公开记录中等
软件健康报告模式 0.27.0 · 指标 1.13.0 · 2026-07-28 03:05 UTC
ThatCatDev / tanrenai
Tanrenai — a self-evolving local LLM system
ThatCatDev/tanrenai 的健康指数为 100 分中的 50 分，处于「中等」区间。 其得分最高的类别是AI Readiness（86/100），最低的是Community & Adoption（12/100）。 最近一次更新在 18 天前。 近期的大部分工作由 1 位贡献者完成。
50
总分 / 100软件健康指数
指标归入加权类别，统一采用 1–100 量表。总体分先取类别加权平均；当公开证据触发高风险司法辖区政策时，评级会按政策调整，并设置 49（有风险）的上限。AI 就绪度不计入总体分。
50
优秀85-100堪称典范；基本满足所有检验标准
良好70-84健康；仅有轻微不足
中等50-69可接受，但存在明显不足；建议进行审查
存在风险30-49存在重大薄弱环节；采用时应保持审慎
危急1-29问题严重（项目被弃置、仅有单一维护者、缺乏基本工程规范）
评分画像
每条轴代表一个类别。形状比平均值更重要——健康的对象会填满整个图形，而“一峰一谷”式画像意味着某一维度的优势正掩盖另一维度的风险。
所有权
软件包生态系统
| 注册表 | 软件包 | 版本 | 月下载量 | 版本数 | 最近发布 |
|---|---|---|---|---|---|
| Go | github.com/ThatCatDev/tanrenai | v1.33.4 | - | 61 | 18 天前 |
按类别列示的指标
活力
项目是否仍有生命——是否仍在编写代码，是否仍在发布版本？
75
开发活跃度
65中等
评分方式
| 28.8/36 | 推送新近度 — 最近一次推送于 18 天前 |
| 9/36 | 提交节奏 — 52 周中有 13 周有提交 |
| 17.4/18 | 提交量 — 最近一年 85 次提交 |
| 10/10 | OpenSSF Scorecard：Maintained — 16 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
所用输入
| commits_last_year | 85 |
| human_commit_share | 1 |
| days_since_last_push | 18 |
| active_weeks_last_year | 13 |
发布纪律
90优秀
评分方式
| 27/27 | 有发布版本 — 已发布 63 个发布版本 |
| 36/36 | 发布时效 — 最近一次发布版本于 18 天前 |
| 27/27 | 发布节奏 — 约每 3.5 天发布一次 |
| 0/10 | OpenSSF Scorecard：Signed-Releases — Project has not signed or included provenance with any releases. |
所用输入
| releases_count | 63 |
| latest_release_tag | vscode-v1.0.2 |
| releases_from_tags | 否 |
| days_since_latest_release | 18 |
| mean_days_between_releases | 3.5 |
社区与采用
项目是否拥有用户、下载量与关注度，并具备欢迎贡献者参与的配置？
12
流行度与采用
1危急
评分方式
| 0/60 | 星标 — 1 个星标 |
| 0/25 | 复刻 — 0 个复刻 |
| 0/15 | 关注者 — 0 位关注者 |
所用输入
| forks | 0 |
| stars | 1 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
社区健康
25危急
评分方式
| 22.5/22.5 | README |
| 0/22.5 | 许可证 — 未检测到许可证文件 |
| 0/18 | CONTRIBUTING 指南 |
| 0/13.5 | 行为准则 |
| 0/7.2 | 议题模板 |
| 0/6.3 | PR 模板 |
所用输入
| has_readme | 是 |
| has_license | 否 |
| has_contributing | 否 |
| has_issue_template | 否 |
| has_code_of_conduct | 否 |
| has_pull_request_template | 否 |
可持续性与治理
项目能否在其成员之外延续——巴士系数、响应能力、由谁支持，以及软件包的维护状况？
50
维护者韧性（巴士系数）
13危急
评分方式
| 9/54 | 巴士系数 — 1 位贡献者贡献了半数提交 |
| 0/22.5 | 提交分布 — 头号贡献者编写了 100% 的提交 |
| 1.4/13.5 | 贡献者广度 — 1 位贡献者 |
| 3/10 | OpenSSF Scorecard：Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
所用输入
| bus_factor | 1 |
| contributors_sampled | 1 |
| top_contributor_share | 1 |
议题与 PR 响应能力
57中等
评分方式
| 0/46.8 | 议题解决 — 没有议题或无数据 |
| 30.4/38.3 | PR 接受 — 已裁定的 PR 中 27/34 已合并 |
| 0/15 | OpenSSF Scorecard：Code-Review — Found 0/30 approved changesets -- score normalized to 0 |
所用输入
| merged_prs | 27 |
| open_issues | 0 |
| closed_issues | 0 |
| issue_closed_ratio | — |
| closed_unmerged_prs | 7 |
已排除计分（无数据或不适用）：议题解决。 其余权重已重新归一化。
所有权与托管责任
48存在风险
评分方式
| 30/30 | 所有权背书 — 组织持有 |
| 0/20 | 已验证域名 |
| 0/25 | 所有者影响力 — ThatCatDev 有 0 位关注者 |
| 18/25 | 既往记录 — 14 个公开仓库，账户约 4 年 |
所用输入
| followers | 0 |
| owner_type | Organization |
| is_verified | — |
| owner_login | ThatCatDev |
| public_repos | 14 |
| account_age_days | 1,715 |
软件包维护
100优秀
评分方式
| 25/25 | 已发布且可解析 — go 上有 1 个软件包 |
| 35/35 | 发布时效 — 最近一次发布于 18 天前 |
| 20/20 | 版本历史 — 61 个已发布版本 |
| 20/20 | 未被弃用 — 活跃，未被弃用或撤回 |
所用输入
| packages | github.com/ThatCatDev/tanrenai |
| ecosystems | go |
| any_deprecated | 否 |
| min_days_since_publish | 18 |
工程质量
基础的工程与文档实践是否到位？
70
工程实践
84良好
评分方式
| 24/24 | CI 工作流 — 4 个工作流 |
| 24/24 | 存在测试 |
| 16/16 | Linter 配置 — .golangci.yml |
| 0/9.6 | Pre-commit 钩子 |
| 0/6.4 | .editorconfig |
| 20/20 | OpenSSF Scorecard：CI-Tests — 27 out of 27 merged PRs checked by a CI test -- score normalized to 10 |
所用输入
| has_ci | 是 |
| has_tests | 是 |
| has_editorconfig | 否 |
| has_linter_config | 是 |
| has_precommit_config | 否 |
文档
50中等
评分方式
| 30/30 | README |
| 0/25 | 文档目录 |
| 0/15 | 文档 / 主页站点 |
| 10/10 | 仓库描述 |
| 0/10 | 主题标签 |
| 10/10 | Wiki |
所用输入
| topics | — |
| has_wiki | 是 |
| homepage | — |
| has_readme | 是 |
| has_docs_dir | 否 |
| has_description | 是 |
安全
可见的安全与供应链实践是否稳固，且不存在未解决的高风险司法辖区暴露？
36
安全态势
36存在风险
评分方式
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 2.5/2.5 | CI-Tests — 27 out of 27 merged PRs checked by a CI test -- score normalized to 10 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 0/30 approved changesets -- score normalized to 0 |
| 0.8/2.5 | Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 0/2.5 | 许可证 — license file not detected |
| 7.5/7.5 | Maintained — 16 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 5/5 | Packaging — packaging workflow detected |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 5/5 | SAST — SAST tool is run on all commits |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — Project has not signed or included provenance with any releases. |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 52 existing vulnerabilities detected |
所用输入
| source | openssf_scorecard |
| checks_evaluated | 18 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 0 |
| scorecard_aggregate | 3.6 |
AI 就绪度
该仓库在多大程度上具备与 AI 编码代理协同开发与维护的条件？这是一枚独立的实验性徽章——权重为 0.0，因此单独呈现，不影响总体健康评分。
86
AI 代理上下文与指引
85优秀
评分方式
| 45/45 | 代理指令 — CLAUDE.md |
| 0/15 | 机器可读文档（llms.txt） |
| 40/40 | 可读的提交历史 — 85 次人类提交中有 85 次说明了意图（结构化标题或解释性正文） |
所用输入
| has_llms_txt | 否 |
| legible_history_share | 1 |
| agent_instruction_files | CLAUDE.md |
| agent_instruction_max_bytes | 5,577 |
评分方式
| 18/18 | 一条命令的引导启动 — Makefile |
| 22/22 | 自动化测试 |
| 11/11 | Lint / 格式化配置 — .golangci.yml |
| 11/11 | 静态类型检查 — clients/vscode/tsconfig.json |
| 10/10 | 可复现环境 — Dockerfile, lockfile |
| 10/10 | 已体现的代理实践 — 最近 85 次提交中有 76 次由代理编写或署名代理 |
| 0/8 | 自动化维护 — 未观察到自动依赖更新 |
| 0/10 | OpenSSF Scorecard：Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
所用输入
| has_nix | 否 |
| has_tests | 是 |
| lockfiles | go.sum, package-lock.json |
| has_dockerfile | 是 |
| typed_language | 是 |
| bootstrap_files | Makefile |
| has_devcontainer | 否 |
| has_linter_config | 是 |
| typecheck_configs | clients/vscode/tsconfig.json |
| agent_commit_share | 0.894 |
| toolchain_manifests | clients/cli/go.mod, clients/desktop/go.mod, clients/shared/go.mod, infra/go.mod, server/go.mod |
| dependency_bot_commit_share | 0 |
面向模型的代码可读性
100优秀
评分方式
| 45/45 | 可类型检查的代码 — Go（静态类型） |
| 55/55 | 可控的文件大小 — 采样的 301 个源文件中有 0 个超过 60KB |
所用输入
| primary_language | Go |
| largest_source_bytes | 53,708 |
| source_files_sampled | 301 |
| oversized_source_files | 0 |
关键数据
1GitHub 星标
1贡献者
85最近 12 个月提交数
18距最近推送天数
63发布版本数
1巴士系数（bus factor）
0开放议题
Go软件包生态系统数
数据采集警告
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
更多细节
OpenSSF Scorecard 3.6 / 10
3.6综合
来自开源项目 OpenSSF Scorecard 的独立、工具无关的安全评估。每项检查奖励的是安全实践本身，而非特定供应商的工具。Scorecard 无法判定的检查项标记为 不适用，并从安全评分中剔除（绝不按零分计）。
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| 10 | CI-Tests | 27 out of 27 merged PRs checked by a CI test -- score normalized to 10 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 0/30 approved changesets -- score normalized to 0 |
| 3 | Contributors | project has 1 contributing companies or organizations -- score normalized to 3 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 0 | License | license file not detected |
| 10 | Maintained | 16 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 10 | Packaging | packaging workflow detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 10 | SAST | SAST tool is run on all commits |
| 0 | Security-Policy | security policy file not detected |
| 0 | Signed-Releases | Project has not signed or included provenance with any releases. |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 52 existing vulnerabilities detected |
直接依赖 6
| 注册表 | 软件包 | 版本约束 | 清单文件 |
|---|---|---|---|
| Go | github.com/charmbracelet/bubbletea | v1.3.10 | infra/go.mod |
| Go | github.com/spf13/cobra | v1.10.2 | infra/go.mod |
| Go | golang.org/x/crypto | v0.39.0 | infra/go.mod |
| Go | github.com/google/uuid | v1.6.0 | server/go.mod |
| Go | github.com/philippgille/chromem-go | v0.7.0 | server/go.mod |
| Go | github.com/spf13/cobra | v1.10.2 | server/go.mod |
全部依赖 未采集
本报告未能采集到解析后的依赖集合：GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
原始 JSON 报告 机器可读
{
"data": {
"repo": {
"topics": [],
"is_fork": false,
"size_kb": 43494,
"has_wiki": true,
"homepage": null,
"languages": {
"Go": 1310578,
"CSS": 42489,
"HTML": 7077,
"NSIS": 12390,
"Shell": 10970,
"Makefile": 4174,
"Dockerfile": 357,
"JavaScript": 3906,
"TypeScript": 319628
},
"pushed_at": "2026-07-09T18:20:20Z",
"created_at": "2026-02-21T00:36:38Z",
"owner_type": "Organization",
"updated_at": "2026-07-09T18:19:50Z",
"description": "Tanrenai — a self-evolving local LLM system",
"is_archived": false,
"is_disabled": false,
"license_spdx": null,
"default_branch": "main",
"license_spdx_raw": null,
"primary_language": "Go",
"significant_languages": [
"Go",
"TypeScript"
]
},
"owner": {
"blog": null,
"name": null,
"type": "Organization",
"login": "ThatCatDev",
"company": null,
"location": null,
"followers": 0,
"avatar_url": "https://avatars.githubusercontent.com/u/94362358?v=4",
"created_at": "2021-11-15T10:35:26Z",
"is_verified": null,
"public_repos": 14,
"account_age_days": 1715
},
"license": {
"state": "absent",
"spdx_id": null,
"raw_spdx": null,
"file_present": false,
"scorecard_found": false,
"profile_has_license": false
},
"activity": {
"releases": [
{
"tag": "vscode-v1.0.2",
"kind": "other",
"published_at": "2026-07-09T18:22:32Z"
},
{
"tag": "v1.33.4",
"kind": "patch",
"published_at": "2026-07-09T18:20:06Z"
},
{
"tag": "v1.33.3",
"kind": "patch",
"published_at": "2026-07-09T18:13:08Z"
},
{
"tag": "vscode-v1.0.1",
"kind": "other",
"published_at": "2026-06-25T13:15:02Z"
},
{
"tag": "v1.33.2",
"kind": "patch",
"published_at": "2026-06-25T13:12:53Z"
},
{
"tag": "vscode-v1.0.0",
"kind": "other",
"published_at": "2026-06-25T11:41:34Z"
},
{
"tag": "v1.33.1",
"kind": "patch",
"published_at": "2026-06-25T11:41:31Z"
},
{
"tag": "v1.33.0",
"kind": "minor",
"published_at": "2026-06-25T11:37:33Z"
},
{
"tag": "v1.32.0",
"kind": "minor",
"published_at": "2026-06-25T11:31:53Z"
},
{
"tag": "v1.31.0",
"kind": "minor",
"published_at": "2026-06-08T15:48:59Z"
},
{
"tag": "v1.30.0",
"kind": "minor",
"published_at": "2026-06-08T15:47:35Z"
},
{
"tag": "v1.29.0",
"kind": "minor",
"published_at": "2026-06-08T15:04:20Z"
},
{
"tag": "v1.28.0",
"kind": "minor",
"published_at": "2026-05-24T03:00:00Z"
},
{
"tag": "v1.27.0",
"kind": "minor",
"published_at": "2026-05-23T19:00:06Z"
},
{
"tag": "v1.26.0",
"kind": "minor",
"published_at": "2026-05-23T02:11:42Z"
},
{
"tag": "v1.25.0",
"kind": "minor",
"published_at": "2026-05-22T12:02:30Z"
},
{
"tag": "v1.24.1",
"kind": "patch",
"published_at": "2026-05-22T03:02:52Z"
},
{
"tag": "v1.24.0",
"kind": "minor",
"published_at": "2026-05-10T03:32:00Z"
},
{
"tag": "v1.23.1",
"kind": "patch",
"published_at": "2026-04-20T03:55:26Z"
},
{
"tag": "v1.23.0",
"kind": "minor",
"published_at": "2026-04-20T03:51:39Z"
},
{
"tag": "v1.22.2",
"kind": "patch",
"published_at": "2026-04-12T00:26:03Z"
},
{
"tag": "v1.22.1",
"kind": "patch",
"published_at": "2026-04-12T00:07:56Z"
},
{
"tag": "v1.22.0",
"kind": "minor",
"published_at": "2026-04-06T01:02:50Z"
},
{
"tag": "v1.21.0",
"kind": "minor",
"published_at": "2026-04-05T19:33:05Z"
},
{
"tag": "v1.20.0",
"kind": "minor",
"published_at": "2026-04-05T18:19:38Z"
},
{
"tag": "v1.19.0",
"kind": "minor",
"published_at": "2026-04-05T03:50:03Z"
},
{
"tag": "v1.18.0",
"kind": "minor",
"published_at": "2026-04-02T04:43:50Z"
},
{
"tag": "v1.17.0",
"kind": "minor",
"published_at": "2026-03-18T03:15:00Z"
},
{
"tag": "v1.16.0",
"kind": "minor",
"published_at": "2026-03-17T02:24:26Z"
},
{
"tag": "v1.15.0",
"kind": "minor",
"published_at": "2026-03-15T21:51:02Z"
},
{
"tag": "v1.14.0",
"kind": "minor",
"published_at": "2026-03-15T21:48:11Z"
},
{
"tag": "v1.13.4",
"kind": "patch",
"published_at": "2026-03-15T21:13:07Z"
},
{
"tag": "v1.13.3",
"kind": "patch",
"published_at": "2026-03-15T20:52:14Z"
},
{
"tag": "v1.13.2",
"kind": "patch",
"published_at": "2026-03-15T20:49:53Z"
},
{
"tag": "v1.13.1",
"kind": "patch",
"published_at": "2026-03-15T20:45:10Z"
},
{
"tag": "v1.13.0",
"kind": "minor",
"published_at": "2026-03-15T19:15:11Z"
},
{
"tag": "v1.12.2",
"kind": "patch",
"published_at": "2026-03-15T18:25:37Z"
},
{
"tag": "v1.12.1",
"kind": "patch",
"published_at": "2026-03-15T18:23:34Z"
},
{
"tag": "v1.12.0",
"kind": "minor",
"published_at": "2026-03-15T18:14:21Z"
},
{
"tag": "v1.11.1",
"kind": "patch",
"published_at": "2026-03-15T16:58:40Z"
},
{
"tag": "v1.11.0",
"kind": "minor",
"published_at": "2026-03-15T16:46:53Z"
},
{
"tag": "v1.10.0",
"kind": "minor",
"published_at": "2026-03-15T02:12:46Z"
},
{
"tag": "v1.9.0",
"kind": "minor",
"published_at": "2026-03-15T01:47:38Z"
},
{
"tag": "v1.8.0",
"kind": "minor",
"published_at": "2026-03-14T05:46:03Z"
},
{
"tag": "v1.7.8",
"kind": "patch",
"published_at": "2026-03-14T05:33:24Z"
},
{
"tag": "v1.7.7",
"kind": "patch",
"published_at": "2026-03-12T15:02:53Z"
},
{
"tag": "v1.7.6",
"kind": "patch",
"published_at": "2026-03-12T14:55:01Z"
},
{
"tag": "v1.7.5",
"kind": "patch",
"published_at": "2026-03-12T14:50:39Z"
},
{
"tag": "v1.7.4",
"kind": "patch",
"published_at": "2026-03-12T14:20:35Z"
},
{
"tag": "v1.7.3",
"kind": "patch",
"published_at": "2026-03-12T06:11:02Z"
},
{
"tag": "v1.7.2",
"kind": "patch",
"published_at": "2026-03-12T05:18:12Z"
},
{
"tag": "v1.7.1",
"kind": "patch",
"published_at": "2026-03-12T04:48:05Z"
},
{
"tag": "v1.7.0",
"kind": "minor",
"published_at": "2026-03-12T04:02:13Z"
},
{
"tag": "v1.5.0",
"kind": "minor",
"published_at": "2026-03-12T03:00:28Z"
},
{
"tag": "v1.4.0",
"kind": "minor",
"published_at": "2026-03-11T23:36:27Z"
},
{
"tag": "v1.3.3",
"kind": "patch",
"published_at": "2026-03-11T23:34:16Z"
},
{
"tag": "v1.3.2",
"kind": "patch",
"published_at": "2026-03-11T23:14:43Z"
},
{
"tag": "v1.3.1",
"kind": "patch",
"published_at": "2026-03-11T22:56:37Z"
},
{
"tag": "v1.3.0",
"kind": "minor",
"published_at": "2026-03-11T22:40:05Z"
},
{
"tag": "v1.2.0",
"kind": "minor",
"published_at": "2026-03-11T22:32:46Z"
},
{
"tag": "v1.1.0",
"kind": "minor",
"published_at": "2026-03-11T21:48:16Z"
},
{
"tag": "v1.0.1",
"kind": "patch",
"published_at": "2026-03-11T21:36:58Z"
},
{
"tag": "v1.0.0",
"kind": "major",
"published_at": "2026-03-11T21:29:11Z"
}
],
"recent_commits": [
{
"oid": "38c1bbeaaa9f58cf675829f247468436c3a6cec0",
"body": "…eady' + usage dump (#34)\n\nWhen agent-rpc failed during startup (dead credentials being the common\ncase) the extension showed the generic 'tanrenai agent-rpc exited (exit\ncode 1) before ready' plus a 400-char stderr tail dominated by cobra's\nusage dump — even though the CLI had already reported the \n[…]\nt strings the CLI emits.\n\nCompanion to the CLI-side fix (#33), which removes the refresh-token\nrotation race that caused most of these failures.\n\nCo-authored-by: Claude Fable 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(vscode): surface the CLI's real error instead of 'exited before r…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-07-09T18:19:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "d3d0eb94b83523e207030f012014e913e2688571",
"body": "…errors (#33)\n\nThe platform rotates the refresh token on every use, so concurrent CLI\nprocesses sharing credentials.json (a terminal session plus an\neditor-spawned agent-rpc, or two editor windows) raced to refresh: the\nloser presented an already-rotated token, got 400 'Invalid Refresh\nToken: Alread\n[…]\noot command: runtime failures are not usage\n errors, and the flag dump was burying the real message in the VS Code\n extension's error surface.\n\nCo-authored-by: Claude Fable 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(cli): serialize token refresh across processes + actionable auth …",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-07-09T18:12:42Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a6d59fe3e7d756e291803ebd61abe0811cab8866",
"body": "…ookup (#32)\n\nThree related fixes so the published VS Code extension works out of the box.\n\n**1. Installer picked the wrong \"latest\" release.** The repo publishes the CLI\non `v*` tags and the VS Code extension on a separate `vscode-v*` tag line.\nGitHub's /releases/latest returns the most recent rele\n[…]\nains only its own binary; resolveCliPath unit tests +\nfull extension suite (47) pass.\n\nCo-authored-by: James Trotter <james@MacBook-Pro-2.local>\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(vscode): bundle CLI per-platform + fix installer latest-release l…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-25T13:12:28Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "4391ddd796a187fd9fa9e93ec4506d756a6ae5a5",
"body": "* feat(vscode): add Marketplace icon, MIT license, set publisher\n\n- icon.png (256x256, from the website logo) + top-level \"icon\" field so\n the Marketplace listing has a real icon instead of a placeholder\n- LICENSE (MIT) + \"license\" field; clears vsce's missing-license warning\n- set \"publisher\" to t\n[…]\nt a branch push), so it's unaffected by the rule.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(vscode): unblock Marketplace release + add icon/license (#31)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-25T11:40:50Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "df80bbe1268a52c3846883f1f7257182fb38191b",
"body": "Publish the VS Code extension like the repo does — conventional commits,\nno manual version bumps — but on its OWN version line so it stays\ndecoupled from the repo's v1.x (the Marketplace requires monotonic semver\nper extension).\n\n- vscode-release.yml: on push to main, runs semantic-release scoped to\n[…]\nds\n for a proper Marketplace listing.\n\nRequires repo secrets: VSCE_PAT (Azure DevOps Marketplace token), and\noptionally OVSX_PAT for Open VSX.\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(vscode): automated publishing via scoped semantic-release (#29)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-25T11:37:05Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e229616db00d3cd77a7cb9787da3263370fe076d",
"body": "…tion (#30)\n\n* feat(clients): live context-usage + subagent-isolated mid-turn compaction\n\nFooter percentage now updates as tool results land mid-turn instead of\nfreezing at the pre-turn value, and the agent loop folds older history\ninto a summary as soon as it crosses the high-water mark — no more\n\"\n[…]\nAuthored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: James Trotter <james@Mac.localdomain>\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(clients): live context-usage + subagent-isolated mid-turn compac…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-25T11:31:30Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "bec604e6b807ee9c971d723348f6d26480694b0f",
"body": "…ystem (#28)\n\nThe page the browser lands on after `tanrenai login` was a bare,\nunstyled snippet. Replace it with a polished, self-contained page using\nthe web app's palette (#0e0f11 bg, #16171a card, #00b4a0 accent), Inter,\nand a centered card with a status badge — success (check) and error (x)\nvari\n[…]\nerror, missing token) now render the\nsame styled page instead of plain http.Error text. Messages are\nHTML-escaped; no external assets required.\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(cli): style the browser auth-callback page to match the design s…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-08T15:48:27Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e23c09918d67d815552e808fd2b0cbf759701cf2",
"body": "… (#27)\n\n* refactor(cli): move agent system prompt to an embedded file\n\nThe default agent system prompt was a long inline const in run.go, hard\nto find and awkward to iterate on. Move it to\nclients/cli/cmd/agent_system_prompt.md and load it via //go:embed, so the\nprompt is a plain editable file. Tri\n[…]\ne.\nHolistic edit to the existing working-directory concern, not a new rule.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(cli): embed agent prompt in a file + sharpen it for decisiveness…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-08T15:47:08Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "d0003efd00eb8514629ad6bec663790cdc8985ad",
"body": "…vscode) (#26)\n\n* feat(cli): activate command + readable plan-gate errors\n\nThe platform now gates GPU access behind a plan. Surface that in the CLI:\n\n- `tanrenai activate <code>` redeems a single-use invite code (POST\n /api/activate) and reports the granted plan.\n- platformGet/platformPost now rend\n[…]\nvered\nby the shared apiclient change in this PR.)\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(clients): plan-gate handling, activate cmd, hosted-model (CLI + …",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-06-08T15:03:53Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "331029ea060a9fe28ab169556d2799995d44a51f",
"body": "Adds a structured JSONL output mode to `tanrenai run --pipe`, opt-in via\n`--format json` (default `text` preserves the existing behavior exactly).\nProgrammatic consumers (IDE plugins, agent runners, CI scripts, the\nOpen Design daemon) can now drive tanrenai without parsing the\nhuman-friendly text fo\n[…]\n: `--format text` is the default and behaves identically\nto today — `---END---` framing, bracketed `[status]` on stderr, no JSON\non stdout. Existing scripts and the human TUI/repl flow are unaffected.",
"is_bot": false,
"headline": "feat(cli): add --format json to pipe mode for programmatic hosts (#25)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-24T02:59:38Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c8866ede05a2462b0847098b1615b1fec619acec",
"body": "…#24)\n\n* feat(mcp): wire external MCP servers into the agent's tool registry\n\nAdds an MCP client layer so tanrenai's agent can use tools exposed by\nany external MCP server — Playwright, filesystem-mcp, GitHub MCP,\ncustom in-house servers, etc. Config matches Claude Code's\nmcpServers schema so existi\n[…]\nL, malformed header).\n\nCo-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: James Trotter <james@Mac.localdomain>\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(mcp): wire external MCP servers into the agent's tool registry (…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-23T18:59:42Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "d3743edaf2f528369a2b5fe15c8aae262cd3b32e",
"body": "* feat(cli): add agent-rpc subcommand for editor extensions\n\nIntroduces the JSON-over-stdio protocol that lets external clients\n(e.g. the upcoming VS Code extension) drive the existing agent loop\nwithout re-implementing it in another language.\n\nWire format: NDJSON, init/ready handshake with a protoc\n[…]\n0ms.\n\nCo-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\nCo-authored-by: James Trotter <james@MacBook-Pro-2.local>",
"is_bot": false,
"headline": "feat: VS Code extension v1 (hybrid Go agent + TS UI) (#20)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-23T02:11:22Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "0abb7bc71c8ad4579b433b6a8ea95b35113e7938",
"body": "TUI status bar now appends \" 45 t/s\" next to the existing ctx counter\nduring streaming, and pipe mode emits a \"[gen: 192 tokens, 42.3 t/s]\"\nsummary line on stderr at the end of each turn. The rate refreshes on\nevery content/reasoning delta so users get live feedback on how the\nmodel is performing, \n[…]\nig)\n\nReset at iteration boundaries so back-to-back turns don't bleed\ninto each other.\n\nCo-authored-by: James Trotter <james@MacBook-Pro-2.local>\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(cli): show generation tokens-per-second (#23)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-22T12:02:05Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "0902d894547b35c5ca3dc38befcc3655b36cb439",
"body": "…rt (#22)\n\nb8277 errors with `missing tensor 'blk.40.ssm_conv1d.weight'` when loading\nQwen3.6-A3B-MTP GGUFs — llama.cpp didn't fully support hybrid MTP\narchitectures yet. b9274 (~1000 builds newer) recognizes the MTP head\nand enables speculative decoding via the model's own checkpoints, so the\nload \n[…]\nip at b9274. No code changes needed elsewhere; the\nbundled binary swap is sufficient.\n\nCo-authored-by: James Trotter <james@MacBook-Pro-2.local>\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(release): bump bundled llama-server b8277 → b9274 for MTP suppo…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-22T11:50:34Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "8e86228fe554a1a7235b7d106c0655780f45617b",
"body": "`tanrenai --local list` silently ignored --local and hit the configured\nremote URL. `tanrenai --local pull hf://.../<repo>-GGUF/<quant>` saved the\nfile under the source GGUF's filename instead of the bare name derived from\nthe repo, so a subsequent `tanrenai --local run <bare-name>` couldn't find\nwh\n[…]\nI pass-through, and the wire-level invariant\nthat the Name field reaches the backend.\n\nCo-authored-by: James Trotter <james@MacBook-Pro-2.local>\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(cli): --local list + on-disk basename matches user-typed name (#21)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-22T03:02:29Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1cd3869d6b4c1fe95247d4e5c76c2cbe6e45147e",
"body": "* feat(pull): plumb optional name through /api/pull (CLI + server + apiclient)\n\nAdds a `name` field to the PullRequest API type and wires it through every\nlayer that talks to /api/pull on the GPU:\n\n- `clients/shared/pkg/api`, `server/pkg/api`: PullRequest gains `Name string`\n- `clients/shared/apicli\n[…]\ntui_agent.go / tui_input.go / run.go: integration\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(cli): bare-name pull resolution + swarm progress panel (#19)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-05-10T03:31:38Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "d7494c0b238e624ff5f34abaff909897f8384e02",
"body": "The `success` step of @semantic-release/github tries to comment on\nevery issue/PR referenced in the release's commit messages. When any\nof those refs fails to resolve (as happened with #13 — closed PR that\nsemantic-release couldn't query for reasons still unclear), the entire\nrelease step errors out\n[…]\nComment\n- failComment\n- labels\n- releasedLabels\n\nNet effect: fewer moving parts during the release; builds fire\ncorrectly when a new version is cut.\n\nCo-authored-by: ThatCatDev <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(ci): disable semantic-release success/fail comments (#18)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-20T03:55:03Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "417350ecfd6ecf9f4b94a7df1b1aba07f54c2d10",
"body": "… remote-auto (#17)\n\n* feat: pre-built GPU Docker image, eliminate build-from-source on deploy\n\nAdd gpu/docker/Dockerfile that builds llama-server (CUDA, multi-arch)\nand tanrenai-gpu into a single image pushed to Docker Hub as\nthatcatdev/tanrenai-gpu. On vast.ai deploy, binaries are extracted from\nt\n[…]\n them. GPU CI now lives in the tanrenai-gpu repo.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: consolidated — platform extraction + GPU image + Supabase CLI +…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-20T02:56:37Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "7b04cab68df013b5d54bc449f8b38e5c94abb198",
"body": "…og errors (#12)\n\n- Suppress \"failed to load memory index\" warning on first run when the\n index file doesn't exist yet (os.IsNotExist check)\n- Add memory search + injection to simple chat mode (startChatTurn),\n which previously only worked in agent/swarm modes\n- Log memory search failures instead of silently swallowing errors in\n all three modes (simple, planned agent, swarm)\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: memory system — suppress false warning, enable in simple chat, l…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-12T00:25:32Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "64796645b7a187ca52881e85ccf0e127322db480",
"body": "The installer previously overwrote all files in the bin directory,\nincluding user-compiled shared libraries (CUDA/GPU .so/.dylib files).\nNow skips shared libraries that already exist to avoid breaking\nGPU acceleration setups.\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: preserve user-built GPU libraries during installer upgrades (#11)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-12T00:07:37Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "eeb0caf710e04d228ceed0c508e9bb7c0fc77fa2",
"body": "…limits (#10)\n\n* feat: improve swarm quality with architecture spec and smart recursion\n\nThree fixes for small model quality in swarm mode:\n\n1. Architecture spec phase: before planning tasks, the orchestrator\n generates a shared technical spec (framework, structure, conventions).\n Every worker g\n[…]\nupposed to\nset up package.json and config files).\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: improve swarm quality — architecture spec, smart recursion, no …",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-06T01:02:31Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e873e63fae7da13f9191cf9c1d79d3b1a8b2ab23",
"body": "Expose llama-server's MoE-specific flags through the full stack:\n\nGPU server flags:\n- --cpu-moe: keep all MoE expert weights on CPU (attention/router on GPU)\n- --n-cpu-moe N: keep first N layers' MoE experts on CPU\n- --no-kv-offload: keep KV cache on CPU to save VRAM for weights\n- --fit: auto-adjust\n[…]\nfload all 999 layers.\n\nClient CLI (--local mode): --cpu-moe, --no-kv-offload, --fit flags\npass through to the embedded GPU server.\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add MoE model optimization flags and auto-detection (#9)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-05T19:32:45Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "859acc8a3bcf173c4ef17a02fde089d1e0c3ce86",
"body": "* feat: add --swarm mode for recursive multi-agent orchestration\n\nAdd a new --swarm flag that coordinates multiple sub-agents with fresh\ncontexts. An orchestrator plans the task into file-level work units, then\nsequential workers each get an isolated context with only their specific\ntask description\n[…]\n are\nindented under their parent with tree lines.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: recursive multi-agent swarm mode (--swarm) (#8)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-05T18:19:20Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "76db6bba295ff4a99639d73b336343c58d8e317e",
"body": "…l (#7)\n\nAgent improvements:\n- Add \"no code in thinking\" rule to system prompt — prevents models from\n writing files inside <think> blocks instead of calling file_write\n- Remove default 16384 max_tokens cap — when --max-tokens is unset, don't\n send max_tokens in the API request, letting the model \n[…]\nh TypeScript scroll covering OOP, SOLID\n principles, design patterns, React component architecture, and\n frontend best practices\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: agent quality improvements, docs, and prebuilt TypeScript scrol…",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-05T03:49:38Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "9d279e0403b5b09166e5e04548b68aebe39e63b3",
"body": "* feat: show reasoning content + remove iteration limit + CI coverage check\n\n- Display LLM reasoning/thinking text in gray in the chat view instead\n of silently discarding it. Makes the agent's thought process visible\n between tool calls.\n- Change default --max-iterations from 200 to 0 (unlimited)\n[…]\n nothing-to-clean\n\nCLI cmd coverage: 6.9% → 13.5%\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: reasoning display, agent fixes, go-test-coverage CI (#3)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-04-02T04:43:26Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "632b0076603506a62c165b61f7b673d5bf0a1765",
"body": "Display matched scroll names in the TUI when procedural knowledge\nis injected into context, so users know which scrolls are being used.\n\nCo-authored-by: Claude Opus 4.5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: show UI feedback when scrolls are matched (#2)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-03-18T03:14:34Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "f6a970f5286c8d107e558f66d71805a62cc8b02b",
"body": "* feat: add scrolls for automatic procedural knowledge injection\n\nScrolls are markdown files with YAML frontmatter (name, description, tags)\nstored in .tanrenai/scrolls/ (project) or ~/.tanrenai/scrolls/ (global).\nThey are automatically matched against user input each turn via keyword/tag\nscoring an\n[…]\ny fails. The comment should always update on PRs.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add scrolls for automatic procedural knowledge injection (#1)",
"author_name": "James",
"author_login": "bludot",
"committed_at": "2026-03-17T02:24:01Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "457689f75215f9308f099a1325e43ae35cd92fb4",
"body": "Configurable via CLI flag, wired through to agent config.\nAgent already auto-continues on finish_reason=\"length\".\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add --max-tokens flag for controlling response length",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T21:50:44Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "c8b2e66693e27f65e9d477ee3f911ea341da7244",
"body": "4096 was too small for code generation — model output got cut off\nmid-response. 16384 gives plenty of room while still capping runaway\ngeneration.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: bump default max response tokens from 4096 to 16384",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T21:47:51Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "9ccec11a2f85b68e721e3d5f4f33d0983b3b0cbb",
"body": "…ry request\n\nThe runner stored the full filename (e.g. model-00001-of-00003.gguf) as\nthe model name, but clients send the base name (model). The mismatch\ncaused LoadModel to be called on every chat request, killing and\nrestarting llama-server each time.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: strip split GGUF suffix from model name to prevent reload on eve…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T21:12:45Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "079043b3540daf11e138b943f8a64f6b6498f111",
"body": "Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: symlink llama-server and shared libs to tanrenai bin dir on deploy",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T20:51:47Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "7c0a54319609e9a75aac90f64e67f1eec7221be1",
"body": "filepath.Walk does not follow symlinks to directories.\nUse filepath.EvalSymlinks to resolve the models dir first.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: resolve symlinks before walking models directory",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T20:49:29Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0f5d1547c6b3b3aeac5324f16915f01b50080f54",
"body": "Split files like model-00001-of-00003.gguf now show as one model\nwith combined size and first part's path for loading.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: group split GGUFs into single model entry in list",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T20:44:46Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "88f46bab5da54ebfb008edca5221f6b0e78a1ef6",
"body": "- Cloud deployment section (vast.ai + Headscale)\n- Docker backend images with auto-discovery\n- HuggingFace hf:// pull examples\n- Model size → VRAM/disk table\n- Infra CLI commands reference\n- Prefer persistent storage over tmpfs in deploy setup\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: add cloud deployment, infra CLI, and HF pull to README",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T19:43:54Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "333ea5d12b9e7fb9089af31e2aea5e77a573b673",
"body": "- DiskForModelSize: 2x model size + 50GB headroom, min 100GB, round to 50GB\n- --model-size flag now auto-sets --disk-gb (e.g. 120b → 200GB)\n- Deploy shows disk in search/create UI\n- storage-setup stage finds largest writable mount (shm, workspace, etc.)\n and symlinks models dir there\n- Fix GPU server restart: use Python to isolate signal handling\n- Add .gitignore for infra binary\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: auto-calculate disk from model size, storage setup on deploy",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T19:14:51Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a2818c920a3193a188641522338e0eb92de6b6fd",
"body": "Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: force fresh clone on deploy to ensure new GPU code",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T18:25:15Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "275085a4a431b2944d8e5c477b5369b614e894cf",
"body": "Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: kill old GPU server on redeploy, clear Go build cache",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T18:23:12Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "47b09694b2320b3784d16bddd56e3672608b1db5",
"body": "…ixes\n\n- Add hf:// model references (hf://owner/repo/quant) to pull command\n - Resolves repo files via HuggingFace API\n - Supports split GGUFs (multi-part downloads with per-file progress)\n - Auto-picks Q4_K_M quant when none specified\n - Lists available quants on mismatch\n- Add tanrenai-infra n\n[…]\nrver from Headscale nodes\n - Auto-generate auth key from Headscale API\n- Always rebuild tanrenai-gpu on deploy (pull latest code)\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: HuggingFace GGUF pull support, network CLI, Docker entrypoint f…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T18:13:59Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "5c5a47699a3fca58f207ef93c09f3a7de5380af6",
"body": "…r Blackwell\n\n- Use net.JoinHostPort instead of fmt.Sprintf for IPv6 compatibility\n- Auto-upgrade CUDA toolkit when GPU arch requires newer nvcc\n- Install modern cmake, make all setup stages idempotent\n- Clear cmake build cache on re-runs\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: IPv6 vet error, idempotent setup stages, CUDA toolkit upgrade fo…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T16:58:16Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0750a41af3e5fcaffd11d35087bde7f47efdb722",
"body": "- New infra/ module with CLI for deploying GPU servers to vast.ai\n - Interactive TUI for instance selection and offer browsing\n - Headscale/Tailscale/none network tunnel support\n - SSH-based remote setup (llama.cpp, tanrenai-gpu, model pull)\n - Spinners for all long-running operations, verbose m\n[…]\nst/vet\n- Makefile updated with build-infra, test, clean targets\n- CLAUDE.md updated with infra module docs and deployment workflow\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add infra module for vast.ai GPU deployment and Docker images",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T16:46:24Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3847be11698abd4fee5536bba08058852348fb45",
"body": "…inary\n\nAllow running GPU server, backend server, or both from the single\ntanrenai binary instead of requiring separate builds. Expands\npkg/serve.Config structs with missing fields (chat template, reasoning\nformat, VastAI, idle timeout) so the unified binary has full parity\nwith the standalone binaries.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add gpu serve, server serve, and serve subcommands to unified b…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T02:12:23Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "5c30453bdd36af0d66f68f323e0812b9b0080688",
"body": "…gement\n\n- Add plan-execute agent with sub-agents: decomposes complex requests into\n steps, runs each as an isolated sub-agent with fresh context, then\n synthesizes results. Auto-detects when planning is needed based on input\n complexity. Falls back to direct mode for simple requests.\n- Add slash\n[…]\nsses.\n- Parse reasoning_content for plan generation (thinking models).\n- Remove artificial token caps on planning/synthesis calls.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: plan-execute agent architecture, autocomplete, and process mana…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-15T01:47:14Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f7ede972bf990dcc226aef6647d3ca2307c9c358",
"body": "- Replace single-line InputField with multiline TextArea (3 rows)\n- Enter submits, Shift+Enter inserts a newline\n- Enable bracket paste mode so pasted multiline text is handled correctly\n- Detect NVIDIA GPU on Linux and warn if llama-server lacks CUDA support\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: multiline input support and CUDA detection warning",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-14T05:43:38Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "ed3b0202de9b97d5c994b9f9155beae5ff89e3ff",
"body": "- Copy .so files alongside llama-server in Linux release builds (fixes\n exit code 127 due to missing libllama/libggml shared libraries)\n- Fail CI if llama-server binary is missing from the bundle\n- Document Linux CUDA build instructions for GPU users\n- Add Development Setup section with prerequisites and build steps\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: bundle shared libraries with llama-server and add dev setup docs",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-14T05:32:58Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "faeb45443d298f484bc8b491206654a72b1d84f1",
"body": "…llback\n\nRemove the family registry that auto-detected Qwen model architectures\nand instead prefer GGUF embedded templates, then HuggingFace sidecar,\nthen a generic ChatML fallback. This makes template resolution\nmodel-agnostic and prioritizes model-specific templates from upstream.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "refactor: replace Qwen-specific template logic with generic ChatML fa…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-14T04:05:56Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "47f0577c9cff335a326fbe49288cace29c05c244",
"body": "macOS uses DYLD_LIBRARY_PATH, not LD_LIBRARY_PATH. This fixes\n\"Library not loaded: @rpath/libmtmd.0.dylib\" errors when running\nllama-server with bundled shared libraries.\n\nCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: use DYLD_LIBRARY_PATH on macOS for shared library lookup",
"author_name": "James Trotter",
"author_login": "bludot",
"committed_at": "2026-03-12T15:02:25Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "2001889537ad40c00363f32fbd1c94f284f26165",
"body": "GNU tar --wildcards works on Ubuntu CI, but the approach of extracting\nthe full tarball and then copying dylibs is more reliable and easier\nto debug.\n\nCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: extract full tarball then copy dylibs (avoid --wildcards)",
"author_name": "James Trotter",
"author_login": "bludot",
"committed_at": "2026-03-12T14:54:33Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d8e95e76438130daa0ec858983655f8bfd70e7f2",
"body": "The tarball has files under llama-{V}/ directory, so the wildcard\npattern needs to match 'llama-*/*.dylib' not just '*.dylib'.\n\nCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: correct dylib extraction pattern for llama.cpp tarball",
"author_name": "James Trotter",
"author_login": "bludot",
"committed_at": "2026-03-12T14:50:18Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d7694aa75fcab979bee633a9a6e9a5e1e36c2ef9",
"body": "macOS llama-server requires libggml, libllama, and libmtmd dylibs at runtime.\nPreviously only the executable was extracted from llama.cpp releases, causing\n\"dyld: Library not loaded\" errors. Now extracts all .dylib files alongside\nllama-server for both CLI and desktop macOS builds.\n\nCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: bundle shared libraries (.dylib) for macOS llama-server",
"author_name": "James Trotter",
"author_login": "bludot",
"committed_at": "2026-03-12T14:19:31Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "348b388f7a33b3d363b00cab8cf61f57dd21145e",
"body": "- Add ReasoningContent field to MessageDelta across all three API type files\n so thinking model deltas aren't silently dropped by JSON deserialization\n- Detect reasoning-only responses and nudge the model to produce visible content\n- Skip GGUF-embedded chat templates instead of overriding with gene\n[…]\nnking model compatibility\n- Generate synthetic tool_call IDs when backends omit them\n- Add agent tests for tool message formation and streaming\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: support thinking models in agent loop (reasoning_content handling)",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-12T06:10:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "4b486d191dbb3633f2346f24f2dfa69899fe740c",
"body": "The template resolver skipped the chat_template already present in GGUF\nmetadata, jumping straight to a HuggingFace fetch when the family\nregistry didn't match. Now uses the model's own template directly,\nwhich fixes tool-calling for models whose architecture isn't in the\nhardcoded registry.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: use GGUF-embedded chat template before falling back to HuggingFace",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-12T05:17:49Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "8a71a2dd06aac6046b68314d122b3fe5190a5349",
"body": "Windows lacks Linux's Pdeathsig, so llama-server would survive if\ntanrenai exited or crashed. Now assigns the subprocess to a Windows\nJob Object with KILL_ON_JOB_CLOSE — the OS auto-terminates all\nchild processes when the parent's handles are closed.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: kill orphaned llama-server on Windows using Job Objects",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-12T04:47:39Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a55f53516b694ee3d082c6af4bd7fd88a4a32f07",
"body": "Replace old box-drawing animation with ASCII art hammer+anvil matching\nthe logo. Hammer moves with cubic ease-in/ease-out motion, colored\nper-character (orange hammer, red handle, steel anvil), with spark\neffects on impact. Fix QueueUpdateDraw deadlock that blocked TUI startup.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: colored ASCII art loading animation with eased hammer strike",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-12T04:01:52Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "7becf9f183bf75e2d6b3e2130a5bcdec915b25d4",
"body": "Shows an animated hammer striking an anvil (鍛錬 = forging) in the\nchat view while the model and servers are loading. Orange hammer,\nsteel-gray anvil, yellow sparks on impact.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: anvil forging animation during startup loading",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-12T03:04:00Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a9de090caffaacdf620d0352a0bc0871252f62a9",
"body": "- Read-only tools (file_read, list_dir, etc.) can be blanket-approved\n- File-writing tools can be approved per-path or blanket\n- Shell commands can only be approved by command prefix (e.g. \"git *\"),\n never blanket-approved, for safety\n- Permission rules support exact match, prefix wildcards (cmd *), and\n path wildcards (dir/*)\n- Add permission tests for matching logic\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: granular tool permissions based on risk level",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-12T03:00:06Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d5b177d82180dccd5477300f9c088cb2b372a9bf",
"body": "- Add installers/install.sh: one-line curl installer that auto-detects\n OS/arch, downloads latest release, and installs to ~/.local/bin\n- Add build-deb CI job: builds .deb package from Linux CLI release\n- Update README with install instructions for Linux, macOS, and Windows\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add Linux/macOS install script and .deb packaging",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T23:36:01Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "77e5a3efaa20293f5a37bbf950eef1d66cdb75af",
"body": "- Convert Go-level tool execution errors to ErrorResult instead of\n returning early, so the LLM always sees the error and can respond\n- Extract processToolCalls/checkStuck helpers in CLI agent (matching\n shared agent) to eliminate duplicated inline logic\n- Blocked tools no longer count toward stuck detection\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: agent no longer stops when a tool fails",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T23:33:45Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "2aacb18b91c2ed64cf49614eecf6bde2f3a6477c",
"body": "Uses cmd /C on Windows and sh -c on other platforms.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: make shell_exec cross-platform for Windows, macOS, and Linux",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T23:14:03Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a14da56b4ffcff05a2b6b949c635aedb5b2603e4",
"body": "… build\n\n- CLI installer: install NSIS with choco, run makensis directly instead\n of using joncloud/makensis-action (which expects NSIS pre-installed)\n- Desktop Windows: add mingw-w64-ucrt-x86_64-gobject-introspection to\n msys2 packages (fixes pkg-config missing gobject-introspection-1.0)\n- Desktop installer: same choco + direct makensis approach\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: install NSIS via choco and add gobject-introspection for desktop…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T22:56:10Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "39d6dae69355320221b9cfd8e546565a1bc51a9a",
"body": "- NSIS installer scripts for both CLI and Desktop with icon, PATH setup,\n Start Menu shortcuts (desktop), and Add/Remove Programs entries\n- EnvVarUpdate.nsh for reliable user PATH manipulation\n- Generated logo.ico from logo.png (256/128/64/48/32/16px)\n- Release workflow builds .exe installers along\n[…]\n artifact and packages\n on windows-latest; Desktop installer runs in existing windows job\n- Update README with installer download instructions\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add Windows NSIS installers for CLI and Desktop",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T22:39:40Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f980cef21425028fc4b275af6baca8102e614b84",
"body": "- Show colored inline unified diffs in TUI when patch_file/file_write edit\n files (green added, red removed, blue hunk headers with background tints)\n- Add tool approval system: Allow / Always Allow / Block modal with keyboard\n navigation. Permissions saved to .tanrenai/permissions.json (project-l\n[…]\nefile with build/install/test/clean targets (installs to ~/.local/bin)\n- Update README with tool permissions docs and make install instructions\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: colored diffs, tool permissions, Pdeathsig, and Makefile installer",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T22:32:23Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a1c0f3dbf7b8e5c664dfad1b0f9a1edf576a62be",
"body": "Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: add logo to README",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T21:52:23Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "80e57730371402a5e3730ba256602256e04af3c6",
"body": "Download pre-built llama-server from llama.cpp releases during CI and\ninclude it in the bin/ subdirectory of each release archive. Windows\nbuilds include CUDA 12.4 support with bundled cudart DLLs.\n\nUpdate resolveBinary to check bin/ next to the executable in addition\nto the data directory, so bundled llama-server is found automatically.\nSet LD_LIBRARY_PATH/PATH to include the binary directory for CUDA\nshared library resolution.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: bundle llama-server with release builds",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T21:47:51Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "33a6a78b55b3d47a26b1c703a8eba982ea4f7d4a",
"body": "Add Flush() method to responseWriter in both GPU and backend server\nlogging middleware so http.Flusher interface is preserved through the\nmiddleware chain. This fixes \"streaming not supported\" errors on\n/api/pull and other SSE endpoints.\n\nAlso fix desktop CI/release builds:\n- Add libgirepository1.0-dev for Linux GTK4 builds\n- Add gobject-introspection for macOS Homebrew builds\n- Remove deprecated macos-13 runner (only arm64 via macos-14)\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: streaming middleware and CI/CD desktop build failures",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T21:36:30Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "8365431d50c7c3caa25719e9f93ea006bec82d9d",
"body": "Add GitHub Actions release workflow using semantic-release to automate\nversioning from conventional commits. Builds CLI (linux/darwin/windows\namd64+arm64) and desktop GTK4 app (linux, macOS Intel+ARM, Windows\nwith bundled DLLs via MSYS2). Also adds desktop to CI pipeline,\nlocal server embedding for CLI, desktop session/settings, and removes\ndeprecated server-old directory.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add semantic release with cross-platform CI/CD builds",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-11T21:28:30Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "c9d20920a7c5d6e8dad1778d7167de5c7c09929e",
"body": "The GPU server now reads the model's native context length from GGUF\nmetadata during load and returns it in the /api/load response. The\nbackend proxies this through to the CLI, which uses it for context\nwindowing. The --ctx-size flag defaults to 0 (auto-detect) and acts\nas an explicit override when set.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: auto-detect context size from GGUF model metadata",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-07T04:48:28Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "9f697fdf8e47c86e827494da289c43dfd841e0d3",
"body": "- Add request body size limits (MaxBytesReader) to all GPU and server handlers\n- Add HTTP client timeouts with separate streaming/non-streaming clients\n- Fix VastAI race condition in EnsureRunning with double-check locking\n- Fix context propagation in embeddings handler\n- Fix memory Add to use *Entr\n[…]\nwith apiclient.PullModel\n- Add CI workflow (.github/workflows/ci.yml)\n- Add 59 new tests across memory, handlers, apiclient, and tools packages\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "refactor: production hardening across all three services",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-07T04:02:57Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a220d3d7a3ec600942fc5e222d4fa30765ec5ae5",
"body": null,
"is_bot": false,
"headline": "feat: slash commands",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-07T03:08:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a908f5329252a8d18b5b6735e7298b1de8001af5",
"body": "Move apiclient, tools, and pkg/api from clients/cli into clients/shared/\nso both the CLI and the new desktop client can depend on them. Add\nclients/desktop/ (Gio-based GUI), gpu/pkg/serve, and server/pkg/serve\nhelper packages.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "refactor: extract shared packages for multi-client reuse",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-06T00:55:21Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a174043a382fbf9dff09cd18cbf01dde35032346",
"body": "The escapeJinja helper was double-escaping quotes that were already\nproperly escaped in backtick strings (\\\" → \\\\\"), causing llama-server's\nJinja lexer to reject the template.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: remove double-escaping in generated Jinja templates",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-01T03:05:36Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "4a0487f683b70f6a6b76adc2089c58505eff8461",
"body": "Replace hardcoded Jinja template constants with a generator that produces\ntemplates programmatically from a ChatMLConfig struct. At model load time,\nthe server reads GGUF metadata (architecture + name), matches it against a\nfamily registry, and generates the appropriate template automatically.\n\n- Ad\n[…]\nth HF repo provenance at download time\n- Add --no-auto-template flag to disable auto-detection\n- Remove static qwen25/qwen35 template constants\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: generate chat templates at runtime from GGUF metadata",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-03-01T03:01:14Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "0af99dd170245ff56fae89d9dbc876bc49fd43a2",
"body": "…gress\n\nAdd --reasoning-format flag for thinking mode support (e.g. deepseek for\nQwen3.5) and expose --flash-attn as a CLI flag on the GPU server.\n\nStream model download progress as SSE events through all three tiers\n(GPU → backend → client) so the CLI shows a live progress bar during\nmodel pulls.\n\nAlso moves client/ to clients/cli/ and updates .gitignore for binaries.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add --reasoning-format, --flash-attn flags and SSE download pro…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-28T23:02:53Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "6c6588e1e70dfdcaa76bb09a9bab873e8ac121b0",
"body": null,
"is_bot": false,
"headline": "fix: underline issue",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-28T22:29:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "94dce704fae28cacbe9115869628699c29279bb1",
"body": null,
"is_bot": false,
"headline": "fix: small fixes",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-28T15:12:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "eaa24ca0418a457181ede07e19184d4ddb7fa7cb",
"body": null,
"is_bot": false,
"headline": "feat: new TUI",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-28T02:23:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "736ff659f3187b213046534aed53b36a3a7d2288",
"body": null,
"is_bot": false,
"headline": "feat: tui bubbletea",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-28T01:55:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b0f016f32fcfe6b35449ef49aba2dd2840a27542",
"body": null,
"is_bot": false,
"headline": "feat: split and TUI",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-28T00:58:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b93c67e59f7cb557c95147154336d82cb7227ec6",
"body": "Add patch_file tool for surgical find-and-replace edits to prevent the\nLLM from destroying files with file_write. Update file_write description\nto warn about full-file overwrites and direct users to patch_file.\n\nFix web_search by switching from DuckDuckGo HTML (CAPTCHA-blocked) to\nDDG Lite POST endp\n[…]\n00, 0 = unlimited) instead of hardcoded 20.\n\nUpdate system prompt with rules to prefer patch_file for edits and\nverify changes with build/test.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add patch_file tool, fix web_search, make iterations configurable",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-24T00:40:40Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f7f6c26aa2baf1ac14a65975dc7002e599c09497",
"body": "Consolidate shared subprocess logic into a new Subprocess helper used by\nboth ProcessRunner and EmbeddingRunner. This adds graceful shutdown\n(SIGTERM with 5s fallback to SIGKILL), dynamic port allocation to avoid\nconflicts, crash detection with auto-restart (max 3 attempts), structured\nlog prefixing, health check progress feedback, and an optimized HTTP\nclient transport for loopback communication.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: harden llama-server process management",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-23T03:55:02Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "2e15ee65314f21c01ab014285abcc166d44b8d79",
"body": null,
"is_bot": false,
"headline": "fix: imports",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-22T15:59:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d628a9a86be0ada607d2d08b980f356307bee1f2",
"body": null,
"is_bot": false,
"headline": "feat: less tokens, faster response",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-22T15:57:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1461f9d95614c13bb1a840b7f38698673fe6fdd9",
"body": "Qwen3-70B doesn't exist. Replaced with Llama-3.3-70B-Instruct Q4_K_M\n(~42GB, fits A100 80GB). Fixed embedding model URL to use leliuga repo.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "Fix model download URLs in server_setup.sh",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-22T02:20:27Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "65e86041f1e5edfe172918995c4a1bcdbfe4de09",
"body": "…p.sh\n\nThe models/ gitignore rule was matching server/internal/models/ (the Go\npackage for model store/download). Changed to /models/ so it only matches\nthe top-level data directory. Also rewrote server_setup.sh to use a direct\nGo install instead of Homebrew.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "Fix gitignore excluding internal/models package, clean up server_setu…",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-22T02:17:24Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "e78109b359d3bfb6aa32656a6033a40794465c1d",
"body": "- Agent framework with streaming support, tool execution, and stuck detection\n- Context manager with token budgeting, windowed history, and auto-summarization\n- Built-in tools: file_read, file_write, list_dir (with depth), shell_exec\n- Memory/RAG via chromem-go: hybrid search (semantic + keyword), p\n[…]\n\n- Server-side agent handler (POST /v1/agent/completions)\n- REPL commands: /memory, /context, /tokens, /clear\n- CLAUDE.md project documentation\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "Phase 2-4: Agent loop, context management, tools, and memory/RAG",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-22T01:15:55Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "8bbc118384a2fa2ed5b2f843ba133a2f48bdac6f",
"body": "Tanrenai server with OpenAI-compatible API that manages llama-server\nas a subprocess for GGUF model inference. Includes CLI commands for\nserve, run, chat, list, and pull.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "Phase 1: Model serving via llama-server subprocess",
"author_name": "ThatCatDev",
"author_login": "bludot",
"committed_at": "2026-02-21T00:36:53Z",
"body_truncated": false,
"is_coding_agent": true
}
],
"releases_count": 63,
"commits_last_year": 85,
"latest_release_at": "2026-07-09T18:22:32Z",
"latest_release_tag": "vscode-v1.0.2",
"releases_from_tags": false,
"days_since_last_push": 18,
"active_weeks_last_year": 13,
"days_since_latest_release": 18,
"mean_days_between_releases": 3.5
},
"community": {
"has_readme": true,
"has_license": false,
"has_description": true,
"has_contributing": false,
"health_percentage": 37,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "github.com/ThatCatDev/tanrenai",
"exists": true,
"license": null,
"keywords": [],
"ecosystem": "go",
"matches_repo": true,
"registry_url": "https://pkg.go.dev/github.com/ThatCatDev/tanrenai",
"is_deprecated": false,
"latest_version": "v1.33.4",
"repository_url": "https://github.com/ThatCatDev/tanrenai",
"versions_count": 61,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": null,
"first_published_at": null,
"latest_published_at": "2026-07-09T18:19:35Z",
"latest_version_yanked": null,
"days_since_latest_publish": 18
}
]
},
"popularity": {
"forks": 0,
"stars": 1,
"watchers": 0,
"fork_history": {
"days": [],
"complete": true,
"collected": 0,
"total_forks": 0
},
"star_history": null,
"open_issues_and_prs": 0
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": true,
"has_mcp_signal": false,
"bootstrap_files": [
"Makefile"
],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"clients/vscode/tsconfig.json"
],
"toolchain_manifests": [
"clients/cli/go.mod",
"clients/desktop/go.mod",
"clients/shared/go.mod",
"infra/go.mod",
"server/go.mod"
],
"largest_source_bytes": 53708,
"source_files_sampled": 301,
"oversized_source_files": 0,
"agent_instruction_files": [
"CLAUDE.md"
],
"agent_instruction_max_bytes": 5577
},
"dependencies": {
"manifests": [
"infra/go.mod",
"server/go.mod"
],
"advisories": {
"error": null,
"scope": null,
"source": null,
"findings": [],
"collected": false,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 0,
"malicious_count": 0,
"assessed_package": null,
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"go"
],
"dependencies": [
{
"name": "github.com/charmbracelet/bubbletea",
"manifest": "infra/go.mod",
"ecosystem": "go",
"version_constraint": "v1.3.10"
},
{
"name": "github.com/spf13/cobra",
"manifest": "infra/go.mod",
"ecosystem": "go",
"version_constraint": "v1.10.2"
},
{
"name": "golang.org/x/crypto",
"manifest": "infra/go.mod",
"ecosystem": "go",
"version_constraint": "v0.39.0"
},
{
"name": "github.com/google/uuid",
"manifest": "server/go.mod",
"ecosystem": "go",
"version_constraint": "v1.6.0"
},
{
"name": "github.com/philippgille/chromem-go",
"manifest": "server/go.mod",
"ecosystem": "go",
"version_constraint": "v0.7.0"
},
{
"name": "github.com/spf13/cobra",
"manifest": "server/go.mod",
"ecosystem": "go",
"version_constraint": "v1.10.2"
}
],
"all_dependencies": {
"error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"source": null,
"packages": [],
"collected": false,
"truncated": false,
"total_count": null,
"direct_count": null,
"indirect_count": null
}
},
"maintainership": {
"issues": {
"open_prs": 0,
"merged_prs": 27,
"open_issues": 0,
"closed_ratio": null,
"closed_issues": 0,
"closed_unmerged_prs": 7
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "bludot",
"commits": 85,
"avatar_url": "https://avatars.githubusercontent.com/u/2181540?v=4"
}
],
"contributors_sampled": 1,
"top_contributor_share": 1
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"ci.yml",
"docker.yml",
"release.yml",
"vscode-release.yml"
],
"has_docs_dir": false,
"linter_configs": [
".golangci.yml"
],
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"go.sum",
"package-lock.json"
],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 10,
"reason": "27 out of 27 merged PRs checked by a CI test -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 0,
"reason": "Found 0/30 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 0,
"reason": "license file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "16 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": 10,
"reason": "packaging workflow detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 10,
"reason": "SAST tool is run on all commits",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": 0,
"reason": "Project has not signed or included provenance with any releases.",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": 0,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "52 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "38c1bbeaaa9f58cf675829f247468436c3a6cec0",
"ran_at": "2026-07-28T03:04:47Z",
"aggregate_score": 3.6,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-09T18:45:37Z",
"oldest_open_prs": [],
"last_merged_pr_at": "2026-07-09T18:19:35Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/ThatCatDev/tanrenai",
"host": "github.com",
"name": "tanrenai",
"owner": "ThatCatDev"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"security": 36,
"vitality": 75,
"community": 12,
"governance": 50,
"engineering": 70
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "good",
"name": "Vitality",
"value": 75,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "moderate",
"name": "Development activity",
"note": null,
"notes": [],
"value": 65,
"inputs": {
"commits_last_year": 85,
"human_commit_share": 1,
"days_since_last_push": 18,
"active_weeks_last_year": 13
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 18 days ago",
"points": 28.8,
"status": "partial",
"details": [
{
"code": "push_recency",
"params": {
"days": 18
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "13/52 weeks with commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 13
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "85 commits in the last year",
"points": 17.4,
"status": "partial",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 85
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "16 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "excellent",
"name": "Release discipline",
"note": null,
"notes": [],
"value": 90,
"inputs": {
"releases_count": 63,
"latest_release_tag": "vscode-v1.0.2",
"releases_from_tags": false,
"days_since_latest_release": 18,
"mean_days_between_releases": 3.5
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "63 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 63
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 18 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 18
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~3.5 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 3.5
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "Project has not signed or included provenance with any releases.",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "unverified",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": "repository_too_young",
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": null,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "maintenance record not established from the collected data",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_unverified",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "critical",
"name": "Community & Adoption",
"value": 12,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "critical",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 1,
"inputs": {
"forks": 0,
"stars": 1,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "1 stars",
"points": 0,
"status": "missed",
"details": [
{
"code": "stars",
"params": {
"count": 1
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "0 forks",
"points": 0,
"status": "missed",
"details": [
{
"code": "forks",
"params": {
"count": 0
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "0 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 0
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "critical",
"name": "Community health",
"note": null,
"notes": [],
"value": 25,
"inputs": {
"has_readme": true,
"has_license": false,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "no license file detected",
"points": 0,
"status": "missed",
"details": [
{
"code": "license_absent",
"params": {}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "moderate",
"name": "Sustainability & Governance",
"value": 50,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 13,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 1,
"top_contributor_share": 1
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 100% of commits",
"points": 0,
"status": "missed",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 100
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "1 contributors",
"points": 1.4,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 1
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "moderate",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Issue resolution. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"issue_resolution"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 57,
"inputs": {
"merged_prs": 27,
"open_issues": 0,
"closed_issues": 0,
"issue_closed_ratio": null,
"closed_unmerged_prs": 7
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "no issues or no data",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_issues_or_data",
"params": {}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "27/34 decided PRs merged",
"points": 30.4,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 27,
"decided": 34
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "at_risk",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 48,
"inputs": {
"followers": 0,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "ThatCatDev",
"public_repos": 14,
"account_age_days": 1715
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "organization-owned",
"points": 30,
"status": "met",
"details": [
{
"code": "owner_organization",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "0 followers of ThatCatDev",
"points": 0,
"status": "missed",
"details": [
{
"code": "owner_followers",
"params": {
"count": 0,
"login": "ThatCatDev"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "14 public repos, account ~4 yr old",
"points": 18,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 14
}
},
{
"code": "account_age_years",
"params": {
"years": 4
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"github.com/ThatCatDev/tanrenai"
],
"ecosystems": "go",
"any_deprecated": false,
"min_days_since_publish": 18
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on go",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "go"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 18 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 18
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "61 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 61
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "good",
"name": "Engineering Quality",
"value": 70,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 84,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "4 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 4
}
}
],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": ".golangci.yml",
"points": 16,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": ".golangci.yml"
}
}
],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "27 out of 27 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "moderate",
"name": "Documentation",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"topics": [],
"has_wiki": true,
"homepage": null,
"has_readme": true,
"has_docs_dir": false,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "at_risk",
"name": "Security",
"value": 36,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "at_risk",
"name": "Security posture",
"note": null,
"notes": [],
"value": 36,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 18,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 0,
"scorecard_aggregate": 3.6
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "27 out of 27 merged PRs checked by a CI test -- score normalized to 10",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 0/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "16 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow detected",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is run on all commits",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "Project has not signed or included provenance with any releases.",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "detected GitHub workflow tokens with excessive permissions",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "52 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "excellent",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"review_only_matches": 0,
"assessed_self_published_locations": 2
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "excellent",
"name": "AI Readiness",
"value": 86,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "excellent",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 85,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 1,
"agent_instruction_files": [
"CLAUDE.md"
],
"agent_instruction_max_bytes": 5577
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "CLAUDE.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "CLAUDE.md"
}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "85 of 85 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 85,
"sampled": 85
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "good",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 82,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"go.sum",
"package-lock.json"
],
"has_dockerfile": true,
"typed_language": true,
"bootstrap_files": [
"Makefile"
],
"has_devcontainer": false,
"has_linter_config": true,
"typecheck_configs": [
"clients/vscode/tsconfig.json"
],
"agent_commit_share": 0.894,
"toolchain_manifests": [
"clients/cli/go.mod",
"clients/desktop/go.mod",
"clients/shared/go.mod",
"infra/go.mod",
"server/go.mod"
],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": "Makefile",
"points": 18,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Makefile"
}
}
],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": ".golangci.yml",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": ".golangci.yml"
}
}
],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "clients/vscode/tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "clients/vscode/tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "Dockerfile, lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Dockerfile, lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "76 of the last 85 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 76,
"sampled": 85
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "excellent",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"primary_language": "Go",
"largest_source_bytes": 53708,
"source_files_sampled": 301,
"oversized_source_files": 0
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Go (statically typed)",
"points": 45,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "Go"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "0/301 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 301,
"oversized": 0
}
}
],
"max_points": 55
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
"GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
],
"report_type": "repository",
"generated_at": "2026-07-28T03:05:04.415681Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/t/ThatCatDev/tanrenai.svg",
"full_name": "ThatCatDev/tanrenai",
"license_state": "absent",
"license_spdx": null
}