upstream-archive/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-09-21 13:38:14 -05:00
Code Issues Packages Projects Releases Wiki Activity
5,777 Commits 462 Branches 666 Tags
main
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Parth Sareen d0c8cdb795 api: expose model thinking levels and defaults (#18473) 2026-09-18 14:10:53 -07:00
Parth Sareen 38fdb5dd58 docs: refresh getting started guides (#18450) 2026-09-14 23:32:30 -07:00
Parth Sareen 2d26fafc42 docs: add ChatGPT Desktop integration (#18377) 2026-09-14 13:24:31 -07:00
Parth Sareen c16bf9892a cmd: remove built-in agent (#18393) 2026-09-11 12:21:52 -07:00
Parth Sareen d8ab4b4f0c openai: support standalone named function outputs (#18348) 2026-09-09 14:51:50 -07:00
Parth Sareen 3738935d0c proxy: normalize namespaced commands in Full Access (#18331) 2026-09-09 10:20:48 -07:00
Parth Sareen 86f7292934 openai: accept plaintext-labeled Codex agent messages (#18329) 2026-09-08 17:09:48 -07:00
Parth Sareen cd1c5a145d openai: finalize responses at the web search limit (#18328) 2026-09-08 16:27:20 -07:00
Parth Sareen 1b45aa19da server/openai: retry compaction after context overflow (#18324) 2026-09-08 14:42:03 -07:00
Parth Sareen 9ef6c19341 app: preserve Codex configuration across host changes (#18247) 2026-09-08 12:42:37 -07:00
Parth Sareen 83ed7d9965 app: harden Codex desktop proxy handling (#18244) 2026-09-04 17:48:55 -07:00
Parth Sareen b043d891c2 openai: preserve images through response compaction (#18245) 2026-09-04 17:48:45 -07:00
Parth Sareen 43e667004a app: route Codex auto review through selected model (#18246) 2026-09-04 17:48:37 -07:00
Parth Sareen 3f77cb6dfb openai: add Codex compaction support (#18224) 2026-09-04 13:07:33 -07:00
Parth Sareen cf8b605b06 openai: add client tool search support (#18223) 2026-09-04 13:07:23 -07:00
Parth Sareen 39f7f91563 app: synchronize macOS app handoff (#18056) 2026-08-26 23:15:54 -07:00
Parth Sareen d366f4868a proxy: continue requests when the model catalog changes (#18058) 2026-08-26 19:39:05 -07:00
Parth Sareen 13f2fb8c99 app: consume Claude recommendation mappings (#18042) 2026-08-26 15:55:01 -07:00
Parth Sareen e2c6c7e894 docs: claude docs (#18006) 2026-08-25 19:34:13 -07:00
Parth Sareen 9dbf139133 docs: document Claude Desktop integration (#18004) 2026-08-25 19:12:21 -07:00
Parth Sareen ebf200f952 proxy: preserve string content during image fallback (#18002) 2026-08-25 15:03:57 -07:00
Parth Sareen 6e19e916c7 app: reject browser origins on Claude Desktop gateway (#17989) 2026-08-25 09:48:44 -07:00
Parth Sareen 82ad9fa38b app: add Claude Desktop Auto mode setting (#17975) 2026-08-24 18:20:59 -07:00
Parth Sareen 60d83f8b0e app: make integrations list scrollable (#17977) 2026-08-24 17:46:45 -07:00
Parth Sareen fb30760996 app: prevent Apps title bar overlap (#17925) 2026-08-21 18:48:22 -07:00
Parth Sareen 124e9af9d2 app: sign model recommendation endpoint (#17919) 2026-08-21 17:21:00 -07:00
Parth Sareen 2d9622a4d4 app: claude model management (#17915) 2026-08-21 15:04:58 -07:00
Parth Sareen 8f912415e8 launch: fall back to npx for DeepSeek Harness (#17758) 2026-08-20 14:04:44 -07:00
Parth Sareen 30546d1fd4 app: add claude desktop app (#17899) 2026-08-20 14:03:43 -07:00
Parth Sareen b8a6272440 qwen3.8: normalize system messages (#17855) 2026-08-19 13:08:09 -07:00
Parth Sareen 78e818e3ce docs: register DeepSeek Harness (#17751) 2026-08-14 14:30:21 -07:00
Parth Sareen 39df91c982 launch: add DeepSeek Harness integration (#17733) 2026-08-13 15:19:02 -07:00
Parth Sareen 9a56a0e845 agent: allow multiple edits per edit tool call (#17711) 2026-08-12 16:45:53 -07:00
Parth Sareen b6b1b258c3 openai: support web search in Responses API (#17686) 2026-08-12 11:51:54 -07:00
Parth Sareen f91cb0d6a7 agent/tui: stream thinking traces (#17611) 2026-08-07 13:11:45 -07:00
Parth Sareen 0e2e34aa86 cmd/tui: improve prompt debug rendering (#17334) 2026-07-27 17:29:18 -07:00
Parth Sareen 76929b0a8a agent: accept file mentions on Enter (#17384) 2026-07-27 17:28:55 -07:00
Parth Sareen bf7be180e3 tui: avoid table detection for pipe prose (#17424) 2026-07-27 13:42:08 -07:00
Parth Sareen 3f07e022ac cmd/tui: agent system prompt command (#17296) 2026-07-24 14:44:25 -07:00
Parth Sareen 551809688b agent: permission skill loading (#17304) 2026-07-24 14:37:21 -07:00
Parth Sareen fce745fe5e agent: import skills from coding agents (#17294) 2026-07-22 22:40:25 -07:00
Parth Sareen e8f7c93a0b launch: update Hermes integration (#17202) 2026-07-20 11:28:01 -07:00
Parth Sareen 0de38190d7 cmd/tui/chat: render bold emphasis consistently across markdown (#17224) 2026-07-20 11:25:43 -07:00
Parth Sareen 681dfaedcc cmd: remove standalone agent command (#17229) 2026-07-20 11:25:31 -07:00
Parth Sareen 9893d39218 cmd: complete slash commands before submitting (#17230) 2026-07-20 11:25:12 -07:00
Parth Sareen 5ba17e6fdf agent/tui: remove redundant context-window refreshes from event loop (#17241) 2026-07-20 11:25:01 -07:00
Parth Sareen 6f3b997dec cmd: route root command server start through checkServerHeartbeat (#17245) 
The bare `ollama` command (and `ollama launch` with no integration) used a
bespoke `ensureServerRunning` that forked `ollama serve` directly and polled
its heartbeat forever (no timeout, no platform-aware launch). Every other
subcommand (`ollama run`, `ollama pull`, `ollama launch <integration>`, ...)
goes through `checkServerHeartbeat` -> `startApp`, so the root command behaved
differently and could hang indefinitely.

Route `runInteractiveTUI` through `checkServerHeartbeat(cmd, nil)` — the same
path `ollama launch <thing>` uses — so the root command is consistent and no
longer runs an unbounded server-spawn loop. `ensureServerRunning` and its
`backgroundServerSysProcAttr` helpers (only it referenced them) are removed,
along with the now-unused `os/exec` import.

The platform `startApp`/`waitForServer` paths are unchanged, so behavior on
macOS/Windows is identical to the other subcommands, and on Linux the root
command now errors the same way the subcommands already do when no server is
running.
 2026-07-20 11:24:25 -07:00
Parth Sareen 573386c35e agent: skills system (#17203) 2026-07-17 10:32:22 -07:00
Parth Sareen 714b6fc2a4 agent: allow unlimited tool rounds for cloud models by default (#17217) 2026-07-16 19:07:01 -07:00
Parth Sareen 61e1b1ba5e agent: clean up semantics, UX, DX, and procedural code (#17212) 2026-07-16 19:06:06 -07:00
Parth Sareen 5865a01e48 agent: reorder working directory instruction (#17228) 2026-07-16 19:05:30 -07:00
Parth Sareen e61c1c73fe cmd: remove dead agent prompt wrappers (#17227) 2026-07-16 17:16:14 -07:00
Parth Sareen 30c390384e cmd: put current working dir in the system prompt (#17188) 2026-07-15 12:10:28 -07:00
Parth Sareen d590830091 agent/tools: isolate web tests from cloud policy (#17208) 2026-07-15 12:07:05 -07:00
Parth Sareen fdcf9efafd fix launch model picker recovery (#17170) 2026-07-15 11:31:22 -07:00
Parth Sareen 76188f60cd docs: add VS Code extension setup (#17158) 2026-07-15 11:30:43 -07:00
Parth Sareen 3bd506bd1c agent/tools: surface actionable web auth error (#17169) 2026-07-14 13:35:16 -07:00
Parth Sareen f1a0ffd621 launch: rename Codex App integration to ChatGPT (#17161) 2026-07-13 14:34:17 -07:00
Parth Sareen cd600e19a3 cmd/tui: simplify integration selection and update menu description (#17159) 2026-07-13 12:52:40 -07:00
Parth Sareen 82f905cd9c cmd: agent UI (#17017) 2026-07-09 17:27:31 -07:00
Parth Sareen cb3d98ccb2 launch: warn before launching old agent models (#17063) 2026-07-09 16:55:10 -07:00
Parth Sareen 87b64213b4 launch: disable claude code telemetry by default (#17061) 2026-07-06 15:24:11 -07:00
Parth Sareen a2b3a5e9a3 agent: harness core (#16963) 2026-07-02 11:44:31 -07:00
Parth Sareen 2e474c98f9 parser/renderer: add Ornith 9B renderer/parser support (#16920) 2026-06-25 23:18:47 -07:00
Parth SareenandDaniel Hiltgen c191a145bb llm: preserve generation headroom for shifted prompts (#16856) 
---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
 2026-06-23 15:29:40 -07:00
Parth Sareen 479e1cf94e docs: document max think level (#16877) 2026-06-23 15:29:15 -07:00
Parth Sareen e1f7f9cbdb ci: pin darwin release xcode (#16788) 2026-06-17 13:01:10 -07:00
Parth Sareen 12e04379cd launch: Fix launch provider drift (#16683) 2026-06-11 17:21:46 -07:00
Parth Sareen e09b3f9fb5 openai: align models list with tags (#16556) 2026-06-05 17:59:05 -07:00
Parth Sareen ac3d0657a2 launch: migrate pi (#16213) 2026-06-03 14:35:32 -07:00
Parth Sareen f57d111754 launch: isolate Codex launch configuration (#16437) 2026-06-02 12:10:46 -07:00
Parth Sareen 2c71d8d7ca launch: migrate Codex config (#16397) 
* launch: migrate Codex config
 2026-06-01 13:46:41 -07:00
Parth Sareen 91c8e5e1a8 launch: enriched model inventory (#16230) 2026-05-21 11:57:20 -07:00
Parth Sareen b9c0421f03 docs: add codex app (#16163) 2026-05-14 17:53:15 -07:00
Parth Sareen c28ddc0a7b launch: codex app restarts (#16155) 2026-05-14 12:08:13 -07:00
Parth Sareen 3ad2fa3fb5 launch: update codex app UI copy (#16157) 2026-05-14 12:08:08 -07:00
Parth Sareen 6b6f45ef0e docs: hide codex app till launch (#16153) 2026-05-14 10:56:52 -07:00
Parth Sareen ac7295ccab launch: codex app integration (#16120) 2026-05-13 17:11:52 -07:00
Parth Sareen f866e7608f launch: disable Claude Desktop launch (#16028) 2026-05-07 10:46:18 -07:00
Parth Sareen bab59072fb launch: add plan-aware model gating (#16027) 2026-05-06 14:34:26 -07:00
Parth Sareen d319227df0 server: cache show responses (#15967) 2026-05-05 14:40:18 -07:00
Parth Sareen 4017af96cd go: bump to 1.26 (#15904) 2026-05-03 23:24:35 -07:00
Parth Sareen 9ba5a04914 launch: claude app (#15937) 2026-05-02 19:19:57 -07:00
Parth Sareen c7c2837c96 renderers: update gemma4 renderer (#15886) 2026-04-29 18:40:23 -07:00
Parth Sareen b6447caebc launch: use vram bytes for model recommendations (#15885) 2026-04-29 18:40:14 -07:00
Parth Sareen 321cc8a2ba server/launch: add model recommendations cache endpoint (#15868) 2026-04-28 17:09:04 -07:00
Parth Sareen ea01af6f76 openai: map responses reasoning effort to think (#15789) 2026-04-24 02:49:36 -07:00
Parth Sareen c2ebb4d57c api: accept "max" as a think value (#15787) 2026-04-24 01:49:39 -07:00
Parth Sareen 590109c835 launch: harden OpenClaw onboarding flow (#15777) 2026-04-23 16:47:20 -07:00
Parth Sareen 160660e572 launch: use bundled OpenClaw ollama web search (#15757) 2026-04-22 16:34:19 -07:00
Parth Sareen 21883571b7 launch: replace kimi-k2.5 with k2.6 as top recommended model (#15737) 2026-04-21 15:13:20 -07:00
Parth Sareen 5d1021603a server: apply format when think=false for gemma4 (#15678) 2026-04-20 17:42:29 -07:00
Parth Sareen 8e05d734b9 launch: add kimi cli integration with installer flow (#15723) 2026-04-20 15:33:32 -07:00
Parth Sareen 123b300af6 docs: update hermes (#15655) 2026-04-17 14:20:59 -07:00
Parth Sareen 57653b8e42 cmd/launch: show WSL guidance on Windows instead of handing off (#15637) 2026-04-16 17:18:04 -07:00
Parth Sareen a50ce61c54 launch: skip unchanged managed-single rewrite (#15633) 2026-04-16 16:20:42 -07:00
Parth Sareen 43f90def04 launch: add hermes (#15569) 2026-04-15 12:00:23 -07:00
Parth Sareen 80d3744c5d launch: update openclaw channel message (#15463) 2026-04-09 15:20:30 -07:00
Parth Sareen 673726fa0e app: restore launch default and refine launch sidebar open for app (#15437) 2026-04-08 16:59:21 -07:00
Parth Sareen 4e16f562c0 launch: add openclaw channels setup (#15407) 2026-04-08 13:25:27 -07:00