* feat(box): bidirectional attachment transfer for sandbox
Materialize inbound attachments into the sandbox workspace so agents can
process user-sent files, and collect agent-produced files from the outbox
to attach them back to the reply.
- box(service): add materialize_inbound_attachments / collect_outbound
attachments. Prefer direct host-filesystem read/write on the bind-mounted
workspace (no size limit), falling back to chunked exec only for
non-shared backends (e2b/remote). Clear per-query inbox/outbox dirs at
turn start to avoid query_id-reuse collisions.
- provider(localagent): inject inbound attachment descriptors into the
sandbox and append a system note telling the agent the inbox/outbox paths.
- pipeline(wrapper): collect outbox files on the final stream chunk and
append them as attachment components to the response chain.
- web(debug-dialog): render File components with a download link when
base64/url is present; add base64/path fields to the File entity.
- tests: cover inbound/outbound, large-file transfer without truncation,
and stale-dir clearing (86 passing).
* feat(box): support voice/file attachment round-trip end-to-end
Extends the bidirectional attachment transfer to audio and arbitrary files
through the real webchat UI, and fixes the model-payload errors that
non-image attachments triggered.
- platform(websocket_adapter): resolve Voice/File component storage keys to
base64 (previously only Image), so audio/documents reach the sandbox inbox.
- web(debug-dialog): accept audio/* and any file in the uploader (was
image-only), classify by mimetype, upload Voice/File via the documents
endpoint, and render non-image staged attachments as a chip.
- provider(litellmchat): drop non-image file parts (file_base64 / file_url)
when building the OpenAI/LiteLLM payload. These come from Voice/File
attachments — including ones replayed from conversation history — and the
agent reads their bytes from the sandbox, not the model. Without this the
provider rejects the request: 'invalid content type=file_base64'.
- provider(localagent): also strip those parts from the current user message
alongside the sandbox-path note (model-facing clarity; the requester is the
real safety net for history).
- tests: cover the requester strip/keep behavior (file dropped, image kept and
reshaped to image_url, mixed history, plain-string content).
* test(box): cover inbound/outbound attachment helpers; fix ruff format
- ruff format localagent.py (CI ruff format --check was failing)
- add unit tests for ResponseWrapper outbound-attachment helpers (wrapper.py 78%->98%)
- add unit tests for LocalAgentRunner._inject_inbound_attachments
- add unit tests for WebSocketAdapter._process_image_components (0%->covered)
Lifts PR patch coverage from 68.97% to ~88% (>75% target).
* feat: add WebChat adapter for pipeline debugging
- Create WebChatAdapter for handling debug messages in pipeline testing
- Add HTTP API endpoints for debug message sending and retrieval
- Implement frontend debug dialog with session switching (private/group chat)
- Add Chinese i18n translations for debug interface
- Auto-create default WebChat bot during database initialization
- Support fixed session IDs: webchatperson and webchatgroup for testing
Co-Authored-By: Junyan Qin <Chin>, 秦骏言 in Chinese, you can call me my english name Rock Chin. <rockchinq@gmail.com>
* perf: ui for webchat
* feat: complete webchat backend
* feat: core chat apis
* perf: button style in pipeline card
* perf: log btn in bot card
* perf: webchat entities definition
* fix: bugs
* perf: web chat
* perf: dialog styles
* perf: styles
* perf: styles
* fix: group invalid in webchat
* perf: simulate real im message
* perf: group timeout toast
* feat(webchat): add supports for mentioning bot in group
* perf(webchat): at component styles
* perf: at badge display in message
* fix: linter errors
* fix: webchat was listed on adapter list
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin>, 秦骏言 in Chinese, you can call me my english name Rock Chin. <rockchinq@gmail.com>
Junyan Chin