Fetching metadata from the HF Docker repository...
-
deploy: sync GitHub main 07450c9
Deploys 07450c98611aacaa07df903a778fada118aa3c7f.
Co-authored-by: Codex <noreply@openai.com>
-
deploy: sync GitHub main de5dbf9
Deploys the split commit series through de5dbf9ba3f4846fb642cd34e0c2ae37e2fc7c16.
Co-authored-by: Codex <noreply@openai.com> -
feat: add live project atlas
Sync GitHub commit 76e4930 with atlas dashboard, MiniCPM quest LoRA, refresh APIs, and tests.
-
fix: tighten advisor command routing
Co-authored-by: Codex <noreply@openai.com> -
feat: stream advisor progress
Co-authored-by: Codex <noreply@openai.com> -
fix: stabilize llama embedding runtime
Co-authored-by: Codex <noreply@openai.com> -
chore: remove minicpm raw output logging
-
fix: normalize minicpm xml tool fragments
-
chore: log minicpm planner output when enabled
-
fix: pin deployed lora adapter revision
-
fix: align minicpm tool prompt with lora data
-
fix: strip unused minicpm generation inputs
-
feat: enable zerogpu minicpm lora runtime
-
fix: clear stale seals for project references
Co-authored-by: Codex <noreply@openai.com> -
fix: align model prompts with user workflow
Co-authored-by: Codex <noreply@openai.com>
-
feat: adopt almanac frontend
Co-authored-by: Codex <noreply@openai.com> -
fix: guard empty board commands
Co-authored-by: Codex <noreply@openai.com> -
feat: execute planner tool calls
Co-authored-by: Codex <noreply@openai.com> -
feat: add model runtime adapter
Co-authored-by: Codex <noreply@openai.com>
