When a shell command times out, process.kill() is called but the
process object was never awaited after that. This leaves subprocess
pipes undrained and file descriptors open. If many commands time out,
fd leaks accumulate.
Add a bounded wait (5s) after kill to let the process fully terminate
and release its resources.
Address review feedback:
- Remove on_progress call for interim text to prevent duplicate
messages when the model simply answers a direct question
- Reset final_content to None before continue to avoid stale
interim text leaking as the final response on empty retry
Closes#705
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
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
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>
- 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
File tools now resolve relative paths (e.g., "test.txt") against the
workspace directory instead of the current working directory. This fixes
failures when models use simple filenames instead of full paths.
- Add workspace parameter to _resolve_path() in filesystem.py
- Update all file tools to accept workspace in constructor
- Pass workspace when registering tools in AgentLoop
Fix TypeError when LLM returns JSON objects instead of strings for
history_entry or memory_update.
Changes:
- Update prompt to explicitly require string values with example
- Add type checking and conversion for non-string values
- Use json.dumps() for consistent JSON formatting
Fixes potential memory consolidation failures when LLM interprets
the prompt loosely and returns structured objects instead of strings.
Re-bin
Rudolfs Tilgass
Nikolas de Hor
Darye
chtangwin
ruby childsandClaude Opus 4.6
dxtime
Ivan
nano bot
jopo
Harry Zhou
Oleg Medvedev
chengyongru
wymcmhandGitHub
Xubin RenandGitHub
3927o
lemon
Sergio Sánchez Vallés