| pr |
1.00 |
docs: restore num_gpu as a valid Modelfile parameter |
|
Explicit disclosure: 'Generated with Cla |
2026-04-12 |
| pr |
1.00 |
llm: context shift allow shiftable prompts |
|
PR includes '[bot](ai_bot)' and 'Codex R |
2026-06-16 |
| pr |
1.00 |
llm: keep projector offload enabled for integrated ROCm GPUs |
|
PR body explicitly mentions AI collabora |
2026-06-16 |
| pr |
1.00 |
llm: size-aware mmproj offload instead of blanket 10 GiB VRA |
|
PR body explicitly mentions AI collabora |
2026-06-06 |
| pr |
1.00 |
docs: correct the default seed value to -1 |
|
Explicit Claude Code AI generation note |
2026-06-06 |
| pr |
0.40 |
ml/backend/ggml: add experimental SYCL backend support |
|
Slightly more formal and explanatory but |
2026-05-07 |
| pr |
0.30 |
Add reranking in new engine (ollamarunner) |
|
Some polished phrasing but technical and |
2025-07-08 |
| pr |
0.30 |
llm: allow MMProj offload for CUDA on integrated GPUs |
|
Some generic phrases but maintains domai |
2026-06-13 |
| pr |
0.30 |
Fix/mmproj gpu offload dgx spark |
|
Structured summary with technical detail |
2026-06-13 |
| pr |
0.20 |
Refactor cmd.go for Improved Readability |
|
Concise technical phrasing, no AI hallma |
2024-07-13 |
| pr |
0.20 |
Add reranking support |
|
Detailed, domain-specific, minimal AI si |
2026-02-09 |
| pr |
0.20 |
Add CapyBro to Community Integrations (Productivity & Apps) |
|
Concise, domain-specific description; no |
2026-06-16 |
| pr |
0.20 |
server: Add OLLAMA_NO_MMAP to disable mmap globally |
|
Uses casual tone and fragment sentences |
2024-09-18 |
| pr |
0.20 |
Add gokin to Terminal & CLI integrations |
|
Brief, domain-targeted, lacking AI-style |
2026-06-16 |
| pr |
0.20 |
lfm2: support ColBERT embedding models |
|
Contains domain-specific jargon, concise |
2026-05-17 |
| pr |
0.20 |
llm: fix ollama ps double-counting mmap'd weights on partial |
|
Technical explanation with domain detail |
2026-06-13 |
| pr |
0.20 |
launch: Add VS Code extension launch flow |
|
Technical explanation + testing steps; h |
2026-06-09 |
| pr |
0.20 |
launch: Fix launch provider drift |
|
Technical summary and causal analysis; h |
2026-06-11 |
| pr |
0.20 |
Decouple prompt caching from context shift |
|
Structured but clear technical detail; n |
2026-06-09 |
| pr |
0.20 |
perf: improve profiling support |
|
Technical writeup and informal review co |
2026-06-07 |
| pr |
0.20 |
discover: fix inverted iGPU/dGPU Vulkan classification on Wi |
|
Detailed root cause analysis, domain-spe |
2026-06-11 |
| pr |
0.15 |
fix(progress): truncate rendered lines to terminal width to |
|
Uses template but free-text is technical |
2026-06-14 |
| pr |
0.13 |
Restructure file-path regex pattern to explicitly traverse d |
|
Technical jargon and code references ind |
2026-06-11 |
| 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 |
| commit |
0.10 |
mlx: "requires" in modelfile is being ignored for mlx based |
|
Technical, concise; just slightly formal |
2026-06-03 |
| commit |
0.10 |
log template details to aid troubleshooting (#16403) |
|
Concise technical explanation, natural f |
2026-06-01 |
| commit |
0.10 |
mlxrunner: add DFlash speculative decoding (#16134) |
|
Technical content, direct style, domain |
2026-05-14 |
| commit |
0.10 |
mlx: rework the MLX sampler (#16122) |
|
Technical explanation with domain-specif |
2026-05-14 |
| pr |
0.10 |
Add model eval metrics to /metrics |
|
Domain-specific data and concise descrip |
2025-06-22 |
| pr |
0.10 |
fix cuda toolkit lookup and parallel |
|
Technical summary with abbreviations and |
2026-06-07 |
| pr |
0.10 |
x/mlxrunner: cap MLX wired/cache memory to fit the host |
|
Technical explanation with clear domain |
2026-06-15 |
| pr |
0.10 |
x/mlxrunner: support the diffusion-gemma architecture (MLX/s |
|
Uses jargon, inline code, and informal d |
2026-06-14 |
| pr |
0.10 |
x/mlxrunner: support gemma-4 MLX models (mixed-precision qua |
|
Uses domain jargon, references, and an i |
2026-06-15 |
| pr |
0.10 |
server: don't clamp a dedicated GPU carveout to host RAM |
|
Dense technical writing, informal tone, |
2026-06-16 |
| pr |
0.10 |
mlx: remove experimental image generation code for now |
|
Technical, mentions review by human, no |
2026-06-07 |
| pr |
0.10 |
responses: support namespace tool calls |
|
Technical details with domain-specific p |
2026-05-22 |
| pr |
0.10 |
fix: Audio only projector without vision capability |
|
Human style: domain vocabulary, issue re |
2026-06-09 |
| pr |
0.10 |
llm: load models from non-ASCII paths on Windows |
|
Human: Windows internals discussed infor |
2026-06-15 |
| pr |
0.10 |
cmake: add zendnn backend for AMD EPYC CPUs |
|
Project-specific terms, bullet lists, an |
2026-06-15 |
| pr |
0.10 |
llm: size mmproj offload by projector |
|
Issue-focused technical summary, domain |
2026-06-15 |
| pr |
0.10 |
llm: set --ctx-checkpoints 0 for Gemma 4 models to prevent O |
|
Direct technical style, links to externa |
2026-06-15 |
| pr |
0.10 |
x/mlxrunner: cap MLX wired/cache memory to fit the host |
|
Technical explanation with clear domain |
2026-06-15 |
| pr |
0.10 |
x/mlxrunner: support the diffusion-gemma architecture |
|
Detailed technical breakdown and domain |
2026-06-15 |
| pr |
0.10 |
docs: add missing usage fields to ChatStreamEvent in OpenAPI |
|
Domain-specific explanation; concise and |
2026-04-12 |
| pr |
0.10 |
llm: allow forcing projector offload on integrated GPUs |
|
Uses technical justification and direct |
2026-06-15 |
| pr |
0.10 |
server: expose llama-server slot API |
|
Technical rationale, domain detail, and |
2026-06-15 |
| pr |
0.10 |
cmd: extract complete file paths with dotted directories |
|
Technical, specific bug and regex explan |
2026-06-15 |
| pr |
0.10 |
model/parsers: recover qwen3-coder bare function calls |
|
Concise, technical fix with domain-speci |
2026-06-15 |
| pr |
0.10 |
readme: add Bandit Stealth to community integrations |
|
Informal summary, repo URL, and typos su |
2026-06-15 |
| pr |
0.10 |
discover: allow gfx1150 (RDNA 3.5) integrated GPU by default |
|
Detailed technical context, domain terms |
2026-06-13 |
| pr |
0.10 |
x/agent: detect sibling cwd escapes |
|
Technical, concise, with domain details |
2026-06-15 |
| pr |
0.10 |
cmd: preserve UNC image path prefixes |
|
Uses technical notation, concise issues/ |
2026-06-15 |
| pr |
0.10 |
cmd: keep image paths with dotted parent dirs intact |
|
Contains domain detail, code specifics, |
2026-06-15 |
| pr |
0.10 |
x/imagegen: restore image editing dispatch for flux2 models |
|
Structured with technical details and re |
2026-02-25 |
| pr |
0.10 |
cmd/launch: add support for glm-5.2 cloud model |
|
Technical changes, domain abbreviations, |
2026-06-14 |
| pr |
0.10 |
llm: allow setting the K/V cache type per model in the Model |
|
Technical motivation, specific error, re |
2026-06-14 |
| pr |
0.10 |
cmd/internal/fileutil: avoid backup filename collisions |
|
Technical, concise, clear 'Why' and 'How |
2026-05-06 |
| pr |
0.10 |
Community Integrations: add MyLLM (mobile) and MyLLM Connect |
|
Conversational tone with some informalit |
2026-06-14 |
| pr |
0.10 |
cmd/interactive.go: convert "true"/"false" strings to bools |
|
Clear technical summary, concise, minima |
2026-06-13 |
| pr |
0.10 |
mlxrunner: harden linear/embedding layers against over-promo |
|
Brief, technical commit message; no AI s |
2026-06-11 |
| pr |
0.09 |
Support automatic installation for Pool |
|
Manual testing steps and domain referenc |
2026-05-14 |
| pr |
0.09 |
cuda: prevent Gemma 4 Dense FA hang for head_dim=512 |
|
Contains domain-specific analysis and in |
2026-04-30 |
| pr |
0.08 |
launch: add NanoClaw integration |
|
Integration details, technical jargon, n |
2026-06-15 |
| pr |
0.07 |
docs: update goose docs |
|
Detailed documentation update, domain sp |
2026-06-15 |
| pr |
0.06 |
README: add Ollama Monitor to community integrations |
|
Community addition, technical but casual |
2026-06-15 |
| 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 |
| commit |
0.05 |
mlx: fix reported information in `ollama show` (#16289) |
|
Concise changelog with technical details |
2026-05-24 |
| commit |
0.05 |
launch: enriched model inventory (#16230) |
|
Brief, technical with domain-specific ph |
2026-05-21 |
| commit |
0.05 |
Reduce startup model hydration (#16215) |
|
Commit messages and PR are concise, tech |
2026-05-19 |
| commit |
0.05 |
test: integration test hardening (#13532) |
|
Terse, technical commit log style; likel |
2026-05-08 |
| commit |
0.05 |
mlx: refined model push behavior (#15431) |
|
Technical, domain-specific commit log wi |
2026-05-08 |
| pr |
0.05 |
server/sched: trust GPU free memory on unified-memory APUs |
|
Technical language, inline code, and inf |
2026-06-14 |
| pr |
0.05 |
Add num_cpu_moe option to keep MoE expert tensors on the CPU |
|
Technical description, option details; h |
2026-06-12 |
| pr |
0.05 |
cmd: keep version output local when server is unavailable |
|
Short, technical, focused change descrip |
2026-06-14 |
| pr |
0.05 |
fix: resolve CLI image path parsing bugs |
|
Brief, focused bug fix with domain speci |
2026-06-14 |
| pr |
0.05 |
feat(cache): write CACHEDIR.TAG into the models directory |
|
Clear, brief summary and technical chang |
2026-06-10 |
| pr |
0.05 |
server: "PARAMETER env" for setting environment variables fr |
|
Straightforward technical update with co |
2026-06-14 |
| commit |
0.01 |
server: remove duplicate template parsing (#16287) |
|
Very terse, typical human commit message |
2026-05-24 |
| 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 |
| commit |
0.00 |
Add AGENTS.md and CLAUDE.md to root repository (#16604) |
|
Concise subject, no AI signals present. |
2026-06-07 |
| commit |
0.00 |
docs: describe llama.cpp update process (#16603) |
|
Standard technical commit summary, human |
2026-06-07 |
| commit |
0.00 |
openai: align models list with tags (#16556) |
|
Concise commit message, domain shorthand |
2026-06-06 |
| commit |
0.00 |
launch: use native Windows Hermes config path (#16558) |
|
Brief technical message, human style, no |
2026-06-06 |
| commit |
0.00 |
docs: update Zod example to use native toJSONSchema (#14746) |
|
Short technical message, human, includes |
2026-06-05 |
| commit |
0.00 |
launch: oh-my-pi (#16410) |
|
Commit message is brief and typical of h |
2026-06-05 |
| commit |
0.00 |
mlx: allow the embedding layer to use the nvfp4 global scale |
|
Technical title, no signs of AI phrasing |
2026-06-05 |
| commit |
0.00 |
docs: add cloud model retirement (#16528) |
|
Minimal changelog, concise and domain-sp |
2026-06-04 |
| commit |
0.00 |
launch: hermes-desktop app (#16516) |
|
Direct and brief, uses domain language a |
2026-06-04 |
| commit |
0.00 |
llama.cpp version update (#16511) |
|
Detailed but technical, with issue refer |
2026-06-04 |
| commit |
0.00 |
integrations: hermes windows install (#16487) |
|
Very brief changelog, standard human com |
2026-06-04 |
| commit |
0.00 |
docs: add Cline CLI integration doc (#16341) |
|
Very short, docs update typical for huma |
2026-06-04 |
| commit |
0.00 |
llama-server: fix gemma4 patch wiring (#16477) |
|
Terse technical commit message with spec |
2026-06-03 |
| commit |
0.00 |
launch: migrate pi (#16213) |
|
Brief, informal, just a technical migrat |
2026-06-03 |
| commit |
0.00 |
llama-server: allow GPU offload for projectors (#16473) |
|
Contains jargon and specific details; in |
2026-06-03 |
| commit |
0.00 |
server: classify mmproj GGUFs as projector layers (#16472) |
|
Direct technical commit; no AI signals. |
2026-06-03 |
| commit |
0.00 |
launch: clean legacy codex profile before launch (#16467) |
|
Short, domain-specific; no sign of AI ge |
2026-06-03 |
| commit |
0.00 |
Kill llama-server during Windows cleanup (#16458) |
|
Clear, specific description with informa |
2026-06-03 |
| commit |
0.00 |
llama.cpp version update (#16463) |
|
Technical changelog; concise and domain- |
2026-06-03 |
| commit |
0.00 |
models: add support for gemma4-12b (#16457) |
|
Very terse and standard technical commit |
2026-06-03 |
| commit |
0.00 |
fix laguna patch build breakage (#16445) |
|
Technical fix with domain details and te |
2026-06-02 |
| commit |
0.00 |
llm: ignore llama-server SSE ping comments (#16443) |
|
Contains domain jargon, informal explana |
2026-06-02 |
| commit |
0.00 |
docs: configure hermes desktop app (#16440) |
|
Minimal template-driven docs commit, no |
2026-06-02 |
| commit |
0.00 |
llama: add laguna (poolside) arch via a llama.cpp patch unde |
|
Contains technical specifics and human c |
2026-06-02 |
| commit |
0.00 |
launch: isolate Codex launch configuration (#16437) |
|
Short, domain-specific commit message; n |
2026-06-02 |
| commit |
0.00 |
llama.cpp version update (#16426) |
|
Generic update message, but no AI marker |
2026-06-02 |
| commit |
0.00 |
More harden app markdown URL handling (#16436) |
|
Domain phrase, human-typical wording for |
2026-06-02 |
| commit |
0.00 |
llm: detect llama-server load stalls from output (#16427) |
|
Complex technical description with jargo |
2026-06-02 |
| commit |
0.00 |
discover: allow Radeon 8060S iGPU by default (#16429) |
|
Detailed technical explanation, issue re |
2026-06-02 |
| commit |
0.00 |
Harden app markdown URL handling (#16380) |
|
Human-style commit with domain-specific |
2026-06-02 |
| commit |
0.00 |
llm: include cached prompt tokens in llama-server counts (#1 |
|
Contains technical jargon and concise ex |
2026-06-02 |
| commit |
0.00 |
launch: fix opencode local model limits (#16425) |
|
Technical language, no signs of AI-style |
2026-06-02 |
| commit |
0.00 |
cmd/launch: add Qwen code integration (#15900) |
|
Minimal message, no AI indicators. |
2026-06-01 |
| commit |
0.00 |
feat(launch): show and auto-install Cline CLI (#16402) |
|
No free text or AI hallmarks, only chang |
2026-06-01 |
| commit |
0.00 |
launch: migrate Codex config (#16397) |
|
Brief commit summary without AI characte |
2026-06-01 |
| commit |
0.00 |
cmd/launch: fix configure cline ollama provider via provider |
|
Human-style technical commit; no AI sign |
2026-06-01 |
| commit |
0.00 |
launch: avoid legacy Codex App profiles (#16364) |
|
Brief, technical; co-author is human, no |
2026-06-01 |
| commit |
0.00 |
llama-server followups (#16353) |
|
Informal, domain-specific, natural human |
2026-06-01 |
| commit |
0.00 |
convert: fixes for qwen3next model conversion (#16354) |
|
Technical bulleted list, domain-specific |
2026-06-01 |
| commit |
0.00 |
model: improvements to laguna-xs.2 parser/renderer (#16362) |
|
— |
2026-05-31 |
| commit |
0.00 |
llama: handle Gemma 4 and LFM2 BOS override in llama server |
|
— |
2026-05-31 |
| commit |
0.00 |
mlx: fix dev mode search path (#16355) |
|
— |
2026-05-29 |
| commit |
0.00 |
runner: Remove CGO engines, use llama-server exclusively for |
|
— |
2026-05-29 |
| commit |
0.00 |
mlxrunner: keep gated-delta recurrent state in float32 |
|
Dense technical detail and jargon, clear |
2026-05-20 |
| commit |
0.00 |
create: read draft architecture from its config.json |
|
Succinct technical summary with domain-s |
2026-05-20 |
| commit |
0.00 |
mlxrunner: move YaRN RoPE helpers into x/models/nn |
|
Brief, direct, and domain-specific refac |
2026-05-20 |
| commit |
0.00 |
Revert "mlxrunner: add DFlash speculative decoding (#16134)" |
|
Classic human rollback PR, with informal |
2026-05-20 |
| commit |
0.00 |
codex: omit patch tool type (#16231) |
|
Brief, technical commit; no AI signs vis |
2026-05-19 |
| commit |
0.00 |
launch: add codex model metadata catalog (#15795) |
|
Very terse commit message, domain-specif |
2026-05-18 |
| commit |
0.00 |
ci: speed up release builds (#15982) |
|
Terse, informal, typical human commit su |
2026-05-15 |
| commit |
0.00 |
quiet down kv log spew (#16105) |
|
Brief, colloquial phrase; no AI signals. |
2026-05-15 |
| commit |
0.00 |
docs: add codex app (#16163) |
|
Standard changelog style; no AI signs. |
2026-05-15 |
| commit |
0.00 |
launch: codex app restarts (#16155) |
|
Minimal, terse commit message common for |
2026-05-14 |
| commit |
0.00 |
launch: update codex app UI copy (#16157) |
|
Short message; typical human commit summ |
2026-05-14 |
| commit |
0.00 |
docs: hide codex app till launch (#16153) |
|
Short and clear, typical human commit me |
2026-05-14 |
| commit |
0.00 |
launch: codex app integration (#16120) |
|
Short, integration commit message, human |
2026-05-14 |
| commit |
0.00 |
mlx: add memory trace logging (#16131) |
|
Terse commit message with direct referen |
2026-05-13 |
| commit |
0.00 |
launch/opencode: add image modalities for vision models (#15 |
|
Concise commit summary with code-specifi |
2026-05-12 |
| commit |
0.00 |
anthropic: Preserve Claude local image-path tool results in |
|
Technical summary, project-specific cont |
2026-05-12 |
| commit |
0.00 |
mlx: fix macOS 26 target leakage in v3 metallib (#16053) |
|
Detailed bugfix, uses precise terminolog |
2026-05-11 |
| commit |
0.00 |
mlx: avoid status timeout during inference (#16086) |
|
Uses technical jargon and plain, concise |
2026-05-11 |
| commit |
0.00 |
mlx: update the imagegen runner for mlx thread affinity (#16 |
|
Short summary with technical jargon and |
2026-05-11 |
| commit |
0.00 |
app: harden update flows (#16100) |
|
Uses technical terms, concise style, min |
2026-05-11 |
| commit |
0.00 |
launch: disable Claude Desktop launch (#16028) |
|
Terse commit message; domain-specific; n |
2026-05-07 |
| commit |
0.00 |
launch: add plan-aware model gating (#16027) |
|
Concise commit title, natural engineerin |
2026-05-06 |
| commit |
0.00 |
cmd/launch: improve integration backup UX (#15907) |
|
Compact message with direct domain abbre |
2026-05-06 |
| commit |
0.00 |
server: cache show responses (#15967) |
|
Terse, domain-specific, and typical of c |
2026-05-05 |
| commit |
0.00 |
mlx: partial cleanup of imagegen layout (#15435) |
|
Informal and terse with domain reference |
2026-05-05 |
| commit |
0.00 |
mlx: Gemma4 MTP speculative decoding (#15980) |
|
Uses bulleted domain details and include |
2026-05-05 |
| commit |
0.00 |
go: bump to 1.26 (#15904) |
|
Extremely terse and typical version bump |
2026-05-04 |
| pr |
0.00 |
agent: ollama agent loop |
|
Only a title, no free text to evaluate. |
2026-06-15 |
| pr |
0.00 |
launch: add Darwin MLX recommendations |
|
Detailed technical changelog, normal hum |
2026-06-17 |
| pr |
0.00 |
app: add first-run terminal onboarding |
|
Domain details, onboarding context, huma |
2026-06-17 |
| pr |
0.00 |
fix(cmd): don't write terminal escape sequences when stdout |
|
Technical explanation with code, natural |
2026-06-17 |
| pr |
0.00 |
ci: pin Darwin release Xcode |
|
Technical, specific references, human te |
2026-06-17 |
| pr |
0.00 |
fix(server): don't force thinking on for chat requests with |
|
Technical reasoning, references, cuts of |
2026-06-16 |
| pr |
0.00 |
docs: update stale README and documentation. |
|
Technical doc fix, commit links, no AI p |
2026-06-17 |
| pr |
0.00 |
llama: update llama.cpp to b9672 |
|
Minimal commit message, human terse styl |
2026-06-17 |
| pr |
0.00 |
models: add Cohere2MoE model |
|
Includes bot review template; no AI in a |
2026-06-11 |
| pr |
0.00 |
add compiler checks for arm build |
|
Terse title, no indications of AI-genera |
2026-06-01 |
| pr |
0.00 |
feat(server): allow Anthropic client headers in CORS preflig |
|
Technical summary, domain jargon, no AI |
2026-06-16 |
| pr |
0.00 |
server: cancel pull on client disconnect |
|
Uses domain-specific shorthand and infor |
2026-04-29 |
| pr |
0.00 |
docs: clarify ROCm visible device behavior |
|
Technical, clear use of jargon, natural |
2026-04-29 |
| pr |
0.00 |
launch: improve cloud model recommendations |
|
Concise summary, human review, no AI phr |
2026-06-16 |
| pr |
0.00 |
progress: render plain output when stderr is not a TTY |
|
Technical, domain-specific explanation, |
2026-06-16 |
| pr |
0.00 |
integration: look for the "hf" tool in integration tests |
|
Commit message is concise and technical. |
2026-06-16 |
| pr |
0.00 |
fix: improve image path extraction and support quoted paths |
|
No free-text; single brief line, too min |
2026-06-16 |
| pr |
0.00 |
server: context shift for context windows larger than 8k, ad |
|
No free-text; only template/meta structu |
2026-06-14 |
| pr |
0.00 |
cmd/interactive: show /list in usage message |
|
Terse, informal commit log typical of hu |
2026-06-05 |
| pr |
0.00 |
model: update lfm2 parser/renderer for optional thinking |
|
Domain details, informal explanation, an |
2026-05-30 |
| pr |
0.00 |
llama: update llama.cpp to b9637 |
|
No free-text; only template/meta structu |
2026-06-07 |
| pr |
0.00 |
add OLLAMA_NO_FILE_FRAGMENTATION |
|
Informal, includes edit, typos and casua |
2026-05-21 |
| pr |
0.00 |
cmd: preserve nested file paths in multimodal parsing |
|
Succinct change notes and terse verifica |
2026-06-14 |
| pr |
0.00 |
fix: use structured logging with 'error' key in slog calls |
|
Concise commit-style change summary typi |
2026-06-14 |
| pr |
0.00 |
launch: add goose cli/desktop integration |
|
Technical detail, domain jargon, descrip |
2026-05-18 |
| pr |
0.00 |
Fix build issues on IBM Z (s390x) |
|
Direct, concise phrasing and specific sy |
2026-05-29 |
| pr |
0.00 |
fix(parsers/qwen3coder): recover bare tool ca |
|
Technical, problem-focused, domain-speci |
2026-06-12 |
| pr |
0.00 |
Add Ollama API Gateway with Docker Compose stack |
|
Detailed changelog, domain-specific abbr |
2026-06-05 |
| pr |
0.00 |
Add conversation context usage indicator |
|
UI-specific technical jargon, informal t |
2026-03-27 |
| pr |
0.00 |
server: truncate embedding inputs to the physical batch size |
|
Direct, technical language and clear pro |
2026-06-12 |
| pr |
0.00 |
llm: warn when model silently falls back to CPU despite GPU |
|
Technical explanation, issue reference, |
2026-06-12 |
| pr |
0.00 |
progress: fix data races on ticker and states fields |
|
Detailed technical changelog with domain |
2026-06-08 |
| pr |
0.00 |
server: validate safetensors architecture before copying blo |
|
Human-authored, uses domain-specific det |
2026-06-08 |
| pr |
0.00 |
docs: add Qwen Code integration |
|
No free-text content; only a template he |
2026-06-01 |
