{"full_name":"Gentleman-Programming/gentle-ai","owner":"Gentleman-Programming","name":"gentle-ai","shard":"1","url":"https://github.com/Gentleman-Programming/gentle-ai","description":"Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.","homepage":"https://gentlemanprogramming.com/","topics":["ai-coding","claude-code","code-review","copilot","cursor","developer-tools","golang","llm","mcp","opencode","persistent-memory","spec-driven-development","agent-skills","ai-agents","codex"],"tag_pages":["agent-skills","ai-agents","ai-coding","claude-code","code-review","codex","copilot","cursor","developer-tools","golang","llm","mcp","opencode","spec-driven-development"],"language":"Go","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/97131605?v=4","created_at":"2026-02-27T23:28:01Z","pushed_at":"2026-11-13T23:01:57Z","metrics":{"stars":9214,"forks":899,"watchers":46,"issues":3561,"prs":2508,"releases":298,"issues_open":375,"issues_closed":3186,"prs_open":37,"prs_closed":896,"prs_merged":1575,"discussions":43},"growth":{"day":{"stars":41,"forks":1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-14","2026-11-15","2026-11-16"],"stars":[9149,9173,9214],"forks":[898,898,899],"watchers":[46,46,46],"issues_open":[366,370,375],"prs_open":[37,36,37]},"boards":{},"same_owner":[],"issues":[{"number":4571,"title":"bug(review 2.8.2): correction_required capture's own status_continuation classifies the just-minted authority corrupted_or_unverifiable_authority, so the bounded correction is unreachable","comments":395,"created_at":"2026-09-14T11:39:03Z"},{"number":5422,"title":"[Automated provider defect] bound STATUS after granted START times out pre_native for ~800+ changed-line candidates on 4.0.0 stable (Windows / Claude Code) — follow-up to #5094","comments":159,"created_at":"2026-10-09T00:24:16Z"},{"number":4655,"title":"bug(review): bound STATUS still times out pre_native after a granted START on a 3-path medium candidate (2.9.1 stable) — regression of #3733 / #4258","comments":109,"created_at":"2026-09-16T00:53:49Z"},{"number":5129,"title":"Review integration blocks on undocumented intended-untracked capture","comments":66,"created_at":"2026-09-30T04:31:28Z"},{"number":5209,"title":"[Automated provider defect] Claude Code: a granted, never-reoffered START's first capture-result lands directly on correction_required, and the bound STATUS goes terminal corrupted_or_unverifiable_authority with zero admitted captures (3.7.0)","comments":58,"created_at":"2026-10-02T19:25:31Z"},{"number":5055,"title":"bug(review): lens_context_inspection_failed on every fresh Claude Code slot for a candidate with a ~2.6 MB binary-attributed path; refresh-and-retry reoffers the same failing slots (3.7.0)","comments":51,"created_at":"2026-09-27T21:49:47Z"},{"number":4790,"title":"bug(review): the frozen-evidence budget is validated only after consent and lineage creation — validate at inspect/START and recommend a commit-range slice","comments":49,"created_at":"2026-09-19T14:34:47Z"},{"number":2029,"title":"fix(review): relay admission feedback and require canonical proof paths","comments":38,"created_at":"2026-07-30T12:11:25Z"}],"discussions":[{"number":6117,"title":"Solicitud para colaborar como maintainer/revisor de la comunidad","comments":0,"category":"General","created_at":"2026-11-13T09:38:55Z"},{"number":6052,"title":"DeepSeek harness","comments":0,"category":"General","created_at":"2026-11-10T06:12:13Z"},{"number":6043,"title":"Supported budget-preserving disposition after initial unknown_causality escalation (CLI 4.3.1)","comments":1,"category":"Q&A","created_at":"2026-11-08T18:56:52Z"},{"number":6016,"title":"Supported disposition after a Pi verifier exits with EDQUOT before agent_settled","comments":0,"category":"Q&A","created_at":"2026-11-07T06:21:49Z"},{"number":5978,"title":"noob: cómo _uso_ Gentle AI?","comments":1,"category":"Q&A","created_at":"2026-11-05T11:20:34Z"},{"number":5846,"title":"Proposal: configurable ODD evaluation with automatic execution graphs","comments":0,"category":"Ideas","created_at":"2026-10-29T05:25:41Z"},{"number":5767,"title":"pi-reply-thread — keep track of the replies one prompt produces and the questions still waiting on you (Pi / Gentle Shell, MIT)","comments":1,"category":"Show and tell","created_at":"2026-10-26T08:21:56Z"},{"number":5764,"title":"PRoblema en la instalacion","comments":0,"category":"General","created_at":"2026-10-25T23:10:14Z"}],"latest_release":{"name":"v4.5.0 — Stopped Reviews Report Their Findings, Windows 10 22H2 Installs","tag":"v4.5.0","published_at":"2026-11-13T23:11:41Z","body":"Gentle AI v4.5.0 is a minor release over v4.4.0. A review that stops at `correction_required` or `escalated` now returns the findings it admitted as non-blocking to a client that explicitly opts in, and a correction-plan request that cannot be built reports `correction_request_unavailable` instead of a corrupted authority. The Separate installer qualifies Windows 10 22H2 (build 19045) on amd64, Codex receives the core-plus-on-demand module split, and Gentle Shell stops refusing a normally used Windows installation on runtime-state byte counts while keeping one recent replacement backup. One verification method now serves the installed runtimes instead of a copy that only OpenCode carried. The provider contract moves to `1.5.0` with an additive stop reason; the review integration contract stays at `v2`, its capability identity stays `capabilities/v2.6`, and the module path stays at `/v4`.\n\n## Provenance\n\n- **Previous stable:** `v4.4.0` → `55240afb100ad6d2ef5fbe16f7be33a7693f77ad`\n- **Release target:** `v4.5.0` → `f2f7d7b16c2cf1afe5e07f717cf8265946ac3feb`\n- **Release workflow:** [run 43523988281](https://github.com/Gentleman-Programming/gentle-ai/actions/runs/43523988281)\n- **Verification:** preflight, release, and verify jobs all succeeded.\n- **Provider contract:** `1.5.0`\n\n## What's new\n\n### Stopped reviews report their non-blocking findings\n\nA `correction_required` or `escalated` closure returned only the findings to correct. The informational, follow-up and refuted findings it admitted existed only inside the transaction state, while the `approved` branch already returned them. `review status` now returns them as `non_blocking_findings` with claims when the caller passes `--non-blocking-findings` and negotiates `--contract gentle-ai.review-integration/v2`. STATUS v9 declares the field as optional, the approved closure keeps its existing payload, and every frozen v1 response is unchanged.\n\nIncluded work: [#6092](https://github.com/Gentleman-Programming/gentle-ai/pull/6092), [#6107](https://github.com/Gentleman-Programming/gentle-ai/pull/6107), [#6108](https://github.com/Gentleman-Programming/gentle-ai/pull/6108) (issue #6088).\n\n### Windows 10 22H2 qualifies for the Separate installer\n\nThe Separate installer required Windows build 22000 or newer on amd64, so a supported Windows 10 22H2 workstation was refused with a diagnostic that named only the rejected build. `UserKernelCheck` now accepts build 19045 and newer on amd64, and the refusal names the accepted range. ARM64, Windows Server and older builds keep the fail-closed refusal.\n\nIncluded work: [#5989](https://github.com/Gentleman-Programming/gentle-ai/pull/5989) (issue #5927) by @decode2.\n\n### Codex receives the core-plus-on-demand module split\n\nCodex now gets the same split runtime guidance as the other hosts — a core orchestrator plus modules delivered on demand — and its deprecated capability configuration is replaced with the current multi-agent form. The other runtimes keep their existing rendering.\n\nIncluded work: [#6121](https://github.com/Gentleman-Programming/gentle-ai/pull/6121) (issue #5256).\n\n### The provider contract adds one stop reason\n\nA correction-plan request that cannot be built used to be indistinguishable from corrupted authority. The shipped continuation contract now carries the stop reason `correction_request_unavailable`, and an eligible manual release is offered only where the existing read-only eligibility check permits it. The change is additive, which is why the contract moves to `1.5.0`.\n\nIncluded work: [#6087](https://github.com/Gentleman-Programming/gentle-ai/pull/6087), [#6101](https://github.com/Gentleman-Programming/gentle-ai/pull/6101) (issue #6086).\n\n## Breaking changes\n\nNo breaking changes are declared for v4.5.0. The module path stays at `/v4`, the review integration contract stays at `v2`, its capability identity stays `capabilities/v2.6`, and no existing review CLI flag changed; `--non-blocking-findings` is a new opt-in flag and `non","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}