* fix(runtime): prevent IndexError in MemoryStreamBridge._make_gap on empty events buffer
* fix(runtime): handle empty stream replay gap bounds across backend and frontend
- Clamp MemoryStreamBridge queue_maxsize at 1 and validate StreamBridgeConfig.queue_maxsize >= 1
- Update StreamGap docstring to clarify None retained bounds
- Allow StreamReplayGapData and parseStreamReplayGap in frontend to accept string | null bounds, safely resuming when bounds are null
- Add backend and frontend regression unit tests for queue clamping and null bounds replay gap
* docs(stream-bridge): bump config_version and document empty buffer replay gap behavior
* docs: document nullable gap bounds and sync helm config_version to 37
* feat(frontend): render markdown artifacts in the new window
The artifacts panel's "open in new window" action handed the browser the
raw Gateway response. For markdown that is a `text/markdown` body the
browser can only show as source, so the new window was a text dump rather
than a reader.
Route markdown artifacts to a new `/artifacts/view` page that renders them
with the same components the panel uses (SafeStreamdown + the artifact
rehype chain + citation links/panel), including the truncated-preview
banner and its "load full file" action. Everything else keeps the raw
Gateway URL — notably HTML/SVG, which the Gateway deliberately serves as a
download so active content never executes in the application origin.
- `core/artifacts/viewer.ts` centralizes which stored artifacts are
markdown (`.skill` archives included, since they hold a SKILL.md), so
the panel and the viewer route cannot drift.
- `ArtifactFilePreview` and its siblings move out of
`artifact-file-detail.tsx` into `artifact-file-preview.tsx`; otherwise
the standalone route would pull the CodeMirror editor into its bundle.
- The window title comes from the route's `generateMetadata`, not
`document.title`, which the App Router overwrites after hydration.
- The viewer reads content through `useStandaloneArtifactContent`, which
shares `useArtifactContent`'s query key but not its `useThread`
dependency, since a detached window has no thread context.
Claude-Session: https://claude.ai/code/session_013AiCrC5SBc3HdFYNxsp1EC
* fix(frontend): keep the artifact target across re-authentication
Review found the standalone viewer unrecoverable from an expired session.
The window's target lives entirely in `?path=...&thread_id=...`, and both
auth paths dropped it:
- The layout guard redirected to `/login` with no `next` at all. A layout
cannot read `searchParams`, so the guard moves into the page, which can
— and rebuilds the full viewer address for `next`. The layout loses its
AuthProvider along the way: nothing under this route reads `useAuth`,
and the guard now makes a single `getServerSideUser` call per request.
- The shared fetch wrapper built `next` from `window.location.pathname`,
which silently truncated the query string. It now carries `search` too,
so any route holding state in the query survives a 401, not just this
one. `validateAuthNextPath` already accepts a query string.
`buildArtifactViewerURL` is split out of `resolveArtifactOpenURL`: the
guard needs the route itself, never the Gateway fallback that the latter
takes for non-markdown targets.
Tests: the login round trip (unit — the rebuilt URL survives
`validateAuthNextPath` and parses back to the same target), the fetch
wrapper preserving the query on 401 (unit), and the expired-session
window reaching `/login` with the artifact intact (E2E). The E2E asserts
on the popup's navigation *requests*, since `(auth)/layout` answers
`/login` with a server redirect under DEER_FLOW_AUTH_DISABLED and no
navigation commits.
`tests/unit/core/models/api.test.ts` stubbed `window.location` without
`search`; a real Location always has it.
Claude-Session: https://claude.ai/code/session_013AiCrC5SBc3HdFYNxsp1EC
* fix(frontend): keep public showcase artifacts out of the auth gate
Review found that the viewer's access check regressed `/showcase`. Those
pages render with `isMock`, their artifacts are served by the
unauthenticated demo route, and the raw artifact URL this window replaced
stayed public — so gating the window unconditionally bounced every
logged-out showcase visitor to /login for a document that is already
public.
`requiresAuthenticatedViewer` exempts a mock target only when
`resolveStaticDemoArtifact` would actually serve it. The allowlist is the
authority rather than the flag: `mock=true` is caller-supplied, so a
target the demo route answers with 404 — a non-allowlisted path, or a
thread that is not a demo thread — still needs a session.
Covered in `tests/e2e-auth/`, since the default E2E config disables auth
and cannot see this: a public showcase artifact renders without a
session, while a non-allowlisted path and a missing mock flag both land
on /login. Verified the positive case goes red without the exemption.
Claude-Session: https://claude.ai/code/session_013AiCrC5SBc3HdFYNxsp1EC
Add deerflow.community.serply.tools:web_search_tool, a Google SERP
provider for the web_search slot that also covers Google News and Google
Scholar through an optional `vertical` config option. Reads the key from
api_key in config.yaml or SERPLY_API_KEY, clamps max_results to Serply's
1-100 range, and returns the same structured JSON errors as the Serper
and Brave tools.
Register the provider in config.example.yaml, scripts/doctor.py,
scripts/wizard/providers.py, .env.example, backend/docs/CONFIGURATION.md,
the en/zh tools.mdx provider tabs, and tools/AGENTS.md. Tests mock httpx.
* feat(mcp): map request-scoped secrets to HTTP/SSE headers
`user_auth` binds a credential to a configured DeerFlow user, so a caller
that picks the credential per request — a multi-tenant gateway, a per-run
API key, one shared MCP server fronting several environments — had to
register one MCP server entry per credential.
Add a declarative `mcpServers.<server>.headers_from_context` block mapping
HTTP header names to keys of the run request's `config.context.secrets`
carrier. A new built-in interceptor resolves the mapping on every tool call
and rewrites those headers, mirroring `user_scoped_auth`. The config file
stores names only, never a credential, so the Gateway returns the block
unmasked.
Registered after OAuth and `user_auth` in the interceptor chain: the later
interceptor runs closer to the transport, and the value chosen for this one
request is the most specific, so it wins. Fail-closed by default — a mapped
key missing from the request raises a `ToolException` naming only that key,
because falling back to the server's discovery credential would send one
tenant's call under another tenant's authority. `on_missing: "passthrough"`
opts out.
Durable background tasks are excluded: `McpTaskToolCaller` drives status and
cancel polls after the Agent run ends, where no run context exists, so the
fail-closed interceptor would deny every poll. Those calls keep using
server-level credentials, and a server declaring both `headers_from_context`
and `task_toolsets` now logs a warning.
Also corrects the custom-interceptor example in docs/MCP_SERVER.md (and the
matching claim in skills/AGENTS.md), which read request secrets from
`langgraph.config.get_config()["context"]`. That key is `None` inside a tool
call — the run context rides the LangGraph runtime, not the RunnableConfig
propagated to child runnables — so interceptors written from that example
never saw a value. The example now reads `request.runtime`, and
tests/test_mcp_context_headers.py pins LangGraph's runtime-injection rule by
driving a real langchain-mcp-adapters tool through a real graph with the
ambient-runtime fallback disabled.
Closes#5005
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(mcp): resolve credential headers case-insensitively, carry them on durable submit
Review follow-ups on `headers_from_context`.
HTTP field names are case-insensitive, but every dict on the path to the wire
is not: `build_server_params` copies the operator's static `headers` spelling
verbatim, and langchain-mcp-adapters merges interceptor overrides into the
connection with a plain `{**connection_headers, **override_headers}` splat. A
static `authorization` and an injected `Authorization` therefore both reached
httpx as separate field lines, and a server reading the field with a
single-value accessor got the static discovery credential — inverting the
documented `headers` < `oauth` < `user_auth` < `headers_from_context`
precedence and running a per-request call under the shared credential.
Normalizing inside the interceptor cannot fix that on its own: the adapter
builds the request with `headers=None`, so an interceptor never sees the
connection's static headers and cannot displace them however it spells its own
key. A new `mcp/headers.py::apply_header_overrides` therefore drops any key
differing only in case and emits the spelling the connection already uses.
Applied to `headers_from_context`, `user_auth`, the OAuth interceptor, the
OAuth discovery-header write, and the durable-task connection merge, which all
carried the same collision. `headers_from_context.headers` now also rejects one
header mapped under two spellings at config load, in both the harness model and
the Gateway mirror.
Durable submit now carries the mapped headers, as docs/MCP_SERVER.md already
promised. `McpTaskToolCaller` disabled the interceptor for the whole caller, but
that caller serves submit as well as the polls, and submit is awaited inline
inside the Agent's tool call — where the run's LangGraph runtime is still the
ambient contextvar, so no secret has to be threaded through `TaskSubmitRequest`
or reach durable storage. The caller builds one chain and keeps a second view of
it without the context-headers interceptor; `call_tool` takes
`request_scoped_headers`, set only by `OrdinaryMcpTaskDriver.submit`. Status and
cancel keep server-level credentials, so background polls still cannot fail
closed, and the startup warning now describes the half it actually covers.
`_merge_preserving_secrets` restores masked extras inside `headers_from_context`
instead of writing the `***` sentinel back over the stored value, matching the
treatment `user_auth` extras and server-level extras already get; extras a PUT
omits carry over as well, while the declared mapping still replaces verbatim so
a round trip can remove an entry. `extra="allow"` plus name-based sensitivity
detection means the usual casualty is a name-valued key such as `tokenHeader`,
not only a credential.
The existing override test seeded the static header onto `request.headers`,
which production never does, so it modelled a merge that really happens one
layer down; the new tests drive a real adapter tool through a real connection
and assert on the headers the session is opened with, and the durable-submit
test runs through a real tool node with no runtime patching.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(mcp): reject case-insensitive duplicate static header names
* fix(mcp): preserve omitted headers_from_context fields on partial updates
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
* fix(frontend): restore sanitization in custom streamdown rehype chains
Streamdown 2.5 replaces its entire default rehype chain
[rehype-raw, rehype-sanitize, rehype-harden] with whatever array the
caller passes via the rehypePlugins prop. Every custom chain in this
repo therefore rendered LLM/stored markdown without any sanitization:
- Artifact markdown previews (markdown-preview-plugins.ts +
artifact-file-detail.tsx) parse raw HTML via rehypeRaw, so a
generated .md artifact could inject <style>/<iframe>/on* handlers
into the workspace DOM (stored XSS; only javascript: anchors were
blocked by the ArtifactLink component).
- The memory settings summary (memory-settings-page.tsx) spread the
shared preset without component overrides, so a hostile
<a href="javascript:..."> in stored memory content rendered as a
clickable anchor.
Fix strategy:
- Add rehype-sanitize (already resolved in the lockfile via streamdown)
as a direct dependency and re-insert a [rehypeSanitize, schema] step
in the shared preset (core/streamdown/plugins.ts). It runs after
rehypeRaw (raw HTML must be parsed into hast before it can be
cleaned) and before rehypeKatex/rehypeSlug (their output is trusted
and would otherwise be filtered or clobbered) - the same
raw -> sanitize -> math ordering streamdown itself uses.
- The schema extends rehype-sanitize's GitHub-style defaultSchema (the
base of streamdown's own sanitize schema) so legitimate authored
artifact HTML (tables, details, images, alignment/size attributes)
keeps working while script/iframe/style, on* handlers and
non-allow-listed URL schemes (javascript:, data:, ...) are dropped.
The only extensions are tel: hrefs and the math-inline/math-display
class markers remark-math emits and rehype-katex detects.
- Position rehypeSlug after the sanitize step in the artifact chain so
sanitize's id clobbering (id="x" -> id="user-content-x") cannot break
the heading anchors it creates.
- Pass a: createMarkdownLinkComponent() on the memory settings page as
defense in depth, matching the chat rendering path.
Unit tests feed a hostile payload (<a href="javascript:...">,
<img onerror>, <script>, <iframe>, <style>, ontoggle) through both
render paths and assert no executable/clickable equivalent survives,
plus regression guards for heading anchors, legitimate HTML and KaTeX
math rendering.
* fix(frontend): keep the sanitize clobber prefix on heading anchors; minimal lockfile
Review follow-ups on the sanitization change:
- Heading anchors: rehypeScopedSlug replaces rehype-slug in the artifact
chain. It runs after the sanitize step (so raw-HTML headings are also
anchored) but keeps rehype-sanitize's user-content- id prefix — an
untrusted heading like "## current" cannot mint an unprefixed
id="current" (the DOM-clobbering shape the sanitizer guards against).
In-page fragment links are translated to the prefixed anchors so they
still resolve; external URLs, bare "#", already-prefixed fragments and
sanitize-prefixed raw-HTML ids are left untouched.
- Lockfile: regenerated as a minimal diff — only the two direct-dependency
importer entries (rehype-sanitize, github-slugger for the scoped slug)
are added; the libc platform selectors on the 64 native package records
are preserved byte-for-byte instead of being dropped by lockfile
normalization.
Full frontend suite: 1034 tests passing; tsc and prettier clean.
* style: reorder github-slugger import ahead of the hast type import
* test(e2e): expect the clobber-prefixed heading anchor in artifact preview
The scoped slug plugin gives generated heading ids rehype-sanitize's
user-content- prefix and translates fragment links to match, so the
anchor-scroll test must locate the prefixed id.
* fix(frontend): reset the scoped slugger per tree; keep footnote anchors single-prefixed
Review follow-ups:
- The scoped slug attacher holds one GithubSlugger, but streamdown
caches the unified processor by plugin name, so the instance survived
across parses and repeated renders of the same heading grew -1/-2
suffixes (the artifact-anchor e2e could not find the id on re-render).
The transformer now resets the slugger per tree, as rehype-slug does;
a regression test renders identical artifact markdown twice.
- remark-rehype emits GFM footnote anchors already clobber-prefixed
(user-content-fn-1); the sanitize step prefixed those ids again while
their hrefs stayed single-prefixed, breaking footnote navigation in
every chain built on the shared preset. A new rehypeClobberFragments
step runs right after sanitize: double-prefixed ids are normalized
back to one prefix, and unprefixed fragment hrefs are translated to
the prefixed form (already-prefixed and external links untouched).
The artifact slug now inserts after this step; covered by a footnote
regression test on the shared render path.
Unit suite 1036 passing; artifact-preview e2e verified locally
(9/9, including the heading-anchor scroll test).
* fix: DeerFlow brand casing in disclaimer, 'What's New' title, setup-sandbox .PHONY
- en-US disclaimer said 'Deerflow'; every other user-facing string
brands it 'DeerFlow' (rendered under the chat composer)
- landing section title 'Whats New in DeerFlow 2.0' -> 'What's New'
- setup-sandbox was the only Makefile target missing from .PHONY
* test: align disclaimer assertions with DeerFlow brand casing
The unit and e2e suites still expected the old "Deerflow" spelling in
inputBox.disclaimer; update both to the corrected locale string so the
i18n load test and the chat footer assertion pass again.
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(artifacts): serve SHA-256 via ETag so preview/edit work on non-secure contexts
crypto.subtle is only available in secure contexts (HTTPS or localhost). The frontend fell back to it to compute an artifact's SHA-256 when the Gateway did not return one, which threw on http://<lan-ip>:<port> and broke both artifact preview and inline editing (issue #4864).
- Gateway now returns the real SHA-256 as an ETag header for inline text and active-content artifact responses (and skill-archive members).
- Frontend prefers the ETag and only computes a hash as a last resort, falling back gracefully (FNV-1a) instead of throwing when crypto.subtle is missing.
* fix(artifacts): address PR review feedback for #4864
- Cache SHA-256 digests by (path, mtime_ns, size) so the many small Range
requests a browser issues while scrubbing/paginating a preview do not each
re-hash a potentially huge artifact from scratch (performance).
- Gate inline editing on a real 64-hex revision: hasRevision requires
sha256.length === 64, so the FNV-1a fallback on non-secure origins keeps
preview working but no longer 422s on save (contract).
- Anchor and lowercase the ETag regex and accept the weak W/ prefix gzip
emits, so uppercase hex and longer digests (sha-384/512) can't masquerade
as sha-256.
- Cover the forced-download ETag on the backend and add frontend tests for
weak-ETag parsing and the non-secure-context FNV fallback.
Feedback from reviewer willem-bd on PR #4865.
* style: fix ruff format and prettier issues
- test_artifacts_router.py: collapse two over-split client.get() calls to
satisfy ruff format (line-length 240)
- loader.ts / artifact-file-detail.tsx / loader.test.ts: apply prettier
formatting and restore LF line endings
* style: fix ruff format and prettier issues
- test_artifacts_router.py: collapse two over-split client.get() calls to
satisfy ruff format (line-length 240)
- loader.ts / artifact-file-detail.tsx / loader.test.ts: apply prettier
formatting and restore LF line endings
* style: fix ruff format and prettier issues
- test_artifacts_router.py: collapse two over-split client.get() calls to
satisfy ruff format (line-length 240)
- loader.ts / artifact-file-detail.tsx / loader.test.ts: apply prettier
formatting and restore LF line endings
* style: fix ruff format and prettier issues
- test_artifacts_router.py: collapse two over-split client.get() calls to
satisfy ruff format (line-length 240)
- loader.ts / artifact-file-detail.tsx / loader.test.ts: apply prettier
formatting and restore LF line endings
* style: reformat artifact-file-detail.tsx for prettier with tailwind class ordering
* fix: invalidate SHA-256 cache after artifact edit
Clear the LRU cache after os.replace() so the next preview request
computes the new digest. Edits are rare, so clearing the whole
256-entry cache costs nothing (addressing PR review comment #5).
* fix(artifacts): skip ETag for oversized files + CRLF->LF + cache invalidation (#4865)
* fix(loader): use real empty-content SHA-256 for empty 416 range (#4865)
* test(artifacts): assert oversized artifacts carry no SHA-256 ETag (#4865)
* style(frontend): format long sha256 constant (prettier)
* test(backend): fix oversized-artifact ETag assertions and formatting (ruff)
* test(backend): keep oversized-payload line within ruff 240-col config
* feat(mcp): per-user credential injection for shared MCP servers
A single HTTP/SSE MCP server entry can now serve several users, each
authenticated to the remote service with their own credential. A server
opts in with a user_auth block mapping user ids to credential header
values ($ENV_VAR references supported):
"user_auth": {
"header": "Authorization",
"users": { "<user-id>": "$SERVICE_TOKEN_ALICE" }
}
The built-in user-scoped auth interceptor resolves the authenticated
runtime user on every tool call (request runtime -> ambient LangGraph
runtime -> auth config -> request-scoped user ContextVar) and rewrites
the configured header via request.override(), the same per-call
mechanism as the OAuth interceptor. It registers after OAuth in the
shared assembly so its per-user value wins the header when a server
declares both. The entry's static headers are used only for startup
tool discovery.
Fail-closed by default: an unmapped user - including the anonymous
default-user fallback - or a credential whose env reference resolved
empty gets an actionable ToolException instead of another user's
credential; on_missing: "passthrough" opts out per server. Combined
with the existing per-(user, thread) MCP session scoping this gives
credential isolation on shared servers.
Gateway API: user_auth.users values are masked in GET responses, and
PUT round-trips preserve stored credentials for masked values (same
contract as env/headers/oauth secrets); a masked value for a user id
not already stored is rejected.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(mcp): address review — preserve stored user_auth sub-fields on partial PUT, warn-and-skip stdio, allow extras
Review findings from #4868:
1. A partial user_auth payload (e.g. {"enabled": false}) merged to
users={} and default on_missing, irreversibly wiping stored
credentials on PUT. The merge is now sub-field-aware via
model_fields_set — omitted sub-fields carry the stored values, an
explicitly sent users map still replaces (so full-round-trip removal
works), masked values still swap back for stored credentials.
2. user_auth on a stdio server was a silent no-op: rewritten headers go
to call meta, never a transport header, while deny errors still fired.
The interceptor builder now warns and skips non-sse/http servers,
matching the tool_call_timeout transport-mismatch convention.
3. McpUserScopedAuthConfigResponse now allows extra keys like the
harness-side model, and extras survive masking and merge, matching
the server-level model_extra handling.
Adds four regression tests (partial-PUT preservation, explicit-map
replacement, extras round-trip, stdio warn-and-skip).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(mcp): reject blank user_auth.header at the gateway
A blank header passed the gateway response model, was persisted, then
failed the harness-side ExtensionsConfig validator on reload — the PUT
returned 500 after the write and every later config load/startup failed
until the file was hand-edited. Mirror the harness non-blank validator
on McpUserScopedAuthConfigResponse so the PUT fails with 422 before
anything is written.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* style: ruff format extensions_config.py
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(mcp): harden the trust chain and masking around user-scoped credential selection
Address review round 4:
- Scrub client-supplied user_id from run context/configurable for
external callers in inject_authenticated_user_context, before every
early return, and restamp only from request.state.user. Now that
user_id selects which user's credential user-scoped MCP auth injects,
a forged value must not survive any future path that skips the
restamp. Internal callers (IM channels, scheduler) keep supplying
end-user identity as before (PR #3294 contract). Regression tests pin
both the scrub and that a forged body.context.user_id can never
resolve as another user through merge + inject ordering.
- Include the caller's own resolved user id in the fail-closed deny
message so operators can copy the exact users key (it differs by
deployment path), and document the key formats in the mcp.mdx doc.
- Mask sensitive extra keys inside user_auth on GET like server-level
extras, and swap masked sentinels back for stored values on PUT via
_merge_extra_value_preserving_masked.
- Extract the interceptor wrap loop into compose_tool_interceptors and
pin the security property functionally: an OAuth interceptor that
actually sets Authorization loses the final header to the per-user
credential through the same composition the session-pool path uses.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* docs: govern agent guidance size
* refactor: split agent guidance by code scope
* Clarify virtual path handling in AGENTS.md
Updated the translation section to clarify the role of `LocalSandboxProvider` and the handling of virtual paths in the tool layer.
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(frontend): restore user message above same-run steps after mid-run reload
After a mid-run page reload, replayed messages-tuple steps can reach the
merged list before the turn's human message (the retained replay buffer
may have dropped it), and the live-only human is woven in before the next
shared history anchor. The steps panel then renders above the user
message it belongs to and the per-turn token row splits one run in two.
restoreLocalTurnMessageOrder only covers the locally submitted turn, so
add restoreReconnectedTurnMessageOrder for the reconnected path: a
visible AI/tool step above the last visible human is provably misplaced
when the same run also appears below the human (canonical history is
seq-sorted), or when the step is run_id-less (live-only) and a
run_id-less step follows the human. Pagination orphans from older turns
(#4399) and resent turns after an interrupted run fail both checks and
keep their position.
* fix(frontend): never move a completed turn's terminal answer below the next human
Branch-seeded threads and mocked feeds can share one run_id across turns,
so the same-run sandwich check alone misfired on completed multi-turn
history: a previous turn's final answer was pulled below the next user
message, stripping the turn of its branchable assistant group (e2e
branch-thread.spec.ts).
Only steps after the last terminal assistant answer (visible content, no
tool calls) in the segment are now candidates for reordering. A
still-streaming text step can look like a terminal answer until its tool
call arrives (#4304); it then stays above the human until canonical
history heals the order — an accepted transient, far safer than moving a
completed answer.
Two related fixes in the reasoning extraction path of
core/messages/utils.ts:
1. splitInlineReasoning's first pass stripped every closed
<think>...</think> pair unconditionally, so a message that discusses
the tag literally in markdown inline code (e.g. "Wrap your reasoning
in `<think>...</think>`") had its code span hollowed out and the
inner text shipped to the Reasoning panel. The streaming pass already
guards backtick-adjacent openers; apply the same guard to the
closed-pair pass so both passes agree on what counts as literal tag
talk.
2. getAssistantTurnCopyData fell back to reasoning via
`content ?? reasoning`, but extractContentFromMessage never returns
null, so the fallback was dead code and a reasoning-only turn (e.g.
stopped mid-thinking) rendered no copy button at all - inconsistent
with getMessageCopyData, which does copy reasoning in that case. Use
the same empty-string check it uses.
* feat(frontend): reopen the skill list after a skill is selected
Selecting a skill closed the composer's skill list for good: `/` no longer
reopened it, so a skill could not be looked up or swapped without deleting
the chip first.
The list now reopens from the editable text beside the chip, and picking an
entry swaps the chip rather than stacking a second activation, since the wire
format carries exactly one leading /skill. Builtin commands are withheld in
that state because they own the whole composer line, and Enter navigates the
list before submitting except while an IME is composing.
The trigger is unchanged: a slash still opens the list only at the start of
the input.
* fix(frontend): keep builtin names reserved in the reopened skill list
Withholding the builtin list from getMatchingSkillSuggestions in chip mode
also disabled the reserved-name filter it drives, so a custom skill named
after a builtin command became selectable there. Nothing rejects such a name
at install time, and submitting the resulting chip runs the command instead
of the skill.
Pass the builtin list as before and drop the builtin entries from the result
instead. The new regression covers both sides of the reservation, and the
reopen test now waits for the list before pressing Enter.
* fix(frontend): hide skills the slash parsers refuse from the picker
The composer picker reserved only the two builtin command names, while both
slash parsers refuse the seven names in the shared contract. A skill named
bootstrap, help, memory, models, new or status was therefore offered, could
be selected into a chip, and submitted — and then activated nothing, because
parse_slash_skill_reference drops the name on the way in. The turn reached
the model as literal text with no skill loaded and no error anywhere.
Reserve the contract names alongside the builtin ones, so the picker cannot
offer what the parsers will not honour.
* fix(frontend): hide stale follow-up chips while a turn is streaming (#3395)
Follow-up suggestion chips are generated when a turn finishes streaming,
but `showFollowups` did not exclude the streaming state. If a user sent a
new message before the previous response finished, the old chips (and the
lone close button) stayed mounted and overlapped the To-dos panel and the
input box.
Gate `showFollowups` on `status !== "streaming"` so stale chips are never
shown while a response is in progress.
* fix(frontend): suppress follow-up suggestions for user-interrupted turns (#3395)
Gating showFollowups on status alone was not enough: stopping a streaming
turn (or sending a new message mid-stream, which also stops it) flips
status back to a non-streaming state and triggers the follow-up generation
effect on that streaming->ready transition, producing chips for a
half-finished, interrupted response.
Track user interruption with a ref set in the stop path, and have the
generation effect skip that transition (and clear/hide any pending chips),
so follow-ups are only generated for turns that finished on their own.
appendHtmlPreviewBaseHref detected the head tag with /<head[^>]*>/i,
which also matches <header ...>. For a fragment with no <head> that
opens with <header> - a common shape in agent-generated report pages -
the <base> element was injected after the <header> opening tag instead
of being prepended, so relative assets appearing before that point
(e.g. a leading <img>) resolved without the base and failed to load in
the sandboxed iframe.
Use the word-boundary-safe /<head(?:\s[^>]*)?>/i that the sibling
appendHtmlPreviewScrollRestoration already uses, keeping the two
injectors consistent.
* feat(artifacts): inline editing for text artifacts in the panel
Add a PUT /api/threads/{id}/artifacts/{path} endpoint that atomically
replaces an existing UTF-8 text file under /mnt/user-data/outputs after
verifying its SHA-256 revision. Active runs conflict (409); binary,
symlink, oversized, and non-output paths are rejected.
Frontend: edit/save/discard buttons, draft state with conflict detection,
CodeEditor onChange/onSave, loader SHA-256 from ETag, i18n, beforeunload guard.
Backend: PUT endpoint with thread reservation, atomic temp-file replacement,
sandbox sync for non-mounted providers, rollback on failure, ETag on GET.
Tests: 8 backend + 1 blocking-IO + 3 frontend test files.
* fix(artifacts): scope replacement permissions and release sandboxes
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* feat: show real-time context window usage in chat UI (#3125)
Adds a `context_usage` block to `GET /api/threads/{id}/token-usage`
(token count from the live checkpoint, the thread model's
`context_window`, and a percentage), introduces a new
`ModelConfig.context_window` distinct from the per-call `max_tokens`
output cap, and surfaces the percentage in the chat header — inside
`TokenUsageIndicator` when token-usage tracking is on, or as a
standalone badge when it's off so context capacity stays visible
independent of cost tracking.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat: per-category breakdown for context window usage
Replace the single-number context_usage payload with a Claude-Code-style
breakdown — messages, system prompt, skills, system/MCP tools (active +
deferred), custom agents, memory injection, autocompact buffer, and free
space — and surface it in the chat UI with a segmented progress bar and
per-row table.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(config): document context_window across model examples
Add `context_window` to every example model in config.example.yaml so the
new chat-UI "% context used" indicator works out of the box for whichever
example a user adopts. Each value is the published default at the time of
writing; users are pointed at the official model spec to verify. Bumps
config_version to 11 so `make config-upgrade` flags outdated user configs.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* style: ruff format (line-length 240)
No behavior change — collapses two multi-line expressions that fit on
one line under the project's 240-char limit. Picked up by `make format`.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* review: address Copilot bot comments on #3183
- token-usage-indicator: switch `{contextPercentage && (...)}` to an
explicit `!= null` check. (The string `"0"` is actually truthy in JS so
the original code wasn't buggy, but the explicit check is clearer.)
- context-usage-breakdown: drop the `useMemo` around segments/totals — the
computation is O(n) over a handful of rows and the previous memo deps
omitted `t.contextUsage.categories`, so the bar's tooltips/aria-labels
could stay in the old language after a locale switch.
- context_usage._split_tools: snapshot MCP names from
`get_cached_mcp_tools()` directly instead of re-reading
`extensions_config.json` after `get_available_tools()` already loaded
it. Removes redundant file I/O on every `/token-usage` poll.
(`get_available_tools()` still emits its own INFO logs — silencing
those is out of scope here.)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* style(frontend): prettier --write context-usage-breakdown
CI's `pnpm format` (prettier --check) caught two lines previously
formatted by hand. Collapses one comma to fit on one line; no behavior
change.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(gateway): correct context-usage breakdown + add exact token counting
The context-usage indicator shipped two bugs that silently zeroed whole
breakdown rows (both caught by try/except, so the feature looked alive but
produced wrong numbers):
1. _count_system_prompt passed app_config= to get_deferred_tools_prompt_section,
which only accepts deferred_names -> TypeError swallowed -> system_prompt
row always 0, and used_tokens/percentage undercounted by the full prompt.
Also subtracted the deferred section twice (the rendered prompt already
excluded it). Fix: derive deferred names deterministically and pass them to
apply_prompt_template; drop the redundant subtraction.
2. _split_tools imported a non-existent get_deferred_registry -> ImportError
swallowed -> all four tool-category rows always 0. Fix: classify via the
public is_mcp_tool predicate + tool_search.enabled (mirrors
build_deferred_tool_setup); the MCP tag is set by get_available_tools.
Added token_usage.counting (approximate|exact). 'exact' routes text/schema/
message counting through the model tokenizer (tiktoken cl100k_base) via the
existing memory-module machinery (lazy load + cache + cooldown + CJK-aware
fallback), so CJK-heavy threads stop being undercounted by chars//4.
Regression + e2e tests added; 6621 backend tests pass.
* fix(gateway): harden context usage accounting
* fix(gateway): count promoted MCP tools as active in context usage
Promoted tools (deferred MCP tools the thread has fetched via tool_search)
have their full schema bound on every subsequent turn by
DeferredToolFilterMiddleware, so they consume context like any active tool.
The breakdown previously left them in the reserved *_deferred rows, under-
counting the thread's used_tokens.
Classification now treats a tool as deferred only when tool_search is enabled,
it is MCP-sourced, AND it has not been promoted. The promoted set is read from
the checkpoint's channel_values and scoped by catalog hash — matching the
runtime middleware, so a stale promotion from MCP-config drift cannot inflate
the active count.
The static system prompt still lists all deferred tool names (promotions only
affect schema binding, not the prompt), so _count_system_prompt's deferred
rendering is intentionally left unchanged.
8 new tests cover classification, catalog-hash scoping (match / drift /
compute-failure / malformed), and checkpoint extraction.
* fix(context): address review feedback
* fix(context): count structured message payloads
* fix(context): harden usage accounting
* fix(config): bump schema for context usage fields
* refactor: narrow context usage to core indicator
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
parseUploadedFiles stopped the filename capture at the first "("
([^\n(]+), so an entry like "- photo (1).png (12.3 KB)" failed to
match and the file silently disappeared from the message's file chips.
Browsers produce such names for duplicate downloads, making this a
common real-world shape.
Anchor the size group on the "(<number> <unit>)" pair the backend
emits (uploads_middleware formats sizes as "%.1f KB"/"%.1f MB") and
let the filename match greedily up to it, so parenthesized filenames
parse correctly.
* fix(frontend): refresh active artifact content
* fix(frontend): remove 1Hz polling, keep only final refetch after run
Address review feedback: the 1Hz refetchInterval could poll
indefinitely when a write tool call is left unresolved (abort,
error, or missing ToolMessage). Removing the polling entirely
eliminates this risk while still satisfying the core requirement:
artifact content is refreshed once when the run settles, so edits
are visible without a manual reload.
- Remove refetchInterval / hasActiveWrite logic from hooks.ts
- Delete refresh.ts (hasActiveWriteForArtifact helper)
- Delete refresh.test.ts
* docs: align README and AGENTS.md with settle-time refetch behavior
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.
