Pull Request Explorer
| Title | Author | Size | AI | Cycle Time | Review | Merged |
|---|---|---|---|---|---|---|
| Improve /prompt rendering performance | ParthSareen | M | No | 122.7h | 119.1h | Jul 28, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd/tui: accept file mentions with Enter in the agent TUI | ParthSareen | M | No | 72.7h | 69.2h | Jul 28, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd/tui: keep pipe-delimited prose out of tables | ParthSareen | S | No | 0.3h | 0.2h | Jul 27, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| ci: on release builds dont fail fast | dhiltgen | XS | No | 14.6h | 0.5h | Jul 27, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| mlx update | dhiltgen | XS | No | 27.6h | 27.6h | Jul 26, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| model: add Laguna MLX support | dhiltgen | XL | No | 176.9h | 98.0h | Jul 25, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| x/create: quantize a draft model's output head at the requested type | jessegross | S | No | 0.7h | 0.7h | Jul 25, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| mlx: keep loaded model memory resident | dhiltgen | M | No | 18.5h | 15.8h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd/tui: agent system prompt command | ParthSareen | L | No | 71.0h | 21.5h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| agent: permission skill loading | ParthSareen | M | No | 61.8h | 10.9h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| qwen3_5: fix expert quantization handling and gather packed gate_up in one launch | jessegross | L | No | 46.9h | 46.3h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| server: fix ps data race on scheduler loaded map | dhiltgen | M | No | 3.7h | 1.9h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| test: harden flaky updater and transfer unit tests | dhiltgen | S | No | 0.3h | 0.2h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| x/create: quantize lm_head at 8-bit in the requested family | jessegross | S | No | 4.6h | 4.4h | Jul 24, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| agent: import skills from coding agents | ParthSareen | XL | No | 31.4h | 22.0h | Jul 23, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| model: align Laguna with upstream llama.cpp | dhiltgen | XL | No | 2.2h | 0.9h | Jul 23, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| docs: update retirements | mxyng | S | No | 25.9h | - | Jul 22, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| model/parsers: finalize incomplete GLM tool calls | dhiltgen | L | No | 98.5h | 98.5h | Jul 22, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| mlx update | dhiltgen | XS | No | 1.3h | 0.9h | Jul 22, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| model: add Laguna v8 chat support and fix Metal inference | dhiltgen | XL | No | 1.1h | 1.0h | Jul 21, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| CI: fix missing CUDA v13.4 sub-package | dhiltgen | XS | No | 0.3h | - | Jul 21, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| server: detect download stalls before the first byte | TheJhyeFactor | M | No | 53.1h | 30.6h | Jul 21, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| llama: enable dio on linux CUDA/ROCm iGPUs | dhiltgen | XS | No | 3.2h | 2.9h | Jul 21, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| add renderer/parser fields to the API docs | pdevine | S | No | 0.9h | 0.2h | Jul 20, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| build: bump Linux toolchain to GCC 13 | dhiltgen | S | No | 68.9h | 68.7h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| MLX update | dhiltgen | XS | No | 139.9h | 139.7h | Jul 20, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| launch: update Hermes integration | ParthSareen | M | No | 132.0h | 127.3h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd/tui/chat: render bold emphasis consistently across markdown | ParthSareen | L | No | 94.3h | 89.7h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd: remove standalone agent command | ParthSareen | M | No | 88.5h | 83.9h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd: complete slash commands before submitting | ParthSareen | M | No | 88.0h | 83.4h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| agent/tui: remove redundant context-window refreshes from event loop | ParthSareen | S | No | 69.9h | 65.3h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd: route root command server start through checkServerHeartbeat | ParthSareen | M | No | 67.9h | 16.8h | Jul 20, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| llama.cpp update | dhiltgen | XS | No | 141.0h | 141.0h | Jul 20, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| agent: skills system | ParthSareen | XL | No | 58.5h | 56.9h | Jul 17, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| anthropic: close text block before starting thinking block | hoyyeva | M | AI | 18.1h | 2.1h | Jul 17, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| agent: allow unlimited tool rounds for cloud models by default | ParthSareen | M | No | 18.4h | 17.7h | Jul 17, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| agent: clean up semantics, UX, DX, and procedural code | ParthSareen | XL | No | 26.1h | 25.3h | Jul 17, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| agent: reorder working directory instruction | ParthSareen | XS | No | 1.3h | 0.6h | Jul 17, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd: remove dead agent prompt wrappers | ParthSareen | S | No | 1.1h | 1.1h | Jul 17, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| launch: keep Claude Code channels available | hoyyeva | S | AI | 19.4h | 9.8h | Jul 16, 2026 |
|
LLM analysis pending This PR has not been analyzed yet. |
||||||
| cmd: put current working dir in the system prompt for agent | ParthSareen | M | No | 20.6h | 20.4h | Jul 15, 2026 |
SummaryHealth AssessmentAI DetailsTech Stack |
||||||
| agent/tools: isolate web tests from cloud policy | ParthSareen | M | No | 0.5h | 0.5h | Jul 15, 2026 |
SummaryBug FixIsolate web tests from cloud policy Ensures web tool tests run independently of cloud policy, improving test reliability and preventing false failures in CI environments. Health Assessment
Small
Low
Low
AI DetailsTech Stack
Languages:
Go
|
||||||
| launch: fix alternate model picker recovery | ParthSareen | M | AI | 42.3h | 21.6h | Jul 15, 2026 |
SummaryBug FixFix alternate model picker recovery Ensures users can recover from deprecated model warnings and launch successfully, improving reliability. Health Assessment
Medium
Low
Low
AI Details
Usage:
AI Assisted
Category:
Code AI
Tools:
Claude
Confidence:
0.95
Tech Stack
Languages:
Go
|
||||||
| docs: add VS Code extension setup | ParthSareen | M | No | 48.1h | 26.8h | Jul 15, 2026 |
SummaryDocsAdd VS Code extension setup documentation Provides updated documentation for installing and using the Ollama VS Code extension, replacing the launch guide and aligning with marketplace flow. Health Assessment
Small
Low
Medium
AI DetailsTech Stack |
||||||
| model: align gemma4 chat template handling | dhiltgen | L | No | 2.9h | 1.6h | Jul 14, 2026 |
SummaryBug FixAlign Gemma4 chat template handling Improves Gemma4 chat template handling for more stable tool calls, better turn closure, and multi-turn reasoning, enhancing user experience and reliability. Health Assessment
Medium
Low
Low
AI Details
Confidence:
0.95
Tech Stack
Languages:
Go
|
||||||
| docs: collapsed previous retirements | mxyng | S | No | 21.6h | 19.5h | Jul 14, 2026 |
SummaryDocsCollapse previous retirements in docs This change collapses previous retirements in the documentation, improving readability and navigation. Health Assessment
Small
Low
Low
AI DetailsTech Stack |
||||||
| agent/tools: surface actionable web auth error | ParthSareen | M | No | 21.1h | 21.0h | Jul 14, 2026 |
SummaryBug FixSurface actionable web authentication error Provides clear, actionable error messages for web tool authentication failures, improving user experience and reducing support tickets. Health Assessment
Medium
Low
Low
AI DetailsTech Stack
Languages:
Go
|
||||||
| mlxrunner: MTP follow-up fixes and tuning | jessegross | XL | No | 162.0h | 123.7h | Jul 14, 2026 |
SummaryBug FixMTP follow-up fixes and tuning Improves memory usage and performance for MLX runner's MTP speculative decoding, addressing cache leaks and optimizing convolution boundaries, preparing for upcoming draft cache support. Health Assessment
X-Large
High
High
AI Details
Confidence:
0.10
Tech Stack
Languages:
Go
|
||||||
| launch: rename Codex App integration to ChatGPT | ParthSareen | XL | AI | 1.4h | 0.2h | Jul 13, 2026 |
SummaryFeatureRename Codex App integration to ChatGPT Unifies the integration name for the ChatGPT desktop app, improving user experience while preserving backward compatibility with legacy aliases. Health Assessment
Large
Low
Low
AI Details
Category:
Code AI
Confidence:
0.75
Tech Stack
Languages:
Go, Typescript
Frameworks:
React
|
||||||
| cmd/tui: simplify integration selection and update menu description | ParthSareen | L | No | 1.1h | 0.1h | Jul 13, 2026 |
SummaryRefactorSimplify TUI integration selection and menu This PR streamlines the TUI launcher menu by replacing a dynamic expansion mechanism with a curated list of integrations, improving user experience and reducing menu complexity. The change also updates menu descriptions for clarity. Health AssessmentAI Details
Confidence:
0.75
Tech Stack
Languages:
Go
|
||||||