* fix(security): close the low-severity shared-space findings
Verified and fixed from the shared-space permission review:
- Embed channels kept knowledge_ids, tag_ids, mentioned_items, skill_names
and summary_model_id from anonymous visitors. Mentions are only scoped
for shared agents, so a visitor could query any KB (and pick any model)
of the channel workspace by ID. The payload now drops them; the widget
never sends them.
- PUT /knowledgebase/:kb_id/wiki/issues/:issue_id/status updated any issue
by ID. The update is now scoped to the path's KB (404 otherwise).
- A direct org invite let the inviter attach any user of the target
workspace (or any user by ID) as its representative, whose username and
email the roster then showed to all members. Direct adds attach no
representative, and the roster returns emails only for the caller's own
workspace.
- COS and KS3 dropped the bucket (and COS the region) segment when turning
a path into an object key, while the tenant check scans every segment:
cos://42/<region>/prefix/7/... passed as tenant 42 and read tenant 7's
object from a shared bucket. Both must now match the service's config.
- Shared agent listings returned the full agent to receivers. Prompts and
the creator's user ID are withheld; capabilities and scope stay visible.
- Temporary document uploads let the caller pick the parser engine (and
its credentials) of a shared agent's workspace; only the agent's rules
choose one there now.
- Suggested questions used request / message-snapshot knowledge_ids
without a permission check. Each document is now resolved to its KB and
checked like KB IDs, including a shared agent's scope.
- IM channels accepted any knowledge_base_id (and any agent ID on create).
Both must belong to the channel's workspace, the KB also to a restricted
API key's allow-list.
- KB-restricted API keys could list org-shared KBs outside their allow-list
in the organization views; those listings are now filtered.
- With enable_rbac=false, RequireKBAccess let cross-workspace denials
through. That switch is for roles inside a workspace; the guard now
always denies another workspace's KB, since handlers behind it load by
ID without a tenant filter.
- The org member limit was counted before and enforced apart from the
insert; it is now checked in the insert's transaction with the
organization row locked (SQLite serializes writers instead).
- The UpdateOrganization route comment and API doc said owner-only; the
service and UI allow org admins. Comment and doc corrected.
Documented, not changed: issued /r/ and presigned links stay valid until
they expire after a share is revoked.
* fix(security): address review of the low-severity shared-space fixes
- Embed payloads also drop question_origin. It selects a KB like an
@mention for agents that retrieve only when mentioned, and the widget
never sends it; the selection stays inside the agent's scope, but an
anonymous visitor should not pick among its KBs. suggestion_attribution is
kept (the widget sends it and it is validated).
- The receiver view of a shared agent also withholds the follow-up
suggestion instruction, a prompt like the others. Starter questions are
shown to receivers anyway, and the sharer's name is displayed by design.
- Follow-up suggestion generation moves into the agent's workspace with
types.WithExecutionTenant instead of a bare tenant rewrite, so the
caller is pinned before the document permission check runs. The auth
middleware and the shared run already pinned it; this removes the
dependency on that.
- KS3 CopyFile copies only from the service's own bucket (as COS and S3
do); another bucket's path is a cross-backend copy.
Tests cover the dropped question_origin, the follow-up instruction and the
/shared-agents listing, a follow-up context with the tenant switched, a
repeated wiki issue status update, and the KS3 copy source.
Repeating the same query in another mode is usually wasted, but keyword
mode can still recall identifiers that hybrid never surfaced. Stop telling
the model that switching mode cannot help.
The agent searched seven times for "Echo 开放权重模型 降低成本". Hybrid
retrieval ranked the right chunk first (RRF rank 0) every time, but the
rerank model saw only the chunk text, which never names Echo or cost;
it scored 0.0025 and all 18 candidates fell below the 0.15 fallback
floor. The tool reported "No matching chunks", and the model cycled
hybrid -> semantic -> keyword, which cannot help since every mode shares
the same rerank check. Scoring the same chunk with its document title
("Show HN: Echo - ... at 1/3 the cost using open-weight models") gives
0.45, and 0.55 for the query written as a question.
- Rerank passages are title + enriched chunk (rerankPassage); FAQ chunks
keep their own question, and the pattern filter still sees chunk text
only.
- When retrieval found candidates but the rerank model rejected all of
them, the empty statement says so and that switching mode will not
help, instead of "No matching chunks".
- The tool description, query schema and agent system prompt ask for a
complete natural-language question in hybrid/semantic mode rather than
a keyword list, and drop "switch mode" as the retry advice. Every
keyword engine matches any token (OR + BM25), so a question costs the
keyword leg no recall; on the same 20 bases the Echo chunks rank the
same for both query styles.
read_document's in-document query was matched as one literal string, so a
keyword query such as "sunflower f(n,k)" found nothing in a 708-chunk
document even when both words were there. The zero-match result gave the
model no next step, and the UI rendered it as "0 / 708 chunks loaded",
which reads like a failed load.
Paging mode also had no size bound: the registry truncates
ToolResult.Output, but the model sees the result rendered from Data, so a
limit=100 page reached ~68k characters in the model context.
- A plain query is split on whitespace; a chunk matches when it contains
every word, in any order. regex=true still matches one expression.
- A zero-match result carries a <hint> suggesting fewer/different words
or reading a chunk from search_knowledge results.
- A page stops adding chunks at 80% of the output budget (counting
per-chunk rendering overhead); next_offset resumes at the first chunk
not returned, and an oversized first chunk is still returned.
- The UI summary shows in-document search results ("no matches" /
"N matches") and, for offset paging, the chunk range instead of a page
number that no longer holds.
* refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents
The agent's retrieval surface had grown to five overlapping tools whose
behaviour was scattered across long descriptions, interleaved "tips" in
tool output (most of which modelcontext discarded before the model saw
them), and a grep_chunks implementation that ran an unindexed regex scan
over the chunks table ordered by created_at, so large knowledge bases lost
recall and paid a full-table scan on every call.
Tool surface
- search_knowledge replaces knowledge_search and grep_chunks: one query,
mode = hybrid | semantic | keyword, optional knowledge_base_ids, limit.
Keyword mode runs through the retrieval engine's keyword index instead of
the DB regex scan. Modes unavailable for the scope are refused with a
reason. Rerank, MMR and de-duplication are kept; already_seen markers,
retrieval_statistics and the zero-result "CRITICAL" block are gone.
- read_document replaces list_knowledge_chunks, get_document_info and
wiki_read_source_doc: id accepts a dN or cN handle, always returns the
document header, pages by exact offset (fixing the old floor-to-page
bug), finds passages with query (literal by default, regex opt-in) and
reads neighbours around a chunk with context.
- list_documents pages through one knowledge base, honouring @file/@tag
scope.
- wiki_search takes a single query plus regex, knowledge_base_ids, limit;
literal queries are escaped so the model never reasons about JSON
escaping. Legacy queries / knowledge_base_id are still accepted.
- query_knowledge_graph is registered only when a graph-enabled KB is in
scope and its description/tips were trimmed.
Compatibility
- Retired names in stored allowlists, presets and API calls are mapped to
their successors by NormalizeAllowedTools at registration time; no data
migration. Stored histories with old names still decode, render and
redact. Calls to retired names return a replacement hint.
- modelcontext gains an "id" key space that decodes against both the chunk
and document handle tables (decode-only), plus rendering for the
document header, chunk roles, in-document matches and next_offset.
Prompts and surfaces
- The RAG, wiki researcher and hybrid templates now name the tools and the
search -> read -> cite order; tool descriptions are short and contain no
workflow instructions.
- Engine display names, history redaction, grounding prompt, IM rendering,
the built-in MCP server (search_knowledge gains mode/limit, grep_chunks
becomes keyword search, read_document gains query, wiki_search gains
regex), frontend editor/renderers/i18n, presets, website docs and the
changelog are updated accordingly.
Tests cover name mapping, mode validation and refusal, output shape,
read_document paging/context/query/scope, list_documents, wiki_search
escaping and legacy arguments, modelcontext decoding and rendering, and
registration-time aliasing and graph gating.
* fix(agent): address review findings on read_document, list_documents and model rendering
- read_document: fetch the second page whenever the first page did not
reach the end of the document, so an unaligned window near the end no
longer drops the trailing chunks (also fixes context windows around a
chunk near the end); a query passed together with a cN handle now
searches the owning document instead of being ignored; query mode stops
collecting once the output budget is nearly spent and reports truncated;
the document row is authorized in place instead of being fetched twice;
the context read takes the total from the window fetch instead of a
separate count query.
- list_documents: resolve the page's document scope in one batched tag
lookup instead of one call per row.
- modelcontext: render read_document output once and read next_offset
through the existing intValue helper.
- search_knowledge: point title/file-name lookups at list_documents.
- Tests for the boundary window, chunk context near the end, cN + query,
and budget-bound query results.
* fix(agent): close compatibility gaps in the consolidated retrieval tools
- Wiki-only scopes: read_document and list_documents are registered
whenever a wiki KB is in scope, since every KB stores chunks. Their
capability requirement includes wiki but is marked auxiliary, so they do
not widen a RAG agent's derived "all knowledge bases" filter to wiki-only
bases (Go and frontend derivations both honour it).
- search_knowledge resolves the retrieval mode per knowledge base instead
of refusing the call: FAQ and vector-only bases answer keyword requests
semantically, keyword-only bases answer semantic requests by keyword.
Results carry requested_mode and mode_fallbacks, the empty-result text
names the fallback, and the call is refused only when no base in scope
has a chunk index.
- The model rendering uses the mode the search actually ran with (it was
always labelled semantic) and emits <mode_fallback> per degraded base.
- list_documents applies the @file/@tag scope before paging: tags are
pushed into the database filter, pinned documents are loaded by ID, and
total/next_page count only readable documents.
- read_document resolves chunk context by chunk_index through a new
ChunkRepository.ListChunkNeighbors, so parent, summary and image chunks
sharing the index sequence no longer shift the neighbourhood; offset is
documented as a reading-order position, not a chunk index.
- wiki_search (agent and MCP) keeps its regular-expression default and
only matches literally when the text is not a valid expression;
regex=false forces a literal match and regex=true rejects invalid input.
- MCP grep_chunks keeps grep semantics: literal terms from the pattern
fetch candidates from the keyword index (semantic for bases without
one), and every returned chunk is verified against the pattern.
* docs(changelog): align the consolidation entry with regex wiki_search and grep_chunks semantics
* docs(mcp): note that grep_chunks recall is bounded by index candidates
* refactor(wiki): consolidate source_refs parsing and resolution
source_refs entries ("uuid" or "uuid|title") were parsed by ten
independent implementations that disagreed on whitespace handling, on
whether a model-supplied title could be trusted, and on how a leading
pipe was treated. The scope-enforced and legacy agent resolvers also
duplicated the lookup and the routing step looked every document up a
second time.
- types.ParseWikiSourceRef / FormatWikiSourceRef / WikiSourceRefMatchesKnowledge
are now the only readers and writer of the format.
- resolveWikiSourceDocuments replaces resolveAuthorizedSourceRefs,
resolveSourceRefs and wikiKnowledgeBasesForSourceRefs: one lookup per
document, titles always rebuilt from server data, dedupe by canonical ID,
unknown documents fail closed in every mode.
- removeSourceRef now matches padded or titled refs of a deleted document.
* refactor(data_analysis): expose the selected document as a fixed table name
The tool required the document ID inside the SQL text and blindly
string-replaced it with the physical DuckDB table name, which forced the
model-context codec to rewrite handles inside quoted SQL and let the
UUID-derived k_<uuid> table name reach the model through stored schema
summaries.
The document is now selected only by knowledge_id. Every query runs on a
dedicated connection where "dataset" is a temporary view over the
physical table (DuckDB temporary objects are connection-local, so
concurrent sessions stay isolated). The physical name remains accepted
for internal callers; any other table fails validation with an error
naming the table the model should use. Schema summaries, the schema
tool, the analyst prompt and the tool schema all name the same table, so
data_analysis.sql no longer carries source handles and its text codec
policy is removed.
* feat(modelcontext): report raw identifiers that survive encoding
Text-level compaction exists because raw UUIDs reach model context through
producers the registry never sees: error strings, slugs, results of
unknown shape. Retiring it requires knowing where those producers are.
Registry.LeakedIdentifiers scans an encoded message list for UUID-shaped
values in every application-composed field (user messages are skipped),
classifies each as registered (codec missed a rewrite) or unregistered
(producer emitted a raw ID), and SummarizeLeaks renders one line per
field. The agent engine and the three RAG pipeline call sites log the
report as a warning after EncodeMessages.
* fix(chat_pipeline): align RAG data analysis with the fixed table contract
The RAG data-analysis plugin still asked the planning model to fill in
knowledge_id and to write SQL from a prompt that exposed the raw
knowledge UUID, then passed the model's JSON straight to Execute. Under
the new data_analysis contract a query that names anything but the
dataset table is rejected, and the plugin logged that rejection at error
level and moved on, so the analysis vanished without any signal. A
"no analysis needed" plan took the same error path.
The pipeline now owns document selection: the model returns only
needs_analysis and sql, the prompt names the dataset table and never
shows the knowledge ID or physical table, and the plugin builds the tool
input itself. A rejected query is fed back to the model once for repair;
a query that still fails is reported through pipelineWarn with the SQL
and the tool error, and "not needed" is logged as such instead of as a
failure.
Covered by unit tests with a scripted model and executor: not-needed,
pipeline-owned knowledge_id, one-shot repair, persistent failure
surfaced, unparseable plan rejected.
Serply returns Google results through a keyed JSON API, which fills the
gap between Google Custom Search (needs an engine ID and a restricted
scope) and the scrapers. The adapter follows brave.go: hardcoded
endpoint, redirects refused so the key never leaves the official host,
4MB response cap, and per-call country and freshness filters. country
maps to Google's gl parameter and pd/pw/pm/py map to tbs qdr:d/w/m/y.
Serply has no date-range filter, so that form returns an error instead
of being silently dropped. num is clamped to 10 because the API serves
one results page per call.
Wiring matches the Bocha provider: type constant and metadata, registry
factory, service validation, frontend union, swagger enum entries (edited
by hand; a full swag regen drags in unrelated drift), and the web search
docs table.
* feat(browser): enhance BrowserIcon component and update localization strings
- Updated BrowserIcon component to accept dynamic width and height props.
- Revised localization strings in English, Japanese, Korean, Russian, and Chinese for improved clarity and user guidance regarding browser connection and usage instructions.
- Enhanced BrowserConnectionSettings view with better structure and user feedback elements.
* Default BrowserSkill tasks to a separate window
* refactor(prompts): streamline agent system prompts and context templates
- Updated agent system prompts to enhance clarity and specificity in user interactions.
- Revised context templates to better separate metadata and user requests, improving overall structure.
- Adjusted fallback and intent prompts to ensure consistent language handling and response requirements.
- Introduced new localization strings for browser search instructions across multiple languages.
- Added tests for agent prompt serialization and hydration to ensure template integrity and functionality.
* chore: wrap prompt strings to satisfy golangci-lint
Keep the settings, separate-window, and prompt commits pushable together
without rewriting their history.
* fix(frontend): match agent editor save test to serialized payload
The prompt-inheritance save path still closes after update; the test
should assert that payload, not the unsanitized form object.
* feat(browser): implement browser connection management and related tests
- Introduced a new `browserConnection` store to manage the state of browser connections, including online status and device information.
- Updated the `Input-field` component to handle browser connection states, enabling/disabling features based on the connection status.
- Added tests for the `browserConnection` store to ensure correct behavior under various scenarios.
- Enhanced the `Input-field` and `BrowserConnectionSettings` components to provide user feedback based on the browser connection state.
- Adjusted related components and views to integrate the new browser connection logic, improving overall user experience.
* fix(frontend): update model-save assertion for serialized agent payload
The agent editor still persists the selected model ID via a spread of
formData; the source test should match that payload, not the raw form.
The agent engine derives every tool's execution ctx from a blanket 60s
budget (toolExecutionTimeout), so MCP calls on services configured with a
longer advanced_config.timeout were silently cancelled mid-flight even
though the MCP transport layers honor that value (internal/mcp/client.go,
manager.go). The configuration was partially applied without any signal.
Re-derive the CallTool window from ApprovalCtx (the round-level parent
without the per-tool deadline) using the service timeout when it extends
the engine window. Widening-only by design: services without an explicit
longer timeout keep today's behavior, and shorter values stay enforced
where they already apply (HTTP transport timeout).
Fixes#3135
BREAKING CHANGE: Updates that explicitly include usage_instructions must supply nonblank text of at most 16000 characters. Omitting the field preserves existing instructions; legacy descriptions remain readable.
* feat(mcp)!: persist tool catalogs and add guided configuration
* fix(mcp): write caller-owned catalogs and require a real tool sync
OAuth viewers can now persist their own directory, and the setup wizard no longer treats an unsynced service as complete. Missing catalogs auto-fetch on the tools step; already-used MCP functions are restored across engine turns.
* fix(mcp): skip redundant list_servers and tighten catalog UI
When the advertised server directory already fits in discover_mcp_tools, models should list_tools or describe directly. Chat and settings now show server names, collapsed docs, and initialize debug metadata for empty optional fields.
* fix(mcp): surface catalog summaries and polish tool detail UI
List responses now include a saved catalog count without live MCP calls, so settings cards and @ mentions can show sync state. Tool details open in a popup instead of expanding the row.
* fix(mcp): drop incomplete Anthropic calls and gate shared catalog refresh
Unclosed streamed tool_use was emitted as {} and executed. list_tools refresh=true now re-lists upstream instead of returning the saved snapshot, and only Admin (or MCP-capable API keys) can overwrite tenant-wide static-auth catalogs.
* fix(mcp): wrap client refresh path to satisfy lll
The metadata refresh URL made doRequest exceed the 120-character limit in the client module CI lint.
* fix(mcp): require schema discovery before calls and render tool results
* fix(mcp): keep proxy identity until describe and localize embed results
Listing still cached the target, so skipped describe showed as an mcp_* failure instead of the proxy error. Embed chat also lacked the new MCP strings.
* fix(agent): improve web search and persistent page reading
* fix(agent): make web fetch snapshots waitable and retryable
Keep in-flight page fetches independent of a caller's short deadline so
content=true and continuations cannot cancel a shared download or miss a
snapshot that is still loading. Mark snapshot_expired as retryable, fetch
only the first three search hits in parallel, and stop forcing Brave's
country to US.
* feat(sandbox): run sandboxed execs as root by default
Every chat session owns its own sandbox, so the in-container account is
not a tenant boundary and root is the least surprising default for an
agent that installs packages and writes wherever it needs. Host and
cross-tenant isolation stay at the container boundary.
DefaultSandboxExecUser becomes "root" (remote_client.go) and the sandbox
image ends with USER root. The three backends keep naming the account
explicitly on every exec so the account a call lands on does not depend
on which backend a workspace selected; the adapter default, the file
operations and the artifact-directory bootstrap all follow the constant.
The template still provisions a uid 1000 "user" account for interop with
E2B/Cube tooling that addresses it by name.
Root also makes the skill-install flow's account hand-over pointless, so
it goes: verification no longer runs after a chown/chmod lock-down and a
repair round no longer reopens the tree (normalizeSkillPermissions and
reopenSkillDirForRepair are gone), and the prepare and scratch commands
stop chowning. The scratch wipe now also clears /tmp, and the cache
budget guard sizes only root's caches, since no second account can grow
one. Verification is asserted to stay on the ordinary executor (no
AsRoot, no AllowSkillsRoot) rather than on which account it ran as.
* refactor(skills): install chat-time extras into the skill's own env
PYTHONPATH / NODE_PATH pointed at a per-session overlay
(/workspace/.skill-packages/<skill>) because the skill tree was frozen
after install: root-owned, mode 555, and often built by `uv venv` with no
pip, so `pip install --target` somewhere else was the only way a chat
session could add a package.
None of that holds now. The lock-down is gone and execs run as root, so a
missing package goes straight into the skill's own environment, and the
write is already session-local: a chat sandbox is built from the config's
image and its filesystem dies with the session, so nothing reaches the
image other sessions start from. The overlay bought nothing over that
while splitting one skill's packages across two locations.
SessionSkillPackageDir goes, and applySessionPackagePath becomes
applySkillNodePath: it appends the skill's own node_modules after
whatever the caller supplied, replacing a `+=` that prepended a bare
separator once the overlay stopped seeding the variable. No PYTHONPATH is
injected at all. Python dependencies are reached through the skill's venv
interpreter, which the shell wrapper already puts first on PATH; the
overlay-era value named the venv root, which is not an importable path.
PYTHONPATH stays on the injected-name blacklist so a stored value cannot
shadow the venv.
The runtime hints and every prompt that described the overlay now name
`<skillDir>/.venv/bin/python -m pip install` and `npm install` in the
skill directory. frozenSkillTreeGuidance / isFrozenSkillVenvFailure are
renamed for what they detect now that nothing is frozen.
* docs(prompts): reserve /workspace/output for finished deliverables
/workspace/output is the one directory an artifact collector reads, so
everything written there is offered to the user as a deliverable. The
prompts described it as the place for "deliverables" or "downloadable
artifacts" without saying it is exclusively that, which reads as "the
directory you write results to" — and a model doing multi-step work has
results at every step. Drafts, intermediate renders and debug dumps land
next to the finished file and the user is handed all of them.
The four places that describe the workspace now say the same thing: the
collector reads only /workspace/output, so finished deliverables go there
and everything in progress goes anywhere else under /workspace. The
attachment block gains the matching half for the other direction —
/workspace/input holds the user's own files and is not ours to write to,
which it previously implied by calling the paths "read-only inputs" while
the tools that enforce it say so plainly.
Only the /workspace/input half is enforced (write_sandbox_file refuses
that tree). Whether a file is finished is a judgement no tool can make,
so the output half stays guidance and is stated wherever the model is
already reading about the workspace rather than in one place it might
not see.
* fix(skills): restore executable bundles and package recovery
* style(sandbox): wrap prompt text for repository lint checks
* fix(sandbox): guard recovery paths and document root execution
---------
Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
* feat(mcp): add per-tool enable toggle
* style: format migration test
* fix(mcp): keep enable and approval updates from overwriting each other
Partial policy writes now touch only the supplied columns, and a missing
tenant fails closed so a disabled tool cannot slip through.
---------
Co-authored-by: myysophia <myysophia@users.noreply.github.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
* feat(agent): unify sandbox tools and drop host preloaded skills
Read workspace and skill files through read_file, and run installed or staged skills through shell_exec(skill_name). Remove the unused skills/preloaded tree and keep generated-file previews stable across re-renders.
* fix(frontend): do not assume classList in markdown sanitize hooks
Node unit tests stub anchors without a DOM classList. Detect download cards from class/download attributes instead.
Large write/edit calls used to sit on a spinner until the full JSON
arrived. Emit path and running line counts from partial arguments so
the UI can update in place, without putting file bodies on the SSE wire.
Refuse truncated tool calls, compact-and-retry once on overflow, and let
sandbox files be appended, paged, and batch-edited instead of rewritten.
Models can set context_window (default 200K) so compaction sizes itself
from the real window; agent max_iterations of -1 means unlimited.
Three inconsistencies in how the sandbox tools are granted and bounded.
Tool checkboxes that decide nothing. list/read/write/edit_sandbox_file,
shell_exec, read_skill and execute_skill_script were offered in the settings
UI, but registerSandboxFileTools, registerSandboxShellIfAllowed and
initializeSkillsManager all register from the capability (a sandbox with a
session filesystem, SkillsEnabled, install mode) and never consult
AllowedTools. Clearing a checkbox changed nothing. Drop them from
AvailableToolDefinitions the way search_memory and web_search already are,
so the switch that decides is the only thing shown.
Readers narrower than writers. write_sandbox_file accepts anything under
/workspace except the attachment tree, while list/read stopped at the
artifact output dir, so the agent could not read back the scratch script it
had just written and had to detour through `shell_exec cat`. Since
shell_exec reaches those files anyway the narrowing bought no safety; the
inspectable roots now cover /workspace, still ordered so a reported root
names the artifact or attachment tree when the path is inside one.
Two answers for one directory. A WEKNORA_SKILL_OUTPUT_DIR override was
validated on the execution path (falling back to /workspace/output) but
taken as-is from the host environment by the tools and ArtifactCollector, so
an override outside /workspace pointed the readers at a directory no skill
could write. Both now go through sandbox.ValidatedSessionOutputDir.
The installer agent was recently given its working directory up front and
stopped prefixing `cd <skill-dir> &&` onto every command. Session agents
never got the same treatment: shell_exec only mentioned /workspace as the
work_dir default, so the model could not tell it was already there, and
execute_skill_script never said scripts run with /workspace as their cwd —
a relative path inside a skill script silently resolves outside the skill.
Describe the workspace once, where each tool is described: shell_exec gains
a Working Directory section (already in /workspace, relative paths, no `cd`
prefix, and each call starts there again so a `cd` does not carry over),
execute_skill_script states its cwd and points at $WEKNORA_SKILL_DIR, and
the skills prompt gains a Workspace section covering input, output and the
per-session package overlay.
Also drop the installer prompt's paragraph about write_sandbox_file and
friends: those tools are not registered in install mode, so the model never
sees them in its schema and the note only spent tokens describing — and
misdescribing — a scope it could not reach.
- Added write_skill_file and edit_skill_file tools to facilitate writing and editing files directly within the skill directory during installation.
- Updated the agent service to register these tools exclusively for the built-in skill installer, ensuring they operate within the correct scope.
- Enhanced error handling and validation to prevent unauthorized file access outside the designated skill directory.
- Improved documentation and prompts to clarify usage and limitations of the new tools, emphasizing the importance of proving import resolutions by executing them.
- Added tests to validate the functionality and security of the new file management tools.
Some upstream inference gateways append an extra `""` arguments delta
right after a zero-argument tool call, so the accumulated payload becomes
`{}""` and fails to parse. RepairJSON now drops anything following the
first balanced top-level value, which also covers a duplicated payload.
Truncated JSON is left untouched so balanceBrackets can still recover it.
Generated PPT/report scripts overflowed the shell_exec command cap, and
session agents kept mutating the frozen skill tree or failing SkillHub
installs on display titles. Add write/edit sandbox tools, attach the
skill venv to /workspace scripts, and accept slug-based install names.
list/read sandbox tools were advertised for skills-off agents so they could inspect /workspace/input, but they still refused anything outside /workspace/output. Register shell_exec independently of the skills manager so a skills-enabled sandbox with no ready skill gets a shell without empty read_skill / execute_skill_script tools.
Failed execute_skill_script results were reduced to "exited with code 1" plus a retry hint, so the chat card hid the real stderr/stdout and the next model round could not correct arguments like a missing chart axis.
Capture existed so a credential a user typed in chat survives the turn.
It also overwrote values already stored, inferred the skill from a path in
the command, and logged the command that carried the secret — so one
hallucinated `export KEY=test` could permanently replace a working key,
and the key ended up in the application log either way.
Capture now only fills a blank: a name the workspace or the caller has
already filled in is dropped before the write path sees it, the skill must
be named explicitly, and assignment values are masked in logs.
The path the error message advertised did not exist: a required variable
was refused before the call's own env was considered, so an IM user, who
has no settings page, could never get the skill to run. Values supplied by
the call now satisfy the requirement, and the message names the tool that
accepts them.
Also take envs out of the generic UpdateSkill. Every install-progress
write is a read-modify-write of the whole row, and the heartbeat reloads
it every 30 seconds, so carrying envs along could put a stale declaration
back over one just recorded. Encryption failures abort the write instead
of storing plaintext in a queryable JSONB column, matching TenantAPIKey.
Reverts an unrelated deletion of the no-volume-support warning.
Skills declare the environment variables they read at run time, so a
credential no longer has to be an admin-set value shared by everyone
using the same skill image.
The installer agent writes a declaration the server validates against the
bundle. Admins fill workspace-wide values from the skill drawer, members
fill their own under Settings, and a successful shell_exec captures the
declared names a run already used for the current speaker. Resolution is
keyed by Principal so IM callers do not collapse onto one synthetic
account, and values are injected only into the process of that one run.
Values are AES-GCM encrypted at rest and never returned by any endpoint.
Dedicated rerank already scores the recall set; falling back to the
conversation model mixed RRF scores with [0,1] ratings and could
resurface documents the reranker had rejected.
* feat(agent): preview skill artifacts and verify installs without running them
Generated files open in the chat drawer with overlay/Esc returning to the
list, and install verification no longer executes guessed skill entry
points. A failed install can be retried from the saved archive.
* ui(chat): use a folder icon and corner count for skill artifacts
The eye and document glyphs read as preview or copy, and TDesign's
loading spinner sat beside the icon. A folder with a top-right count
matches the generated-files drawer without covering the toolbar action.
* feat(artifact): implement inline artifact references with previews
Add support for inline artifact references in Markdown, allowing generated files to be displayed as clickable cards. Implemented a new rendering mechanism for artifacts, enabling previews directly from the chat interface. Updated localization files for new inline preview hints and missing file messages. Introduced tests for artifact reference normalization and rendering logic.
* fix(client): document AgentResponseType constants for revive
Touching the const block made golangci-lint require comments on every
exported value. Match the rest of the SDK and describe artifacts_pending.
* fix(agent): wrap artifact-reference prompt lines for lll
Pre-push golangci-lint rejected the branch on three lines over 120
characters in the sandbox: reference guidance.
* fix(agent): scope HTML scripts and tighten install verification
Keep scripted HTML preview on skill artifacts only, recreate sandbox
workspace dirs after they are deleted, and treat nested skill files as
dependencies rather than first-party imports.
* refactor(artifact): enhance artifact reference handling and metadata
Updated artifact metadata to include a stable resource handle for better identification. Adjusted artifact reference resolution to support both handle and name forms, ensuring compatibility with existing references. Enhanced tests to validate the new handling logic and ensure proper rendering of artifacts in chat messages. Improved documentation for clarity on artifact reference formats and their usage in the system.
shell_exec with display_type was collapsed to a one-line omit placeholder,
so the next turn and a history reload lost stdout/stderr. Keep a capped
copy of the streams in both Output and Data.
Local was a host-subprocess fallback that skill install, snapshots, and
session sandboxes already excluded. Drop it so Cube, E2B, and Docker are
the only backends; leftover local configs can only be deleted.
Give sandbox shell calls a display_type and keep stdout/stderr on the
live payload so the timeline can show the command, exit code, and
streams instead of the generic raw-output fallback.
Abort a queued install if the skill row was removed or superseded, refuse to
restamp a snapshot with a rotated provider fingerprint, and honor the workspace
sandbox kill switch before creating a maintenance session.
Introduce the hidden skill-installer agent and TenantSkillService so a
sandbox config can install or remove skills into snapshot images under a
per-config lock, without yet exposing HTTP or UI entry points.
Co-authored-by: Cursor <cursoragent@cursor.com>