* 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.
* feat(agent): size agent history by the window and calibrate token estimates
Agent history was capped at history_turns (default 5) because compaction
could not survive a turn. With checkpoints persisted, load history by
tokens instead, and let compaction bound the session.
Budget. The loader drops the oldest turns that do not fit, and what it
drops is lost: neither replayed nor summarized. A budget equal to the
compaction threshold (the earlier attempt, since reverted) let the loader
trim first, so whenever one turn was larger than the system prompt plus
the new question the request never crossed the threshold; nothing was
summarized and the session became a sliding window with no checkpoint.
agent.HistoryTokenBudget is now the whole window: overflow reaches the
first round's compaction, which summarizes it into a new checkpoint.
A turn-by-turn regression test drives the real loader, budget and
compactor and fails as soon as a stored turn after the checkpoint is
missing from the loaded history; restoring the old budget fails it.
Summarizer input. History can now reach the window, so the part being
summarized can outgrow one request. An overflowing request degrades to a
raw archive that is never persisted, so every later turn would fail the
same way. Prepare keeps the newest messages that fit, the prompt states
how many were left out, and file paths still come from all of them.
Calibration. cl100k counts Chinese at about a token a character where
Qwen and DeepSeek spend about 0.6. The estimator now carries a scale
(clamped to 0.5-1.5, text only), learned from consecutive requests in a
turn: they share tools, system prompt and earlier messages, so the
provider's growth between them prices exactly the appended messages,
without mixing in how a provider renders tool schemas. The turn's scale
is stored on its usage (context_token_scale); the next turn's loader
prices history with it and hands it to the engine. Loading, the first
compaction check and compaction itself share one estimator, so they
agree; calibrating only the trigger would let the loader drop turns
again, which the regression test covers.
Also: history is priced as the engine sends it (redacted KB/Wiki results
cost one line); a checkpoint older than the rows read is matched by the
assistant rows' (created_at, id) order; a read ending on a turn's
question keeps that turn; a compaction discarded for freeing under 5%
still persists its checkpoint; a checkpoint write matching no row is an
error; a partial index backs the newest-checkpoint lookup. Agent mode no
longer reads history_turns: the field leaves AgentConfig, the editor
hides it in smart-reasoning mode, and quick-answer keeps its turn cap.
* fix(agent): address review of window-sized history loading
Summarization. The summarizer call had a fixed 60s total timeout. With
history loaded up to the window, a request could carry ~175k tokens and be
cut off while prefilling or writing normally; the degraded result left no
checkpoint, so the next turn reloaded the same history and failed the same
way. Summarization now streams and is cancelled only after no output for the
engine's stall timeout (120s by default, LLMCallTimeout overrides), with the
overall ceiling left to the transport, as for the engine's own rounds and as
in Codex and Pi. A stopped turn is not retried. When the summarizer still
fails, the raw archive is persisted as a checkpoint marked degraded so the
loop is broken, and the next compaction refines it as the previous summary.
The archive is held to the summary budget, newest messages first, so a
degraded compaction always frees room.
Loading. The loader priced turns as sent but returned and held them as
stored, so wiki pages stored in full and sent as one line could pile up in
memory. It now returns the as-sent history and releases each turn's stored
rows once replayed, keeping about a page of rows at a time.
Index. The partial checkpoint index is replaced by a composite
(session_id, created_at DESC, id DESC) index serving the backwards page,
the newest-checkpoint lookup and the recent-messages reads. It is built with
CREATE INDEX CONCURRENTLY so writes to messages are not blocked; the
migration holds that single statement, since a multi-statement query runs as
an implicit transaction. A PostgreSQL integration test, skipped without
WEKNORA_MIGRATION_TEST_POSTGRES_DSN, applies the chain, runs 000106 down and
up through golang-migrate, and checks both queries use the index without a
sort; the SQLite migration test checks the same plans.
Calibration. It no longer waits for a total token count, and a usage with
only a scale is persisted. A turn that measures nothing carries forward the
scale it started from, so the newest turn always has the latest one.
* feat(agent): persist compaction checkpoints across turns
Agent compaction only lived inside the turn that ran it: the summary was
discarded at turn end and LoadAgentHistory rebuilt raw history from the
messages table, so every later turn past the threshold paid for another
summarization of nearly the same history.
A compaction whose history summary ends exactly on a stored turn is now
written onto that turn's assistant message (messages.context_checkpoint).
LoadAgentHistory starts from the newest checkpoint: the summary replaces
that turn and everything before it, and later turns are replayed verbatim.
The compactor already treats a leading summary as the previous summary, so
checkpoints fold forward incrementally.
History messages carry their turn's assistant message ID (chat.Message
TurnID, engine-internal) so compaction can tell whether its cut lands on a
stored-turn boundary. Nothing is persisted when the cut ends inside a stored
turn, covers only the live turn, or the history summary degraded to a raw
archive; a split turn's prefix summary is never persisted because that turn
is replayed whole next time. Writes are column-scoped and best-effort, and a
failed lookup falls back to history without a checkpoint.
Storing the checkpoint on the covered turn keeps the boundary implicit, so
session forks copy it with the turn and deleting the turn drops it. The
HistoryTurns cap still applies, now to the turns after the checkpoint.
* test(skill): wait for the background install in the name-conflict test
InstallSkill queues the install on a goroutine, and the fixture row already
starts at installing, so reading the status right after the call raced the
mock install and failed whenever it landed on ready first. Wait for the run
to finish on the reused row instead, as the other install tests do.
* feat(agent): size agent history by tokens instead of turn count
Agent history was capped at history_turns (default 5) because every turn
used to rebuild raw history and compaction could not persist. With
compaction checkpoints persisted, the cap is no longer what keeps a session
inside the window, and it threw away context that would have fit.
LoadAgentHistory now loads the newest checkpoint summary plus the newest
turns after it that fit a token budget: the run's compaction threshold
(agent.HistoryTokenBudget, the window less the reply reserve). History
that large already triggers the first round's compaction, which persists a
new checkpoint, so compaction rather than a turn count bounds the session.
Loading more would only hand that compaction a summarizer input larger
than the model can read.
Rows are paged backwards by (created_at, id) and the read stops at the
checkpoint or once the budget is full, so a long session is never read
whole. Kept turns stay contiguous, the newest turn is kept even when it
alone exceeds the budget (compaction splits it), and a turn cut by the read
is left out rather than replayed without its original question.
Agent mode no longer reads history_turns: AgentConfig.HistoryTurns is
removed, the editor hides the input in smart-reasoning mode and explains
the automatic behavior, and the smart-reasoning builtins drop the setting.
Quick-answer (KnowledgeQA) keeps its turn cap since it has no compaction.
* Revert "feat(agent): size agent history by tokens instead of turn count"
This reverts commit d05fb6e5f1f161813a88e9127609f7a059f38f12.
Loading history up to the compaction threshold lets the loader drop the
oldest turns before compaction can trigger: whenever a single turn's
replay is larger than the system prompt plus the new question, the
trimmed history stays under the threshold, nothing is summarized, and the
session degrades into a large sliding window that never gets a
checkpoint. A turn-by-turn simulation of LoadAgentHistory with the real
compactor showed zero compactions over 60 turns in those cases.
Keep the persisted checkpoints with the HistoryTurns cap for now; token
budgeted history returns in a separate change with a budget that leaves
the overflow to compaction.
* fix(agent): search bound knowledge bases before answering, and pass suggested-question origins
A user picked the suggested question "为什么在比较图形时需要谨慎处理?"
and the agent answered in round 1 with no tool call, claiming it had
searched the knowledge base and found nothing, then explained misleading
statistical charts. The question had been generated from "Corners Don't
Look Like That: Regarding Screenspace Ambient Occlusion" in a bound base,
where "comparing graphs" means SSAO falloff curves.
Two things let that happen: the grounding prompt said "Stable general
explanations need no lookup", and nothing told the agent where the
question came from - the base in question had no profile, only two
recent titles in the directory, and the click sent the text alone.
Prompt
- With knowledge tools available, search bound bases before answering a
question about a topic, even one that reads like general knowledge;
directory profiles and recent titles cannot prove a base lacks it.
- The general-explanation exemption applies only without bound bases.
- Say you searched or found nothing only when a search tool ran.
Question origin
- Suggested questions from FAQ/document chunks also return knowledge_id.
- Picking one on the home or chat page sends question_origin
{knowledge_base_id, knowledge_id} with that question only.
- The service keeps the origin only when its base is inside the turn's
resolved scope and the document belongs to that base; it never
changes the scope (unlike knowledge_base_ids, which narrows it).
- The engine renders it in runtime_context as <question_origin> with the
base and document handles and a note to search it before answering.
* fix(agent): keep question origins across file/tag scopes and bind them to the send
Review follow-up for the suggested-question origin.
- Scope check: the origin was kept only when its base was in the resolved
KB list, which is empty for file-only and tag-only scopes even though
their bases are searched. It is now checked against SearchTargets after
they are built; the document is kept only when a target for that base
covers it (unfiltered base, or a document scope listing it).
resolveQuestionOriginInfo re-checks SearchTargets, looks up the name of
a base that is not in kbInfos, and the renderer omits an unknown name.
- Frontend: the origin travelled through module-level "pending" state, so
a send that returned early (agent not ready, upload in progress,
steering) left it behind and a second pick overwrote it. It now rides
with the one send: triggerSend(text, options) -> createSession ->
send-msg -> sendMsg / changeFirstQuery.
- RetrieveKBOnlyWhenMentioned: suggestions are still generated from the
agent's bases, but picking one retrieved nothing. The origin now
selects its base, as an @mention would, when the agent may read it.
- API sync: question_origin in docs/api/chat.md and swagger;
QuestionOrigin on the Go SDK's KnowledgeQARequest/AgentQARequest and
knowledge_id on SuggestedQuestion.
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
* feat(knowledge): derive knowledge base descriptions from document profiles
Knowledge bases only had a hand-written description, which most users
leave empty, so agents bound to several knowledge bases had nothing to
route on and searched all of them. This adds a generated description
that is derived from per-document data instead of maintained by a model.
Document profile: the summary call now returns JSON with a 2-3 sentence
summary plus a gist, 3-5 topic keywords, a document type and one
typical question (knowledges.profile). Input is capped at 8k chars and
output at 1024 tokens; plain-text replies from custom templates still
work and simply carry no profile. The summary chunk embeds the gist and
short summary.
Knowledge base aggregate: a database-only fold over those rows (counts
per file type, tag, normalized topic and doc type; stratified samples of
titles and questions; a hash of the inputs). Deleting, moving or
re-parsing a document changes nothing but the rows, so the next rebuild
is exact without any model judgement.
Description text: one small model call over the aggregate yields a
gist, merged topics and typical questions (knowledge_bases.
generated_profile). The call is skipped when the aggregate hash is
unchanged; failures keep the previous text and record the error; an
empty knowledge base clears it. The manual description is never
touched, and the agent runtime context renders both so the model can
pass knowledge_base_ids instead of fanning out.
Refreshes are requested from summary task exit, post-process completion,
deletion, cross-KB moves and enabling the option, debounced per
knowledge base in 30 s windows via kb:profile on the summary queue.
POST /knowledge-bases/:id/profile/generate regenerates synchronously.
profile_config (enabled, model_id, custom_instructions) opts a document
knowledge base in; the settings dialog shows the generated card with
regenerate and adopt-as-description actions in five locales. Search
results now log hits per chunk type so the value of indexing summary
chunks can be measured.
Migrations 000101 (PostgreSQL) and 000021 (SQLite) add the columns; the
SQLite schema test expects the new version and columns.
* fix(knowledge): keep generated descriptions out of duplicates and refresh clones
DuplicateKnowledgeBase copies the source row through JSON, which carried
generated_profile onto a knowledge base that has no documents yet, so
an empty duplicate advertised the source's topics. The duplicate now
starts without a generated description and keeps profile_config so it
derives its own once documents arrive.
CopyKnowledgeBase builds the target field by field and skipped
profile_config, and the clone task never asked for a description after
copying the documents, so a clone stayed undescribed until its next
upload. The target now carries a copy of profile_config and both clone
paths request a refresh on completion.
* fix(knowledge): refresh the loaded clone target and carry document profiles
ProcessKBClone requested the description refresh with the reservation
stub it builds before CopyKnowledgeBase runs. For the main create path
that stub has neither a type nor profile_config, so the refresh helper
rejected it and nothing was enqueued. The refresh now uses the loaded
target returned by CopyKnowledgeBase.
cloneKnowledge copied the summary text but not the structured profile,
so even a scheduled refresh would have aggregated titles without topics
until every clone was re-summarized. Cloned documents now carry an
independent copy of the profile.
* 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.
analyzeResponse emitted EventAgentFinalAnswer with Done=true before
returning emptyContent=true to the retry loop, so every empty natural
stop produced a premature terminal answer event while the agent was
still running. Consumers that finalize on Done=true (e.g. the IM
channel, which closes its answer-done channel and then only waits a
bounded time for EventAgentComplete) can lock in a fallback and cancel
the still-running agent when the nudged retry is slower than that
window (#2906).
An empty natural stop now emits nothing — the verdict alone tells the
caller the round is retryable. When retries are exhausted, the loop
emits the selected fallback as the turn's sole terminal answer, so a
turn always ends with exactly one terminal answer event.
Regression tests cover all three shapes: the empty verdict emits no
answer events; empty-then-answer ends with exactly one terminal event
carrying the real answer; all-empty runs end with exactly one terminal
event carrying the fallback (each red on the pre-fix code).
* 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
* feat(stream): persist live-run markers and per-run steer queues
Mid-run sends need a cross-replica pointer to the generating
assistant and a control-plane list that never hits the SSE stream.
* feat(agent): inject queued user messages at ReAct round boundaries
The engine drains the steer sink after each round, persists accepted
rows, and delays Done until after a loop-end inject so the turn can continue.
* feat(session): expose /steer and hand leftover messages to a follow-up turn
Owner-scoped steer routes queue or inject into the live run, single-flight
AgentQA via the live-run marker, and history replay keeps multiple user rows
inside one turn.
* feat(frontend): queue mid-run messages while an agent turn streams
Stop and Send stay visible together, the overlay follows server delivery,
and history splits the transcript around injected user bubbles.
* fix(frontend): type pending and client_id on SteerQueueItem
vue-tsc failed because the overlay sets those fields while POST /steer is in flight.
* fix(session): harden steer persist, handoff, and new_run
Keep SetLiveRun ahead of SSE and roll back orphan turns, make inject
persist idempotent, append-then-delete on rebind, cap overrun rounds,
and stop aborting a live stream when /steer returns new_run.
* fix(session): satisfy pre-push lint on steer paths
Wrap long lines, check discarded Error/Emit results, and keep
context as the first argument so the fork push hook can pass.
---------
Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
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.
* fix(chat): send one completion-token field per provider
Agent dual-wrote max_tokens and max_completion_tokens, which Volcengine Ark
rejects. Collapse them to one budget and pick the wire name the way Pi does.
Fixes#3014
* fix(chat): shrink max_tokens provider whitelist to documented hosts
Only DeepSeek, Zhipu, SiliconFlow, Moonshot, NVIDIA, and self-hosted
vLLM-class runtimes stay on the legacy field. Aliyun DashScope documents
max_completion_tokens for thinking models and must not be forced onto
max_tokens.
* fix(chat): send max_tokens for LKEAP completions
Tencent LKEAP documents max_tokens only. Keep Pi's default of
max_completion_tokens, and classify every AllProviders() host so a new
vendor cannot silently inherit the default.
* 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.
Provider prefix caches only hit when system/tools stay byte-stable and
cache routing is actually on the request. Stop rewriting those prefixes
mid-turn, attach prompt_cache_key / cache_control, and log hit rate
instead of showing it in the conversation tree.
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.
- Updated .env.example to clarify the skill bundle size limits and their impact on Nginx configuration.
- Refactored frontend/docker-entrypoint.sh to separate max file size settings for skills and general uploads.
- Enhanced nginx.conf to apply specific body size limits for skill uploads without affecting other endpoints.
- Added tests to ensure proper handling of skill bundle file indexing and size constraints.
- Improved error handling in tenant_source.go and tenant_sandbox_config.go to manage skill file limits effectively.
Each catalog keeps a single object: same SHA skips SaveBytes, a new zip replaces the old ref, and install rows only store CatalogID. Agent and admin caches keep the zip compressed under a 64MiB budget so read_skill does not unpack the whole tree.
Large GitHub skill folders were rejected because the installer counted the whole repo zip. Count only the SKILL.md subtree, raise the file cap, and hide uninstall while install is running.
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.