digline 0.1.0__tar.gz

digline-0.1.0/.gitignore

@@ -0,0 +1,40 @@
+# Python bytecode and build output
+__pycache__/
+*.py[cod]
+build/
+dist/
+*.egg-info/
+
+# Environment. Recreated by `uv sync`; it pins absolute paths, so it must
+# never be committed.
+.venv/
+.env
+
+# Tool caches. Each already drops its own `.gitignore`; listed here so a
+# fresh clone is clean before the tools have run once.
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+
+# IDE. Excluded because the project files carry machine-specific SDK paths
+# (`digline.iml` names the interpreter by absolute path). Drop these two lines
+# to version the shared part, and keep ignoring `.idea/workspace.xml`.
+.idea/
+*.iml
+
+# Local Claude Code settings. `.claude/settings.json`, if it appears, is shared
+# and stays versioned. `CLAUDE.local.md` is the personal working agreement —
+# how I want to be worked with — as against `CLAUDE.md`, which is the project.
+.claude/settings.local.json
+CLAUDE.local.md
+
+# macOS
+.DS_Store
+
+# Working material that stays local and is not part of the package.
+private/
+
+# NOT ignored: `.digline/`. Decision 2 — baselines are versioned, run
+# artifacts are not — and the split is enforced one level down, by the
+# `.gitignore` the store itself writes into `.digline/` (`*/runs/`).
+# Ignoring `.digline/` here would take the baselines out of git with it.

digline-0.1.0/CLAUDE.md

@@ -0,0 +1,126 @@
+# digline
+
+Python-native evaluation engine for LLM output. Starting reference: promptfoo
+(analysis in private/promptfoo-analysis.md). Not a clone: the decisions below
+correct its structural mistakes and are not negotiable.
+
+## Architectural decisions (fixed)
+
+1. **One assertion engine, two drivers.** Assertions are pure functions
+   `(EvaluatorInputs) -> Verdict` in `digline.core`, with no I/O, callable on
+   their own (amended by ADR 0001: it used to be `(output, context) -> Score`).
+   The offline driver (prompt × provider × test matrix) and the online one
+   (stream of production responses) use the same code. If a change to the core
+   makes an assertion callable only inside a runner, it is wrong.
+2. **Per-project storage.** Everything lives in `.digline/<tenant>/` inside the
+   user's repo: config and baselines versioned in git, run artifacts
+   gitignored. Behind the `ResultStore` protocol, file-based implementation by
+   default. Never a DB in the home directory, never global state on the machine.
+3. **No vacuously green assertion.** Every assertion has a mandatory threshold
+   or a default that can fail. A default of 0 that always passes is a bug.
+4. **Cost and latency are budgets, not metrics.** A declared ceiling fails the
+   run.
+5. **Zero telemetry, zero phone-home.** No network call the user has not
+   explicitly configured.
+6. **Providers as plugins** (entry points), not vendored into the repo.
+7. **The core must accept a single response**, not only a matrix: the reactive
+   side (shadow path / in-path) is not decided yet, but must not be precluded.
+8. **The tenant is the perimeter.** `Run.tenant` is mandatory and non-empty.
+   `compare()` and `promote_baseline` raise if the tenants differ. The tenant is
+   a directory in the layout — `.digline/<tenant>/` — so that the separation is
+   enforced by the filesystem, not by a field inside a document.
+   **No sub-perimeter**: `Run.environment` (mandatory, no default) says where
+   inside the perimeter the run happened, does not enter the layout, and
+   `compare()` reports it without constraining — comparing staging against the
+   production baseline is the pre-release check. (ADR 0002)
+9. **The payload stays where it is born, the verdict travels.** These cross a
+   boundary: name, `assertion_id`, status, score, threshold, tolerance, and the
+   metadata *measured by an assertion*. These do not: the `reason` and any
+   metadata not covered by a `Disclosure` declared in code. Redaction is a
+   function on the value (`redact`), not a serializer option; in the document
+   the payload fields are absent, not emptied, and `"redacted": true` declares
+   it. (ADR 0002)
+   The **artifacts** a suite declares — the prompt is the thing under test — are
+   recorded in every run and cross a boundary only under
+   `Disclosure(artifacts=True)`: a prompt carries the end company's rules, so
+   the prudent default holds here too. (ADR 0003)
+
+## Structure
+
+    src/digline/core/       pure domain: Score, Verdict, assertions, protocols. No imports from other packages.
+    src/digline/store/      ResultStore and its implementations (file-based, inside the repo)
+    src/digline/targets/    prompt template, pricing, the ProviderTarget base. No SDK, ever;
+                            real providers are separate packages under packages/
+    src/digline/run/        offline driver
+    src/digline/report/     the document for world 3: pure functions, self-contained HTML, mandatory locale
+    src/digline/production/ [planned] production store, Postgres first, mandatory retention
+    src/digline/bridge/     [planned] production → repo: mandatory anonymization, generated case_id
+    src/digline/online/     production driver
+    src/digline/cli/        last layer: the **only** one allowed to read the clock and git
+                            (the *clock*, meaning wall time: `created_at` is passed in so a
+                            run is reproducible. A **duration** is not a clock — it cannot
+                            say what time it is — so `perf_counter` for `latency_ms` in a
+                            target is allowed and is what fills `Response.latency_ms`.)
+    docs/                   public documentation: API reference, decisions (numbered ADRs)
+
+Allowed dependencies: cli → targets → run/report/bridge/online →
+store/production → core. Never the other way round, and nothing under `src/`
+ever imports a plugin from `packages/`.
+
+Build order: offline driver → report → store and CLI. **Nothing online before
+the report**: it is what world 3 sees, and it is the only one of the three
+artifacts that today exists in none of the audited competitors.
+
+## Conventions
+
+- Python 3.12+, uv, ruff, pyright strict, pytest. Types everywhere, `Protocol`
+  for abstractions, frozen dataclasses for values.
+- **The whole repository is in English**: comments, docstrings, test and
+  variable names, error messages and runtime strings (`Verdict.reason` ends up
+  in the committed baseline, which is a public format), plus `docs/`, the ADRs
+  and this file. Italian only in conversation and in `private/`, which is not
+  committed.
+  **The one declared exception: `digline/report/text.py`.** The report is not a
+  runtime string, it is a document with a recipient who did not choose English.
+  `TEXT` is the per-locale table; `render_html` and `headline` take a mandatory
+  `locale` with no default, like `environment`. ISO dates and the decimal point
+  are not localized: two reports of the same run must stay comparable line by
+  line.
+  In the CLI the distinction is between *document* and *terminal*:
+  `report --locale` is mandatory, `compare --locale` defaults to `en` like every
+  other terminal output. Consistency between the two sentences is guaranteed by
+  `headline()`, not by the user.
+- Every assertion has tests with at least one failing case.
+- `tests/test_layering.py` is a **mandatory gate**, not a style test: it guarantees
+  that the core stays pure and importable from Plumbline without dragging storage
+  along. It must not be weakened or made optional; if it fails, the change is
+  wrong, not the test.
+- Every decision touching the "fixed" section requires an ADR in docs/adr/
+  before the code.
+- Small commits, message in English, imperative.
+
+## Relationship with Plumbline
+
+Plumbline (CLI `plumb`) is the methodology for preventive verification of the
+development process; digline verifies the model's output. digline.core must be
+importable from Plumbline as a library. Plumbline's wall/friction dichotomy maps
+onto in-path/shadow-path here: use the same terms.
+
+## The three worlds (ADR 0002)
+
+1. **Developer** — works in the repo, writes the assertions, sees everything.
+2. **Software house** — maintains N customers, must see the signal **without
+   holding the production data** of any of them.
+3. **End company** — owns the data, does not read code, is entitled to an
+   understandable verdict and to its data not leaving.
+
+The tenant (decision 8) separates customers from each other; the
+payload/verdict boundary (decision 9) separates what the end company may send
+from what it must not.
+
+## Where the working material lives
+
+The frictions log — what tripped a real user, in order of discovery — lives
+in `private/`, which is a **separate repository** and is gitignored here.
+Commits to it are made there, not in this repo. It is the record of use, so
+it is written in whatever language the using happened in.

digline-0.1.0/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 Alessandro Prandini
+
+   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.

digline-0.1.0/PKG-INFO

@@ -0,0 +1,254 @@
+Metadata-Version: 2.5
+Name: digline
+Version: 0.1.0
+Summary: Python-native evaluation engine for LLM output. The verdict lives in your repo.
+Project-URL: Documentation, https://github.com/digline/digline/blob/main/docs/api.md
+Project-URL: Repository, https://github.com/digline/digline
+Project-URL: Issues, https://github.com/digline/digline/issues
+Author-email: Alessandro Prandini <alessandro.prandini@ict-group.it>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: assertions,baseline,eval,evaluation,llm,regression,testing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Software Development :: Testing
+Classifier: Typing :: Typed
+Requires-Python: >=3.12
+Requires-Dist: jsonschema>=4.21
+Description-Content-Type: text/markdown
+
+# digline
+
+**Regression testing for LLM applications — with the baseline in your repository, not on someone's server.**
+
+[![Python 3.12+](https://img.shields.io/badge/python-3.12%2B-blue)](pyproject.toml)
+[![License: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-green)](LICENSE)
+
+Your prompt worked on Tuesday. On Thursday it works a little less — not enough
+to break, enough for a user to notice in two weeks. No ordinary test catches it,
+because there is no correct output to compare against, only a better or a worse
+one.
+
+digline gives you an **approved reference** — the baseline — and on every change
+tells you whether you are below it: which case, which check, by how much. The
+baseline is a JSON file in your repository, so it goes through code review and
+it rolls back with `git`. No server, no account, no network call you have not
+configured yourself.
+
+```console
+$ digline compare --suite suite.py --run latest
+2 checks got worse compared with the reference. Every case could be judged. No case is suspended. The configuration is the same as the reference.
+
+how-do-i-return · llm_rubric · Score fell from 1.000000 to 0.700000.
+how-do-i-return · contains · Went from passing to failing (1.000000 → 0.000000).
+```
+
+## Why digline
+
+Most evaluation tools tell you whether an output is below a threshold. digline
+also tells you whether it is *worse than it was* — the drift from 0.91 to 0.78
+that trips no threshold and is the first thing a user feels.
+
+The suite is **Python, not YAML**: a judge is an object, a target is a function,
+and what may leave a perimeter is declared in code — none of which a
+configuration file expresses without reinventing a language. Built for teams
+shipping LLM features for someone else, who have to show a customer what was
+tested, when, under which commit, and who approved it.
+
+## Quickstart
+
+```bash
+uv sync                       # inside a clone; not published to PyPI yet
+```
+
+`suite.py` — complete and runnable, no API key:
+
+```python
+"""suite.py — complete and runnable: no API key, nothing else to install."""
+
+from digline.core import Contains, CostBudget, JudgeReply, LlmRubric
+from digline.run import Case, Response, Suite
+
+ANSWERS = {
+    "where-is-my-order": "Order 4821 ships Thursday. — Northwind Support",
+    "how-do-i-return": "Any item, within 30 days, unused. — Northwind Support",
+}
+
+
+def judge(prompt: str) -> JudgeReply:
+    """Your judge. digline composes `prompt` from the rubric, the question and
+    the answer; it wants a score in [0, 1] and a reason back."""
+    signed = "Northwind Support" in prompt
+    concise = len(prompt.split()) <= 60
+    return JudgeReply(
+        score=0.4 + 0.3 * signed + 0.3 * concise,
+        reason=f"signed={signed}, concise={concise}",
+    )
+
+
+def target(case: Case) -> Response:
+    """Your application, called once per case. Canned here so this runs as is."""
+    text = ANSWERS[case.id]
+    return Response(output=text, cost_usd=0.004 + 0.001 * len(text) / 100)
+
+
+suite = Suite(
+    tenant="northwind",
+    environment="staging",
+    name="support",
+    assertions=[
+        Contains(needle="Northwind Support"),
+        LlmRubric(
+            rubric="Does the reply answer the question in at most three sentences?",
+            judge=judge,
+            threshold=0.7,
+            tolerance=0.05,
+        ),
+        CostBudget(max_usd=0.02, tolerance=0.05),
+    ],
+    cases=[Case(id="where-is-my-order"), Case(id="how-do-i-return")],
+)
+```
+
+```console
+$ digline run --suite suite.py
+2026-08-26T15-44-09-282929-00-00-e7421ec503ccefe8
+
+$ digline promote --suite suite.py --run latest
+support baseline set to 2026-08-26T15-44-09-282929-00-00-e7421ec503ccefe8
+```
+
+Now change the prompt, the model, an answer — anything — and ask again:
+
+```console
+$ digline run --suite suite.py
+2026-08-26T15-44-09-492722-00-00-e7421ec503ccefe8
+
+$ digline compare --suite suite.py --run latest
+2 checks got worse compared with the reference. Every case could be judged. No case is suspended. The configuration is the same as the reference.
+
+how-do-i-return · llm_rubric · Score fell from 1.000000 to 0.700000.
+how-do-i-return · contains · Went from passing to failing (1.000000 → 0.000000).
+
+$ echo $?
+1
+```
+
+The exit code is the answer: `0` fine, `1` got worse, `2` could not be judged.
+Everything lands in `.digline/<tenant>/` — `baselines/` committed, `runs/`
+git-ignored through a `.gitignore` digline writes for you.
+
+## What it checks
+
+**Per case** — pure functions `(inputs) -> Verdict`, no I/O, callable on their own:
+
+| Assertion | Use it when |
+|---|---|
+| `Equals`, `Contains`, `NotContains`, `Affix`, `Regex` | the output must, or must not, contain something specific |
+| `IsJson`, `JsonSchema` | the output is structured |
+| `Length` | answers are growing, or must fit a channel |
+| `Levenshtein` | "close enough" to `Case.expected`, graded rather than binary |
+| `LlmRubric` | the criterion is a judgement — is it polite, does it stay on policy |
+| `Faithfulness` | RAG: is the answer supported by the retrieved context |
+| `FromAutoevals` | you already have an `autoevals` scorer and want it under a baseline |
+| `PiiAbsent` | the output reaches a person — IBAN, codice fiscale, partita IVA, email, phone, checksum-verified where one exists |
+| `CostBudget`, `LatencyBudget` | always. Graded, so a cost creeping up *within* budget is still visible |
+| `Repeated` | the judge oscillates: grade the same output `n` times and fold the votes |
+
+**Per run** — one verdict on the whole suite, the kind that goes in a contract:
+
+| Aggregate | Use it when |
+|---|---|
+| `Precision` | false positives are what your users see |
+| `Recall` | what is missed is what your users miss |
+| `Accuracy`, `F1` | you need a single number for both |
+
+Every assertion carries a **threshold that can fail** — there is no default that
+passes vacuously, and `Contains("")` is a `ValueError` when the suite loads
+rather than a green run — and a **tolerance** below which a difference from the
+baseline is noise. Where a number is really "k out of n", write it as one:
+`min_agreement="2/3"`, and a float no `k/n` can produce is refused at
+construction.
+
+One card each — parameters, typical values, what to watch out for — in
+[`docs/metrics.md`](docs/metrics.md). Custom assertion? Subclass
+`AssertionBase`, or `RunAssertionBase` for an aggregate: [`docs/api.md`](docs/api.md).
+
+## How it thinks
+
+- **The judge is yours.** digline never calls a model API: you inject a
+  function, and in your tests you inject a deterministic one.
+- **Three states, not two** — `pass`, `fail`, `error`. An error is neither green
+  nor a regression: it means *could not judge*, and a run containing one cannot
+  become the baseline.
+- **Two kinds of noise, two answers.** `Suite.samples` asks the target more than
+  once — the same input answered differently. `Repeated` grades the same output
+  more than once — the judge changing its mind. `min_agreement` becomes
+  mandatory as soon as you sample.
+- **Set the threshold where the system measurably is**, not where you want it:
+  the gate protects against getting worse, and raising the bar is a visible
+  change in a pull request.
+- **Promote the median of several runs**, not the first green one — `digline
+  view` is the table you pick it from. Cases diagnose, aggregates gate.
+
+Worked through with real numbers in [`docs/guide.md`](docs/guide.md); the
+reasoning behind every fixed decision is in [`docs/adr/`](docs/adr/).
+
+## Commands
+
+| Command | |
+|---|---|
+| `digline run` | execute the suite, write the run, print its key |
+| `digline compare` | headline plus the lines that got worse; `--json`, `--json full` for CI |
+| `digline promote` | make a run the baseline — refused if the tenant differs, the configuration changed, or any check errored |
+| `digline report` | self-contained HTML for readers who do not read code; `--locale` mandatory, `--redacted` keeps the verdicts and drops the payload |
+| `digline list` | stored runs, newest first, baseline marked |
+| `digline view` | local browser UI — [`docs/view.md`](docs/view.md) |
+| `digline migrate` | bring stored runs forward across schema versions — [`docs/migrate.md`](docs/migrate.md) |
+
+## What digline is not
+
+- **Not an observability platform.** Dashboards over production traces are a
+  served market. What is designed and not yet built is narrower: evaluating
+  production responses inside *your* perimeter, and turning a failure into a
+  committed test case.
+- **Not a red-teaming tool.** digline generates no attacks. Once one is found,
+  it becomes a `Case`, and the suite makes sure it never works again.
+- **Not YAML.** Cases are data and may come from files; the suite is Python.
+
+## Status
+
+`0.1.0`, alpha. The offline cycle — write the suite, run, promote, compare,
+report — is complete, covered by tests, and used daily on a real project. The
+production store, the bridge from production failures back to committed cases,
+and the reactive side are designed in
+[ADR 0002](docs/adr/0002-three-worlds-and-where-the-data-lives.md) and not
+written yet.
+
+Python 3.12+. One runtime dependency: `jsonschema`.
+
+## Docs
+
+- [`docs/guide.md`](docs/guide.md) — how to reason with digline, in eight chapters
+  and the order the problems arrive: baseline, judge noise, sampling, tolerance,
+  threshold, which run to promote, what to gate on, what to maintain
+- [`docs/metrics.md`](docs/metrics.md) — a card per assertion and aggregate: when
+  to reach for it, what it produces, what it will do to you if you are not looking
+- [`docs/api.md`](docs/api.md) — what is imported from where, every assertion
+  and its parameters, custom assertions, and the complete example in
+  [`examples/quickstart/`](examples/quickstart/), which a test runs on every build
+- [`docs/view.md`](docs/view.md) · [`docs/migrate.md`](docs/migrate.md) — the two commands with a surface of their own
+- [`docs/adr/`](docs/adr/) — the architectural decisions, numbered, with the reasoning
+
+## License
+
+Apache-2.0.