Commit graph

620 commits

Author SHA1 Message Date
Patrick Devine
0c666ce5ee
cmd: omit bias and gamma vectors from verbose safetensors show (#19803) 2026-11-20 14:44:24 -08:00
Eva H
5187f59581
test: stabilize Pi catalog timeout regressions (#19742) 2026-11-20 16:34:09 -05:00
Gaurav Jain
169626b403 cmd: leave multiline mode when Ctrl+C or Ctrl+G discards input
Abandoning a """ block left the REPL in multiline mode, so the next
line was swallowed or saved as the system message. Reset the multiline
state along with the buffer whenever readline returns an error.

Fixes #19340

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-16 18:20:35 -08:00
Parth Sareen
9da7dfd5c3
cmd: show help for noninteractive bare invocations (#19557) 2026-11-12 14:35:02 -08:00
Eva H
8a89b76cc7
launch: refresh Pi metadata after sign-in and honor prompt args (#19575) 2026-11-10 17:43:58 -05:00
Eva H
f1ee5679fe
cmd/launch: use thinking metadata for OpenCode settings (#19409) 2026-11-09 17:29:01 -05:00
Eva H
1f23c7232e
Improve ChatGPT CLI restore and graceful restart (#19583)
Make --restore confirm before changing an active profile, leave a closed
app closed, and preserve existing settings and chat history. Let interactive
users finish ChatGPT's own quit prompt instead of force-quitting it.

Carry cancellation and timeouts through status checks, quit requests and
exit polling. Check cancellation before profile writes, and keep legacy
PID and singleton probes read-only until shutdown is confirmed, including
when a legacy client starts after preflight.

Keep context checks around process queries so a canceled probe cannot be
mistaken for a confirmed exit. Publish the legacy-quit test marker with an
atomic rename so cancellation cannot interrupt its write.

Validation: 591 launch tests, focused race checks, CLI build, and 100 repeated
legacy-quit cancellation checks with the race detector.

* Fix ChatGPT restore CI setup

Stub installed-app discovery in the late legacy-start consent test so it
runs without ChatGPT installed on the CI host.

Document the containedctx exception for the context implementation that
observes spinner cancellation synchronously. This preserves the existing
cancellation behavior while satisfying the repository lint configuration.
2026-11-09 12:29:51 -05:00
Eva H
5e983d4f80
launch: fix Claude Code routing and retired model errors (#19587) 2026-11-06 21:28:13 -05:00
J Berg
02480ca2a4
cmd/launch: add Kimi Code CLI support (#19506) 2026-11-05 13:41:21 -08:00
Parth Sareen
f60dd2060f
cmd: restore the no-argument launcher (#19478)
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2026-11-05 13:41:22 -05:00
Parth Sareen
32ce4379cc
cmd/launch: show gateway model names in Claude Desktop's model picker (#19533) 2026-11-05 10:40:54 -08:00
Eva H
e9fde36d75
launch: populate Pi models automatically (#19460) 2026-11-03 15:26:02 -08:00
Eva H
0c85e0afbe
launch: check ChatGPT routing before configuring (#19470) 2026-11-02 13:39:49 -08:00
Parth Sareen
f9323416f0
feat(launch): use model output limits for Claude Code (#19410) 2026-10-30 14:34:54 -07:00
Eva H
174cb1dcca
app: make ChatGPT disconnect failures retryable (#19336) 2026-10-30 17:34:24 -04:00
Eva H
c31a690bc2
cmd: show help when running ollama without arguments (#19248) 2026-10-28 16:58:14 -04:00
Daniel Hiltgen
f067033f91
mlx: add LFM3 and d1 models (#19333) 2026-10-27 08:47:18 -07:00
Eva H
8ec9ecdf69
cmd/launch: fix OpenCode v2 launch and config parsing (#19310)
Co-authored-by: 0d00ciallo0721 <259874237+0d00ciallo0721@users.noreply.github.com>
2026-10-26 22:18:30 -04:00
Jeffrey Morgan
675150d6ad
voice: add voice catalog for Phonon (#19242)
* mlxrunner: import and list Phonon catalog voices

* docs: document Phonon voices
2026-10-23 16:15:08 -07:00
Eva H
1472203c47
launch: use allocated context for OpenCode (#19193) 2026-10-23 11:45:15 -07:00
J Berg
4568674810
Make sure all launchers know about cloud model metadata (#19223) 2026-10-22 15:41:36 -07:00
Jeffrey Morgan
6ef847b8fe
mlxrunner: add Phonon text-to-speech support (#19166)
* mlxrunner: add Phonon text-to-speech support

Add Phonon text-to-speech through the existing MLX runner, with an
OpenAI-compatible speech endpoint and CLI playback.

Include model loading, text preprocessing, streaming audio, and
regression tests.

* docs: add speech models

* fix min version

---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2026-10-22 11:36:42 -07:00
Parth Sareen
8886afcd80
launch: use cloud model context in Claude Code (#19119) 2026-10-22 11:04:30 -07:00
Daniel Hiltgen
f20eb3b312
mlx: add d3 decision model support (#19196)
* mlx: add d3 decision model support

* bench: report loaded VRAM for decision runs
2026-10-22 08:50:14 -07:00
Eva H
e61ba8b470
openai: finish reasoning before client tool calls (#19146) 2026-10-19 18:51:48 -07:00
Jonathan Berg
b5c4e9058a avoid scary claude warning about auto compact window being too big 2026-10-19 15:06:12 -07:00
Daniel Hiltgen
36a6e994d2
api: populate show renderer/parser fields and add template_source (#19095)
ShowResponse's renderer and parser fields existed but the server never
set them; they now carry the effective values (renderer resolves the
gemma4 legacy alias by model size). A new template_source names what
actually renders chat prompts: the configured renderer/parser (leaving
any packaged template inert), a Go template layer, the GGUF's embedded
jinja, harmony, or none.

The CLI prints renderer/parser/template source rows only when set, so
ollama show output is unchanged for models without rendering config.
2026-10-17 17:31:52 -07:00
Jonathan Berg
6f035d4195 test 2026-10-15 17:21:37 -07:00
Jonathan Berg
f94778a7fe use identifiers for --ask mode question keys 2026-10-15 17:17:43 -07:00
Parth Sareen
45e6011815
launch: allow usage credits without upgrading (#18985) 2026-10-13 14:23:05 -07:00
Jeffrey Morgan
7a5ae12ead
cli: add decision model support to ollama run (#18962) 2026-10-13 12:39:05 -07:00
Daniel Hiltgen
72f61ca412
Add decision model integration tests and benchmarks (#18746)
* Add decision model integration tests and benchmarks

Support external JSONL corpora, quality scoring, concurrent requests, vision, and System One timing metrics.

* Refine decision tests and benchmarks with cache checks, external endpoints, and consistent response validation and timing
2026-10-13 12:16:57 -07:00
Parth Sareen
6eaad72953
launch: populate Codex model picker with installed Ollama models (#18887) 2026-10-12 10:52:41 -07:00
Eva H
021cda5228
launch: suppress Claude Code connector warning for Ollama (#18878)
Co-authored-by: Parth Sareen <parth.sareen@ollama.com>
2026-10-09 11:04:07 -04:00
Eva H
c2b7368d41
launch: avoid inherited service-tier warnings in Codex (#18879) 2026-10-08 16:18:09 -04:00
Jonathan Berg
0c7340b4bb respect CLAUDE_CODE_AUTO_COMPACT_WINDOW user setting 2026-10-08 10:33:11 -07:00
Jonathan Berg
c77b81c503 Set CLAUDE_CODE_MAX_CONTEXT_TOKENS to whatever the models context window is 2026-10-07 16:09:35 -07:00
Eva H
468e7e5008
cmd: remove account step from CLI onboarding (#18826) 2026-10-07 13:51:57 -04:00
Daniel Hiltgen
a00d083bb5
mlx: System one support (#18701)
* mlxrunner: restore System One scoring

Carry the MLX implementation and its tests from the original System One
commit. The API/compiler and llama-server implementation already exist on
the release branch, so retain those versions. Adapt the optional model test
to the renamed decision package and its explicit rendering/context setup.

(cherry picked from commit 26e546ddb3)

* Enable MLX System One and add regression coverage

* mlxrunner: add Laya support for System One

Import Laya checkpoints and implement bidirectional decision scoring.

* mlxrunner: release cached buffers after System One scoring

* decision: match Tev1 and Nimble publisher prompt formats

Select Tev1 prompts using renderer metadata and fix JSON formatting, with regression coverage for GGUF and MLX.

* mlx: support Clef and Clef Flash decision models

Add model import, quantization safeguards, and text/image scoring with the Clef joint decision head.

* support vision capabilities for decision models

* Make Clef scoring cancellable between prefill chunks

Preserve joint-head inputs and test cancellation, cleanup, and recovery.

* mlx: separate decision preparation and readout from forward

Let serial and batched scoring share model-owned preparation and readout
without duplicating architecture-specific logic in the runner.

* mlx: add Strands Decider support

* implement caching

---------

Co-authored-by: ParthSareen <parth.sareen@ollama.com>
2026-10-03 13:17:21 -07:00
Daniel Hiltgen
eadb68a609 Merge remote-tracking branch 'upstream/main' into release_v0.40.0
# Conflicts:
#	server/routes.go
2026-09-29 11:15:31 -07:00
Daniel Hiltgen
b3f78b7732
create: support explicit model capabilities (#18708)
Add CAPABILITY declarations to Modelfiles and an additive capabilities
field to create requests. Preserve declarations across GGUF and safetensors
creation, inheritance, and Modelfile export.

Require decision capability before scheduling System One requests instead
of matching Qwen architecture/renderer metadata. Retain main's GGUF-only
scoring restriction until the separate MLX runtime work lands.

Extracted from the capability foundation in 36d46a0c3 on system_one_mlx;
MLX scoring and manifest-list changes are intentionally separate.
2026-09-29 11:10:25 -07:00
Daniel Hiltgen
47bbe1eebe Merge remote-tracking branch 'upstream/main' into release_v0.40.0
# Conflicts:
#	server/images.go
#	server/routes.go
2026-09-28 14:14:00 -07:00
Daniel Hiltgen
16b4376aea
bench: use HumanEval patch prompts (#17480)
* bench: use code prompts for prompt-token runs

Replace the synthetic word-list prompt with packed HumanEval Python prompts so speculative draft models see code-like continuations.

Keep the benchmark on the chat path, and calibrate -prompt-tokens with untimed chat probes that read PromptEvalCount instead of relying on a separate token-count API.

Each request still gets a nonce prefix to avoid prefix-cache hits while timed epochs measure the chat-rendered workload.

* review comments

* use different windows for each epoch

* add OpenAI API support

* address comments
2026-09-26 07:29:54 -07:00
Daniel Hiltgen
75b952780f llama-server: prepare to remove compatibility patch
Add manifest-list storage so runner-specific manifests can coexist under one tag while preserving existing v1 tags as best-effort downgrade anchors. Show/list/copy/remove/pull/push now understand runner and digest selection and transfer referenced child manifests and layers.

Add lazy local compatibility migration for legacy Ollama GGUFs into llama.cpp-compatible children, covering the patched model families and preserving parser/renderer, templates, projectors, media metadata, split GGUFs, and MTP/draft tensors where applicable.

Extend create/import/conversion paths for the same compatibility rules, harden manifest-list combine validation, and add focused manifest, migration, transfer, and integration coverage for first-load conversion plus chat/tools/vision/audio/embedding behavior.
2026-09-24 19:25:52 -07:00
Daniel Hiltgen
7af393188d
api: deprecate typical_p (#18627)
Switch from rejecting API requests to logging a warning.  Model creation still rejects the deprecated param.

Follow up from #18448 to remove the hard API failure.
2026-09-24 15:03:28 -07:00
Parth Sareen
01c0fbfd35
launch: default Claude Code to client-side auto checks (#18596) 2026-09-23 15:20:45 -07:00
Eva H
ac3439083d
app: avoid System Events for ChatGPT/Codex detection (#18601) 2026-09-22 13:28:58 -07:00
Parth Sareen
d0c8cdb795
api: expose model thinking levels and defaults (#18473) 2026-09-18 14:10:53 -07:00
Eva H
7fa8a024b7
cli: add first-run onboarding shared with the desktop app (#18495) 2026-09-17 11:49:24 -07:00
Jesse Gross
04b450a81b mlxrunner, cmd, server: fold three small packages into their users
model/base held the Model interface and the architecture registry while
model held weight loading and quant parameters, and every architecture
imported both. create/client was the CLI side of safetensors imports,
with the create command as its only caller, a duplicate of the command's
adapter error, and a name that read like a second API client. The
safetensors show helpers had their own package under x/ although it
already declared package server.

base merges into model, so base.Model and base.Register become
model.Model and model.Register; nothing in the two overlapped. The create
client's two files and their tests join package cmd, and the five names
the command called are no longer exported. The show helpers join the
server package, and the three entry points routes.go calls become
unexported like the helpers around them.
2026-09-16 14:06:08 -07:00