| pr |
1.00 |
Update README.md |
|
Codex review bot signature present indic |
2026-07-16 |
| pr |
1.00 |
docs: correct the default seed value to -1 |
|
Explicit AI generation note and AI revie |
2026-06-06 |
| pr |
1.00 |
README: add PickySteve to community integrations |
|
Explicitly discloses PR was prepared by |
2026-07-14 |
| pr |
0.70 |
Create 556 |
|
Overly formal and generic, with classic |
2026-07-16 |
| pr |
0.40 |
feat: add Operator integration to Coding section |
|
Somewhat promotional tone in Operator in |
2026-07-15 |
| pr |
0.20 |
This pull request adds extensive documentation improvements, |
|
Mostly changelog-style listing, some for |
2026-05-26 |
| pr |
0.20 |
feat(cli): add local semantic memory compression for interac |
|
Uses PR template, some formality but ful |
2026-07-12 |
| commit |
0.15 |
mlx: x/create rewrite (#16919) |
|
Technical breakdown with domain specific |
2026-07-04 |
| pr |
0.15 |
Brucemacd/allow ollama |
|
Technical description and domain-specifi |
2026-07-16 |
| commit |
0.10 |
model: align gemma4 chat template handling (#17182) |
|
Uses domain-specific terms and natural, |
2026-07-14 |
| commit |
0.10 |
MLX: wire up scheduler selected context size for ps (#16918) |
|
Technical detail and mild tone; no AI ha |
2026-06-26 |
| commit |
0.10 |
llm: decouple prompt caching from context shift (#16639) |
|
Direct, domain-specific language; no AI |
2026-06-11 |
| commit |
0.10 |
mlxrunner: harden linear/embedding layers against over-promo |
|
Concise technical phrasing and jargon; h |
2026-06-11 |
| pr |
0.10 |
cmd: route root command server start through checkServerHear |
|
Concise, domain-specific, minimal formal |
2026-07-17 |
| pr |
0.10 |
mlx: implement Nemotron 3 Nano Omni |
|
Technical summary with domain terms, no |
2026-07-06 |
| pr |
0.10 |
docs: clarify Claude Code context limits |
|
Summary and testing sections fit human d |
2026-07-06 |
| pr |
0.10 |
Launch codex-app not working after Codex update |
|
Detailed debugging with domain terms, hu |
2026-07-17 |
| pr |
0.10 |
agent/tui: remove redundant context-window refreshes from ev |
|
Clear summary, bullet points; technical, |
2026-07-17 |
| pr |
0.10 |
docs: update goose docs |
|
Changelog format, domain details, no AI |
2026-06-15 |
| pr |
0.10 |
openai: report incomplete status when responses hit the outp |
|
Detailed technical bug description; doma |
2026-07-17 |
| pr |
0.10 |
fix: Audio only projector without vision capability |
|
Technical explanations, contextually spe |
2026-06-09 |
| pr |
0.10 |
anthropic: close text block before starting thinking block |
|
In-depth technical explanation with exam |
2026-07-16 |
| pr |
0.10 |
llm: allow iGPU mmproj offload with fit padding |
|
Highly technical, specific context, abbr |
2026-07-01 |
| pr |
0.10 |
launch: keep Claude Code channels available |
|
Thorough technical root cause; human-lik |
2026-07-12 |
| pr |
0.10 |
mlxrunner: reject structured output requests instead of igno |
|
Technically specific, clear human author |
2026-07-17 |
| pr |
0.10 |
server: clone cached tool call arguments |
|
Detailed technical explanation, zero AI |
2026-07-17 |
| pr |
0.10 |
launch: update Hermes integration |
|
Specific references, technical test comm |
2026-07-15 |
| pr |
0.10 |
agent: allow unlimited tool rounds for cloud models by defau |
|
Domain jargon, casual touch in the 'Why' |
2026-07-16 |
| pr |
0.10 |
agent: clean up semantics, UX, DX, and procedural code |
|
Detailed, technical, with commit refs an |
2026-07-16 |
| pr |
0.10 |
cmd: remove dead agent prompt wrappers |
|
Uses human-focused reasoning, test valid |
2026-07-16 |
| pr |
0.10 |
create: add server-side MLX imports and drop GGUF conversion |
|
Technical, flows like human engineering |
2026-03-19 |
| pr |
0.10 |
fix(readline): support Ctrl+Left/Right word navigation |
|
Technical writeup with specifics and bri |
2026-06-20 |
| pr |
0.10 |
launch: keep Claude Code channels available |
|
Domain terms, changelog structure, and s |
2026-07-15 |
| pr |
0.10 |
discover: recognize the SYCL ggml backend |
|
Technical, context-rich, and uses domain |
2026-06-27 |
| pr |
0.10 |
fix: validate manifest digest in x/transfer to prevent path |
|
Concise security-focused writeup; techni |
2026-07-16 |
| pr |
0.10 |
README: add Tura community integration |
|
Has template structure but free-text is |
2026-07-16 |
| pr |
0.10 |
launch: fix alternate model picker recovery |
|
Templated but technical and specific; no |
2026-07-14 |
| pr |
0.10 |
docs: add VS Code extension setup |
|
Technical writing, direct, no AI style. |
2026-07-13 |
| pr |
0.10 |
openai: map reasoning_effort "minimal" to "low" instead of r |
|
Technical explanations and clear changel |
2026-07-15 |
| pr |
0.10 |
convert: reject num_hidden_layers values that would overflow |
|
Detailed technical root cause and code, |
2026-07-15 |
| pr |
0.10 |
launch: add WebBrain handoff |
|
Domain-specific, useful details, lacks A |
2026-07-02 |
| pr |
0.10 |
fix(cuda): correct Windows CUDA 12+ runtime version detectio |
|
Technical summary, code references, huma |
2026-07-14 |
| pr |
0.10 |
CUDA error from the newest updates |
|
Casual, technical issue post with code, |
2026-07-14 |
| pr |
0.10 |
glm-ocr repeated results |
|
Technical explanation, model/token detai |
2026-07-14 |
| pr |
0.10 |
Vulkan Multi-GPU Allocation Anomaly |
|
Contains domain jargon and technical dis |
2026-07-14 |
| pr |
0.10 |
fix(glm-ocr): register <|user|> as EOT for legacy glmocr GGU |
|
Technical bugfix, reviews section, no ge |
2026-07-14 |
| pr |
0.10 |
fix(sched): order multi-GPU spread by most free memory first |
|
Consistent technical explanation, review |
2026-07-14 |
| pr |
0.10 |
llm: clarify the error when llama-server is not bundled |
|
Technical, concise, with minor typo and |
2026-06-02 |
| pr |
0.10 |
model: align gemma4 chat template handling |
|
Domain-specific and concise; no AI signa |
2026-07-14 |
| pr |
0.10 |
model/parsers: classify assistant prefill by role |
|
Uses domain jargon, clear structure, ter |
2026-07-14 |
| pr |
0.10 |
fix: recover panics in background goroutines to prevent serv |
|
Technical, problem-driven, no AI phrasin |
2026-07-14 |
| pr |
0.10 |
fix: cleanup goroutine and file handle on GGUF Open error pa |
|
Technical explanation, human style, not |
2026-07-14 |
| pr |
0.10 |
convert: guard gemma3n activation sparsity values before Qua |
|
Technical explanation with domain terms |
2026-07-14 |
| pr |
0.10 |
middleware: emit role only in first OpenAI stream chunk |
|
Detailed technical PR, but tone, detail, |
2026-07-13 |
| pr |
0.10 |
Fix minor text formatting in ollama |
|
Slightly generic but casual; typical of |
2026-07-12 |
| commit |
0.05 |
launch: auto-install opencode when missing (#16806) |
|
Terse, domain-specific commit message; h |
2026-06-19 |
| commit |
0.05 |
launch: auto-install Claude Code (#16802) |
|
Concise changelog phrasing; lacks AI sty |
2026-06-19 |
| commit |
0.05 |
server: context shift for context windows larger than 8k, ad |
|
Terse commit message, human style, no AI |
2026-06-15 |
| commit |
0.05 |
model: update lfm2 parser/renderer for optional thinking (#1 |
|
Brief technical wording, lacks AI-style |
2026-06-15 |
| commit |
0.05 |
llama: update llama.cpp to b9637 (#16609) |
|
Direct update message, domain-specific, |
2026-06-15 |
| pr |
0.05 |
Private/issue 15781 vulkan source build |
|
Technical language and specific details, |
2026-07-16 |
| pr |
0.05 |
api: expose default context length in status |
|
Detailed, domain-specific language and t |
2026-07-13 |
| pr |
0.05 |
cmd: agent UI |
|
Terse, technical changelog; includes hum |
2026-07-03 |
| pr |
0.05 |
cmd/tui: simplify integration selection and update menu desc |
|
Concise technical summary and commit sty |
2026-07-13 |
| pr |
0.05 |
docs: clarify desktop update check in FAQ |
|
Brief, well-structured explanation with |
2026-07-13 |
| pr |
0.05 |
llm: raise and expose Gemma 4 image token budget |
|
Free-text contains specific details, tec |
2026-07-13 |
| pr |
0.05 |
launch: Add VS Code extension launch flow |
|
Technical VS Code integration detail, cl |
2026-06-09 |
| commit |
0.00 |
agent: skills system (#17203) |
|
Concise commit message with domain jargo |
2026-07-17 |
| commit |
0.00 |
anthropic: close text block before starting thinking block ( |
|
Brief message with code-specific termino |
2026-07-17 |
| commit |
0.00 |
agent: allow unlimited tool rounds for cloud models by defau |
|
Direct commit message using standard tec |
2026-07-17 |
| commit |
0.00 |
agent: clean up semantics, UX, DX, and procedural code (#172 |
|
Uses standard technical terms, terse and |
2026-07-17 |
| commit |
0.00 |
agent: reorder working directory instruction (#17228) |
|
Very terse, domain-specific commit messa |
2026-07-17 |
| commit |
0.00 |
cmd: remove dead agent prompt wrappers (#17227) |
|
Short, descriptive technical commit mess |
2026-07-17 |
| commit |
0.00 |
launch: keep Claude Code channels available (#17210) |
|
Concise and contextually relevant techni |
2026-07-16 |
| commit |
0.00 |
cmd: put current working dir in the system prompt (#17188) |
|
Terse commit message with domain jargon, |
2026-07-15 |
| commit |
0.00 |
agent/tools: isolate web tests from cloud policy (#17208) |
|
Short, jargon-filled commit message; no |
2026-07-15 |
| commit |
0.00 |
fix launch model picker recovery (#17170) |
|
Plain, brief, typo-like commit summary, |
2026-07-15 |
| commit |
0.00 |
docs: add VS Code extension setup (#17158) |
|
Concise, standard doc commit message, no |
2026-07-15 |
| commit |
0.00 |
docs: collapsed previous retirements (#17167) |
|
Short, template-like commit; no AI hallm |
2026-07-14 |
| commit |
0.00 |
agent/tools: surface actionable web auth error (#17169) |
|
Terse and specific; no AI characteristic |
2026-07-14 |
| commit |
0.00 |
mlxrunner: raise the MTP pending-flush cap to 256 tokens |
|
Technical, informal tone, clear domain k |
2026-07-07 |
| commit |
0.00 |
mlxrunner: key the cache trie by token pairs for draft cache |
|
Technical jargon, concise and informal s |
2026-07-06 |
| commit |
0.00 |
mlxrunner: construct per-model state at load |
|
Technical, includes specifics, not AI-ty |
2026-07-06 |
| commit |
0.00 |
mlxrunner: rename kvCache to prefixCache |
|
Technical rename, brief rationale, no AI |
2026-07-06 |
| commit |
0.00 |
cache: stop recurrent conv state from pinning the forward bu |
|
Technical explanation, uses domain terms |
2026-06-03 |
| commit |
0.00 |
nn/recurrent: derive conv boundary states from a single conv |
|
Technical explanation, natural phrasing, |
2026-06-03 |
| commit |
0.00 |
mlx: configurable model load timeout (#14796) |
|
Template-like PR title, no free-form AI |
2026-07-13 |
| commit |
0.00 |
launch: rename Codex App integration to ChatGPT (#17161) |
|
Standard terse commit with no AI signals |
2026-07-13 |
| commit |
0.00 |
cmd/tui: simplify integration selection and update menu desc |
|
Standard changelog commit, no signs of A |
2026-07-13 |
| commit |
0.00 |
mlx: restore NAX in Metal v4 builds (#17160) |
|
Domain-specific technical explanation, h |
2026-07-13 |
| commit |
0.00 |
cmd: agent UI (#17017) |
|
Very terse commit message, no AI hallmar |
2026-07-10 |
| commit |
0.00 |
launch: warn before launching old agent models (#17063) |
|
Short, domain-specific; likely human-wri |
2026-07-09 |
| commit |
0.00 |
create: select the qwen3.5 parser and renderer for Qwen3.5/N |
|
Technical, concise, uses domain-specific |
2026-06-03 |
| commit |
0.00 |
llm: allow iGPU mmproj offload with fit padding (#16996) |
|
Contains domain-specific jargon and info |
2026-07-07 |
| commit |
0.00 |
server: apply format constraint for all thinking parsers whe |
|
Very terse template-based message; no AI |
2026-07-07 |
| commit |
0.00 |
server: remove unused internal/ code (#17071) |
|
Extremely terse commit message; clearly |
2026-07-07 |
| commit |
0.00 |
create: harden GGUF create flows (#17062) |
|
Terse, uses abbreviation and developer s |
2026-07-06 |
| commit |
0.00 |
launch: disable claude code telemetry by default (#17061) |
|
Short commit title, no AI phrasing or to |
2026-07-06 |
| commit |
0.00 |
mlx: update to de7b4ed9 (#17056) |
|
Standard commit update, no AI patterns e |
2026-07-06 |
| commit |
0.00 |
server: remove OLLAMA_EXPERIMENT=client2 (#16962) |
|
Direct removal note, concise and human-l |
2026-07-06 |
| commit |
0.00 |
llama.cpp update (#17055) |
|
Brief update, typical human committer st |
2026-07-06 |
| commit |
0.00 |
llama: enable FA on CUDA CC 6.x GPUs (#16994) |
|
Technical language with domain specifics |
2026-07-03 |
| commit |
0.00 |
compat: use UTF-8-safe file open (#16999) |
|
Brief, technical summary with human-like |
2026-07-02 |
| commit |
0.00 |
rocm: remove no longer supported devices (#17010) |
|
Informal, human tone and concise problem |
2026-07-02 |
| commit |
0.00 |
llama: clean up dead code from llama-server work (#17007) |
|
Terse, technical language; typical human |
2026-07-02 |
| commit |
0.00 |
agent: harness core (#16963) |
|
Minimal, standard changelog line with no |
2026-07-02 |
| commit |
0.00 |
discover: fall back to standard CUDA when the JetPack runner |
|
Extensive technical detail, domain jargo |
2026-07-02 |
| commit |
0.00 |
docs(cloud): update retirement list (#17000) |
|
Standard doc update, no free-text or AI |
2026-07-02 |
| commit |
0.00 |
fix cuda toolkit lookup and parallel (#16613) |
|
Terse commit messages with technical jar |
2026-06-30 |
| commit |
0.00 |
ci: avoid unbounded parallelism (#16966) |
|
Casual tone, domain-specific explanation |
2026-06-30 |
| commit |
0.00 |
mlx: tighten up gemma4 moe loading code (#16964) |
|
Technical content with human phrasing an |
2026-06-30 |
| commit |
0.00 |
launch: check for min version for hermes desktop (#16912) |
|
Terse commit message, technical, no AI s |
2026-06-29 |
| commit |
0.00 |
llama.cpp update (#16960) |
|
Brief update message, no AI characterist |
2026-06-29 |
| commit |
0.00 |
mlx: bump dependency (#16935) |
|
Contains tech jargon, concise and direct |
2026-06-29 |
| commit |
0.00 |
tools: ignore braces inside JSON strings when detecting tool |
|
Concise, technical language with some in |
2026-06-27 |
| commit |
0.00 |
parser/renderer: add Ornith 9B renderer/parser support (#169 |
|
Very terse, uses minimal language; human |
2026-06-26 |
| commit |
0.00 |
launch: update hermes install urls to official (#16913) |
|
Concise, technical commit, typical human |
2026-06-25 |
| commit |
0.00 |
fix capability grid dark mode style (#16907) |
|
Terse bugfix commit, minimal context, cl |
2026-06-25 |
| commit |
0.00 |
CUDA: require driver 550 or newer for v12 (#16895) |
|
Contains technical jargon, details, huma |
2026-06-25 |
| commit |
0.00 |
docs: redesign coding integration docs (#16808) |
|
Very brief, typical for docs update comm |
2026-06-25 |
| commit |
0.00 |
llama.cpp version update (#16548) |
|
Sparse, standard technical commit title, |
2026-06-24 |
| commit |
0.00 |
jetson: add CC 87 for CUDA v13 (#16628) |
|
Concise title and brief technical explan |
2026-06-24 |
| commit |
0.00 |
server: align generate with native chat templates (#16878) |
|
Technical jargon, informal phrasing, no |
2026-06-24 |
| commit |
0.00 |
docs: redesign docs landing and integrations overview (#1680 |
|
Standard docs commit message with co-aut |
2026-06-24 |
| commit |
0.00 |
llm: fix ollama ps double-counting mmap'd weights on partial |
|
Detailed technical explanation, normal i |
2026-06-24 |
| commit |
0.00 |
mlx: update and fix CUDA JIT packaging (#16871) |
|
Technical, specific, human-like explanat |
2026-06-24 |
| commit |
0.00 |
llm: use host Vulkan loader on Windows (#16869) |
|
Short technical summary, human phrasing. |
2026-06-24 |
| commit |
0.00 |
llama: default qwen2.5vl window attention metadata (#16868) |
|
Detailed domain-specific description, in |
2026-06-24 |
| commit |
0.00 |
llm: preserve generation headroom for shifted prompts (#1685 |
|
Brief message, touches on context, no AI |
2026-06-23 |
| commit |
0.00 |
docs: document max think level (#16877) |
|
Concise, uses common docs commit format, |
2026-06-23 |
| commit |
0.00 |
llm: size mmproj offload by projector memory (#16866) |
|
Technical, domain acronyms, no generic o |
2026-06-23 |
| commit |
0.00 |
llama: add sm_86 architecture to cuda_v13_windows preset (#1 |
|
Detailed technical explanation, signed b |
2026-06-23 |
| commit |
0.00 |
launch/codex: detect model drift when Codex App UI switches |
|
Concise, technical summary with context- |
2026-06-22 |
| commit |
0.00 |
mlxrunner: choose the speculative draft length to maximize t |
|
Uses technical abbreviations and concise |
2026-06-10 |
| commit |
0.00 |
mlxrunner: resolve each speculative round in one host sync |
|
Efficient phrasing and technical descrip |
2026-06-11 |
| commit |
0.00 |
mlxrunner: run one target forward per MTP decode step |
|
Terse, technical, and uses inline explan |
2026-06-10 |
| commit |
0.00 |
mlxrunner: apply in-flight drafts to proposal penalty histor |
|
Precise technical explanation, abbreviat |
2026-06-12 |
| commit |
0.00 |
mlxrunner: support draft heads that maintain draft caches |
|
Domain-specific language, clear technica |
2026-06-10 |
| commit |
0.00 |
mlxrunner: host speculative decoding in the text generation |
|
Direct technical restructuring, no boile |
2026-06-09 |
| commit |
0.00 |
mlxrunner: unify the MTP decode paths |
|
Concise explanation of code changes, ver |
2026-06-02 |
| commit |
0.00 |
discover: fix inverted iGPU/dGPU Vulkan classification on Wi |
|
Specific bug description, technical deta |
2026-06-22 |
| commit |
0.00 |
launch: add thinking capability detection to opencode (#1543 |
|
Commit message is terse and technical wi |
2026-06-18 |
| commit |
0.00 |
ci: pin darwin release xcode (#16788) |
|
Terse commit message, no AI signals. |
2026-06-17 |
| commit |
0.00 |
llama: update llama.cpp to b9672 (#16775) |
|
Brief update, domain specific, human-lik |
2026-06-17 |
| commit |
0.00 |
models: add cohere2_moe (Command A / North) to the MLX engin |
|
Includes jargon, succinct, typical human |
2026-06-17 |
| commit |
0.00 |
llm: context shift allow shiftable prompts (#16764) |
|
Terse commit title, zero AI signals. |
2026-06-16 |
| commit |
0.00 |
integration: look for the "hf" tool in integration tests (#1 |
|
Concise, technical, no AI hallmarks. |
2026-06-16 |
| commit |
0.00 |
launch: Fix launch provider drift (#16683) |
|
Brief message with domain jargon and inf |
2026-06-12 |
| commit |
0.00 |
mlxrunner: record committed MTP drafts before streaming them |
|
Technical, terse, contains domain-specif |
2026-06-01 |
| commit |
0.00 |
mlxrunner: capture prefill snapshots across the forward |
|
Contains domain-specific terms and natur |
2026-05-29 |
| commit |
0.00 |
mlxrunner: drive MTP speculation through cache snapshots |
|
Casual engineering tone, with technical |
2026-05-29 |
| commit |
0.00 |
nn/recurrent: return per-boundary states from the gated-delt |
|
Technical with specific kernel/layer det |
2026-05-29 |
| commit |
0.00 |
mlxrunner/cache: split KVCache and RotatingKVCache into thei |
|
File reorganization with clear, brief en |
2026-05-29 |
| commit |
0.00 |
mlxthread: preserve the original stack when worker work pani |
|
Precise, technical description with natu |
2026-05-27 |
| commit |
0.00 |
docs: omp (#16552) |
|
Terse, domain-specific commit; no AI sig |
2026-06-08 |
| commit |
0.00 |
docs: hermes desktop (#16549) |
|
Minimal content; no AI stylistic feature |
2026-06-08 |
| commit |
0.00 |
docs: update docs examples to use Gemma 4 instead of Gemma 3 |
|
Standard technical commit message, no AI |
2026-06-07 |
| pr |
0.00 |
cmd/tui/chat: render bold emphasis consistently across markd |
|
Technical changelog with code details, n |
2026-07-16 |
| pr |
0.00 |
agent/tui: remove redundant context-window refreshes from ev |
|
Structured technical summary, standard f |
2026-07-17 |
| pr |
0.00 |
cmd: complete slash commands before submitting |
|
Typical changelog format with domain con |
2026-07-17 |
| pr |
0.00 |
build: bump Linux toolchain to GCC 13 |
|
Terse, specific to Linux/GCC, no AI indi |
2026-07-17 |
| pr |
0.00 |
Add ULTRA to Community Integrations (Desktop) |
|
Informal, concise announcement, fits hum |
2026-07-17 |
| pr |
0.00 |
docs: add Qwen Code integration |
|
Commit message is empty, review is human |
2026-06-01 |
| pr |
0.00 |
docs: update hermes docs |
|
No free-text in commit, review is short |
2026-06-25 |
| pr |
0.00 |
model: add Laguna MLX support |
|
Informal, technical language; uses abbre |
2026-07-17 |
| pr |
0.00 |
cmd: remove standalone agent command |
|
Template format, free-form text is terse |
2026-07-17 |
| pr |
0.00 |
agent: skills system |
|
Short, technical description; informal a |
2026-07-15 |
| pr |
0.00 |
model: add Laguna MLX support with custom kernels |
|
Terse technical summary; typical human P |
2026-07-17 |
| pr |
0.00 |
README: add OpenTypeless to community integrations |
|
Concise, template-driven, context-approp |
2026-07-17 |
| pr |
0.00 |
mlx: install required libraries for docker image |
|
Contains typos, informal structure, doma |
2026-07-17 |
| pr |
0.00 |
imagegen: add libraries and includes for imagegen in docker |
|
Brief, specific technical complaint, hum |
2026-01-30 |
| pr |
0.00 |
agent: reorder working directory instruction |
|
Short, direct, technical, informal phras |
2026-07-17 |
| pr |
0.00 |
test: revamp integration test entrypoints |
|
Casual, concise commit-style; domain ter |
2026-06-06 |
| pr |
0.00 |
Docs: add pixeltable integration to OSS docs |
|
Template used, concise technical languag |
2026-07-15 |
| pr |
0.00 |
api: keep JSON Schema constraints on tool parameters |
|
Direct, technical explanation; lacks hal |
2026-07-15 |
| pr |
0.00 |
cmd: put current working dir in the system prompt for agent |
|
Short and informal; clearly human. |
2026-07-14 |
| pr |
0.00 |
agent/tools: isolate web tests from cloud policy |
|
Template structure, domain-specific free |
2026-07-15 |
| pr |
0.00 |
docs: Document the Ollama VS Code extension |
|
Bullet points, concise modern language, |
2026-07-14 |
| pr |
0.00 |
docs: add Cursor integration for Ollama.com cloud models |
|
Technical notes, informal TODOs, lacks A |
2026-07-13 |
| pr |
0.00 |
Ollama cloud not working with any model |
|
Issue report analysis with domain jargon |
2026-07-15 |
| pr |
0.00 |
llama.cpp update |
|
Very brief, lacks AI tone or structure. |
2026-07-14 |
| pr |
0.00 |
server: cap static template ranges |
|
Technical and terse, using domain-specif |
2026-07-08 |
| pr |
0.00 |
fix(gguf): prevent goroutine and fd leak on partial header p |
|
Concise, technical, with human-like stru |
2026-07-15 |
| pr |
0.00 |
x/transfer: reject unsafe blob redirects |
|
Technical summary with test listing, wri |
2026-07-08 |
| pr |
0.00 |
llm: account for compute buffer and per-layer KV in the VRAM |
|
Technical VRAM discussion, concise and h |
2026-07-15 |
| pr |
0.00 |
fix(cli): resolve CLI image path parsing drag-and-drop failu |
|
Technical depth, root cause detail, doma |
2026-05-29 |
| pr |
0.00 |
docs: add WebBrain to integrations |
|
Very brief, checklist/README update, no |
2026-07-12 |
| pr |
0.00 |
fix gemma4 chat template rendering |
|
Very specific, uses references, test com |
2026-07-14 |
| pr |
0.00 |
MLX update |
|
Very minimal and terse; no AI hallmarks. |
2026-07-14 |
| pr |
0.00 |
docs: collapsed previous retirements |
|
Terse summary, no AI indicators. |
2026-07-13 |
| pr |
0.00 |
agent/tools: surface actionable web auth error |
|
Detailed technical explanation, clearly |
2026-07-13 |
| pr |
0.00 |
x: configurable model load timeout for MLX text models |
|
Brief, technical, uses expected abbrevia |
2026-03-12 |
| pr |
0.00 |
progress: fix data races on ticker and states fields |
|
Technical diagnosis, hands-on terminolog |
2026-06-08 |
| pr |
0.00 |
progress: fix Spinner data races and stop its ticker |
|
Links, issue numbers, and casual phrasin |
2026-07-14 |
| pr |
0.00 |
mlxrunner: MTP follow-up fixes and tuning |
|
Technical details, domain context, unmis |
2026-07-07 |
| pr |
0.00 |
server: centralize backend load planning |
|
In-depth technical explanation, domain-s |
2026-07-13 |
| pr |
0.00 |
mlx: restore NAX in Metal v4 builds |
|
Duplicates item #3; same human-written t |
2026-07-13 |
| pr |
0.00 |
launch: rename Codex App integration to ChatGPT |
|
Structured summary and changes, but prec |
2026-07-13 |
| pr |
0.00 |
discover: work around ROCm iGPU free memory overreport |
|
Technical, domain-specific, informal; no |
2026-07-01 |
| pr |
0.00 |
rpreslar4765/Ollama |
|
Only bot comment about Copilot, not gene |
2026-07-13 |
