xonecas.io
64875
Mc

mini-coder / commit e7ef185

chore: todo updates

Sean2026-03-01 e7ef1852b3283c7a8fef26ad13383bc244fddc2c parent 022d66b

1 file changed

TODO.md+6−6
@@ -1,11 +1,5 @@
11 # TODO
22
3-## Agent get's stuck on thinking
4-
5-- When using Google models, there is a rare occurence where the LLM seems to be stuck on thinking. There is no output for several minutes, and the only solution is to use CTRL+c to interrupt.
6-- This is not a infinite reasoning loop, there are requests being made, the app is "stuck", or "hanguing".
7-- Setting a thinkingConfig is also not a fix, 8000 is the default.
8-
93 ## Help agent edits error less:
104
115 - Agents sometimes include `|` at the end of the hash, this is because how we display the hashed to them, let's check if the anchor last char is `|` and strip it if it instead of letting it error.
@@ -18,6 +12,12 @@ https://exa.ai/docs/reference/search-quickstart
1812 https://exa.ai/docs/reference/contents-quickstart
1913 **Ask the user for text versions if you can't find these pages**
2014
15+## Agent get's stuck on thinking
16+
17+- When using Google models, there is a rare occurence where the LLM seems to be stuck on thinking. There is no output for several minutes, and the only solution is to use CTRL+c to interrupt.
18+- This is not a infinite reasoning loop, there are requests being made, the app is "stuck", or "hanguing".
19+- Setting a thinkingConfig is also not a fix, 8000 is the default.
20+
2121 ## Subagents don't have access to MCP tools?
2222
2323 Investigate if subagents are able to see the mcp tools. The user reported that after adding the exa mcp tools, that the subagents claimed to not be able to search online, but the main agent could.