@takk/bayesoutputgate 1.0.0

package/CHANGELOG.md

@@ -0,0 +1,92 @@
+# Changelog
+
+All notable changes to `@takk/bayesoutputgate` are documented in this file.
+
+The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). Every entry carries a UTC timestamp.
+
+## [1.0.0] - 2026-06-23T22:58:26Z
+
+Initial stable release. A universal, zero-runtime-dependency NPM library and CLI for calibrated output validation with the Bayes Factor, the validation layer for Massive Intelligence (IM) systems and non-human entities (NHEs). Feed the per-dimension quality scores of an output, from an LLM-as-judge, a classifier, or a regex; BayesOutputGate weighs a high-quality hypothesis against a low-quality one, computes the Bayes Factor between them, interprets it on the Jeffreys scale, and returns a calibrated pass, fail, or escalate decision, the principled answer to "is this output good enough to ship" instead of an arbitrary threshold.
+
+### Added
+
+#### The calibrated Beta engine
+
+- Beta model (`@takk/bayesoutputgate/beta`): `BetaModel`, a calibrated Beta distribution over a quality score in [0, 1] that both Bayes Factor modes are built on. It is fit from labeled scores by method of moments, regularized by a prior Beta treated as pseudo-observations carrying the prior's own mean and variance, and updated online from sufficient statistics, so a cold model returns its prior and a warm model is data-driven. `fromSamples`, `fromSnapshot`, `observe`, `params`, `mean`, `logDensity`, and `snapshot` make it serializable across processes.
+
+#### Hypotheses and likelihoods
+
+- Hypothesis manager (`@takk/bayesoutputgate/hypothesis`): `HypothesisManager` keeps a high-quality and a low-quality `BetaModel` per dimension plus a weight, calibrated from labeled observations and updatable online. The weakly-informative defaults, Beta(2, 1) for high and Beta(1, 2) for low with only a few pseudo-observations of concentration, let labeled data dominate quickly. `models()` snapshots the calibration as the dimension models the Bayes Factor consumes.
+- Likelihoods (`@takk/bayesoutputgate/likelihood`): `logScoreLikelihood` (the Beta log-density of a continuous score), `logBinaryMarginalLikelihood` (the Beta-Binomial marginal for binary pass/fail outcomes), `toScoreMap`, and `logVectorLikelihood` (the weighted per-dimension log-likelihood of a score vector under one hypothesis, with a matched-dimension count).
+
+#### The Bayes Factor and the decision policy
+
+- Bayes Factor (`@takk/bayesoutputgate/bayesfactor`): `bayesFactor` computes the combined natural-log Bayes Factor in favor of high quality as the weighted sum of per-dimension Beta log-density differences, over the dimensions that have both a score and a model, with boundary scores clamped inward so a 0 or 1 never produces a non-finite density. `jeffreysStrength` maps the log-Bayes-Factor to a seven-way Jeffreys-scale category using the symmetric boundaries 3, 10, and 100 (Kass and Raftery, 1995).
+- Decision policy (`@takk/bayesoutputgate/policy`): `decide` and `posteriorHighQuality`. The Bayes Factor policy passes at or above `passAbove`, fails at or below `failBelow`, and escalates in between. The decision-theoretic policy converts the Bayes Factor to a posterior probability of high quality through an explicit prior (posterior log-odds equal log-Bayes-Factor plus prior log-odds, via a numerically stable logistic), then chooses the action that minimizes expected loss under the asymmetric costs of a false pass, a false fail, and escalation, which makes the gate utility-aware rather than a re-skinned threshold.
+
+#### Trust diagnostics
+
+- Dependence diagnostic (`@takk/bayesoutputgate/dimensions`): `dependenceDiagnostic` measures pairwise Pearson correlation between dimensions across a history of score vectors and flags pairs at or above a threshold, because correlated dimensions double-count evidence and inflate the Bayes Factor. It surfaces whether the conditional-independence assumption behind the summed log-Bayes-Factors is safe.
+- Calibration measurement (`@takk/bayesoutputgate/calibration`): `goodnessOfFit` (the Kolmogorov-Smirnov statistic of observed scores against a fitted Beta, with an asymptotic critical value), `brierScore`, `expectedCalibrationError`, `reliability`, and `assessAssumptions` (the per-dimension fit and the dependence diagnostic combined into one report the gate guards consult). Goodness-of-fit comes first, because if the Beta assumption fails the Bayes Factor is optimizing the wrong model; decision calibration then measures whether the posterior probabilities match realized outcomes. Calibration is measured, never asserted.
+
+#### The gate, the audit trail, and the tool
+
+- Gate orchestrator (`@takk/bayesoutputgate/gate`): `evaluate` ties the calibrated models, the Bayes Factor, and the policy into one call returning a `GateDecision`. `OutputGate` wraps fixed models and a fixed policy. `OutputGateMonitor` wraps the same pipeline with a tamper-evident audit chain and online recalibration: it seals each decision, folds labeled outcomes back into the calibration, and returns the sealed chain.
+- Assumption guards (`GateGuards`, `AssumptionReport`): `evaluate`, `OutputGate`, and `OutputGateMonitor` accept guards that escalate to human review rather than trusting a Bayes Factor from a misspecified model. With `requireGoodnessOfFit` or `requireIndependence`, a violated assumption forces the action to `escalate` with rationale `"assumption-violated"`, and the report is attached to every `GateDecision`. The monitor reassesses the report from the history on each batch `fit`.
+- Tamper-evident audit trail (`@takk/bayesoutputgate/audit`): an append-only `AuditChain` with a SHA-256 hash chain you `append` to and `verifyChain`, plus `sha256Hex` and `GENESIS_HASH`. Each entry hashes its canonical JSON with the previous entry's hash, so any later edit breaks every link after it. It uses the Web Crypto API, not `node:crypto`, so the surface stays node-free, and timestamps are caller-supplied so hashing is deterministic.
+- Tool adapter (`@takk/bayesoutputgate/adapter`): `bayesOutputGateTool`, `runTool`, and `describeTool`, a framework-agnostic tool definition (name `bayes_output_gate`, description, JSON Schema, handler) matching what MCP servers and LLM tool-calling APIs expect, so a non-human entity (NHE) can validate its own output before acting. Input arriving from a model is parsed defensively and the output is made JSON-safe.
+
+#### Persistence and CLI
+
+- `@takk/bayesoutputgate/node` ships `readJsonFile`, `loadLabeledObservations`, `parseCsvScores`, and `loadScores` over `node:fs`, defensively validated, and re-exports the full core. It is the only entry point that touches a Node built-in.
+- Binary `bayesoutputgate` exposed via `package.json#bin`. `bayesoutputgate gate` fits from labeled history and decides each output, `bayes-factor` computes the Bayes Factor against explicit dimension models, `calibrate` reports goodness-of-fit per dimension and the dependence diagnostic, and `audit-verify` checks a sealed decision chain. Flags `--pass-above`, `--fail-below`, and `--json`. Single-process exit codes: 0 ok, 2 usage or input error, 30 a fail decision, 40 an escalate decision, 20 a broken audit chain.
+
+#### Distribution
+
+- Thirteen entry points, each a subpath export with split `import`/`require` conditions: the root facade plus `beta`, `hypothesis`, `likelihood`, `bayesfactor`, `dimensions`, `policy`, `calibration`, `gate`, `audit`, `adapter`, `node`, and `edge`.
+- Dual ESM + CJS bundles built with tsup 8 in a single neutral-platform pass, with separate `.d.ts` and `.d.cts` type files per entry point, and the CLI shebang preserved from source.
+- Node-free, platform-neutral core importable in Node, edge runtimes, and the browser; `@takk/bayesoutputgate/edge` re-exports it verbatim, audit trail included, since Web Crypto is present there too.
+- Zero required runtime dependencies. `@takk/keymesh` and `@takk/modelchain` are optional peer dependencies, integration points the core takes no dependency on.
+
+#### Documentation and project site
+
+- A complete project site (`index.html`, `404.html`) and documentation set (`README.md`, `SPEC.md`, `SECURITY.md`, `PRIVACY.md`, `CLA.md`, `CODE_OF_CONDUCT.md`, `.github/CONTRIBUTING.md`, `.github/RELEASING.md`), with five JSON-LD structured-data blocks, an Open Graph card, a bespoke hero diagram that traces the flow from per-dimension scores through the Bayes Factor and the Jeffreys scale to a pass, fail, or escalate decision sealed in the audit trail, and a robots and sitemap pair. Every claim is phrased honestly: the Bayes Factor is calibrated from the user's own labeled data, the goodness-of-fit and dependence checks are diagnostics the caller inspects, the gate returns a recommendation an orchestrator consumes rather than acting itself, and "calibrated" is backed by the metrics the library measures.
+
+#### Examples and benchmark
+
+- Five runnable, offline, deterministic examples under `examples/`, executed end-to-end against the compiled `dist`: the basic gate, the decision-theoretic policy, the assumption guards, the MCP tool adapter, and node-free edge usage with a verifiable audit chain.
+- A value benchmark (`benchmarks/value.ts`) executed against the compiled `dist`, scoring the gate against fairly-tuned fixed thresholds (on the mean and on the min of two dimensions) on a held-out test set the gate never calibrates on, under an asymmetric loss (false pass 10, false fail 2, escalation 1), with a "masking" low-quality output that scores high on factuality but low on safety. When the Beta assumption holds, the calibrated multi-dimension gate cuts average loss to 0.456 against the best tuned threshold's 0.619 (accuracy 93.7% against 78.6%), escalating the ambiguous 23.7% to review. When the assumption is violated (a strongly bimodal score distribution), goodness-of-fit detects it, the gate keeps the lowest loss (0.869 against about 0.986) with zero false passes, and the goodness-of-fit guard escalates every output rather than acting on a model it knows is misspecified. The gate sustains roughly 2.7 million two-dimension decisions per second. Every number is from real execution, never invented.
+
+### Quality
+
+- 90 tests across 15 suites passing under Vitest 4, including the special functions verified against closed forms, the Beta-Binomial marginal verified against its uniform-prior identity, the calibrated Beta fit and online update, the Bayes Factor verified against the Jeffreys boundaries, the decision-theoretic policy verified against expected loss, the goodness-of-fit and dependence diagnostics, the assumption guards that escalate on a violated assumption, and the audit chain verified against a known SHA-256 digest and to detect tampering and broken links.
+- Coverage: statements 94.64%, branches 87.58%, functions 96.24%, lines 95.91%.
+- Lint clean under Biome 2.5. Typecheck clean under TypeScript 6 in maximum strict mode (`exactOptionalPropertyTypes`, `noUncheckedIndexedAccess`, `verbatimModuleSyntax`, `noPropertyAccessFromIndexSignature`, `isolatedModules`).
+- `publint` clean and `@arethetypeswrong/cli` green across all thirteen subpaths and `package.json`.
+- `size-limit` under budget on every bundle (brotli core facade 5.29 kB against an 8 kB limit, bayes factor 1.03 kB, gate 3.01 kB, edge barrel 5.29 kB, node entry 5.95 kB).
+- Distribution smoke test exercising the compiled ESM and CJS artifacts and every subpath, with the compiled CLI spawned as a single Node process. The full suite, the smoke test, and the CLI are re-verified on Node 24.
+
+### Security
+
+- Every release is published to the npm registry with `npm publish --provenance`, carrying a SLSA provenance attestation generated by GitHub Actions over OIDC. Consumers can verify with `npm view @takk/bayesoutputgate --json | jq .dist.attestations`.
+- Tamper-evident audit trail backed by a SHA-256 hash chain, suitable as compliance evidence (EU AI Act) that the recorded decisions were not altered after sealing. It is an integrity seal, not a signature.
+- Zero runtime dependencies, the smallest possible supply-chain surface. The node-free core uses the Web Crypto API, not `node:crypto`.
+
+### Licensing
+
+- Licensed under the Apache License, Version 2.0. The `NOTICE` file ships in the tarball alongside `LICENSE`.
+
+### Engines
+
+- Node `>=20.0.0`. Verified locally on Node 22 and Node 24; the continuous integration matrix covers Node 20, 22, and 24.
+
+## [Unreleased]
+
+Highlights queued for future releases:
+
+- A finer-grained, per-output adequacy signal, so the gate can escalate only the outputs a misspecified model is uncertain about rather than the whole stream.
+- Streaming and multi-rater score aggregation, with inter-annotator agreement.
+- Drift and change-point detection over the calibrated models, to flag a shift in the score regime before it costs quality.
+- Non-Beta score families (a calibrated mixture, a nonparametric density) for scores the Beta cannot fit.
+- Turnkey runtime integrations (MCP server, orchestrator hooks) that consume the gate decision and act on it.
+- Signed and timestamped audit seals for stronger third-party evidence.

package/LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for describing the origin of the Work and
+      reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may accept and charge a
+      fee for the acceptance of support, warranty, indemnity, or other
+      liability obligations and/or rights consistent with this License.
+      However, in accepting such obligations, You may act only on Your own
+      behalf and on Your sole responsibility, not on behalf of any other
+      Contributor, and only if You agree to indemnify, defend, and hold
+      each Contributor harmless for any liability incurred by, or claims
+      asserted against, such Contributor by reason of your accepting any
+      such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 David C Cavalcante
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/NOTICE

@@ -0,0 +1,45 @@
+@takk/bayesoutputgate
+Copyright 2026 David C Cavalcante (Takk Innovate Studio)
+
+This product includes software developed by David C Cavalcante
+(https://takk.ag, davcavalcante@proton.me).
+
+BayesOutputGate is a universal, zero-runtime-dependency library and CLI for
+calibrated output validation with the Bayes Factor. You feed the per-dimension
+quality scores of an output, from any scorer, and it weighs a high-quality
+hypothesis against a low-quality one, returns a calibrated pass, fail, or
+escalate decision on the Jeffreys scale, and seals the decision in a
+tamper-evident audit trail, for Massive Intelligence (IM) systems and non-human
+entities that must validate their own outputs before acting on them.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not
+use the software in this repository except in compliance with the License.
+A copy of the License is in the LICENSE file at the root of this repository,
+and is also available at:
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+────────────────────────────────────────────────────────────────────────────
+THIRD-PARTY COMPONENTS
+────────────────────────────────────────────────────────────────────────────
+
+BayesOutputGate has ZERO required runtime dependencies. Its core is node-free; the
+audit seal uses the Web Crypto API, not node:crypto. The @takk sibling packages
+(@takk/keymesh and @takk/modelchain) are OPTIONAL peer dependencies, resolved
+only when you compose with them, and each is distributed under the Apache
+License, Version 2.0.
+
+The core package pulls in none of the above. Only the @takk/bayesoutputgate/node
+entry point uses the Node standard library (node:fs and node:path) for reading
+labeled history and score vectors from disk.
+
+Development-only tooling (NOT shipped in the published package):
+
+  - tsup            MIT
+  - tsx             MIT
+  - vitest          MIT
+  - typescript      Apache-2.0
+  - @biomejs/biome  MIT OR Apache-2.0
+  - publint         MIT
+  - @arethetypeswrong/cli  MIT
+  - size-limit      MIT