dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-24 14:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

improved token limit err msgs and docs #678

Browse source
This commit is contained in:
Paul Gauthier 2024-06-14 07:28:33 -07:00
parent 0fc6b9beaa
commit a30e656304
3 changed files with 150 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

70
aider/coders/base_coder.py
View file

@ -795,8 +795,11 @@ class Coder:
except ExhaustedContextWindow:
exhausted = True
except litellm.exceptions.BadRequestError as err:
self.io.tool_error(f"BadRequestError: {err}")
return
if "ContextWindowExceededError" in err.message:
exhausted = True
else:
self.io.tool_error(f"BadRequestError: {err}")
return
except openai.BadRequestError as err:
if "maximum context length" in str(err):
exhausted = True
@ -804,12 +807,8 @@ class Coder:
raise err
if exhausted:
self.show_exhausted_error()
self.num_exhausted_context_windows += 1
self.io.tool_error("The chat session is larger than the context window!\n")
self.commands.cmd_tokens("")
self.io.tool_error("\nTo reduce token usage:")
self.io.tool_error(" - Use /drop to remove unneeded files from the chat session.")
self.io.tool_error(" - Use /clear to clear chat history.")
return
if self.partial_response_function_call:
@ -878,6 +877,63 @@ class Coder:
else:
self.reflected_message = add_rel_files_message
def show_exhausted_error(self):
output_tokens = 0
if self.partial_response_content:
output_tokens = self.main_model.token_count(self.partial_response_content)
max_output_tokens = self.main_model.info.get("max_output_tokens", 0)
input_tokens = self.main_model.token_count(self.format_messages())
max_input_tokens = self.main_model.info.get("max_input_tokens", 0)
total_tokens = input_tokens + output_tokens
if output_tokens >= max_output_tokens:
out_err = " -- exceeded output limit!"
else:
out_err = ""
if input_tokens >= max_input_tokens:
inp_err = " -- context window exhausted!"
else:
inp_err = ""
if total_tokens >= max_input_tokens:
tot_err = " -- context window exhausted!"
else:
tot_err = ""
res = ["", ""]
res.append(f"Model {self.main_model.name} has hit a token limit!")
res.append("")
res.append(f"Input tokens: {input_tokens} of {max_input_tokens}{inp_err}")
res.append(f"Output tokens: {output_tokens} of {max_output_tokens}{out_err}")
res.append(f"Total tokens: {total_tokens} of {max_input_tokens}{tot_err}")
if output_tokens >= max_output_tokens:
res.append("")
res.append("To reduce output tokens:")
res.append("- Ask for smaller changes in each request.")
res.append("- Break your code into smaller source files.")
if "diff" not in self.main_model.edit_format:
res.append(
"- Try using a stronger model like gpt-4o or opus that can return diffs."
)
if input_tokens >= max_input_tokens or total_tokens >= max_input_tokens:
res.append("")
res.append("To reduce input tokens:")
res.append("- Use /tokens to see token usage.")
res.append("- Use /drop to remove unneeded files from the chat session.")
res.append("- Use /clear to clear the chat history.")
res.append("- Break your code into smaller source files.")
res.append("")
res.append(f"For more info: {urls.token_limits}")
res = "".join([line + "\n" for line in res])
self.io.tool_error(res)
def lint_edited(self, fnames):
res = ""
for fname in fnames: