Claude (agent-stats)
acd724079a
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VdfEGXA7aJ6ftMsCc9PJze
388 lines
19 KiB
YAML
388 lines
19 KiB
YAML
name: CI
|
|
|
|
on:
|
|
# `push` unrestricted plus `pull_request` ran every job TWICE on any branch
|
|
# with an open PR — visible as the (push) / (pull_request) pairs in the checks
|
|
# list. Restricting push to main means a PR branch is covered once by
|
|
# pull_request, and main once by push, which is also what pages-deploy needs.
|
|
push:
|
|
branches: [main]
|
|
pull_request:
|
|
|
|
env:
|
|
CARGO_TERM_COLOR: always
|
|
|
|
# Every job runs on the self-hosted NixOS microVM runners, and every `run:`
|
|
# step inside the flake's `ci` dev shell. Generic-Linux downloads (rustup,
|
|
# setup-node's node, Playwright's browsers) cannot run on NixOS, so the
|
|
# toolchain comes from flake.nix, the same one `nix develop` gives locally.
|
|
# Each step re-enters the shell; after the first, the eval cache makes it cheap.
|
|
defaults:
|
|
run:
|
|
shell: nix develop .#ci --command bash --noprofile --norc -eo pipefail {0}
|
|
|
|
jobs:
|
|
# ---------------------------------------------------------------------------
|
|
# The one place wasm-pack runs (improvise CI dedup).
|
|
#
|
|
# Before this job there were two: `pages-build` ran `web/build.sh`, and the
|
|
# browser harness ran `harness/build.sh`, which CALLS `web/build.sh`. The two
|
|
# wasm-pack builds were therefore done twice per run, in parallel jobs, with
|
|
# separate rust-cache keys (`add-job-id-key` is on by default, so `browser`
|
|
# and `pages-build` never shared a target dir). Measured on run 35535225637
|
|
# (push to main, caches warm): 68s inside `pages-build`, and the same 68s
|
|
# inside the browser job's 110s build step.
|
|
#
|
|
# Everything downstream now DOWNLOADS. The invariant that buys is artifact
|
|
# identity: the harness and Pages are served bytes from one wasm-pack run,
|
|
# so "the harness runs against the tree Pages publishes" (improvise-vvl3) is
|
|
# true by construction rather than because two scripts agree.
|
|
#
|
|
# The native binary is deliberately NOT built here. Nothing downstream
|
|
# consumes one — `cargo test --workspace` in the `test` job builds its own,
|
|
# for its own target dir and its own cache key, and a `needs:` on this job
|
|
# would serialise a 109s job behind a 126s one for no artifact at all.
|
|
build:
|
|
name: Build all bundles
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
# First, because it needs nothing and takes a second: the gate that stops
|
|
# an unstamped bundle shipping was deleted by injection on PR #69 and the
|
|
# assembly still exited 0 (improvise-w8ih). It guards the assemble step
|
|
# below, so it fails under this job's name rather than another's.
|
|
- name: The stamp gate refuses what it claims to
|
|
run: ./scripts/checkers.sh --ci build
|
|
# Built by Nix (packages.web and packages.site in nix/ci.nix), which runs
|
|
# the same harness/build.sh and web/assemble.sh a developer runs, so there
|
|
# is still one answer to "how is the bundle built". `web` is the three
|
|
# wasm bundles plus `harness/serve`; `site` re-assembles from web's pkg
|
|
# dirs with the commit SHA as the cache-bust token (improvise-9x6), where
|
|
# the harness tree is stamped `harness`. Dependencies are their own
|
|
# derivations, substituted from titan's cache when Cargo.lock is unchanged.
|
|
- name: Build the bundles, the harness tree and the site
|
|
run: |
|
|
nix build --print-build-logs --out-link result-web .#web
|
|
nix build --print-build-logs --out-link result-site .#site
|
|
# The upload steps below read these paths. Copied rather than linked:
|
|
# an artifact of a symlink into /nix/store is a dangling link elsewhere.
|
|
- name: Lay the outputs out where the uploads read them
|
|
run: |
|
|
rm -rf harness/serve web/pkg web/worker-pkg site
|
|
cp -rL result-web/harness-serve harness/serve
|
|
cp -rL result-web/pkg web/pkg
|
|
cp -rL result-web/worker-pkg web/worker-pkg
|
|
cp -rL result-site site
|
|
chmod -R u+w harness/serve web/pkg web/worker-pkg site
|
|
|
|
- run: find site -type f | sort
|
|
- run: du -sh site
|
|
|
|
# The tree the browser harness serves. Uploaded whole rather than
|
|
# reassembled downstream: a second assembly path is a second answer to
|
|
# "what does the harness serve", which is the thing improvise-vvl3 exists
|
|
# to prevent.
|
|
- name: Upload the harness tree
|
|
uses: actions/upload-artifact@v7
|
|
with:
|
|
name: harness-serve
|
|
path: harness/serve
|
|
retention-days: 1
|
|
include-hidden-files: true
|
|
|
|
# For a job that needs the raw wasm-pack output rather than the
|
|
# assembled site — the Node bundle suite under `web/tests/bundle/`.
|
|
- name: Upload the wasm bundles
|
|
uses: actions/upload-artifact@v7
|
|
with:
|
|
name: wasm-bundles
|
|
path: |
|
|
web/pkg
|
|
web/worker-pkg
|
|
retention-days: 1
|
|
include-hidden-files: true
|
|
|
|
- uses: actions/upload-pages-artifact@v5
|
|
with:
|
|
path: site
|
|
|
|
test:
|
|
name: Test and lint (host)
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
# NOT `cargo fmt --all`, which reaches only ONE of the two workspace
|
|
# roots. Exit 2 here is a usage error, never a verdict (improvise-b4ks).
|
|
- name: Every workspace root is formatted
|
|
run: ./scripts/fmt-workspaces.sh
|
|
# A manifest-only change to a crate the harness reaches by path stales
|
|
# its own lock, which only the slow `build` job saw (improvise-zs2r).
|
|
- name: The harness lock matches the manifests it resolves against
|
|
run: ./scripts/check-harness-lock.sh --allow-network
|
|
# checks.clippy and checks.test in nix/ci.nix: the same cargo commands,
|
|
# on the dev/test profiles, with dependencies as a cached derivation.
|
|
- name: cargo clippy --workspace --all-targets -- -D warnings
|
|
run: nix build --print-build-logs .#checks.x86_64-linux.clippy
|
|
# Also runs the test-evidence gate (check-comment-runs.py
|
|
# --check-evidence), which lists the tests this derivation compiled.
|
|
- name: cargo test --workspace, and test-evidence headings name real tests
|
|
run: nix build --print-build-logs .#checks.x86_64-linux.test
|
|
# The comment cap and the test-evidence keys (improvise-9c8c); without
|
|
# this step the rule is advisory. See context/design-principles.md §6.
|
|
- name: The comment checker catches what it has been fixed for
|
|
run: python3 scripts/check-comment-runs.py --self-test
|
|
- name: Comment runs capped at two lines
|
|
run: python3 scripts/check-comment-runs.py
|
|
# `pages-deploy` needs every other job, and saying so was not enough: a
|
|
# job added during review of PR #83 was ungated and nothing noticed.
|
|
- name: The deploy gate refuses what it claims to
|
|
run: python3 scripts/check-ci-graph.py --self-test
|
|
- name: Every check job gates the deploy
|
|
run: python3 scripts/check-ci-graph.py
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# The crate2nix build (Cargo.nix), which `cargo` never exercises. It was off
|
|
# because GitHub-hosted runners start with an empty store and rebuilt every
|
|
# dependency crate each run. The NixOS runners substitute from titan's
|
|
# harmonia first, and titan builds gh/main's `#improvise` hourly, so a PR that
|
|
# leaves Cargo.lock alone rebuilds only the workspace crates it changed.
|
|
#
|
|
# The repo-stats pipeline runs here because it needs this job's binary:
|
|
# `nix shell .#improvise` reuses the build above instead of a second one.
|
|
# Its suite gates; the report on a push to main never fails the build, and
|
|
# its step fails only when improvise refuses the pipeline's input
|
|
# (context/code/tooling.md section 7). Full history is for the report.
|
|
nix-build:
|
|
name: Nix build (crate2nix) and the repo-stats pipeline
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
with:
|
|
fetch-depth: 0
|
|
- name: nix build .#improvise
|
|
run: nix build --print-build-logs .#improvise
|
|
- name: The repo-stats pipeline computes what it claims to
|
|
run: nix shell .#improvise --command ./scripts/checkers.sh --ci nix-build
|
|
- name: Churn, coupling and doc-growth report (report only)
|
|
if: github.event_name == 'push'
|
|
continue-on-error: true
|
|
run: |
|
|
rc=0
|
|
nix shell .#improvise --command ./scripts/repo-stats --out repo-stats > repo-stats.txt || rc=$?
|
|
{ echo '```'; cat repo-stats.txt; echo '```'; } >> "$GITHUB_STEP_SUMMARY"
|
|
exit "$rc"
|
|
- name: Upload the repo-stats model and its CSVs
|
|
if: github.event_name == 'push'
|
|
uses: actions/upload-artifact@v7
|
|
with:
|
|
name: repo-stats
|
|
path: repo-stats
|
|
retention-days: 30
|
|
|
|
wasm:
|
|
name: wasm32 check (browser bundle crates)
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
# checks.wasm-check in nix/ci.nix: `cargo check --target wasm32` for each
|
|
# crate in the browser bundle, one at a time, so features are not unified
|
|
# across them. The root `improvise` crate is the terminal binary and
|
|
# depends on crossterm, which does not build for wasm — that is correct,
|
|
# not a gap (improvise-ywd). The log names each crate as it is checked.
|
|
- name: cargo check --target wasm32-unknown-unknown, per bundle crate
|
|
run: nix build --print-build-logs .#checks.x86_64-linux.wasm-check
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# The browser JavaScript's unit tests. Its own job, deliberately: a failure
|
|
# here is a decision `web/shell.js` or `web/serial.js` got wrong, and
|
|
# reporting that as "Browser harness" would put it behind an 80 MB browser
|
|
# download and two wasm-pack builds. It needs neither — `node --test` is in
|
|
# the runtime, which the dev shell supplies; this job installs nothing.
|
|
js:
|
|
name: Browser JS unit tests (node --test)
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
# The glob is the SCRIPT's, not the shell's and not node's. Under bash an
|
|
# unmatched glob survives as a literal, node globs it, matches nothing and
|
|
# exits 0 having run no test -- so this step gated nothing the moment
|
|
# `web/tests/` moved (improvise-vz54). `web/tests/bundle/` needs a built
|
|
# wasm bundle and runs in the browser job instead.
|
|
- name: What the page decides between its boundaries
|
|
run: ./scripts/node-test.sh 'web/tests/*.test.js'
|
|
# The guard above is only worth its line if its refusals are themselves
|
|
# checked -- the step it replaces was green while asserting nothing.
|
|
- name: The node test runner refuses what it claims to
|
|
run: ./scripts/checkers.sh --ci js
|
|
|
|
kb:
|
|
name: Knowledge base consistency
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
# kb.pl is executable knowledge, so it gets checked like code: rules
|
|
# must reject what they should, domains must close, and functional keys
|
|
# must not carry conflicting values. See kb_report/0 in the file.
|
|
# trealla comes from the dev shell, as it does locally.
|
|
- name: kb_consistent
|
|
run: |
|
|
tpl prolog-sessions/kb.pl \
|
|
-g "(kb_consistent -> halt(0) ; (kb_report, halt(1)))"
|
|
# Every suite goes through scripts/checkers.sh, which scrubs the
|
|
# environment (improvise-f9qf); its bash is the dev shell's. Which suites
|
|
# this job runs is the `kb` row of the CI table in checkers.sh, deliberately
|
|
# not listed here. check-ci-graph.py holds that table to `checkers.sh --list`.
|
|
- name: Every checker in scripts/ refuses what it claims to
|
|
run: ./scripts/checkers.sh --ci kb
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Lints the one crate the `test` job cannot reach.
|
|
#
|
|
# `harness/opfs-contract` carries an empty `[workspace]` table, so it is its
|
|
# own root and `cargo clippy --workspace` at the repo root never sees it.
|
|
#
|
|
# Its own job rather than a step inside `browser`, for two reasons. It took
|
|
# 37s of the browser job's 263s on run 35535225637 while gating nothing the
|
|
# harness needs — a lint failure and a harness failure are different reports,
|
|
# and here the lint failure wore the harness's name. And `cargo fmt --all`
|
|
# from inside that directory formats the WHOLE outer workspace (114 files,
|
|
# measured) rather than the one crate, because cargo-fmt's `--all` walks past
|
|
# the nested workspace boundary — so a rustfmt violation anywhere in the repo
|
|
# failed the *Browser harness* job. `-p opfs-contract` scopes it to 1 file.
|
|
harness-lint:
|
|
name: Lint the harness crate
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
# checks.harness-lint in nix/ci.nix, run from inside harness/opfs-contract:
|
|
# `cargo fmt -p opfs-contract -- --check` and clippy for wasm32.
|
|
- name: cargo fmt -p opfs-contract and clippy --target wasm32
|
|
run: nix build --print-build-logs .#checks.x86_64-linux.harness-lint
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# The browser harness (improvise-vvl3, absorbing improvise-xf1).
|
|
#
|
|
# This is the only job that RUNS any of the browser half. `OpfsFs`,
|
|
# `web/app.js` and `web/worker.js` were previously compile-checked,
|
|
# syntax-checked and read — never executed — so every bug in them was found
|
|
# by reading or by a person pressing keys, neither of which is repeatable.
|
|
#
|
|
# It can fail the build, deliberately: a harness nobody runs is worse than
|
|
# none, because it reads as coverage.
|
|
#
|
|
# It now needs NO Rust toolchain: the tree it serves is downloaded from
|
|
# `build`, which is what makes "the harness runs against the tree Pages
|
|
# publishes" (improvise-vvl3) a fact about bytes rather than about two
|
|
# scripts agreeing. The download is `harness/serve` whole, so there is still
|
|
# exactly one place that arrangement is decided — `harness/build.sh`.
|
|
browser:
|
|
name: Browser harness (OPFS contract + shell)
|
|
needs: build
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
- name: Install the harness
|
|
working-directory: harness
|
|
run: npm ci
|
|
# No browser install step and no version probe: the dev shell sets
|
|
# PLAYWRIGHT_BROWSERS_PATH to nixpkgs' browsers, which pin them. `npm ci`
|
|
# stays because @playwright/test itself is not nix-provided.
|
|
# The tree `build` assembled, not one this job rebuilds. Same bytes as
|
|
# the Pages artifact, modulo the cache-bust token `web/assemble.sh`
|
|
# stamps — the harness tree is stamped `harness` and the site the commit
|
|
# SHA, which was already true when both jobs built their own.
|
|
- name: Download the harness tree
|
|
uses: actions/download-artifact@v7
|
|
with:
|
|
name: harness-serve
|
|
path: harness/serve
|
|
# `web/pkg` and `web/worker-pkg` as wasm-pack left them, for the .d.ts
|
|
# the step below reads. The artifact's root is `web/`, so this restores
|
|
# both directories at the paths the test resolves relative to itself.
|
|
- name: Download the wasm bundles
|
|
uses: actions/download-artifact@v7
|
|
with:
|
|
name: wasm-bundles
|
|
path: web
|
|
# The JS↔wasm boundary: every call web/app.js makes is declared by the
|
|
# bundle, with that arity. It needs the bundle and nothing else, so it
|
|
# runs here rather than in the `js` job, and before Playwright — a
|
|
# renamed export is cheaper to read here than as a blank page.
|
|
- name: The page's calls match the bundle it calls
|
|
run: ./scripts/node-test.sh 'web/tests/bundle/*.test.js'
|
|
# Chromium and Firefox only, for now. nixpkgs' WebKit (WPEWebProcess)
|
|
# aborts on its first page inside the runner VMs, though not on the
|
|
# host; its four specs skip on the OPFS probe anyway, so nothing gated
|
|
# is lost. Put `--project=webkit` back once that abort is understood.
|
|
- name: Run the harness
|
|
working-directory: harness
|
|
run: npx playwright test --project=chromium --project=firefox
|
|
- if: failure()
|
|
uses: actions/upload-artifact@v7
|
|
with:
|
|
name: playwright-traces
|
|
path: harness/test-results
|
|
retention-days: 7
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# GitHub Pages delivery (improvise-d31).
|
|
#
|
|
# The artifact is uploaded by `build`, which runs on every push and pull
|
|
# request, so a change that breaks `web/build.sh` or the bundle fails on the
|
|
# PR that made it — the build is a gate. `pages-deploy` runs only on a push
|
|
# to main and `needs` the check jobs, so nothing that failed `cargo test`,
|
|
# the wasm32 gate or the browser harness can reach the published site. The
|
|
# deploy depends on those checks rather than repeating them (improvise-d31
|
|
# AC 2).
|
|
#
|
|
# Not path-filtered, deliberately. The bundles are `improvise-wasm-client` and
|
|
# `improvise-worker-server` plus, between them, most of the workspace — the
|
|
# worker bundle is the whole App: core, formula, io, protocol and command. A
|
|
# filter
|
|
# that meant "skip when the bundle cannot have changed" would have to name
|
|
# most of the workspace, and the failure mode of getting it wrong is a stale
|
|
# site with no signal that it is stale. A redundant build is the cheaper error.
|
|
#
|
|
# On improvise-864a: the mechanism is NOT supersession and NOT queue depth —
|
|
# another run's SUCCESSFUL deployment invalidates this run's `github-pages`
|
|
# artifact, measured over 100 runs. Building once shortens the upload→deploy
|
|
# window (182s → ~115s on the run 35535225637 shape), and the window is where
|
|
# the whole risk lives. It narrows the race; it does not close it. The
|
|
# evidence and what it rules out: context/code/tooling.md §3.
|
|
# `needs` is EVERY check job, which is the only rule that does not go stale.
|
|
# `kb` was the one absent, on the unstated ground that kb.pl is not shipped by
|
|
# the site — but neither is `harness-lint`'s crate, and it was in the list, so
|
|
# the ground proved too much (improvise-x7cq). A failing consistency check
|
|
# means main is broken, and publishing from a broken main is what this list
|
|
# exists to stop.
|
|
pages-deploy:
|
|
name: Deploy to GitHub Pages
|
|
needs: [test, wasm, js, browser, harness-lint, kb, build, nix-build]
|
|
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
|
runs-on: [self-hosted, nixos, microvm]
|
|
permissions:
|
|
contents: read
|
|
pages: write
|
|
id-token: write
|
|
# A superseded deploy is allowed to finish rather than being cancelled:
|
|
# `deploy-pages` cancelled midway can leave the Pages deployment in a
|
|
# half-applied state, and the next push republishes anyway.
|
|
concurrency:
|
|
group: pages
|
|
cancel-in-progress: false
|
|
environment:
|
|
name: github-pages
|
|
url: ${{ steps.deployment.outputs.page_url }}
|
|
steps:
|
|
# `enablement: false` (the default) configures the environment URL
|
|
# without attempting to create or modify the Pages site via the API.
|
|
# GitHub Pages must be enabled once in the repository settings
|
|
# (Settings → Pages → Source: GitHub Actions) before this job will
|
|
# produce a live URL. Using `enablement: true` fails when the workflow
|
|
# token lacks admin permission to create the site (improvise-3gy).
|
|
- uses: actions/configure-pages@v6
|
|
with:
|
|
enablement: false
|
|
- id: deployment
|
|
uses: actions/deploy-pages@v5
|