* fix(provider): decouple token counting from reasoning validation
Co-authored-by: multica-agent <github@multica.ai>
* fix(plugins): 修复 EssentialCommands !func 兼容性并清理 HelloPlugin 调试输出 (LANG-391) (#2967)
Co-authored-by: multica-agent <github@multica.ai>
* fix(plugin): wait for runtime recovery before workspace dispatch (#2968)
Co-authored-by: multica-agent <github@multica.ai>
* fix(runner): wait for installed plugins to initialize (LANG-393) (#2971)
Co-authored-by: multica-agent <github@multica.ai>
* fix(persistence): release SQLite writer during image refresh (#2973)
Co-authored-by: multica-agent <github@multica.ai>
* fix(telemetry): report cancellations as cancelled, keep route failure detail, tolerate already-terminal runs (#2974)
- Cancelled ingress / handed-off lanes / event deliveries close as `cancelled`
instead of `failed` (CancelledError and GeneratorExit).
- Every `runner_failed` event-route record carries the exception type and
message in `error`, including invalid Agent configuration.
- Closing the stream of a run another writer already finalized no longer
raises "Cannot transition terminal run"; the ledger status is kept and
reported, and the Runner's own error propagates.
- Platform API calls that return None without raising are `success`, not
`unknown`.
- Command lanes name their adapter and no longer claim the Pipeline's
configured Runner; only a Runner that actually ran is attributed.
LANG-395
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): bound token counting and preserve text turns on failure
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(acp): 修复文件回复的调用上下文与原始消息定位
* style(acp): 修正上下文回归测试的 Ruff 格式
* fix(acp): send ACP-shaped MCP descriptors and dispatch daemon MCP calls concurrently
- Serialize MCP servers for ACP through one shared helper so HTTP headers and
stdio env are always [{name, value}] arrays (local and daemon paths alike);
OpenCode rejects session/new with -32602 when headers is missing.
- Dispatch daemon mcp.request in its own task inside the owning job's
Context so a slow tool call no longer blocks pings, run events or other
jobs on the same daemon socket; cancel in-flight calls on disconnect after
the daemon ID is released.
- Keep runtime internals out of the public Runner API docs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Junyan Qin (Chin) <rockchinq@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* refactor(agent): derive Runner input media from one ordered list
Every Runner input is now rendered once from the platform message chain
by agent/runner/input_media.py, replacing the contents/message-chain
cross matching, the descriptor merge from #2926 and the Box ref
reconciliation:
- contents place [attachment att-N: <type> <name>] at each media
position; quoted messages are wrapped in [quoted message from X] ...
[/quoted message] and their media marked source=quote.
- attachments describe the same media one-to-one as metadata only and
never carry inline content. Media added by user_message_alter stay
model-only.
- read_input_attachment(ref) serves bytes on demand (ExecutionAPI run
scope, available_apis.input_attachments): base64, http(s) URL,
adapter path, then adapter get_file_url for ID-only media; 10 MiB per
attachment, 50 MiB per run, no caching or payload logging.
- Event envelopes carry inline payloads Host-internally until
prepare_input_files registers them by ref; steering items drop refs
that would address the claimed run's own input.
- The media cache defaults to a 1024 MB cap (oldest removed first).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* docs(plugin): document input attachment refs and read_input_attachment
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* feat(plugins): read input attachments by ref in official Runners
Dify, Coze, Tbox and ACP read attachment bytes with
ctx.read_input_attachment when the SDK and Host support it, upload each
media once under an att-N prefixed name, and skip unreadable ones;
older SDKs or Hosts keep the previous inline/URL/contents logic.
DeerFlow takes images from contents only on current Hosts, n8n forwards
attachment metadata, and LocalAgent exposes refs to the model.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* chore(deps): pin langbot-plugin 0.7.23 from PyPI
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* docs(plugin): note the SDK version for read_input_attachment
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(plugin): accept the SDK send_message timeout and route read_input_attachment
SDK 0.7.23 sends a client-side send_message timeout that the Runtime
strips; an older Runtime forwards it unchanged, so the Host now accepts
and ignores it instead of rejecting the call. The routing integration
test covers the new read_input_attachment operation.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
Pipelines on adapters without streamed replies (QQ, OneBot, ...) ran the
response stages once per runner turn, so only the final message reached the
platform and progress messages a Runner completed before its answer were
dropped. Send every completed assistant message as its own reply, matching
Agent bindings; tool-call rounds and deltas stay aggregated, so single-message
runners (LocalAgent and the other official runners) keep one reply per turn.
Refs LANG-325
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
send_message now waits 60s by default and accepts a keyword-only
`timeout` (langbot-app/langbot-plugin-sdk#219). Document the parameter,
its validation, the fact that a timeout does not cancel the host send,
and the SDK/Runtime version requirement in zh/en/ja.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
- Document workspace.language.get with exposure 'all' and risk 'read' so
plugins can declare it and Agents/Pipelines can select it as a workspace
tool. It requires workspace.view, takes no arguments and reads the
Workspace only from the trusted context. workspace.language.update stays
member/API-key only.
- Declare the operation in LocalAgent.
- Document it in zh/en/ja plugin Workspace API references and dev-docs.
- Cover grants, denial, invalid input, the unset default and the processor
tool path.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* feat(monitoring): show messages handled by plugins in monitoring
A plugin can take a message over with prevent_default() and answer through
ctx.reply / send_message / invoke_llm. Monitoring then showed the user
message as handled by the pipeline Runner, with no reply, no LLM call and
no delivery errors (LANG-320).
- monitoring_messages.handled_by (0045): runner:<id> | plugin:<author>/<name>;
plugin-handled messages no longer claim the Runner.
- Attribute prevent_default to the plugin reported by the Runtime, falling
back to a single emitted plugin for older Runtimes.
- Record ctx.reply and plugin send_message as assistant messages, with
PluginReplyError / PluginSendError on failure; delivery behaviour is
unchanged and monitoring failures are swallowed.
- Link plugin-level LLM calls and sends to the triggering message through
origin_query_uuid. The Host opts in per event (origin_attribution), so
plugins never send the new field to Hosts with strict schemas. Used for
attribution only, never for authorization.
- WebUI: "Handled by plugin" badge in the execution list and detail.
- Docs (zh/en/ja) and dev-docs contract note.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* test(migrations): account for the 0045 handled_by index on downgrade
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* test(postgres): register the capacity requester instead of patching _build_provider
#2896 builds providers on a staged ModelManager during load_models_from_db,
so the per-instance _build_provider patch no longer applied and the populated
Cloud startup test loaded zero providers on master. Register a network-free
requester that the staged manager inherits instead.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* feat(api): open marketplace search and install to plugins and Agents
- Add plugin.marketplace.search, a read operation that proxies the configured
Space plugin search, honours plugin.enable_marketplace and returns only the
fields needed to install.
- Expose plugin.install.marketplace to plugins and processors as a dangerous
operation. Plugins and Agents cannot auto-confirm permissions or replace an
installed plugin; new installations stay disabled until a member confirms.
GitHub and local installs keep their current exposure.
- Expose task.get so callers can follow installation progress; non-member
principals receive the public projection, now including
pending_permission_confirmation.
- Declare the new operations in LocalAgent, document them in zh/en/ja and
localize the new errors.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* test(api): include marketplace search and task status in processor read sweep
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
Unified Workspace and execution APIs for LangBot (#2639).
- Versioned Application API shared by HTTP, MCP, the Workspace assistant
and plugins, with one authorization and error contract.
- Execution API facade for every plugin and Runner action.
- Plugin installation permissions: manifest declarations, member
confirmation, capability ceilings, compatibility mode, revocation and
audit. Typed Workspace API in the plugin SDK.
- Processor tool configuration: workspace operations, event and bot tools,
default tool sets for new Agents and Pipelines, and sensitive-tool
warnings.
- Plugin permission picker in the WebUI; LocalAgent declares every
plugin-callable permission.
- Documentation for plugin permissions and the Workspace API in English,
Chinese and Japanese.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* 重构文档结构:移除 docs 目录,调整文件组织结构
* Reorder "插件 SDK API" section in docs.json
* Refactor and clarify various documentation sections
* Refine warnings and info boxes across multiple docs
* Refactor and simplify Japanese documentation content
* Update package.json to include mintlify as a dependency and add pnpm-lock.yaml for dependency management
* Update blog link and add description in docs.json
---------
Co-authored-by: Junyan Chin <rockchinq@gmail.com>