The in-product plugin/add-extension help links went through
link.langbot.app/{lang}/docs/plugins, which now 404s (it resolved to the
removed /usage/plugin/plugin-intro path). Point them directly at the
current docs page docs.langbot.app/{lang}/plugin/plugin-intro (verified
200 for zh/en/ja).
The previous truncate/shrink-0 pass only touched leaf nodes, but the
min-content floor was set by two ancestors: the flex-1 left group lacked
min-w-0, and CardHeader is a CSS grid whose implicit single column
defaults to min-content. Constrain both (min-w-0 on the header grid +
explicit grid-cols-[minmax(0,1fr)], min-w-0 on the inner flex groups) so
the provider name / base_url+key subtitle actually truncate instead of
forcing the card — and the whole settings modal — wider than the viewport.
- PanelToolbar: allow wrapping and tighten padding on small screens so the
primary action (e.g. "创建 API 密钥") no longer runs off the dialog edge.
- ProviderCard header: let the provider name truncate and pin the model-count
badge and right-side action group with shrink-0 so credits / + controls stay
inside the card on narrow viewports.
Radix tooltips open on hover/focus only and stay closed on touch input,
so on mobile every hover tooltip was unreachable. Detect coarse/no-hover
pointers via matchMedia and drive the tooltip's open state ourselves so a
tap on the trigger toggles it. Desktop hover/focus behaviour is unchanged
(we only intercept the tap when the device has no hover capability). Fixes
all tooltips app-wide from the shared primitive.
Two unrelated frontend fixes:
- LanguageSelector mounts each time the sidebar account dropdown opens and
unconditionally called i18n.changeLanguage() on mount, emitting a
languageChanged event even when the language was unchanged. That handed
every useTranslation() consumer a fresh `t` reference, re-running effects
keyed on `t` (e.g. the plugins page system-status fetch) and surfacing as
a page "refresh". Guard the call so it only fires on an actual change.
- Plugin logs auto-refresh control changed from a toggle Button to a
Switch + Label; the on/off button i18n keys are replaced by a single
static logsAutoRefresh label across all 8 locales.
Port the Space marketplace recommendation carousel UX into the in-app
add-extension page: a 10s auto-advance driven by a smooth countdown ring
that doubles as a pause/resume toggle, and manual prev/next now reset the
countdown. Adds market.recommendation.{pause,resume} across 8 locales.
Replace fixed grid-cols breakpoints (which forced up to 4 narrow cards on
wide screens) with auto-fill columns and a 24rem minimum card width on
both the main market grid and the featured recommendation rows. The
featured rows already measure real column count via ResizeObserver, so
pagination adapts automatically.
Replace the three-way transport choice (stdio / sse / httpstream) for
connecting LangBot to external MCP servers with two modes: local (stdio)
and remote. Remote servers only require a URL; the runtime auto-detects
the transport (tries Streamable HTTP, falls back to SSE).
- provider/tools/loaders/mcp.py: add _init_remote_server() with
Streamable-HTTP-then-SSE probing; dispatch 'remote' lifecycle, keep
legacy sse/http branches for back-compat
- plugin/connector.py: normalize legacy http/sse marketplace modes to
'remote' on Space install, preserving connection params
- entity/persistence/mcp.py: document mode as stdio, remote (legacy: sse, http)
- alembic 0006: idempotent data migration mapping existing sse/http rows
to remote (downgrade maps back to http)
- api/http/service/mcp.py: stash runtime_info (status + tool list) into
test task metadata before tearing down the temp session
- web: collapse mode dropdown to local/remote, remote renders URL+timeout
only, edit auto-maps legacy sse/http to remote; show tools after test in
create mode from task metadata; remove dead plugins/mcp-server/ tree
- i18n: local/remote labels + mode/url hints across 8 locales
- monitoring: stack filters full-width, scrollable tab bar, reduce card/content padding on mobile
- models dialog: provider form modal no longer overflows viewport on small screens; shared panel body padding shrinks on mobile
- plugin logs: reduce horizontal padding on mobile
* feat(api): support global API key from config.yaml (api.global_api_key)
Accept a config-defined global API key anywhere a web-UI key is accepted
(X-API-Key / Bearer), with no login session and no DB record. Useful for
automated deployments and AI agents (HTTP API + MCP). Defaults to empty
(disabled); does not require the lbk_ prefix.
- templates/config.yaml: add api.global_api_key with security notes
- service/apikey.py: verify_api_key checks global key first (constant-time)
- docs/API_KEY_AUTH.md: document the global key + security guidance
- tests: cover global-key match, prefix-free, fallback-to-db, disabled
* feat(mcp): expose LangBot management as an MCP server at /mcp
Add an MCP (Model Context Protocol) server so external AI agents can manage a
LangBot instance. Reuses the same API-key auth as the HTTP API (including the
config.yaml global API key).
- pkg/api/mcp/server.py: FastMCP server wrapping the service layer; 21 curated
tools across system/bots/pipelines/models/knowledge/mcp-servers/skills
- pkg/api/mcp/mount.py: ASGI dispatcher fronting Quart; authenticates /mcp
requests with an API key, runs the streamable-HTTP session manager lifespan
- controller/main.py: serve the wrapped ASGI app via hypercorn (was run_task)
- web: new 'MCP' tab in the API integration dialog showing endpoint, auth, and
client config; i18n for 8 locales
- tests/manual/mcp_smoke.py: e2e check (401 unauth, list tools, call tools)
Tool surface is intentionally curated (not all ~25 route groups) to keep the
agent surface small, safe, and maintainable. Extend deliberately.
* feat(skills): add in-repo skills/ as the single source of truth
Migrate the agent skills + QA/e2e test harness from the (now archived)
langbot-app/langbot-skills repo into LangBot/skills/, and add four new skills.
Migrated:
- langbot-plugin-dev, langbot-testing (e2e), langbot-env-setup,
langbot-skills-maintenance, langbot-eba-adapter-dev
- the bin/lbs CLI (src/, test/, scripts/, schemas/, qa-agent-docs/)
New:
- langbot-dev core backend + web development
- langbot-deploy Docker/K8s deployment + config.yaml + global API key
- langbot-mcp-ops operating the LangBot MCP server (/mcp)
- langbot-space-ops operating the Space marketplace MCP server
- src/cli.ts repoRoot(): recognize the skills assets root (skills.index.json +
bin/lbs) so the CLI works when nested inside the LangBot repo
- README.md: unified skill catalog; skills.index.json regenerated
Parity with source verified: bin/lbs validate + node test suite match the
source repo (only the uncommitted .lbpkg build-artifact fixture differs).
* docs(agents): document agent-facing surfaces + API/MCP/skills sync rule
* docs(readme): add 'Built for AI Agents' section across all locales
Highlight MCP server, in-repo skills (single source of truth), AGENTS.md
sync rule, and llms.txt. Cross-link LangBot Space MCP marketplace.
* style(mcp): fix ruff format + prettier lint in MCP server and API panel
* style(web): prettier format MCP i18n locale entries
* docs(skills): note MCP instance control in dev/testing skills
All development-guidance skills now point to the LangBot instance MCP
server (/mcp) and the Space marketplace MCP server, reusing API keys.
Make the quick-filter tag pills more compact: h-8 -> h-7, default text
-> text-xs with px-2.5, gap-2 -> gap-1.5, and the selected-X icon
h-3.5 -> h-3. Keeps the single-row horizontal-scroll layout.
With many category tags the quick-filter row used `sm:flex-wrap` on
desktop, so once tags overflowed the available width they wrapped onto a
second, center-aligned line — leaving an orphan tag floating under the
row (looked broken and only gets worse as more tags are added).
Make the row a single, never-wrapping line that scrolls horizontally at
every breakpoint, left-aligned, with the scrollbar hidden and a subtle
right-edge fade to signal there's more to scroll. Adds a reusable
`.scrollbar-hide` utility to global.css.
* feat(box): bidirectional attachment transfer for sandbox
Materialize inbound attachments into the sandbox workspace so agents can
process user-sent files, and collect agent-produced files from the outbox
to attach them back to the reply.
- box(service): add materialize_inbound_attachments / collect_outbound
attachments. Prefer direct host-filesystem read/write on the bind-mounted
workspace (no size limit), falling back to chunked exec only for
non-shared backends (e2b/remote). Clear per-query inbox/outbox dirs at
turn start to avoid query_id-reuse collisions.
- provider(localagent): inject inbound attachment descriptors into the
sandbox and append a system note telling the agent the inbox/outbox paths.
- pipeline(wrapper): collect outbox files on the final stream chunk and
append them as attachment components to the response chain.
- web(debug-dialog): render File components with a download link when
base64/url is present; add base64/path fields to the File entity.
- tests: cover inbound/outbound, large-file transfer without truncation,
and stale-dir clearing (86 passing).
* feat(box): support voice/file attachment round-trip end-to-end
Extends the bidirectional attachment transfer to audio and arbitrary files
through the real webchat UI, and fixes the model-payload errors that
non-image attachments triggered.
- platform(websocket_adapter): resolve Voice/File component storage keys to
base64 (previously only Image), so audio/documents reach the sandbox inbox.
- web(debug-dialog): accept audio/* and any file in the uploader (was
image-only), classify by mimetype, upload Voice/File via the documents
endpoint, and render non-image staged attachments as a chip.
- provider(litellmchat): drop non-image file parts (file_base64 / file_url)
when building the OpenAI/LiteLLM payload. These come from Voice/File
attachments — including ones replayed from conversation history — and the
agent reads their bytes from the sandbox, not the model. Without this the
provider rejects the request: 'invalid content type=file_base64'.
- provider(localagent): also strip those parts from the current user message
alongside the sandbox-path note (model-facing clarity; the requester is the
real safety net for history).
- tests: cover the requester strip/keep behavior (file dropped, image kept and
reshaped to image_url, mixed history, plain-string content).
* test(box): cover inbound/outbound attachment helpers; fix ruff format
- ruff format localagent.py (CI ruff format --check was failing)
- add unit tests for ResponseWrapper outbound-attachment helpers (wrapper.py 78%->98%)
- add unit tests for LocalAgentRunner._inject_inbound_attachments
- add unit tests for WebSocketAdapter._process_image_components (0%->covered)
Lifts PR patch coverage from 68.97% to ~88% (>75% target).
- Add PanelToolbar/PanelBody primitives so all four settings tabs share
the same top-toolbar + scrollable-body rhythm under the unified header.
- API panel: drop the heavy gray shadowed TabsList; move the create
action into the toolbar next to the tabs, lighten per-tab hints.
- Storage panel: reuse PanelToolbar for the generated-at/refresh bar.
- Account panel: wrap content in PanelBody for consistent padding.
- Models panel: keep the pinned LangBot Models (Space) card at the very
top, above the add-custom-provider row (intentional pin), using
PanelBody instead of a top toolbar.
- Add a shared section header (icon + title + description) with right
padding so the dialog close X no longer overlaps panel content, and
every tab now shares the same top layout for a consistent look.
- Shorten inner sidebar nav labels (Models/API/Storage/Account) via new
settingsDialog.nav.* i18n keys across all 8 locales.
- Add common.apiIntegrationDescription and account.settingsDescription
for the new header.
The model-selector in dynamic forms (pipeline / knowledge base settings)
still opened the old standalone ModelsDialog. Point it at the unified
SettingsDialog (section pinned to models) and delete the now-unused
ModelsDialog wrapper so only the new dialog remains.
es-ES pipelines, th-TH bots+pipelines and vi-VN pipelines were left in
English in the sidebar. Translate them: es Flujos, th บอท/ไปป์ไลน์,
vi Quy trình.
Pin the dialog to a fixed 80vh (cap 800px) so switching sections no
longer resizes it; panels scroll their own content internally. Override
the SidebarProvider wrapper's default h-svh with h-full so both columns
fill the dialog height. Narrow the inner settings sidebar to w-44.
Merge API integration, model settings, account settings and storage
analysis into one SettingsDialog with a shadcn inner sidebar for
section switching. Preserve existing ?action= query-param deep links
(showModelSettings / showAccountSettings / showApiIntegrationSettings /
showStorageAnalysis) by mapping each to a section. Extract reusable
panels and keep ModelsDialog as a thin wrapper for the dynamic-form
model picker.
Add a Logs tab beside Documentation on the plugin detail page, showing
the output a plugin prints through the standard Python logger (per the
wiki style guide). Logs are captured from the plugin's stderr by the
plugin runtime and fetched on demand.
- Bump langbot-plugin pin to 0.4.4 (adds GET_PLUGIN_LOGS action)
- plugin_connector/handler: get_plugin_logs RPC client
- HTTP route GET /api/v1/plugins/<author>/<name>/logs (limit + level)
- Frontend: wrap detail right panel in Docs/Logs Tabs; PluginLogs
component with level filter, manual + 3s auto refresh, bottom-follow
- i18n: 7 new keys across all 8 locales
- i18n: add models.searchProviders, monitoring.tabs.tokens and the
monitoring.tokens.* block (incl. bucket.hour/day) to es-ES, ja-JP,
ru-RU, th-TH, vi-VN and zh-Hant, which were missing them and failed
the Check i18n Keys CI.
- api: generate_jwt_token built 'exp' from a naive datetime.now(), which
PyJWT validates against UTC — in any timezone ahead of UTC the token
was already expired at issue time. Use datetime.now(timezone.utc).
* refactor(provider): use LiteLLM as unified LLM requester backend
- Replace 23+ individual requester implementations with unified litellmchat.py
- Add litellm_provider field to 27 YAML manifests for provider routing
- Delete redundant requester subclasses
- Add unit tests for LiteLLMRequester (29 tests)
- Fix num_retries parameter name (was max_retries)
- Fix exception handling order for subclass exceptions
LiteLLM provides unified API for 100+ providers, eliminating need for
provider-specific requesters.
* fix: ruff format provider.py
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* refactor(provider): simplify LiteLLM requester usage handling
- Remove unused Anthropic-specific tool schema generation
- Share completion argument construction between normal and streaming calls
- Use LiteLLM/OpenAI native usage fields for monitoring
- Collect stream token usage from LiteLLM stream_options
- Update LiteLLM requester tests for unified usage fields
* restore: restore deleted provider requester files
Restore individual provider requester implementations that were
removed in de61b5d3. These files coexist with the unified
litellmchat.py backend.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat: update requesters and improve provider selection UI
- Added `litellm_provider` field to various requesters' YAML configurations.
- Removed obsolete Python requester files for OpenRouter, PPIO, QHAIGC, ShengSuanYun, SiliconFlow, Space, TokenPony, VolcArk, and Xai.
- Introduced new requesters for Tencent and Together AI with corresponding YAML configurations and SVG icons.
- Enhanced the ProviderForm component to include a searchable dropdown for selecting providers, improving user experience.
- Updated localization files to include search provider text for both English and Chinese.
* fix(provider): align litellm rebase with master
* fix(provider): capture streaming token usage; add token observability
The LiteLLM streaming requester only captured usage when a chunk had an
empty `choices` list. Many OpenAI-compatible gateways (e.g. new-api) and
providers send the final usage payload in a chunk that still carries an
empty-delta choice, so streamed calls always recorded 0 tokens in the
monitoring logs/dashboard (non-streaming worked).
- Capture stream usage whenever a chunk carries it, regardless of choices
- Add robust _normalize_usage (dict/obj shapes, derive missing total_tokens)
- Register litellm in bootutils/deps.py (was in pyproject only)
- Add MonitoringService.get_token_statistics + /monitoring/token-statistics
endpoint: summary, per-model breakdown, token timeseries, and a
zero-token-success data-quality signal
- Add TokenMonitoring dashboard tab (summary tiles, stacked token chart,
per-model table) + i18n (en/zh)
- Regression tests for stream usage capture and usage normalization
Verified end-to-end against a real OpenAI-compatible endpoint with
gpt-5.5 and claude-opus-4-8: tokens now recorded non-zero for both
streaming and non-streaming paths.
* refactor(provider): simplify litellm capabilities
* style: simplify wrapped expressions
* feat(models): persist context metadata
* fix(provider): handle dict embeddings and openai-compatible rerank in LiteLLMRequester
- invoke_embedding: support both object- and dict-shaped response.data
entries (OpenAI-compatible gateways like new-api return dicts)
- invoke_rerank: litellm.arerank rejects the 'openai' provider, so for
openai-compatible (or unspecified) providers call the standard
Jina/Cohere-style POST /v1/rerank endpoint directly over HTTP
- accept both 'relevance_score' and 'score' fields in rerank results
- add unit tests for the openai-compatible HTTP rerank path
* feat(provider): enforce requester support_type when adding models
- frontend: AddModelPopover only shows model-type tabs (llm/embedding/
rerank) that the provider's requester declares in its manifest
support_type; ModelsDialog fetches requester manifests and maps
requester -> support_type, passed down through ProviderCard
- backend: add _validate_provider_supports guard in create_llm_model /
create_embedding_model / create_rerank_model so a model cannot be
attached to a provider whose requester does not support that type,
even if the frontend restriction is bypassed (manifests without
support_type are allowed for backward compatibility)
- manifests: correct support_type for providers that do not offer all
three model types:
- llm only: anthropic, deepseek, groq, moonshot, openrouter, xai
- llm + text-embedding: openai, gemini, mistral
- add rerank to new-api (verified working via /v1/rerank)
- set llm + text-embedding + rerank for aggregator/unknown gateways
* feat(provider): add searchable alias to requester manifests
- add a free-text 'alias' field to every requester manifest spec,
containing the vendor's English/Chinese names, pinyin, common
nicknames and flagship model-series names (e.g. moonshot -> kimi,
月之暗面; zhipu -> glm, 智谱清言)
- frontend: ProviderForm requester search now also matches against
alias (substring/contains), so searching 'kimi' surfaces Moonshot,
'硅基' surfaces SiliconFlow, etc.
- also fix support_type: openrouter (relay) supports embedding+rerank;
LangBot Space gains rerank (coming soon)
* fix(provider): make support_type guard defensive against incomplete model_mgr
- _validate_provider_supports now uses getattr to gracefully skip when
model_mgr / provider_dict / manifest lookup is unavailable, instead of
raising AttributeError (fixes unit tests that mock ap.model_mgr as a
bare SimpleNamespace)
- add TestValidateProviderSupports covering: allow supported type,
reject unsupported type, allow when support_type missing, allow when
provider unknown, degrade safely when model_mgr is incomplete
* fix(persistence): guard 0004 migration against missing llm_models table
The 0004_add_llm_model_context_length migration called
inspector.get_columns('llm_models') unconditionally, raising
NoSuchTableError when the table does not exist (e.g. migrating a
fresh/empty DB, as exercised by the integration tests where
create_all() registers no tables because the ORM models are not
imported). Every other migration guards with a table-existence check
first; add the same guard here for both upgrade and downgrade.
Also restore the test head assertion to 0004 (it had been lowered to
0003 to mask this failure).
* Merge branch 'master' into feat/litellm
Resolve conflicts:
- uv.lock: regenerated via 'uv lock' to reconcile litellm/fastuuid
(ours) with openai bump (master).
- Alembic migrations: master added 0004_add_mcp_readme while this
branch added 0004_add_llm_model_context_length, both as children of
0003 (would create multiple heads). Re-chain the litellm migration as
0005_add_llm_model_context_length with down_revision=0004_add_mcp_readme
for a single linear head. Update test head assertion accordingly.
* fix(persistence): shorten migration revision id to fit varchar(32)
PostgreSQL stores alembic_version.version_num as varchar(32).
'0005_add_llm_model_context_length' (33 chars) overflowed it, raising
StringDataRightTruncationError in the PG migration tests. Rename the
revision (and file) to '0005_add_llm_context_length' (27 chars) and
update the head assertions in both SQLite and PostgreSQL migration
tests.
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: fdc310 <2213070223@qq.com>
Co-authored-by: RockChinQ <rockchinq@gmail.com>
The MCP detail page invokes testMcp() through an imperative handle
(formRef.current.testMcp()). The handle closure is only refreshed when
[mcpTesting] changes, so testMcp read a stale snapshot of the stdioArgs/
extraArgs React state — on the detail page that snapshot is the empty
initial [], so stdio 'args' were dropped entirely. The sandbox then
launched 'uvx' with no package, which exits 2 and surfaces only an opaque
'Connection closed' with no detail.
Read command/args/env via form.getValues() (kept in sync on every edit and
on load) instead of the captured state, matching how 'command' was already
read. Fixes stdio MCP test failing with empty args on the detail page.
Cloud/NAT deployments couldn't complete WeCom-family / Official Account /
QQ Official setup because the trusted-IP (IP whitelist) value — the
server's egress IPs — was nowhere visible in LangBot.
- config.yaml: new system.outbound_ips list (env: SYSTEM__OUTBOUND_IPS,
comma-separated), exposed via GET /api/v1/system/info
- dynamic form: generic __system.*-named display-only fields resolved
from systemContext (same namespace as show_if), one read-only row per
value with a copy button, excluded from form state and emitted values;
hidden entirely when the deployment provides no IPs
- manifests: trusted-IP display field for wecom, wecomcs, wecombot,
officialaccount, qqofficial
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(box): trust Box-reported skill paths when filesystem is not shared
In separated deployments (Docker Compose, k8s sidecar, --standalone-box,
remote runtime.endpoint) the Box runtime owns its own filesystem, so the
skill package_root it reports via list_skills is not resolvable on the
LangBot side. LangBot's reload_skills and build_skill_extra_mounts
validated those paths with os.path.isdir() against its own filesystem,
which silently dropped every skill in such deployments — breaking the
sandbox skill feature for the nsjail/SaaS backend.
Add BoxService.shares_filesystem_with_box, derived from the connector
transport (stdio = shared, WebSocket = separated), with an explicit
override seam for tests/embedders. Gate both isdir() guards on it: keep
local validation in shared-fs stdio mode, trust Box-reported paths
otherwise. The Box runtime only reports skills found on its own
filesystem, so those paths are valid there by construction.
Adds topology-derivation tests (real connector, no mocks) and
skill-retention tests for both shared and separated filesystems.
* build(docker): ship a self-contained nsjail sandbox backend in the image
Compile nsjail 3.6 from source in a dedicated multi-stage build and carry
only the binary plus its runtime libs (libprotobuf32, libnl-route-3-200)
into the final image. This lets the Box runtime isolate sandboxed code via
nsjail user/mount/pid/net namespaces without a host Docker socket — the
prerequisite for running Box on LangBot Cloud (k8s), where mounting
docker.sock would grant node root and is not acceptable for multi-tenant.
The build toolchain (build-essential/bison/flex/protobuf-dev/libnl-dev)
stays in the nsjail-build stage and is not present in the shipped image.
Verified: image builds (583MB), nsjail --help exits 0, libraries resolve,
and the real NsjailBackend executes an isolated command end-to-end on a
v6.1/cgroup2 host matching LangBot Cloud prod (rlimit fallback path, since
container /sys/fs/cgroup is read-only; PID-namespace isolation confirmed).
* feat(box): SaaS guard to force a single global sandbox scope
Add system.limitation.force_box_session_id_template: when non-empty it
overrides every pipeline's box-session-id-template at resolve time, pinning
all queries to one shared sandbox (e.g. {global}). This is the authoritative,
unbypassable guard — it runs on every exec call, so editing the pipeline
config via API cannot escape it. The web UI locks the Sandbox Scope selector
via a combined box_scope_editable flag (box available AND not forced).
* build(deps): pin langbot-plugin==0.4.2b1 (nsjail cgroup container-safety beta)
* fix(web): show forced sandbox scope + make disabled tooltip tap-friendly
When a SaaS deployment pins every pipeline to a fixed sandbox scope via
system.limitation.force_box_session_id_template, the Sandbox Scope selector was
correctly locked but still displayed the pipeline's stored value (e.g. the
per-chat default), misrepresenting the scope that the runtime actually enforces
on every exec. Coerce the displayed/saved value to the forced template so the
locked selector truthfully shows the active scope (e.g. Global).
Also fix the disabled_tooltip being invisible on touch devices: hover-only Radix
tooltips never open without a pointer, so the explanation of why the field is
locked could not be read on mobile. Wrap the info icon so a tap toggles the
tooltip while desktop hover still works.
* feat(web): hide sidebar new-version prompt for edition=cloud
Cloud instances are upgraded centrally by the operator, so surfacing a GitHub
'new version available' badge to tenants is misleading and actionable only by
the operator. Skip the release check entirely when edition=cloud.
* style(web): prettier formatting for DisabledTooltipIcon ternary
* chore(deps): bump langbot-plugin to 0.4.2b2
Picks up the SDK fix that creates a read-write host_path before the
nsjail bind-mount, fixing the SaaS MCP shared-workspace sandbox failure
(exec exit 255 with empty output when host_path didn't exist).
* chore(deps): bump langbot-plugin to 0.4.2b3
Picks up the nsjail /dev-node fix so stdio MCP servers (uvx-launched) can
start under force_global_sandbox instead of failing with 'Connection closed
/ please check URL'.
* fix(web): show real MCP runtime status on installed extensions list
The installed-extensions list badge keyed solely off the enable flag, so a
server that was still CONNECTING (or in ERROR) was shown as 'Connected'.
Reflect the actual runtime_info.status (connecting/connected/error/disabled)
with matching colors, and poll quietly every 3s while any MCP server is
connecting so the badge transitions without a manual refresh.
* chore(deps): bump langbot-plugin to 0.4.2b4
Picks up the 30s start_managed_process timeout so cold uvx MCP bootstraps
don't get torn down mid-install.
* style(web): satisfy prettier — parenthesize nullish-coalescing in ternary
* fix(mcp): isolate transient test sessions from the shared Box session
A config-page 'test' (server_name='_', no persisted UUID) ran in the same
shared 'mcp-shared' Box session as live MCP servers. A failing test (e.g.
empty args) churned that shared session and tore down healthy, already-
connected servers — leaving them stuck after exhausting their retries.
Mark UUID-less sessions as transient, give them their own isolated Box
session ('mcp-test-<uuid>'), and fully delete that session on cleanup so
tests can never disturb live servers and don't leak sessions.
* fix(mcp): tear down transient test session after test completes
A successful config-page test left its isolated 'mcp-test-<uuid>' Box
session running (the lifecycle task blocks until shutdown). Wrap the
transient test coroutine so it always shuts the session down afterward,
preventing isolated test sessions from leaking.
Detail pages (plugin / MCP / pipeline / knowledge base / skill) only showed
the type in the tab title. Drive the /home document title from HomeLayout,
which has the selected entity name via context: '<entity> · <type> · LangBot'
when a sub-entity is open, '<type> · LangBot' otherwise. The top-level hook
now skips /home and only handles login/register/reset-password/wizard.
Type label falls back to a route-derived i18n key on direct page loads.
The browser tab title was hard-coded to 'LangBot' in index.html and never
changed. Add a useDocumentTitle hook that maps the active route to an
existing i18n key and sets document.title to '<page> · LangBot', driven by
a new top-level RootLayout route element. Re-runs on navigation and on
language change so the title stays localized. Falls back to the bare app
name for unmapped routes.
The result grid used auto-fit tracks, so a single search result stretched
to fill the whole row. Switch to fixed responsive column counts (1/2/3/4
across breakpoints), matching langbot-space, so cards keep a consistent
max width no matter how many results are shown.
Mirror the langbot-space marketplace change: drop the '共 xxx 个扩展'
stats line below the tag filter, surface the count in the search
placeholder ('搜索 xxx 个扩展、能力或场景...') when no query is active,
and show the total at the bottom via allLoadedCount when searching.
Adds searchPlaceholderCount + allLoadedCount to all 8 locales.
Mirror the LangBot Space marketplace: the advanced-filter type options
(plugin / MCP / skill) now display their live extension count, e.g.
"插件 (74)". Counts are fetched on mount via three lightweight
searchMarketplaceExtensions calls (page_size=1) reading total per type.
The all-formats option intentionally shows no count.
When the install confirm dialog is opened via URL query params (e.g. from a
marketplace deep link), installInfo carried no icon, so the icon fell back to
the /resources/icon endpoint which 404s for extensions whose icon is an
external URL (simpleicons / iconify), showing a Package placeholder.
Fetch the icon from the marketplace detail API (mcp/skill/plugin) after opening
the dialog and inject it into installInfo, and reset the icon-failed state when
the resolved URL changes so the <img> retries instead of sticking on the
placeholder.
- Update test_migrations / test_migrations_postgres head assertion from
0003 to 0004 after adding the mcp readme migration.
- Reformat MCPForm.tsx / MCPReadme.tsx to satisfy prettier/prettier.
Wrap the MCP detail right panel in a compact left-aligned Docs/Tools
tablist (Docs first). Move the tool count into the Tools tab label and
drop the redundant panel title/subtitle; connecting/failed states still
render the status component. Shorten the sidebar 'Installed Extensions'
entry to 'Installed' across all 8 locales, and add tabTools/tabDocs/
noReadme strings.
Many MCP / skill records store their icon as an absolute external URL
(simpleicons.org / iconify.design) rather than an uploaded file, so the
/resources/icon endpoint 404s and the card icon breaks. Add
resolveMarketplaceIconURL() which prefers an absolute http(s) icon field
and otherwise falls back to the resources endpoint.
Capture the README markdown from LangBot Space when installing an MCP
server and store it on the mcp_servers record (new readme column +
alembic migration 0004). The detail page can then render docs offline,
independent of the server's runtime/connection state.
Add a "Join our Discord" entry to the account dropdown's external-links
group, opening https://discord.gg/wdNEHETs87 in a new tab. lucide-react
has no Discord brand glyph, so include a small inline Discord SVG icon
(brand color). Add the joinDiscord label to all 8 locales.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The softened shadow alone left cards with no visible edge against the
page background. Add `border border-border` so each card has a clear,
restrained boundary while keeping the gentle shadow.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reduce the marketplace card box-shadow (4px/0.2 -> 2px/0.06) and the
hover shadow (8px/0.15 -> 5px/0.08, dark proportional) for a more
restrained, understated look.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The format filter used Wrench/AudioWaveform/Book for plugin/mcp/skill,
which collided with the plugin-component icons (Tool/EventListener/
KnowledgeEngine) shown right below. Switch formats to Puzzle/Server/
Sparkles — matching the canonical getTypeIcon used by the detail badges
— across the market filter, installed filter, install-queue map and
install-progress dialog.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The marketplace now lists plugins, MCPs and skills, so the item count
("Total N plugins") read wrong. Update market.totalPlugins and
market.searchResults to "extensions" across all 8 locales.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
huanghuoguoguo