feat(cli): add model profile max input tokens - #1520
Closed
Arthur Drozdov (arthur-drozdov) wants to merge 7 commits into
Closed
feat(cli): add model profile max input tokens#1520Arthur Drozdov (arthur-drozdov) wants to merge 7 commits into
Arthur Drozdov (arthur-drozdov) wants to merge 7 commits into
Conversation
Arthur Drozdov (arthur-drozdov)
requested a review
from Mason Daugherty (mdrxy)
as a code owner
February 26, 2026 17:33
github-actions
Bot
added
cli
Arthur Drozdov (arthur-drozdov)
marked this pull request as draft
February 26, 2026 17:53
… for profile support
github-actions
Bot
added
feature
github-actions
Bot
added
feature
Arthur Drozdov (arthur-drozdov)
marked this pull request as ready for review
February 26, 2026 19:11
github-actions
Bot
added
feature
Member
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR allows users to set a
max_input_tokensproperty inside their~/.deepagents/config.tomlthat acts as an explicit context limit for models (like OpenAI-compatible ones) that don't auto-report their profile sizes.The system dynamically instantiates string-declared models via
langchain.chat_models.init_chat_model, allowing the context limit to be explicitly bound to the model profile upon initialization. This properly enables fraction-based triggering inside the internal CLISummarizationMiddlewareeverywhere the deep agent operates, instead of defaulting to 170k.Related issue: #444
Changes
create_cli_agentto useinit_chat_modelfor string models, passing the explicitprofilekwarg ifmodel_context_limitis set.init_chat_modelpatching and profile injection logic.