@mcptoolshop/research-os 0.3.3 → 0.5.0

package/README.md

@@ -7,7 +7,7 @@
 </p>
 
 <p align="center">
-  <a href="https://github.com/mcp-tool-shop-org/research-os/releases/tag/v0.3.3"><img src="https://img.shields.io/badge/version-0.3.3-blue" alt="version 0.3.3"></a>
+  <a href="https://github.com/mcp-tool-shop-org/research-os/releases/tag/v0.5.0"><img src="https://img.shields.io/badge/version-0.5.0-blue" alt="version 0.5.0"></a>
   <a href="https://github.com/mcp-tool-shop-org/research-os/actions/workflows/ci.yml"><img src="https://github.com/mcp-tool-shop-org/research-os/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License"></a>
   <img src="https://img.shields.io/badge/node-%E2%89%A520-brightgreen" alt="Node ≥20">
@@ -149,8 +149,46 @@ This is the structural alternative to *search → summarize → pretty report*.
 
 `research-os` is a local-first CLI. It reads and writes files within the research-pack directory you point it at, and (when using `gather`) issues outbound HTTP requests to fetch source URLs you provide. It does not: run a server, accept inbound connections, store credentials, or send telemetry. No secrets are written to pack artifacts. See [SECURITY.md](SECURITY.md) for the vulnerability reporting policy.
 
+## Reviewer calibration
+
+v0.5.0 makes reviewer calibration durable. A reviewer profile is not trusted because
+it ran once; it earns a status through structured seeded-failure receipts and
+multi-run aggregation.
+
+**No profile is currently admitted as `trusted_baseline`.** The canonical receipts
+in the repo show `hermes-two-pass=failed`, `mistral-nemo-two-pass=conditional_pass`,
+`hermes-single-pass=comparison_only`. This is intentional: trust is earned through
+repeated seeded-failure evidence, not assumed.
+
+Calibration receipts live at `calibration/reviewer-profiles/<profile>/seeded-v1.{json,md}`.
+Each receipt records PASS/FAIL against seven bars, four status labels
+(`trusted_baseline`, `conditional_pass`, `failed`, `comparison_only`), and
+honestly discloses what the fixture cannot test (`needs_contradiction_mapping`
+is unreachable from `seeded-v1`). See [CHANGELOG.md](CHANGELOG.md).
+
+```bash
+# Single-run calibration (quick local check)
+node scripts/reviewer-calibration.mjs --model hermes3:8b --two-pass --profile hermes-two-pass
+
+# Multi-run aggregate calibration (canonical evidence — 3 runs, median-based PASS/FAIL)
+node scripts/reviewer-calibration.mjs --model hermes3:8b --two-pass --profile hermes-two-pass --runs 3
+
+# Promote a section's review — auto-populates calibration_summary from pack-relative receipt
+research-os review-promote 01-section --pack <pack> --profile hermes-two-pass
+```
+
+When `--runs <n>` is used, per-run receipts are written to `<profile>/runs/run-NNN.json`
+and an aggregate receipt (with median-based bars and recurring-failure detection) is written
+to `<profile>/seeded-v1.{json,md}`. The aggregate receipt carries `receipt_kind: 'aggregate'`
+to discriminate from single-run receipts. Single-run mode (`--runs 1` or omitted) preserves
+the existing direct-write behavior.
+
 ## Status
 
+**v0.5.0** — published to npm as `@mcptoolshop/research-os@0.5.0`, 2026-05-10. v0.5.0 makes reviewer calibration durable. A reviewer profile is not trusted because it ran once; it earns a status through structured seeded-failure receipts and multi-run aggregation. Ships: structured calibration receipt schema (`seeded-v1.{json,md}`, Zod-validated, four status labels); multi-run harness (`--runs <n>`, per-run isolation, median-based PASS/FAIL bars, recurring-failure demotion); architecture-aware decision-vocab bar; pack-relative receipt lookup in `review-promote`. **No trusted baseline admitted:** `hermes-two-pass=failed` (aggregate, 3 runs), `mistral-nemo-two-pass=conditional_pass`, `hermes-single-pass=comparison_only`. research-os can now refuse to trust a reviewer profile when repeated seeded failures do not support trust. **No gate, freeze, or synthesis-law changes. All four frozen packs verify-pack byte-identically.** 671/671 vitest passing. See [CHANGELOG.md](CHANGELOG.md).
+
+**v0.4.0** — published to npm as `@mcptoolshop/research-os@0.4.0`, 2026-05-10. v0.4.0 makes source identity durable. Deterministic source-type rules handle the repeatable majority, override ledgers preserve operator corrections across re-gather, and `source-card audit` replaces scratch-script drift checks with a first-class CLI surface. Ships: centralized source-type classifier (Component B — `classifySourceType`, 11 canonical vendors, `source-type-rules.json`); source-card override ledger (Component A — `source-card-overrides.jsonl`, `validate` + `list` subcommands); and source-card audit CLI (Component D — `research-os source-card audit --pack <dir>`, 7 finding kinds, JSON + Markdown artifacts, `--apply --from` apply path). F-46 cosmetic fix: pack manifests now stamp the live binary version rather than the version frozen into `research.yaml` at pack-init. **No gate, freeze, or synthesis-law changes. All four existing frozen packs verify-pack byte-identically.** 620/620 vitest passing. See [CHANGELOG.md](CHANGELOG.md) and the [source-card audit handbook page](https://mcp-tool-shop-org.github.io/research-os/handbook/source-card-audit/).
+
 **v0.3.3** — published to npm as `@mcptoolshop/research-os@0.3.3`, 2026-05-10. Ships gate-semantics clarity earned by Pack-3 (Godot export/runtime durability, Experiment 3 pack #3 of 3). Gate output now carries section-scoped publisher + primary counts alongside pack-wide counts (F-43); `no_source_cluster_monopoly` reworded from WARN to informational diagnostic (F-41). **Pass/fail behavior unchanged; existing frozen packs verify-pack byte-identically.** 570/570 vitest passing. See [CHANGELOG.md](CHANGELOG.md) and [`docs/section-scoped-waivers.md`](docs/section-scoped-waivers.md).
 
 **v0.3.2** — published to npm as `@mcptoolshop/research-os@0.3.2`, 2026-05-09. Ships normalized accepted-claim accounting for `pack publish` admission. The strict equality check between `claim-reviews.jsonl` and `pack-audit.json::accepted_claims` is replaced with an effective-set comparison — accepted claims are unique `claim_id`s whose latest canonical review decision is `accepted_for_synthesis` (latest-decision-wins per `claim_id`). Frozen packs whose legacy audit count differs from the effective set now admit with a warning rather than refusing; the legacy audit file is preserved verbatim (Law 15) while the archive manifest reflects the normalized count. Refusal stays hard for phantom claim_ids, incompatible duplicate decisions, and non-synthesis-eligible gates. Earned by Experiment 3 XRPL pack Session K — pack publish refused on a real closure-ledger seam disagreement (Section 07 had 24 raw `accepted_for_synthesis` rows but only 19 unique `claim_id`s due to overlapping reviewer windows). 558/558 vitest passing. See [CHANGELOG.md](CHANGELOG.md) and [`docs/pack-publish.md`](docs/pack-publish.md).

package/README.pt-BR.md

@@ -7,7 +7,7 @@
 </p>
 
 <p align="center">
-  <a href="https://github.com/mcp-tool-shop-org/research-os/releases/tag/v0.3.3"><img src="https://img.shields.io/badge/version-0.3.3-blue" alt="version 0.3.3"></a>
+  <a href="https://github.com/mcp-tool-shop-org/research-os/releases/tag/v0.5.0"><img src="https://img.shields.io/badge/version-0.5.0-blue" alt="version 0.5.0"></a>
   <a href="https://github.com/mcp-tool-shop-org/research-os/actions/workflows/ci.yml"><img src="https://github.com/mcp-tool-shop-org/research-os/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License"></a>
   <img src="https://img.shields.io/badge/node-%E2%89%A520-brightgreen" alt="Node ≥20">
@@ -149,8 +149,33 @@ Esta é a alternativa estrutural para *pesquisar → resumir → gerar relatóri
 
 `research-os` é uma ferramenta de linha de comando que opera localmente. Ela lê e grava arquivos dentro do diretório do pacote de pesquisa que você especificar e, quando usa o comando `gather`, faz solicitações HTTP para buscar URLs de origem que você fornecer. Ela não: executa um servidor, aceita conexões de entrada, armazena credenciais ou envia dados de telemetria. Nenhum segredo é gravado nos arquivos do pacote. Consulte [SECURITY.md](SECURITY.md) para a política de relatório de vulnerabilidades.
 
+## Calibração de revisores
+
+A versão v0.5.0 torna a calibração de revisores mais robusta. Um perfil de revisor não é considerado confiável apenas porque foi executado uma vez; ele adquire um status através de relatórios estruturados de falhas simuladas e agregação de múltiplas execuções.
+
+**Atualmente, nenhum perfil é considerado como "baseline confiável".** Os relatórios canônicos no repositório mostram `hermes-two-pass=failed`, `mistral-nemo-two-pass=conditional_pass`, `hermes-single-pass=comparison_only`. Isso é intencional: a confiança é conquistada através de evidências repetidas de falhas simuladas, e não é presumida.
+
+Os relatórios de calibração estão localizados em `calibration/reviewer-profiles/<perfil>/seeded-v1.{json,md}`. Cada relatório registra PASS/FAIL em relação a sete critérios, quatro rótulos de status (`trusted_baseline`, `conditional_pass`, `failed`, `comparison_only`), e revela honestamente o que o teste não consegue verificar (`needs_contradiction_mapping` é inacessível a partir de `seeded-v1`). Consulte [CHANGELOG.md](CHANGELOG.md).
+
+```bash
+# Single-run calibration (quick local check)
+node scripts/reviewer-calibration.mjs --model hermes3:8b --two-pass --profile hermes-two-pass
+
+# Multi-run aggregate calibration (canonical evidence — 3 runs, median-based PASS/FAIL)
+node scripts/reviewer-calibration.mjs --model hermes3:8b --two-pass --profile hermes-two-pass --runs 3
+
+# Promote a section's review — auto-populates calibration_summary from pack-relative receipt
+research-os review-promote 01-section --pack <pack> --profile hermes-two-pass
+```
+
+Quando `--runs <n>` é usado, os relatórios de cada execução são gravados em `<perfil>/runs/run-NNN.json` e um relatório agregado (com critérios baseados na mediana e detecção de falhas recorrentes) é gravado em `<perfil>/seeded-v1.{json,md}`. O relatório agregado contém `receipt_kind: 'aggregate'` para diferenciá-lo dos relatórios de execução única. O modo de execução única (`--runs 1` ou omitido) preserva o comportamento de gravação direta existente.
+
 ## Status
 
+**v0.5.0** — publicado no npm como `@mcptoolshop/research-os@0.5.0`, 10 de maio de 2026. A versão v0.5.0 torna a calibração de revisores mais robusta. Um perfil de revisor não é considerado confiável apenas porque foi executado uma vez; ele adquire um status através de relatórios estruturados de falhas simuladas e agregação de múltiplas execuções. Inclui: esquema de relatório de calibração estruturado (`seeded-v1.{json,md}`, validado com Zod, quatro rótulos de status); sistema de execução de múltiplas execuções (`--runs <n>`, isolamento por execução, critérios PASS/FAIL baseados na mediana, detecção de falhas recorrentes); critério de avaliação baseado na arquitetura; pesquisa de relatórios relativa ao pacote em `review-promote`. **Nenhum baseline confiável admitido:** `hermes-two-pass=failed` (agregado, 3 execuções), `mistral-nemo-two-pass=conditional_pass`, `hermes-single-pass=comparison_only`. O research-os agora pode recusar a confiança em um perfil de revisor quando falhas simuladas repetidas não suportam a confiança. **Nenhuma alteração nos gates, congelamentos ou leis de síntese. Todos os quatro pacotes congelados verificam a identidade dos bytes.** 671/671 testes vitest aprovados. Consulte [CHANGELOG.md](CHANGELOG.md).
+
+**v0.4.0** — Publicada no npm como `@mcptoolshop/research-os@0.4.0`, 10 de maio de 2026. A versão 0.4.0 garante a durabilidade da identidade da fonte. Regras determinísticas para o tipo de fonte lidam com a maioria repetível, os registros de substituição preservam as correções do operador durante a re-coleta, e o comando `source-card audit` substitui as verificações de derivação de scripts por uma interface de linha de comando (CLI) completa. Inclui: um classificador centralizado de tipo de fonte (Componente B — `classifySourceType`, 11 fornecedores padrão, `source-type-rules.json`); um registro de substituição de cartão de fonte (Componente A — `source-card-overrides.jsonl`, subcomandos `validate` e `list`); e uma CLI para auditoria de cartão de fonte (Componente D — `research-os source-card audit --pack <dir>`, 7 tipos de detecção, artefatos JSON + Markdown, opções `--apply --from` para aplicar o caminho). Correção estética F-46: os arquivos de manifesto agora indicam a versão binária em execução, em vez da versão fixada no arquivo `research.yaml` durante a inicialização da criação do pacote. **Não há alterações nas regras de validação, congelamento ou síntese. Todos os quatro pacotes existentes passam na verificação de integridade byte a byte.** 620/620 testes vitest aprovados. Consulte o arquivo [CHANGELOG.md](CHANGELOG.md) e a página do manual de auditoria de cartão de fonte: [https://mcp-tool-shop-org.github.io/research-os/handbook/source-card-audit/](https://mcp-tool-shop-org.github.io/research-os/handbook/source-card-audit/).
+
 **v0.3.3** — Publicado no npm como `@mcptoolshop/research-os@0.3.3`, 10 de maio de 2026. Inclui melhorias na clareza da semântica das "gates" obtidas com o Pack-3 (durabilidade da exportação/runtime do Godot, Experimento 3, pacote nº 3 de 3). A saída da "gate" agora inclui contadores específicos da seção, além dos contadores globais (F-43); a mensagem `no_source_cluster_monopoly` foi alterada de um aviso para um diagnóstico informativo (F-41). **O comportamento de aprovação/reprovação não foi alterado; os pacotes congelados existentes são verificados byte a byte.** 570/570 testes do vitest passaram. Consulte o arquivo [CHANGELOG.md](CHANGELOG.md) e o arquivo [`docs/section-scoped-waivers.md`](docs/section-scoped-waivers.md).
 
 **v0.3.2** — Publicado no npm como `@mcptoolshop/research-os@0.3.2`, 09 de maio de 2026. Inclui a normalização das reivindicações aceitas, levando em consideração a aprovação para publicação do pacote. A verificação estrita de igualdade entre `claim-reviews.jsonl` e `pack-audit.json::accepted_claims` foi substituída por uma comparação de conjuntos efetivos — as reivindicações aceitas são os `claim_id`s únicos cuja última decisão de revisão canônica é "aceita para síntese" (a última decisão prevalece para cada `claim_id`). Pacotes congelados cuja contagem de auditoria legada difere do conjunto efetivo agora são aceitos com um aviso, em vez de serem rejeitados; o arquivo de auditoria legada é preservado integralmente (Lei 15), enquanto o manifesto do arquivo reflete a contagem normalizada. A rejeição permanece intransigente para `claim_id`s inexistentes, decisões duplicadas incompatíveis e restrições não elegíveis para síntese. Obtido através do Experimento 3 XRPL pack Session K — a publicação do pacote foi rejeitada devido a uma divergência real no registro de fechamento (a Seção 07 continha 24 linhas brutas de "aceito para síntese", mas apenas 19 `claim_id`s únicos devido a janelas de revisores sobrepostas). 558/558 testes vitest passaram. Consulte [CHANGELOG.md](CHANGELOG.md) e [`docs/pack-publish.md`](docs/pack-publish.md).

package/README.zh.md

@@ -7,7 +7,7 @@
 </p>
 
 <p align="center">
-  <a href="https://github.com/mcp-tool-shop-org/research-os/releases/tag/v0.3.3"><img src="https://img.shields.io/badge/version-0.3.3-blue" alt="version 0.3.3"></a>
+  <a href="https://github.com/mcp-tool-shop-org/research-os/releases/tag/v0.5.0"><img src="https://img.shields.io/badge/version-0.5.0-blue" alt="version 0.5.0"></a>
   <a href="https://github.com/mcp-tool-shop-org/research-os/actions/workflows/ci.yml"><img src="https://github.com/mcp-tool-shop-org/research-os/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License"></a>
   <img src="https://img.shields.io/badge/node-%E2%89%A520-brightgreen" alt="Node ≥20">
@@ -149,8 +149,33 @@ discover
 
 `research-os` 是一个本地优先的命令行工具。它在您指定的“研究包”目录中读取和写入文件，并在使用 `gather` 命令时，会向外部发送 HTTP 请求以获取您提供的来源 URL。它不会：运行服务器、接受传入连接、存储凭据或发送遥测数据。任何敏感信息都不会写入到包文件中。请参阅 [SECURITY.md](SECURITY.md)，了解漏洞报告政策。
 
+## 评审员校准
+
+v0.5.0版本使评审员校准更加可靠。评审员配置文件不会因为只运行一次而被信任，而是通过结构化的、带有预设错误的测试结果和多次运行的聚合来获得信任状态。
+
+**目前没有任何配置文件被认为是`trusted_baseline`（可信基线）。** 仓库中的标准测试结果显示`hermes-two-pass=failed`（失败），`mistral-nemo-two-pass=conditional_pass`（条件通过），`hermes-single-pass=comparison_only`（仅供比较）。这是有意为之：信任是通过反复的、带有预设错误的结果来获得的，而不是默认信任。
+
+校准结果文件位于`calibration/reviewer-profiles/<profile>/seeded-v1.{json,md}`。每个结果文件记录了针对七个方面的PASS/FAIL（通过/失败）结果，四个状态标签（`trusted_baseline`、`conditional_pass`、`failed`、`comparison_only`），并诚实地披露了测试框架无法测试的内容（`needs_contradiction_mapping`无法从`seeded-v1`访问）。请参阅[CHANGELOG.md](CHANGELOG.md)。
+
+```bash
+# Single-run calibration (quick local check)
+node scripts/reviewer-calibration.mjs --model hermes3:8b --two-pass --profile hermes-two-pass
+
+# Multi-run aggregate calibration (canonical evidence — 3 runs, median-based PASS/FAIL)
+node scripts/reviewer-calibration.mjs --model hermes3:8b --two-pass --profile hermes-two-pass --runs 3
+
+# Promote a section's review — auto-populates calibration_summary from pack-relative receipt
+research-os review-promote 01-section --pack <pack> --profile hermes-two-pass
+```
+
+当使用`--runs <n>`参数时，每个运行的结果文件会被写入到`<profile>/runs/run-NNN.json`，并且会生成一个聚合结果文件（包含基于中位数的PASS/FAIL结果，以及重复失败检测），写入到`<profile>/seeded-v1.{json,md}`。聚合结果文件包含`receipt_kind: 'aggregate'`，用于区分单次运行的结果文件。单次运行模式（`--runs 1`或省略）会保留现有的直接写入行为。
+
 ## 状态
 
+**v0.5.0** — 发布到npm，版本号为`@mcptoolshop/research-os@0.5.0`，发布日期：2026-05-10。v0.5.0版本使评审员校准更加可靠。评审员配置文件不会因为只运行一次而被信任，而是通过结构化的、带有预设错误的测试结果和多次运行的聚合来获得信任状态。包含：结构化的校准结果模式（`seeded-v1.{json,md}`，经过Zod验证，包含四个状态标签）；多运行测试框架（`--runs <n>`，每个运行隔离，基于中位数的PASS/FAIL结果，重复失败降级）；能够感知架构的决策词汇表；在`review-promote`中进行包相关的结果文件查找。**没有可信的基线：** `hermes-two-pass=failed`（聚合，3次运行），`mistral-nemo-two-pass=conditional_pass`，`hermes-single-pass=comparison_only`。research-os现在可以拒绝信任评审员配置文件，当反复的、带有预设错误的测试结果不支持信任时。**没有对网关、冻结或合成规则的更改。所有四个现有的冻结包都以字节级别的相同方式进行验证。** 671/671个vitest测试通过。请参阅[CHANGELOG.md](CHANGELOG.md)。
+
+**v0.4.0** — 发布到npm，版本号为`@mcptoolshop/research-os@0.4.0`，发布日期：2026-05-10。v0.4.0版本使源代码身份更加可靠。基于确定性的源代码类型规则处理可重复的多数情况，覆盖账本保留了操作员的更正，并且`source-card audit`（源代码卡审计）取代了对临时脚本漂移的检查，提供了一个一流的命令行界面。包含：集中式的源代码类型分类器（组件B — `classifySourceType`，11个标准供应商，`source-type-rules.json`）；源代码卡覆盖账本（组件A — `source-card-overrides.jsonl`，`validate` + `list`子命令）；以及源代码卡审计命令行界面（组件D — `research-os source-card audit --pack <dir>`，7种发现类型，JSON + Markdown格式，`--apply --from`用于应用路径）。F-46：一个小的修复，现在包清单会记录实际的二进制版本，而不是冻结在`research.yaml`中的版本，该版本在包初始化时被冻结。**没有对网关、冻结或合成规则的更改。所有四个现有的冻结包都以字节级别的相同方式进行验证。** 620/620个vitest测试通过。请参阅[CHANGELOG.md](CHANGELOG.md)以及[源代码卡审计手册页面](https://mcp-tool-shop-org.github.io/research-os/handbook/source-card-audit/)。
+
 **v0.3.3** — 已发布到 npm，版本号为 `@mcptoolshop/research-os@0.3.3`，发布日期：2026年5月10日。此版本改进了“门”机制的语义清晰度，这是Pack-3（Godot导出/运行时稳定性，实验3的第3个包）所取得的成果。现在，“门”的输出结果除了包含整个包的计数外，还包含按“门”划分的发布者和主要计数（F-43）；`no_source_cluster_monopoly` 的警告信息已更改为信息性诊断信息（F-41）。**通过/失败的行为未改变；现有的冻结包在字节级别上进行验证。** 570/570 个 vitest 测试通过。请参阅 [CHANGELOG.md](CHANGELOG.md) 和 [`docs/section-scoped-waivers.md`](docs/section-scoped-waivers.md)。
 
 **v0.3.2** — 已发布到 npm，版本号为 `@mcptoolshop/research-os@0.3.2`，发布日期：2026年5月9日。此版本对“已接受的声明”进行了标准化处理，以适应“包发布”的流程。严格的 `claim-reviews.jsonl` 文件和 `pack-audit.json::accepted_claims` 之间的相等性检查已被替换为集合比较——已接受的声明是具有最新规范审查决策为 `accepted_for_synthesis` 的唯一 `claim_id`（`claim_id` 遵循“最新决策优先”原则）。对于那些其历史审计计数与集合比较结果不同的冻结包，现在会发出警告而不是拒绝；原始的审计文件将被完整保留（第15条规定），而归档清单会反映标准化后的计数。对于虚假 `claim_id`、不兼容的重复决策以及不符合合成条件的“门”，仍然会拒绝。这是 Experiment 3 XRPL pack Session K 的成果——由于实际的账本关闭时的差异，包发布被拒绝（第07部分有 24 行原始的 `accepted_for_synthesis` 数据，但由于审查窗口的重叠，只有 19 个唯一的 `claim_id`）。558/558 个 vitest 测试通过。请参阅 [CHANGELOG.md](CHANGELOG.md) 和 [`docs/pack-publish.md`](docs/pack-publish.md)。

package/dist/calibration/aggregate-receipt-schema.d.ts

@@ -0,0 +1,509 @@
+import { z } from 'zod';
+
+declare const AggregateMetricSchema: z.ZodObject<{
+    median: z.ZodNumber;
+    min: z.ZodNumber;
+    max: z.ZodNumber;
+    values: z.ZodArray<z.ZodNumber, "many">;
+}, "strip", z.ZodTypeAny, {
+    median: number;
+    min: number;
+    max: number;
+    values: number[];
+}, {
+    median: number;
+    min: number;
+    max: number;
+    values: number[];
+}>;
+declare const PerCategoryAggregateEntrySchema: z.ZodObject<{
+    median_ratio: z.ZodNumber;
+    min_ratio: z.ZodNumber;
+    max_ratio: z.ZodNumber;
+    total: z.ZodNumber;
+    per_run_ratios: z.ZodArray<z.ZodNumber, "many">;
+}, "strip", z.ZodTypeAny, {
+    median_ratio: number;
+    min_ratio: number;
+    max_ratio: number;
+    total: number;
+    per_run_ratios: number[];
+}, {
+    median_ratio: number;
+    min_ratio: number;
+    max_ratio: number;
+    total: number;
+    per_run_ratios: number[];
+}>;
+declare const PerCategoryAggregateSchema: z.ZodRecord<z.ZodString, z.ZodObject<{
+    median_ratio: z.ZodNumber;
+    min_ratio: z.ZodNumber;
+    max_ratio: z.ZodNumber;
+    total: z.ZodNumber;
+    per_run_ratios: z.ZodArray<z.ZodNumber, "many">;
+}, "strip", z.ZodTypeAny, {
+    median_ratio: number;
+    min_ratio: number;
+    max_ratio: number;
+    total: number;
+    per_run_ratios: number[];
+}, {
+    median_ratio: number;
+    min_ratio: number;
+    max_ratio: number;
+    total: number;
+    per_run_ratios: number[];
+}>>;
+declare const AggregatePassFailSchema: z.ZodObject<{
+    fp_ceiling: z.ZodEnum<["PASS", "FAIL"]>;
+    any_flag_recall_floor: z.ZodEnum<["PASS", "FAIL"]>;
+    per_category_any_flag_floor: z.ZodEnum<["PASS", "FAIL"]>;
+    strict_recall_floor: z.ZodEnum<["PASS", "FAIL"]>;
+    decision_vocab_completeness: z.ZodEnum<["PASS", "FAIL"]>;
+    latency_soft: z.ZodEnum<["PASS", "WARN"]>;
+    latency_hard: z.ZodEnum<["PASS", "FAIL"]>;
+    empty_or_malformed: z.ZodEnum<["PASS", "FAIL"]>;
+    overall: z.ZodEnum<["PASS", "FAIL"]>;
+}, "strip", z.ZodTypeAny, {
+    fp_ceiling: "PASS" | "FAIL";
+    any_flag_recall_floor: "PASS" | "FAIL";
+    per_category_any_flag_floor: "PASS" | "FAIL";
+    strict_recall_floor: "PASS" | "FAIL";
+    decision_vocab_completeness: "PASS" | "FAIL";
+    latency_soft: "PASS" | "WARN";
+    latency_hard: "PASS" | "FAIL";
+    empty_or_malformed: "PASS" | "FAIL";
+    overall: "PASS" | "FAIL";
+}, {
+    fp_ceiling: "PASS" | "FAIL";
+    any_flag_recall_floor: "PASS" | "FAIL";
+    per_category_any_flag_floor: "PASS" | "FAIL";
+    strict_recall_floor: "PASS" | "FAIL";
+    decision_vocab_completeness: "PASS" | "FAIL";
+    latency_soft: "PASS" | "WARN";
+    latency_hard: "PASS" | "FAIL";
+    empty_or_malformed: "PASS" | "FAIL";
+    overall: "PASS" | "FAIL";
+}>;
+declare const AggregateDecisionVocabBarSchema: z.ZodObject<{
+    architecture: z.ZodEnum<["single-pass", "two-pass"]>;
+    required: z.ZodNumber;
+    median_produced: z.ZodNumber;
+    passed: z.ZodBoolean;
+}, "strip", z.ZodTypeAny, {
+    required: number;
+    architecture: "single-pass" | "two-pass";
+    median_produced: number;
+    passed: boolean;
+}, {
+    required: number;
+    architecture: "single-pass" | "two-pass";
+    median_produced: number;
+    passed: boolean;
+}>;
+declare const AggregateCalibrationReceiptSchema: z.ZodObject<{
+    schema_version: z.ZodLiteral<1>;
+    receipt_kind: z.ZodLiteral<"aggregate">;
+    profile_name: z.ZodString;
+    status: z.ZodEnum<["trusted_baseline", "conditional_pass", "failed", "comparison_only"]>;
+    model: z.ZodString;
+    architecture: z.ZodEnum<["single-pass", "two-pass"]>;
+    fixture: z.ZodString;
+    fixture_total_claims: z.ZodNumber;
+    fixture_good_claims: z.ZodNumber;
+    fixture_bad_claims: z.ZodNumber;
+    runs_count: z.ZodNumber;
+    run_files: z.ZodArray<z.ZodString, "many">;
+    aggregated_at: z.ZodString;
+    research_os_version: z.ZodString;
+    good_fp_count: z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    any_flag_recall_ratio: z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    strict_recall_ratio: z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    decisions_produced_count: z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    runtime_ms: z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    empty_or_malformed_responses: z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    per_category_any_flag: z.ZodRecord<z.ZodString, z.ZodObject<{
+        median_ratio: z.ZodNumber;
+        min_ratio: z.ZodNumber;
+        max_ratio: z.ZodNumber;
+        total: z.ZodNumber;
+        per_run_ratios: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }>>;
+    per_category_strict: z.ZodRecord<z.ZodString, z.ZodObject<{
+        median_ratio: z.ZodNumber;
+        min_ratio: z.ZodNumber;
+        max_ratio: z.ZodNumber;
+        total: z.ZodNumber;
+        per_run_ratios: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }>>;
+    decision_vocabulary: z.ZodRecord<z.ZodString, z.ZodObject<{
+        median: z.ZodNumber;
+        min: z.ZodNumber;
+        max: z.ZodNumber;
+        values: z.ZodArray<z.ZodNumber, "many">;
+    }, "strip", z.ZodTypeAny, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>>;
+    decision_vocab_bar: z.ZodObject<{
+        architecture: z.ZodEnum<["single-pass", "two-pass"]>;
+        required: z.ZodNumber;
+        median_produced: z.ZodNumber;
+        passed: z.ZodBoolean;
+    }, "strip", z.ZodTypeAny, {
+        required: number;
+        architecture: "single-pass" | "two-pass";
+        median_produced: number;
+        passed: boolean;
+    }, {
+        required: number;
+        architecture: "single-pass" | "two-pass";
+        median_produced: number;
+        passed: boolean;
+    }>;
+    unreachable_decisions: z.ZodArray<z.ZodString, "many">;
+    pass_fail: z.ZodObject<{
+        fp_ceiling: z.ZodEnum<["PASS", "FAIL"]>;
+        any_flag_recall_floor: z.ZodEnum<["PASS", "FAIL"]>;
+        per_category_any_flag_floor: z.ZodEnum<["PASS", "FAIL"]>;
+        strict_recall_floor: z.ZodEnum<["PASS", "FAIL"]>;
+        decision_vocab_completeness: z.ZodEnum<["PASS", "FAIL"]>;
+        latency_soft: z.ZodEnum<["PASS", "WARN"]>;
+        latency_hard: z.ZodEnum<["PASS", "FAIL"]>;
+        empty_or_malformed: z.ZodEnum<["PASS", "FAIL"]>;
+        overall: z.ZodEnum<["PASS", "FAIL"]>;
+    }, "strip", z.ZodTypeAny, {
+        fp_ceiling: "PASS" | "FAIL";
+        any_flag_recall_floor: "PASS" | "FAIL";
+        per_category_any_flag_floor: "PASS" | "FAIL";
+        strict_recall_floor: "PASS" | "FAIL";
+        decision_vocab_completeness: "PASS" | "FAIL";
+        latency_soft: "PASS" | "WARN";
+        latency_hard: "PASS" | "FAIL";
+        empty_or_malformed: "PASS" | "FAIL";
+        overall: "PASS" | "FAIL";
+    }, {
+        fp_ceiling: "PASS" | "FAIL";
+        any_flag_recall_floor: "PASS" | "FAIL";
+        per_category_any_flag_floor: "PASS" | "FAIL";
+        strict_recall_floor: "PASS" | "FAIL";
+        decision_vocab_completeness: "PASS" | "FAIL";
+        latency_soft: "PASS" | "WARN";
+        latency_hard: "PASS" | "FAIL";
+        empty_or_malformed: "PASS" | "FAIL";
+        overall: "PASS" | "FAIL";
+    }>;
+    recurring_bar_failures: z.ZodArray<z.ZodString, "many">;
+    notes: z.ZodArray<z.ZodString, "many">;
+}, "strip", z.ZodTypeAny, {
+    status: "trusted_baseline" | "conditional_pass" | "failed" | "comparison_only";
+    architecture: "single-pass" | "two-pass";
+    schema_version: 1;
+    receipt_kind: "aggregate";
+    profile_name: string;
+    model: string;
+    fixture: string;
+    fixture_total_claims: number;
+    fixture_good_claims: number;
+    fixture_bad_claims: number;
+    runs_count: number;
+    run_files: string[];
+    aggregated_at: string;
+    research_os_version: string;
+    good_fp_count: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    any_flag_recall_ratio: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    strict_recall_ratio: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    decisions_produced_count: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    runtime_ms: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    empty_or_malformed_responses: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    per_category_any_flag: Record<string, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }>;
+    per_category_strict: Record<string, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }>;
+    decision_vocabulary: Record<string, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    decision_vocab_bar: {
+        required: number;
+        architecture: "single-pass" | "two-pass";
+        median_produced: number;
+        passed: boolean;
+    };
+    unreachable_decisions: string[];
+    pass_fail: {
+        fp_ceiling: "PASS" | "FAIL";
+        any_flag_recall_floor: "PASS" | "FAIL";
+        per_category_any_flag_floor: "PASS" | "FAIL";
+        strict_recall_floor: "PASS" | "FAIL";
+        decision_vocab_completeness: "PASS" | "FAIL";
+        latency_soft: "PASS" | "WARN";
+        latency_hard: "PASS" | "FAIL";
+        empty_or_malformed: "PASS" | "FAIL";
+        overall: "PASS" | "FAIL";
+    };
+    recurring_bar_failures: string[];
+    notes: string[];
+}, {
+    status: "trusted_baseline" | "conditional_pass" | "failed" | "comparison_only";
+    architecture: "single-pass" | "two-pass";
+    schema_version: 1;
+    receipt_kind: "aggregate";
+    profile_name: string;
+    model: string;
+    fixture: string;
+    fixture_total_claims: number;
+    fixture_good_claims: number;
+    fixture_bad_claims: number;
+    runs_count: number;
+    run_files: string[];
+    aggregated_at: string;
+    research_os_version: string;
+    good_fp_count: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    any_flag_recall_ratio: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    strict_recall_ratio: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    decisions_produced_count: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    runtime_ms: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    empty_or_malformed_responses: {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    };
+    per_category_any_flag: Record<string, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }>;
+    per_category_strict: Record<string, {
+        median_ratio: number;
+        min_ratio: number;
+        max_ratio: number;
+        total: number;
+        per_run_ratios: number[];
+    }>;
+    decision_vocabulary: Record<string, {
+        median: number;
+        min: number;
+        max: number;
+        values: number[];
+    }>;
+    decision_vocab_bar: {
+        required: number;
+        architecture: "single-pass" | "two-pass";
+        median_produced: number;
+        passed: boolean;
+    };
+    unreachable_decisions: string[];
+    pass_fail: {
+        fp_ceiling: "PASS" | "FAIL";
+        any_flag_recall_floor: "PASS" | "FAIL";
+        per_category_any_flag_floor: "PASS" | "FAIL";
+        strict_recall_floor: "PASS" | "FAIL";
+        decision_vocab_completeness: "PASS" | "FAIL";
+        latency_soft: "PASS" | "WARN";
+        latency_hard: "PASS" | "FAIL";
+        empty_or_malformed: "PASS" | "FAIL";
+        overall: "PASS" | "FAIL";
+    };
+    recurring_bar_failures: string[];
+    notes: string[];
+}>;
+type AggregateMetric = z.infer<typeof AggregateMetricSchema>;
+type PerCategoryAggregateEntry = z.infer<typeof PerCategoryAggregateEntrySchema>;
+type PerCategoryAggregate = z.infer<typeof PerCategoryAggregateSchema>;
+type AggregatePassFail = z.infer<typeof AggregatePassFailSchema>;
+type AggregateDecisionVocabBar = z.infer<typeof AggregateDecisionVocabBarSchema>;
+type AggregateCalibrationReceipt = z.infer<typeof AggregateCalibrationReceiptSchema>;
+
+export { type AggregateCalibrationReceipt, AggregateCalibrationReceiptSchema, type AggregateDecisionVocabBar, AggregateDecisionVocabBarSchema, type AggregateMetric, AggregateMetricSchema, type AggregatePassFail, AggregatePassFailSchema, type PerCategoryAggregate, type PerCategoryAggregateEntry, PerCategoryAggregateEntrySchema, PerCategoryAggregateSchema };