* fix(browser): use openTab return value to prevent wsUrl race in ensureTabAvailable
When ensureTabAvailable opens a new tab on empty list, the return value
from openTab was discarded. A subsequent listTabs() call may return tabs
without webSocketDebuggerUrl populated yet, causing the wsUrl filter to
eliminate the newly opened tab and throw BrowserTabNotFoundError.
Fix: capture openTab's return value and merge it into candidates if the
wsUrl filter excluded it. openTab's internal discovery loop already
resolves wsUrl, so the returned tab is always valid.
* fix(browser): harden tab selection discovery
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(feishu): paginate wiki node and space listing (fixes#37626)
client.wiki.spaceNode.list / wiki.space.list return at most one page (max
50 items); the tool ignored has_more/page_token and silently dropped every
node past the first page. Drain both endpoints via a bounded shared helper
that loops on has_more with a 100-page safety cap.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(feishu): expose wiki pagination cursors
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(google): keep parallel Gemini tool responses in the turn after the model
On Gemini < 3 vision models, a parallel tool-call turn whose non-last result
returns an image split function responses across user turns. The merge heuristic
only inspected contents[last], so the separate "Tool result image:" turn landed
between two parallel responses and stranded the second one in a fresh turn. The
turn right after the model then carried fewer functionResponse parts than the
model issued functionCall parts, so Gemini returned 400 INVALID_ARGUMENT. Because
the malformed turn is persisted, every later turn re-400s and the session sticks.
Replace the contents[last] heuristic with a run-scoped accumulator: all responses
for one model turn merge into the single user turn after it, and Gemini < 3 image
turns defer to the end of the tool-result run so they trail that response turn.
Covers both google.ts and google-vertex.ts, which share this convertMessages.
* fix(google): align provider transport tool result turns
---------
Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com>
* fix(memory): await search-sync before returning results to prevent stale index
When the gateway process has been running for a while, memory_search
returns stale results because startAsyncSearchSync fires off the index
sync as a background task (void ... .catch()) without waiting for it
to complete. Search results are then read from the old index state.
Change startAsyncSearchSync from sync/fire-and-forget to async/await
so that the index is synced before search results are returned. This
ensures memory_search reflects the current filesystem state, matching
the behavior of the CLI command which creates
a fresh manager each time.
Fixes#52115
* test(memory): prove search waits for dirty sync
* test(memory): align search with synchronous sync
---------
Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com>
* fix(feishu): recover CJK filenames from JSON file_name field
Apply recoverUtf8FileNameFromLatin1Header to JSON-derived filenames in
extractFeishuDownloadMetadata, matching the behavior already present for
Content-Disposition headers in decodeDispositionFileName.
Fixes#81103
* fix(feishu): recover inbound CJK filenames
---------
Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com>
* fix(reasoning-tags): strip MiniMax `mm:` namespaced reasoning tags
MiniMax M3 (e.g. via Fireworks) emits its chain-of-thought inline in the
content stream wrapped in `<mm:think>…</mm:think>` rather than in a separate
`reasoning_content` field. The reasoning-tag stripper only recognized the
`antml:` namespace, so `mm:`-namespaced tags slipped through QUICK_TAG_RE and
leaked the model's hidden reasoning into visible chat output.
Accept the `mm:` prefix alongside `antml:` in the shared sanitizer
(reasoning-tags.ts) and in the Telegram reasoning-lane coordinator's tag regex
and prefix list. Adds unit tests covering mm: think/thinking/thought blocks,
truncated-open orphan close recovery, and code-fence preservation.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(reasoning): handle MiniMax tags in streams
---------
Co-authored-by: DrHack1 <DrHack1@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com>
* feat(inbound-meta): expose message_type in trusted inbound metadata (fixes#50482)
Add resolveInboundMessageType() that extracts the media type prefix
(e.g. 'audio' from 'audio/ogg') from MediaType or MediaTypes fields.
Expose it as message_type in the inbound metadata JSON so agents can
distinguish voice messages from typed text for turn-completion heuristics.
* fix(inbound-meta): preserve per-turn source modality
---------
Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com>
