- Fetch `/props` endpoints in parallel to get context length and auto-unload sleeping models
- Add support for reasoning content and tool calls in streaming openai chat/completions responses
Adds lock-protected dictionaries to track running background refresh tasks, preventing duplicate executions per endpoint. Increases cache freshness thresholds from 30s to 300s to reduce blocking behavior.
fix: /v1 endpoints use correct media_types and usage information with proper logging
- updated reasoning handling
- improved model and error caches
- fixed openai tool calling incl. ollama translations
- direct support for llama.cpp's llama_server via llama_server_endpoint config
- basic llama_server model info in dashboard
- improved endpoint info fetching behaviour in error cases
- Increased error and loaded model cache freshness thresholds from 10s to 30s.
- Added `skip_error_cache` parameter to `endpoint_details` to prevent cached failures from blocking health checks.
- Implemented automatic error recording in `_available_error_cache` on API request failures.
Adds support for correctly handling tool calls in chat requests. Normalizes tool call data (ensuring IDs, types, and JSON arguments) in non-streaming mode and accumulates OpenAI-style deltas during streaming to build the final Ollama response.
Add `llama_server_endpoints` configuration field to support llama_server OpenAI-compatible endpoints for status checks. Implement helper functions to parse model names and quantization levels from llama-server responses (best effort). Update `is_ext_openai_endpoint` to properly distinguish these endpoints from external OpenAI services. Update sample configuration documentation.
Refactor error tracking to use separate caches for 'available' and 'loaded' models, preventing cross-contamination of transient errors. Implement background refresh for available models to prevent blocking requests, and use stale-while-revalidate (300-600s) to serve stale data immediately when the cache is between 300s and 600s old.
- Added proper API key validation in router.py with 401 response when key is missing
- Implemented CORS headers for authentication requests
- Updated table header from "Until" to "Unload" in static/index.html
- Improved security by preventing API key leakage in access logs
- Renamed Feedback class to follow PascalCase convention
- Fixed candidate enumeration start index from 0 to 1
- Simplified candidate content access by removing .message.content
- Updated CONFIG_PATH environment variable name to CONFIG_PATH_ARG
- Bumped version from 0.5 to 0.6
- Removed unnecessary return statement and trailing newline
Added in-flight request tracking mechanism to prevent cache stampede when multiple concurrent requests arrive for the same endpoint. This introduces new dictionaries to track ongoing requests and a lock to coordinate access. The available_models method was refactored to use an internal helper function and includes request coalescing logic to ensure only one HTTP request is made per endpoint when cache entries expire. The loaded_models method was also updated to use the new caching and coalescing pattern.
- Reduced min-width of model columns from 340px to 200px with max-width of 300px
- Added specific styling for narrow columns (3rd-5th) with fixed width and center alignment
- Removed "Instance count" as it has redundant information
- Enhanced time formatting logic to show relative time instead of absolute dates
- Simplified digest display to show last 6 characters instead of truncated format
- Added proper handling for various time value types (number, string, null)
Added endpoint differentiation for models PS board to see where which model is loaded and for how long to ease the viewing of multiple same models deployed for load balancing
- Added validation to check that the extracted key is not empty before returning it
- Added CORS headers to enforce_router_api_key() for proper cross-origin request handling and CORS-related error prevention
Create atomic snapshots by deep copying usage data structures to prevent race conditions.
Protect concurrent reads of usage counts with explicit locking in endpoint selection.
Replace README screenshot with a video link.
Optional router-level API key that gates router/API/web UI access (leave empty to disable)
## Supplying the router API key
If you set `nomyo-router-api-key` in `config.yaml` (or `NOMYO_ROUTER_API_KEY` env), every request to NOMYO Router must include the key:
- HTTP header (recommended): `Authorization: Bearer <router_key>`
- Query param (fallback): `?api_key=<router_key>`
Examples:
```bash
curl -H "Authorization: Bearer $NOMYO_ROUTER_API_KEY" http://localhost:12434/api/tags
curl "http://localhost:12434/api/tags?api_key=$NOMYO_ROUTER_API_KEY"
```
feat add:
Multiple Opinions Ensemble
prefix any ollama model with "moe-" on /api/chat and the original user request gets passed to the selected model 3 times with temp=1 to get 3 different response variants.
Each variant is then revisited and finally scored to find the best response among them all and finally returned to the user.
Runs longer, uses more tokens for expected better quality response.
Mixture of Experts:
- prefix any ollama model with "moe-" on api/chat and the original user request gets passed to the selected model 3 times with temp=1 to get response variants. Each variant is then revisited and finally scored to find the best repsonse among them all and finally returned to the user. Runs longer, uses more tokens for expected better quality response.
Add logic to only append ":latest" suffix to models without existing version suffixes, preventing duplicate version tags and ensuring correct endpoint selection for models following Ollama naming conventions.
