| COMMIT |
1.00 |
runner: fix swallowed error in allocModel graph reservation |
|
Commit message contains explicit AI assi |
2026-03-14 |
| PR |
1.00 |
api: check error from json.Unmarshal in checkError |
|
Explicitly states AI contribution in the |
2026-03-19 |
| PR |
1.00 |
Add Trepan as a new VS Code extension |
|
PR body explicitly mentions AI collabora |
2026-03-18 |
| PR |
0.60 |
fix: remove duplicate TopLogprobs validation in GenerateHand |
|
Generic overview section is formal and v |
2026-03-21 |
| PR |
0.30 |
docs: fix Linux uninstall command using sed instead of tr |
|
Some template artifacts missing, awkward |
2026-03-20 |
| PR |
0.20 |
docs: add multilingual quick-start README |
|
Slightly polished, but strong domain con |
2026-03-18 |
| PR |
0.20 |
mlx: add prequantized tensor packing + changes for qwen35 |
|
Detailed technical explanation, slight f |
2026-03-16 |
| PR |
0.15 |
Add /api/tokenize and /api/detokenize endpoints for model-al |
|
Detailed but technical and domain-approp |
2025-08-22 |
| PR |
0.15 |
tools: warn when model tool call names don't match registere |
|
Informal tone and domain-specific conten |
2026-03-21 |
| PR |
0.15 |
fix(format): preserve decimal precision for values >= 10 in |
|
Well-structured but technical, no AI phr |
2026-03-18 |
| PR |
0.15 |
server: apply format constraint when thinking is disabled |
|
Structured technical writing; no generic |
2026-03-06 |
| PR |
0.12 |
docs: fix Linux uninstall command that mangles paths with tr |
|
Technical, example-driven, and informal— |
2026-03-22 |
| PR |
0.11 |
Use LXCFS' formula to compute free memory in a cgroup |
|
Technical, informal, references source a |
2026-01-19 |
| COMMIT |
0.10 |
build: smarter docker parallelism (#14653) |
|
Structured explanation, minor polish, mo |
2026-03-07 |
| COMMIT |
0.10 |
don't require pulling stubs for cloud models (#14574) |
|
Detailed, technical PR with domain terms |
2026-03-03 |
| PR |
0.10 |
mlx: add mxfp4/mxfp8/nvfp4 importing |
|
Concise, domain-specific; no AI phrasing |
2026-03-22 |
| PR |
0.10 |
fix: install.sh no longer reports success on sudo failure |
|
Clear, technical explanation with natura |
2026-03-22 |
| PR |
0.10 |
docs: fix Linux uninstall command using sed instead of tr |
|
Technical language, examples, and some i |
2026-03-22 |
| PR |
0.10 |
launch: fix openclaw --model override handling |
|
Technically dense, natural phrasing; no |
2026-03-21 |
| PR |
0.10 |
envconfig: fallback to default for invalid boolean env value |
|
Template headings with brief, technical |
2026-03-05 |
| PR |
0.10 |
fix: exit on critical sudo failures in install.sh |
|
Clear technical summary; concise languag |
2026-03-22 |
| PR |
0.10 |
anthropic: support num_ctx parameter in /v1/messages endpoin |
|
Technical problem/solution; domain-speci |
2026-03-17 |
| PR |
0.10 |
ggml-metal: compile tensor probes as Metal 4 |
|
Technical summary with specific device/t |
2026-03-21 |
| PR |
0.10 |
ggml-metal: probe tensor support with Metal 4 |
|
Domain-specific technical detail and str |
2026-03-21 |
| PR |
0.10 |
Revert revert vendor update (Vendor Update to b8353) |
|
Structured patch notes and domain jargon |
2026-02-07 |
| PR |
0.10 |
feat: Add TencentOS Server to supported distributions in ins |
|
Technical, concise, some incomplete sent |
2026-03-20 |
| PR |
0.10 |
fix: close temp file on Import error paths |
|
Contains domain jargon, example code, di |
2026-03-20 |
| PR |
0.10 |
iGPU: reduce memory overhead, RAM pressure guard, cap concur |
|
Technical, domain-specific, detailed; la |
2026-03-19 |
| PR |
0.10 |
Fix mlxrunner subprocess deadlocks |
|
Informal, technical notes with abbreviat |
2026-03-18 |
| PR |
0.10 |
add ability to turn on debug request logging |
|
Brief, informal, and technical explanati |
2026-02-05 |
| PR |
0.10 |
create: Clean up experimental paths |
|
Direct, concise technical note; lacks AI |
2026-03-06 |
| PR |
0.10 |
mlx: update as of 3/19 |
|
Highly technical, specific results and c |
2026-03-12 |
| PR |
0.10 |
api: add capabilities field to /api/tags response |
|
Informal changelog style with domain ter |
2026-03-19 |
| PR |
0.10 |
Fix streaming timeout during tool call composition |
|
Title and review snippet strongly human, |
2026-03-18 |
| PR |
0.10 |
brazilian-portuguese/readme |
|
Brief PR title and human reviewer commen |
2026-03-18 |
| PR |
0.10 |
fix: correctly count CRLF line endings in modelfile parser |
|
Direct technical bugfix, reviewer commen |
2026-03-18 |
| PR |
0.10 |
launch: disable claude attribution header to preserve KV cac |
|
Direct technical explanation, domain-spe |
2026-03-18 |
| PR |
0.10 |
runner: enable returning more info from runner processing |
|
Refactor description uses domain jargon |
2025-02-22 |
| PR |
0.10 |
launch: register websearch for openclaw |
|
Casual tone, brief explanation, domain-s |
2026-03-17 |
| PR |
0.10 |
mlx: add op wrappers for Conv2d, Pad, activations, trig, and |
|
Technical changelog, direct and specific |
2026-03-17 |
| PR |
0.10 |
cloud_proxy: for the web_search legacy path, flush on newlin |
|
Technical detail, natural phrasing, info |
2026-03-17 |
| PR |
0.10 |
mlx: quantized embeddings, fast SwiGLU, and runtime fixes |
|
Human-written, technical focus, concise |
2026-03-16 |
| PR |
0.09 |
server: usage api |
|
Stats explanation uses domain terms; no |
2026-01-28 |
| PR |
0.08 |
cmd: add /usage to chat to see token consumption |
|
Casual, concise explanation and example; |
2026-01-28 |
| PR |
0.07 |
docs: add steps to implement a new model |
|
Detailed guide summary but direct and do |
2025-02-19 |
| COMMIT |
0.05 |
cmd/launch: skip --install-daemon when systemd is unavailabl |
|
Commit message and description are conci |
2026-03-16 |
| COMMIT |
0.05 |
bench: improve benchmarking tool (#14240) |
|
Technical jargon and bullet point change |
2026-03-15 |
| COMMIT |
0.05 |
config: use native OpenClaw Ollama onboarding (#14829) |
|
Brief, domain-focused text with technica |
2026-03-13 |
| COMMIT |
0.05 |
server: decompress zstd request bodies in cloud passthrough |
|
Technical language and error context; no |
2026-03-13 |
| COMMIT |
0.05 |
middleware: handle non-JSON error responses gracefully (#148 |
|
Brief technical explanation with domain |
2026-03-13 |
| COMMIT |
0.05 |
anthropic: close thinking block before tool_use when no text |
|
Detailed root cause and fix; clear domai |
2026-03-13 |
| COMMIT |
0.05 |
cmd: still populate `ollama ls` when using `ollama run |
|
Short, technical note; lacks generic AI |
2026-03-13 |
| PR |
0.05 |
Preserve thought signatures in tool calls and messages (fix |
|
Technical vocabulary and concise explana |
2026-03-06 |
| PR |
0.05 |
fix: preserve partial download files during PruneLayers |
|
Informal, thorough explanation, practica |
2026-03-23 |
| PR |
0.05 |
fix: preserve partial chunk progress before returning fatal |
|
Terse, domain-specific jargon, human-lik |
2026-03-23 |
| PR |
0.05 |
docs(openapi): add missing usage fields to ChatStreamEvent |
|
Structured technical summary; concise, h |
2026-03-16 |
| PR |
0.05 |
model/parsers: fall back to content when qwen tool call XML |
|
Domain-specific language, technical expl |
2026-03-22 |
| PR |
0.05 |
docs: restore num_gpu in Modelfile reference |
|
Minimal, technical changelog wording; no |
2026-03-22 |
| PR |
0.05 |
add MoltenVK support for Intel macs |
|
Conversational, informal tone with perso |
2026-03-21 |
| PR |
0.05 |
fix: correct cursor positioning when backspacing over line w |
|
Technical reasoning, terse explanations, |
2026-01-01 |
| PR |
0.05 |
create: add vision capability detection and fix capability i |
|
Technical, concise, no AI phrasing or st |
2026-03-17 |
| PR |
0.05 |
mlx: add multimodal pipeline infrastructure for vision and a |
|
Consistently technical, uses domain jarg |
2026-03-17 |
| PR |
0.05 |
Fix RotatingKVCache trim and wrap handling for sliding windo |
|
Technical debugging language, specific a |
2026-03-17 |
| PR |
0.05 |
fix: respect format parameter when think is disabled for qwe |
|
Uses code blocks, in-depth error context |
2026-03-18 |
| PR |
0.05 |
tui: fix signin on headless Linux systems |
|
Concise technical explanation, domain te |
2026-03-04 |
| PR |
0.05 |
x: harden bash approval prompts with parser-based analysis |
|
Direct, technical, with domain jargon an |
2026-03-16 |
| PR |
0.05 |
docs: fix incorrect tr command in Linux uninstall instructio |
|
Commit message is terse and technical, r |
2026-03-18 |
| PR |
0.05 |
docs: fix Linux uninstall command path mangling |
|
Commit and review both show informal ton |
2026-03-18 |
| PR |
0.05 |
cmd/launch: check for both npm and git before installing Ope |
|
Specific install instructions and error |
2026-03-16 |
| PR |
0.04 |
Add missing hipBLASLt kernels and some gfx targets cleanup |
|
Human style: direct, technical, informal |
2026-03-20 |
| PR |
0.04 |
docs: EU AI Act compliance guide for ollama deployers |
|
Specific regulatory jargon, concise bull |
2026-03-23 |
| PR |
0.04 |
add MoltenVK support for Intel macs |
|
Conversational, candid tone, personal an |
2026-03-22 |
| PR |
0.04 |
cmd/tui: add left arrow back navigation in model selector |
|
Brief, informal, with domain-specific UI |
2026-03-18 |
| PR |
0.04 |
pull: refine safetensors pull |
|
Technical, concise, informal, uses preci |
2026-03-18 |
| PR |
0.04 |
create: move safetensor model creation server-side |
|
Structured technical changelog, concise |
2026-03-19 |
| PR |
0.04 |
Reduce per-call tokenizer overhead by 3-5× |
|
Metrics table and profiling details; hig |
2026-02-07 |
| PR |
0.04 |
mlxrunner: share KV cache across conversations with common p |
|
Technical and concise; domain details an |
2026-03-16 |
| PR |
0.04 |
cmd/launch: skip redundant config writes when model unchange |
|
Brief, technical changelog with domain o |
2026-03-18 |
| PR |
0.04 |
launch: fix openclaw not picking up newly selected model |
|
Code examples, real terminal output, and |
2026-03-18 |
| PR |
0.03 |
Update mlx to 0.31.1 |
|
Contains human review comment; overall i |
2026-03-22 |
| PR |
0.03 |
integration: improve ability to test individual models |
|
Direct, technical, domain jargon, and in |
2026-03-18 |
| PR |
0.03 |
server: prevent system sleep during active inference on Wind |
|
Technical jargon, direct tone, and succi |
2026-03-19 |
| PR |
0.03 |
docs: update claude code and openclaw for web search and non |
|
Sparse, no AI signals, includes human re |
2026-03-18 |
| PR |
0.03 |
Add model eval metrics to /metrics |
|
Contains specific metric info and direct |
2025-06-22 |
| PR |
0.02 |
Upgrades of multiple libraries to fix security issues |
|
Minimal changelog, no AI phrasing or exc |
2025-11-28 |
| PR |
0.02 |
mlx: qwen3.5 vision support |
|
Very terse and technical; contains domai |
2026-03-19 |
| PR |
0.01 |
launch/docs: update minimax-m2.5 references to m2.7 |
|
Single line, only references version num |
2026-03-18 |
| COMMIT |
0.00 |
docs: nemoclaw integration (#14962) |
|
Commit has domain abbreviations, informa |
2026-03-20 |
| COMMIT |
0.00 |
launch: skip openclaw gateway health check when no daemon in |
|
Commit is terse, domain-specific, lacks |
2026-03-20 |
| COMMIT |
0.00 |
llm, mlxrunner: fix done channel value consumed by first rec |
|
Technical commit, concise language, doma |
2026-03-18 |
| COMMIT |
0.00 |
mlx: fix subprocess log deadlock |
|
Technical explanation, domain-specific d |
2026-03-18 |
| COMMIT |
0.00 |
add ability to turn on debug request logging (#14106) |
|
Debugging-focused, brief, domain-specifi |
2026-03-20 |
| COMMIT |
0.00 |
parsers: robust xml tool repair (#14961) |
|
Direct language, co-author trailer, tech |
2026-03-19 |
| COMMIT |
0.00 |
app: fix desktop app stuck loading when OLLAMA_HOST is an un |
|
Template style, minimal description, no |
2026-03-19 |
| COMMIT |
0.00 |
mlxrunner: share KV cache across conversations with common p |
|
Technical jargon, detailed and informal, |
2026-03-05 |
| COMMIT |
0.00 |
mlxrunner: fix Slice(0, 0) returning full dimension instead |
|
Technical details, informal tone, domain |
2026-03-18 |
| COMMIT |
0.00 |
cmd/launch: skip redundant config writes when model unchange |
|
Brief, domain-specific, concise commit s |
2026-03-18 |
| COMMIT |
0.00 |
docs: update claude code and openclaw for web search (#14922 |
|
Template style, terse, technical referen |
2026-03-18 |
| COMMIT |
0.00 |
launch: fix openclaw not picking up newly selected model (#1 |
|
Technical context, concise explanation, |
2026-03-18 |
| COMMIT |
0.00 |
docs: update minimax-m2.5 references to m2.7 (#14942) |
|
Standard commit message, concise and tec |
2026-03-18 |
| COMMIT |
0.00 |
tui: fix signin on headless Linux systems (#14627) |
|
Uses domain-specific language and inform |
2026-03-18 |
| COMMIT |
0.00 |
launch: disable claude attribution header to preserve KV cac |
|
Human tone; specific, clear technical ex |
2026-03-17 |
| COMMIT |
0.00 |
cmd/launch: check for both npm and git before installing Ope |
|
Brief, domain-specific, no signs of AI t |
2026-03-18 |
| COMMIT |
0.00 |
launch: register websearch for openclaw (#14914) |
|
Minimal content, lacks AI phrasing or to |
2026-03-17 |
| COMMIT |
0.00 |
cloud_proxy: for the web_search legacy path, flush on newlin |
|
Casual tone, technical explanation; clea |
2026-03-17 |
| COMMIT |
0.00 |
mlx: quantized embeddings, fast SwiGLU, and runtime fixes (# |
|
Commit is terse and uses domain jargon; |
2026-03-17 |
| COMMIT |
0.00 |
mlx: add prequantized tensor packing + changes for qwen35 (# |
|
Technical, jargon-rich, informal; no AI |
2026-03-17 |
| COMMIT |
0.00 |
sched: Model eviction for MLX |
|
Informal, specific, technical detail; la |
2026-03-02 |
| COMMIT |
0.00 |
launch: fix web search, add web fetch, and enable both for l |
|
Short, technical, and informal; typical |
2026-03-16 |
| COMMIT |
0.00 |
cmd/launch: add guards for headless mode (#14837) |
|
Extremely terse commit message, no AI si |
2026-03-14 |
| COMMIT |
0.00 |
rocm: doc driver constraints (#14833) |
|
Very terse, doc update; too minimal for |
2026-03-13 |
| COMMIT |
0.00 |
launch: remove warning for default policy (#14830) |
|
Short and terse; typical human commit me |
2026-03-13 |
| COMMIT |
0.00 |
launch: add compact window for claude code (#14823) |
|
Terse commit message, domain-specific co |
2026-03-13 |
| COMMIT |
0.00 |
api/create: always propagate `:cloud` source for cloud model |
|
Includes technical detail and informal e |
2026-03-13 |
| COMMIT |
0.00 |
launch: fix headless --yes integration flow and policy scopi |
|
Short, technical, and informal phrasing |
2026-03-13 |
| COMMIT |
0.00 |
docs: document reasoning_effort support in OpenAI-compatible |
|
Uses domain-specific language and concis |
2026-03-13 |
| COMMIT |
0.00 |
cmd: TUI model ordering (#14814) |
|
Very terse, domain-specific commit |
2026-03-13 |
| COMMIT |
0.00 |
server: remove experimental aliases support (#14810) |
|
Short technical phrase, no AI markers |
2026-03-13 |
| COMMIT |
0.00 |
cmd: refactor tui and launch (#14609) |
|
Brief, domain-specific with technical ja |
2026-03-13 |
| COMMIT |
0.00 |
ci: fix missing windows zip file (#14807) |
|
Contains technical explanation and infor |
2026-03-12 |
| COMMIT |
0.00 |
mlx: perf improvements (#14768) |
|
Technical, uses abbreviations and inform |
2026-03-12 |
| COMMIT |
0.00 |
middleware: enable local tool model for web search (#14787) |
|
Brief technical phrasing, no AI indicato |
2026-03-11 |
| COMMIT |
0.00 |
openai: split mixed thinking stream chunks via ToChunks (#14 |
|
Commit messages are concise and domain-s |
2026-03-11 |
| COMMIT |
0.00 |
mlx: only log load errors when MLX is needed (#14764) |
|
Technical reason for logging change; con |
2026-03-11 |
| COMMIT |
0.00 |
MLX: harden for init failures (#14777) |
|
Uses informal tone and domain details; n |
2026-03-11 |
| COMMIT |
0.00 |
Revert "runner: add token history sampling parameters to oll |
|
Standard revert with precise reference; |
2026-03-11 |
| COMMIT |
0.00 |
config: qwen3.5 recommendations (#14758) |
|
Brief, domain-specific wording; typical |
2026-03-11 |
| COMMIT |
0.00 |
cloud_proxy: send ollama client version (#14769) |
|
Specific technical history; naturally ph |
2026-03-10 |
| COMMIT |
0.00 |
docs: update claude code docs (#14770) |
|
Brief doc update, matches human commit s |
2026-03-10 |
| COMMIT |
0.00 |
server: add experimental web search and web fetch routes (#1 |
|
Short, domain term 'experimental'; human |
2026-03-10 |
| COMMIT |
0.00 |
ci: Fix windows build (#14754) |
|
Technical explanation; informal, Go-spec |
2026-03-10 |
| COMMIT |
0.00 |
MLX: add header vendoring and remove go build tag (#14642) |
|
Detailed changelog with domain jargon; h |
2026-03-10 |
| COMMIT |
0.00 |
mlx: get parameters from modelfile during model creation (#1 |
|
Brief commit msg, technical, no AI trait |
2026-03-09 |
| COMMIT |
0.00 |
app: auto update should be enabled when reset to defaults (# |
|
Short, technical, lacks AI signs. |
2026-03-09 |
| COMMIT |
0.00 |
rocm: update linux to v7.2 (#14391) |
|
Update message, terse, no AI signals. |
2026-03-09 |
| COMMIT |
0.00 |
x/mlxrunner: replace sampler interface chain with single sta |
|
Detailed technical changelog, domain jar |
2026-03-08 |
| COMMIT |
0.00 |
cloud_proxy: handle stream disconnects gracefully (#14685) |
|
Casual tone, mentions specific errors, h |
2026-03-07 |
| COMMIT |
0.00 |
mlx: int4 groupsize 64 (#14682) |
|
Technical, concise, no AI markers. |
2026-03-07 |
| COMMIT |
0.00 |
create: fix localhost handling (#14681) |
|
Brief technical commit message. |
2026-03-07 |
| COMMIT |
0.00 |
docs: format compat docs (#14678) |
|
Single-word, template-like commit, absen |
2026-03-06 |
| COMMIT |
0.00 |
Reapply "don't require pulling stubs for cloud models" again |
|
Git history details, human Co-authored t |
2026-03-06 |
| COMMIT |
0.00 |
parsers: repair unclosed arg_value tags in GLM tool calls (# |
|
Technical explanation with domain detail |
2026-03-06 |
| COMMIT |
0.00 |
cmd: override stale entries for context window pi (#14655) |
|
Extremely terse with no AI-style phrasin |
2026-03-06 |
| COMMIT |
0.00 |
mlx: prevent remote creation mismatch (#14651) |
|
Brief, specific language and clear domai |
2026-03-05 |
| COMMIT |
0.00 |
cmd/config: fix cloud model limit lookups in integrations (# |
|
Minimalist commit message, typical human |
2026-03-05 |
| COMMIT |
0.00 |
cmd: use native Ollama API endpoint for OpenClaw (#14649) |
|
Concise technical description, no AI hal |
2026-03-05 |
| COMMIT |
0.00 |
cmd: add qwen3.5 context length for launch (#14626) |
|
Short, context-specific phrasing, human- |
2026-03-04 |
| COMMIT |
0.00 |
server: loosen thinking level constraint (#14625) |
|
Terse, non-formal language, domain-speci |
2026-03-04 |
| COMMIT |
0.00 |
model: fix renderer and parser for qwen3.5 (#14605) |
|
Brief technical commit, no signs of AI s |
2026-03-04 |
| COMMIT |
0.00 |
Revert "Reapply "don't require pulling stubs for cloud model |
|
Revert message with standard commit temp |
2026-03-04 |
| COMMIT |
0.00 |
Add qwen3.5-next-moe support to MLX runner and models (#1441 |
|
Human-written changelog, uses domain jar |
2026-03-04 |
| COMMIT |
0.00 |
chore: remove old imagegen LLMs models (#14597) |
|
Brief, technical commit message with dom |
2026-03-03 |
| COMMIT |
0.00 |
Reapply "don't require pulling stubs for cloud models" |
|
Human-style revert message; no AI signal |
2026-03-03 |
| COMMIT |
0.00 |
model/renderers: fix glm-ocr image tags in renderer prompts |
|
Short, domain-specific fix; no AI traits |
2026-03-03 |
| COMMIT |
0.00 |
Revert "don't require pulling stubs for cloud models (#14574 |
|
Standard revert format, concise and doma |
2026-03-03 |
| COMMIT |
0.00 |
mlx: Remove peak memory from the API |
|
Casual tone and technical phrasing, no A |
2026-03-02 |
| COMMIT |
0.00 |
mlxrunner: Refcount pinned tensors |
|
Technical, succinct commit message, huma |
2026-03-02 |
| COMMIT |
0.00 |
cmd/opencode: rename provider from "Ollama (local)" to "Olla |
|
Short technical note, natural phrasing, |
2026-03-02 |
| COMMIT |
0.00 |
server: verify digest is not empty on create (#14555) |
|
Concise technical summary, fits human au |
2026-03-02 |
| COMMIT |
0.00 |
runner: add token history sampling parameters to ollama runn |
|
Short, domain-specific; no AI-style phra |
2026-03-02 |
| COMMIT |
0.00 |
model/qwen3next: avoid crash in in DeltaNet when offloading |
|
Domain-specific commit title, normal co- |
2026-03-02 |
| COMMIT |
0.00 |
qwen3next: add compatibility with imported GGUF models (#145 |
|
Jargon and terse phrasing, no AI signals |
2026-02-28 |
| COMMIT |
0.00 |
mlxrunner: Fix prompt eval timing and count metrics |
|
Technical issue explanation, concise and |
2026-02-26 |
| COMMIT |
0.00 |
mlxrunner: Enforce model context limit |
|
Clear technical language, bullet points, |
2026-02-25 |
| COMMIT |
0.00 |
mlxrunner: Propagate pipeline errors to client via api.Statu |
|
Technical description, domain-specific t |
2026-02-26 |
| COMMIT |
0.00 |
mlxrunner: Report actual memory usage from runner |
|
Detailed technical explanation, informal |
2026-02-25 |
| COMMIT |
0.00 |
mlxrunner: Fix panic on full KV cache hit |
|
Terse, domain-specific explanation, no A |
2026-02-26 |
| COMMIT |
0.00 |
show peak memory usage (#14485) |
|
Brief commit message, human style, zero |
2026-02-27 |
| COMMIT |
0.00 |
model/parsers: add stable tool call indexing for glm47 and q |
|
Concise technical title with jargon, no |
2026-02-27 |
| COMMIT |
0.00 |
model: fix qwen3 tool calling in thinking (#14477) |
|
Detailed, domain-specific changelog, hum |
2026-02-27 |
| COMMIT |
0.00 |
fix: window app crash on startup when update is pending (#14 |
|
Terse, domain-specific fix; no AI signal |
2026-02-26 |
| COMMIT |
0.00 |
app: fix first update check delayed by 1 hour (#14427) |
|
Very brief commit; typical human style. |
2026-02-25 |
| COMMIT |
0.00 |
mlxrunner: Cancel in-flight requests when the client disconn |
|
Technical, concise explanation; no AI ha |
2026-02-24 |
| COMMIT |
0.00 |
mlxrunner: Simplify pipeline memory and cache management |
|
Clearly domain-specific, minimal formal |
2026-02-24 |
| COMMIT |
0.00 |
model: add support for qwen3.5-27b model (#14415) |
|
Very brief, technical; human style. |
2026-02-25 |
| COMMIT |
0.00 |
model: support for qwen3.5 architecture (#14378) |
|
Short, domain term usage; human writing. |
2026-02-25 |
| COMMIT |
0.00 |
ggml: ensure tensor size is valid (#14406) |
|
Direct, technical language; human phrasi |
2026-02-25 |
| PR |
0.00 |
mlxrunner: support partial match on pure transformer caches |
|
Technical, concise explanation with doma |
2026-03-20 |
| PR |
0.00 |
fix: use fallback hostname when os.Hostname() fails |
|
Template sections filled with specific, |
2026-03-21 |
| PR |
0.00 |
fix: use fallback hostname when os.Hostname() fails |
|
Template sections filled with specific, |
2026-03-20 |
| PR |
0.00 |
docs: nemoclaw integration |
|
Brief, human-written summary with domain |
2026-03-19 |
| PR |
0.00 |
launch: skip openclaw gateway health check when no daemon in |
|
Informal, direct explanation of bug fix |
2026-03-20 |
| PR |
0.00 |
server: thread pre-loaded model through scheduleRunner |
|
Technical changelog, domain-specific, in |
2026-03-17 |
| PR |
0.00 |
manifest: hoist BlobsPath regex to package level |
|
Domain jargon, informal review comment, |
2026-03-17 |
| PR |
0.00 |
Add command-r tool call parser for Cohere models |
|
Technical bug explanation, domain jargon |
2026-03-20 |
| PR |
0.00 |
model/parsers: treating failed parsing of tool calls as cont |
|
Detailed, domain-specific, natural human |
2026-03-17 |
| PR |
0.00 |
Added : OpenAPI spec: ChatStreamEvent missing usage fields i |
|
Concise, human style in issue descriptio |
2026-03-08 |
| PR |
0.00 |
ml/backend/ggml: add cascadelake ggml build config |
|
Brief, technical references; no AI hallm |
2026-02-26 |
| PR |
0.00 |
Add 'loki' to LLM CLI tools list in README (fixes #14011) |
|
Terse, followed template; human phrasing |
2026-02-01 |
| PR |
0.00 |
parsers: robust xml tool repair |
|
Concise technical summary; informal tone |
2026-03-19 |
| PR |
0.00 |
app: fix desktop app stuck loading when OLLAMA_HOST is an un |
|
Technical, detailed changelog; specific |
2026-03-16 |
| PR |
0.00 |
use default nvidia-smi as fallback when on WSL2 |
|
References docs, uses domain jargon; hum |
2026-01-02 |
| PR |
0.00 |
add uninstall.sh |
|
Short, rationale provided; casual, human |
2026-01-02 |
| PR |
0.00 |
model/parsers: fix GLM-4.6 parser returning 500 on truncated |
|
Template summary, technical details; no |
2026-03-18 |
| PR |
0.00 |
server: return 404 when model not found in ChatHandler |
|
Structured, technical explanation; thoro |
2026-03-19 |
| PR |
0.00 |
fix(docs): correct AMD linux drivers link in linux.mdx |
|
Brief, direct correction with URL; typic |
2026-03-17 |
| PR |
0.00 |
WIP |
|
Minimal WIP comment, typical human brevi |
2026-03-18 |
| PR |
0.00 |
Make llama.cpp's cache_prompt parameter configurable |
|
Concise technical change and issue refer |
2024-07-18 |
| PR |
0.00 |
README: add iOS chat client |
|
Empty PR description, no content to eval |
2026-03-17 |
| PR |
0.00 |
readline: harden history persistence |
|
Terse, technical commit; typical human e |
2026-03-17 |
