Rename free_models.{json,py} → providers.{json,py}; fix stale GitHub base_url in README#31
Merged
BillJr99 merged 1 commit intoMay 29, 2026
Conversation
The sidecar holds templates for every supported provider, not only free ones — the believed_free / model_reasoning / free_limits fields are just the free-tier metadata for providers that offer it. Rename to reflect that: - llmproxy/free_models.json -> llmproxy/providers.json - llmproxy/free_models.py -> llmproxy/providers.py - tests/test_free_models_data.py -> tests/test_providers_data.py Update all imports (setup_wizard, scraper, sources, tests), DATA_PATH, setup.py package_data, the CI drift-guard message, and the README (file tree + all references). Also fix the one remaining stale GitHub Models base_url in the README provider table (Azure -> models.github.ai/inference). The update_free_models.py scraper keeps its name — it still updates the free-tier fields within providers.json. No behavior change; config.example regen is byte-identical.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 sidecar describes every supported provider — not just free ones. The
believed_free/model_reasoning/free_limitsfields are merely the free-tier metadata for providers that offer it. Thefree_modelsname was misleading, so this renames the data file and its loader, and cleans up the last stale GitHub Models endpoint reference.Renames (history preserved via
git mv)llmproxy/free_models.json→llmproxy/providers.jsonllmproxy/free_models.py→llmproxy/providers.pytests/test_free_models_data.py→tests/test_providers_data.pyReference updates
from llmproxy.free_models/from .free_models→…providers(setup_wizard, scraper,scripts/sources/api_models.py, and tests).DATA_PATH→providers.json;setup.pypackage_data→providers.json.providers.json.free_models.jsonreference →providers.json, with wording clarifying it holds all provider templates.base_urlin the README provider table:https://models.inference.ai.azure.com→https://models.github.ai/inference(the Azure endpoint was deprecated 2025-07-17 and stopped responding after 2025-10-17).Intentionally not renamed
scripts/update_free_models.pykeeps its name — it specifically updates the free-tier fields withinproviders.json, so the name is still accurate.Notes
config.example.jsonregeneration is byte-identical (the CI drift guard passes).claude/free-models-comparison-7vI4R) so this diff shows only the rename. Merge Expand free-model catalogs; add /version, non-root Docker, and config sync #30 first, then this.Test plan
ruffclean acrossllmproxy/,scripts/,tests/.python -c "from llmproxy.providers import load_data, DATA_PATH"loads 25 providers fromproviders.json.free_models.json/free_models.pyreferences ormodels.inference.ai.azure.comoccurrences.https://claude.ai/code/session_01Ey3m4qS4tWxG6kT5fF7YrA
Generated by Claude Code