modelrig 0.0.1 → 0.2.0

package/CHANGELOG.md

@@ -0,0 +1,94 @@
+# Changelog
+
+All notable changes to the `modelrig` npm package are recorded here. The public
+surface is one thing with two halves — this package and the docs/registry site
+at [modelrig.dev](https://modelrig.dev). They ship together under one release
+ceremony (see `docs/ModelRig/oss-publish-policy.md`, §6). The generated docs
+carry an "as of modelrig vX.Y.Z" stamp so a reader can see when the docs and the
+published package diverge.
+
+This project adheres to [Semantic Versioning](https://semver.org/). Dates are
+UTC.
+
+## [0.2.0] — unreleased (staged for the R-A ceremony)
+
+- Ships the probed capability registry and leaderboard (`registry/registry.json`, `registry/leaderboard.json`) so a clean install routes on the probed profile instead of the static fallback (R-1 F2 ruling). The `modelrig-oracle` MCP server remains unreleased and is flagged as such in the docs.
+
+`0.1.0` was frozen on 2026-08-07 and shipped **dist-only** (`files: [dist,
+README, LICENSE]`). The SDK grew a large public surface across the following six
+weeks while the published artifact stood still, and one runtime dependency —
+`data/` — was never in the tarball at all. This release makes the published
+package match the workspace and self-tests that it does.
+
+### Fixed — packaging (the reason for this release)
+
+- **`data/` now ships.** `getPricing()` reads `data/pricing-map.json` (and the
+  optional `data/pricing-overlay.json`) from the package root at runtime, with
+  no `existsSync` guard — so on `0.1.0` the very first cost lookup threw
+  `ENOENT` on a clean `npm i modelrig`, breaking the flagship "effective cost"
+  story out of the box. `data` is now in the `files` allowlist. It is public
+  pricing data (CC BY 4.0; see `data/PROVENANCE.md`), safe to distribute.
+- **Regression pinned forever.** A new hermetic test (`npm pack` → install the
+  tarball into a temp dir → load the *installed* package) asserts
+  `getPricing()` returns a real rate and the `modelrig` bin runs. Packaging
+  breaks are now caught before publish, not by a customer.
+- **`modelrig --help` / `-h` / `help` exit 0** with usage on stdout (was: fell
+  through to the unknown-command path and exited 1).
+
+### Added — public API surface accumulated since 0.1.0
+
+None of the below existed in the published `0.1.0`; instructions written for the
+current docs failed against it with missing exports. They are all in this tag:
+
+- **Inspectable artifact store** — the `artifacts` namespace (runs → steps →
+  artifacts, lineaged and integrity-hashed), `resolveArtifactsConfig`,
+  per-artifact and per-run evaluation (`artifact.evaluate` / `run.evaluate`).
+- **Run verdicts** — the automatic deterministic `run-outcome@v1` on every run,
+  the explicit bounded model judge `run-judge@v1` (`modelrig judge <runId>`),
+  and the feedback protocol (`rig.feedback`, `POST /v1/feedback`,
+  `computeCoverage`).
+- **Cache accounting & routing** — cache-aware `estimateCostUsd` (cache-read
+  and cache-write buckets), `effectiveInputRate` / `classifyCacheVerdict`, the
+  `cache: auto` route directive with the miss-streak alert, and the customer
+  cache-handle pass-through `rig.run(task, { input, cache: { key, provider } })`
+  / `rig.runRaw({ …, cache: { key } })` (CE-1) — the customer owns the TTL
+  heartbeat; ModelRig never creates, refreshes, or deletes the resource.
+- **Observe / init (T0–T2)** — `modelrig observe` (scaffold the record-step seam
+  behind `MODELRIG_ARTIFACTS=1`, no route migration), `modelrig init --scope`
+  (draft a route bundle per call site), `modelrig validate` (keyless structural
+  check of `rig.yaml` + every bundle), and `modelrig verify-swap`
+  (shadow-equivalence report for a same-model swap).
+- **Route sampling params (CE-6)** — `policy.sampling: { temperature?, top_p?,
+  max_output_tokens? }` on a route, validated at load and sent to the provider
+  as declared; a sub-1.0 temperature on a Gemini-3 candidate loads with a
+  load-time advisory. **This is in the tag.**
+- **OTLP ingest** — bring your own traces (`normalizeOtlpTraces`,
+  `startOtlpEmitterIfConfigured`, the OTel semantic-convention map).
+- **Raw lane** (`runRaw` / `runRawStream`), streaming (`runStream`), the
+  grounding-inject rung, the `openai-compat` adapter host, and the Anthropic /
+  Grok adapters.
+- **Bake-offs & the optimization loop** — `runBakeoff`, `replayVariant`,
+  `computeProposal`, the Wilson-interval stats, the swap ledger + verified-
+  savings odometer, and the scheduled Rig Analyst Insights surface.
+
+### Fixed — behaviour
+
+- **H1 close-drain.** `rig.close()` now resolves only after the exporter's final
+  flush drains and after the artifacts streams drain (stores close last), so a
+  one-shot CLI or a serverless per-invocation `close()` can no longer lose the
+  last rows. One-shot callers **must** `await rig.close()`.
+
+### Notes
+
+- Requires **Node ≥ 20**. Installs a native module (`better-sqlite3`), so the
+  machine needs a build toolchain. Assumes a long-lived process with a writable
+  disk; serverless and edge callers: see the Runtime requirements section of the
+  [quickstart](https://modelrig.dev/quickstart.html).
+- Route output schemas validate under **JSON Schema 2020-12** (primary), with
+  **draft-07** also accepted. See the quickstart / route-bundles reference.
+
+## [0.1.0] — 2026-08-07
+
+Initial public release: capability-aware gateway, routes-as-code, provider
+adapters (Gemini / OpenAI / DeepSeek), typed failures, budget envelopes, and
+local-first SQLite telemetry.

package/LICENSE

@@ -0,0 +1,201 @@
+                                 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 reasonable and customary use in 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 choose to offer,
+      and charge a fee for, 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 ModelRig
+
+   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/README.md

@@ -1,12 +1,149 @@
-# ModelRig
+# modelrig
 
-**The capability-aware AI gateway. Rig it. Prove it. Sell it.**
+**A capability-aware AI gateway.** You declare a route — the shape of the
+answer you need and the set of models allowed to serve it — and ModelRig picks
+a model that can, validates what comes back, retries the right way when it
+doesn't, and records every attempt. Routes are code, failures are typed, and
+cost is capped by an envelope you set.
 
-This package name is reserved for ModelRig — probes of what every model can
-actually do, routes that call a task (not a model), and rails to meter and
-sell AI endpoints.
+- Node **≥ 20**
+- Works standalone with just a provider key. The hosted console, bake-offs, and
+  the model registry are an optional upgrade — see [Signing up](#what-you-get-by-signing-up).
 
-Full release coming soon.
+## Install
 
-- Website: [modelrig.ai](https://modelrig.ai)
-- Docs: [modelrig.dev](https://modelrig.dev)
+```bash
+npm i modelrig
+```
+
+> **Native dependency.** ModelRig writes one telemetry row to a local SQLite
+> file before each run returns, so a run never blocks on the network. That
+> buffer is `better-sqlite3`, a native module — prebuilt binaries cover
+> macOS and Linux on x64/arm64 (nearly everyone); an unusual platform will
+> compile it at install time and needs a C++ toolchain. Node ≥ 20 is assumed.
+
+## Quickstart
+
+This runs with **only a provider key** — no account, no signup.
+
+**1. Set a provider key** (any one your route allows):
+
+```bash
+export GEMINI_API_KEY=...       # or OPENAI_API_KEY, ANTHROPIC_API_KEY, …
+```
+
+**2. Define a route** at `modelrig/routes/example.support_summarize.yaml` (the
+example the package ships, in `modelrig/routes/`):
+
+```yaml
+route: example.support_summarize
+version: 1
+schema: ./schemas/support_summarize.schema.json  # JSON Schema (2020-12 recommended; draft-07 still accepted)
+candidates:                                      # THE candidate set — nothing else can serve
+  - provider: openai
+    model: gpt-5.4-mini
+  - provider: gemini
+    model: gemini-3.1-flash-lite
+  - provider: deepseek
+    model: deepseek-chat
+require: [schema_conformant]
+prefer: [cost]
+prompt:
+  system: ./prompts/support_summarize.system.md  # {{var}} + {{#if capability.X}} blocks
+  variables: [ticket, product, priorContext]
+policy:
+  retries: { content_invalid: 2, network: 4, capacity_shed: 3 }
+  timeout_ms: 60000
+  tier: flex
+  json: native
+```
+
+**3. Call it:**
+
+```ts
+import { createRig, loadConfigFromEnv } from "modelrig";
+
+const rig = createRig(loadConfigFromEnv());        // keys from GEMINI_API_KEY etc.
+const result = await rig.run("example.support_summarize", {
+  input: { ticket, product, priorContext },        // template variables
+  tags: { run_id, step: "summarize" },
+  budget: { envelope: run_id },                    // hard-stop cost envelope
+});
+// result.output  — schema-validated JSON (ajv), regardless of serving model
+// result.meta    — servedCandidate, tokens (in/out/cached), cost, tiers,
+//                  validation status, attempts by failure class
+rig.close();
+```
+
+**Data-governance routing (opt-in).** Add `zero_retention` to a route's
+`require`, or pass `zeroRetention: true` on a single `rig.run(...)` call, to
+route only to zero-retention–designated endpoints. It is a hard, opt-in filter
+that fails closed: if no candidate is designated zero-retention, the run raises
+the no-eligible-candidate error rather than dispatching to a retaining endpoint.
+(Capability gating is on by default here — unlike OpenRouter's opt-in
+`require_parameters`.)
+
+**Request-time routing controls (opt-in).** A single `rig.run(...)` call can
+narrow the candidate set: `maxPriceUsdPerMTok` drops any model over a price
+ceiling (unknown price + a ceiling → dropped, fail-closed), and
+`providers: { only, ignore }` restricts or excludes providers. `maxPrice` is a
+candidate *filter* (which models are eligible) — distinct from `budget.envelope`,
+which is a *spend cap* on the run's total cost; both compose, both fail closed on
+unpriced models.
+
+**Customer cache handle (opt-in).** If your code already engineered provider
+caching, carry it through: `rig.run(task, { input, cache: { key, provider } })`
+passes a customer-owned cache identifier (a Gemini `cachedContents/<id>`, or a
+`prompt_cache_key` value) verbatim to the matching-provider candidate. It wins
+over the route's `cache: auto` stamp, and a non-matching fallback dispatches
+without it. ModelRig carries the handle and prices the hits — it never creates,
+refreshes, or deletes the resource, so a long job needs your own TTL heartbeat
+(see the [caching lifecycle](https://modelrig.dev/caching-lifecycle.html) doc).
+The Lane-B `rig.runRaw({ provider, model, …, cache: { key } })` seam takes the
+same field.
+
+Every attempt is recorded in a local SQLite file (`.modelrig/telemetry.db`)
+tagged with your `tags`. Failures are typed —
+`RigFailureError.failure.class` is one of `content_invalid`, `capacity_shed`,
+`network`, `refusal`, `cache_invalid`, `timeout`, `budget_exhausted`,
+`invariant_violation` — with a separate retry budget per class, so a flaky
+network never spends your content-validation retries.
+
+## CLI
+
+The package ships a `modelrig` binary:
+
+```bash
+npx modelrig init         # scan a repo for provider call sites, scaffold routes
+npx modelrig bakeoff      # compare candidates on recorded inputs
+npx modelrig watch        # keep the pricing/capability registry current
+npx modelrig swap         # propose + actuate a candidate-set change (git-tracked)
+npx modelrig samples      # inspect recorded telemetry samples
+```
+
+`npx modelrig serve` (a thin HTTP wrapper over `rig.run`) lives in a separate
+package, `modelrig-server`; the CLI tells you so if it isn't installed.
+
+## What you get by signing up
+
+The gateway above is complete on its own. An account at
+[app.modelrig.ai](https://app.modelrig.ai) adds, as an upgrade — never a gate
+on the quickstart:
+
+- a **console** for telemetry, cost, and route health across your runs,
+- **bake-offs** and a maintained **model registry** (pricing + capabilities),
+- **hosted telemetry ingest** — set `MODELRIG_API_KEY=rig_sk_…` and the
+  exporter posts to the hosted API instead of writing only local SQLite.
+
+## Honest limits
+
+- **Prepaid balances and managed billing are not built yet.** This release is
+  the gateway and the self-host lane; the hosted control plane has one customer.
+- **`0.x` means the shape may still move.** Route and config contracts are
+  stable enough to build on, not frozen.
+- **`modelrig serve` needs the `modelrig-server` package** — it is not bundled
+  here.
+
+## License
+
+Apache-2.0. See [LICENSE](./LICENSE).

package/data/PROVENANCE.md

@@ -0,0 +1,19 @@
+# data/pricing-map.json — provenance
+
+Copied manually from `vendor/litellm-upstream/model_prices_and_context_window.json`
+at the pinned SHA recorded in `upstream/litellm.pin.json` (`de706a35a6`, pinned
+2026-07-30). 2,986 model entries at time of copy.
+
+Source: LiteLLM (https://github.com/BerriAI/litellm),
+Copyright (c) 2023 Berri AI, MIT License.
+
+NOTE (Phase 0 gap): the automated extraction script (`scripts/sync-upstream.ts`
+with provenance header + diff output) was not built before Phase 1 started, so
+this snapshot was copied by hand per implementation-plan §9. Replace this manual
+copy with the sync script's output when Phase 0 tooling lands; until then, any
+pin bump must re-copy this file and update this note.
+
+Key naming (verified against the snapshot):
+- Gemini API models: `gemini/<model>` (bare ids resolve to vertex_ai pricing — do not use)
+- OpenAI models: bare `<model>`
+- DeepSeek models: `deepseek/<model>` (bare ids also present)

package/data/pricing-manual.json

@@ -0,0 +1,22 @@
+{
+  "_provenance": {
+    "role": "Website-sourced per-token prices for hosts that do not expose pricing via an API our key can read (today: Fireworks — its /models listing rejects an inference-scoped key). Hand-read from the vendor's public model page, each entry carrying its source URL + read date. Merged into pricing-overlay.json by scripts/pricing-sweep.ts alongside the API-swept prices; both are gap-fillers beneath the pinned LiteLLM snapshot (snapshot wins on shared keys). Replace an entry here with an API/scraper adapter when one exists.",
+    "note": "Flat prices (input_cost_per_token / output / cache_read) are the BASE serverless standard rate. Serving-tier multipliers (Fireworks: +25% priority, +50% fast, +10% US-only) are now carried in the additive `pricing_v2` block (pricing-first-class spec) as MULTIPLIERS on base (1.25 / 1.5 / 1.1). Context-length/batch/modality bands are still uncaptured for this model and are absent (not guessed). The flat fields stay for backward compatibility."
+  },
+  "prices": {
+    "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+      "input_cost_per_token": 3.0e-6,
+      "output_cost_per_token": 1.5e-5,
+      "cache_read_input_token_cost": 3.0e-7,
+      "source": "fireworks-website:https://fireworks.ai/models/fireworks/kimi-k3 (base serverless standard; +25% priority / +50% fast / +10% US-only)",
+      "as_of": "2026-08-09",
+      "pricing_v2": {
+        "base": { "input": 3.0e-6, "output": 1.5e-5, "cache_read": 3.0e-7 },
+        "tiers": { "priority": 1.25, "fast": 1.5, "region_us": 1.1 },
+        "source": "fireworks-website:https://fireworks.ai/models/fireworks/kimi-k3",
+        "as_of": "2026-08-09",
+        "basis": "base serverless · standard tier · text"
+      }
+    }
+  }
+}