The send() payload contains user message content (msg.content) which
may include non-ASCII characters (e.g. CJK, German umlauts, emoji).
The auth frame and Discord heartbeat/identify payloads are left
unchanged as they only carry ASCII protocol fields.
Some LLM providers (MiniMax, Gemini Flash, GPT-4.1, etc.) send an
initial text-only response like "Let me investigate..." before actually
making tool calls. The agent loop previously broke immediately on any
text response without tool calls, preventing these models from ever
using tools.
Now, when the model responds with text but hasn't used any tools yet,
the loop forwards the text as progress to the user and gives the model
one additional iteration to make tool calls. This is limited to a
single retry to prevent infinite loops.
Closes#705
The /help command was routed through _forward_command → _handle_message
→ is_allowed(), which denied access to users not in the allowFrom list.
Since /help is purely informational, it should be accessible to all
users — similar to how /start already works with its own handler.
Add a dedicated _on_help handler that replies directly without going
through the message bus access control.
Closes#687
Add a `_consolidating` set to track which sessions have an active
consolidation task. Skip creating a new task if one is already in
progress for the same session key, and clean up the flag when done.
This prevents the excessive API calls reported when messages exceed
the memory_window threshold — previously every single message after
the threshold triggered a new background consolidation.
Closes#751
Wire up an AgentLoop with an on_job callback in the cron_run CLI
command so the job's message is sent to the agent and the response
is printed. Previously, CronService was created with no on_job
callback, causing _execute_job to skip execution silently and
always report success.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The deny pattern `\b(format|mkfs|diskpart)\b` incorrectly blocked
commands containing "format" inside URLs (e.g. `curl https://wttr.in?format=3`)
because `\b` fires at the boundary between `?` (non-word) and `f` (word).
Split into two patterns:
- `(?:^|[;&|]\s*)format\b` — only matches `format` as a standalone
command (start of line or after shell operators)
- `\b(mkfs|diskpart)\b` — kept as-is (unique enough to not false-positive)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add VolcEngine ProviderSpec entry in registry.py
- Add volcengine to ProvidersConfig class in schema.py
- Update model providers table in README.md
- Add description about VolcEngine coding plan endpoint
Adds `_validate_schedule_for_add()` to `CronService.add_job` so that
invalid or misplaced `tz` values are rejected before a job is persisted,
regardless of which caller (CLI, tool, etc.) invoked the service.
Surfaces the resulting `ValueError` in `nanobot cron add` via a
`try/except` so the CLI exits cleanly with a readable error message.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Strip non-standard keys like 'reasoning_content' before sending to LLM
- Always include 'content' key in assistant messages (required by StepFun)
- Add _sanitize_messages to LiteLLMProvider to prevent 400 BadRequest errors
