Keep a bounded streaming preview, then deliver the complete final answer across multiple cards. Preserve all provider message IDs and cover long snapshots and Unicode boundaries with regression tests.
Fixes#78
Add shared /history parsing, read-only session access, message filtering, and bounded replies. Default to three messages, cap at five, and exclude saved history commands.
Include channel integration tests, translations, command help, and the Issue #62 implementation plan.
Wrap all user-facing chat text in src/channels with a host-side t()
translator (Chinese is the identity default, so untranslated text is
always sent verbatim in Chinese). English is selected via the host
plugin config `language: en` or the DSH_IM_LANGUAGE environment
variable, and the settings UI keeps following the DSH web locale.
- add src/channels/shared/i18n.mjs with setImHostLanguage/t() and a
Chinese-key -> English dictionary split by area (shared + channels)
- complete the English dictionary for every t() key in src/channels,
including the feishu channel (welcome/help, repair flow, interactive
cards, watch flow) and the shared command/approval/stream text
- wrap previously untranslated chat-facing strings in feishu bridge,
feishu runtime, editable-message-stream, harness-client,
connection-test and image-prompt
- dedupe dictionary entries that existed in multiple channel files and
canonicalize conflicting translations into the shared dictionaries
- extend the i18n unit test to decode string-literal escapes so keys
containing \n are checked correctly
- document the language switch in README.md, README.en.md and
CHANGELOG.md, and rebuild lib/index.js
Added English support for bot chat messages across all nine IM
channels and AI Office without changing any Chinese output.
Resolve qq-bridge.mjs by keeping the inbound-file support (hasFiles,
files passthrough) and dropping the upstream stream session, which
this branch replaces with the discrete turn-feed notices.
Show what the agent is actually doing during a turn, the way Claude
Code does: interim explanation text, every Tool call, and the error
detail when a tool fails, each as its own pushed message before the
final markdown answer.
- HarnessReplyTracker.consume now returns every frame of a polling
batch in order (same-batch text frames collapse to the latest)
instead of dropping all but the last event, which silently ate
tool-call frames that shared a batch with their result
- tool frames carry callId; status frames carry the correlated
toolName and a flattened error text parsed from the tool/result
error payload (message, or name: code)
- the QQ bridge holds interim step text until the next tool call
(or the end of the turn) pushes it, emits 'Tool call <name>' per
call, emits 'Tool call <name>\nError: <reason>' for failures, and
skips re-sending interim text that already equals the final answer
Other channels keep their existing behaviour: the status frame still
reads '正在整理结果…' and they ignore the new optional fields.
The menu card renders the repair fallback as **5**<emoji>修复, so the two assertions that matched **5**修复 are broadened to tolerate the marker emoji. The number-reply on a later session page now reads the last text confirmation instead of assuming the last outgoing message is text, since #bindSession refreshes the menu card after binding. Rebuild bundle.
- /watch resolves the target READ-ONLY: sessions are validated against
registered workspace listings (current or any other) without binding the
conversation or switching workspaces. /unwatch and /watchlist round out
the command set; the watchlist card supports button and number-reply
unwatching.
- Watches persist in the state store (sessionId + title + chatId + lastSeq)
and resume at runtime start: the bridge starts the global event-mux
watcher in its constructor when the harness supports it.
- Completion pushes fire on turn/end, deduped by sessionId + turn id, with
the seq watermark persisted per watch. After a mux reconnect the bridge
replays each watched session's recent history (session.history) through
the normal handler, so missed turn/end events are compensated without
duplicates.
- Bound-session push targets are persisted (chatTargets) instead of living
only in memory, and refresh on every accepted message.
- Watch failures map to safe user-facing messages.
- /m (or /menu) opens a card menu; /sessionlist and /workspacelist render
cards with bind/switch buttons; number replies stay usable as a fallback
when the app does not subscribe card.action.trigger.
- card.action.trigger callbacks validate the operator's open_id against the
allowed senders: group members outside the allowlist can never drive
binding, workspace switches or other card actions.
- Session-list pagination uses page numbers everywhere (buttons carry
sessions:<page>), fixing the previous double page-size scaling that
skipped pages past 20 sessions.
- Bind/workspace failures map to safe user-facing messages instead of raw
error details.
- Apps registered after this change subscribe card.action.trigger during
the scan flow.
