dsh-auto-model-routing 0.4.0 → 0.4.2

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## 0.4.2
+
+- AUTO now handles Claude and GPT model families only: selecting any other main model switches the session to MANUAL instead of failing the turn in the effort mapper.
+- Support the renamed `dsh-magpie-connector` Magpie route as an exact policy transport (replacing `dsh-magpie`); `dsh-magpie-connect` remains supported.
+- Fix the missing feedback entry on turns whose request configuration did not change: the main decision is marked applied from the effective request header instead of waiting for a new one.
+- Record two implicit feedback facts as separate ledger events keyed by session and decision: reply exposure and a later switch to MANUAL. No message text is stored; routing is unchanged.
+- The usage report adds a mutually exclusive implicit-signal breakdown per comparison group, with a fixed caveat that implicit no-objection is not the same as appropriate.
+- Sync the AUTO-selected effort through the official selection and simplify the picker display.
+
+## 0.4.1
+
+- Add the on-demand `auto-model-routing-report` skill and read-only `lib/usage-report.js`: joins policy-v2 decisions to actual per-call usage by message ID, grouped by version × model × depth, with coverage gaps, sample thresholds and fixed caveats. Observational only; never writes, spawns or uses the network, and never prints message text, paths or session IDs.
+
 ## 0.4.0
 
 - Upgrade AUTO by default: keep the main model fixed, independently judge child capability and reasoning investment, and enforce exact fresh-child bindings with persisted replay. Preserve explicit legacy rollback and MANUAL behavior.

package/README.md

@@ -2,8 +2,37 @@
 
 English · [简体中文](README.zh.md)
 
+![AUTO interaction: toggle AUTO/MANUAL and inspect the decision](docs/auto-routing.gif)
+
+*Interaction recording from the earlier four-tier UI (isolated mock Host); current decisions use independent capability and depth as described below.*
+
+[Repository](https://github.com/prgrmrwy/dsh-auto-model-routing) · [Releases](https://github.com/prgrmrwy/dsh-auto-model-routing/releases) · [npm](https://www.npmjs.com/package/dsh-auto-model-routing)
+
 <!-- problem -->
-Keep the main model you chose; let AUTO select reasoning investment for each turn and suitable resources for fresh sub-agents. Jev judges **capability and effort independently**. DSH applies the route, and the UI distinguishes a decision from a configuration that actually reached a request.
+**Add AUTO mode to DSH: automatic effort for the main agent, automatic model + effort for sub-agents.** Stop adjusting reasoning investment every turn or choosing a model for every delegated task.
+
+- **Main agent: keep your selected model and adjust reasoning effort per user turn.**
+- **Sub-agents: judge capability needs and reasoning investment independently, then select model + effort.** A stronger model does not automatically mean deeper reasoning.
+- **Visible decisions, local feedback:** inspect candidate distributions and actual application status, then rate the allocation below a reply.
+
+### Which DSH scenarios does AUTO cover?
+
+| Scenario | AUTO behavior | Current boundary |
+|---|---|---|
+| Main-agent user turn | Judge effort for each new user turn; keep the main model | Not rejudged at every tool step; model must support the effort |
+| Official fresh `subagent` | Select and bind child model + effort before its first request | Real Magpie Claude/GPT ordinary child calls verified; catalog and allowlist apply |
+| Official fresh `spawn_teammate` | Bind the new teammate's model + effort using the same policy | Mock-host coverage; real-provider teammate acceptance remains unverified |
+| Resume or continue a bound child | Replay its initial allocation without rejudging | Requires the plugin enabled and intact route records |
+| Explicit model / effort | Preserve the specified dimension; judge only the other | Both specified: validate without calling Jev |
+| Fork, third-party or unbound creation paths | No automatic-allocation guarantee | Fork and unbound AUTO child paths are explicitly rejected, not silently replaced |
+
+This describes official integration paths—not acceptance of every DSH entry point, CLI/TUI interface or third-party plugin. The Web UI is the currently verified interface. MANUAL makes no new judgments. `route_subagent` is a preview, not a required step before dispatch.
+
+### Local feedback → future learning and adjustment
+
+**Available now:** rate a decision-bound reply as appropriate, too high, too low or unknown; change or clear the rating. Feedback and decision snapshots stay on your machine. Submitting feedback does not upload it to the decision service or immediately change routing; AUTO task judgments themselves still use your selected external service.
+
+**Planned direction:** add learning, evaluation and policy adjustment based on local feedback and execution outcomes, so AUTO can better fit your tasks. **Automatic learning and feedback-driven tuning are not implemented yet.** Today's records support later evaluation; they are not evidence of measured quality gains or cost savings.
 
 **Install.** Tested with DSH `0.2.0-rc.2`, Web UI, Node.js `>=22.19`.
 
@@ -13,7 +42,7 @@ dsh plugin --profile web add dsh-auto-model-routing
 dsh plugin --profile web add prgrmrwy/dsh-auto-model-routing
 ```
 
-Restart DSH and refresh the Web page. In **Settings → 自动模型路由**, choose a decision service, save its API key, and use **测试连接** with a fixed public sample. New chats default to **MANUAL**; click the chip to use AUTO. The companion delegation skill is included—no separate skill installation is needed.
+Restart DSH and refresh the Web page. In **Settings → Auto model routing**, choose a decision service, save its API key, and use **Test connection** with a fixed public sample. These are English descriptions of the controls; the plugin's interface labels are currently in Chinese. New chats default to **MANUAL**; click the chip to use AUTO. The companion delegation skill is included—no separate skill installation is needed.
 
 ## Use
 
@@ -22,11 +51,12 @@ Restart DSH and refresh the Web page. In **Settings → 自动模型路由**, ch
 | **AUTO / MANUAL chip**, left of the model picker | Click to switch. Hover for the decision, candidate distribution, certainty, model/effort and application status. |
 | **Decision hint** | Shows new decisions briefly; its Settings switch does not hide the hover panel. |
 | **Gauge button** below an eligible reply | Mark the allocation appropriate, too high, too low or unknown; change or clear your feedback later. Only replies bound to an applied main decision qualify. |
-| **Settings → 自动模型路由** | Choose service/model, manage its separate key, test the connection, set defaults/cap/deadline, or expand **查看决策策略** to inspect the actual rubric and model slots. |
+| **Settings → Auto model routing** | Choose service/model, manage its separate key, test the connection, set defaults/cap/deadline, or expand **View decision strategy** to inspect the actual rubric and model slots. |
 
 ### Main model stays fixed; children are selected separately
 
-- **Main chat:** `lower / baseline / higher` moves at most one supported effort step below/at/above the model's verified recommended starting point. The cap defaults to `xhigh`; AUTO never selects `max`. It does not change the main provider/model or write global model defaults.
+- **Main chat:** `lower / baseline / higher` moves at most one supported effort step below/at/above the model's verified recommended starting point. The cap defaults to `xhigh`; AUTO never selects `max`. It keeps the main provider/model and synchronizes the selected effort through official `selectModel`, which also saves global defaults.
+- **Claude/GPT families only:** AUTO manages models whose id (after any transport prefix) starts with `claude-` or `gpt-`. Selecting any other main model — DeepSeek, GLM, Grok, Gemini, Kimi, Qwen, … — switches the session to MANUAL and locks the chip: it shows an outlined info icon, and hovering the whole button explains the support scope with an issue/PR link to the repository. Switching back to a Claude/GPT model restores a clickable MANUAL chip; AUTO is never re-enabled automatically.
 - **Fresh children:** capability is `bounded / analytical / frontier`; effort is judged separately. Claude slots are Haiku / Sonnet / Opus 5.5; GPT slots are Luna / Sol / Sol. The current catalog, supported efforts and official child allowlist must all permit the route. Magpie uses its exact provider and full family-prefixed model IDs, not a fallback to local transports.
 - **Explicit choices win:** specifying a model or effort leaves only the other dimension to judge. Specifying both skips Jev and validates the route. Missing task scope stops delegation rather than guessing.
 - **Official creation binds the route:** fresh `subagent` and fresh `spawn_teammate` paths bind an exact child identity before its first request. `route_subagent` is an optional preview—not proof of application and not a user constraint to copy into a subsequent call. Fork and unbound creation paths are unsupported; there is no silent substitution.
@@ -45,6 +75,12 @@ Preset model menus expose documented versions, not live availability guarantees.
 
 **Certainty is not the selected probability.** Choice certainty is `(pmax − 1/n) / (1 − 1/n)`: with three candidates, a 70% top probability gives 55% certainty. The panel shows the service's returned certainty and full candidate distribution separately, including returned zeroes; missing values are marked unavailable. Neither number is task success rate.
 
+### Magpie transports and picker display
+
+The default policy accepts both exact transports, `dsh-magpie-connector` and `dsh-magpie-connect`. They are not aliases: full model ids, live model capabilities, supported effort/caps, the current allowlist and the parent's captured allowlist all retain their exact transport identity. Unknown families need an explicit model. With a root AUTO session and explicit `policy: legacy`, both Magpie previews reject before Jev; MANUAL still returns `routed: false` without judging or state writes. Already bound children replay their saved route.
+
+AUTO applies the selected effort to the current main request and awaits official `selectModel` on the same provider/model when the effort changes. This also updates global defaults; the official picker shows one effort value. MANUAL requests pass through unchanged and bound children never write the main selection. A selection-sync failure is logged while the current request retains its selected effort. Magpie menu grouping still requires ohmydsh's managed five-package Host extension; stock rc.2 keeps a flat list. See [Magpie setup and display requirements](<../dsh-magpie-connector/README.md#model-menu-groups-and-effort>); local tests do not establish deployment or live GUI acceptance.
+
 ## Good to know
 
 - **Failures are visible.** Main judgment failure disables AUTO with a reason; child judgment/route failure stops dispatch. No local classifier, automatic retry, upgrade or cross-service fallback.
@@ -54,16 +90,12 @@ Preset model menus expose documented versions, not live availability guarantees.
 - **Local state:** configuration is under `$DSH_HOME/plugins/dsh-auto-model-routing/`; mode, child routes and feedback are under `$DSH_HOME/state/auto-model-routing/`. Feedback stores resource metadata, IDs, versions, returned distributions and timestamps—not task/reply text. Request event IDs allow later usage correlation; costs are not fabricated when unavailable. See [feedback and evaluation](docs/feedback-evaluation.md).
 - **No automatic learning.** Human allocation feedback is observational. It does not change routing or prove quality/cost benefits. Old messages without decision bindings are not backfilled; old records with missing evaluation fields remain unknown.
 - **Upgrade:** existing AUTO sessions use the new policy without a version switch or rewriting their stored mode. New chats still default to MANUAL unless configured otherwise. Historical four-tier mappings remain only for explicit `policy: "legacy"` rollback in plugin configuration; they are not the current policy or feedback menu.
-
 ## Architecture
 <!-- section: architecture -->
 
-```text
-user turn → pre-step → selected Jev service → depth → main request effort
-fresh child creation → exact child binding → capability + depth → validated route
-request/header → configuration match → applied evidence
-assistant message → immutable decision snapshot → human feedback events
-```
+![AUTO architecture — independent judgments, validated requests and allocation feedback](docs/architecture-v2.en.svg)
+
+Main failures disable AUTO; child failures stop dispatch. Explicit model/effort constraints are preserved. The diagram shows the AUTO paths; MANUAL makes no new judgments and fork is unsupported. Feedback does not automatically alter routing.
 
 Entry: [index.ts](src/index.ts). Enforcement: [policy-host.ts](src/policy-host.ts). Actual rubric: [policy-v2-rubric.json](src/policy-v2-rubric.json). Model slots: [policy-v2.ts](src/policy-v2.ts). UI: [client](src/client/index.ts). Coverage and limitations: [development verification](docs/policy-v2-development.md), [real Magpie acceptance](docs/magpie-live-acceptance.md).
 
@@ -72,11 +104,9 @@ Entry: [index.ts](src/index.ts). Enforcement: [policy-host.ts](src/policy-host.t
 
 These isolated-host recordings use mock Jev/model responses and show the previous UI, not the current default policy.
 
-![Legacy AUTO effort adjustment demo](docs/auto-routing.gif)
 ![Legacy four-tier routing settings](docs/settings.gif)
 
 </details>
-
 ## Development
 
 ```sh
@@ -85,7 +115,9 @@ npm run typecheck
 npm run build
 ```
 
-Tests use the official AgentLoop with fake LLM streams and mock/loopback Jev responses, not paid model calls. `scripts/label-report.mjs` reports **legacy tier labels only**; it is not a report for new allocation feedback. Evaluation schema and deduplication rules are in [feedback-evaluation.md](docs/feedback-evaluation.md).
+Tests use the official AgentLoop with fake LLM streams and mock/loopback Jev responses, not paid model calls. `scripts/label-report.mjs` reports **legacy tier labels only**. To observe AUTO decisions and their actual token usage, ask the agent to use the `auto-model-routing-report` skill (on demand only; it runs the read-only `lib/usage-report.js`). It is observational, not a savings measurement. Evaluation schema and deduplication rules are in [feedback-evaluation.md](docs/feedback-evaluation.md).
+
+Development stays in the source monorepo; this repository is its release mirror. The package builds and loads independently using its declared dependencies, bundled skill and official DSH services; no monorepo checkout or monorepo instruction file is required. External design references are optional background, not runtime inputs.
 
 The [current specification](https://github.com/prgrmrwy/ohmydsh/blob/main/openspec/specs/auto-model-routing/spec.md) lives in the source monorepo. The bundled [delegation skill](skills/subagent-model-routing/SKILL.md) supplies guidance; enforcement belongs to the official host hooks, not the prompt. No measured task-quality or token-savings claim is made.
 

package/README.zh.md

@@ -2,8 +2,37 @@
 
 [English](README.md) · 简体中文
 
+![AUTO 交互：切换 AUTO/MANUAL 并查看决策](docs/auto-routing.gif)
+
+*此交互录屏来自早期四档界面（隔离 mock 宿主）；当前策略按下文独立判断能力与投入。*
+
+[插件仓库](https://github.com/prgrmrwy/dsh-auto-model-routing) · [版本发布](https://github.com/prgrmrwy/dsh-auto-model-routing/releases) · [npm](https://www.npmjs.com/package/dsh-auto-model-routing)
+
 <!-- problem -->
-主模型由你选，AUTO 为每轮选择推理投入，并为 fresh 子任务选配资源。Jev **独立判断能力需求和投入**，DSH 验证并应用配置；界面区分“做出了判断”和“实际请求已生效”。
+**为 DSH 增加 AUTO 模式：主 Agent 自动调 effort，子 Agent 自动选 model + effort。** 不必每轮手动选择推理投入，也不必为每个子任务手动挑模型。
+
+- **主 Agent：保留你选择的模型，按回合调整推理投入（effort）。**
+- **子 Agent：按任务独立判断能力需求与推理投入，选择模型与 effort。** 不是把“更强模型”和“更深推理”捆成一个档位。
+- **看得见、能反馈：** 展示决策分布与实际生效状态，在回复下方提交本机分配反馈。
+
+### AUTO 覆盖哪些 DSH 场景？
+
+| 场景 | AUTO 的作用 | 当前边界 |
+|---|---|---|
+| 主 Agent 用户回合 | 每个新用户回合判断 effort，主模型不换 | 不逐工具步骤重判；模型必须支持相应 effort |
+| 官方 fresh `subagent` | 首次请求前选择并绑定子 model + effort | 真实 Magpie Claude/GPT 普通子调用已验证；受目录和允许列表约束 |
+| 官方 fresh `spawn_teammate` | 按同一策略绑定新 teammate 的 model + effort | 已有 mock 宿主覆盖，尚未完成真实模型 teammate 验收 |
+| 已绑定子实例恢复或继续执行 | 重用初始路线，不重新分配 | 依赖插件保持启用及路由记录完整 |
+| 显式指定 model / effort | 保留已指定维度，仅判断未指定维度 | 两者都指定则只校验，不调用 Jev |
+| fork、第三方或未绑定创建路径 | 不承诺自动选配 | fork 与未绑定 AUTO 子路径会明确拒绝，不静默替代 |
+
+这里是官方接入路径的覆盖说明，不代表所有 DSH 入口、CLI/TUI 界面或第三方插件都已验收。Web UI 是当前验证入口；MANUAL 不做新判断。`route_subagent` 仅预览，不是必须先调用的派发步骤。
+
+### 本机反馈 → 未来的学习调整
+
+**现在：** 在已绑定决策的回复下评价“合适 / 投入偏高 / 投入不足 / 无法判断”，可修改、撤销。反馈与决策快照保存在本机，不会因点击反馈而上传到决策服务，也不会立即改变路由；AUTO 任务判断本身仍按所选服务外发。
+
+**未来方向：** 增加基于本机反馈与执行结果的学习、评估和策略调整，让 AUTO 更贴合你的任务。**尚未实现自动学习或反馈驱动调参**，目前记录用于后续评估，不承诺已证明的质量提升或成本节省。
 
 **安装**：已验证 DSH `0.2.0-rc.2`、Web UI，Node.js `>=22.19`。
 
@@ -26,7 +55,8 @@ dsh plugin --profile web add prgrmrwy/dsh-auto-model-routing
 
 ### 主模型不换，子任务独立选配
 
-- **主会话**：`lower / baseline / higher` 相对于具体模型已验证的推荐起点，在受支持序列降低一档、保持或提高一档。缺省上限 `xhigh`，自动不选 `max`；不修改主 provider/model，也不改写全局模型默认值。
+- **主会话**：`lower / baseline / higher` 相对于具体模型已验证的推荐起点，在受支持序列降低一档、保持或提高一档。缺省上限 `xhigh`，自动不选 `max`；主 provider/model 不变；通过官方 `selectModel` 同步选定 effort，同时保存全局默认值。
+- **仅支持 Claude / GPT 系列**：AUTO 只管理模型名（去掉 transport 前缀后）以 `claude-` 或 `gpt-` 开头的主模型。切换到其他主模型（DeepSeek、GLM、Grok、Gemini、Kimi、Qwen 等）会自动落为 MANUAL 并锁定芯片：芯片显示描边 info 图标，悬停整个按钮说明支持范围并提供仓库的 issue/PR 链接。切回 Claude / GPT 系列后芯片恢复可点击且保持 MANUAL，不会自动重新启用 AUTO。
 - **fresh 子任务**：能力需求为 `bounded / analytical / frontier`，推理投入独立判断。Claude 能力槽为 Haiku / Sonnet / Opus 5.5；GPT 为 Luna / Sol / Sol。实际路由必须同时满足当前目录、支持的 effort 和官方子智能体允许列表。Magpie 保留真实 provider 与家族前缀完整模型 ID，不回退到本地入口。
 - **尊重显式选择**：只指定模型或投入时，仅判断另一维；两者都指定则不请求 Jev，只校验路由。缺少任务目标或范围时停止委派，不猜。
 - **官方创建绑定路由**：fresh `subagent` 和 fresh `spawn_teammate` 在子任务首次请求前绑定精确身份。`route_subagent` 只是可选预览，不代表已应用，也不能把推荐复制成用户约束。fork 和未绑定创建路径暂不支持，不静默替换。
@@ -45,6 +75,12 @@ dsh plugin --profile web add prgrmrwy/dsh-auto-model-routing
 
 **判定确定度不等于选中概率**：Choice 公式为 `(pmax − 1/n) / (1 − 1/n)`，三个候选中最高概率 70% 对应确定度 55%。面板分别显示服务返回的确定度和完整分布，保留返回的 0%，缺值标未提供。两者都不是任务成功率。
 
+### Magpie transport 与选择器展示
+
+默认策略接受 `dsh-magpie-connector`、`dsh-magpie-connect` 两个精确 transport，不互为 alias：完整 model id、实时模型能力、支持 effort/cap、当前允许列表与父 captured allowlist 都按原 transport 校验。未知家族需显式 model。根会话 AUTO 且显式 `policy: legacy` 时，两种 Magpie 预览均在 Jev 前拒绝；MANUAL 仍直接返回 `routed: false`，不判档、不写状态。已绑定子实例恢复原路线。
+
+AUTO 将选定 effort 应用于本次主请求；effort 改变时，等待官方 `selectModel` 同步同一 provider/model，并允许保存全局默认值。官方选择器只显示一个 effort。MANUAL 请求原样通过，已绑定子会话不写主选择；同步失败会记录告警，本次请求仍保留选定 effort。Magpie 菜单分组仍需 ohmydsh 受管五包 Host 扩展，stock rc.2 保持 flat 列表。见 [Magpie 配置与展示前提](<../dsh-magpie-connector/README.zh.md#模型菜单分组与-effort>)；本地测试不等于已部署或 live GUI 验收。
+
 ## 须知
 
 - **失败可见**：主判断失败会停用 AUTO 并显示原因，子判断或路由失败则停止派发。没有本地分类器、自动重试、自动升级或跨服务降级。
@@ -58,12 +94,9 @@ dsh plugin --profile web add prgrmrwy/dsh-auto-model-routing
 ## 架构
 <!-- section: architecture -->
 
-```text
-用户回合 → pre-step → 所选 Jev 服务 → depth → 主请求 effort
-fresh 子创建 → 精确身份绑定 → capability + depth → 校验路由
-request/header → 配置匹配 → applied 证据
-assistant 消息 → 不可变决策快照 → 人工反馈事件
-```
+![AUTO 架构：独立判断、请求校验与分配反馈](docs/architecture-v2.zh.svg)
+
+主判断失败停用 AUTO，子失败停止派发；保留显式 model/effort。图示为 AUTO 路径，MANUAL 不做新判断，fork 暂不支持。反馈不会自动改变路由。
 
 入口：[index.ts](src/index.ts)。执行接入：[policy-host.ts](src/policy-host.ts)。实际判据：[policy-v2-rubric.json](src/policy-v2-rubric.json)。模型槽：[policy-v2.ts](src/policy-v2.ts)。界面：[client](src/client/index.ts)。覆盖边界：[开发验证](docs/policy-v2-development.md)、[真实 Magpie 验收](docs/magpie-live-acceptance.md)。
 
@@ -72,11 +105,9 @@ assistant 消息 → 不可变决策快照 → 人工反馈事件
 
 下列隔离宿主录屏使用模拟 Jev/模型响应，展示旧界面，不代表当前默认策略。
 
-![旧版 AUTO 推理强度调整](docs/auto-routing.gif)
 ![旧版四档路由设置](docs/settings.gif)
 
 </details>
-
 ## 开发验证
 
 ```sh
@@ -85,7 +116,9 @@ npm run typecheck
 npm run build
 ```
 
-测试使用官方 AgentLoop、假 LLM 流和 mock/回环 Jev，不产生真实模型费用。`scripts/label-report.mjs` **仅汇总旧四档标注**，不是新分配反馈报表；新数据结构与去重口径见[feedback-evaluation.md](docs/feedback-evaluation.md)。
+测试使用官方 AgentLoop、假 LLM 流和 mock/回环 Jev，不产生真实模型费用。`scripts/label-report.mjs` **仅汇总旧四档标注**。如需观察 AUTO 决策及实际 token 用量，请明确让 agent 使用 `auto-model-routing-report` skill（仅按需调用，运行只读的 `lib/usage-report.js`）；它是观察统计，不衡量节省；新数据结构与去重口径见[feedback-evaluation.md](docs/feedback-evaluation.md)。
+
+继续在主仓开发，本仓库仅作发布镜像。插件使用自身声明的依赖、包内 skill 和官方 DSH 服务即可独立构建与加载，不要求检出主仓，也不要求安装主仓环境指令。外部设计链接仅供背景阅读，不是运行输入。
 
 [当前规范](https://github.com/prgrmrwy/ohmydsh/blob/main/openspec/specs/auto-model-routing/spec.md)在源码 monorepo 中维护。包内[委派 skill](skills/subagent-model-routing/SKILL.md)提供指引，执行保障来自官方宿主钩子，而不是提示词。暂无完整任务质量或 token 节省的量化结论。
 

package/docs/architecture-v2.en.json

@@ -0,0 +1,26 @@
+{
+ "schema_version":1,"diagram_type":"architecture",
+ "meta":{"title":"AUTO resource allocation","output":".archify/architecture-auto-routing-20261026-014646/auto-routing.html","locale":"en","quality_profile":"showcase","repository":{"url":"git@github.com:prgrmrwy/ohmydsh.git","revision":"79f9eab467047e054a2d66f8bce060834a261a2a","link_mode":"local-only"}},
+ "components":[
+ {"id":"turn","type":"frontend","label":"AUTO user turn","sublabel":"Main model stays fixed","pos":[40,80],"size":[190,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":68,"end_line":88}]},
+ {"id":"judge","type":"cloud","label":"Selected Jev service","sublabel":"Depth / capability independently","pos":[360,80],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/decision-service.ts","line":1,"end_line":23},{"path":"packages/auto-model-routing/src/policy-host.ts","line":81,"end_line":88}]},
+ {"id":"route","type":"backend","label":"Validated allocation","sublabel":"Catalog / allowlist / effort cap","pos":[710,80],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":122,"end_line":150}]},
+ {"id":"child","type":"backend","label":"Fresh child binding","sublabel":"Exact child identity; explicit wins","pos":[360,270],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":94,"end_line":132}]},
+ {"id":"request","type":"backend","label":"Official model request","sublabel":"Main effort / child full route","pos":[710,270],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":138,"end_line":160}]},
+ {"id":"persist","type":"database","label":"Persisted child route","sublabel":"Resume keeps initial allocation","pos":[40,270],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":132,"end_line":160}]},
+ {"id":"evidence","type":"backend","label":"Request match evidence","sublabel":"Applied only when config matches","pos":[710,460],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":178,"end_line":201}]},
+ {"id":"feedback","type":"frontend","label":"Decision and reply feedback","sublabel":"Observe allocation; never auto-train","pos":[360,460],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":162,"end_line":174}]},
+ {"id":"snapshot","type":"database","label":"Bound decision snapshot","sublabel":"Metadata / IDs; no task text","pos":[40,460],"size":[220,68],"sources":[{"path":"packages/auto-model-routing/src/policy-host.ts","line":167,"end_line":172}]}
+ ],
+ "connections":[
+ {"id":"main-judge","from":"turn","to":"judge","label":"depth"},
+ {"id":"judge-route","from":"judge","to":"route","label":"decision"},
+ {"id":"child-judge","from":"child","to":"judge","label":"task","fromSide":"top","toSide":"bottom"},
+ {"id":"child-store","from":"child","to":"persist","label":"bind"},
+ {"id":"route-request","from":"route","to":"request","label":"apply"},
+ {"id":"request-match","from":"request","to":"evidence","label":"header"},
+ {"id":"match-feedback","from":"evidence","to":"feedback","label":"matched"},
+ {"id":"feedback-snapshot","from":"feedback","to":"snapshot","label":"bind reply"}
+ ],
+ "cards":[{"dot":"cyan","title":"Decision services","items":["OpenRouter / TypeSafe / Concentrate / custom System One","No automatic service fallback or retry"]},{"dot":"amber","title":"Boundaries","items":["MANUAL: no new judgments; explicit constraints preserved","Fork unsupported; applied is not task success"]}]
+}