| pr |
1.00 |
create: respect explicitly empty system prompts |
|
Explicitly states that AI assistance was |
2026-10-13 |
| pr |
1.00 |
llm: retry llama-server startup with eager CUDA module loadi |
|
Explicitly states that the change was ge |
2026-10-13 |
| pr |
1.00 |
app/updater: keep earlier upgrade logs on Windows |
|
Explicitly states it was generated with |
2026-10-12 |
| pr |
1.00 |
manifest: find models through Windows junctions and volume m |
|
Explicitly states that Claude assisted w |
2026-10-11 |
| pr |
1.00 |
model/parsers: process cohere block markers in order |
|
Explicitly states it was prepared with C |
2026-10-12 |
| pr |
1.00 |
model/parsers: preserve content between functiongemma calls |
|
Explicitly states it was prepared with C |
2026-10-12 |
| pr |
1.00 |
llama: update llama.cpp to b11521 for decision models and Em |
|
The included review explicitly identifie |
2026-10-10 |
| pr |
1.00 |
Add OLLAMA_PARALLEL_HYBRID so a hybrid model can run several |
|
Explicitly marked as generated with Clau |
2026-10-11 |
| pr |
1.00 |
fs/gguf: honor general.alignment declared as uint32 |
|
Explicitly states Claude helped find the |
2026-08-30 |
| pr |
1.00 |
types/model: ignore null generation defaults |
|
Explicitly states that AI assistance was |
2026-10-08 |
| pr |
1.00 |
discover: fall back to native probe when runner output is em |
|
PR body explicitly mentions AI collabora |
2026-10-10 |
| pr |
0.70 |
fix(llm): mirror GraphSize KV accounting in PredictServerVRA |
|
Extensive formula analysis and polished |
2026-08-07 |
| pr |
0.68 |
fix(gemma4): trim channel-boundary whitespace independent of |
|
Highly polished, exhaustive narrative ha |
2026-08-04 |
| pr |
0.22 |
README: add omnexx to community integrations |
|
Promotional but concrete project details |
2026-10-12 |
| pr |
0.18 |
server: validate local path on safetensor create |
|
Generic structured summary, though the s |
2025-02-26 |
| pr |
0.12 |
fix(metal): resolve static_assert crash on Apple M5 |
|
Detailed technical explanation with spec |
2026-03-04 |
| pr |
0.12 |
openai: rate prompt timings by evaluated tokens |
|
Detailed but domain-specific engineering |
2026-10-12 |
| pr |
0.12 |
launch: add Atomic Agent integration |
|
Highly polished, but contains extensive |
2026-08-25 |
| pr |
0.10 |
fix(glm-ocr): register <|user|> as EOT for legacy glmocr GGU |
|
Concise technical summary with issue-spe |
2026-07-14 |
| pr |
0.10 |
cmd/launch: align Claude context suffix with effective cloud |
|
Concise domain-specific summary and exac |
2026-09-15 |
| pr |
0.10 |
openai: accept custom tool calls in Responses history |
|
Highly domain-specific change summary wi |
2026-10-09 |
| commit |
0.08 |
server: hide duplicate and downgrade guards from list (#1887 |
|
Specific llama.cpp, GGUF, manifest, and |
2026-10-08 |
| commit |
0.08 |
model: add multimodal embeddings (#18820) |
|
Specific architecture and API details su |
2026-10-06 |
| pr |
0.08 |
README: add DiscourseCopilot to community integrations |
|
Polished but contains specific extension |
2026-10-13 |
| pr |
0.08 |
tokenizer: merge pre-tok REs to prevent multiple matches |
|
Terse technical wording and concrete aff |
2026-02-12 |
| pr |
0.08 |
api: preserve numeric precision in tool call arguments |
|
Detailed compatibility and boundary disc |
2026-10-11 |
| pr |
0.08 |
launch: preserve model thinking controls in Pi configuration |
|
Polished but highly specific implementat |
2026-10-10 |
| pr |
0.06 |
docs: restructuring to separate out cloud features |
|
Template-like documentation bullets, wit |
2026-10-13 |
| pr |
0.06 |
api: bound thinking with a token budget, per request or per |
|
Detailed implementation mechanics and ru |
2026-08-04 |
| commit |
0.05 |
launch: suppress Claude Code connector warning for Ollama (# |
|
Brief technical commit with a normal co- |
2026-10-09 |
| commit |
0.05 |
launch: avoid inherited service-tier warnings in Codex (#188 |
|
Terse, domain-specific commit-style titl |
2026-10-08 |
| commit |
0.05 |
respect CLAUDE_CODE_AUTO_COMPACT_WINDOW user setting |
|
Brief configuration change phrased like |
2026-10-08 |
| commit |
0.05 |
mlx: match publisher tokenizer semantics (#18779) |
|
Detailed tokenizer terminology and focus |
2026-10-04 |
| pr |
0.05 |
llama: add prism model support 0f8e8d |
|
Terse, conventional commit title with no |
2026-10-12 |
| pr |
0.05 |
docs: restructuring |
|
Terse, specific documentation changes wi |
2026-10-06 |
| pr |
0.05 |
server: reuse verified manifests and loaded models in infere |
|
Specific performance data and implementa |
2026-10-11 |
| pr |
0.05 |
qwen3coder: tolerate a dropped closing tag, and stop rewriti |
|
Concrete failure modes and parser behavi |
2026-08-21 |
| commit |
0.04 |
Set CLAUDE_CODE_MAX_CONTEXT_TOKENS to whatever the models co |
|
Concise technical commit message without |
2026-10-07 |
| commit |
0.04 |
Reduce model lookup and MLX decision request overhead (#1880 |
|
Specific implementation details and revi |
2026-10-06 |
| commit |
0.04 |
nemotron_h: add MLX vision support (#17714) |
|
Detailed domain-specific changes and rev |
2026-09-17 |
| pr |
0.04 |
thinking: allow model metadata to set the default |
|
Specific model behavior, CLI, metadata, |
2026-10-13 |
| pr |
0.04 |
app: always show all apps on Connect your apps screen |
|
Uses specific implementation details and |
2026-08-22 |
| pr |
0.04 |
launch: include installed models in Codex /model picker |
|
Detailed domain-specific behavior and im |
2026-10-08 |
| pr |
0.04 |
mlx: compact restored recurrent state after speculative roll |
|
Specific cache behavior, benchmark data, |
2026-10-05 |
| pr |
0.04 |
mlx: compact restored recurrent state after speculative roll |
|
Specific cache behavior, benchmark data, |
2026-10-12 |
| pr |
0.04 |
model: reject empty scheme prefix in names |
|
Technical terminology, fuzzing details, |
2026-10-07 |
| pr |
0.04 |
api: clamp keep_alive durations that overflow int64 |
|
Concise, domain-specific bug explanation |
2026-10-11 |
| pr |
0.04 |
qwen3.5: a tool call can open before the thinking channel is |
|
Highly specific parser analysis and empi |
2026-09-24 |
| pr |
0.04 |
gemma4: do not answer with a channel name the parser was cut |
|
Specific streaming behavior and reproduc |
2026-08-08 |
| pr |
0.04 |
app/ui: prevent sidebar animation on initial load |
|
Concise conventional engineering summary |
2026-10-11 |
| commit |
0.03 |
mlx: preserve generation panics during cleanup (#18886) |
|
Specific panic and cache behavior with c |
2026-10-13 |
| commit |
0.03 |
Add Kev decision scoring to MLX (#18976) |
|
Terse change summary with MLX-specific t |
2026-10-13 |
| commit |
0.03 |
mlx: compact restored recurrent state after speculative roll |
|
Detailed but domain-specific technical c |
2026-10-12 |
| commit |
0.03 |
server: reuse verified manifests and loaded models in infere |
|
Thorough engineering changelog with conc |
2026-10-12 |
| commit |
0.03 |
mlx: mitigate high latency after GPU idle (#18807) |
|
Technical description references a concr |
2026-10-05 |
| commit |
0.03 |
mlx: System one support (#18701) |
|
Detailed commit history and explicit co- |
2026-10-03 |
| commit |
0.03 |
server: report only decision capability for decision models |
|
Specific technical explanation using rel |
2026-10-01 |
| pr |
0.03 |
server: allow tool calls with structured output |
|
Specific technical summary and tests; no |
2026-10-13 |
| pr |
0.03 |
docs: model recs and language standardization |
|
Concise documentation changes expressed |
2026-10-13 |
| pr |
0.03 |
mlx: deduplicate CUDA runtime payloads |
|
Technical packaging and runtime-path det |
2026-08-23 |
| pr |
0.03 |
README: add Synaps to community integrations |
|
Specific product, installation, and inte |
2026-10-13 |
| pr |
0.03 |
README: add ALEPH source agent workflow |
|
Specific project details and validation |
2026-10-13 |
| pr |
0.03 |
README: add Pudding to desktop integrations |
|
Concise integration description follows |
2026-10-13 |
| pr |
0.03 |
app: rename Connect your apps page title to Apps |
|
Concise, specific UI change with a concr |
2026-08-22 |
| pr |
0.03 |
MLX, MLX-C: version bump |
|
Informal release-note style with issue r |
2026-10-12 |
| pr |
0.03 |
Integration test improvements |
|
Brief, informal test-change summary with |
2025-03-11 |
| pr |
0.03 |
middleware: forward errors that arrive after an OpenAI strea |
|
Highly specific debugging details and pr |
2026-10-12 |
| pr |
0.03 |
server: support slashes in OpenAI retrieve model IDs |
|
Concrete route behavior, identifiers, an |
2026-10-07 |
| pr |
0.03 |
api: include HTTP status in client error messages |
|
Specific API behavior, regression covera |
2026-10-07 |
| pr |
0.03 |
model/renderers: preserve schema keyword parameter names |
|
Brief template-style summary and testing |
2026-10-11 |
| commit |
0.02 |
Add decision model integration tests and benchmarks (#18746) |
|
Technical test details and project-speci |
2026-10-13 |
| commit |
0.02 |
docs: update README to include cloud and privacy language |
|
Brief conventional documentation commit |
2026-10-12 |
| commit |
0.02 |
standardizing language referring to cloud services |
|
Short editorial change description, with |
2026-10-08 |
| commit |
0.02 |
manifest: avoid symlinks on Windows (#18852) |
|
Specific Windows, locking, and pruning d |
2026-10-07 |
| commit |
0.02 |
changing wording |
|
Very brief commit title, lacking typical |
2026-10-07 |
| commit |
0.02 |
mlx: fix patch for recent mlx update (#18812) |
|
Terse technical title with issue referen |
2026-10-06 |
| commit |
0.02 |
test: split create integration tests out (#18470) |
|
Plain, domain-specific explanation with |
2026-10-05 |
| commit |
0.02 |
pull: allow RCs to pull matching min_version (#18790) |
|
Concise release-version behavior change |
2026-10-04 |
| commit |
0.02 |
mlx: Decision model improvements (#18776) |
|
Terse technical bullets describing concr |
2026-10-04 |
| commit |
0.02 |
openai: split tool results with images instead of adding [im |
|
Specific implementation details and doma |
2026-10-03 |
| commit |
0.02 |
MLX: version bump (#18576) |
|
Terse, domain-specific commit message wi |
2026-09-23 |
| commit |
0.02 |
server: fix getExistingName canonicalizing model name parts |
|
Detailed Go bug analysis uses concrete r |
2026-09-22 |
| commit |
0.02 |
tests: fix metadata deletion test flake (#18493) |
|
Terse, issue-specific wording with concr |
2026-09-17 |
| pr |
0.02 |
MLX: version bump |
|
Terse release note with specific model a |
2026-10-13 |
| pr |
0.02 |
launch: add Wirken integration |
|
Specific implementation details, tests, |
2026-10-13 |
| pr |
0.02 |
decision: fix JSON state prompts for MLX decision models |
|
Contains specific model and formatting d |
2026-10-13 |
| pr |
0.02 |
mlx: preserve generation panics during cleanup |
|
Specific failure behavior, cleanup paths |
2026-10-08 |
| pr |
0.02 |
llm: reuse llama-server HTTP connections for embed load |
|
Detailed implementation and test specifi |
2026-09-12 |
| pr |
0.02 |
llama: handle byte fallback tokens in tokenizer types |
|
Terse title and placeholder text are typ |
2026-07-06 |
| pr |
0.02 |
models: add Strands Decider support |
|
Brief domain-specific title; automated r |
2026-10-02 |
| pr |
0.02 |
server: fix multimodal embedding load with small num_ctx |
|
Concise, concrete bug description with d |
2026-10-13 |
| pr |
0.02 |
Revert "docs: restructuring" |
|
Standard terse revert message with repos |
2026-10-12 |
| pr |
0.02 |
agent: add condition with env variable OLLAMA_TOOLS_ALL_ALLO |
|
Awkward terse wording and a specific env |
2026-07-26 |
| pr |
0.02 |
docs: fix wording in compatibility and gpu docs |
|
Brief documentation change summary is te |
2026-08-22 |
| pr |
0.02 |
server: do not hand over a tool call the model did not finis |
|
Highly specific debugging evidence and i |
2026-08-04 |
| pr |
0.02 |
server: reload when two tags share a blob but need different |
|
Uses concrete scheduler internals, repro |
2026-09-07 |
| pr |
0.02 |
parsers: drop an unmatched thinking close tag instead of lea |
|
Domain-specific parser behavior and cand |
2026-09-07 |
| pr |
0.02 |
llm: send assistant thinking to the chat template |
|
Specific code paths, client behavior, an |
2026-09-07 |
| pr |
0.02 |
llama: end a spent reasoning budget at a line, not mid-word |
|
Detailed compatibility and upstream life |
2026-09-03 |
| pr |
0.02 |
gemma4: recover a finished tool call that is missing its clo |
|
Includes captured failure context and ca |
2026-08-04 |
| pr |
0.02 |
llm: stop guessing that a repetitive payload is a runaway |
|
Concrete incident, reproduction, and nua |
2026-08-04 |
| pr |
0.02 |
docs: fix powershell casing in windows guide |
|
Terse, specific documentation edit with |
2026-10-11 |
| pr |
0.02 |
docs: hyphenate compound adjective in development guide |
|
Brief, task-specific wording typical of |
2026-10-11 |
| pr |
0.02 |
docs: fix proper-noun casing in modelfile example |
|
Concise technical note with specific sco |
2026-10-11 |
| pr |
0.02 |
docs: fix copy-pasted alt on xcode dropdown image |
|
Short, concrete description of an image |
2026-10-11 |
| pr |
0.02 |
docs: drop mdx extension on vscode link in faq |
|
Specific repository convention and verif |
2026-10-11 |
| pr |
0.02 |
docs: fix Nvidia casing in gpu guide |
|
Concise brand-casing note with repositor |
2026-10-11 |
| pr |
0.02 |
docs: fix http links in web-search example |
|
Brief, concrete URL correction with expl |
2026-10-11 |
| pr |
0.02 |
docs: fix MacOS casing in macos guide |
|
Specific Apple casing correction written |
2026-10-11 |
| pr |
0.02 |
docs: fix MacOS casing in docs readme |
|
Short scope note for a simple documentat |
2026-10-11 |
| commit |
0.01 |
docs: Merge pull request #18981 from ollama/cloud_recommende |
|
Terse merge commit with repository-speci |
2026-10-14 |
| commit |
0.01 |
mlx: port the Metal custom kernels to CUDA (#18657) |
|
Detailed, domain-specific CUDA and MLX i |
2026-10-13 |
| commit |
0.01 |
launch: allow usage credits without upgrading (#18985) |
|
Concise conventional commit message with |
2026-10-13 |
| commit |
0.01 |
Update README for improved privacy wording |
|
Brief, natural documentation update summ |
2026-10-13 |
| commit |
0.01 |
decision: fix JSON state prompts for MLX decision models (#1 |
|
Specific implementation references and c |
2026-10-13 |
| commit |
0.01 |
cli: add decision model support to `ollama run` (#18962) |
|
Terse commit message naming the affected |
2026-10-13 |
| commit |
0.01 |
docs: changing model recs to Models page link, updating refe |
|
Brief, slightly awkward wording typical |
2026-10-13 |
| commit |
0.01 |
gemma4: use MLX SDPA for CUDA prefill with wide head dims (# |
|
Specific MLX, CUDA, SDPA, and head-dimen |
2026-10-13 |
| commit |
0.01 |
ci: harden download steps with retries (#18883) |
|
Informal concise wording with a concrete |
2026-10-13 |
| commit |
0.01 |
server: fix multimodal embedding load with small num_ctx (#1 |
|
Terse, domain-specific commit title; no |
2026-10-13 |
| commit |
0.01 |
docs: Merge pull request #18963 from ollama/security.md_upda |
|
Standard merge commit message with repos |
2026-10-12 |
| commit |
0.01 |
docs: update SECURITY.md |
|
Brief, specific documentation change wit |
2026-10-12 |
| commit |
0.01 |
Revert "docs: restructuring" (#18960) |
|
Conventional terse revert commit message |
2026-10-12 |
| commit |
0.01 |
MLX, MLX-C: version bump (#18956) |
|
Concise technical version-bump commit ti |
2026-10-12 |
| commit |
0.01 |
launch: populate Codex model picker with installed Ollama mo |
|
Specific feature description using proje |
2026-10-12 |
| commit |
0.01 |
mlx: drop carried metal residency patch now that it is upstr |
|
Terse, domain-specific commit title with |
2026-10-07 |
| commit |
0.01 |
re-ordering top nav, splitting out sample project into new P |
|
Terse summary of concrete repository cha |
2026-10-07 |
| commit |
0.01 |
removing repetition, fixing a typo |
|
Informal, concise wording and a specific |
2026-10-07 |
| commit |
0.01 |
cmd: remove account step from CLI onboarding (#18826) |
|
Short, conventional commit message with |
2026-10-07 |
| commit |
0.01 |
keeping old urls, updating model retirement page |
|
Concise documentation-focused summary wi |
2026-10-07 |
| commit |
0.01 |
llama: fix clef head reads past 2GiB on windows (#18777) |
|
Highly specific implementation details a |
2026-10-07 |
| commit |
0.01 |
server: proxy cloud usage and balance APIs (#18829) |
|
Concise technical summary naming concret |
2026-10-07 |
| commit |
0.01 |
reorganizing the docs folder, adding error handling to the s |
|
Terse list of specific repository change |
2026-10-06 |
| commit |
0.01 |
docs: fix 6 dead links in README community integrations list |
|
Brief conventional documentation commit |
2026-10-06 |
| commit |
0.01 |
MLX: version bump (#18720) |
|
Brief release notes with specific MLX an |
2026-10-06 |
| commit |
0.01 |
llama.cpp: version update (#18761) |
|
Concise version-update commit message. |
2026-10-06 |
| commit |
0.01 |
docs: document image input for decision models (#18757) |
|
Terse, conventional documentation commit |
2026-10-02 |
| commit |
0.01 |
docs: link to available decision models (#18758) |
|
Terse, conventional documentation commit |
2026-10-02 |
| commit |
0.01 |
ci: fix missing build context (#18742) |
|
Terse, conventional commit message with |
2026-10-02 |
| commit |
0.01 |
models: add clef support (#18741) |
|
Brief domain-specific commit title; no s |
2026-10-01 |
| commit |
0.01 |
README: add oxi to community integrations |
|
Terse, repository-specific integration u |
2026-10-01 |
| commit |
0.01 |
llama.cpp: version update (#18577) |
|
Concise technical changelog with specifi |
2026-09-22 |
| commit |
0.01 |
app: avoid System Events for ChatGPT/Codex detection (#18601 |
|
Brief, natural commit title with concret |
2026-09-22 |
| commit |
0.01 |
server: allow registry cross-host redirects among allowliste |
|
Terse, issue-specific commit title with |
2026-09-19 |
| commit |
0.01 |
api: expose model thinking levels and defaults (#18473) |
|
Terse, issue-specific title with no AI-s |
2026-09-18 |
| commit |
0.01 |
app: keep closed macOS windows from reopening on activation |
|
Concise, domain-specific commit-style wo |
2026-09-18 |
| pr |
0.01 |
Remove llama.cpp compatibility patches and migrate legacy GG |
|
Highly domain-specific migration details |
2026-10-08 |
| pr |
0.01 |
mlx: port the Metal custom kernels to CUDA |
|
Deep CUDA and Metal implementation detai |
2026-09-25 |
| pr |
0.01 |
launch: allow usage credits without upgrading |
|
Brief informal wording is characteristic |
2026-10-13 |
| pr |
0.01 |
app: clarify cloud payment errors |
|
Concise, specific behavior change lacks |
2026-10-13 |
| pr |
0.01 |
docs: update README to include cloud and privacy language |
|
Minimal templated change description pro |
2026-10-12 |
| pr |
0.01 |
docs: update Msty link from .app to .ai |
|
Terse issue reference and verification d |
2026-10-13 |
| pr |
0.01 |
Add decision model integration tests and benchmarks |
|
Short, technical scope summary lacks sty |
2026-10-02 |
| pr |
0.01 |
AMD: update to ROCm v10 with improved HCL (+5 Linux, +7 Wind |
|
Detailed release and hardware specifics |
2026-06-03 |
| pr |
0.01 |
gemma4: use MLX SDPA for CUDA prefill with wide head dims |
|
Terse, domain-specific wording and bench |
2026-10-05 |
| pr |
0.01 |
ci: harden download steps with retries |
|
Casual phrasing and concrete CI context |
2026-10-08 |
| pr |
0.01 |
Add libquadmath0 to Dockerfile dependencies |
|
Brief, informal dependency note lacks AI |
2026-05-01 |
| pr |
0.01 |
app: fix dropped chat errors and "undefined" in tool-call me |
|
Terse, concrete bug-fix summary suggests |
2026-10-13 |
| pr |
0.01 |
Add Kev decision scoring to MLX |
|
Concise domain-specific summary and huma |
2026-10-13 |
| pr |
0.01 |
docs: remove stale OLLAMA_TMPDIR and %TEMP% references |
|
Highly specific repository history and i |
2026-10-12 |
| pr |
0.01 |
x/mlxrunner/mlx: link against libdl on linux |
|
Concise diagnosis with exact glibc behav |
2026-08-04 |
| pr |
0.01 |
docs: fix article in n8n image alt |
|
Very terse, repository-specific wording |
2026-10-11 |
| commit |
0.00 |
typo in docs |
|
Extremely terse and informal commit mess |
2026-10-12 |
| commit |
0.00 |
mlx: read candidate logits in float32 for quantized heads |
|
Concise technical commit title with doma |
2026-10-12 |
| commit |
0.00 |
mlx: clip long laya states instead of rejecting them |
|
Terse, domain-specific commit summary wi |
2026-10-12 |
| commit |
0.00 |
llm: support multimodal embeddings through llama-server |
|
Concise technical wording and project-sp |
2026-10-10 |
| commit |
0.00 |
llama: update to b11521 and use native decision support |
|
Specific version reference and technical |
2026-10-09 |
| commit |
0.00 |
decision: align request validation and option descriptions |
|
Brief, technical commit title with concr |
2026-10-10 |
| commit |
0.00 |
server: skip local model compatibility migration (#18908) |
|
Terse, specific commit message with no A |
2026-10-09 |
| commit |
0.00 |
documentation re-structuring |
|
Terse commit-style wording with no AI in |
2026-10-06 |
| commit |
0.00 |
routes: fix embed 413 vs 400 routing (#18822) |
|
Terse, issue-linked routing fix typical |
2026-10-06 |
| commit |
0.00 |
openai: keep image positions when merging tool result parts |
|
Terse, code-specific explanation with co |
2026-10-02 |
| commit |
0.00 |
openai: keep empty tool results sent as an empty content arr |
|
Concise bug description uses precise too |
2026-10-01 |
| commit |
0.00 |
openai: keep tool message content parts in one message |
|
Detailed protocol-specific diagnosis and |
2026-09-30 |
| commit |
0.00 |
docs: document System One API (#18702) |
|
— |
2026-09-30 |
| commit |
0.00 |
create: support explicit model capabilities (#18708) |
|
— |
2026-09-29 |
| commit |
0.00 |
llama.cpp: version bump b11232 (#18652) |
|
— |
2026-09-29 |
| commit |
0.00 |
MLX: version bump (#18651) |
|
— |
2026-09-29 |
| commit |
0.00 |
feat: allow ten web searches per response (#18602) |
|
— |
2026-09-28 |
| commit |
0.00 |
mlx: bound pull stall retries and let the watchdog interrupt |
|
— |
2026-09-28 |
| commit |
0.00 |
feat: add System One scoring API (#18606) |
|
— |
2026-09-28 |
| commit |
0.00 |
bench: use HumanEval patch prompts (#17480) |
|
— |
2026-09-26 |
| commit |
0.00 |
llama-server: prepare to remove compatibility patch |
|
Highly domain-specific migration and man |
2026-07-29 |
| commit |
0.00 |
api: deprecate typical_p (#18627) |
|
— |
2026-09-24 |
| commit |
0.00 |
app: isolate cloud-setting tests from Windows user config (# |
|
— |
2026-09-24 |
| commit |
0.00 |
app: defer Settings model discovery (#18598) |
|
— |
2026-09-24 |
| commit |
0.00 |
app: sync macOS update menu and icon at startup (#18622) |
|
— |
2026-09-24 |
| commit |
0.00 |
mlxrunner: Update XGrammar to 0.2.7 for structured outputs |
|
— |
2026-09-23 |
| commit |
0.00 |
launch: default Claude Code to client-side auto checks (#185 |
|
— |
2026-09-23 |
| commit |
0.00 |
xgrammar: add standalone CMake project for native library (# |
|
— |
2026-09-23 |
| commit |
0.00 |
docs: document thinking control discovery (#18501) |
|
— |
2026-09-23 |
| commit |
0.00 |
mlx: speed up Qwen 3.8 prompt processing (#18550) |
|
— |
2026-09-23 |
| commit |
0.00 |
mlx: select Gemma 4 image resolution dynamically (#18603) |
|
— |
2026-09-23 |
| commit |
0.00 |
server: apply structured outputs in a single pass on thinkin |
|
Detailed domain-specific explanation lac |
2026-09-14 |
| commit |
0.00 |
llm: apply a format after the thinking in one llama-server r |
|
Technical implementation details and cav |
2026-09-15 |
| commit |
0.00 |
mlxrunner: constrain a format after the thinking in one gene |
|
Specific MLX grammar behavior and limita |
2026-09-14 |
| commit |
0.00 |
parsers: report the strings that end a response's thinking |
|
Parser-specific terminology and concrete |
2026-09-14 |
| pr |
0.00 |
cli: add decision model support to `ollama run` |
|
Short, conventional technical title with |
2026-10-12 |
| pr |
0.00 |
Introduce clef and clef flash on cloud |
|
Brief informal note referencing a specif |
2026-10-12 |
| pr |
0.00 |
docs: update SECURITY.md |
|
Short conventional documentation update |
2026-10-12 |
