Feature/token limit #193
Open
Feature/token limit #193
+130
−2
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
elaminm2003
force-pushed
the
feature/token-limit
branch
from
deea484 to
1dca53e
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #176
This PR introduces a necessary feature to prevent message history from growing indefinitely, which previously led to high operational costs and frequent context length errors in LLM calls.
We now enforce a configurable token limit, ensuring better stability and cost control.
Key Changes
Token Limit Enforcement:
Added a new setting, MAX_TOKEN_LIMIT (default: 100,000 tokens), in src/ansari/config.py.
Integrated the tiktoken library to accurately count tokens in the message history (src/ansari/agents/ansari.py).
The process_message_history function now checks the token count. If the limit is exceeded, the agent gracefully refuses to process the request and prompts the user to start a new conversation.
Bug Fix:
Resolved a circular import issue in src/ansari/app/main_api.py by reordering imports. This ensures the server starts correctly when whatsapp_router is included.
Testing
Added new unit tests in tests/unit/test_token_limit.py to verify that the token limit is enforced correctly (blocking long histories while allowing short ones).