公开记录良好
软件健康报告模式 0.30.0 · 指标 2.3.1 · 2026-08-03 04:51 UTC
OpenRouterTeam / typescript-agent
OpenRouter Agent SDK
OpenRouterTeam/typescript-agent 的健康指数为 100 分中的 73 分，处于「良好」区间。 其得分最高的类别是Vitality（85/100），最低的是Community & Adoption（44/100）。 最近一次更新在 2 天前。 近期的大部分工作由 1 位贡献者完成。
73
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，再依据公开记录的分布进行校准，使各等级具有百分位含义；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 34（存在风险）的上限。
73
卓越93-100公开记录中的最高层级（约前 5%）；基本满足所有检验标准
优秀80-92各方面均表现强劲；仅有少量不足
良好65-79健康；不足之处有限且可控
中等50-64可接受，但存在明显不足；建议进行审查
薄弱35-49多个领域存在实质性薄弱环节
存在风险20-34存在重大薄弱环节；采用时应保持审慎
危急1-19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。
加权总体分 64 经校准后在公布的指数量表上为 73（记录校准 2026-08-02）。
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 | 标签 |
|---|---|---|---|---|---|---|
| npm | @openrouter/mcp | 0.0.1 | 133 | 1 | 9 天前 | openroutermcpmodel-context-protocolagenttypescriptaitoolsllm |
| npm | @openrouter/agent | 0.8.0 | 382,454 | 13 | 11 天前 | openrouteragenttypescriptaitoolsstreamingllm |
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？
85
开发活跃度
75良好
评分方式
| 36/36 | 推送新近度 — 最近一次推送于 2 天前 |
| 11.1/36 | 提交节奏 — 52 周中有 16 周有提交 |
| 18/18 | 提交量 — 最近一年 152 次提交 |
| 10/10 | OpenSSF Scorecard：Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
所用输入
| commits_last_year | 152 |
| human_commit_share | 0.94 |
| days_since_last_push | 2 |
| active_weeks_last_year | 16 |
发布纪律
100卓越
评分方式
| 27/27 | 有发布版本 — 已发布 7 个发布版本 |
| 36/36 | 发布时效 — 最近一次发布版本于 11 天前 |
| 27/27 | 发布节奏 — 约每 13 天发布一次 |
| 0/10 | OpenSSF Scorecard：Signed-Releases — 无数据 |
所用输入
| releases_count | 7 |
| latest_release_tag | @openrouter/agent@0.8.0 |
| releases_from_tags | 否 |
| days_since_latest_release | 11 |
| mean_days_between_releases | 13 |
已排除计分（无数据或不适用）：OpenSSF Scorecard：Signed-Releases。 其余权重已重新归一化。
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？
44
流行度与采用
29存在风险
评分方式
| 20.4/60 | 星标 — 19 个星标 |
| 8.3/25 | 复刻 — 11 个复刻 |
| 0/15 | 关注者 — 0 位关注者 |
所用输入
| forks | 11 |
| stars | 19 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
社区健康
25存在风险
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 |
| readme_badges | 0 |
| has_contributing | 否 |
| has_issue_template | 否 |
| has_code_of_conduct | 否 |
| readme_badge_services | — |
| has_pull_request_template | 否 |
生态采用（下载量）
93卓越
评分方式
| 74.4/80 | 月度下载量 — npm 合计每月 382,587 次下载 |
| 0/20 | 注册表被依赖数 — 该生态系统不报告此项 |
所用输入
| packages | @openrouter/mcp, @openrouter/agent |
| dependents | — |
| ecosystems | npm |
| total_downloads | — |
| monthly_downloads | 382,587 |
已排除计分（无数据或不适用）：注册表被依赖数。 其余权重已重新归一化。
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？
60
维护者韧性（巴士系数）
37薄弱
评分方式
| 9/54 | 巴士系数 — 1 位贡献者贡献了半数提交 |
| 5.8/22.5 | 提交分布 — 头号贡献者编写了 74% 的提交 |
| 12.2/13.5 | 贡献者广度 — 9 位贡献者 |
| 10/10 | OpenSSF Scorecard：Contributors — project has 5 contributing companies or organizations |
所用输入
| bus_factor | 1 |
| contributors_sampled | 9 |
| top_contributor_share | 0.743 |
议题与 PR 响应能力
43薄弱
评分方式
| 6/42 | 议题解决 — 14% 的议题已关闭 |
| 23.8/30 | PR 接受 — 已裁定的 PR 中 58/73 已合并 |
| 7.5/13 | Newcomer PR acceptance — 30 天内首次贡献者的 PR 已合并 15/26 |
| 6/15 | OpenSSF Scorecard：Code-Review — Found 8/18 approved changesets -- score normalized to 4 |
所用输入
| merged_prs | 58 |
| open_issues | 6 |
| closed_issues | 1 |
| prs_merged_7d | 3 |
| prs_decided_7d | 3 |
| prs_merged_30d | 17 |
| prs_decided_30d | 29 |
| issue_closed_ratio | 0.143 |
| closed_unmerged_prs | 15 |
| first_time_authors_30d | 3 |
| first_time_prs_merged_30d | 15 |
| first_time_prs_decided_30d | 26 |
所有权与托管责任
72良好
评分方式
| 30/30 | 所有权背书 — 组织持有 |
| 0/20 | 已验证域名 |
| 25/25 | 所有者影响力 — OpenRouterTeam 有 3,536 位关注者 |
| 17.5/25 | 既往记录 — 36 个公开仓库，账户约 3 年 |
所用输入
| followers | 3,536 |
| owner_type | Organization |
| is_verified | — |
| owner_login | OpenRouterTeam |
| public_repos | 36 |
| account_age_days | 1,117 |
软件包维护
100卓越
评分方式
| 25/25 | 已发布且可解析 — npm 上有 2 个软件包 |
| 35/35 | 发布时效 — 最近一次发布于 9 天前 |
| 20/20 | 版本历史 — 13 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 | @openrouter/mcp, @openrouter/agent |
| ecosystems | npm |
| any_deprecated | 否 |
| min_days_since_publish | 9 |
工程质量
基础的工程与文档实践是否到位？
75
工程实践
82优秀
评分方式
| 24/24 | CI 工作流 — 3 个工作流 |
| 24/24 | 存在测试 |
| 16/16 | Linter 配置 — biome.json |
| 0/9.6 | Pre-commit 钩子 |
| 0/6.4 | .editorconfig |
| 18/20 | OpenSSF Scorecard：CI-Tests — 18 out of 19 merged PRs checked by a CI test -- score normalized to 9 |
所用输入
| has_ci | 是 |
| has_tests | 是 |
| has_editorconfig | 否 |
| has_linter_config | 是 |
| has_precommit_config | 否 |
文档
65良好
评分方式
| 30/30 | README |
| 0/25 | 文档目录 |
| 15/15 | 文档 / 主页站点 — https://openrouter.ai/docs/sdks/typescript/call-model |
| 10/10 | 仓库描述 |
| 0/10 | 主题标签 |
| 10/10 | Wiki |
所用输入
| topics | — |
| has_wiki | 是 |
| homepage | https://openrouter.ai/docs/sdks/typescript/call-model |
| 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？
50
安全态势
38薄弱
评分方式
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 2.2/7.5 | Branch-Protection — branch protection is not maximal on development and all release branches |
| 2.2/2.5 | CI-Tests — 18 out of 19 merged PRs checked by a CI test -- score normalized to 9 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 3/7.5 | Code-Review — Found 8/18 approved changesets -- score normalized to 4 |
| 2.5/2.5 | Contributors — project has 5 contributing companies or organizations |
| 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 — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 0/5 | Packaging — 无数据 |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — 无数据 |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 16 existing vulnerabilities detected |
所用输入
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 3.8 |
已排除计分（无数据或不适用）：packaging, signed_releases。 其余权重已重新归一化。
依赖安全公告
100卓越
评分方式
| 35/35 | 直接依赖不含已知公告 — 没有直接依赖携带已知公告 |
| 25/25 | 间接依赖不含已知公告 — 没有间接依赖携带已知公告 |
| 0/40 | 没有长期未处理的公告 — 没有公告带有发布日期 |
所用输入
| source | osv |
| advisories | 0 |
| affected_packages | 0 |
| assessed_packages | 95 |
| unassessed_packages | 0 |
| affected_by_severity | none |
| direct_affected_packages | 0 |
已排除计分（无数据或不适用）：没有长期未处理的公告。 其余权重已重新归一化。 比对的是 npm:@openrouter/mcp@0.0.1 的运行时依赖闭包——安装已发布的软件包时真正被拉取进来的内容——共 95 个软件包。 未对可达性进行分析。
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？权重刻意设小（4%）：代理工具链是一项真实的维护信号，但完全不具备的仓库仍可达到 100/100。
55
AI 代理上下文与指引
40薄弱
评分方式
| 0/45 | 代理指令 — 没有 CLAUDE.md / AGENTS.md / 编辑器规则 |
| 0/15 | 机器可读文档（llms.txt） |
| 40/40 | 可读的提交历史 — 94 次人类提交中有 89 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 | 0.947 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
评分方式
| 0/18 | 一条命令的引导启动 |
| 22/22 | 自动化测试 |
| 11/11 | Lint / 格式化配置 — biome.json |
| 11/11 | 静态类型检查 — packages/agent/tsconfig.json, packages/mcp/tsconfig.json |
| 10/10 | 可复现环境 — lockfile |
| 10/10 | 已体现的代理实践 — 最近 100 次提交中有 12 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 | pnpm-lock.yaml |
| has_dockerfile | 否 |
| typed_language | 是 |
| bootstrap_files | — |
| has_devcontainer | 否 |
| has_linter_config | 是 |
| typecheck_configs | packages/agent/tsconfig.json, packages/mcp/tsconfig.json |
| agent_commit_share | 0.12 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
面向模型的代码可读性
99卓越
评分方式
| 45/45 | 可类型检查的代码 — TypeScript（静态类型） |
| 54.1/55 | 可控的文件大小 — 采样的 120 个源文件中有 2 个超过 60KB |
所用输入
| primary_language | TypeScript |
| largest_source_bytes | 181,323 |
| source_files_sampled | 120 |
| oversized_source_files | 2 |
机器可读接口
20存在风险
评分方式
| 0/40 | API 模式（OpenAPI/GraphQL/proto） |
| 20/20 | MCP 服务器 |
| 0/40 | 可运行示例 |
所用输入
| example_dirs | — |
| has_mcp_signal | 是 |
| api_schema_files | — |
关键数据
19GitHub 星标
9贡献者
152最近 12 个月提交数
2距最近推送天数
7发布版本数
1巴士系数（bus factor）
6开放议题
npm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
Star 与 Fork 历史 0 ★ / 11 ⇿
0Star
11Fork
7发布
每颗 star 和每个 fork 的添加时间，来自 GitHub 并按天汇总。累计增长位于其构成来源——每日新增——的正上方，二者可相互对照：稳定的自然增长与短暂的突增形态截然不同。当这一差别可被衡量时，它会作为增长真实性予以报告。
主版本 0次版本 0修订 1
OpenSSF Scorecard 3.8 / 10
3.8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 |
| 3 | Branch-Protection | branch protection is not maximal on development and all release branches |
| 9 | CI-Tests | 18 out of 19 merged PRs checked by a CI test -- score normalized to 9 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 4 | Code-Review | Found 8/18 approved changesets -- score normalized to 4 |
| 10 | Contributors | project has 5 contributing companies or organizations |
| 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 | 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 不适用 | Packaging | packaging workflow not detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| 不适用 | Signed-Releases | no releases found |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 16 existing vulnerabilities detected |
直接依赖 5
| 注册表 | 软件包 | 版本约束 | 清单文件 |
|---|---|---|---|
| npm | @openrouter/sdk | ^0.13.7 | packages/agent/package.json |
| npm | zod | ^4.0.0 | packages/agent/package.json |
| npm | @modelcontextprotocol/sdk | ^1.29.0 | packages/mcp/package.json |
| npm | @openrouter/agent | workspace:* | packages/mcp/package.json |
| npm | zod | ^4.0.0 | packages/mcp/package.json |
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
依赖安全公告 0
安装 npm:@openrouter/mcp@0.0.1 会引入 95 个包（直接与传递）：其中 0 个存在已知公告，0 个为直接依赖。
没有已知公告影响已评估的依赖。
公告表示依赖图中记录的版本落入某条公告的受影响范围。可达性未经分析，且依赖图包含开发与测试的版本固定——某项发现可能只涉及工具链而非交付的软件。
原始 JSON 报告 机器可读
{
"data": {
"repo": {
"topics": [],
"is_fork": false,
"size_kb": 1889,
"has_wiki": true,
"homepage": "https://openrouter.ai/docs/sdks/typescript/call-model",
"languages": {
"TypeScript": 1376001
},
"pushed_at": "2026-07-31T21:54:32Z",
"created_at": "2026-03-27T18:10:53Z",
"owner_type": "Organization",
"updated_at": "2026-07-30T16:01:38Z",
"description": "OpenRouter Agent SDK",
"is_archived": false,
"is_disabled": false,
"license_spdx": null,
"default_branch": "main",
"license_spdx_raw": null,
"primary_language": "TypeScript",
"significant_languages": [
"TypeScript"
]
},
"owner": {
"blog": "https://openrouter.ai",
"name": "OpenRouter",
"type": "Organization",
"login": "OpenRouterTeam",
"company": null,
"location": null,
"followers": 3536,
"avatar_url": "https://avatars.githubusercontent.com/u/139423088?v=4",
"created_at": "2023-07-13T03:37:47Z",
"is_verified": null,
"public_repos": 36,
"account_age_days": 1117
},
"license": {
"state": "absent",
"spdx_id": null,
"raw_spdx": null,
"file_present": false,
"scorecard_found": false,
"profile_has_license": false
},
"activity": {
"releases": [
{
"tag": "@openrouter/agent@0.8.0",
"kind": "other",
"published_at": "2026-07-22T20:50:38Z"
},
{
"tag": "@openrouter/agent@0.7.2",
"kind": "other",
"published_at": "2026-06-17T13:50:00Z"
},
{
"tag": "@openrouter/agent@0.7.1",
"kind": "other",
"published_at": "2026-06-03T17:10:40Z"
},
{
"tag": "0.7.1",
"kind": "patch",
"published_at": "2026-06-03T14:41:39Z"
},
{
"tag": "@openrouter/agent@0.7.0",
"kind": "other",
"published_at": "2026-05-18T21:45:22Z"
},
{
"tag": "@openrouter/agent@0.6.0",
"kind": "other",
"published_at": "2026-05-14T15:59:51Z"
},
{
"tag": "@openrouter/agent@0.5.0",
"kind": "other",
"published_at": "2026-05-06T00:53:03Z"
}
],
"recent_commits": [
{
"oid": "d03060256c4c7d55432e508544d8d35d2f65d4bb",
"body": "* ci(release): dispatch the Python and Go ports on publish (HOP C)\n\nThe Python and Go ports of @openrouter/agent track this repo as their reference\nspec, but nothing told them when a version shipped. Both were generated by hand\nagainst 0.7.2 and have sat a minor version behind since — missing HooksM\n[…]\nf the port\n repos cannot resolve, making them fail on checkout instead of degrading.\n\n---------\n\nCo-authored-by: Claude Fable 5 <noreply@anthropic.com>\nCo-authored-by: LukasParke <luke@openrouter.ai>",
"is_bot": false,
"headline": "ci(release): dispatch the Python and Go ports on publish (HOP C) (#84)",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-30T15:58:38Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "78c562ef53da0edd84dfbcc6d6ee38a095d72b37",
"body": "* feat(agent): doom-loop detection for the tool-execution loop\n\nOpt-in via doomLoop on callModel. Deterministic detection of runs that\nstop making progress: consecutive identical tool calls (per-tool\nfingerprint streaks over tool-declared loopKey identity, incl. repeated\nempty and invalid-JSON calls\n[…]\n--------\n\nCo-authored-by: cortex-github-agent[bot] <305999463+cortex-github-agent[bot]@users.noreply.github.com>\nCo-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>",
"is_bot": false,
"headline": "feat(agent): doom-loop detection for the tool-execution loop (#73)",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-29T17:42:53Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "89ae3ff3f5a6b929337ed347b388937bc80339ac",
"body": "…flow (#82)\n\n* fix(release): use real npm trusted publishing (OIDC) for publish workflow\n\nThe release workflow claimed to use OIDC but never did. changesets/action\nonly checks `process.env.NPM_TOKEN`, and the workflow passed the secret as\n`NODE_AUTH_TOKEN`, so the action logged \"No NPM_TOKEN found, \n[…]\nhat is the primary release path.\n\nSame doc-drift class flagged in review; no behavior change.\n\nCo-Authored-By: Claude <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(release): use real npm trusted publishing (OIDC) for publish work…",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-28T20:26:11Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "fc8a7f7298ed3f9fdbb3009fbfbd1d05ec5a0264",
"body": "…t npm publish (DEV-684) (#80)\n\n* fix(release): mark @openrouter/mcp private until its first npm publish\n\nThe push-to-main publish leg fails on every release because changeset\npublish retries @openrouter/mcp, whose first-ever publish 404s — trusted\npublishing (OIDC) cannot create a brand-new package\n[…]\nrusted publisher\nconfig still has to happen npm-side before the publish leg can pick it up.\n\nCo-authored-by: Cursor <cursoragent@cursor.com>\n\n---------\n\nCo-authored-by: Cursor <cursoragent@cursor.com>",
"is_bot": false,
"headline": "fix(release): reset unpublished @openrouter/mcp to 0.0.1 for its firs…",
"author_name": "Dennis Jeong",
"author_login": "w0nche0l",
"committed_at": "2026-07-22T21:41:37Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "680bceb4598f228d3e2ec58e2416e4335cdff059",
"body": "Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>",
"is_bot": true,
"headline": "chore: version packages (#57)",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-22T20:49:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "61a2a9ab312f973b599bad886e97a270f798565f",
"body": "* docs: update README banner to rebrand design system\n\nGenerated from the openrouter-web monorepo banner template\n(scripts/repo-banners/ — see its AGENTS.md for the process).\nInk background, Volt accent, Gordita/Plus Jakarta Sans type, and the\ncanonical brand lockup, per the rebrand DESIGN.md.\n\n* docs: restore README trailing newline",
"is_bot": false,
"headline": "docs: rebrand README banner (#71)",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-21T21:37:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6807c51d56a35e07a2c549d92ab6d8a0c106ac0a",
"body": "…e: true (DEV-658) (#68)\n\n* fix(agent): append default final-answer directive for bare allowFinalResponse: true\n\nBare `allowFinalResponse: true` stripped tools on the forced final turn\nbut gave the model no signal that this was its last turn. Models that\nemit tool-call syntax as text (e.g. GLM) woul\n[…]\nl turn.\n\nChangeset bumped to minor: runs that previously ended on a halted\ntool-call turn now make one additional request by default.\n\n* docs(skill): update example for default-on final turn semantics",
"is_bot": false,
"headline": "fix(agent): default final-answer directive for bare allowFinalRespons…",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-21T19:20:10Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "620a5c8e42fece2b795a60526a4f9dd229c12f11",
"body": "* testing actions\n\n* testing actions 2\n\n* testing force node24\n\n* testing force node24 2\n\n* force node24 final note: The warning about using node20 will still be present. However, node24 will be used with the environment variable set\n\n* removed comment from readme\n\n* decided against forcing node24, \n[…]\n chore(ci): bump remaining v4 actions to v6 (structural-gate, bump-openrouter-sdk); restore README trailing newline\n\n---------\n\nCo-authored-by: Luke Parke <5702154+LukasParke@users.noreply.github.com>",
"is_bot": false,
"headline": "Fix/force node24 (#36)",
"author_name": "Logan Lyons",
"author_login": "okacodes",
"committed_at": "2026-07-21T15:23:13Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e499be1c336b05238cf7479826675c74dc17a0fc",
"body": "* testing actions\n\n* testing actions 2\n\n* testing force node24\n\n* testing force node24 2\n\n* force node24 final note: The warning about using node20 will still be present. However, node24 will be used with the environment variable set\n\n* implemented vitest coverage and update vitest to most up to dat\n[…]\ntted coverage artifacts, gitignore coverage/, package-relative coverage glob, align coverage-v8 pin, regen lockfile\n\n---------\n\nCo-authored-by: Luke Parke <5702154+LukasParke@users.noreply.github.com>",
"is_bot": false,
"headline": "Feat/vitest upgrade (#37)",
"author_name": "Logan Lyons",
"author_login": "okacodes",
"committed_at": "2026-07-21T15:22:49Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "cb83f45209ff66f8c58077f4e0a85d35f884afdb",
"body": "…#67)\n\n* feat: add HooksManager lifecycle hook system to callModel (rebased onto main)\n\nSquashed rebase of feat/hooks-manager (fe319a2) onto origin/main (8edae63).\nConflicts resolved:\n- async-params/call-model: keep both allowFinalResponse and hooks options\n- model-result: runToolWithHooks now propa\n[…]\n.ts priming the\nmanager with run B's id and asserting run A's tool hooks still see\nrun A's state id.\n\n---------\n\nCo-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>",
"is_bot": false,
"headline": "feat(hooks): PostModelCall telemetry hook + SessionEnd usage totals (…",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-17T15:58:23Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c83cceb17ec1d66b9a1fd2d46ac8ac9b6e60fa4c",
"body": "* feat(agent): versioned ConversationState serialization contract (PR-6)\n\n* fix: address review — restore createInitialState JSDoc placement, validate createdAt/updatedAt in deserializer\n\n* style: fix biome formatting\n\nCo-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.githu\n[…]\nn' alongside id/createdAt/updatedAt\n- new test: reshaped version-2 blob still gets the version error\n\n---------\n\nCo-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>",
"is_bot": false,
"headline": "feat(agent): versioned ConversationState serialization contract (#66)",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-17T15:55:37Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "09a041ea717b384c6c85d7c81ef391b170b0dd8f",
"body": "* fix(agent): infer tool context types from contextSchema (PR-3)\n\ntool() now preserves the concrete contextSchema type through its\noverloads: execute's ctx.local is typed from the schema, and\ncallModel's context map slots accept/reject the real per-tool shape.\nNo more 'ctx.local as X' or 'context: m\n[…]\ne behavior change (one sanctioned construction-\ntime write cast for the readonly field).\n\n315 tests green; type gates verified red/green.\n\n* refactor: remove no-op WithConcreteContextSchema per review",
"is_bot": false,
"headline": "fix(agent): infer tool context types from contextSchema (#65)",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-17T15:55:25Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "80ff8a730292aa00a3acfcce6ab1e9f5a6a7f0de",
"body": "* feat: add HooksManager lifecycle hook system to callModel (rebased onto main)\n\nSquashed rebase of feat/hooks-manager (fe319a2) onto origin/main (8edae63).\nConflicts resolved:\n- async-params/call-model: keep both allowFinalResponse and hooks options\n- model-result: runToolWithHooks now propagates e\n[…]\nsult-hooks.test.ts priming the\nmanager with run B's id and asserting run A's tool hooks still see\nrun A's state id.\n\n---------\n\nCo-authored-by: Luke Parke <5702154+LukasParke@users.noreply.github.com>",
"is_bot": false,
"headline": "feat: add HooksManager lifecycle hook system to callModel (#7)",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-07-17T15:22:49Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e4d06e38215d6eafbd5c198e3485f476e65d26f0",
"body": "…tools (#64)\n\n* feat(agent): persist unresolved manual tool calls as awaiting_client_tools\n\nManual tools (execute: false) stopped the loop without persisting\nanything; getPendingToolCalls() returned [] and cold-start consumers\ncould not see the calls in serialized state. Persist unresolved manual\nca\n[…]\nPR #63 hardened the no-tool exit to reject empty final outputs\n(validateFinalResponse), which this test's mock tripped after rebase.\nA real resumed response carries assistant content; fixture updated.",
"is_bot": false,
"headline": "feat(agent): persist unresolved manual tool calls as awaiting_client_…",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-15T17:20:20Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d96cd9fc589c27978bcdc2fd1921f754be88e3f0",
"body": "… (#63)\n\n* fix(agent): tolerate empty final response after completed tool rounds\n\nMini-class models intermittently return an empty final turn when the\ntool call was the answer; the SDK threw away successful runs. Now:\nretry the follow-up once; if still empty, resolve with empty text.\nstrictFinalResp\n[…]\n\npassed validateFinalResponse but was never executed — silently dropped.\nThe retry now strips those fields (mirroring makeFinalResponseRequest)\nto coerce a text turn, with a test pinning the behavior.",
"is_bot": false,
"headline": "fix(agent): tolerate empty final response after completed tool rounds…",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-15T16:37:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c020bc7c86d2f743ecf9158ca3c9ff7b315e43b3",
"body": "…(#61)\n\nA resumed ConversationState with a bare-string input pushed the raw\nstring into the request input array; OpenResponses rejects that with a\n400. Use normalizeInputToArray in the history+fresh branch, matching\nthe no-history branch. Found battletesting a production agent.\n\n- 3-line fix in ModelResult.initStream history branch\n- regression test: resume-string-input.test.ts (fails without fix)",
"is_bot": false,
"headline": "fix(agent): normalize string input when resuming with loaded history …",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-15T16:36:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1362232975f0254343f9842f30ec1b35d391f4fe",
"body": "…semantics (#62)",
"is_bot": false,
"headline": "docs(agent): fix README/API drift — ctx.local, StateAccessor, stream …",
"author_name": "Luke Parke",
"author_login": "LukasParke",
"committed_at": "2026-07-15T16:36:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8edae63f4f6fe89e146f3abbf6d24dab7a164681",
"body": "… sending broken history (#59)\n\nWhen a round mixes auto-executed tools with manual (execute-less) client\ntools, executeToolRound returns no output for the manual calls, yet the\nloop still made a follow-up request whose input carried the manual\nfunction_call with no matching function_call_output. Pro\n[…]\n loop and surface the response when any tool call in the round\nhas no output — mirroring the existing all-manual hasExecutableToolCalls\nguard — so the caller can execute its manual calls and continue.",
"is_bot": false,
"headline": "fix(agent): stop tool loop on unresolved manual tool calls instead of…",
"author_name": "ayush-or",
"author_login": "ayush-or",
"committed_at": "2026-07-08T17:00:04Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "4e1f98d74902c845a0be5a7e161be832cce3d25f",
"body": "…ckage\n\nfeat(mcp): add @openrouter/mcp package",
"is_bot": false,
"headline": "Merge pull request #56 from OpenRouterTeam/worktree-openrouter-mcp-pa…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-30T17:59:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d3539eea1056e629cd6930d1682f0496d7e98820",
"body": "Tighten the fallback test to pin Date.now() substitution (before <= cachedAt <=\nnow) rather than mere non-negativity, catching a regression to a hard-coded\nsentinel.",
"is_bot": false,
"headline": "test(mcp): assert negative-cachedAt fallback uses a fresh timestamp",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-30T15:05:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "209499abacd6783ee5c98155bb2a676e3932c3f4",
"body": "…'t untype client tools\n\nAdds a `source: 'client' | 'mcp'` discriminant to ToolExecutionResult and the\nstreaming ToolResultEvent. An MCP tool's `unknown` output no longer collapses the\nwhole result union — narrowing on source keeps client-tool results precise and\nisolates MCP results as unknown.\n\n- \n[…]\n.\n\nVerified: full monorepo build/typecheck/lint/test green (295 agent + 39 mcp tests,\nincl. type-level tests); sentrux structural gate passes (cycles 1->1, quality up,\nno complex-function regression).",
"is_bot": false,
"headline": "feat(agent,mcp): discriminate tool results by source so MCP tools don…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-30T15:03:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "38bf22d2b7d3a0c12e7bce70465ed68602500e5a",
"body": "isFiniteEpoch's value>=0 tightening means serializeServer now substitutes\nDate.now() for a negative cachedAt; assert that branch produces a valid,\nnon-negative epoch that passes the read validator.",
"is_bot": false,
"headline": "test(mcp): cover serializeServer's negative-cachedAt write-side fallback",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T18:28:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1eb518475b25823a609327344daf21e0d43c6e99",
"body": "An epoch (ms) is non-negative by definition; rejecting negatives validates\nthe invariant at the snapshot boundary instead of relying on downstream\nmaxAge arithmetic to fail-safe on a clock-skewed/garbage value.",
"is_bot": false,
"headline": "fix(mcp): reject negative cachedAt in isFiniteEpoch",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T17:57:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c638f43c486244028d2ec57c9556ba60ba3ef726",
"body": "…ializer\n\nExtract the 'valid cachedAt' predicate into a single exported isFiniteEpoch\nin cache-types.ts, consumed by both the read-side isSerializedMCPServer\nvalidator and the write-side serializer, so the two can't drift if the rule\nis later tightened. No behavior change.",
"is_bot": false,
"headline": "refactor(mcp): share isFiniteEpoch between snapshot validator and ser…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T17:45:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "43ed315256dd5e8ab6177fddd77dddb5ddefea06",
"body": "A poisoned snapshot with NaN/Infinity cachedAt passed isSerializedMCPServer\n(typeof NaN === 'number'), making tryCacheHit's staleness comparison always\nfalse so the entry never expired. Mirror serialize.ts's isExpiry guard with a\nNumber.isFinite check. Also document that includeTools/excludeTools apply to\ndiscovered MCP tools only; resource tools are gated by the resources option.",
"is_bot": false,
"headline": "fix(mcp): reject non-finite cachedAt in snapshot validator",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T17:31:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "37e420566e5692563f430c6ed596649924a6f2ef",
"body": "Extract the buildTools-args and serializeServer-input assembly out of\nmakeHandle into buildToolsArgs/serializeArgs helpers, dropping makeHandle\nfrom cc=17 to under the gate's threshold of 15. No behavior change.",
"is_bot": false,
"headline": "fix(mcp): drop makeHandle below max cyclomatic complexity",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T16:41:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "60a0ae76fc8053076c383bc291dbd49161c3f98a",
"body": "The sentrux structural gate failed on cycle + quality + complexity\nregressions. Resolved without weakening the baseline:\n\n- extract makeHandle/freshConnect/listToolDefs into a leaf handle.ts so\n create-mcp-tools and rehydrate no longer form a cycle\n- move MCPTransportKind to a leaf transport-types.\n[…]\nd into)\n- collapse tryCacheHit's option forwarding into a data-driven helper to\n drop it back under the max-cyclomatic-complexity threshold\n\nGate now: cycles 1->1, quality 0.51->0.52, no degradation.",
"is_bot": false,
"headline": "fix(mcp): pass structural-gate by eliminating import-cycle regressions",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T16:37:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a94f9c4c25357cd63afb66d81b192186033b08c7",
"body": "… thread clientInfo\n\nAddresses remaining Perry review threads:\n- freshConnect tears down the connection if listToolDefs or the initial\n writeCache throws, so a failed setup never leaks the open transport\n- the tools/list_changed auto-refresh now .catch()es, so a failed refresh\n cannot escape as an unhandled rejection; listeners keep the last good set\n- thread clientInfo through the cache-hit/rehydrate path so a warm handle\n initializes with the same client identity as a cold one",
"is_bot": false,
"headline": "fix(mcp): close connection on setup failure, guard refresh rejection,…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T16:15:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c2a376c4db2084a4f5991c2cbcc23eb8524b92e6",
"body": "…pagination\n\n- freshConnect breaks the recursive cache-fallback loop (no-auth/expired\n snapshots no longer re-read their own cache and re-enter rehydrate)\n- reconstruct MCPAuth from a credential-bearing snapshot so reconnects\n authenticate when no explicit auth is passed\n- thread toolNamePrefix/in\n[…]\nde/exclude/resources/emitProgress/\n autoRefresh/cacheCredentials through cache hits so filters and prefixes\n survive rehydration\n- follow nextCursor in tools/list, resources/list, and templates/list",
"is_bot": false,
"headline": "fix(mcp): correct cache/rehydrate option loss, credential reuse, and …",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T16:12:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "26336b5c44e5591b380ca4c41bf93b05f0ccdfe2",
"body": "Expose remote MCP server tools (Streamable HTTP / SSE) as callModel tools,\nwith pluggable auth, faithful JSON-Schema->Zod conversion, and a\nserializable, rehydratable cache.",
"is_bot": false,
"headline": "feat(mcp): add @openrouter/mcp package",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-26T15:24:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "adc7939f4b7ed85b1a060d13433b8be6063cff73",
"body": "chore: version packages",
"is_bot": false,
"headline": "Merge pull request #35 from OpenRouterTeam/changeset-release/main",
"author_name": "Ben",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-17T13:49:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "21c2268117882ed291829fee1456b8adbf4d5135",
"body": null,
"is_bot": true,
"headline": "chore: version packages",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-17T12:55:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4d79d358cfe7945a35f2ad4a4d7d9ff605a43dfc",
"body": "…0.13.7\n\nchore: bump @openrouter/sdk to 0.13.7",
"is_bot": false,
"headline": "Merge pull request #53 from OpenRouterTeam/chore/bump-openrouter-sdk-…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-17T12:55:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a5341f21555b5d2d982484c199d7d9c3093eabe6",
"body": "Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore: bump @openrouter/sdk to 0.13.7",
"author_name": "Ben Heidorn",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-17T12:47:49Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "839b3819869cb944c00077159fc49bb209cb45a6",
"body": "…-gh-token\n\nci: use GH_TOKEN for release-chain workflows",
"is_bot": false,
"headline": "Merge pull request #51 from OpenRouterTeam/sdk-bot/release-automation…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-03T17:50:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "168da4755a64b8cdcf1677fb2a3edeb1e3c2f359",
"body": "Switch the release-chain workflows from SUBTREE_PUSH_PAT to the dedicated\nGH_TOKEN PAT now configured on this repo. Follows up the merged #49, which\nlanded before this rewire.",
"is_bot": false,
"headline": "ci: use GH_TOKEN secret for PR open/merge and monorepo dispatch",
"author_name": "OpenRouter SDK Bot",
"author_login": null,
"committed_at": "2026-06-03T17:44:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b7ceb298dab6b1b72233bbbf3630fdc9354b7a9e",
"body": "…-bump\n\nci: auto-bump @openrouter/sdk and dispatch monorepo on release",
"is_bot": false,
"headline": "Merge pull request #49 from OpenRouterTeam/sdk-bot/release-automation…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-06-03T16:33:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8917615dd47bbf9b9da7240b70921c18aaa5ada8",
"body": "Drop the GitHub App (AGENT_BUMP_APP_*) and WEB_DISPATCH_PAT in favor of the\norg's existing SUBTREE_PUSH_PAT for opening/merging the bump PR and for the\nmonorepo dispatch. Slack alerts use the org-level CI_RELEASE_ALERT_SLACK_*\nsecrets, so no new secrets are required on this repo.",
"is_bot": false,
"headline": "ci: reuse SUBTREE_PUSH_PAT instead of new App/PAT secrets",
"author_name": "OpenRouter SDK Bot",
"author_login": null,
"committed_at": "2026-06-03T14:39:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "aa4f6b525fc518c7f29f259f2b872b73dcaff30a",
"body": "chore(agent): bump version to 0.7.1",
"is_bot": false,
"headline": "Merge pull request #50 from OpenRouterTeam/release/v0.7.1",
"author_name": "Ben",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-03T14:35:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "33a807abc07ecde1b7a4fb0f7fdf853ca7c2a4a9",
"body": "Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(agent): bump version to 0.7.1",
"author_name": "Ben Heidorn",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-03T14:32:45Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "faaf82cf0cf69b32719db403370cdd19686b83e3",
"body": "fix(agent): update OutputInputImage re-export for SDK compat and persist user input",
"is_bot": false,
"headline": "Merge pull request #48 from OpenRouterTeam/cyb/user-input-persistence",
"author_name": "Ben",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-03T14:13:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8c1196c700b2e8a835703ab229e4a098193215f3",
"body": "HOP A + HOP B of the SDK release chain:\n\n- bump-openrouter-sdk.yaml: receives openrouter-sdk-published dispatch (or\n manual workflow_dispatch), opens a PR bumping @openrouter/sdk in\n packages/agent (caret floor + relock + changeset) via an App token so Perry\n and CI run, then self-polls Perry + C\n[…]\non a real @openrouter/agent publish (changesets published\n output, or npm version diff on manual publish), dispatch\n openrouter-agent-published to openrouter-web to kick off the server-tools\n bump.",
"is_bot": false,
"headline": "ci: auto-bump @openrouter/sdk and dispatch monorepo on release",
"author_name": "OpenRouter SDK Bot",
"author_login": null,
"committed_at": "2026-06-03T14:08:37Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7b6704ae792df992df15dcf56c04a0afffe412fe",
"body": "Add assistant-item assertion to the streaming-failure regression test,\nmaking the atomicity invariant explicit: after a successful retry, both\nexactly one user turn and one assistant turn are present in state.\n\nCo-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "test(agent): assert assistant message lands atomically with user input",
"author_name": "Ben Heidorn",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-02T15:39:31Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "ce00bf9bede9a68d1b38d798c906c72356cc97a2",
"body": "Move fresh user-item persistence from initStream (after ok:true) to\nsaveResponseToState (after stream consumption). Previously, an ok:true\nresponse followed by a mid-stream failure would leave the user turn in\nstate with no assistant reply — on retry the same input was appended\nagain, producing dupl\n[…]\n a\nretry starts clean.\n\nAdds a streaming-failure regression test (ok:true + stream error + retry)\nto user-input-persistence.test.ts.\n\nCo-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(agent): persist user input atomically with assistant output",
"author_name": "Ben Heidorn",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-02T15:14:06Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "76876339a98105b868cf80e1a978d16e29e48e78",
"body": "…ist user input\n\n- Replace removed `OutputInputImage` with `OutputImage` + backward-compat\n alias (`OutputImage as OutputInputImage`) after @openrouter/sdk dropped\n the old export name.\n- Persist fresh user input items to state only after the API call succeeds,\n preventing duplicates on transient retries.\n\nCo-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(agent): update OutputInputImage re-export for SDK compat and pers…",
"author_name": "Ben Heidorn",
"author_login": "Cybourgeoisie",
"committed_at": "2026-06-02T11:46:19Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d8a8f659187994cca917f6d1e7dfef140c9e4e25",
"body": "…ponse-470ET\n\nfeat(agent): add allowFinalResponse option to callModel",
"is_bot": false,
"headline": "Merge pull request #44 from OpenRouterTeam/claude/add-allow-final-res…",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-18T21:44:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7a404a4d633b562abbde4aebe1931cb7ea24084c",
"body": "Bumps @openrouter/agent to 0.7.0 and consumes the\nallowFinalResponse changeset into the CHANGELOG.\n\nhttps://claude.ai/code/session_01Up1UhjF9mQBDq4rFwULovN",
"is_bot": false,
"headline": "chore: version packages (0.7.0)",
"author_name": "Claude",
"author_login": "claude",
"committed_at": "2026-05-18T21:41:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8057b775f48e7db6d71aaef6c434e85a9495e2e4",
"body": "- Save real tool outputs to state BEFORE the HITL pause check so a\n mixed batch (HITL + regular tools) doesn't drop the regular tool's\n output from state on resume. Matches the in-loop ordering.\n- Apply nextTurnParams from executed tools so tools that mutate\n request params (model, temperature, e\n[…]\nath that the\n non-streaming fixtures didn't cover).\n- Add a unit test asserting that stubs land in the request but never\n in persisted state.\n\nhttps://claude.ai/code/session_01Up1UhjF9mQBDq4rFwULovN",
"is_bot": false,
"headline": "fix(agent): address adversarial review of allowFinalResponse",
"author_name": "Claude",
"author_login": "claude",
"committed_at": "2026-05-18T21:37:54Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ad789c80235777bc65765bc7cf49bbd07b4995d4",
"body": "…ow-up\n\nAddress review feedback on the allowFinalResponse implementation:\n\n- Execute pending tool calls when the trigger fires so they have real\n matching outputs in the input, rather than always synthesizing stubs.\n Stubs now only cover any manual (non-executable) tool calls in the\n halted turn \n[…]\nbled by the falsy check).\n- Add 6 unit tests that mock betaResponsesSend and assert the second\n request shape, tool execution, and edge cases.\n\nhttps://claude.ai/code/session_01Up1UhjF9mQBDq4rFwULovN",
"is_bot": false,
"headline": "fix(agent): execute pending tool calls before allowFinalResponse foll…",
"author_name": "Claude",
"author_login": "claude",
"committed_at": "2026-05-18T21:25:03Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c33195cf89e10316fc9ddbf222d6717e831db04c",
"body": "Sibling of stopWhen. When the loop is halted by stopWhen while the last\nresponse still contains tool calls, set allowFinalResponse: true (or a\nstring) to make one more no-tools request so the loop ends with a\nnatural-language summary instead of an unfinished tool call. A string\nvalue is appended as a final user message. The full accumulated input\narray and the original instructions are sent.\n\nhttps://claude.ai/code/session_01Up1UhjF9mQBDq4rFwULovN",
"is_bot": false,
"headline": "feat(agent): add allowFinalResponse option to callModel",
"author_name": "Claude",
"author_login": "claude",
"committed_at": "2026-05-18T21:05:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7222108ee9bc2de1e382d4f25c4ec517029e97bf",
"body": "chore: version packages (0.6.0)",
"is_bot": false,
"headline": "Merge pull request #43 from OpenRouterTeam/changeset-release-0.6.0",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-14T15:36:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "660731ecd645c28fad40f0eefed9deae857adefd",
"body": "The 0.5.0 → 0.6.0 work (notably the HITL tooling that landed earlier)\nshifted the structural metrics far enough that the gate flags a drop\nagainst the stale baseline even on no-source-change PRs. Re-baselining\ncaptures the current state so subsequent PRs are measured from here.\n\n quality_signal: 0.5195 → 0.5094\n coupling_score: 0.4173 → 0.4286\n total_import_edges: 127 → 133\n cross_module_edges: 55 → 59",
"is_bot": false,
"headline": "chore: refresh sentrux baseline for 0.6.0 release",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-14T15:34:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "101f7f71d4a78a4e65c21c80e446541a9c57ba62",
"body": "Consumes the changeset from #42 (remove implicit 5-step cap in\ncallModel). Bumps @openrouter/agent from 0.5.0 to 0.6.0 and updates\nthe CHANGELOG.",
"is_bot": false,
"headline": "chore: version packages (0.6.0)",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-14T15:27:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "06501a9116deb90761c6af1bce5c28f0849333ea",
"body": "feat(agent): remove implicit 5-step cap in callModel",
"is_bot": false,
"headline": "Merge pull request #42 from OpenRouterTeam/remove-implicit-max-steps",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-14T15:26:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8e71f06024f41e60ccdc68577016637a31912779",
"body": "When `stopWhen` is omitted, the tool-execution loop now runs until the\nmodel produces a turn with no tool calls instead of being silently\ncapped at 5 steps. Callers who want a bound must pass an explicit\n`stopWhen` (e.g. `stepCountIs(n)`, `maxCost(...)`).",
"is_bot": false,
"headline": "feat(agent): remove implicit 5-step cap in callModel",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-14T15:24:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3e5ef28746ede546293ee0b96a4143262294a0bf",
"body": "chore(release): @openrouter/agent 0.5.0 (HITL tools)",
"is_bot": false,
"headline": "Merge pull request #40 from OpenRouterTeam/changeset/hitl-tools-release",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:52:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4cb0c3b4ff1f9534674cfd602213b2eddf80a0e0",
"body": "Consumes the pre-existing `curvy-streams-watch` patch changeset (stream\ndetection regression coverage from #34) and adds a new minor changeset\ncovering the human-in-the-loop tool type merged in #38.",
"is_bot": false,
"headline": "chore: version packages for HITL tools release (0.5.0)",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:50:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c649c9cc99521ae9e3fbb42d109146f31f040ce1",
"body": "feat(tools): add human-in-the-loop tool type",
"is_bot": false,
"headline": "Merge pull request #38 from OpenRouterTeam/feat/hitl-tools",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:48:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "396d44b3371df99ddf660288a8d53cd4fc810728",
"body": "applyOnResponseReceivedHooks and executeToolRound grew cyclomatic\ncomplexity above 15 when HITL logic landed, tripping sentrux gate\n(complex functions 9 -> 11). Extract per-item helpers so the gate\nmatches baseline again:\n\n- applyOnResponseReceivedHooks: move per-item hook/validate logic into\n comp\n[…]\nutForModel; describeNonRecord factors out the nested\n typeof/Array.isArray ternary.\n\nPure refactor — no behavior change. All 280 unit tests still pass;\nsentrux gate reports \"No degradation detected\".",
"is_bot": false,
"headline": "refactor(tools): extract helpers to keep cc under structural gate",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:34:12Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "51a983d256d3594060283e6a95b3c2fac0e9cfff",
"body": "- Preserve content-array FunctionCallOutputItem shapes in the HITL\n onResponseReceived pipeline instead of JSON.stringify'ing them; export\n isContentArray from conversation-state for reuse.\n- Require outputSchema on HITL tool configs and use it to validate\n caller-supplied responses. Validation f\n[…]\nooksToFreshItems.\n- Drop the onResponseReceived call on SDK-generated outputs in\n continueWithUnsentResults. The hook is now strictly for caller-supplied\n outputs, matching its documented semantics.",
"is_bot": false,
"headline": "fix(tools): address HITL review feedback",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:19:13Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8ac64b5b1b9046ee3e3db9b42e19432452ccb4c5",
"body": "chore: add sentrux architectural gating",
"is_bot": false,
"headline": "Merge pull request #39 from OpenRouterTeam/chore/sentrux-setup",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:16:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "74493d8889dd1b94d9b4533e803e99f0c02dd28a",
"body": "Wire up sentrux via .mcp.json for Claude Code MCP integration and add\n.sentrux/rules.toml encoding the inner-loop -> lib -> api-shape-helpers\nlayering. CI gains a structural-gate job that installs sentrux v0.5.7 and\nruns `sentrux gate` against the saved baseline on every PR, blocking merges\nthat regress structural metrics (coupling, cycles, god files, complexity).",
"is_bot": false,
"headline": "chore: add sentrux architectural gating",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-06T00:14:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dc2ba48b88662be93c0ccd3e1e17ced61a2a30b8",
"body": "- Route auto-resolvable checks through isAutoResolvableTool so pure-HITL\n turns actually enter the execution loop and invoke onToolCalled.\n- Propagate HITL pauses out of executeToolRound; the outer loop now\n persists pending calls under a new awaiting_hitl status and returns\n before issuing a fol\n[…]\nput alongside error when onResponseReceived throws,\n so the model can distinguish hook failure from tool-reported error.\n- Replace unsafe InputsUnion cast with a structurally-typed rewritten\n array.",
"is_bot": false,
"headline": "fix(tools): close HITL execution gaps surfaced in review",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-05T23:47:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5155f4456ee3e0aed8734ad15a6949dbb068ee68",
"body": null,
"is_bot": false,
"headline": "style: apply biome formatting and optional-chain suggestion",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-05T22:55:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8faf9bb846887c01a6d526ffc19526dfe30822d1",
"body": "Adds a fourth client tool kind that extends manual-tool semantics with two\nasync hooks. `onToolCalled` runs when the model invokes the tool — returning\na value short-circuits like `execute`, returning `null` pauses the loop like\na manual tool. `onResponseReceived` runs on a later turn when an incomi\n[…]\non_call.name) a HITL\ntool, letting the tool post-process caller-supplied results before the\nmodel sees them.\n\nKeeps HITL control flow local to the tool definition instead of smeared\nacross the caller.",
"is_bot": false,
"headline": "feat(tools): add human-in-the-loop tool type",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-05-05T22:54:32Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ac3f82f8871caf7edb0aa0c38b2f892b73039014",
"body": "Use getReader for stream shape checks",
"is_bot": false,
"headline": "Merge pull request #34 from w0nche0l/codex/getreader-stream-shape-check",
"author_name": "robert-j-y",
"author_login": "robert-j-y",
"committed_at": "2026-05-01T22:38:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "61aca10fd9434fe69fbe1e069e4b1858613a7da7",
"body": null,
"is_bot": false,
"headline": "Add stream detection regression coverage",
"author_name": "Dennis",
"author_login": "w0nche0l",
"committed_at": "2026-05-01T20:24:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "596726ca44d338ac4a8e916e3b28c50071ae1410",
"body": null,
"is_bot": false,
"headline": "Use getReader for stream shape checks",
"author_name": "Dennis",
"author_login": "w0nche0l",
"committed_at": "2026-05-01T08:28:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e3a868cfcc68eee699473e034f09d4efb7d6d41c",
"body": "chore: convert to Turborepo monorepo (v2.9.6)",
"is_bot": false,
"headline": "Merge pull request #26 from OpenRouterTeam/turborepo-migration",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:59:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "232f6c50411eb8bce000f127a0f7655964844d74",
"body": "# Conflicts:\n#\tpackage.json",
"is_bot": false,
"headline": "Merge remote-tracking branch 'origin/main' into turborepo-migration",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:59:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c3404cb0a37698590afb4bd37dbe7aa62a33a770",
"body": "chore: version packages",
"is_bot": false,
"headline": "Merge pull request #29 from OpenRouterTeam/changeset-release/main",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:57:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dc6f77e83543163a0a4802853e8e7ac6cdccc42a",
"body": "# Conflicts:\n#\tpackages/agent/tests/unit/has-approval-tools.test-d.ts\n#\tpackages/agent/tests/unit/server-tool-stream-narrowing.test-d.ts\n#\tpackages/agent/tests/unit/server-tool.test.ts",
"is_bot": false,
"headline": "Merge remote-tracking branch 'origin/main' into turborepo-migration",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:57:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "469aff365862127ee1460c4468b130dc9665c6ba",
"body": null,
"is_bot": true,
"headline": "chore: version packages",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-04-20T18:55:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ffa0ae4b1d9bfa5f779303070c070b1da8aa494a",
"body": "feat: add OpenRouter server tools to callModel",
"is_bot": false,
"headline": "Merge pull request #30 from OpenRouterTeam/add-server-tools",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:55:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "46a45f2ddd87a15669c82abb8946f67b8b10c4d9",
"body": "Previously fell through to the default branch, which widened the runtime\nfilter by setting acceptGenericServerItem=true. The type-level\nKnownServerToolOutputs map already narrows this tool's output to the\n'openrouter:datetime' literal, so the runtime allow-list should match.",
"is_bot": false,
"headline": "fix: add explicit openrouter:datetime case to item stream scope",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:54:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e4e3ed5e0a4f132e8cae1c33d7831f65aa46c211",
"body": null,
"is_bot": false,
"headline": "chore: add changeset for serverTool feature",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:26:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5e1db17d3c1a97316cc16efef25d4bd84366c948",
"body": "- Defensively accept both `web_search_call` and `openrouter:web_search`\n item literals for the `openrouter:web_search` request variant (runtime\n filter + KnownServerToolOutputs type) so items aren't silently dropped\n when the provider wraps results in OutputServerToolItem.\n- Replace the deny-list\n[…]\nem` / `isFileSearchCallOutputItem`\n / `isImageGenerationCallOutputItem` branches in `handleOutputItemAdded`\n and `handleOutputItemDone`; the `isServerToolResultItem` catch-all\n already covers them.",
"is_bot": false,
"headline": "fix: tighten server tool output routing and filter correctness",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:12:11Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5965684ec15e2a8a4b9620e0eb933663132d8ad9",
"body": "Adds first-class support for OpenRouter's server-executed tools\n(web_search, openrouter:datetime, image_generation, mcp, file_search,\ncode_interpreter, etc.) through a new `serverTool()` factory that lives\nalongside the existing `tool()`. Server tools are passed through to the\nAPI via the SDK's `Res\n[…]\ntions, proper typeguards\nthroughout. The `getItemsStream` scope filter is backed by a real\nruntime allow-list derived from `TTools`, so the type-level narrowing\ncorresponds to actual runtime behavior.",
"is_bot": false,
"headline": "feat: add OpenRouter server tools to callModel",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T18:09:02Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "54475e856547b690a175ecd36b6bb58c3e166097",
"body": "# Conflicts:\n#\tpackage.json\n#\tpnpm-lock.yaml",
"is_bot": false,
"headline": "Merge remote-tracking branch 'origin/main' into turborepo-migration",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:52:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3baff61ca7e90871ccb65c7a826be64fc800e570",
"body": "chore: version packages",
"is_bot": false,
"headline": "Merge pull request #28 from OpenRouterTeam/changeset-release/main",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:39:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ec4ff3f4d97c576aec4669ec8271b1d39cbd8a85",
"body": "chore: bump @openrouter/sdk from 0.11.2 to 0.12.12",
"is_bot": false,
"headline": "Merge pull request #25 from OpenRouterTeam/chore/bump-sdk-0.12.12",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:39:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e23eb4256098b3ed21e9a13fbf8145e3691eb936",
"body": null,
"is_bot": false,
"headline": "Merge remote-tracking branch 'origin/main' into turborepo-migration",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:36:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d3cff5f023d3c19a44083baa40c7e14a924f39cc",
"body": "- Remove dead \"Check for pending changesets\" step in publish.yaml;\n nothing reads steps.changesets.outputs.pending anymore.\n- Add \"globalDependencies\": [\"tsconfig.base.json\"] to turbo.json so\n edits to the shared base tsconfig invalidate build/typecheck/test\n caches instead of serving stale output.",
"is_bot": false,
"headline": "chore: address review feedback",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:35:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c41af68aa9c42103aa342c4787a68e5724a5e066",
"body": null,
"is_bot": true,
"headline": "chore: version packages",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-04-20T17:28:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8e516726cad9139975e572c0ac448e012d6672d7",
"body": "fix(openrouter): normalize hooks constructor option so shorthand input isn't silently dropped",
"is_bot": false,
"headline": "Merge pull request #27 from OpenRouterTeam/fix-e2e-tests",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:28:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ef157612ca213d23ef1bfbfec012db09144315bf",
"body": "The underlying SDK only wires `hooks` into the request pipeline when it's an\n`SDKHooks` instance; passing a plain hook object (e.g. `{ beforeRequest }`) was\nsilently ignored, causing `hooks` to no-op for every caller who used the\nnatural shorthand.\n\n`new OpenRouter({ hooks })` now accepts an `SDKHoo\n[…]\nng from `@openrouter/sdk`, which hit the SDK's older `ModelResult` that\ndoesn't yield manual-tool `function_call` items from `finalResponse`) and\nbumps a 6s timeout on a Sonnet-with-tools test to 20s.",
"is_bot": false,
"headline": "fix(openrouter): normalize hooks constructor option",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:27:16Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b5743a1c3a25a7c815bae969bdcebb9bacf02248",
"body": "Move @openrouter/agent into packages/agent/ under a pnpm workspace with\nTurborepo managing build/test/lint/typecheck task graphs at the root.\n\nRelease flow now uses `changeset publish`, which walks the workspace and\npublishes only packages whose on-disk version differs from npm — the\npipeline genera\n[…]\nEADME, CHANGELOG,\n.npmignore, vitest.config.ts, and tsconfig move into packages/agent/.\nBiome + grit plugins stay at the root; scope globs widened to cover\npackages/*. Vitest loads a shared root .env.",
"is_bot": false,
"headline": "chore: convert to Turborepo monorepo (v2.9.6)",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-20T17:01:37Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e2e61ceb20c248bfd5615abd35c9c38236a72f51",
"body": "ci: split CI into parallel jobs",
"is_bot": false,
"headline": "Merge pull request #9 from OpenRouterTeam/ci-parallel-checks",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-17T14:26:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "36eda074cb0616122892f9e79c60c06977d94750",
"body": "- Apply Biome formatter to tests/unit/conversation-state.test.ts to\n break long array literals across multiple lines.\n- Have the e2e-tests job short-circuit with a warning when\n OPENROUTER_API_KEY is not set instead of hard-failing, so the check\n passes in contexts where the secret is unavailable (e.g. forks).",
"is_bot": false,
"headline": "ci: fix lint formatting and skip e2e tests when API key is absent",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-16T21:03:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "66f85cf1a54ff188c2eb11d333aa2020e82a2a8b",
"body": "Combines the parallel-job split from this branch with the named-step\nstyle added on main. Also passes the OPENROUTER_API_KEY secret into\nthe e2e-tests job so it can actually run.",
"is_bot": false,
"headline": "ci: resolve merge conflict and wire OPENROUTER_API_KEY for e2e job",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-16T20:48:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8faa32c4d1069dfbdbf590ee73f78823bb024fdb",
"body": null,
"is_bot": false,
"headline": "style: fix biome formatting in conversation-state test",
"author_name": "Jakob Castro",
"author_login": "jakobdylanc",
"committed_at": "2026-04-16T17:05:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ec94de8c16fa114ba1e6369db25b4a2cd4ebc359",
"body": "Co-Authored-By: jakob <jakob.castro@openrouter.ai>",
"is_bot": true,
"headline": "chore: bump @openrouter/sdk from 0.11.2 to 0.12.12",
"author_name": "Devin AI",
"author_login": "devin-ai-integration[bot]",
"committed_at": "2026-04-16T16:45:08Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "bc686d2249e577efb0f47b8e92d8574d66467e4a",
"body": "Add support for passing input_text, input_image, and input_file content\nblocks directly as tool output without JSON.stringify. This enables tools\nthat produce rich outputs like images to pass them through efficiently.\n\nBump version to 0.3.2.",
"is_bot": false,
"headline": "feat: support content arrays in tool outputs",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-14T20:25:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "358253d5d3b6b36465afbf1c76f5445e963cdf2b",
"body": "feat(tools): add toModelOutput for custom tool result formatting",
"is_bot": false,
"headline": "Merge pull request #24 from OpenRouterTeam/feature/to-model-output",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-14T20:21:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1e43375cc85a774afdd3faad92ec4be4f8ca73cc",
"body": "Adds optional toModelOutput function to tool definitions that converts\nexecution output to model-facing content blocks (Responses API format).\nThis decouples what calling code receives from what the model sees.",
"is_bot": false,
"headline": "feat(tools): add toModelOutput for custom tool result formatting",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-14T19:52:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1572b88ba8c2f2b4bcb38a2526a894a3ea193917",
"body": "chore: version packages",
"is_bot": false,
"headline": "Merge pull request #23 from OpenRouterTeam/changeset-release/main",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-12T14:43:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f7a90634fb25ccfb0794dd50c77aa1e6ea61d567",
"body": null,
"is_bot": true,
"headline": "chore: version packages",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-04-12T12:10:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f697969678f86da1ef04952d78625bca659eb043",
"body": "chore: add changeset for type fixes (patch)",
"is_bot": false,
"headline": "Merge pull request #22 from OpenRouterTeam/changelog/fix-types-patch",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-12T12:10:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8535b77d462fc82c8c52019948cb9de7852688f0",
"body": "Ensures code quality checks run before pushing to remote.",
"is_bot": false,
"headline": "feat: add husky pre-push hooks for lint and typecheck",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-12T12:08:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5d947e6ad5ba291d43322168b11782c19b71b8e2",
"body": "- Use `import type` for Item import in async-params.ts\n- Organize imports per biome rules\n- Remove extra blank line in item-types.ts",
"is_bot": false,
"headline": "fix: resolve biome lint errors",
"author_name": "Matt Apperson",
"author_login": "mattapperson",
"committed_at": "2026-04-12T12:07:31Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 7,
"commits_last_year": 152,
"latest_release_at": "2026-07-22T20:50:38Z",
"latest_release_tag": "@openrouter/agent@0.8.0",
"releases_from_tags": false,
"days_since_last_push": 2,
"active_weeks_last_year": 16,
"days_since_latest_release": 11,
"mean_days_between_releases": 13
},
"artifacts": {
"collected": true,
"structure": [],
"declarations": [
{
"name": null,
"path": "package.json",
"tokens": [
"npm.private"
],
"ecosystem": "npm"
},
{
"name": "@openrouter/agent",
"path": "packages/agent/package.json",
"tokens": [
"npm.entry"
],
"ecosystem": "npm"
},
{
"name": "@openrouter/mcp",
"path": "packages/mcp/package.json",
"tokens": [
"npm.entry"
],
"ecosystem": "npm"
}
]
},
"community": {
"has_readme": true,
"has_license": false,
"readme_badges": {
"hosts": [],
"total": 0,
"header": 0,
"collected": true,
"has_inspect_badge": false
},
"has_description": true,
"has_contributing": false,
"health_percentage": 25,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "@openrouter/mcp",
"exists": true,
"license": "Apache-2.0",
"keywords": [
"openrouter",
"mcp",
"model-context-protocol",
"agent",
"typescript",
"ai",
"tools",
"llm"
],
"ecosystem": "npm",
"categories": [],
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@openrouter/mcp",
"declared_type": null,
"is_deprecated": false,
"latest_version": "0.0.1",
"repository_url": "https://github.com/OpenRouterTeam/typescript-agent",
"versions_count": 1,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 8,
"monthly_downloads": 133,
"first_published_at": "2026-07-24T20:05:28.313000Z",
"latest_published_at": "2026-07-24T20:05:28.695000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 9
},
{
"name": "@openrouter/agent",
"exists": true,
"license": "Apache-2.0",
"keywords": [
"openrouter",
"agent",
"typescript",
"ai",
"tools",
"streaming",
"llm"
],
"ecosystem": "npm",
"categories": [],
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@openrouter/agent",
"declared_type": null,
"is_deprecated": false,
"latest_version": "0.8.0",
"repository_url": "https://github.com/OpenRouterTeam/typescript-agent",
"versions_count": 13,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 8,
"monthly_downloads": 382454,
"first_published_at": "2026-04-01T16:43:16.521000Z",
"latest_published_at": "2026-07-22T20:50:29.987000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 11
}
]
},
"popularity": {
"forks": 11,
"stars": 19,
"watchers": 0,
"fork_history": {
"days": [
{
"date": "2026-04-10",
"count": 1
},
{
"date": "2026-05-01",
"count": 1
},
{
"date": "2026-05-02",
"count": 1
},
{
"date": "2026-05-10",
"count": 1
},
{
"date": "2026-05-25",
"count": 1
},
{
"date": "2026-05-30",
"count": 1
},
{
"date": "2026-06-15",
"count": 1
},
{
"date": "2026-06-17",
"count": 1
},
{
"date": "2026-06-26",
"count": 1
},
{
"date": "2026-07-16",
"count": 1
},
{
"date": "2026-07-29",
"count": 1
}
],
"complete": true,
"collected": 11,
"total_forks": 11
},
"star_history": null,
"open_issues_and_prs": 17
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": true,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"packages/agent/tsconfig.json",
"packages/mcp/tsconfig.json"
],
"toolchain_manifests": [],
"largest_source_bytes": 181323,
"source_files_sampled": 120,
"oversized_source_files": 2,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [
"package.json"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 95,
"malicious_count": 0,
"assessed_package": "npm:@openrouter/mcp@0.0.1",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"npm"
],
"dependencies": [
{
"name": "@openrouter/sdk",
"manifest": "packages/agent/package.json",
"ecosystem": "npm",
"version_constraint": "^0.13.7"
},
{
"name": "zod",
"manifest": "packages/agent/package.json",
"ecosystem": "npm",
"version_constraint": "^4.0.0"
},
{
"name": "@modelcontextprotocol/sdk",
"manifest": "packages/mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^1.29.0"
},
{
"name": "@openrouter/agent",
"manifest": "packages/mcp/package.json",
"ecosystem": "npm",
"version_constraint": "workspace:*"
},
{
"name": "zod",
"manifest": "packages/mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^4.0.0"
}
],
"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": 11,
"merged_prs": 58,
"open_issues": 6,
"closed_ratio": 0.143,
"closed_issues": 1,
"closed_unmerged_prs": 15
},
"bus_factor": 1,
"bot_contributors": 2,
"top_contributors": [
{
"type": "User",
"login": "mattapperson",
"commits": 101,
"avatar_url": "https://avatars.githubusercontent.com/u/192433?v=4"
},
{
"type": "User",
"login": "LukasParke",
"commits": 12,
"avatar_url": "https://avatars.githubusercontent.com/u/5702154?v=4"
},
{
"type": "User",
"login": "Cybourgeoisie",
"commits": 8,
"avatar_url": "https://avatars.githubusercontent.com/u/301326?v=4"
},
{
"type": "User",
"login": "claude",
"commits": 4,
"avatar_url": "https://avatars.githubusercontent.com/u/81847?v=4"
},
{
"type": "User",
"login": "robert-j-y",
"commits": 4,
"avatar_url": "https://avatars.githubusercontent.com/u/212159665?v=4"
},
{
"type": "User",
"login": "w0nche0l",
"commits": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/3719829?v=4"
},
{
"type": "User",
"login": "okacodes",
"commits": 2,
"avatar_url": "https://avatars.githubusercontent.com/u/193345390?v=4"
},
{
"type": "User",
"login": "jakobdylanc",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/38699060?v=4"
},
{
"type": "User",
"login": "ayush-or",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/291842981?v=4"
}
],
"contributors_sampled": 9,
"top_contributor_share": 0.743
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"bump-openrouter-sdk.yaml",
"ci.yaml",
"publish.yaml"
],
"has_docs_dir": false,
"linter_configs": [
"biome.json"
],
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"pnpm-lock.yaml"
],
"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": 3,
"reason": "branch protection is not maximal on development and all release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 9,
"reason": "18 out of 19 merged PRs checked by a CI test -- score normalized to 9",
"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": 4,
"reason": "Found 8/18 approved changesets -- score normalized to 4",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 10,
"reason": "project has 5 contributing companies or organizations",
"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": "30 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": null,
"reason": "packaging workflow not 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": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"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": null,
"reason": "no releases found",
"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": "16 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "d03060256c4c7d55432e508544d8d35d2f65d4bb",
"ran_at": "2026-08-03T04:51:18Z",
"aggregate_score": 3.8,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"recent_prs": {
"merged_7d": 3,
"decided_7d": 3,
"merged_30d": 17,
"authors_30d": 6,
"decided_30d": 29,
"sample_size": 60,
"window_days": 30,
"sample_exhausted": false,
"authors_probed_30d": 6,
"newcomer_merged_30d": 15,
"bot_prs_excluded_30d": 1,
"newcomer_authors_30d": 3,
"newcomer_decided_30d": 26
},
"ci_last_run_at": "2026-07-30T15:59:39Z",
"oldest_open_prs": [
{
"number": 31,
"created_at": "2026-04-20T18:44:41Z",
"last_comment_at": "2026-07-29T19:17:56Z",
"last_comment_author": "cortex-github-agent"
},
{
"number": 32,
"created_at": "2026-04-21T16:45:08Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 55,
"created_at": "2026-06-26T02:55:58Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 74,
"created_at": "2026-07-22T01:49:06Z",
"last_comment_at": "2026-07-29T19:40:38Z",
"last_comment_author": "devin-ai-integration"
},
{
"number": 85,
"created_at": "2026-07-28T19:31:30Z",
"last_comment_at": "2026-07-29T19:40:37Z",
"last_comment_author": "devin-ai-integration"
},
{
"number": 86,
"created_at": "2026-07-28T19:53:53Z",
"last_comment_at": "2026-07-30T18:48:38Z",
"last_comment_author": "LukasParke"
},
{
"number": 88,
"created_at": "2026-07-29T17:44:01Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 89,
"created_at": "2026-07-29T19:59:32Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 90,
"created_at": "2026-07-31T02:45:53Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 91,
"created_at": "2026-07-31T05:03:44Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 92,
"created_at": "2026-07-31T21:05:35Z",
"last_comment_at": null,
"last_comment_author": null
}
],
"last_merged_pr_at": "2026-07-30T15:58:38Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": [
{
"number": 10,
"created_at": "2026-04-03T21:18:01Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 11,
"created_at": "2026-04-03T21:21:09Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 41,
"created_at": "2026-05-10T20:13:12Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 45,
"created_at": "2026-05-27T17:40:50Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 54,
"created_at": "2026-06-26T02:55:21Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 58,
"created_at": "2026-07-08T04:30:26Z",
"last_comment_at": null,
"last_comment_author": null
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/OpenRouterTeam/typescript-agent",
"host": "github.com",
"name": "typescript-agent",
"owner": "OpenRouterTeam"
},
"metrics": {
"overall": {
"key": "overall",
"band": "good",
"name": "Overall health",
"note": "The weighted overall 64 is calibrated to 73 on the published index scale (record calibration 2026-08-02).",
"notes": [
{
"code": "overall_calibration",
"params": {
"raw": 64,
"calibrated": 73,
"calibration": "2026-08-02"
}
}
],
"value": 73,
"inputs": {
"security": 50,
"vitality": 85,
"community": 44,
"governance": 60,
"calibration": "2026-08-02",
"engineering": 75,
"ai_readiness": 55,
"weighted_overall_raw": 64
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "excellent",
"name": "Vitality",
"value": 85,
"weight": 0.21,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"commits_last_year": 152,
"human_commit_share": 0.94,
"days_since_last_push": 2,
"active_weeks_last_year": 16
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 2 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 2
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "16/52 weeks with commits",
"points": 11.1,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 16
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "152 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 152
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 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": "exceptional",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 100,
"inputs": {
"releases_count": 7,
"latest_release_tag": "@openrouter/agent@0.8.0",
"releases_from_tags": false,
"days_since_latest_release": 11,
"mean_days_between_releases": 13
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "7 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 7
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 11 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 11
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~13 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 13
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "exceptional",
"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": "weak",
"name": "Community & Adoption",
"value": 44,
"weight": 0.17,
"metrics": [
{
"key": "popularity",
"band": "at_risk",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 29,
"inputs": {
"forks": 11,
"stars": 19,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "19 stars",
"points": 20.4,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 19
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "11 forks",
"points": 8.3,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 11
}
}
],
"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": "at_risk",
"name": "Community health",
"note": null,
"notes": [],
"value": 25,
"inputs": {
"has_readme": true,
"has_license": false,
"readme_badges": 0,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"readme_badge_services": [],
"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
}
]
},
{
"key": "ecosystem_adoption",
"band": "exceptional",
"name": "Ecosystem adoption (downloads)",
"note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"registry_dependents"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 93,
"inputs": {
"packages": [
"@openrouter/mcp",
"@openrouter/agent"
],
"dependents": null,
"ecosystems": "npm",
"total_downloads": null,
"monthly_downloads": 382587
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "382,587 downloads/month across npm",
"points": 74.4,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 382587,
"ecosystems": "npm"
}
}
],
"max_points": 80
},
{
"key": "registry_dependents",
"name": "Registry dependents",
"detail": "not reported by this ecosystem",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_reported_by_this_ecosystem",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "moderate",
"name": "Sustainability & Governance",
"value": 60,
"weight": 0.23,
"metrics": [
{
"key": "maintainer_resilience",
"band": "weak",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 37,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 9,
"top_contributor_share": 0.743
},
"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 74% of commits",
"points": 5.8,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 74
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "9 contributors",
"points": 12.2,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 9
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 5 contributing companies or organizations",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "weak",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 43,
"inputs": {
"merged_prs": 58,
"open_issues": 6,
"closed_issues": 1,
"prs_merged_7d": 3,
"prs_decided_7d": 3,
"prs_merged_30d": 17,
"prs_decided_30d": 29,
"issue_closed_ratio": 0.143,
"closed_unmerged_prs": 15,
"first_time_authors_30d": 3,
"first_time_prs_merged_30d": 15,
"first_time_prs_decided_30d": 26
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "14% of issues closed",
"points": 6,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 14
}
}
],
"max_points": 42
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "58/73 decided PRs merged",
"points": 23.8,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 58,
"decided": 73
}
}
],
"max_points": 30
},
{
"key": "newcomer_pr_acceptance",
"name": "Newcomer PR acceptance",
"detail": "15/26 first-time contributors' PRs merged in 30d",
"points": 7.5,
"status": "partial",
"details": [
{
"code": "newcomer_prs_merged",
"params": {
"days": 30,
"merged": 15,
"decided": 26
}
}
],
"max_points": 13
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 8/18 approved changesets -- score normalized to 4",
"points": 6,
"status": "partial",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "good",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 72,
"inputs": {
"followers": 3536,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "OpenRouterTeam",
"public_repos": 36,
"account_age_days": 1117
},
"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": "3,536 followers of OpenRouterTeam",
"points": 25,
"status": "met",
"details": [
{
"code": "owner_followers",
"params": {
"count": 3536,
"login": "OpenRouterTeam"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "36 public repos, account ~3 yr old",
"points": 17.5,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 36
}
},
{
"code": "account_age_years",
"params": {
"years": 3
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "exceptional",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"@openrouter/mcp",
"@openrouter/agent"
],
"ecosystems": "npm",
"any_deprecated": false,
"min_days_since_publish": 9
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "2 package(s) on npm",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 2,
"ecosystems": "npm"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 9 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 9
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "13 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 13
}
}
],
"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": 75,
"weight": 0.19,
"metrics": [
{
"key": "engineering_practices",
"band": "excellent",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 82,
"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": "3 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 3
}
}
],
"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": "biome.json",
"points": 16,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "biome.json"
}
}
],
"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": "18 out of 19 merged PRs checked by a CI test -- score normalized to 9",
"points": 18,
"status": "partial",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 65,
"inputs": {
"topics": [],
"has_wiki": true,
"homepage": "https://openrouter.ai/docs/sdks/typescript/call-model",
"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": "https://openrouter.ai/docs/sdks/typescript/call-model",
"points": 15,
"status": "met",
"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": "moderate",
"name": "Security",
"value": 50,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "weak",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"packaging",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 38,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 3.8
},
"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 is not maximal on development and all release branches",
"points": 2.2,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "18 out of 19 merged PRs checked by a CI test -- score normalized to 9",
"points": 2.2,
"status": "partial",
"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 8/18 approved changesets -- score normalized to 4",
"points": 3,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 5 contributing companies or organizations",
"points": 2.5,
"status": "met",
"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": "30 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 not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"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 not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"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": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"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": "16 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "exceptional",
"name": "Dependency advisories",
"note": "Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@openrouter/mcp@0.0.1 runtime dependency closure — what installing the published package pulls in — 95 packages. Reachability is not analyzed.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"no_advisories_left_outstanding"
]
}
},
{
"code": "weights_renormalized",
"params": {}
},
{
"code": "advisories_scope_published",
"params": {
"package": "npm:@openrouter/mcp@0.0.1",
"assessed": 95
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 100,
"inputs": {
"source": "osv",
"advisories": 0,
"affected_packages": 0,
"assessed_packages": 95,
"unassessed_packages": 0,
"affected_by_severity": "none",
"direct_affected_packages": 0
},
"components": [
{
"key": "direct_dependencies_free_of_known_advisories",
"name": "Direct dependencies free of known advisories",
"detail": "no direct dependency carries a known advisory",
"points": 35,
"status": "met",
"details": [
{
"code": "no_direct_advisories",
"params": {}
}
],
"max_points": 35
},
{
"key": "indirect_dependencies_free_of_known_advisories",
"name": "Indirect dependencies free of known advisories",
"detail": "no indirect dependency carries a known advisory",
"points": 25,
"status": "met",
"details": [
{
"code": "no_indirect_advisories",
"params": {}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory carries a publication date",
"points": 0,
"status": "excluded",
"details": [
{
"code": "advisories_no_publication_date",
"params": {}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "exceptional",
"name": "Malicious dependencies",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"source": "osv",
"meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
"packages": [],
"red_flag": false,
"assessed_packages": 95,
"malicious_packages": 0,
"direct_malicious_packages": 0,
"withdrawn_malicious_packages": 0,
"installable_malicious_packages": 0
},
"components": [
{
"key": "no_dependency_reported_as_a_malicious_package",
"name": "No dependency reported as a malicious package",
"detail": "no dependency is reported as a malicious package",
"points": 100,
"status": "met",
"details": [
{
"code": "no_malicious_dependencies",
"params": {}
}
],
"max_points": 100
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "exceptional",
"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"
],
"commit_weight_rule": {
"min_commits": 50,
"min_commit_share": 0.1
},
"review_only_matches": 0,
"below_threshold_exposures": [],
"assessed_self_published_locations": 5
},
"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": "moderate",
"name": "AI Readiness",
"value": 55,
"weight": 0.04,
"metrics": [
{
"key": "ai_agent_context",
"band": "weak",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.947,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"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": "89 of 94 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 89,
"sampled": 94
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "moderate",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 64,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"pnpm-lock.yaml"
],
"has_dockerfile": false,
"typed_language": true,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": true,
"typecheck_configs": [
"packages/agent/tsconfig.json",
"packages/mcp/tsconfig.json"
],
"agent_commit_share": 0.12,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"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": "biome.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "biome.json"
}
}
],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "packages/agent/tsconfig.json, packages/mcp/tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "packages/agent/tsconfig.json, packages/mcp/tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "12 of the last 100 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 12,
"sampled": 100
}
}
],
"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": "exceptional",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 99,
"inputs": {
"primary_language": "TypeScript",
"largest_source_bytes": 181323,
"source_files_sampled": 120,
"oversized_source_files": 2
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "TypeScript (statically typed)",
"points": 45,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "TypeScript"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "2/120 source files over 60KB",
"points": 54.1,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 120,
"oversized": 2
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "at_risk",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 20,
"inputs": {
"example_dirs": [],
"has_mcp_signal": true,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 20,
"status": "met",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero)."
}
],
"classification": {
"labels": [
"mcp-server",
"library"
],
"scores": {
"sdk": 2,
"library": 4.8,
"mcp-server": 7
},
"primary": "mcp-server",
"evidence": [
{
"tier": "declared",
"label": "library",
"source": "npm.private",
"weight": -6
},
{
"tier": "distribution",
"label": "library",
"source": "registry:npm",
"weight": 6
},
{
"tier": "declared",
"label": "library",
"source": "npm.entry",
"weight": 4.8
},
{
"tier": "dependencies",
"label": "mcp-server",
"source": "dep:@modelcontextprotocol/sdk",
"weight": 4
},
{
"tier": "structure",
"label": "mcp-server",
"source": "mcp_signal",
"weight": 3
},
{
"tier": "description",
"label": "sdk",
"source": "description:sdk",
"weight": 2
}
],
"artifacts": [
{
"path": "package.json",
"labels": [],
"ecosystem": "npm"
},
{
"path": "packages/agent/package.json",
"labels": [
"library"
],
"ecosystem": "npm"
},
{
"path": "packages/mcp/package.json",
"labels": [
"library"
],
"ecosystem": "npm"
}
],
"confidence": "medium",
"host_extension": false,
"runs_as_process": true,
"consumed_by_code": true
},
"metrics_version": "2.3.1"
},
"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": "2026-08-03T04:51:38.340415Z",
"schema_version": "0.30.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/o/OpenRouterTeam/typescript-agent.svg",
"full_name": "OpenRouterTeam/typescript-agent",
"license_state": "absent",
"license_spdx": null
}