The Anthropic SDK raises a client-side ValueError when a non-streaming
`messages.create` call could exceed the 10-minute server timeout (e.g.
high `max_tokens` combined with extended thinking budget). The error
text "Streaming is required for operations that may take longer than
10 minutes" was bubbling up to the user as an opaque LLM error in
channels that use the non-stream path (e.g. wecom in #2709).
Detect this specific ValueError in `chat()` and transparently retry
through `chat_stream()` (without `on_content_delta` so behavior matches
the non-stream contract). Other ValueErrors continue to flow through
`_handle_error` unchanged.
Closes#2709
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the Matrix homeserver returns M_UNKNOWN_TOKEN / M_FORBIDDEN /
M_UNAUTHORIZED (or soft_logout), the previous _sync_loop kept retrying
sync_forever every 2 seconds forever, spamming the homeserver and
filling logs (#1851). The auth state cannot recover by retrying, so
this is pure noise and a soft DoS on the homeserver.
- Extract `_is_fatal_auth_response()` helper
- In `_on_sync_error`, on fatal auth: set `_running=False` and call
`stop_sync_forever()` so the loop exits cleanly
- Add exponential backoff (2s → 60s cap) to the generic exception path
in `_sync_loop` so transient network blips also stop hammering
Closes#1851
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Matrix sync replays the room timeline on each startup or `/restart`,
causing already-handled messages to be reprocessed (#3553). Even with
`store_sync_tokens=True`, the sync token isn't reliably re-injected
when restoring a session via access_token + load_store(), so the
client re-reads recent timeline entries.
Filter `event.server_timestamp` against the process start time so old
events are dropped at the `_on_message` / `_on_media_message` entry
points. Trade-off: messages received during downtime won't be
processed, which matches the issue reporter's expectation.
Closes#3553
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR #3125 added a top-level `oneOf` branch to `_CRON_PARAMETERS` to
advertise per-action required fields. OpenAI Codex/Responses rejects
`oneOf`/`anyOf`/`allOf`/`enum`/`not` at the root of function
parameters, so any agent that registers the cron tool now fails to
start with:
HTTP 400: Invalid schema for function 'cron': schema must have
type 'object' and not have 'oneOf'/'anyOf'/'allOf'/'enum'/'not'
at the top level.
Remove the top-level `oneOf`. The original intent of #3125 (stop LLMs
from looping on the #3113 contract mismatch) is preserved by:
- `validate_params` — runtime-enforces `message` for `action='add'`
and `job_id` for `action='remove'`
- field descriptions — each schema field already flags
"REQUIRED when action='...'" so the LLM sees the contract
The regression test is updated to lock the invariant in the other
direction: the top-level schema must not contain
`oneOf`/`anyOf`/`allOf`/`not`, and the REQUIRED hints must stay on
`message` and `job_id`.
Verified:
- tests/cron/ 70 passed
- tests/agent/test_loop_cron_timezone.py + tests/providers/ 232 passed
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
- Add field to ProviderSpec (default True)
- Add and methods in LiteLLMProvider
- Filter image_url content blocks in before sending to non-vision models
- Reverts session-layer filtering from original PR (wrong layer)
This fixes the issue where switching from Claude (vision-capable) to
non-vision models (e.g., Baidu Qianfan) causes API errors due to
unsupported image_url content blocks.
The provider layer is the correct place for this filtering because:
1. It has access to model/provider capabilities
2. It only affects non-vision models
3. It preserves session layer purity (storage should not know about model capabilities)
Feishu downloads images with incorrect extensions (e.g. .jpg for PNG files).
mimetypes.guess_type() relies on the file extension, causing a MIME mismatch
that Anthropic rejects with 'image was specified using image/jpeg but appears
to be image/png'.
Fix: read the first bytes of the image data and detect the real MIME type via
magic bytes (PNG: 0x89PNG, JPEG: 0xFFD8FF, GIF: GIF87a/GIF89a, WEBP: RIFF+WEBP).
Fall back to mimetypes.guess_type() only when magic bytes are inconclusive.
Commit 0209ad5 moved `import lark_oapi as lark` inside the start()
method (lazy import) to suppress DeprecationWarnings. This had an
unintended side effect: the import now happens after the main asyncio
loop is already running, so lark_oapi's module-level
loop = asyncio.get_event_loop()
captures the running main loop. When the WebSocket thread then calls
loop.run_until_complete() inside Client.start(), Python raises:
RuntimeError: This event loop is already running
and the _connect/_disconnect coroutines are never awaited.
Fix: in run_ws(), create a fresh event loop with asyncio.new_event_loop(),
set it as the thread's current loop, and patch lark_oapi.ws.client.loop
to point to this dedicated loop before calling Client.start(). The loop
is closed on thread exit.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Part 1: Make system prompt static
- Move Current Time from system prompt to user message prefix
- System prompt now only changes when config/skills change, not every minute
- Timestamp injected as [YYYY-MM-DD HH:MM (Day) (TZ)] prefix on each user message
Part 2: Add second cache_control breakpoint
- Existing: system message breakpoint (caches static system prompt)
- New: second-to-last message breakpoint (caches conversation history prefix)
- Refactored _apply_cache_control with shared _mark() helper
Before: 0% cache hit rate (system prompt changed every minute)
After: ~90% savings on cached input tokens for multi-turn conversations
Closes#981
- cancel_by_session: use asyncio.gather for parallel cancellation
instead of sequential await per task
- _dispatch: register in _active_tasks before acquiring lock so /stop
can find queued tasks (synced from #1179)
- SubagentManager tracks _session_tasks: session_key -> {task_id, ...}
- cancel_by_session() cancels all subagents for a session
- SpawnTool passes session_key through to SubagentManager
- /stop response reports subagent cancellation count
- Cleanup callback removes from both _running_tasks and _session_tasks
Builds on #1179
- Add commands.py with CommandDef registry, parse_command(), get_help_text()
- Refactor run() to dispatch messages as asyncio tasks (non-blocking)
- /stop is an 'immediate' command: handled inline, cancels active task
- Global processing lock serializes message handling (safe for shared state)
- _pending_tasks set prevents GC of dispatched tasks before lock acquisition
- _dispatch() registers/clears active tasks, catches CancelledError gracefully
- /help now auto-generated from COMMANDS registry
Closes#849
- Defer Brave API key resolution to execute() time instead of __init__,
so env var or config changes take effect without gateway restart
- Improve error message to reference actual config path
(tools.web.search.apiKey) instead of only mentioning env var
Fixes#1069 (issues 1 and 2 of 3)
- Add content extraction for share cards (chat, user, calendar event)
- Add recursive parsing for interactive card elements
- Fix image download API to use GetMessageResourceRequest with message_id
- Handle BytesIO response from message resource API
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Add download functionality for multimedia messages in Feishu channel,
enabling agents to process images, audio recordings, and file attachments
sent through Feishu.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
