Add agent-level timezone configuration with a UTC default, propagate it into runtime context and heartbeat prompts, and document valid IANA timezone usage in the README.
Keep the mypy-friendly optional execute signatures while returning clearer errors for missing arguments and locking that behavior with regression tests.
Made-with: Cursor
During testing, we discovered that when a user requests the agent to
send a file (e.g., "send me IMG_1115.png"), the agent would call
read_file to view the content and then reply with text claiming
"file sent" — but never actually deliver the file to the user.
Root cause: The system prompt stated "Reply directly with text for
conversations. Only use the 'message' tool to send to a specific
chat channel", which led the LLM to believe text replies were
sufficient for all responses, including file delivery.
Fix: Add an explicit IMPORTANT instruction in the system prompt
telling the LLM it MUST use the 'message' tool with the 'media'
parameter to send files, and that read_file only reads content
for its own analysis.
Co-Authored-By: qulllee <qullkui@tencent.com>
Replace the single _processing_lock (asyncio.Lock) with per-session locks
so that different sessions can process LLM requests concurrently, while
messages within the same session remain serialised.
An optional global concurrency cap is available via the
NANOBOT_MAX_CONCURRENT_REQUESTS env var (default 3, <=0 for unlimited).
Also re-binds tool context before each tool execution round to prevent
concurrent sessions from clobbering each other's routing info.
Tested in production and manually reviewed.
(cherry picked from commit c397bb4229e8c3b7f99acea7ffe4bea15e73e957)
Trigger token consolidation before prompt usage reaches the full context window so response tokens and tokenizer estimation drift still fit safely within the model budget.
Made-with: Cursor
- Add strip_think() to helpers.py as single source of truth
- Filter deltas in agent loop before dispatching to consumers
- Implement send_delta in TelegramChannel with progressive edit_message_text
- Remove duplicate think filtering from CLI stream.py and telegram.py
- Remove legacy fake streaming (send_message_draft) from Telegram
- Default Telegram streaming to true
- Update CHANNEL_PLUGIN_GUIDE.md with streaming documentation
Made-with: Cursor
Preserve the provider and agent-loop streaming primitives plus the CLI experiment scaffolding so this work can be resumed later without blocking urgent bug fixes on main.
Made-with: Cursor
Merge process_direct() and process_direct_outbound() into a single
interface returning OutboundMessage | None. This eliminates the
dual-path detection logic in CLI single-message mode that relied on
inspect.iscoroutinefunction to distinguish between the two APIs.
Extract status rendering into a pure function build_status_content()
in utils/helpers.py, decoupling it from AgentLoop internals.
Made-with: Cursor
Keep status output responsive while estimating current context from session history, dropping low-value queue/subagent counters, and marking command-style replies for plain-text rendering in CLI. Also route direct CLI calls through outbound metadata so help/status formatting stays explicit instead of relying on content heuristics.
Made-with: Cursor
Handle /status at the run-loop level so it can return immediately while the agent is busy, and reset last-usage stats when providers omit usage data. Also keep Telegram help/menu coverage for /status without changing the existing final-response send path.
Made-with: Cursor
Only normalize nullable MCP tool schemas for OpenAI-compatible providers so optional params still work without collapsing unrelated unions. Also teach local validation to honor nullable flags and add regression coverage for nullable and non-nullable schemas.
Made-with: Cursor
Keep multimodal tool outputs on the native content-block path while
restoring redirect SSRF checks for web_fetch image responses. Also share
image block construction, simplify persisted history sanitization, and
add regression tests for image reads and blocked private redirects.
Made-with: Cursor
- wire tools.exec.enable and deny_patterns into the current AgentLoop
- preserve the current WebSearchTool config-based registration path
- treat deny_patterns=[] as an explicit override instead of falling back
to the default blacklist
- add regression coverage for disabled exec registration and custom deny
patterns
Made-with: Cursor
- Catch asyncio.CancelledError separately from generic exceptions
- Re-raise CancelledError only when loop is shutting down (_running is False)
- Continue processing messages if CancelledError occurs during normal operation
- Prevents anyio/MCP cancel scopes from prematurely terminating the agent loop
Adjust the spawn tool description to keep the workspace-organizing hint while
avoiding language that sounds like the system automatically assigns a dedicated
working directory for subagents.
Made-with: Cursor
MCP servers (e.g. Zapier) return JSON Schema union types like
`"type": ["string", "null"]` for nullable parameters. The existing
`validate_params()` and `cast_params()` methods expected only simple
strings as `type`, causing `TypeError: unhashable type: 'list'` on
every MCP tool call with nullable parameters.
Add `_resolve_type()` helper that extracts the first non-null type
from union types, and use it in `_cast_value()` and `_validate()`.
Also handle `None` values correctly when the schema declares a
nullable type.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Addresses review feedback: moves schedule formatting and state
formatting into dedicated static methods, removes duplicate
in-loop imports, and simplifies _list_jobs() to a clean loop.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
_list_jobs() only displayed job name, id, and schedule kind (e.g. "cron"),
omitting the actual timing and run state. The agent couldn't answer
"when does this run?" or "did it run?" even though CronSchedule and
CronJobState had all the data.
Now surfaces:
- Cron expression + timezone for cron jobs
- Human-readable interval for every jobs
- ISO timestamp for one-shot at jobs
- Enabled/disabled status
- Last run time + status (ok/error/skipped) + error message
- Next scheduled run time
Fixes#1496
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace fire-and-forget consolidation with archive_messages(), which
retries until the raw-dump fallback triggers — making it effectively
infallible. /new now clears the session immediately and archives in
the background. Pending archive tasks are drained on shutdown via
close_mcp() so no data is lost on process exit.
PR #881 (commit 755e424) fixed the race condition between normal consolidation
and /new consolidation, but did so by making /new wait for consolidation to
complete before returning. This hurts user experience - /new should be instant.
This PR restores the original immediate-return behavior while keeping safety:
1. **Immediate return**: Session clears and user sees "New session started" right away
2. **Background archival**: Consolidation runs in background via asyncio.create_task
3. **Serialized consolidation**: Uses the same lock as normal consolidation via
`memory_consolidator.get_lock()` to prevent concurrent writes
If consolidation fails after session clear, archived messages may be lost.
This is acceptable because:
- User already sees the new session and can continue working
- Failure is logged for debugging
- The alternative (blocking /new on every call) hurts UX for all users
Instead of adding a separate load_skill tool to bypass workspace restrictions,
extend ReadFileTool with extra_allowed_dirs so it can read builtin skill paths
while keeping write/edit tools locked to the workspace. Fixes the original issue
for both main agent and subagents.
Made-with: Cursor
When restrictToWorkspace is enabled, the agent cannot read builtin skill
files via read_file since they live outside the workspace. This adds a
dedicated load_skill tool that reads skills by name through the SkillsLoader,
which accesses files directly via Python without the workspace restriction.
- Add LoadSkillTool to filesystem tools
- Register it in the agent loop
- Update system prompt to instruct agent to use load_skill instead of read_file
- Remove raw filesystem paths from skills summary
Xubin RenandXubin Ren
chengyongruandXubin Ren
19emtuckandXubin Ren
Eric YangandXubin Ren
gem12andXubin Ren
haosenwang1018andXubin Ren
vandazia
cdkey85andXubin Ren
JilunSun7274andXubin Ren
zhangxiaoyu.yorkandXubin Ren
BenandXubin Ren