| commit |
1.00 |
server/images: prevent skipVerify map collision with duplica |
|
Commit message contains explicit AI assi |
2026-08-12 |
| pr |
1.00 |
docs: fix typo in runner README |
|
Explicitly discloses using Claude for th |
2026-08-21 |
| pr |
1.00 |
llm: load models from non-ASCII paths on Windows |
|
Explicitly states the change was develop |
2026-06-15 |
| pr |
1.00 |
envconfig: normalize OLLAMA_HOST scheme |
|
Explicitly states that OpenAI Codex assi |
2026-08-19 |
| pr |
1.00 |
feat(vision-suite): apple-silicon-mlx preflight profile for |
|
Explicitly states the contribution was g |
2026-08-08 |
| pr |
0.99 |
feat(runner): add ProductionDebtRunnerGate and TechnicalDueD |
|
Grandiose compliance language, rigid met |
2026-08-18 |
| pr |
0.99 |
feat(api): add ActionGateAPIGuardrail and cryptographic Acti |
|
Formulaic enterprise-security language a |
2026-08-18 |
| pr |
0.90 |
⚡ Projects & @-mentions: bring your codebase into the chat |
|
Marketing-heavy phrasing and polished bo |
2026-08-16 |
| pr |
0.78 |
Add /api/tokenize and /api/detokenize endpoints for model-al |
|
Generic benefit headings and phrases lik |
2025-08-22 |
| pr |
0.72 |
server: prevent goroutine leaks on client disconnection in s |
|
Generic polished sections and benchmarki |
2026-08-19 |
| pr |
0.72 |
feat: prevent system sleep during model inference |
|
Generic formal prose and broad claims ha |
2026-06-02 |
| pr |
0.68 |
mlx: implement Ling-3.0 models |
|
Exceptionally polished, expansive prose |
2026-08-10 |
| pr |
0.62 |
Add DeepCellar to Community Integrations |
|
Promotional, polished product language a |
2026-07-28 |
| pr |
0.38 |
Recover panics in CreateHandler's model conversion goroutine |
|
Polished explanatory prose and a generic |
2026-08-07 |
| pr |
0.34 |
sleep: prevent system sleep during model inference |
|
Highly polished structure, broad scope, |
2026-06-03 |
| pr |
0.22 |
docs: add GPU selection guide for different hardware |
|
Very generic wording, but too brief to e |
2026-07-11 |
| pr |
0.18 |
Add whatbroke to community integrations |
|
Polished promotional integration descrip |
2026-07-23 |
| pr |
0.18 |
Add otaku to Terminal & CLI community integrations |
|
Marketing-like feature summary is polish |
2026-07-06 |
| pr |
0.18 |
README: add MindMap Chat to community integrations |
|
Promotional wording is polished, but inc |
2026-08-18 |
| commit |
0.15 |
model: add Laguna MLX support (#17237) |
|
Technical writing with domain details; n |
2026-07-25 |
| pr |
0.12 |
model/qwen3.8: regression tests for markdown image tag in to |
|
Detailed, domain-specific investigation |
2026-08-16 |
| commit |
0.10 |
CI: enable lint on the whole tree (#17457) |
|
Detailed explanation with human domain c |
2026-07-29 |
| commit |
0.10 |
mlx: keep loaded model memory resident (#17367) |
|
Technical, terse, and domain-specific; n |
2026-07-24 |
| commit |
0.10 |
server: fix ps data race on scheduler loaded map (#17376) |
|
In-depth technical details, informal; si |
2026-07-24 |
| commit |
0.10 |
test: harden flaky updater and transfer unit tests (#17378) |
|
Highly specific, informal test rationale |
2026-07-24 |
| pr |
0.10 |
model/parsers: preserve tool-call parsing context in qwen3vl |
|
Specific parser context and issue refere |
2026-08-13 |
| pr |
0.10 |
qwen3.8: normalize system messages |
|
Concise, technically specific summary wi |
2026-08-18 |
| pr |
0.10 |
tests: add launch agent client compatibility test |
|
Specific client names, artifacts, and fa |
2026-08-14 |
| pr |
0.08 |
mlx: add DFlash2 support |
|
Extensive implementation and benchmark d |
2026-08-19 |
| pr |
0.08 |
server: auto-detect qwen3-coder renderer/parser for qwen3moe |
|
Uses repository-specific architecture an |
2026-08-15 |
| pr |
0.08 |
docs: fix broken aka.ms link (tooklit -> toolkit) |
|
Brief typo fix with awkward formatting, |
2026-08-18 |
| pr |
0.08 |
fix: resolve CLI image path parsing bugs |
|
Concise issue-focused technical descript |
2026-06-14 |
| pr |
0.08 |
Fix GGUF tensor endianness for big-endian hosts and add test |
|
Detailed technical changelog is structur |
2026-08-17 |
| pr |
0.08 |
progress: suppress ANSI control characters when stderr is no |
|
Specific lifecycle analysis and an unfin |
2026-07-10 |
| pr |
0.07 |
parsers: preserve tool-call parsing context in qwen3-vl clie |
|
Concise, technically specific explanatio |
2026-08-15 |
| pr |
0.06 |
launch: accept Claude context window suffix |
|
Detailed edge cases, tests, and failures |
2026-08-21 |
| pr |
0.06 |
server: allow parallel requests for qwen35 / qwen35moe now t |
|
Verbose but grounded in precise upstream |
2026-07-12 |
| pr |
0.06 |
app: add desktop onboarding flow |
|
Detailed implementation and validation n |
2026-08-18 |
| pr |
0.06 |
app/ui: keep settings the client did not send |
|
Highly specific race-condition explanati |
2026-08-19 |
| pr |
0.06 |
fix(glm-ocr): register <|user|> as EOT for legacy glmocr GGU |
|
Specific compatibility fix and test deta |
2026-07-14 |
| pr |
0.06 |
cmd: fix PushHandler nil spinner panic, remove stale backwar |
|
Specific bug mechanics and project termi |
2026-06-02 |
| pr |
0.06 |
Add a model metadata cache to reduce Ollama’s per-request ov |
|
Technical details, benchmark data, and m |
2026-08-14 |
| pr |
0.06 |
launch: fill cloud model metadata gaps from show on config w |
|
Highly specific implementation details a |
2026-08-17 |
| pr |
0.06 |
app: replace Windows tray menu with WinUI |
|
Brief, concrete implementation summary w |
2026-08-16 |
| commit |
0.05 |
progress: fix data races on ticker, states, spinner, and bar |
|
Detailed technical language with code co |
2026-08-04 |
| pr |
0.05 |
app/ui: don't animate sidebar open state on initial load |
|
Concise UI behavior explanation with con |
2026-08-19 |
| pr |
0.05 |
docs: clarify update check data collection in FAQ |
|
Concise documentation change with a spec |
2026-08-19 |
| pr |
0.05 |
fix(cmd): improve file path detection for macOS drag-drop pa |
|
Specific implementation details and issu |
2026-06-01 |
| pr |
0.05 |
server: allow the default registry to delegate authenticatio |
|
Clear domain-specific explanation and se |
2026-08-03 |
| pr |
0.05 |
cmd: strip wrapping single-quotes from drag-dropped image pa |
|
Specific Go implementation details and t |
2026-08-12 |
| commit |
0.04 |
qwen3.8: support developer instructions (#17749) |
|
Detailed model-specific implementation a |
2026-08-14 |
| pr |
0.04 |
app: claude model management |
|
Template-style summary is brief and cont |
2026-08-21 |
| pr |
0.04 |
app: add Connect your apps experience |
|
Structured technical PR description with |
2026-08-20 |
| pr |
0.04 |
fix: honor Modelfile temperature on /v1/chat/completions |
|
Concise technical explanation with speci |
2026-08-15 |
| pr |
0.04 |
app: polish onboarding layout and disable zoom |
|
Detailed implementation and validation n |
2026-08-20 |
| pr |
0.04 |
create: add server-side MLX imports and drop GGUF conversion |
|
Highly specific technical scope and issu |
2026-03-19 |
| pr |
0.04 |
docs: clarify that eval_count includes thinking tokens |
|
Detailed source references and focused d |
2026-08-18 |
| pr |
0.04 |
fs/ggml: prevent runtime panics on malformed or corrupt GGUF |
|
Specific GGUF failure details and target |
2026-02-27 |
| pr |
0.04 |
server: warn when embedding input is truncated to fit contex |
|
Concrete code, tests, issue reference, a |
2026-08-16 |
| commit |
0.03 |
app: claude model management (#17915) |
|
Terse, conventional commit title with no |
2026-08-21 |
| commit |
0.03 |
app: add Connect your apps experience (#17900) |
|
Terse, conventional commit title with no |
2026-08-21 |
| commit |
0.03 |
mlx: fix mac assumptions on linux/windows (#17898) |
|
Concise title and specific informal expl |
2026-08-20 |
| commit |
0.03 |
server: don't wedge chat and generate on a mid-stream parser |
|
Specific concurrency failure analysis an |
2026-08-19 |
| commit |
0.03 |
renderers/qwen: tolerate non-leading system messages (#17757 |
|
Specific renderer behavior and integrati |
2026-08-14 |
| commit |
0.03 |
llm: transcode WebP images for llama-server (#17755) |
|
Concrete media-format details and issue |
2026-08-14 |
| commit |
0.03 |
qwen3.8: add renderer and MLX import support (#17745) |
|
Highly specific implementation details a |
2026-08-14 |
| commit |
0.03 |
model/renderers: match Muse Glimmer reasoning template (#177 |
|
Specific renderer behavior and tests sho |
2026-08-13 |
| pr |
0.03 |
mlxrunner: make prefix cache restore points survive cancelle |
|
Highly technical, specific description o |
2026-08-20 |
| pr |
0.03 |
gemma4: accept '=' separator in tool call arguments |
|
Concrete parser behavior, code symbols, |
2026-08-20 |
| pr |
0.03 |
install.sh: auto-install zstd when extracting .tar.zst |
|
Concrete platform, package-manager, and |
2026-08-20 |
| pr |
0.03 |
chat: always preserve the most recent user message during tr |
|
Specific bug mechanics, code paths, and |
2026-08-20 |
| pr |
0.03 |
fix: make WriteWithBackup collision-safe for rapid writes |
|
Concrete timing, backup, and test detail |
2026-08-13 |
| pr |
0.03 |
server: extract GGUF metadata and unify capabilities |
|
Detailed domain-specific explanation wit |
2026-08-18 |
| pr |
0.03 |
launch: fall back to npx for DeepSeek Harness |
|
Concise, project-specific bullets and re |
2026-08-14 |
| pr |
0.03 |
app: add claude desktop app |
|
Brief, domain-specific summary with natu |
2026-08-20 |
| pr |
0.03 |
openai: reject non-string chat stop sequences |
|
Focused technical change with concrete t |
2026-08-20 |
| pr |
0.03 |
server: don't wedge chat and generate on a mid-stream parser |
|
Detailed, concrete debugging narrative u |
2026-08-19 |
| pr |
0.03 |
server: warm prefill cache across model unload/reload |
|
Structured summary and test plan contain |
2026-07-21 |
| pr |
0.03 |
server: add NaN/Inf safety check to EmbeddingsHandler |
|
Concise, technically precise description |
2026-06-02 |
| pr |
0.03 |
docs: fix broken .md/.mdx links |
|
Concise, repository-specific link correc |
2026-08-18 |
| pr |
0.03 |
app: hide macOS app after closing its window |
|
Specific macOS verification steps and co |
2026-08-04 |
| pr |
0.03 |
server: evict loaded runners whose llama-server process has |
|
Detailed domain-specific diagnosis, refe |
2026-08-02 |
| pr |
0.03 |
format: use the rounded hour count for the years label |
|
Deeply specific boundary analysis and te |
2026-08-17 |
| pr |
0.03 |
fix(install): Support different DNF versions |
|
Contains casual phrasing, typos, and con |
2026-08-17 |
| commit |
0.02 |
launch: fall back to npx for DeepSeek Harness (#17758) |
|
Terse, conventional launch commit title |
2026-08-20 |
| commit |
0.02 |
polish onboarding layout and disable zoom (#17885) |
|
Terse, conventional commit title with sp |
2026-08-20 |
| commit |
0.02 |
app: add claude desktop app (#17899) |
|
Brief conventional commit title using pr |
2026-08-20 |
| commit |
0.02 |
app: add desktop onboarding flow (#17853) |
|
Terse conventional commit title describi |
2026-08-19 |
| commit |
0.02 |
Add a model metadata cache to reduce Ollama’s per-request ov |
|
Terse, conventional commit-style title w |
2026-08-18 |
| commit |
0.02 |
mlx update (#17761) |
|
Terse update title with no AI-style phra |
2026-08-15 |
| commit |
0.02 |
llama.cpp update (#17760) |
|
Terse update title with no AI-style phra |
2026-08-15 |
| commit |
0.02 |
docs: register DeepSeek Harness (#17751) |
|
Terse conventional commit message with n |
2026-08-14 |
| commit |
0.02 |
launch: add Muse Code integration (#17594) |
|
Detailed implementation constraints and |
2026-08-13 |
| commit |
0.02 |
mlx: avoid pulling MLX models when MLX is missing (#17710) |
|
Specific architectural rationale and iss |
2026-08-12 |
| pr |
0.02 |
llm: filter per-request llama-server logs unless debug is en |
|
Specific implementation details and diag |
2026-08-21 |
| pr |
0.02 |
qwen3coder: tolerate a dropped closing tag, and stop rewriti |
|
Detailed parser behavior, real-world rep |
2026-08-21 |
| pr |
0.02 |
llm: strip stray LLAMA_API_KEY from llama-server subprocess |
|
Issue-specific diagnosis, code behavior, |
2026-08-21 |
| pr |
0.02 |
convert/llama4: set tokenizer.ggml.pre to llama4 |
|
Detailed tokenizer diagnosis and reposit |
2026-08-16 |
| pr |
0.02 |
convert: set llama4 pre-tokenizer type |
|
Concrete token IDs, file references, and |
2026-08-12 |
| pr |
0.02 |
server: return 204 for OPTIONS on loopback/private hosts |
|
Commit references, middleware behavior, |
2026-08-20 |
| pr |
0.02 |
llm: return error when generation stream ends without a fina |
|
Specific failure mode, endpoint behavior |
2026-08-18 |
| pr |
0.02 |
fix: return 400 when /api/chat messages contain audios/audio |
|
Specific API behavior and test reference |
2026-08-15 |
| pr |
0.02 |
fix(harmony): accept array-wrapped tool call arguments |
|
Specific regression details and reviewer |
2026-08-13 |
| pr |
0.02 |
lint fixes |
|
Short informal commit description with a |
2026-08-20 |
| pr |
0.02 |
mlx: fix mac assumptions on linux/windows |
|
Terse informal wording and specific plat |
2026-08-20 |
| pr |
0.02 |
scripts: fall back to .tgz when zstd CLI is unavailable |
|
Concrete reproduction details and testin |
2026-08-19 |
| pr |
0.02 |
server: reject empty host header in allowedHost check |
|
Concise, domain-specific security explan |
2026-08-13 |
| pr |
0.02 |
progress: track only visible rendered lines |
|
Technical diagnosis, regression details, |
2026-08-19 |
| pr |
0.02 |
readme: add otaku to community integrations |
|
Terse, domain-specific changelog wording |
2026-08-19 |
| pr |
0.02 |
docs: fix stale documentation references |
|
Short list of concrete documentation cor |
2026-06-02 |
| pr |
0.02 |
readme: add Nyx AI to community integrations |
|
Short, concrete integration entry with n |
2026-08-18 |
| pr |
0.02 |
mlxrunner: implement load progress reporting and stall detec |
|
Concise, implementation-specific wording |
2026-08-18 |
| pr |
0.02 |
Fix typo in runner README |
|
Terse typo fix with specific file and re |
2026-08-17 |
| pr |
0.02 |
ci: build desktop apps for app changes |
|
Terse CI change description using reposi |
2026-08-17 |
| pr |
0.02 |
fix(openai): accept reasoning_effort minimal mapping to low |
|
Concise technical commit message with na |
2026-07-20 |
| commit |
0.01 |
lint fixes (#17897) |
|
Minimal, informal commit message typical |
2026-08-20 |
| commit |
0.01 |
mlx update (#17886) |
|
Very terse project-specific maintenance |
2026-08-20 |
| commit |
0.01 |
llama.cpp update (#17851) |
|
Very terse update title; no evidence of |
2026-08-18 |
| commit |
0.01 |
launch: add DeepSeek Harness integration (#17733) |
|
Terse, conventional launch title with no |
2026-08-13 |
| commit |
0.01 |
agent: allow multiple edits per edit tool call (#17711) |
|
Brief conventional commit-style title. |
2026-08-12 |
| commit |
0.01 |
openai: support web search in Responses API (#17686) |
|
Concise, domain-specific feature descrip |
2026-08-12 |
| commit |
0.01 |
mlx: enable CUDA backend in CUDA builds (#17688) |
|
Concise technical change with a specific |
2026-08-12 |
| commit |
0.01 |
docs: require VS Code 1.127 (#17655) |
|
Terse commit message, no AI hallmarks. |
2026-08-10 |
| commit |
0.01 |
docs: add VS Code context length guidance (#17610) |
|
Brief, neutral commit title; no AI signa |
2026-08-10 |
| commit |
0.01 |
Release v0.32.7 (#17646) |
|
Highly technical, domain-specific langua |
2026-08-10 |
| pr |
0.01 |
bench: use HumanEval patch prompts |
|
Terse benchmark-specific wording and con |
2026-07-30 |
| pr |
0.01 |
fix: prevent sidebar open animation on initial load |
|
Short, direct bug-fix summary with no AI |
2026-07-20 |
| pr |
0.01 |
fix(fileutil): make WriteWithBackup collision-safe |
|
Terse technical wording and formatting a |
2026-08-13 |
| pr |
0.01 |
mlx update |
|
Minimal commit message is more consisten |
2026-08-20 |
| pr |
0.01 |
mlx: qwen3.5 vision support |
|
Brief title and highly specific review c |
2026-03-19 |
| pr |
0.01 |
ci: plumb temporary MLX patch through to docker stages |
|
Terse follow-up message with a specific |
2026-08-19 |
| pr |
0.01 |
mlx update |
|
Minimal commit message is more consisten |
2026-08-18 |
| pr |
0.01 |
cmd/launch: fix opencode state path on Windows |
|
Brief, specific change description conta |
2026-06-01 |
| pr |
0.01 |
llm: fix llama-server memory accounting for multi-model load |
|
Dense domain-specific debugging details |
2026-08-18 |
| pr |
0.01 |
llama.cpp update |
|
Terse conventional update title with no |
2026-08-18 |
| commit |
0.00 |
mlxrunner: keep prefill snapshots when a request is cancelle |
|
Highly domain-specific explanation with |
2026-08-19 |
| commit |
0.00 |
mlxrunner: grow the prefix trie by whole child nodes so rest |
|
Detailed cache and trie terminology sugg |
2026-08-20 |
| commit |
0.00 |
mlxrunner: page out generated tokens when close records them |
|
Specific implementation and cache lifecy |
2026-08-20 |
| commit |
0.00 |
mlxrunner: clip prefill captures to their trie node's edge |
|
Concise technical explanation uses preci |
2026-08-20 |
| commit |
0.00 |
mlxrunner: settle the draft caches when a prefill is cancell |
|
Concrete failure mode and recurrent-laye |
2026-08-20 |
| commit |
0.00 |
qwen3.8: normalize system messages (#17855) |
|
Terse conventional commit-style descript |
2026-08-19 |
| commit |
0.00 |
ci: plumb temporary MLX patch through to docker stages (#178 |
|
Brief, repository-specific follow-up not |
2026-08-19 |
| commit |
0.00 |
mlx update (#17850) |
|
Extremely terse patch description with n |
2026-08-19 |
| commit |
0.00 |
nn: speed up prefill on double-scale nvfp4 models |
|
Detailed benchmark data and model-specif |
2026-08-11 |
| commit |
0.00 |
llama.cpp bump (#17702) |
|
Terse conventional bump commit message. |
2026-08-12 |
| commit |
0.00 |
MLX update (#17704) |
|
Terse conventional update commit message |
2026-08-12 |
| commit |
0.00 |
api: stop applying repeat_penalty 1.1 to models that don't s |
|
Detailed model behavior, benchmarks, and |
2026-08-11 |
| commit |
0.00 |
docs: fix broken links (#17676) |
|
Single-line commit message; terse and ty |
2026-08-11 |
| commit |
0.00 |
nemotron_h: support the Nemotron 3.5 prompt layout (#17672) |
|
Casual technical phrasing and in-domain |
2026-08-11 |
| commit |
0.00 |
parsers: recover boundary tokens fumbled into glimmer ATEM i |
|
Detailed, technical, and informal; natur |
2026-08-11 |
| commit |
0.00 |
mlx: implement Nemotron 3 Nano Omni (#17060) |
|
Long, technical, domain-specific jargon |
2026-08-11 |
| commit |
0.00 |
llama.cpp update (#17659) |
|
One-line update message; no AI signals p |
2026-08-10 |
| commit |
0.00 |
MLX: version bump (#17637) |
|
Technical content with informal, precise |
2026-08-09 |
| commit |
0.00 |
qwen3_5: image input support |
|
Contains technical jargon and concise, d |
2026-08-07 |
| commit |
0.00 |
mlxrunner: feed media features to the model during prefill |
|
Practical, precise, informal engineering |
2026-08-06 |
| commit |
0.00 |
mlxrunner: expand image tags into placeholder tokens |
|
Straightforward, technical, with human-l |
2026-08-06 |
| commit |
0.00 |
mlxrunner: fold media identity into prefix-trie keys |
|
Highly technical, domain-specific termin |
2026-08-06 |
| commit |
0.00 |
mlxrunner: reject media requests the model cannot serve |
|
Clear, practical, technical; informal to |
2026-08-06 |
| commit |
0.00 |
create: keep vision towers at source precision when quantizi |
|
Explains rationale with human reasoning, |
2026-08-06 |
| commit |
0.00 |
manifests: remove OCI rootfs from the model config (#17619) |
|
Informal, direct rationale; domain exper |
2026-08-09 |
| commit |
0.00 |
laguna: wire the DFlash target side |
|
Very technical, domain-specific, concise |
2026-08-02 |
| commit |
0.00 |
dflash: add the DFlash block-diffusion draft model |
|
Domain-specific language, technical expl |
2026-08-04 |
| commit |
0.00 |
mlxrunner: add a block-diffusion drafting session |
|
Technical description, succinct, no obvi |
2026-08-02 |
| commit |
0.00 |
sample: define multi-row distributions without a draft chain |
|
Brief, technical, no generic phrasing, c |
2026-08-02 |
| commit |
0.00 |
mlxrunner: let each model declare the cache slots it needs |
|
Detailed technical explanation, concise |
2026-08-02 |
| commit |
0.00 |
mlxrunner: return the draft-conditioning state from a model |
|
Technical, use of jargon, description is |
2026-08-02 |
| commit |
0.00 |
agent/tui: stream thinking traces (#17611) |
|
Short, terse commit message typical of h |
2026-08-07 |
| commit |
0.00 |
cmd/tui: restore launcher integrations menu (#17595) |
|
Terse, clear summary using standard doma |
2026-08-07 |
| commit |
0.00 |
openai: expand namespace tool declarations in the responses |
|
Domain-specific, detailed, informal and |
2026-08-07 |
| commit |
0.00 |
mlxrunner: stop cache rewind refills from corrupting later l |
|
Technical jargon and informal summary su |
2026-08-05 |
| commit |
0.00 |
ci: fix race in darwin build (#17578) |
|
Terse, technical commit message; no AI s |
2026-08-05 |
| commit |
0.00 |
llama.cpp update (#17545) |
|
No free-text content, only title likely |
2026-08-04 |
| commit |
0.00 |
openai: match openai's streaming wire format for chat comple |
|
Technical, domain-specific with terse ch |
2026-08-03 |
| commit |
0.00 |
app/updater: drain background update-check goroutine before |
|
Terse commit summary with domain jargon |
2026-07-31 |
| commit |
0.00 |
qwen3_5: load and run the MTP head as a speculative draft |
|
Technical detail, domain-specific terms, |
2026-06-03 |
| commit |
0.00 |
nn/recurrent: run the gated-delta step in one launch |
|
Technical language, domain-specific abbr |
2026-07-29 |
| commit |
0.00 |
nn/recurrent: activate the conv output in CausalConv1D |
|
Terse change description, technical voca |
2026-07-29 |
| commit |
0.00 |
mlx: factor custom GPU kernel scaffolding into helpers |
|
Technical jargon, concise style, and pra |
2026-07-29 |
| commit |
0.00 |
qwen3_5: pack GDN input projections into one layout at load |
|
Detailed technical breakdown, domain ter |
2026-07-14 |
| commit |
0.00 |
mlx: apply global scales in Dequantize |
|
Technical, concise style and domain-spec |
2026-07-28 |
| commit |
0.00 |
mlx: read scalar items at the array's element width |
|
Short, technical explanation referencing |
2026-07-29 |
| commit |
0.00 |
mlx update (#17476) |
|
Terse commit message; no AI signals. |
2026-07-30 |
| commit |
0.00 |
lint: clean up current tree (#17456) |
|
Concise, terse commit message with domai |
2026-07-29 |
| commit |
0.00 |
mlxrunner: count every speculative round and log stats at in |
|
Technical language and explanation typic |
2026-07-29 |
| commit |
0.00 |
imagegen: remove MLX image generation code (#16615) |
|
Technical changelog, terse and domain-sp |
2026-07-28 |
| commit |
0.00 |
cmd/tui: improve prompt debug rendering (#17334) |
|
Single-line commit message, typical huma |
2026-07-28 |
| commit |
0.00 |
agent: accept file mentions on Enter (#17384) |
|
Short, imperative style—standard human c |
2026-07-28 |
| commit |
0.00 |
tui: avoid table detection for pipe prose (#17424) |
|
Terse commit title, standard developer a |
2026-07-27 |
| commit |
0.00 |
ci: on release builds dont fail fast (#17413) |
|
Bug rationale explained in typical engin |
2026-07-27 |
| commit |
0.00 |
mlx update (#17397) |
|
Short commit message, no AI indicators. |
2026-07-26 |
| commit |
0.00 |
x/create: quantize a draft model's output head at the reques |
|
Informal style, domain jargon, and speci |
2026-07-24 |
| commit |
0.00 |
cmd/tui: agent system prompt command (#17296) |
|
Template section only, no human or AI fr |
2026-07-24 |
| commit |
0.00 |
agent: permission skill loading (#17304) |
|
Template section only, no human or AI fr |
2026-07-24 |
| commit |
0.00 |
qwen3_5: gather packed gate_up experts in one launch |
|
Uses jargon, casual tone, some minor typ |
2026-07-22 |
| commit |
0.00 |
qwen3_5: decode each expert tensor with its own quantization |
|
Contains domain jargon, concise; human s |
2026-07-21 |
| commit |
0.00 |
x/create: quantize lm_head at 8-bit in the requested family |
|
Technical, nuanced explanation, informal |
2026-07-23 |
| commit |
0.00 |
agent: import skills from coding agents (#17294) |
|
Very terse commit title; human-written s |
2026-07-23 |
| commit |
0.00 |
model: align Laguna with upstream llama.cpp (#17335) |
|
Technical summary with abbreviations and |
2026-07-23 |
| commit |
0.00 |
docs: update retirements (#17289) |
|
Very short message, typical commit conve |
2026-07-22 |
| pr |
0.00 |
docs: fix spacing in README get started section |
|
Brief, informal documentation change wit |
2026-08-21 |
