Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: use loguru native format and trim comments in interim retry

Browse Source
This commit is contained in:
Re-bin
2026-02-20 08:31:48 +00:00
parent 0660d614f6
commit 2383dcb3a8
2 changed files with 4 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -16,7 +16,7 @@
⚡️ Delivers core agent functionality in just **~4,000** lines of code — **99% smaller** than Clawdbot's 430k+ lines. ⚡️ Delivers core agent functionality in just **~4,000** lines of code — **99% smaller** than Clawdbot's 430k+ lines.
📏 Real-time line count: **3,781 lines** (run `bash core_agent_lines.sh` to verify anytime) 📏 Real-time line count: **3,793 lines** (run `bash core_agent_lines.sh` to verify anytime)
## 📢 News ## 📢 News

11
nanobot/agent/loop.py
View File

@@ -227,16 +227,11 @@ class AgentLoop:
) )
else: else:
final_content = self._strip_think(response.content) final_content = self._strip_think(response.content)
# Some models (MiniMax, Gemini Flash, GPT-4.1, etc.) send an # Some models send an interim text response before tool calls.
# interim text response (e.g. "Let me investigate...") before # Give them one retry; don't forward the text to avoid duplicates.
# making tool calls. If no tools have been used yet and we
# haven't already retried, add the text to the conversation
# and give the model one more chance to use tools.
# We do NOT forward the interim text as progress to avoid
# duplicate messages when the model simply answers directly.
if not tools_used and not text_only_retried and final_content: if not tools_used and not text_only_retried and final_content:
text_only_retried = True text_only_retried = True
logger.debug(f"Interim text response (no tools used yet), retrying: {final_content[:80]}") logger.debug("Interim text response (no tools used yet), retrying: {}", final_content[:80])
messages = self.context.add_assistant_message( messages = self.context.add_assistant_message(
messages, response.content, messages, response.content,
reasoning_content=response.reasoning_content, reasoning_content=response.reasoning_content,