledge): add verifiable RAGFlow source citations
* docs(knowledge): scope RAGFlow guidance to its own directory
* fix(knowledge): preserve citations through rendering and budgets
* fix(frontend): gate tool-step links through the href scheme allowlist
The chain-of-thought renderer turned web_fetch args and web_search /
image_search result URLs straight into <a href>. Markdown links already
pass isSafeHref, but these tool-step links bypassed it, so a
prompt-injected tool call could put file:, ms-msdt:, vscode: or other
OS protocol-handler links into the chat. React 19 only rewrites
javascript: hrefs.
All three sites now reuse the markdown allowlist and render an unsafe
URL as plain text (the image thumbnail stays, unlinked). Tests render
MessageGroup for each tool with unsafe schemes plus a web-URL control.
* docs(changelog): note tool-step link scheme gating (#5526)
* fix(frontend): mark omitted tool-step links and guard web_fetch url type
Review follow-up. Tool steps dropped an unsafe URL to bare text, while
markdown and artifact links show a dotted "Unsafe link omitted" span, so
the two surfaces applying the same rule degraded differently. That span
was already duplicated between markdown-link.tsx and artifact-link.tsx;
it is now one UnsafeLink component used by all three renderers. It
passes extra props through so the image tile still works as a Radix
tooltip trigger.
web_fetch also read args.url with a cast only. A non-string url (models
occasionally emit one mid-stream) reached JSX as an object and threw,
taking down the message list. It is now typeof-guarded.
* fix(frontend): default missing tool-call args before rendering steps
Review follow-up. The web_fetch typeof guard dropped the optional
chaining of the cast it replaced, so a tool call without an args object
threw again. Other branches were already exposed the same way: seven
tool kinds (web_fetch, web_search, image_search, read_file, write_file,
str_replace, browser_*) threw on a missing or null args while building
their labels. convertToSteps now defaults args to {} once, so every
ToolCall branch receives an object.
* feat(frontend): reference conversations from the composer
Adds a "Reference a conversation" button next to the attachment button,
shown only while GET /api/features reports read_conversation enabled. It
opens a picker over the recent-conversation list (current thread excluded,
capped at max_references) and shows removable chips in the composer.
On send the thread IDs ride SendMessageOptions.conversationReferences into
run context.conversation_references, which the Gateway consumes at
admission; the LangGraph SDK drops unknown top-level body fields. A
display-only copy ({thread_id, title}) on the visible human message lets
the transcript render read-only chips linking to the source.
References are per message: not persisted with the draft and cleared on
send or thread switch; regenerating or editing a turn runs without them
unless they are attached again.
Related to #5398. Depends on #5463.
* fix(frontend): pin the run-context contract and finish the picker states
Both thread.submit paths now build their run context through one exported
buildRunContext helper, tested directly: attached references travel as a
plain string[] under context.conversation_references only when the caller
passed them, a stray key in local settings is dropped instead of forwarded,
and the regenerate/edit replay path never carries references.
The picker shows a loading row while the conversation list is still in
flight instead of claiming there are no conversations, and the transcript
chip group is labelled with the previously unused referencedConversations
translation.
* fix(frontend): route conversation-reference chips to custom-agent sources
The picker offered custom-agent conversations but kept only the thread ID
and title, so transcript chips always linked to /workspace/chats/{id} and
dropped the source's custom-agent context on navigation.
Preserve the agent identity end to end: the picker now attaches
agentNameOfThread() (context first, then metadata.agent_name, mirroring
pathOfThread) to the selection, the display-only additional_kwargs metadata
round-trips it as agent_name, and the transcript chip passes it to
pathOfThread so custom-agent sources resolve to
/workspace/agents/{agent}/chats/{id}.
Tests: agent_name metadata round-trip and malformed-entry tolerance, picker
toggle carrying the metadata agent with run context winning, and a
picker-to-transcript regression pinning the /workspace/agents/writer/chats/
source-1 href.
---------
Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
* fix(frontend): truncate long subtask card titles to a single line
The subtask card header rendered task.description without any width
constraint; when a provider omits the optional description, the full
task prompt becomes the title and overflows the card.
Wrap the title in a truncating span (full text remains available via
the title tooltip and the expanded card body), give the step min-w-0
flex-1, and pin the status cluster with shrink-0 so overflow resolves
at the title.
Add an e2e test asserting a long prompt renders with the truncate
class, a real ellipsis (scrollWidth > clientWidth), and single-line
height.
* fix(frontend): keep subtask card status cluster shrinkable on narrow viewports
The shrink-0 status cluster could not shrink below its max-content (model
label + usage + status pill, up to ~456px with a long tool-call
description), so on narrow viewports it overflowed the header row while the
title collapsed to zero. Drop shrink-0 and add min-w-0 to both the cluster
and the pill (the pill's min-content is the status text's longest
unbreakable word, so one min-w-0 was not enough), and floor the title at
min-w-24 so it stays visible.
Also extend the e2e spec per review: an in_progress shimmer truncation test
(held-open SSE stream keeps the card running), a 375px no-overflow
assertion for both the resting and running card, and a pixel-budget
single-line check instead of parseFloat(lineHeight) which NaNs on the
'normal' keyword.
* test(frontend): honest fixture text and explicit visibility timeout in subtask spec
Review nits: the long-title fixture lifted the stopped test's human turn
whose text narrates the stop scenario; give it its own LONG_TASK_USER_TEXT
and override content alongside id and tool_calls. Add the missing 15s
timeout on the running-375px title visibility assertion so a future
reorder doesn't turn the 5s default into a cold-start flake.
* fix(messages): drop legacy <uploaded_files> tag handling (#4212)
PR #4174 unified upload-context injection on <current_uploads> (IM and web
both flow through UploadsMiddleware), and #4632 documented the current
path. This removes the remaining backward-compat parsing of the
pre-#4174 <uploaded_files> tag, the final cleanup item tracked by the
issue:
- deermem: only <current_uploads> is stripped from human turns before
memory persistence, and the upload-sentence scrubber drops the legacy
tag alternative.
- mem0: the mirrored message filter recognises only <current_uploads>.
- InputSanitizationMiddleware: remove the legacy tag from the blocked-tag
denylist (it existed only because deermem parsed the old tag).
- frontend: stripUploadedFilesTag / stripInternalMarkers /
parseUploadedFiles and the message-list fallback parse only
<current_uploads>; demo thread fixtures are migrated to the current tag.
Scope decision: a <uploaded_files> block in pre-#4174 history is now
treated as ordinary user content (pinned by tests in both layers) instead
of being silently dropped or stripped.
* style: apply prettier formatting to stripUploadedFilesTag
* fix(uploads): keep legacy <uploaded_files> stripping for display/export only
Addresses review feedback on #4826: removing the legacy tag from the
frontend display layer made pre-#4174 threads render raw <uploaded_files>
XML (with server-side upload paths) in chat, copy data, and JSON exports.
The backend cleanup stands — memory pipelines and the sanitization denylist
treat only <current_uploads> as an internal marker. The frontend keeps the
legacy spelling in its display/export-only utilities
(stripUploadedFilesTag / INTERNAL_MARKER_TAGS / parseUploadedFiles and the
message-list fallback) so old history renders cleanly without leaking
internal paths, while the memory/sanitization scope-decision tests remain
unchanged.
Frontend tests now pin both spellings: <current_uploads> and legacy
<uploaded_files> are stripped from copy data, markdown leak-stripping, and
JSON exports.
* docs(ui): record accepted display-spoof tradeoff for legacy upload tag
Review note (willem-bd): since <uploaded_files> is off the sanitization
denylist, a live user can type the legacy spelling and fabricate file
chips / hide their own message text in display. Display-only and
self-inflicted with no backend semantics, so it is accepted for now;
documented at both the message-list fallback and stripUploadedFilesTag.
Age-gating the legacy spelling remains a possible follow-up.
---------
Co-authored-by: betterkite <313258397+betterkite@users.noreply.github.com>
* perf(frontend): cache settled copy-data derivation across streaming chunks
Every SSE values chunk re-renders MessageList, and the re-render re-derived
copy/toolbar text for every settled row: getAssistantTurnCopyData re-ran the
O(turn bytes) content extraction per settled group, and MessageListItem's
toolbar recomputed getMessageCopyData per message. Settled group arrays keep
their identity across chunks (deriveStableMessageGroups), so both derivations
now cache on that stable reference: a WeakMap keyed on the messages array for
turn copy data, and a useMemo on message identity for the toolbar copy text.
Fixes#5094
* fix(frontend): gate row copy-data memo and correct cache win claim
Address review: derive one memoized copy value only when
isHuman || (!isLoading && showCopyButton) and reuse it for both editing
and the toolbar, so settled assistant rows (whose toolbar never renders)
skip the derivation and human rows derive once, not twice; correct the
assistantTurnCopyDataCache comment — the regex/trim split is already
cached per message, the cache's win is the traversal/allocations for
string turns and the uncached O(bytes) map/join/trim for array-content
turns (benchmarked: 5.1x / 17.2x per settled history sweep).
* style(frontend): expand single-line messages array for Prettier
A reasoning model's turn showed its thinking below its answer while
streaming, then flipped to thinking-above-answer once the turn settled.
One message is rendered by two components with opposite ordering rules:
while streaming, an AI message with content and reasoning but no tool
calls yet is deliberately held out of the terminal bubble (#4304) and
rendered by MessageGroup's chain-of-thought panel, which pinned the
trailing reasoning disclosure to the bottom; the settled bubble paints
its <Reasoning> disclosure above the content.
Render the trailing reasoning disclosure before the assistant text that
follows it, and emit a message's reasoning step before its content step
in convertToSteps -- the step list was content-first, so ordering by
step position alone could not fix it. Assistant text emitted before that
reasoning keeps its earlier position.
This also covers two cases the report does not mention: tool-using turns
reversed the same way, and expanding "N more steps" showed a message's
answer above its own thinking.
* fix(frontend): render one workspace-change card per run
The workspace-change card is resolved from (threadId, runId) alone, so
every AI message in a run fetches the identical summary. It was rendered
per AI message.
getMessageGroups() opens a separate terminal assistant group for every AI
message that has content and no tool calls, so a run ends in more than one
bubble whenever the model emits answer text mid-run that never gains a
tool call. Each bubble then painted a byte-identical "Edited N files"
card.
Fold the card onto a single position per run, matching how run duration
already anchors its own run-scoped display after the run's last visible
group. Anchoring keys on group index rather than message id because a
terminal assistant group holds exactly one message whose id may be absent.
Fixes#4555
* docs(frontend): explain the workspace-change anchor's group-type restriction
The helper narrows anchor candidates to terminal assistant groups while
getRunDurationDisplaysByGroupIndex accepts a run's last group of any type.
That asymmetry is load-bearing: run duration is emitted by MessageList
around every group, but the workspace-change card comes from
MessageListItem, which MessageList invokes only for human/assistant
groups. Anchoring a run that ends in an assistant:processing group would
pick a position that never renders and silently drop the card.
Record the rule in both places that could invite a future "unification":
the helper's docstring, and the frontend AGENTS.md paragraph that tells
maintainers where run-scoped displays belong.
* feat(clarification): structured form fields for human-input cards
Add a request-side v2 `form` mode to the ask_clarification protocol so
business flows (e.g. expense reimbursement) can collect several values
in one card instead of sequential free-text questions:
- `ask_clarification` gains a restricted `fields` parameter (text /
textarea / number / select / multi_select / checkbox / date)
- ClarificationMiddleware validates and normalizes fields explicitly
(whitelisted types, unknown -> text, select-likes without options ->
text, duplicate/invalid entries dropped, all-invalid falls back to
the legacy modes) since the middleware short-circuits before tool
execution; the plain-text fallback lists fields for IM channels
- Form payloads carry `version: 2` so older frontends degrade to the
text fallback; replies stay on the v1 response protocol — the card
submits a readable summary as `response_kind: "text"`, so journal
persistence and answered-card recovery are unchanged
- Frontend renders typed field controls with required-field validation
and compact multi-select chips
Part of #4400 (scope narrowed per maintainer feedback: request-side
only, no new response kinds, no top-level multi_choice).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(clarification): harden form protocol per review feedback
Address the five review points on #4406:
- Reject field names colliding with JS Object.prototype members on both
sides; frontend reads form values via own-property access only, so
`constructor`/`toString`-style names can no longer leak inherited
members into required validation or the submitted summary
- Close open requests answered through the legacy text fallback: a
visible plain human reply (no response metadata) now marks every
previously-opened request as answered, so upgrading to a v2-aware
frontend cannot leave the composer locked on an already-answered card
- Give checkbox fields deterministic boolean semantics: values are
seeded to an explicit false ("no" in the summary) and `required` means
must-agree/consent; documented in the tool schema
- Make middleware field validation atomic: structurally broken entries
(bad/duplicate/reserved names, over-cap field/option counts or text
lengths) degrade the whole form instead of silently dropping fields;
options are trimmed/deduped with blanks removed so the backend never
emits payloads the frontend parser rejects
- Associate form labels/controls (htmlFor/id), aria-required,
aria-invalid, and error descriptions for accessibility
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor(clarification): type the fields item schema via TypedDict
Replace `fields: list[dict[str, Any]]` with `list[ClarificationFormField]`
(a TypedDict with `name` required and the type whitelist as a Literal) so
the provider-facing tool schema documents the item shape instead of an
opaque object relying on the docstring. Runtime validation is unchanged
and stays in ClarificationMiddleware, which intercepts the call before
tool execution. Addresses the non-blocking review suggestion on #4406.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(frontend): drop unsupported aria-invalid from multi-select group
jsx-a11y: role=group does not support aria-invalid; the error linkage
stays via aria-describedby.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(clarification): coerce numeric required flags and normalize fields once
- `_normalize_bool` now coerces 1/0 (some providers serialize booleans
as integers), so `required: 1` no longer silently flips to optional
- `_handle_clarification` normalizes `fields` once and passes the result
to both the text fallback and the payload builder
Addresses the non-blocking review nits on #4406.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(clarification): harden form protocol per contract review round 2
Backend:
- Guard unhashable JSON in the intercept path: `type: []`/`{}` degrades
the field to text and `clarification_type: []` coerces to str instead
of raising TypeError (which, with return_direct, ended the turn with
an error and no card or fallback)
- Add a total budget over the serialized normalized fields (16KB UTF-8
bytes): per-item caps alone admitted forms whose IM text fallback
exceeded channel delivery limits (Slack 40k chars, Feishu ~30KB card),
silently truncating trailing fields; a boundary test proves any
accepted form's fallback stays deliverable
Frontend:
- Submission value now appends a JSON block keyed by stable field names
(readable summary alone is delimiter-ambiguous), with a collision
regression test
- Parser boundary tightened to match backend constraints: empty option
values (Radix SelectItem crash), duplicate option ids/values,
duplicate field names, and the form<->version-2 binding are rejected
- Keep the error node mounted while any field is still invalid so
aria-describedby never points at a removed element (happy-dom
interaction test)
- Required semantics are now accessible: native checkbox control (no
HTML required attribute — it would intercept the custom submit path),
visually-hidden localized "required" markers next to the aria-hidden
asterisks
- Legacy-fallback closure narrowed to the latest unanswered request:
nothing guarantees a single outstanding clarification across runs, and
closing all would silently swallow older decisions; an older request
left open becomes the active card again
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(frontend): keep clarification selects controlled
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix(frontend): strip and parse the <current_uploads> upload context tag
#4174 renamed the upload context block that UploadsMiddleware prepends to
the user message from <uploaded_files> to <current_uploads>, but the
frontend tag vocabulary was not updated, so the raw block (file list plus
usage guidance) rendered inside the user's chat bubble and the file-chip
content fallback stopped matching. Add the new tag to
stripUploadedFilesTag, INTERNAL_MARKER_TAGS (covers export and streamdown
preprocessing), parseUploadedFiles, and the chip fallback detection.
<uploaded_files> stays supported for history and IM-channel messages.
* fix(frontend): parse upload-context sizes to bytes for the file chip
parseUploadedFiles stored the raw leading number of the human-readable
size (e.g. parseInt("177.6 KB") -> 177) into FileInMessage.size, which
is documented as bytes. On the content-fallback chip path (history/IM
messages without additional_kwargs.files) formatBytes then rendered a
177.6 KB file as "0.2 KB".
Convert the backend's "<n> KB" / "<n> MB" form back to bytes so the chip
re-renders at the original magnitude; update the parse tests to assert
byte values.
* 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>
* fix(frontend): harden artifact and markdown rendering
* fix(#4117): restore allow-scripts for scroll-restore, fix citation XSS bypass
willem-bd identified these issues:
1. [REGRESSION] sandbox removed allow-scripts which broke HTML artifact
scroll-restoration — the injected postMessage script could not run.
The prior config (allow-scripts allow-forms without allow-same-origin,
i.e. opaque origin) was already safe. Restored with corrected comment.
2. [XSS bypass] CitationLink rendered <a href={href}> directly before
isSafeHref ran, so prompt-injected [citation:x](javascript:...)
bypassed the safety check. Moved citation block after the guard.
Also:
- Added mailto: and tel: to SAFE_HREF_PROTOCOLS
- Kept anchor-only attributes off the <span> fallback (React DOM warning)
Note: the loadMessages re-throw originally in this commit was dropped
during the rebase — upstream #4065 rewrote useThreadHistory as a
TanStack useInfiniteQuery that already surfaces fetch failures.
* test(e2e): update sandbox assertion to match allow-scripts allow-forms
The artifact preview iframe's sandbox was restored to 'allow-scripts allow-forms'
for scroll-restoration. Update the E2E test to expect the corrected value.
* fix(#4117): address review — ArtifactLink XSS guard, urlOfArtifact sandbox e2e
- Apply the isSafeHref guard to ArtifactLink (artifact-link.tsx) so a
prompt-injected javascript:/data: href in a .md artifact preview cannot
reach a real anchor in the main document, matching the guard in
createMarkdownLinkComponent.
- Add an e2e asserting the urlOfArtifact iframe (non-code
browser-previewable files like PDF) keeps its empty sandbox.
Note: the loadMessages error-surfacing changes originally in this commit
were dropped during the rebase — upstream #4065 rewrote useThreadHistory
as a TanStack useInfiniteQuery whose queryFn already throws on
!response.ok and surfaces the failure via a toast.
* fix(frontend): let write_file non-code previewable artifacts render in sandboxed iframe
When a write_file artifact such as PDF is clicked in chat, the component receives a path that forced isCodeFile=true, hiding the sandboxed iframe behind the code editor. Now non-code browser-previewable files are detected early so the sandboxed iframe renders correctly.
Fixes the E2E test: renders sandboxed iframe for a browser-previewable non-code file.
* fix(#4117): align PDF artifact route pattern with convention (drop /mock/ prefix)
The test used /mock/api/threads/... for the PDF artifact content route,
but the urlOfArtifact helper generates /api/threads/... (without /mock/)
when isMock=false. The other tests (e.g. presented artifacts) already use
the correct /api/threads/... pattern.
* test(frontend): add render-level coverage for unsafe markdown/artifact links
- Render MarkdownLink and ArtifactLink via renderToStaticMarkup and
assert an unsafe javascript: href produces a disabled <span> (never an
<a>), including through the citation-labelled branch, and that safe
https hrefs render hardened anchors (target=_blank, rel=noopener).
- The new ArtifactLink render test caught the unsafe href leaking onto
the fallback <span> through the {...rest} spread; drop the spread in
both span fallbacks so anchor-only attributes (href/target/rel) and
react-markdown's node prop never reach the span.
- Cover mailto:/tel: in the isSafeHref unit cases and fix the stale
SAFE_HREF_PROTOCOLS docstring that still claimed http/https-only.
* fix(frontend): route the agent save-hint through the safe localStorage facade
Export safeLocalStorage from core/settings/local and use it for the
agent-create save-hint read/write so blocked browser storage (Safari
private mode, strict containers, embedded WebViews) cannot throw from
the effect. core/agents/feature-cache.ts already guards its
localStorage access with try/catch, so settings + agent pages are now
consistently best-effort.
* fix(frontend): allow scheme-less relative markdown links in isSafeHref
* feat(subagents): show runtime metadata on task cards
* fix(subagents): stop task-card render loop and dedupe model fetches
Address code review on the runtime-metadata cards:
- P1 render loop: the terminal ToolMessage is re-parsed on every
MessageList render and always carries modelName/usage, so the
presence-based setTasks condition fired a fresh state object each
render -> "Maximum update depth exceeded". computeNextSubtask now
returns a value-compared `changed` flag and a pure subtaskNotification()
routes terminal transitions through the deferred after-render path
while skipping no-op re-parses.
- Per-card useModels refetch: add staleTime: Infinity to the ["models"]
query so every subtask card shares one /api/models fetch instead of
refetching on each mount.
* make format
* refactor(subagents): dedupe token-usage validators + tidy event narrowing
Address PR review follow-ups:
- DRY: extract one shared token-usage validator per side. Backend
status_contract.normalize_token_usage() now backs both the terminal
ToolMessage metadata and the subagent.step/.end run events
(step_events.py), and frontend messages/usage.normalizeTokenUsage()
backs both the live task_running event (lifecycle.ts) and the terminal
ToolMessage metadata (subtask-result.ts). Prevents the input/output/
total_tokens validation from drifting across the four former copies.
- Nit: onCustomEvent narrows event.type once instead of re-checking the
object shape per branch; the redundant task_started early-return
(already validated by taskEventToSubtaskUpdate) is dropped.
* feat(frontend): render slash-skill activations as inline chips
Show an explicit `/skill` activation as a compact inline chip in both the
composer and the chat transcript instead of raw slash text.
- Composer: selecting a skill suggestion stores it as a removable chip
aligned inline with the textarea; the leading `/skill ` prefix is
reattached only at submit time, so the backend activation protocol is
unchanged. Backspace on an empty input or the chip's close button clears
it; history navigation is disabled while a chip is active.
- Transcript: human messages that begin with `/skill` render the skill as a
read-only chip followed by the task text.
- Add a shared `core/skills/slash.ts` (`parseSlashSkillReference` +
`resolveSlashSkillDisplay`) mirroring the backend `slash.py` gate, so the
transcript only shows a chip when the skill actually exists and is enabled.
This removes a duplicated regex/reserved-name list and keeps display
semantics consistent with backend activation.
Add unit tests for the shared slash parser and extend the chat e2e to assert
the composer still submits `/skill <task>` after showing a chip.
* chore(frontend): format chat e2e test
* refactor(skills): address slash-skill chip review feedback
Follow-up to the inline slash-skill chip PR, resolving three second-order
review findings:
- Drive the reserved-command set and skill-name grammar from a shared
contracts/slash_skill_contract.json instead of a hand-copied
"keep in sync" pair. slash.ts and slash.py now reference the fixture, and
contract tests on both sides fail CI if either drifts.
- Extract a shared SlashSkillChip so the composer and transcript chips stay
in lockstep, and normalize the off-scale /8 and /12 opacity steps to the
standard /10 and /20 tokens.
- Split HumanMessageText into a pure parse gate plus a slash-only subtree
that owns the useSkills() lookup, so a skill-enabled toggle no longer
re-renders every plain-text human turn.
Verified: frontend eslint + tsc clean, pnpm test 572 pass (incl. new
slash-contract test); backend slash contract + slash-skills tests 31 pass.
* style(tests): sort slash skill contract imports
* fix(composer): inline the slash-skill text so the chip aligns with input
Address the "composer body layout change" review on #3981 by rendering the
active skill as an inline chip in the same text flow as the prompt, rather
than a separate flex row that drifted the box model across states.
- Render the chip + prompt inside one leading-6 wrapper and edit the prompt
through a `contentEditable` span, so the chip sits inline with the first
line and long/multi-line input wraps naturally back to the container edge.
- Align the chip with `align-top`: its h-6 (24px) height matches the text
line height, so chip and first-line centers coincide exactly (measured
delta 0), fixing the chip being raised above the baseline.
- Restore the placeholder in chip mode via a `data-empty` CSS `::before`,
which also gives the empty editable span width so it is no longer treated
as hidden.
- Widen the IME helper to `HTMLElement` and route the span's keydown/paste
through the shared skill-suggestion, prompt-history, backspace-to-clear,
and IME-composition handlers so contentEditable behaves like the textarea.
- Extend chat.spec.ts to drive the inline skill editor instead of the
textarea after a chip is shown.
* style(frontend): fix composer class order formatting
* fix(composer): break long unbroken input inside the slash-skill row
The inline slash-skill editor wrapped with `break-words`
(overflow-wrap: break-word), which only moves an over-long token to the
next line before breaking it. A long unbroken string therefore started
on the line below the chip, and when the string contained a break
opportunity such as a hyphen the browser wrapped there and pushed the
remaining run to the next line, leaving a wide gap on the right.
Switch to `break-all` (word-break: break-all) so the text fills each
line from the chip and packs tightly regardless of hyphens or CJK.
* feat(frontend): add structured human input cards for ask_clarification
Implement a reusable Human Input Card flow for ask_clarification while keeping
the existing text fallback for older clients and IM channels.
Backend:
- Add structured ToolMessage.artifact.human_input payloads for clarification requests.
- Preserve ToolMessage.content as the readable Markdown/text fallback.
- Normalize clarification options from native lists, JSON strings, plain strings,
mixed scalar values, None, and missing options.
- Derive input_mode as choice_with_other when options exist, otherwise free_text.
- Keep disable_clarification non-interactive behavior as a plain ToolMessage with
no human_input artifact.
- Cover artifact persistence and Gateway message metadata preservation in tests.
Frontend:
- Add human input protocol types, runtime guards, extractors, response builders,
and thread-state helpers.
- Add reusable HumanInputCard with option buttons, free-text input, pending,
read-only, disabled, and answered states.
- Render structured clarification cards from artifact.human_input, with Markdown
fallback for malformed or legacy tool messages.
- Preserve line breaks in structured question/context/option text.
- Hide submitted clarification bridge messages from the chat UI via
additional_kwargs.hide_from_ui.
- Send structured human_input_response metadata through the fourth sendMessage
options argument, preserving run context in the third argument.
- Wire submissions for normal chats, custom agent chats, agent bootstrap chats,
and sidecar chats.
- Derive answered state from raw thread.messages so hidden replies still update
the original card.
- Clear pending state when the hidden reply arrives, dispatch is dropped, or a
later async stream failure appears on thread.error.
* perf(frontend): optimize HumanInputCard UI interactions
- Support Enter key to submit text input (Shift+Enter for newline)
- Render question and context fields as Markdown instead of plain text
- Replace deprecated FormEventHandler type with structural typing
* test(frontend): add unit test cover optimize HumanInputCard UI interactions
* feat(frontend): disabled chatbox when has new human-input-card
* fix(style): lint error fix
* fix: sanitize hidden human input replies
- Preserve IME composition safety for human input card Enter submits
- Treat hidden human input responses as genuine user messages for sanitization
- Keep hidden card replies in memory filtering while excluding malformed/internal hidden messages
- Add regression coverage for card IME handling and hidden reply sanitization
* fix: tighten human input response validation
- Reject empty hidden human input response values
- Remove invalid list ARIA role from human input card options
- Add backend coverage for empty response payloads
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(sidecar): correct text-selection toolbar actions inside the side chat
The sidecar panel reuses MessageList, but it did not distinguish the side
chat surface from the main conversation, so selecting text inside the side
chat behaved as if it were the main list:
- The "Ask in side chat" action was shown even though the user is already
in the side chat, which is a no-op interaction.
- "Add to conversation" routed the snippet to the main composer's quotes
(conversationQuotes) instead of the side chat's own composer, so the
reference landed in the wrong input box.
Add a `sidecarSurface` prop to MessageList. On the sidecar surface, hide
"Ask in side chat" and route "Add to conversation" to `sidecar.openContext`
so the snippet attaches to the side chat's own composer (activeReferences).
Main-list behavior is unchanged.
* docs(sidecar): drop AGENTS.md note for the toolbar surface change
The sidecarSurface behavior is self-evident from the code; no dedicated
Interaction Ownership entry is needed.
* feat: add assistant turn branching
* fix(threads): skip workspace clone when branching from historical turn
Workspace files are not checkpointed, so cloning them onto a branch
rooted at an older assistant turn leaked files created in a later
timeline. Restrict the best-effort workspace copy to branches taken from
the latest turn; historical-turn branches now report
workspace_clone_mode="skipped_historical_turn" and keep only the
restored message history.
* style(frontend): fix prettier formatting in e2e mock-api
Collapse the branch-title normalization chain onto a single line to
satisfy the frontend lint (prettier --check) CI gate.
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* 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>
* feat(frontend): add side conversations for quoted follow-ups
* style(frontend): apply prettier formatting to sidecar-chat files
* fix(frontend): surface sidecar cascade cleanup failures via console.warn
Previously deleteSidecarThreadsForParent silently swallowed both
lookup errors and per-thread deletion failures, so parent thread
deletions could succeed while orphaning sidecar threads with no
signal to the caller. Log a warning that includes the parent id
and the failed thread ids/reasons so the leak is discoverable in
telemetry, matching the existing console.warn/error pattern in
this file.
* fix(frontend): address all sidecar review feedback
Resolve every reviewer comment on PR #3934:
- input-box/hooks/sidecar-panel: clear quoted references only via an
`onSent` callback that fires after the in-flight guard, so a dropped
send no longer silently discards quotes (willem-bd #3550).
- message-list: flip the selection toolbar below the selection when it
would clip above the viewport (willem-bd #3551).
- reference-metadata/thread/input-box: keep referenced ids, roles, and
count arrays 1:1 parallel instead of deduping ids (willem-bd #3552).
- message-list: widen selection containment to the shared assistant-turn
container and hint when a selection crosses messages (willem-bd #3553).
- sidecar/api: coalesce concurrent sidecar creates for one parent behind
a single in-flight promise to prevent duplicates (willem-bd #3554).
- sidecar-trigger/context: force-restore on trigger click so a sidecar
deleted elsewhere self-heals instead of opening a dead thread
(willem-bd #3555).
- threads/hooks: surface sidecar cascade cleanup failures via
console.warn for both lookup and per-thread deletes (Copilot).
Add unit + e2e coverage for parallel metadata, atomic create, and
trigger self-healing.
* feat(frontend): add citation sources evidence panel
Inline [citation:Title](URL) links render as badges, but with many
citations the reader has no consolidated, deduplicated list of what a
message or report actually drew on. Add a collapsible "sources" panel
that extracts citation links from AI messages and markdown artifacts,
dedupes by URL, counts occurrences, and offers per-source copy of a
reusable markdown reference.
- extractCitationSources: parse [citation:...](url) links, skip images
and fenced code, dedupe by normalized URL, fall back to domain for
generic labels
- CitationSourcesPanel: collapsible list with per-source cite counts,
internal scroll for long lists, and copy-to-clipboard reference button
- Wire panel into AI message content and markdown artifact preview
- Add en-US/zh-CN citation strings and types
- Unit tests for extraction and panel rendering
* fix(frontend): preserve default link styling in message content override
MessageContent_ passes a custom `a` renderer to MarkdownContent, whose
default `a` (primary underline + external target/rel) is overridden
because MarkdownContent spreads props components last. Restore that
styling/external behavior in the fallback branch so normal links in
messages aren't regressed, while keeping citation: and /mnt/ handling.
* fix(frontend): harden citation source extraction and dedupe link renderer
Address review findings on the citation sources panel:
- Use a non-consuming lookbehind so back-to-back citations no longer drop
every other source.
- Match balanced parenthetical groups in URLs so disambiguation links like
.../Foo_(a)_(b) are no longer truncated.
- Mask inline code (and unclosed streaming fences) so example citations in
code aren't scraped as real sources; masking preserves indices.
- Extract a shared createMarkdownLinkComponent factory used by both message
content and markdown content, removing the duplicated `a` renderer.
* feat(subagents): persist and display subagent step history (#3779)
Capture both assistant turns and tool outputs during subagent execution,
stream them in task_running events, and persist them as subagent.* run
events so the subtask card's step timeline survives a reload.
Backend:
- step_events.py: pure layer (capture_step_message, build_subagent_step,
subagent_run_event) shared by streaming and persistence
- executor.py: capture ToolMessage outputs, not just AIMessage turns
- worker.py: persist task_* custom events to RunEventStore (category
"subagent" keeps them out of the thread feed; list_events backfills)
Frontend:
- core/tasks/steps.ts + api.ts: SubtaskStep model, messageToStep,
eventsToSteps, mergeSteps, fetchSubtaskSteps
- subtask card accumulates live steps and backfills on expand
- carry run_id onto history content messages for the events endpoint
* fix(subagents): show AI turns in subtask card + paginate step backfill (#3779)
Two follow-ups to the subagent step-history feature:
Problem 1 — reload backfill could silently truncate the step timeline because
list_events capped at 500 events (seq-ASC) across the whole run. Add task_id
filtering + an after_seq forward cursor to list_events (all three stores +
abstract base + the /events route), and make fetchSubtaskSteps page through one
task's subagent.step events until a short page. No schema migration: the DB
filter rides the existing run-scoped index via event_metadata["task_id"].
Problem 2 — the card only rendered tool steps, so persisted AI turns were never
shown. Replace toolStepsForDisplay with stepsForDisplay: interleave AI reasoning
turns (with text) and tool steps by message_index, drop blank-text AI turns, and
drop the trailing final-answer AI turn when completed (already shown as result).
Card renders AI steps as muted clamped markdown with a sparkles icon.
Tests: store task_id/after_seq filtering + pagination across memory/db/jsonl,
the /events route forwarding, stepsForDisplay rules, and fetchSubtaskSteps
pagination. Docs updated in both AGENTS.md.
* make format
* fix(subagents): capture full multi-tool step tail, batch step persistence, cap tool-call args (#3779)
Address PR review findings on the subagent step-history feature:
1. executor.py streamed on stream_mode="values" and captured only
messages[-1] per chunk, so a multi-tool-call turn (ToolNode appends
one ToolMessage per call in a single super-step) lost all but the last
tool output in both the live task_running stream and the persisted
history. Replace with capture_new_step_messages, which walks the
newly-appended tail (and still re-checks the trailing message on
no-growth chunks so id-less in-place replacements survive).
2. worker.py persisted each step with the store's low-frequency put()
(a per-thread advisory lock per call); a deep subagent (max_turns=150)
emits hundreds of steps on the hot stream loop. Replace with
_SubagentEventBuffer, which batches via put_batch (flush on terminal
subagent.end, at FLUSH_THRESHOLD, and in the worker finally).
3. build_subagent_step capped only text; tool_calls[].args were copied
verbatim, so a large write_file/bash payload produced an unbounded
subagent.step row. Cap each call's serialized args at
SUBAGENT_STEP_MAX_CHARS, flagged args_truncated.
Tests updated/added for all three; AGENTS.md refreshed.
* fix(subagents): merge backfill into latest subtask state; reuse message_content_to_text (#3779)
Address the remaining two PR review findings:
4. subtask-card's fetchSubtaskSteps().then(updateSubtask) closed over a
stale tasks snapshot: a late-resolving backfill wrote setTasks({...stale}),
clobbering SSE steps/status and sibling subtasks that arrived during the
fetch. useUpdateSubtask now reads/writes through a tasksRef mirroring the
latest state (ref-to-latest), and the pure per-subtask transition is
extracted to core/tasks/subtask-update.ts::computeNextSubtask (unit-tested).
5. step_events._content_to_text duplicated deerflow.utils.messages.
message_content_to_text; call the shared helper instead (guarding None
content with 'or ""' so a tool-call-only turn still renders as "").
Tests added for computeNextSubtask and the None-content case; AGENTS.md docs updated.
* fix(frontend): improve chat math rendering
* fix(frontend): refine math rendering stability
* fix(frontend): address review feedback on math preprocessing
- Fix escaped-backslash blind spot: consume \\\\ as a unit so \\( and
\\[ are not mis-interpreted as math delimiters when the backslash
itself is escaped.
- Thread inInlineCode state across lines so multi-line backtick code
spans are protected from delimiter conversion.
- Remove double math normalization: preprocessStreamdownMarkdown now
only handles Mermaid; math normalization lives solely in
ClipboardSafeStreamdown, preventing non-idempotent double passes.
- Wire parseIncompleteMarkdown to isLoading in MarkdownContent so
Streamdown's streaming-incomplete-math handling is actually active
during streaming.
* fix(frontend): address streamdown math review issues
* refactor(frontend): move streamdown preprocessing out of ai elements
