Open
Conversation
- Change repo references from cc-nim to free-claude-code - Update default model to moonshotai/kimi-k2.5
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…cher Add ./claude-free interactive model picker script that lets users choose any NVIDIA NIM model at launch time. Add model override support via auth token format (freecc:org/model-name). Add GET /v1/models endpoint. Rewrite README for clarity with troubleshooting section. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move PM2 and fzf into the prerequisites table so users install them upfront. Use pm2 start as the default proxy command instead of a foreground process. Remove the now-redundant background proxy section. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace Options A/B/C with a single "Set Up Aliases" section. Remove the Development section. Update Step 4 description and example path. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Runs every 6 hours to merge upstream changes. Uses -X ours so fork edits are never overwritten on conflicts. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sync workflow: add concurrency group, merge-then-rebase fallback, pre-push origin check, and push retry loop to prevent non-fast-forward failures. routes.py: replace broken inline optimizations with try_optimizations() and switch from missing stdlib logger to loguru, matching upstream's refactor. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Restore missing environment variables and documentation to ensure feature parity with upstream. Changes include: .env.example: - Add PROVIDER_TYPE with all 3 options (nvidia_nim, open_router, lmstudio) - Add OpenRouter config (OPENROUTER_API_KEY) - Add LM Studio config (LM_STUDIO_BASE_URL) - Add Discord config (DISCORD_BOT_TOKEN, ALLOWED_DISCORD_CHANNELS) - Add generic provider rate limiting (PROVIDER_RATE_LIMIT, PROVIDER_RATE_WINDOW) - Fix MESSAGING_RATE_LIMIT from 1 to 40 (upstream default) - Update default MODEL to stepfun-ai/step-3.5-flash README.md: - Add "How It Works" section with architecture diagram - Add "Providers" comparison table for all 3 providers - Add complete Discord Bot setup instructions - Reorganize: move Model Aliases after Quick Start - Update Configuration Reference with all missing variables - Add MESSAGING_PLATFORM env var to bot setup examples Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Move fork-specific model picker features into separate files: - api/custom_routes.py: /v1/models endpoint, model override - CUSTOM_FEATURES.md: Documentation for claude-free and aliases - api/app.py: Include custom_routes router - api/routes.py: Remove duplicate /v1/models endpoint - .env.example: Match upstream simplified format Clean separation prevents upstream merge conflicts.
Improve sync workflow robustness: - Add [skip ci] to merge commits to prevent triggering CI checks - Add auto-format step after merge to fix any formatting issues - Commit formatting fixes with [skip ci] to avoid CI loops This prevents sync failures due to formatting mismatches between upstream and fork.
- Add manual trigger to tests.yml so it can be run from GitHub UI - Fix broken indentation for auto-fix and pull steps in sync-upstream.yml Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove dangerous rebase -X ours fallback (inverted semantics), add upstream force-push detection, run tests before push, fix silent error suppression in formatter, add smart push retry with error classification, and auto-create GitHub issues on failure. Also adds dry-run mode, pins action SHAs, and uses setup-uv action matching tests.yml. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…ing sections - Add title, upstream credit callout, and remove upstream star/fork badges - Fix broken nav links (Quick Start, Configuration) - Add git clone instructions and provider callout to Quick Start - Add VSCode login screen tip - Expand Popular Models with OpenRouter and LM Studio dropdowns - Add HTTP timeout vars and fix MESSAGING defaults in config table - Add Development, Contributing, and License sections Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Owner
|
Hi - the original repo owner ended up adding my model picker into the main version. It has been annoying to keep updating the merge conflicts, so I might just end the support for my version because the original repo implements it. Could you describe your change here more thoroughly? |
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.
please review