omegaprompt 2.0.0__tar.gz → 2.0.2__tar.gz

{omegaprompt-2.0.0 → omegaprompt-2.0.2}/.gitignore

@@ -38,6 +38,7 @@ ENV/
 
 # ── Packaging / tooling ──
 .uv/
+.uv-cache/
 pip-log.txt
 pip-delete-this-directory.txt
 

{omegaprompt-2.0.0 → omegaprompt-2.0.2}/CHANGELOG.md

@@ -6,6 +6,37 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [2.0.2] - 2026-06-08
+
+### Added
+
+- **Opt-in parallel item evaluation.** `CalibrateTuning.max_workers` (Python) / `--concurrency` (CLI) parallelize per-item target+judge evaluation within each candidate via a local `concurrent.futures.ThreadPoolExecutor`. Each item still runs its target call then its judge call sequentially, so the number of concurrent calls to any one provider never exceeds the configured value. Default `1` (serial) produces byte-identical artifacts to prior versions. Wall-clock speedup is bounded by — and conditional on — your provider account's concurrency ceiling (RPM/TPM): roughly ~50% at `2`, ~75% at `4`, ~85% at `8` when the account permits it, and **none** if the account effectively serializes calls. No cross-provider rate-limit handling; configure per your account (a value above your real ceiling produces 429s, not speedups).
+
+### Changed
+
+- **Best-candidate evaluation is memoized.** `PromptTarget.evaluate()` now caches results keyed on the resolved params, so the final best-candidate evaluation reuses the grid-search result instead of re-calling the providers. This reduces live API calls during `calibrate()`. No public-surface change (`EvalResult` / `CalibrationArtifact` / `CalibrableTarget` unchanged) and no artifact-schema change.
+
+### Notes
+
+- Package version is `2.0.2`; `CalibrationArtifact.schema_version` remains `2.0`. The omega-lock dependency pin remains `>=0.3.0,<0.4.0`.
+- Golden reference artifacts are **unchanged** — the deterministic harness uses fixed counts/latency and builds artifacts directly (not via `runtime.calibrate()`), so neither feature affects the golden hash.
+- This release-preparation change edits the working tree only; it does not publish to PyPI, push tags, or create/edit GitHub Releases.
+
+## [2.0.1] - 2026-06-07
+
+### Fixed
+
+- **omega-lock 0.3.0 compatibility.** omega-lock 0.3.0 renamed the target-result action count `n_trials` -> `sample_count` (KC-3 action floor) and reads `.sample_count` off the result `PromptTarget.evaluate` returns (in `stress.py`, `grid.py`, and `walk_forward.py`). `EvalResult` now exposes `sample_count` as a read-only property aliasing the stored `n_trials` field, so the calibration path no longer crashes with an `AttributeError` against the 0.3.0 seam. The stored field stays `n_trials`, so serialized artifacts and golden reference hashes are unchanged.
+
+### Added
+
+- **Consumer docking hardlock.** A fail-loud contract test (`tests/test_omega_lock_contract.py`) asserts the omega-lock dependency seam — the specific fields and call signatures omegaprompt consumes off omega-lock's result types — so a future producer-side rename fails LOUD (named, located, pre-merge) instead of surfacing as a silent mid-run `AttributeError`. A scheduled consumer canary workflow (`.github/workflows/omega-lock-compat.yml`) runs omegaprompt's own consumer contract and integration tests against `omega-lock@main`, ahead of the pinned release, so a producer rename of any consumed field is caught before omegaprompt bumps its pin. Isolated from the PR gate on purpose: it triggers only on a schedule / manual dispatch.
+
+### Notes
+
+- Package version is `2.0.1`; `CalibrationArtifact.schema_version` remains `2.0`. The omega-lock dependency pin remains `>=0.3.0,<0.4.0`.
+- This release-preparation change edits the working tree only; it does not publish to PyPI, push tags, or create/edit GitHub Releases.
+
 ## [2.0.0] - 2026-05-23
 
 ### Added

{omegaprompt-2.0.0 → omegaprompt-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: omegaprompt
-Version: 2.0.0
+Version: 2.0.2
 Summary: Provider-neutral prompt calibration engine with sensitivity-ranked meta-axes, hard-gate x soft-score fitness, walk-forward ship gates, guarded/expedition profiles, and explicit capability/risk reporting across Anthropic, OpenAI, Gemini, and local OpenAI-compatible backends. Optional sub-tools (mini-omega-lock, mini-antemortem-cli) distribute separately and plug in via the omegaprompt.preflight interface.
 Project-URL: Homepage, https://github.com/hibou04-ops/omegaprompt
 Project-URL: Repository, https://github.com/hibou04-ops/omegaprompt
@@ -213,7 +213,7 @@ License-File: AUTHORS.md
 License-File: LICENSE
 License-File: NOTICE
 Keywords: llm-as-judge,local-llm,overfitting,prompt-calibration,prompt-engineering,provider-neutral,walk-forward
-Classifier: Development Status :: 3 - Alpha
+Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -226,7 +226,7 @@ Classifier: Topic :: Software Development :: Quality Assurance
 Requires-Python: >=3.11
 Requires-Dist: anthropic>=0.40.0
 Requires-Dist: google-genai>=1.0.0
-Requires-Dist: omega-lock>=0.1.4
+Requires-Dist: omega-lock<0.4.0,>=0.3.0
 Requires-Dist: openai>=1.50.0
 Requires-Dist: pydantic>=2.6.0
 Requires-Dist: typer>=0.12.0
@@ -250,8 +250,8 @@ Description-Content-Type: text/markdown
 [![CI](https://github.com/hibou04-ops/omegaprompt/actions/workflows/ci.yml/badge.svg)](https://github.com/hibou04-ops/omegaprompt/actions/workflows/ci.yml)
 [![License: Apache 2.0](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
 [![Python](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org)
-[![PyPI](https://img.shields.io/badge/pypi-2.0.0-blue.svg)](https://pypi.org/project/omegaprompt/)
-[![Tests](https://img.shields.io/badge/tests-317%20passing-brightgreen.svg)](tests/)
+[![PyPI](https://img.shields.io/badge/pypi-2.0.2-blue.svg)](https://pypi.org/project/omegaprompt/)
+[![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg)](tests/)
 [![Artifact schema](https://img.shields.io/badge/artifact-schema%20v2.0-blueviolet.svg)](#8-the-calibrationartifact-schema-v20)
 [![MCP](https://img.shields.io/badge/MCP-server-blueviolet.svg)](#103-mcp-server-claude-code-cursor)
 [![Parent framework](https://img.shields.io/badge/framework-omega--lock-blueviolet.svg)](https://github.com/hibou04-ops/omega-lock)
@@ -298,7 +298,7 @@ pip install omegaprompt              # core
 pip install "omegaprompt[mcp]"       # + MCP server (Claude Code / Cursor)
 ```
 
-> **v2.0.0 (2026-05-23)** — Public README/PyPI-facing claims and exact deterministic reference metrics are tracked in the generated [claim ledger](https://github.com/hibou04-ops/omegaprompt/blob/main/docs/claims/README_CLAIMS.generated.md). Release gates cover repository consistency, generated claims, golden reference artifacts, artifact integrity, wheel smoke, and local/post-release verification.
+> **v2.0.2 (2026-06-08)** — **What's new:** **opt-in parallel item evaluation** — `--concurrency N` (CLI) / `CalibrateTuning(max_workers=N)` evaluates dataset items concurrently within each candidate via a local thread pool. Each item still runs its target and judge calls sequentially, so concurrent calls to any one provider never exceed N. The default (`1`) is serial and produces byte-identical artifacts to prior versions. Wall-clock speedup is **entirely conditional on your provider account's concurrency ceiling (RPM/TPM)**: roughly 50% at N=2 when the account permits it, and **zero** if your account effectively serializes calls. Also: `PromptTarget.evaluate()` is now **memoized by resolved params**, so the final best-candidate evaluation reuses the grid-search result instead of re-calling the providers — fewer live API calls during `calibrate()`, with no public-surface or artifact-schema change. omega-lock pin unchanged (`>=0.3.0,<0.4.0`); `CalibrationArtifact.schema_version` stays `2.0`; golden reference artifacts are unchanged. The project's PyPI Development Status is now **4 - Beta**. Public README/PyPI-facing claims and exact deterministic reference metrics are tracked in the generated [claim ledger](https://github.com/hibou04-ops/omegaprompt/blob/main/docs/claims/README_CLAIMS.generated.md). Release gates cover repository consistency, generated claims, golden reference artifacts, artifact integrity, wheel smoke, and local/post-release verification.
 
 <!-- public-claim-ledger:start -->
 > Claim evidence source: [docs/claims/public_claim_ledger.json](https://github.com/hibou04-ops/omegaprompt/blob/main/docs/claims/public_claim_ledger.json), rendered by `python tools/generate_readme_claims.py`.
@@ -1363,7 +1363,7 @@ Full changelog: [CHANGELOG.md](CHANGELOG.md).
 - **Train / test split with a pre-declared gate.** The foundational ML defence against overfitting, documented in every undergraduate curriculum. The specific implementation here (Pearson rank correlation threshold, pre-declared and unmodifiable) is `omega-lock`'s KC-4 kill criterion.
 - **LLM-as-judge.** Pattern formalised in *Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena* (Zheng et al., 2023). `omegaprompt` implements the pattern with schema enforcement at the SDK boundary (Pydantic via each vendor's native parse path) so malformed judge responses raise before polluting the fitness.
 - **Winchester defence.** A quant-finance discipline: *kill criteria declared before the run cannot be relaxed after.* Used here to argue that `--max-gap` and `--min-kc4` must be enforced in configuration, not retroactively tuned on inspection of scores.
-- **Sensitivity-driven coordinate descent.** Stress measurement and top-K unlock are the parameter-calibration primitives introduced by `omega-lock` (v0.1.4), originally for trading-strategy calibration, ported here to prompt configuration.
+- **Sensitivity-driven coordinate descent.** Stress measurement and top-K unlock are the parameter-calibration primitives introduced by `omega-lock` (v0.3.0), originally for trading-strategy calibration, ported here to prompt configuration.
 - **Antemortem discipline.** The pre-implementation reconnaissance methodology under which this project was designed and built. Every non-trivial change runs through [`antemortem-cli`](https://github.com/hibou04-ops/antemortem-cli) before the first keystroke. The case studies in the [methodology repository](https://github.com/hibou04-ops/Antemortem) record the recon for this codebase.
 
 Naming: *omega-lock* (parameter calibration) → *omegaprompt* (prompt calibration). The family branding is intentional. `omega-lock` was extracted from a trading-strategy calibration that ended in `KC-4 FAIL` — the overfitting defence firing exactly as designed. `omegaprompt` is the same defence applied one layer up, and the sub-tools `mini-omega-lock` / `mini-antemortem-cli` extend the pattern to preflight measurement.
@@ -1776,7 +1776,7 @@ Every override carries its `parameter`, `default`, `applied`, and `reason`. The
 Short form:
 
 ```
-omegaprompt v1.0.0 — provider-neutral prompt calibration engine.
+omegaprompt v2.0.2 — provider-neutral prompt calibration engine.
 https://github.com/hibou04-ops/omegaprompt, 2026.
 ```
 
@@ -1788,7 +1788,7 @@ BibTeX:
   title   = {{omegaprompt}: Provider-neutral prompt calibration engine
              with sensitivity-ranked meta-axes, walk-forward ship gates,
              and structural capability reporting},
-  version = {1.0.0},
+  version = {2.0.2},
   year    = {2026},
   url     = {https://github.com/hibou04-ops/omegaprompt}
 }
@@ -1798,7 +1798,7 @@ BibTeX:
   title   = {{omega-lock}: Sensitivity-driven coordinate-descent
              calibration framework with walk-forward validation and
              pre-declared kill criteria},
-  version = {0.1.4},
+  version = {0.3.0},
   year    = {2026},
   url     = {https://github.com/hibou04-ops/omega-lock}
 }

{omegaprompt-2.0.0 → omegaprompt-2.0.2}/README.md

@@ -5,8 +5,8 @@
 [![CI](https://github.com/hibou04-ops/omegaprompt/actions/workflows/ci.yml/badge.svg)](https://github.com/hibou04-ops/omegaprompt/actions/workflows/ci.yml)
 [![License: Apache 2.0](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
 [![Python](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org)
-[![PyPI](https://img.shields.io/badge/pypi-2.0.0-blue.svg)](https://pypi.org/project/omegaprompt/)
-[![Tests](https://img.shields.io/badge/tests-317%20passing-brightgreen.svg)](tests/)
+[![PyPI](https://img.shields.io/badge/pypi-2.0.2-blue.svg)](https://pypi.org/project/omegaprompt/)
+[![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg)](tests/)
 [![Artifact schema](https://img.shields.io/badge/artifact-schema%20v2.0-blueviolet.svg)](#8-the-calibrationartifact-schema-v20)
 [![MCP](https://img.shields.io/badge/MCP-server-blueviolet.svg)](#103-mcp-server-claude-code-cursor)
 [![Parent framework](https://img.shields.io/badge/framework-omega--lock-blueviolet.svg)](https://github.com/hibou04-ops/omega-lock)
@@ -53,7 +53,7 @@ pip install omegaprompt              # core
 pip install "omegaprompt[mcp]"       # + MCP server (Claude Code / Cursor)
 ```
 
-> **v2.0.0 (2026-05-23)** — Public README/PyPI-facing claims and exact deterministic reference metrics are tracked in the generated [claim ledger](https://github.com/hibou04-ops/omegaprompt/blob/main/docs/claims/README_CLAIMS.generated.md). Release gates cover repository consistency, generated claims, golden reference artifacts, artifact integrity, wheel smoke, and local/post-release verification.
+> **v2.0.2 (2026-06-08)** — **What's new:** **opt-in parallel item evaluation** — `--concurrency N` (CLI) / `CalibrateTuning(max_workers=N)` evaluates dataset items concurrently within each candidate via a local thread pool. Each item still runs its target and judge calls sequentially, so concurrent calls to any one provider never exceed N. The default (`1`) is serial and produces byte-identical artifacts to prior versions. Wall-clock speedup is **entirely conditional on your provider account's concurrency ceiling (RPM/TPM)**: roughly 50% at N=2 when the account permits it, and **zero** if your account effectively serializes calls. Also: `PromptTarget.evaluate()` is now **memoized by resolved params**, so the final best-candidate evaluation reuses the grid-search result instead of re-calling the providers — fewer live API calls during `calibrate()`, with no public-surface or artifact-schema change. omega-lock pin unchanged (`>=0.3.0,<0.4.0`); `CalibrationArtifact.schema_version` stays `2.0`; golden reference artifacts are unchanged. The project's PyPI Development Status is now **4 - Beta**. Public README/PyPI-facing claims and exact deterministic reference metrics are tracked in the generated [claim ledger](https://github.com/hibou04-ops/omegaprompt/blob/main/docs/claims/README_CLAIMS.generated.md). Release gates cover repository consistency, generated claims, golden reference artifacts, artifact integrity, wheel smoke, and local/post-release verification.
 
 <!-- public-claim-ledger:start -->
 > Claim evidence source: [docs/claims/public_claim_ledger.json](https://github.com/hibou04-ops/omegaprompt/blob/main/docs/claims/public_claim_ledger.json), rendered by `python tools/generate_readme_claims.py`.
@@ -1118,7 +1118,7 @@ Full changelog: [CHANGELOG.md](CHANGELOG.md).
 - **Train / test split with a pre-declared gate.** The foundational ML defence against overfitting, documented in every undergraduate curriculum. The specific implementation here (Pearson rank correlation threshold, pre-declared and unmodifiable) is `omega-lock`'s KC-4 kill criterion.
 - **LLM-as-judge.** Pattern formalised in *Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena* (Zheng et al., 2023). `omegaprompt` implements the pattern with schema enforcement at the SDK boundary (Pydantic via each vendor's native parse path) so malformed judge responses raise before polluting the fitness.
 - **Winchester defence.** A quant-finance discipline: *kill criteria declared before the run cannot be relaxed after.* Used here to argue that `--max-gap` and `--min-kc4` must be enforced in configuration, not retroactively tuned on inspection of scores.
-- **Sensitivity-driven coordinate descent.** Stress measurement and top-K unlock are the parameter-calibration primitives introduced by `omega-lock` (v0.1.4), originally for trading-strategy calibration, ported here to prompt configuration.
+- **Sensitivity-driven coordinate descent.** Stress measurement and top-K unlock are the parameter-calibration primitives introduced by `omega-lock` (v0.3.0), originally for trading-strategy calibration, ported here to prompt configuration.
 - **Antemortem discipline.** The pre-implementation reconnaissance methodology under which this project was designed and built. Every non-trivial change runs through [`antemortem-cli`](https://github.com/hibou04-ops/antemortem-cli) before the first keystroke. The case studies in the [methodology repository](https://github.com/hibou04-ops/Antemortem) record the recon for this codebase.
 
 Naming: *omega-lock* (parameter calibration) → *omegaprompt* (prompt calibration). The family branding is intentional. `omega-lock` was extracted from a trading-strategy calibration that ended in `KC-4 FAIL` — the overfitting defence firing exactly as designed. `omegaprompt` is the same defence applied one layer up, and the sub-tools `mini-omega-lock` / `mini-antemortem-cli` extend the pattern to preflight measurement.
@@ -1531,7 +1531,7 @@ Every override carries its `parameter`, `default`, `applied`, and `reason`. The
 Short form:
 
 ```
-omegaprompt v1.0.0 — provider-neutral prompt calibration engine.
+omegaprompt v2.0.2 — provider-neutral prompt calibration engine.
 https://github.com/hibou04-ops/omegaprompt, 2026.
 ```
 
@@ -1543,7 +1543,7 @@ BibTeX:
   title   = {{omegaprompt}: Provider-neutral prompt calibration engine
              with sensitivity-ranked meta-axes, walk-forward ship gates,
              and structural capability reporting},
-  version = {1.0.0},
+  version = {2.0.2},
   year    = {2026},
   url     = {https://github.com/hibou04-ops/omegaprompt}
 }
@@ -1553,7 +1553,7 @@ BibTeX:
   title   = {{omega-lock}: Sensitivity-driven coordinate-descent
              calibration framework with walk-forward validation and
              pre-declared kill criteria},
-  version = {0.1.4},
+  version = {0.3.0},
   year    = {2026},
   url     = {https://github.com/hibou04-ops/omega-lock}
 }

{omegaprompt-2.0.0 → omegaprompt-2.0.2}/README_KR.md

@@ -5,10 +5,10 @@
 
 [![License: Apache 2.0](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
 [![Python](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org)
-[![PyPI](https://img.shields.io/badge/pypi-2.0.0-blue.svg)](https://pypi.org/project/omegaprompt/)
-[![Tests](https://img.shields.io/badge/tests-317%20passing-brightgreen.svg)](tests/)
-[![Artifact schema](https://img.shields.io/badge/artifact-schema%20v2.0-blueviolet.svg)](#calibrationartifact-schema-v20)
-[![MCP](https://img.shields.io/badge/MCP-server-blueviolet.svg)](#mcp-서버)
+[![PyPI](https://img.shields.io/badge/pypi-2.0.2-blue.svg)](https://pypi.org/project/omegaprompt/)
+[![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg)](tests/)
+[![Artifact schema](https://img.shields.io/badge/artifact-schema%20v2.0-blueviolet.svg)](#10-calibrationartifact-schema-v20)
+[![MCP](https://img.shields.io/badge/MCP-server-blueviolet.svg)](#18-mcp-서버)
 [![Parent framework](https://img.shields.io/badge/framework-omega--lock-blueviolet.svg)](https://github.com/hibou04-ops/omega-lock)
 
 문서: [English](README.md) · [한국어](README_KR.md) · [Easy English](EASY_README.md) · [쉬운 한국어](EASY_README_KR.md)
@@ -26,7 +26,7 @@ pip install omegaprompt              # core
 pip install "omegaprompt[mcp]"       # + MCP server
 ```
 
-> **v2.0.0 (2026-05-23)** — public README/PyPI claim과 deterministic reference metric은 생성된 [claim ledger](docs/claims/README_CLAIMS.generated.md)에서 추적합니다. release gate는 repository consistency, generated claims, golden reference artifacts, artifact integrity, wheel smoke, local/post-release verification을 확인합니다.
+> **v2.0.2 (2026-06-08)** — **새 내용:** **opt-in 병렬 item 평가** — `--concurrency N`(CLI) / `CalibrateTuning(max_workers=N)`이 각 candidate 안에서 dataset item을 local thread pool로 동시에 평가합니다. 각 item은 여전히 target 호출 후 judge 호출을 순차로 실행하므로, 어느 한 provider에 대한 동시 호출 수는 N을 넘지 않습니다. 기본값(`1`)은 serial이며 이전 버전과 byte-identical한 artifact를 만듭니다. wall-clock 속도 향상은 **전적으로 사용 중인 provider 계정의 동시성 한도(RPM/TPM)에 따라 달라집니다**: 계정이 허용하면 N=2에서 대략 50%, 계정이 사실상 호출을 직렬화하면 **0%**입니다. 또한 `PromptTarget.evaluate()`가 이제 **resolved params 기준으로 memoize**되어, 마지막 best-candidate 평가가 provider를 다시 호출하는 대신 grid-search 결과를 재사용합니다 — `calibrate()` 동안 live API 호출이 줄며 public surface나 artifact schema 변경은 없습니다. omega-lock pin은 그대로(`>=0.3.0,<0.4.0`)이고 `CalibrationArtifact.schema_version`은 `2.0`을 유지하며 golden reference artifact는 변경되지 않습니다. 프로젝트의 PyPI Development Status는 이제 **4 - Beta**입니다. public README/PyPI claim과 deterministic reference metric은 생성된 [claim ledger](docs/claims/README_CLAIMS.generated.md)에서 추적합니다. release gate는 repository consistency, generated claims, golden reference artifacts, artifact integrity, wheel smoke, local/post-release verification을 확인합니다.
 
 이름 경계: GitHub repo는 `hibou04-ops/omegaprompt`; PyPI distribution, primary import package, primary CLI는 `omegaprompt`; compatibility package / CLI alias는 `omegacal`; 별도 parent calibration framework는 `omega-lock`입니다.
 
@@ -506,13 +506,13 @@ cost-efficient한 iteration 패턴: 작은 로컬/mini-tier target + frontier-ti
 ```
        ┌─────────────────────────────────────────────┐
 LAYER  │  omegaprompt  (본 repo)                      │  "prompt에 규율 적용 — Prompt CI"
-APPLY  │  v1.4.0 — schema v2.0, 6 meta-axes          │
+APPLY  │  v2.0.0 — schema v2.0, 6 meta-axes          │
        └────────────────────┬────────────────────────┘
                             │ depends on
                             ▼
        ┌─────────────────────────────────────────────┐
 LAYER  │  omega-lock                                 │  "calibration framework"
-CORE   │  v0.1.6 — stress + grid + walk-forward + KC │
+CORE   │  v0.3.0 — stress + grid + walk-forward + KC │
        └────────────────────┬────────────────────────┘
                             │ built under
                             ▼
@@ -591,7 +591,7 @@ artifact의 `walk_forward.generalization_gap`을 읽으세요. 10% 미만 = 강
 
 ## 21. 상태 & 로드맵
 
-**v2.0.0** — package release 2.0.0입니다. CalibrationArtifact schema는 v2.0으로 유지되며, 6 meta-axes, RuleJudge / LLMJudge / EnsembleJudge, guarded/expedition profile, MCP server, generated claim ledger를 포함합니다.
+**v2.0.1** — package release 2.0.1입니다. omega-lock 0.3.0 호환(`EvalResult.sample_count` alias)과 consumer docking hardlock(contract test + canary)을 추가했습니다. CalibrationArtifact schema는 v2.0으로 유지되며, 6 meta-axes, RuleJudge / LLMJudge / EnsembleJudge, guarded/expedition profile, MCP server, generated claim ledger를 포함합니다.
 
 데이터 계약 (`Dataset`, `JudgeRubric`, `PromptVariants`, `PromptSpace`, `CalibrationArtifact`), CLI 계약 (`omegaprompt calibrate / report / diff / check-artifact`), Python/MCP runtime 계약 (`preflight`, `measure_sensitivity`, `grade`, `classify_traps`) 은 stable. CLI exit code는 `0` clean/advisory success, `1` CI gate failure 또는 regression, `2` environment/config/tooling/input 문제로 고정합니다. judge prompt는 실 run의 scoring-quality 데이터가 축적되면서 iterate — minor bump가 judge prompt 개정용, CHANGELOG의 *Judge prompt revisions* 섹션에 추적.