* 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.
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.
* 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>
* 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.
* 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.
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.
Accumulate token usage across every LLM round of an agent turn and
expose the aggregate everywhere a turn is observable:
- AgentState.TurnUsage accumulates each round's reported usage,
including the final-answer synthesis call; TokenUsage.Accumulate
keeps the cache counters as prompt subsets and recomputes the
combined cache status (unsupported survives only while every call
was itself unsupported).
- The agent completion event carries the aggregate, and the complete
stream event exposes it both as data.usage and as a typed
StreamEvent.Usage that buildStreamResponse promotes into the
previously-unused StreamResponse.Usage wire field.
- The assistant message persists it as a nullable usage column on
both migration targets (postgres 000085 jsonb, sqlite 000012 text),
for web and IM channels alike, so history reads still carry the
turn's cost after the live stream is gone.
- "[LLM Usage]" log lines gain ", session_id=..., principal=type:id"
when the context carries them; calls outside sessions stay
byte-identical.
Usage from failed retry attempts is not accumulated: the per-call
usage log remains the ground truth, while the turn aggregate serves
as the operational signal.
Persist extracted and explicit memories across sessions with topic
resolution, semantic recall, document affinity, consolidation, workspace
settings, and inbox/interests UI.
* cubesandbox support
* feat(agent): add sandbox shell execution, file management tools, and Artifacts collection/download system
- Add three sandbox agent tools: shell_exec / sandbox_ls / sandbox_read
- shell_exec: safely execute shell commands in session sandbox with timeout & output truncation
- sandbox_ls: enumerate files under sandbox artifact output directory with recursive listing & pagination
- sandbox_read: read sandbox file content with offset-based chunked reading
- Add Artifacts system:
- ArtifactCollector: real-time collection of sandbox tool output files, attached to messages
- /api/artifacts/{session_id}/{message_id}/{filename}: download endpoint for frontend
- ChatArtifactsDrawer.vue: frontend artifacts sidebar UI
- DB migration 000066_message_artifacts: add artifacts column to messages table
- Attachment sandbox staging: upload user attachments to session sandbox on QA request for skill tool access
- Update Agent Prompts: add shell/sandbox tool usage constraints and safety rules
- Extend Agent Observe: include agent steps in Langfuse observability tracing
- Refactor Sandbox SessionManager: support session-scoped file listing, reading, and status queries
- Frontend: render artifact events in AgentStreamDisplay, i18n updates for 4 locales
- Add comprehensive tests: shell_exec_test, sandbox_read_test, artifact_collector_test, etc.
* feat(agent):add remote sandbox client abstract & client errors
* feat(sandbox): implement Redis binding store with distributed lifecycle lock;
* feat(sandbox): add remote session lifecycle with ownership context
Implement remoteSessionLifecycle to coordinate persistent remote sandboxes
across multi-instance deployments. Supports Resolve (lazy provision,
recovery, race-safe create) and Destroy with compare-delete semantics.
Add ownership context isolation to decouple remote resource cleanup from
request cancellation.
* feat(sandbox): add CubeRemoteClient adapter for RemoteSandboxClient
Implement CubeRemoteClient as a provider-neutral RemoteSandboxClient
implementation. Error normalization, timeout mapping, and metadata
support are fully integrated. SDK details remain private to the
adapter.
* refactor(sandbox): decouple SessionBoundManager from Cube
Remove internal/sandbox/cube.go (CubeSandbox, sync.Map reaper). Add
RemoteSandbox as provider-neutral Sandbox interface implementation.
Rewrite SessionBoundManager to depend on RemoteSandboxClient +
SessionSandboxBindingStore + SessionExistenceChecker, with all
lifecycle ops delegated to remoteSessionLifecycle (Redis + distributed
lock). Application-layer interfaces migrated to RemoteDirEntry/StatEntry
with time.Time ModTime. Cleanup delegated to provider idle-timeout.
* refactor(agent): enhance session capability handling in sandbox manager
- Introduced sessionFileStore and sessionShellExecutor functions to centralize capability checks for session-scoped file and shell execution.
- Updated agent service to register tools based on the presence of session filesystem capabilities, improving compatibility with various sandbox backends.
- Refactored tests to validate behavior when session capabilities are absent, ensuring robust handling of different sandbox types.
- Removed Cube-specific checks, promoting a more provider-neutral approach to session management.
* refactor(sandbox): add E2B backend, modernize Cube adapter, and enable multi-instance Redis binding
- Add e2b_remote_client.go (~850 lines) — full RemoteSandboxClient implementation
covering lifecycle, execution, and filesystem ops (ListDir/Stat/MakeDir/Remove)
- Wire E2B into NewManagerFromType and container/bootstrap path (buildE2BManager)
- Dependency: matiasinsaurralde/go-e2b v0.1.0
- Cut ~1500 lines of legacy SDK wrapper (cube_client.go, cube_envd.go,
cube_defaults.go) and replace with direct *cubesandbox.Client usage
- Parse CubeProxy URL directly in adapter (parseProxyURL), removing the
old hand-rolled envd transport layer
- Pass lifecycle extra fields (onTimeout, autoResume) via SDK CreateOptions.Extra
- Target Cube deployment v0.5.1
- Add RemoteNetworkPolicy to RemoteCreateRequest with AllowInternetAccess,
AllowPublicTraffic, AllowOut/DenyOut — shared by Cube and E2B adapters
- Both adapters default to permissive (internet+public on) for backwards compat
- Add selectSessionBindingStore() — Redis-backed or in-memory, controlled by
WEKNORA_SANDBOX_REDIS_NAMESPACE / WEKNORA_REDIS_NAMESPACE
- Add repositorySessionExistenceChecker — checks session existence via DB
(gorm.ErrRecordNotFound → not exists, transient errors → preserve binding)
- newSandboxManager() now accepts redisClient + sessionRepo; deprecated
hardcoded NewMemorySessionSandboxBindingStore() in production path
- buildSessionCreateRequest default timeout action: Kill → Pause+AutoResume
(Cube and E2B). Sessions survive brief idle periods; providers still
handle TTL-based reaping.
- buildSessionCreateRequest() and effectiveHTTPTimeout() parameterized
by RemoteProvider (was hardcoded to Cube Config fields)
- NewSessionBoundManager validates provider and delegates defaults to
per-provider apply*Defaults helpers
- Legacy SDK wrapper: cube_client.go, cube_envd.go, cube_defaults.go,
cube_envd_test.go, cube_net_diag_test.go, cube_test.go (~2500 lines)
- Unused helpers: DefaultManager.validateExecution, IsRemoteTerminal,
IsRemoteUnsupported, IsRemoteTransient, ShouldPreserveRemoteBinding
- Dead Config fields: CubeEnvdPort, CubeIdleTTL, AllowedCmds
- Dead ExecuteResult method: GetOutput
- Unused test: session_artifacts_integration_test.go
- Preloaded skill: sandbox-test-python
- Extract shared httpErrorKind() from per-adapter normalize functions
- Add SupportsFilesystemEnumeration capability flag — gates SessionFileStore
advertisement (E2B returns true post-reconnect, Cube always true)
- Fix stale comments: Cube-only → remote backends, remove "tomorrow"/"future"
- Bump session sandbox TTL defaults: 604800s → 300s (.env.example)
- Update docs/agent-skills.md: full multi-instance deployment guide
Total: 29 files, +1188 / -3721
* feat(agent): bind collected skill artifacts to owning message in resource registry
When ArtifactCollector persists a skill-generated file it now registers a
resource:// binding (owner_type=message, owner_id=assistantMessageID,
relation=artifact) in addition to the messages.artifacts JSONB record. This
mirrors how knowledge uploads and chat attachments bind their resources, so
artifacts can be enumerated and garbage-collected through the resource
registry instead of only via the message JSONB column.
- ArtifactCollector: inject ResourceCatalog, add messageID to Collect/
maybePersist, and add best-effort bindArtifactResource (binding failures are
logged, never drop the artifact; only resource:// refs are bound).
- agent_stream_handler: pass assistantMessageID into Collect.
- Renumber message_artifacts migration 000066 -> 000077 to resolve the
version collision with existing migrations (upstream now uses 000075/000076).
- Tests: update collector signatures and add coverage for the binding path
and for graceful degradation when Bind fails.
Note: binding applies to newly generated artifacts only; existing rows are
not backfilled.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(sandbox): harden remote sandbox security and artifact collection
Disable Cube local fallback so skill scripts never run on the host when
the remote provider is unavailable. Require Redis for cube/e2b binding
unless WEKNORA_SANDBOX_ALLOW_MEMORY_BINDING=true for single-node dev.
Collect artifacts with WithoutCancel so user stop does not drop files,
reject shell_exec work_dir outside /workspace, and refuse session-scoped
Execute when a local fallback would be engaged.
* fix(ci): gofmt sandbox files and resolve artifact drawer type error
Apply gofmt to PR-touched Go files and narrow ChatArtifactsDrawer
props in AgentStreamDisplay so session-id is always a string.
* fix(sandbox): adapt to upstream main after rebase
Renumber the message_artifacts migration 000077 -> 000079: upstream now
uses 000077_remove_wiki_log and 000078_chunk_editing_and_custom_metadata.
Declare empty model-handle policies for shell_exec / list_sandbox_files /
read_sandbox_file. Upstream added a coverage test requiring every
UI-exposed tool to declare one; sandbox output is arbitrary skill-authored
content, so it gets the same treatment as execute_skill_script.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(sandbox): replace single tenant sandbox config column with a configs table to support multi-sandbox config per tenant.
* feat(sandbox): add sandbox config entity, cordon lease and session pin field
* feat(sandbox): add sandbox config repository with tenant scoping and cordon lease
* feat(sandbox): stamp sandbox config ID onto sandbox metadata
* feat(sandbox): scope sandbox listing, release and reaping to a single config
* feat(sandbox): resolve managers per config and refuse cordoned or missing configs
* feat(sandbox): implement session pinning and config identity change detection
- Add SessionSandboxPinner with read/pin/clear to bind session to config
- Refactor four entry points (execute/attachment/artifact/destroy) to use pinned config
- Add config_identity.go to detect identity changes by effective values (APIURL/APIKey/Domain/ProxyURL)
- Add SandboxIdentityChanged with key-masked comparison to prevent false 409 conflicts
- Fix artifact collection for default backend and destroy for legacy empty-pin sessions
* feat(sandbox): add multi-tenant sandbox config management and HTTP APIs
Service layer:
- Add sandbox config business service supporting CRUD and inventory listing
- For non-identity changes (e.g., template, TTL), save directly without locking or remote interactions
- For identity changes (e.g., API key, endpoint), reject save if there are still live sandboxes under this config on the remote side,
and return structured inventory details (sandbox count, affected sessions, related agents) for frontend prompting
- Before deleting a config, check remote live sandboxes; if occupied, reject and prompt user to end sessions or create a new config
- Identity comparison based on effective values to avoid normal saves being misidentified as credential rotation
HTTP interfaces and routing:
- Add REST endpoints for sandbox config (List/Create/Get/Update/Delete/Inventory)
- Mask sensitive credentials (API key, etc.) in all read responses
- Return 409 with structured inventory details on rejection scenarios
- sandbox-check probing supports specifying an existing config_id directly
- Remove old handler file, consolidate validation logic into service layer
- DI wiring and route registration for all six endpoints
* feat(sandbox): add sandbox_config_id field to allow agent referencing named sandbox config
- Add SandboxConfigID field to CustomAgentConfig with omitempty; empty value falls back to global defaults
- Validate config existence on create/update; return 400 if not found
- Inject sandboxConfigService into CustomAgentHandler
- Add unit tests covering field serialization and validation logic
* feat(sandbox, agent): Migrate sandbox config to multi-config CRUD, support named backend selection and workspace scripts policy
Migrate frontend API from legacy KV single-config to /sandbox-configs REST interface, supplement type definitions, detection methods and policy fields; refactor sandbox settings page to multi-config card grid, manage configs with cube/e2b tabs, add editor drawer for create/edit/delete, connection testing and occupancy hints, and add workspace scripts policy toggle; add sandbox config dropdown in Agent editor skill section, integrate config caching, and support selecting named config or falling back to deployment default.
* feat(sandbox): Unify sandbox disable semantics and add tenant-level policy master switch
- Backend: Unify interception in resolveTenantSandboxForConfig with priority: global disable > tenant disable > default fallback > named config; add deploymentSandboxDisabled() using env var to avoid mis‑impacting named E2B; update WorkspaceSandboxPolicy comment as master switch for entire workspace; add unit tests for various scenarios.
- Frontend: Sync i18n copy: button text changed to "Disable/Enable sandbox execution"; confirmation dialog clarifies impact scope; success/failure messages aligned.
- Semantic layering: WEKNORA_SANDBOX_MODE=disabled disables globally; tenant‑level "Disable sandbox execution" only disables for the current workspace.
* feat(sandbox): Add SSRF protection, Agent binding to named configs, and reference query capabilities
- Add outbound URL security guard to validate Cube/E2B API/Proxy addresses against SSRF (including cloud metadata), support allowing private endpoints via env var, link-local always blocked
- Add named backend type validation, only cube/e2b can be stored as workspace named config
- Add sandbox config ID field to Agent at runtime, resolve sandbox for attachments and execution based on Agent's selected named config instead of always global default
- Add query to list Agents referencing a sandbox config ID, useful for deletion/changes to show dependents
- Adapt artifact collector and other callers to fill missing resolve signature parameter
* fix(sandbox): fix session teardown and config-update, add HTTP pool sharing for Cube
Session teardown & deletion ordering
- Move sandbox destroy (and pin `Clear`) before soft‑delete operations (`DeleteSession`/`BatchDeleteSessions`/`DeleteAllSessions`) to prevent remote sandbox leaks and stale pins.
- Pass deployment‑wide `SessionBoundManager` as fallback into `resolveTenantSandboxForConfig` for sentinel pins (`"-"`) to support deployment‑default sessions.
## Config update edge cases
- When identity fields change but old credentials cannot build a client or list config sandboxes, log a warning and proceed with the update instead of returning `sandbox_inventory_unverifiable`; live sandboxes still return 409.
- UI: move `sandboxes_still_live` / `unverifiable` alerts to the top of the sandbox config drawer and auto‑scroll on save refusal and connectivity check results.
Artifact collection for Cube skills
- Pre‑create `/workspace/output` via envd with correct ownership/permissions for `DefaultSandboxExecUser` to ensure Cube skill artifacts are collected properly by `ArtifactCollector`.
HTTP pool sharing for named Cube configs
- Named sandbox configs rebuilt a client on every `Resolve`, causing fresh TCP connections to CubeAPI and the envd proxy on each request.
- Add `CubeTransportPool` and `cubeSplitTransport`:
- Control plane traffic reuses the same `SharedTransport` as E2B.
- Data plane traffic uses a guarded transport cached per proxy host:port, preserving the sandbox `Host` header.
- Wire the pool through the tenant resolver `buildClient`; keep SDK defaults for the deployment‑default manager and connectivity probes.
* feat(sandbox): sandbox execution DefaultUser change from root to user
* fix(multi-sandbox-config-per-tenant): align deployment config with tenant resolver and centralize defaults
- Merge form overrides onto DeploymentConfig() via WEKNORA_SANDBOX_* env vars
instead of DefaultConfig() hardcoded values, allowing empty fields to inherit
from .env rather than Go constants
- Centralize deployment baseline parsing in sandbox/defaults.go with
DeploymentConfig, CubeConfigFromEnv, E2BConfigFromEnv
- Delegate container startup to shared helpers to avoid drift
- Propagate tenant env_vars through ResolveEffectiveConfig into
buildSessionCreateRequest for both Cube and E2B session sandboxes
* fix(multi-sandbox-config-per-tenant): fix some bugs frontend.
* fix(sandbox): guard check-path dials, fix staging gate and shared-agent binding tenant
Three defects found while reviewing the remote sandbox work:
- The Cube connectivity probe and the deployment-default Cube/E2B managers
built clients without a guarded transport, so an admin-supplied api_url or
proxy_url could reach link-local addresses via DNS rebinding even though
save-time validation passed. All three now dial through the same outbound
guard the per-tenant resolver enforces.
- Attachment staging was gated on the process-wide manager, so a workspace
pointing an agent at a named Cube/E2B config while the deployment default
stayed docker/local would run its tools remotely against an empty
/workspace/input. The gate now resolves the manager the session actually
runs on.
- Session to sandbox bindings were keyed by the tenant in context, which a
shared agent deliberately swaps for the agent owner's so models, KBs and
named configs resolve in the sharing workspace. Session deletion only ever
knows the session's own tenant, so teardown looked up a key nobody wrote
and abandoned a paused MicroVM that keeps billing. The binding tenant is
now carried separately and survives CloneContext.
* chore(sandbox): renumber migrations above upstream and de-collide test stub
Upstream main took 000079 (knowledge_folder_path) and 000080
(knowledge_base_auto_tag_config) while this branch was open, so the three
sandbox migrations move to 000081-000083. golang-migrate requires unique,
ordered versions, and the RAISE NOTICE labels move with the file names.
Main also added a handler test declaring stubSessionService in the same
package; the artifact download test's configurable variant is renamed rather
than merged, since the two stubs answer GetSession differently.
---------
Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
Unify request-local model-handle handling behind a single
modelcontext.Registry (source citations, durable resource handles, wiki
issue handles) with per-tool argument policies and unresolved-handle
rejection before tool execution.
Also fixes issues found in review:
- decode wiki_read_issue's iN issue_id argument (was never resolved)
- preserve stored wiki page aliases when wiki_write_page omits aliases
- validate http/https scheme before registering url fields as web sources
- gate tool-role MultiContent text behind the tool result policy
- dedup KB IDs in NewWikiScopesFromKBIDs to avoid false ambiguity
- remove dead codec facades (decodeJSON, EncodeMessagesWithPolicy,
UnresolvedToolHandles)
Move citation protocol injection to the system layer so custom prompts no
longer own citation syntax. Agents can disable inline citations while source
aliases still encode and decode tool arguments correctly.
Replace raw chunk/document/KB IDs in LLM context with short cN/dN/bN/wN
aliases, decode tool arguments on the way in, and expand compact <ref/>
citations to the public <kb>/<web> format before user-facing output.
Introduce resource://<handle> as the stable application identity for stored
objects, decoupling API responses, persisted rich text, and LLM prompts from
physical storage paths. Adds a resource catalog service (register/resolve/bind,
revocable expiring access grants), a request-local alias registry that compacts
resource references while in the LLM context and restores them (including across
streaming chunks), plus router, IM, chat-pipeline, and multimodal integration.
Includes schema migrations (resources, resource_bindings, resource_access_grants)
for sqlite, and hardens URL/output security handling.
Wire per-turn @mentions for skills, MCP services, tags, and files through
QA handlers into agent config, runtime_context/must_use user blocks, and
tool registration. Fix tag-only scopes dropping KB tools, refresh suggested
questions on mention changes, and strengthen MCP must_use so @selected
services are invoked before local KB search.
- Eliminated all instances of the final_answer tool from the agent's configuration and logic, transitioning to a model where the agent concludes responses with plain text instead.
- Updated event handling and response analysis to reflect this change, ensuring that the agent's output is now directly delivered as text without relying on a dedicated final answer tool.
- Adjusted localization strings across multiple languages to remove references to final_answer, enhancing clarity and consistency in user-facing messages.
- Improved the overall structure of the agent's response handling to streamline the process and reduce potential confusion regarding tool usage.
refactor(agent): streamline answer handling and preamble logic
- Updated the agent's response handling to treat any text streamed before a tool call as a preamble, ensuring it is not included in the final answer.
- Removed the superseded marker logic from the event emission process, simplifying the flow of answer content and enhancing clarity in the UI.
- Adjusted the event handling to ensure that preamble segments are correctly retracted and relocated into the steps tree, improving the overall user experience.
- Enhanced the agent's internal logic to better manage answer segments and their states during streaming, leading to a more coherent response structure.
MiMo and DeepSeek V3.2/V4 reject multi-turn requests in thinking mode
when the prior assistant message lacks reasoning_content with HTTP 400:
"The reasoning_content in the thinking mode must be passed back to the API."
Agent's ReAct loop is the worst-case scenario — every round produces tool
calls, exactly the case DeepSeek's docs specify reasoning_content MUST
participate in subsequent context.
Plumb reasoning_content through the full assistant-message round-trip:
- chat.Message / types.ChatResponse / types.AgentStep gain a
reasoning_content field (AgentStep persists via the existing
Message.AgentSteps jsonb column, no migration needed).
- streamLLMToEventBus accumulates reasoning chunks into
result.ReasoningContent and surfaces it on the round's ChatResponse.
- engine.runReActIteration writes it onto AgentStep so cross-turn replay
preserves it.
- observe.appendToolResults attaches it to the same-turn assistant
message; agent_history.buildAssistantHistoryMessages does the same on
cross-turn replay.
- RemoteAPIChat.ConvertMessages forwards it on assistant turns to
openai.ChatCompletionMessage.ReasoningContent (already supported by
go-openai); providers that don't recognize the field ignore it.
Tests cover the three boundaries: ConvertMessages serializes it for
upstream, appendToolResults preserves it within the same turn, and
buildAssistantHistoryMessages replays it across turns.
Scope is intentionally limited to Agent mode — KnowledgeQA's chat
pipeline and Anthropic's signed thinking_blocks are separate fixes that
require schema changes (rendered_content / thinking_blocks columns).
Fixes#1302
The Agent ran a parallel context cache (Redis/in-memory) on top of the
messages table to feed multi-turn history into the LLM. That dual-write
caused subtle drift (e.g. compression diverging from DB, system-prompt
swaps lost on restart) and required a separate ClearContext path on
session/IM clear.
Make the messages table the single source of truth:
- Add service.LoadAgentHistory: rebuilds chat.Message history per turn
from the persisted messages, expanding AgentSteps into proper OpenAI
assistant_with_tool_calls + tool messages and replaying the canonical
final answer (with <think> blocks stripped). final_answer tool calls
are filtered to avoid duplicating the trailing answer.
- Make AgentEngine stateless across turns: drop ContextManager / sessionID
cache plumbing from the engine, agent service, and CreateAgentEngine
signature. The engine only uses sessionID for logging/event emission.
- Wire AgentQA to load history from DB on demand using HistoryTurns
(default 5) when MultiTurnEnabled, otherwise run with empty history.
- Delete the llmcontext package (ContextManager interface, Redis/memory
storage, factory) and the SessionService.ClearContext API path; IM
/clear and session message clear no longer need to invalidate cache.
Behavior preserved: KnowledgeQA-mode replay is unchanged (turns with
empty AgentSteps just produce the single canonical assistant message),
and Agent-mode turns now consistently see prior tool calls and results.
Add an opt-in human approval gate so Agent runs pause before executing
MCP tools that operators flag as dangerous, surface an approval card in
the chat UI, and only resume after the user approves (optionally with
edited args) or rejects.
Backend
- New mcp_tool_approvals table + repo/service to mark per-tool approval
required (PG migration 000042 + sqlite init).
- approval.Gate coordinates RequestAndWait / Resolve with sync.Once
delivery, configurable timeout, and Redis Pub/Sub fan-out so multi-
replica deployments work without sticky sessions.
- MCPTool.Execute integrates the gate; uses a round-level ApprovalCtx
(without the per-tool 60s timeout) for the wait, and re-derives a
fresh 60s exec ctx after approval so CallTool keeps a full window.
- New SSE response types (tool_approval_required / _resolved) and
EventBus events plumb approval state to AgentStreamDisplay.
- REST: list/set per-tool approval flag, resolve pending approval.
- Configurable via agent.tool_approval_timeout_seconds (yaml) or
WEKNORA_AGENT_TOOL_APPROVAL_TIMEOUT env (accepts seconds or Go
duration).
Frontend
- MCP settings: per-tool "require approval" switch on the test panel.
- Chat: ToolApprovalCard renders the pause point with editable JSON
args, validation feedback, mm:ss countdown that turns warning/danger
near deadline, and a resolved state that retains context.
- i18n strings added for zh-CN / en-US / ko-KR / ru-RU.
Docs
- docs/zh/mcp-approval.md covering behavior, config, API, deployment
considerations (Redis cross-instance, restart limitations).
The existing Langfuse integration covered Chat / Embedding / Rerank / VLM /
ASR generations plus the HTTP + asynq spans, but the agent's own execution
tree was invisible: tool calls never appeared, multi-round ReAct iterations
were flat under the HTTP trace, and there was no single node representing
"one agent run".
This change adds three levels of agent-side spans:
- agent.execute — wraps AgentEngine.Execute, records query preview,
knowledge bases, allowed tools, final-answer length
and totals on finish.
- agent.round.<N> — wraps each ReAct iteration; records finish_reason,
tool-call count, token usage and duration.
- agent.tool.<name> — wraps each tool invocation; records arguments,
success, duration, output preview (rune-safe, 4KB
cap), error, data keys and image count.
To keep the loop's many exit paths (natural stop, stuck loop, empty-content
retry, final_answer, context cancellation) span-safe, the iteration body was
extracted into runReActIteration with a single defer span.Finish() and an
iterOutcome sentinel driving the outer loop. database_query arguments are
redacted (keys only) to avoid leaking raw SQL into the observability
backend, mirroring the existing UI hint policy.
Adds unit tests for the new helpers (truncateForLangfuse, argKeys, dataKeys,
finishToolSpan nil-safety, iterOutcome.String).
Added functionality to enable updates for the `wiki_config` field in the `KnowledgeBaseConfig` struct. This includes:
1. **Type Definition Update**: Added `WikiConfig` field to `KnowledgeBaseConfig` to allow JSON unmarshaling during update requests.
2. **Service Layer Enhancement**: Updated the `UpdateKnowledgeBase` method to persist changes to `wiki_config` when provided in the request.
3. **Frontend TypeScript Adjustments**: Enhanced type definitions in the frontend to support `wiki_config`, improving IDE autocomplete and type checking.
This fix addresses the critical issue where `wiki_config` was not being updated due to its absence in the `KnowledgeBaseConfig` struct, ensuring proper handling of wiki configurations during knowledge base updates.
- guard against empty content completion in analyzeResponse/executeLoop
with retry (max 2), nudge message, and fallback response
- propagate actual finish_reason through streaming pipeline instead of
hardcoding "stop" in streamThinkingToEventBus
- add FinishReason field to StreamResponse and streamLLMResult
- add finish marker chunk in processStreamDelta for empty content scenarios
- propagate lastFinishReason through EOF handler in processStream
- strengthen PureAgent system prompt with MCP tool guidelines and
graceful fallback instructions for unanswerable questions
- add unit tests for empty response bug and finish_reason propagation
- Improved the message consolidation logic to preserve the current turn's user query and all subsequent assistant/tool messages, ensuring better context retention.
- Updated the CompressContext function to reflect the new consolidation strategy, maintaining the system prompt and relevant recent messages.
- Refactored the context manager to support optional message repository for improved context rebuilding from persistent storage.
- Added comprehensive tests to validate the new consolidation behavior and ensure correct message handling across various scenarios.
- Added token usage tracking to the AgentEngine, allowing for better estimation of current context token counts.
- Implemented a new method to estimate current tokens based on previous usage and newly appended messages, improving context management.
- Updated context window management to utilize estimated token counts for more efficient message consolidation.
- Enhanced streaming methods to include token usage information, providing better insights into LLM interactions.
- Refactored the token estimator to support BPE tokenization, ensuring accurate token counts for messages.
- Added unit tests to validate new token estimation and context management functionalities.
- Removed the query display section from the DatabaseQuery component to streamline the UI.
- Updated the DatabaseQueryData interface to eliminate the query field, reflecting changes in tool result handling.
- Enhanced the DatabaseQuery tool execution to focus on returning structured results without exposing raw SQL queries.
- Added a new utility to strip <think> blocks from LLM outputs, improving content clarity and user experience.
- Introduced the AgentEngine with methods for executing tool calls, managing context windows, and handling final answer generation.
- Added functionality to stream LLM responses and tool results through the EventBus, enhancing real-time interaction.
- Implemented context management to consolidate messages and prevent exceeding token limits, ensuring efficient use of context.
- Enhanced error handling and logging for tool execution and response analysis, improving robustness and traceability.
- Added unit tests to validate the new functionalities and ensure reliability in agent operations.
- Introduced a default timeout for tool execution to prevent indefinite hangs during long-running tasks.
- Implemented context cancellation handling in the execution loop to gracefully manage timeouts and user cancellations.
- Added a JSON repair utility to fix common malformations in tool arguments, improving robustness in argument parsing.
- Enhanced message sanitization to merge consecutive user messages and handle orphaned tool results, ensuring compatibility with LLM providers.
- Added unit tests for the new JSON repair and message sanitization functionalities to validate their effectiveness.
- Introduced a memory consolidator to summarize older messages when the context window exceeds a specified limit, preserving key facts and tool results.
- Enhanced the AgentEngine to utilize the new token estimator and memory consolidator for improved context window management.
- Implemented logic to compress message history when approaching token limits, ensuring efficient use of context.
- Added unit tests for the memory consolidator and token estimator to validate functionality and performance.
- Updated tool execution to validate parameters against JSON schema before execution, improving error handling and robustness.
- Introduced a configurable LLM call timeout with a default value, allowing for better control over LLM call durations.
- Added logic to retry transient errors (e.g., timeouts, rate limits) up to a specified maximum number of retries, improving robustness in error handling.
- Implemented parameter casting for tool arguments to ensure correct types are used, addressing common LLM quirks.
- Enhanced tool execution error messages with guidance for retrying with different approaches.
- Added validation for configuration values to prevent runtime errors.
When an MCP tool returns image content items, the agent engine now
automatically generates text descriptions using the configured VLM
model and appends them to the tool result message. This makes image
content accessible to LLMs that receive tool results as text.
Images are not passed directly to the LLM because Chat Completions API
does not reliably support images in tool role messages across providers
(tested: gpt-5.4 silently ignores them, Qwen3.5 processes them).
Changes:
- Add Images field to ToolResult for preserving base64 data URIs
- Add extractContentAndImages() with MIME whitelist, size/count limits
- Add ImageDescriberFunc injection to AgentEngine (no vlm package dep)
- Add describeImages() with graceful error handling and ctx cancellation
- Add VLM model injection in CreateAgentEngine (same pattern as
SetAppConfig/SetSkillsManager)
- Redact image base64 from Data map to prevent log/SSE exposure
- Updated the AgentEngine to emit final answer events even when the LLM stops without calling the final_answer tool, ensuring the frontend can render responses correctly.
- Added fallback logic in the AgentStreamHandler to emit final answers as fallback events when no answer events are streamed, improving robustness in edge cases.
- Added timezone and language settings to the environment configuration.
- Introduced built-in agent configurations with multilingual support for various agents.
- Updated Docker Compose to utilize new environment variables for timezone and language.
- Created new prompt templates for question generation, summary generation, and keywords extraction.
- Added functionality for image uploads in chat, allowing users to attach images for multimodal Q&A.
- Enhanced the input field to handle image selection via drag-and-drop and paste, with validation for file types and sizes.
- Updated the backend to process images alongside text queries, including support for image analysis.
- Introduced new UI components for image previews and management, improving user interaction with uploaded content.
- Added localization strings for image upload features and error messages, enhancing accessibility for users in multiple languages.
These changes significantly improve the chat experience by enabling users to incorporate images into their queries, facilitating richer interactions and responses.
- Introduced the final_answer tool to ensure agents submit their complete responses as the last action, improving response accuracy and consistency.
- Updated the agent engine to log detailed information about tool calls and responses, including the total duration of agent execution.
- Enhanced the chat message model to include agent_duration_ms, tracking the total execution time from query start to answer delivery.
- Implemented JSON field extraction for streaming responses, allowing for more efficient handling of tool call outputs.
These changes significantly improve the agent's response handling and ensure that final answers are consistently delivered, enhancing overall user experience.
Convert all LLM-facing prompts, templates, and tool output labels to
language-neutral English so the model responds in the user's input
language. Update frontend relevance/match-type mappings to match.
Output language strategy:
- User-facing: reply in user's input language
- Vector-indexed: match source document language
- LLM-internal: fixed English