Agent improvement

Comments from @gagb:
Some observations:
1. the agent many times starts to suggest shell commands which makes the code fail. Especially as the conversation gets longer
2. Sometimes the user responds with empty strings and the code agent never returns terminal and the code gets stuck in a loop. Also happens when lang=unknown eg cuz the agent didn't wrap the python code in codeblockss
3. The code fails if the context size > 8k
Original comment: https://github.com/microsoft/FLAML/commit/3b3dd60730931c793e88e4b2aa870fa0192db3f5#diff-9ac9829642f8aa5ad3ed717f7f60eabedf33210195465c1f6473cd2cfd4cd2af

PR microsoft/FLAML#1025
```[tasklist]
### Tasks
- [ ] https://github.com/microsoft/autogen/issues/9
```