MrSphay/intelligence-terminal
1
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases Wiki Activity
127 Commits 6 Branches 0 Tags
d7df2e4aeea5a3ccc0f4cce4b70fb0f1fc669aec
Commit Graph

15 Commits

Author SHA1 Message Date
MrSphay
d7df2e4aee fix: harden terminal action endpoints
All checks were successful
Codex Template Compliance / template-compliance (pull_request) Successful in 5s
Details
Build / test-and-image (pull_request) Successful in 49s
Details
2026-05-17 14:19:28 +02:00
MrSphay
85f97bb2a6 feat: harden intelligence runtime and llm providers 2026-05-16 21:18:34 +02:00
calesthio
1fb50939ce fix(grok): align token caps and docs 2026-03-28 22:36:33 -07:00
3byss
caf4430284 Merge branch 'master' into master 2026-03-21 16:17:13 -06:00
R4V3N
ca8f76cdf9 Fix Ollama integration test to skip when model is not installed 
Check /api/tags for the requested model before running, instead of
only checking server reachability. Provides a descriptive skip reason
listing available models.
 2026-03-21 19:47:08 +01:00
3byss
cb275759bb Fixed types and created tests 2026-03-20 16:26:30 -06:00
R4V3N
38046367a9 Resolve merge conflicts with Mistral provider 
Include both Mistral and Ollama providers in factory,
config, and env docs.
 2026-03-20 22:37:35 +01:00
nirae
4d526ca11b update default model to mistral-large-latest and real integration test 2026-03-19 08:04:08 -07:00
nirae
05b63a68af use mistral-large-latest instead of mistral-medium 2026-03-19 08:04:08 -07:00
nirae
4af53ab25a Add Mistral AI as LLM provider 2026-03-19 08:04:08 -07:00
R4V3N
06514fb5e4 Add Ollama provider for self-hosted LLM inference 
Adds LLM_PROVIDER=ollama for fully local, zero-cost inference
via Ollama's OpenAI-compatible API. No API key required.
Configurable base URL via OLLAMA_BASE_URL env var.
 2026-03-18 17:13:16 +01:00
calesthio
3e2d1a3b5d Merge master into feature/openrouter-support 2026-03-17 14:27:06 -07:00
dan
0612915695 test(llm): split OpenRouter unit and integration tests 2026-03-16 21:24:46 +00:00
dan
f1352ce674 test(llm): add unit and integration tests for OpenRouter 2026-03-16 20:17:00 +00:00
Octopus
6f41c2ff3d feat: add MiniMax as LLM provider 
Add MiniMax (api.minimax.io) as a fifth LLM provider option alongside
Anthropic, OpenAI, Gemini, and Codex. MiniMax offers an
OpenAI-compatible Chat Completions API with the M2.5 model (204K
context window).

Changes:
- lib/llm/minimax.mjs: new provider using raw fetch (no SDK)
- lib/llm/index.mjs: register MiniMax in the factory
- .env.example, crucix.config.mjs, README.md: document the new option
- test/llm-minimax.test.mjs: 10 unit tests (node:test)
- test/llm-minimax-integration.test.mjs: live API integration test

Usage:
  LLM_PROVIDER=minimax
  LLM_API_KEY=sk-...
  LLM_MODEL=MiniMax-M2.5          # optional, this is the default
 2026-03-16 08:45:35 -05:00