Conversation
Complete eversale-cli package (768 files) modified for local operation: - config.yaml: mode=local, all URLs -> Z.AI, all models -> glm-5 - gpu_llm_client.py: ANTHROPIC_BASE_URL/API_KEY priority chains - llm_fallback_chain.py: env var defaults for model/URL - kimi_k2_client.py: anthropic provider + auto-detect priority - eversale.js: license bypass for local dev - license_validator.py: validate_license returns True - config_loader.py: ANTHROPIC_BASE_URL in local/remote chains Tested: 27/27 structural + 3/3 live API (Z.AI glm-5 HTTP 200)
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
8th critical file - enables real LLMClient execution via: OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL env vars Changes: 1. OPENAI_* env vars force remote mode (skip local/license) 2. OPENAI_BASE_URL priority over EVERSALE_LLM_URL 3. OPENAI_API_KEY priority over EVERSALE_LLM_TOKEN 4. OPENAI_MODEL priority over EVERSALE_LLM_MODEL 5. Auto-detect API path (/chat/completions vs /v1/chat/completions) 6. Handle glm-5 reasoning_content field Verified: 3 real API calls to Z.AI glm-5, 223.4s total, all succeeded
codegen-sh
Bot
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
🚀 Eversale-CLI → Z.AI Local Mode — 8 Files Patched, Real Execution Verified
What this does
Patches eversale-cli v2.1.218 to run locally with a personal Z.AI API key (OpenAI-compatible) instead of requiring eversale.io's licensed remote server.
8 Code Changes
config.yamlgpu_llm_client.pyllm_fallback_chain.pykimi_k2_client.pyeversale.jslicense_validator.pyconfig_loader.pyllm_client.py⭐Critical 8th File:
llm_client.py— 6 ChangesOPENAI_*env vars forceremotemode (bypass local/license detection)OPENAI_BASE_URLpriority overEVERSALE_LLM_URLOPENAI_API_KEYpriority overEVERSALE_LLM_TOKENOPENAI_MODELpriority overEVERSALE_LLM_MODEL/chat/completionswhen base_url has/v4,/v1/chat/completionsotherwisereasoning_contentfield (in addition tocontentandreasoning)Real Execution Proof (not simulated)
💻 View my work • 👤 Initiated by @Zeeeepa • About Codegen