feat(agent): expose model budgets and deterministic tool limits - #4954
Merged
Merged
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agents cannot configure provider output budgets or cap advertised tools, causing provider rejections and empty responses.
Add MaxTokens, Effort, Temperature and MaxTools options plus root-package Agent helpers. Forward settings through generation, streaming and ephemeral delegation. Cap the combined tool set deterministically by name and log omitted tools. Groq/OpenAI send explicit temperature (including zero) and return model.ErrOutputLimit for length finishes with no visible output; preserve stop reasons for partial responses.
Validation: fake-provider tests cover Ask, StreamAsk, Stream and delegation; deterministic tool-limit tests cover capped/unlimited lists. Local HTTP tests cover request options, tool follow-ups and empty/partial output limits for both providers and streaming modes. Build and lint pass. Full suite runs in CI.
Closes #4937