Files
d79f7f631b refactor(agent): one ordered media list for Runner inputs, attachments read by ref (#2959)
* 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>
2026-11-09 20:40:13 +08:00
..

DeerFlow Agent

Credentials and provider identifiers are opaque: api-key, auth-header, assistant-id, and model-name keep explicit whitespace and empty values. A nonempty auth-header overrides Bearer api-key. Invalid string/boolean/integer types fail with a field-only configuration error rather than being substituted.

Overview

Run a DeerFlow LangGraph agent as a LangBot Runner.

Package information

Capabilities

  • Enabled: streaming, multimodal input
  • Not declared: tool calling, knowledge retrieval, interrupt

Configuration

Field Type Required Default
api-base string Yes http://127.0.0.1:2026
api-key secret No Empty
auth-header secret No Empty
assistant-id string Yes lead_agent
advanced-settings boolean No false
model-name string No Empty
thinking-enabled boolean No false
plan-mode boolean No false
subagent-enabled boolean No false
max-concurrent-subagents integer No 3
timeout integer No 300
recursion-limit integer No 1000

Host permissions

  • storage: plugin

Installation and usage

  1. Install the plugin from the LangBot plugin marketplace.
  2. Select the Runner ID below in the Pipeline Runner selector.
  3. Fill in connection settings from the table and store credentials in secret fields in the admin UI.

Security and limitations

  • The runner can use only LangBot resources authorized for the current run.
  • Availability, model abilities, and rate limits depend on the external service.
  • See the full Chinese README at the package root for advanced behavior and product-specific limitations.

SDK 0.6.1 shared-runtime candidate

See shared-runtime boundaries and upgrade notes before upgrading.