Fetching metadata from the HF Docker repository...
-
docs: sync submission materials
Co-authored-by: Codex <codex@openai.com>
-
fix: normalize compact quest aliases
Co-authored-by: Codex <codex@openai.com> -
fix: prefer metadata for quest classification
Co-authored-by: Codex <codex@openai.com> -
docs: add dataset motivation to README
Co-authored-by: Codex <codex@openai.com> -
docs: add dataset motivation to article
Co-authored-by: Codex <codex@openai.com> -
docs: revise article with academic framing
Co-authored-by: Codex <codex@openai.com> -
docs: highlight article demo video
Co-authored-by: Codex <codex@openai.com> -
docs: add public X post link
Co-authored-by: Codex <codex@openai.com> -
docs: include video link in X post
Co-authored-by: Codex <codex@openai.com> -
docs: use YouTube demo link
Co-authored-by: Codex <codex@openai.com> -
docs: shorten X submission post
Co-authored-by: Codex <codex@openai.com> -
docs: prepare hackathon submission package
Co-authored-by: Codex <codex@openai.com> -
chore: clear lint leftovers
Co-authored-by: Codex <codex@openai.com>
-
deploy: sync GitHub main 07450c9
Deploys 07450c98611aacaa07df903a778fada118aa3c7f.
Co-authored-by: Codex <noreply@openai.com>
-
deploy: sync GitHub main 2a749ee
Deploys 2a749ee9c27ec0d92bc3dd10eae762f408e42bf1.
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: show quest badge evidence hints
-
feat: add atlas project search
-
fix: accept judged quest label aliases
Co-authored-by: Codex <noreply@openai.com> -
fix: use full embedding context
Co-authored-by: Codex <noreply@openai.com> -
fix: heartbeat dashboard refresh locks
Co-authored-by: Codex <noreply@openai.com> -
feat: cache dashboard quest analysis
Co-authored-by: Codex <noreply@openai.com> -
fix: ignore hosting region tags
Co-authored-by: Codex <noreply@openai.com> -
fix: canonicalize composite quest labels
Co-authored-by: Codex <noreply@openai.com> -
fix: align atlas with almanac style
Co-authored-by: Codex <noreply@openai.com> -
fix: shorten quest analysis batches
Sync GitHub commit 4dce03a; reduce MiniCPM quest refresh batch size to fit ZeroGPU allocations. -
fix: batch quest analysis on zerogpu
Sync GitHub commit 45ef859; split MiniCPM quest refresh into smaller ZeroGPU batches. -
fix: refresh from latest project snapshot
Sync GitHub commit ad338a5; ship the validated 148-project snapshot/index so deployed refresh reuses existing embeddings. -
fix: expose project index payload
Sync GitHub commit 2192785; ProjectIndex retains the validated payload for incremental dashboard refresh reuse. -
fix: reuse unchanged project embeddings
Sync GitHub commit 2bff45e; dashboard refresh now reuses matching text-digest vectors and embeds only new or changed projects. -
fix: reduce embedding context
Sync GitHub commit 663bcb5; use n_ctx=768 for dashboard retrieval embeddings. -
fix: speed up refresh embeddings
Sync GitHub commit 01f6182; reduce retrieval embedding text bounds so Space refresh can rebuild the live atlas promptly. -
fix: bound dashboard embedding text
Sync GitHub commit 29b7083; bound README text used for retrieval embeddings while keeping full README/app source for MiniCPM quest analysis. -
fix: harden dashboard refresh embedding
Sync GitHub commit a6a05cd with bucket-backed HF cache, embedding refresh timeout, and streamed progress logs. -
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> -
feat: embed app file signals in project index
-
fix: avoid embedding work during bootstrap
Co-authored-by: Codex <noreply@openai.com> -
fix: keep embedding bootstrap responsive
Co-authored-by: Codex <noreply@openai.com> -
fix: guard voice recording until bootstrap
Co-authored-by: Codex <noreply@openai.com> -
fix: make voice recording stoppable
Co-authored-by: Codex <noreply@openai.com> -
fix: stabilize llama embedding runtime
Co-authored-by: Codex <noreply@openai.com> -
fix: accept uploaded wav voice notes
Co-authored-by: Codex <noreply@openai.com> -
feat: add nemotron voice input
Co-authored-by: Codex <noreply@openai.com> -
chore: use prebuilt llama cpp wheel
Co-authored-by: Codex <noreply@openai.com> -
feat: build retrieval index with llama cpp
Co-authored-by: Codex <noreply@openai.com> -
docs: align frontend streaming architecture
Co-authored-by: Codex <noreply@openai.com> -
fix: stream deployed advisor turns through app api
Co-authored-by: Codex <noreply@openai.com> -
chore: remove minicpm raw output logging