Repository navigation
Document the model defaults and overrides the code actually uses - #11
Merged
Merged
Conversation
The README listed `gemini-2.0-flash` as the Gemini model. The provider moved to the `gemini-flash-latest` alias because that pinned model was shut down, and the README still pointed readers at it. The EMC_ANTHROPIC_MODEL and EMC_GEMINI_MODEL overrides were not documented. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UigC7feaY8NkAy9oay3GDW
ethanzhoucool
marked this pull request as ready for review
November 3, 2026 17:23
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The README's environment-variable table disagreed with
narrate/llm.py:gemini-2.0-flash. The provider's default isGeminiProvider.DEFAULT_MODEL = "gemini-flash-latest", and its docstring explains why:gemini-2.0-flashwas shut down, and that broke v1. So the README pointed readers at the dead model.EMC_ANTHROPIC_MODELandEMC_GEMINI_MODELare read by the providers but were not documented.Changes
README.md: corrected the Gemini default, and added rows for the two model overrides. TheEMC_GEMINI_MODELrow describes whatGeminiProvider.completedoes on a 404: it retries once against a current model.enrich()then reports that model asenrichment.model, because it readsprovider.modelafter the call.Testing
Docs only. I checked each value against
explain_my_code/narrate/llm.py: theEMC_ANTHROPIC_MODELdefaultclaude-opus-5,DEFAULT_MODEL,EMC_GEMINI_MODEL, and the 404 retry path incomplete().Notes
The hardcoded test counts (the badge's "145 passing", plus "145 tests" in the layout and testing sections) are already stale:
maincollects 150 (147 passed, 3 skipped), and the other open PRs add more. I left them for you to update once those PRs land, or to turn into a CI-driven badge.Generated by Claude Code