|
|
cfeb4e192c
|
tests: deepen all suites (37→87 checks, 0 failures, 100% pass)
Deploy (Gitea) / deploy (push) Failing after 2s
|
2026-05-05 10:54:00 -04:00 |
|
|
|
9dd0ed2f78
|
tests: standardize on embedded tests (migrate all from tests/ to lisp/ sources)
Deploy (Gitea) / deploy (push) Failing after 2s
|
2026-05-05 10:29:09 -04:00 |
|
|
|
d782f58291
|
provider: revert to simple dex:post (API key confirmed valid)
Deploy (Gitea) / deploy (push) Failing after 2s
|
2026-05-04 20:41:46 -04:00 |
|
|
|
d8929aeb24
|
provider: condvar-based timeout (needs dex:post fix)
Deploy (Gitea) / deploy (push) Failing after 2s
|
2026-05-04 20:12:12 -04:00 |
|
|
|
78705f55ec
|
provider: thread-isolated LLM requests + in-package fix
Deploy (Gitea) / deploy (push) Failing after 2s
- Replace bt:with-timeout with thread-per-request + polling loop
(bt:with-timeout cannot interrupt blocking SSL reads)
- Worker thread makes the HTTP call; main thread polls for result
with configurable LLM_REQUEST_TIMEOUT (default 30s)
- Returns timeout error after deadline; worker thread finishes naturally
- Added (in-package :passepartout) for standalone compilation
|
2026-05-04 19:21:41 -04:00 |
|
|
|
740ff3bb89
|
provider: add bt:with-timeout + LLM_REQUEST_TIMEOUT env var
Deploy (Gitea) / deploy (push) Failing after 2s
|
2026-05-04 18:21:10 -04:00 |
|
|
|
abfb7e5cf8
|
setup wizard: verbose descriptions, multi-provider loop, add DeepSeek/NVIDIA/Local, remove Ollama
|
2026-05-04 11:41:01 -04:00 |
|
|
|
ef4ea1db1b
|
skill-loader export fix + TUI config panel + provider test + slot descriptions
- Fix skill loader export: unintern before import (handle existing symbols)
- Add ignore-errors around export (handle package conflicts)
- Add test-provider-connection (live API key testing for TUI config)
- Add *slot-descriptions* with per-slot explanations for TUI config screen
- Rewrite gateway-tui with expanding minibuffer config panel (F2 toggle)
- Fix skill loader exclusion list: add system-model-router
- All org files updated with proper prose
|
2026-05-04 10:26:50 -04:00 |
|
|
|
908936d4d3
|
rename gateway-* → system-model-* + gateway-messaging, de-ollama, add system-model-explorer
- Rename gateway-provider → system-model-provider (generic :local provider, no hardcoded ollama)
- Rename gateway-llm → system-model (model-request dispatcher)
- Rename system-embedding-gateway → system-model-embedding
- Rename gateway-manager → gateway-messaging (public api renamed to messaging-*)
- Add system-model-explorer (model discovery via OpenRouter API, cached, per-slot recommendations)
- Fix skill loader export: replace prefix-matching with fbound/boundp-based export (20 skills now export)
- Add model-router to skill-loader exclusion list (loaded via CLI)
- De-ollama: remove hardcoded assumed-available patterns from provider pipeline
- Default cascade: cloud-only (openrouter, openai, groq, gemini, deepseek, nvidia, anthropic)
- Env example: add LOCAL_BASE_URL, fix cascade order
- All org files updated with architectural prose (literate programming)
|
2026-05-04 09:58:59 -04:00 |
|
