d163fea154
fix: remove aioresponses
...
sec: bumb aiohttp 3.14
fix: tiktoken test issue by pre-cache the vocab file
2026-06-07 13:23:35 +02:00
3cd530586c
feat: cache backend clients per endpoint instead of building one (with a fresh SSL context) per request
Build and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 3m59s
Build and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 1m25s
Build and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 12m46s
Build and Publish Docker Image / merge (push) Successful in 33s
Build and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 19m56s
Build and Publish Docker Image (Semantic Cache) / merge (push) Successful in 33s
2026-06-07 09:55:54 +02:00
1ce792c48b
feat: new load test added
2026-06-07 09:38:14 +02:00
2dceece0d6
feat: add test for ollama stream errors
2026-06-04 10:42:18 +02:00
4b5a70e787
refac: modularize apis VII
2026-05-19 14:57:39 +02:00
db6aa73903
fix:
...
PR Tests / test (pull_request) Successful in 58s
NYX Security Scan / nyx-scan (pull_request) Successful in 6m59s
- _fetch_loaded_models_internal now writes _loaded_error_cache[endpoint] = time.time() on /api/ps or /v1/models failure, and clears the entry on success
- choose_endpoint now filters out candidates with a fresh (<300s) loaded-models error.
- /health now probes both /api/version and /api/ps for Ollama endpoints
- dashboard adaption
relates to #83
2026-05-18 13:45:06 +02:00
0b64a84e96
fix: replace hardcoded tokendb path
PR Tests / test (pull_request) Successful in 1m0s
NYX Security Scan / nyx-scan (pull_request) Successful in 6m24s
2026-05-17 10:53:33 +02:00
29ee360082
feat: adding automated tests
2026-05-15 16:43:12 +02:00
