pi-devbox/Dockerfile.variant

# pi-devbox — variant image
#
# FROMs a base-<hash> image produced by Dockerfile.base and adds only
# the variant-specific tools — currently just the pi install. Kept as a
# separate file (rather than collapsed into Dockerfile.base) so future
# variants (e.g. studio, studio-tex) can FROM the variant or extend
# this Dockerfile with additional build args without rebuilding the
# base on every pi version bump.
#
# Pass `--build-arg BASE_IMAGE=<repo>:base-<hash>` to select the base.
# CI computes the base hash from Dockerfile.base + rootfs/ +
# entrypoint*.sh and feeds it in.
#
# IMPORTANT: the base image sets NPM_CONFIG_PREFIX to
# /home/developer/.pi/npm-global so runtime `pi install npm:...` and
# `npm install -g` by the developer user lands on the named volume.
# At BUILD time we want the baked binaries on /usr so they survive the
# volume mount. Each `npm install -g` below therefore prefixes the
# command with `NPM_CONFIG_PREFIX=/usr`.

ARG BASE_IMAGE
FROM ${BASE_IMAGE}

ARG TARGETARCH
ARG USER_NAME=developer

# ── pi coding-agent + companions ─────────────────────────────────────
# pi-toolkit and pi-extensions are cloned into /opt/. entrypoint-user.sh
# runs each repo's install.sh on container start so symlinks land under
# ~/.pi/agent/ on the named volume.
#
# ── pi version pin: an AUDITED CHECKPOINT, not a freeze ──────────────
# PI_VERSION is pinned to a version whose upstream CHANGELOG has been read
# against this image's integration surface: the theme/TUI API that pi-atelier
# couples to, the session `.jsonl` format that `pi-session-repair` parses, the
# extension/package loader, and the Node engine floor. CI reads THIS LINE as
# the single source of truth (see the `resolve-versions` job) and no longer
# follows npm `latest` — following it meant every release silently adopted
# whatever pi shipped that morning, unaudited, in the very build that then got
# tagged and published.
#
# BUMPING IS ROUTINE AND EXPECTED — the pin exists to force a look, not to
# hold a version forever:
#   1. Read the upstream CHANGELOG for every version between old and new.
#   2. Re-check the companions that couple to pi's private TUI/renderer
#      internals — pi-atelier above all (see PI_ATELIER_REF below for the
#      0.6.0-under-pi-0.84 startup-hang precedent).
#   3. Bump this line, record the audit in CHANGELOG.md, then tag.
# CI fails the build if this pin is not a published npm version, and warns —
# without adopting it — when npm `latest` has moved ahead. That warning is the
# prompt to do step 1; it is not something to silence.
#
# A concrete version here ALSO defeats the registry-buildcache cache-hit
# footgun that `latest` carried: a byte-identical build-arg string produced an
# identical layer hash, so the cache reused the layer from whatever pi was
# current when it was first populated (shipped the same bytes for pi-devbox
# v0.74.0..v0.75.5; discovered + fixed in v0.75.5b, 2026-05-23). The `latest`
# branch below is kept only for a deliberate local `docker build` override.
#
# AUDITED AT 0.84.4 (2026-08-31, was 0.84.3): NO "Breaking Changes" and no
# "Removed" heading in the 0.84.4 section (grepped, 0 matches) — unlike 0.84.3,
# whose heading is described in the paragraph below and stays audited. Adopted
# for three fixes that land on machinery this fleet actually runs:
#   - #6879 large tool results crossing the auto-compaction threshold were sent
#     to the provider BEFORE compacting; pi now compacts between tool execution
#     and the next assistant response in the same run. This is the shape of
#     nearly every session here (multi-hundred-KB logstream/palace tool output).
#   - #8345 a resumed session corrupted its next appended entry when the JSONL
#     lacked a trailing newline. That file is the memory feeder's own input.
#     Measured on tor-ms22 before the bump: 49/49 transcripts end in a newline,
#     0 lines fail json.loads — the bug had not bitten this corpus.
#   - #8537 extension messages sent with `triggerTurn: false` WHILE THE AGENT IS
#     RUNNING were inserted between a tool call and its result, so
#     order-validating providers rejected the replayed history. The mempalace
#     mailbox is outside that precondition — it delivers at `agent_settled`
#     (idle) with `{deliverAs:"steer"}` and deliberately no `triggerTurn` — and
#     0.84.4 leaves the documented steer semantics unchanged, so RFC 003 §7.11
#     still holds. Recorded because the fix is what would make a future mid-run
#     delivery safe, which is the only reason we would ever change that call.
# One doc consequence, fixed in this same release: pi's own docs/compaction.md
# gained exactly one paragraph — the autoCompact threshold is now ALSO checked
# mid-run, after a tool batch's results are appended. See
# docs/observational-memory.md §3, which had said compaction is only checked
# when pi goes idle.
#
# AUDITED AT 0.84.3 (2026-08-25, was 0.84.2): upstream's notes carry a
# "Breaking Changes" heading — `GoogleThinkingLevel` renamed to
# `GoogleApiThinkingLevel`. INERT FOR THIS IMAGE: all four vendored companions
# (/opt/pi-fork, /opt/pi-observational-memory, /opt/pi-atelier, /opt/pi-studio)
# were grepped for that symbol and reference it ZERO times, so nothing here
# couples to the renamed type. Recorded because the heading will look alarming
# to the next reader doing step 1 above — the audit is done, don't redo it.
# Adopted for two fixes that land squarely on this repo's own vendored-skill
# wiring (see devbox-skill-reconcile, v1.8.5): nested Markdown skills inside
# `.agents/skills/<group>/` directories were not discovered, and root Markdown
# files such as README.md / AGENTS.md inside a skill dir were reported as
# broken skills unless they declared valid skill frontmatter.
#
# v1.8.13: 0.84.4 -> 0.85.1. SKIP 0.85.0 deliberately — it accidentally
# published internal experimental code and extra subpaths, breaking SDK
# imports (upstream #9132); 0.85.1 exists specifically to undo that, with the
# supported SDK and stdio RPC API unchanged. Audited: no Breaking/Removed
# changelog headings in either release, engine floor unchanged (>=22.19.0,
# container runs 22.23.2), runtime deps 20 -> 19. User-visible changes are the
# streaming indicator moving into the editor border and faster fullscreen
# transcript search; no deprecation language anywhere.
#
# Verified EMPIRICALLY rather than from the changelog, because a pi bump has
# hung the TUI before (pi-atelier < 0.7.1 + pi >= 0.84): 0.85.1 was
# side-installed and driven under a pty against all four companion extensions,
# with atelier v0.10.0 AND v0.10.1 — five combinations, each rendering alive
# with a CPU delta of 0.00-0.01s over a 5s window, where the known hang
# signature is ~5s of sustained CPU. Two-sided check: the atelier sidebar
# painted ACTIVITY+WORKSPACE identically to the 0.84.4 control, so the test
# could distinguish "loaded" from "silently absent".
#
# v1.9.4: HELD at 0.85.1 while 0.86.1 and 0.87.0 exist upstream. 0.87.0's
# changelog: "Removed the inherited `shouldStopAfterTurn` agent option. Use
# `finishTurn` and return `{ action: "end" }` instead" (no issue number on
# that line); 0.86.0 moved provider stream inputs to `TranscriptContext`, with
# system prompts read from `context.messages`. pi-observational-memory 3.1.4
# (the `master` ref baked below) still uses both the old option and
# `AgentContext.systemPrompt` in its observer, reflector and dropper workers —
# measured 2026-09-22 in src/agents/*/agent.ts, both the baked 3.1.3 tree and
# upstream master 3.1.4: `shouldStopAfterTurn` 1 per worker (3), `finishTurn`
# 0, `systemPrompt` 1 per worker. Its peerDependencies are `*`,
# so nothing at install time would refuse; it would break at runtime (turn
# caps ignored, workers losing their specialised prompts). Upstream tracks it
# as pi-observational-memory #82 with fix PR #83 (opened 2026-09-21, mergeable,
# not merged at this writing). Bump pi and pi-obsmem TOGETHER once #83 has
# shipped in a release. The other extensions were checked against the 0.86.0
# and 0.87.0 breaking lists and are clean: ssh-controlmaster's `user_bash`
# handler already returns `undefined | { operations }` (0.86.0 fail-closed
# contract) and its registerTool calls spread the built-in tools so they
# carry parameter schemas (#9300). 0.86.1 as an intermediate is untested and
# not worth the pty matrix for a stop that #83 will make moot.
ARG PI_VERSION=0.85.1
ARG PI_TOOLKIT_REF=main
ARG PI_EXTENSIONS_REF=main
# Repo URLs default to the canonical gitea origin but are overridable so a
# relocated/forked build can clone from a mirror or a different host
# without editing this Dockerfile — same pattern as PI_FORK_REPO /
# PI_OBSMEM_REPO / PI_STUDIO_REPO below.
ARG PI_TOOLKIT_REPO=https://gitea.jordbo.se/joakimp/pi-toolkit.git
ARG PI_EXTENSIONS_REPO=https://gitea.jordbo.se/joakimp/pi-extensions.git
# pi-fork (fork tool) + pi-observational-memory (recall tool) live on GitHub
# under elpapi42. CI resolves these to commit SHAs to defeat the same
# cache-hit footgun that affects PI_VERSION.
ARG PI_FORK_REPO=https://github.com/elpapi42/pi-fork.git
ARG PI_FORK_REF=master
ARG PI_OBSMEM_REPO=https://github.com/elpapi42/pi-observational-memory.git
ARG PI_OBSMEM_REF=master
# pi-atelier (TUI sidebar: ordered panels, split-pane, themes) is PINNED TO A
# TAG, which CI resolves to that tag's commit SHA — same treatment as
# pi-studio, for reproducibility plus cache-busting.
#
# This floor is hard-earned. pi-atelier 0.6.0/0.7.0 wrapped pi's PRIVATE TUI
# renderer, and under pi 0.84 that wrapper recursed: pi hung at startup with
# sustained CPU. Upstream fixed the recursion in 0.7.1 and restored the
# non-overlapping split in 0.7.2 — "avoiding the recursive render path that
# caused startup hangs and sustained CPU usage". Its own peerDependencies
# still say `>=0.80.7`, which does NOT encode that floor, so nothing would
# have warned us: NEVER pair pi-atelier < 0.7.1 with pi >= 0.84. Bump this
# pin and PI_VERSION together, checking atelier's CHANGELOG for the pi
# version it claims to track.
#
# AUDITED AT v0.10.0 (2026-08-31, was v0.8.2 — two minor releases): no
# BREAKING notice in either release, and both are UI-only (Sidebar calm during
# an active Turn, composer frame + Status Rail, fullscreen-copy-safe Sidebar,
# Windows path normalisation, Workspace Pulse deferred until pi trusts the
# project). The one coupling that matters runs the OPPOSITE way to the floor
# above: v0.9.0 renders the Sidebar as a separate split-layout child and
# therefore "raises the minimum supported Pi version to 0.84.0", which its
# peerDependencies do encode this time (`>=0.84.0`, up from `>=0.80.7`).
# Satisfied with room to spare by PI_VERSION 0.84.4 above — and note that both
# executable floors (scripts/smoke-test.sh, scripts/recreate-sanity-check.sh)
# compare with `sort -V`, so 0.10.0 >= 0.7.1 is evaluated correctly rather than
# as the string comparison that would read 0.10.0 as older than 0.7.1.
# Pairs deliberately with pi 0.84.4's own fullscreen selection-copy controls:
# atelier keeps Sidebar content out of the transcript selection, pi adds
# `fullscreenCopyOnSelect` + Ctrl+X for the selection itself.
#
# No `npm install` step, unlike pi-fork/pi-observational-memory/pi-studio:
# pi-atelier declares ZERO runtime dependencies (only peerDeps, satisfied by
# the baked pi) and has no build step — pi loads its TypeScript directly from
# the /opt checkout. Adding an install here would be a no-op that only costs
# build time.
ARG PI_ATELIER_REPO=https://github.com/michaelmjhhhh/pi-atelier.git
# v1.8.13: v0.10.0 -> v0.10.1. Refactor-only upstream (formatters, tests,
# panel identity); peerDependencies declare pi >=0.84.0, so it spans both the
# old and new pin. Included because it was already exercised: the pty matrix
# for PI_VERSION above ran atelier v0.10.1 against pi 0.85.1 and painted the
# sidebar identically to v0.10.0.
#
# v1.9.4: v0.10.1 -> v0.10.3 (both v0.10.2 and v0.10.3 released 2026-09-22).
# Fixes only per the release notes: sidebar text/borders preserved beside
# inline images (#53), transcript images hidden while capturing overlays are
# open, Workspace Pulse skips redundant HEAD/diff when nothing tracked changed
# (#61), sidebar height from row counts (#59), git/usage scans suspended while
# disabled, Display Revert + Undo ordering. Checked before bumping: package.json
# at v0.10.3 still declares zero runtime dependencies and no build script (so
# the no-`npm install` reasoning above holds) and peerDependencies are still
# pi >=0.84.0, so it still spans the pinned 0.85.1. 13 commits v0.10.1..v0.10.3,
# all under src/ tests/ docs/ scripts/ plus metadata; no entry-point move.
ARG PI_ATELIER_REF=v0.10.3
# Human-readable tag PI_ATELIER_REF was resolved from; recorded as a label.
ARG PI_ATELIER_VERSION=v0.10.3

RUN set -e && \
    # git_fetch_ref: clone-equivalent helper that accepts EITHER a branch name
    # OR a commit SHA as $ref. Uses `git fetch <ref> + checkout FETCH_HEAD`
    # which (a) works with both name and SHA forms uniformly, and (b) defeats
    # the registry-buildcache footgun when CI passes a resolved SHA. The
    # earlier helper `git_clone_retry` (using `git clone --branch`) only
    # worked with branch names — a SHA-resolved build-arg made `git clone
    # --branch <40-char-SHA>` fail with "Remote branch not found". Surfaced
    # in pi-devbox v1.0.0-rerun (run 374) 2026-06-10 and fixed by switching
    # all four clones to git_fetch_ref. Both Gitea and GitHub allow fetching
    # arbitrary commits by default (uploadpack.allowReachableSHA1InWant).
    git_fetch_ref() { \
      url="$1"; ref="$2"; dest="$3"; \
      rm -rf "$dest"; mkdir -p "$dest"; \
      git -C "$dest" init -q && git -C "$dest" remote add origin "$url" && \
      for i in 1 2 3 4 5; do \
        if git -C "$dest" fetch --depth 1 origin "$ref" && git -C "$dest" checkout -q FETCH_HEAD; then return 0; fi; \
        echo "git fetch $url@$ref failed (attempt $i/5), retrying in $((i*5))s..."; \
        sleep $((i*5)); \
      done; \
      return 1; \
    } && \
    # prune_foreign_natives: npm 11 (shipped with Node 24) installs EVERY optional
    # platform package of a native dependency, not just the one matching the host.
    # TWO families are affected in this image, and BOTH have been measured — add a
    # family here only after measuring it, never by widening the pattern on a hunch:
    #
    #   @esbuild/<platform>               26 dirs, 284 MB   (found first, v1.9.1)
    #   @mariozechner/clipboard-<triple>  11 dirs,  12 MB per site, 10 MB foreign
    #
    # esbuild declares those with os/cpu constraints, but npm 11 ignores them and
    # ALSO ignores --os/--cpu and an npmrc carrying os=/cpu= (all three measured).
    # So prune explicitly, keeping only the host platform, computed from
    # `node -p process.arch` so one line stays correct on amd64 and arm64.
    # Measured on pi-fork's tree: npm 10.9.8 -> 165 MB, npm 11.19.0 -> 449 MB,
    # and the 165 MB figure reproduces what v1.9.0's predecessor actually shipped.
    #
    # WHY THE CLIPBOARD FAMILY WAS ADDED (2026-09-11): v1.9.1 pruned @esbuild only
    # and still shipped +131 MB compressed over v1.8.14. That residual was
    # attributed by listing the PUBLISHED arm64 layer tarballs straight from the
    # registry (there is no docker CLI inside the container, so `docker history`
    # was not available):  +110 MB /root/.npm/_cacache (purged below) and +21 MB of
    # clipboard platform packages across the two install sites — 131 MB total, so
    # the delta is now fully accounted for with no unexplained remainder.
    #
    # Keeping linux-$arch-{gnu,musl} is deliberate: clipboard's napi-rs loader
    # tries ./<name>.node then the platform package, per platform in try/catch, and
    # chooses gnu vs musl at runtime from its own isMusl() probe — so both host-arch
    # branches must survive. The musl package is a 420-byte stub, i.e. free. The
    # bare wrapper `@mariozechner/clipboard` has no hyphen suffix and therefore
    # cannot match the regex below. Verified on arm64 against a copy of the real
    # tree before this was written: after pruning to those two,
    # require('@mariozechner/clipboard') still loads and exports all 18 functions.
    # esbuild likewise still compiles TS via transformSync at both install sites.
    # This removes dead weight, not function.
    #
    # MUST run in the SAME layer as the npm installs above: deleting in a later RUN
    # leaves the bytes in this layer and shrinks the image by nothing.
    # NOTE the single backslash in -printf '%f\n': Docker passes '\\n' through
    # verbatim, so v1.9.1's doubled version printed a mangled "li ux-arm64"
    # (find emitted a literal backslash, then `tr` translated the n out of the
    # name). Confirmed from the published image's own recorded created_by.
    prune_foreign_natives() { \
      arch="$(node -p process.arch)"; \
      find /usr/lib/node_modules /opt -type d -regex '.*/@esbuild/[^/]+' \
           ! -name "linux-$arch" -prune -exec rm -rf {} + ; \
      find /usr/lib/node_modules /opt -type d -regex '.*/@mariozechner/clipboard-[^/]+' \
           ! -name "clipboard-linux-$arch-gnu" ! -name "clipboard-linux-$arch-musl" \
           -prune -exec rm -rf {} + ; \
      echo "native platform dirs kept: $(find /usr/lib/node_modules /opt -type d \( -regex '.*/@esbuild/[^/]+' -o -regex '.*/@mariozechner/clipboard-[^/]+' \) -printf '%f\n' 2>/dev/null | sort | uniq -c | tr '\n' ' ')"; \
    } && \
    # purge_build_caches: the build's own download caches are NOT free — they land
    # in whichever layer created them. Measured on the published v1.9.1 arm64
    # variant layer: root/.npm/_cacache was 145.2 MB of a 401.9 MB layer (35.2 MB
    # in v1.8.14), the single biggest item in the +131 MB residual, because npm 11
    # caches every platform tarball it fetched — including the ones just pruned.
    # Nothing at runtime reads it: the build runs as root, the container runs as
    # `developer` with its own cache under $HOME (and $HOME/.pi is a volume).
    # DELIBERATELY NOT purged here: /tmp/node-compile-cache (1.3 MB, written by
    # `pi --version` below). The manifest RUN at the end of this file calls
    # `pi --version` again, so deleting it here only relocates those bytes into
    # that layer instead of removing them from the image — measured, not assumed:
    # today the manifest layer is 128 kB precisely because it finds the cache warm.
    purge_build_caches() { \
      npm cache clean --force >/dev/null 2>&1 || true; \
      rm -rf /root/.npm; \
    } && \
    if [ "${PI_VERSION}" = "latest" ]; then \
      NPM_CONFIG_PREFIX=/usr npm install -g @earendil-works/pi-coding-agent ; \
    else \
      NPM_CONFIG_PREFIX=/usr npm install -g @earendil-works/pi-coding-agent@${PI_VERSION} ; \
    fi && \
    pi --version && \
    git_fetch_ref   "${PI_TOOLKIT_REPO}"    "${PI_TOOLKIT_REF}"    /opt/pi-toolkit && \
    git_fetch_ref   "${PI_EXTENSIONS_REPO}" "${PI_EXTENSIONS_REF}" /opt/pi-extensions && \
    git_fetch_ref   "${PI_FORK_REPO}"   "${PI_FORK_REF}"   /opt/pi-fork && \
    git_fetch_ref   "${PI_OBSMEM_REPO}" "${PI_OBSMEM_REF}" /opt/pi-observational-memory && \
    git_fetch_ref   "${PI_ATELIER_REPO}" "${PI_ATELIER_REF}" /opt/pi-atelier && \
    (cd /opt/pi-fork && npm install --omit=dev --no-audit --no-fund) && \
    (cd /opt/pi-observational-memory && npm install --omit=dev --no-audit --no-fund) && \
    prune_foreign_natives && \
    purge_build_caches && \
    echo "pi-toolkit at $(cd /opt/pi-toolkit && git rev-parse --short HEAD)" && \
    echo "pi-extensions at $(cd /opt/pi-extensions && git rev-parse --short HEAD)" && \
    echo "pi-fork at $(cd /opt/pi-fork && git rev-parse --short HEAD)" && \
    echo "pi-observational-memory at $(cd /opt/pi-observational-memory && git rev-parse --short HEAD)" && \
    echo "pi-atelier at $(cd /opt/pi-atelier && git rev-parse --short HEAD) (${PI_ATELIER_VERSION})"

# ── Image-baked skill refresh: pi-extensions (Option 1 over Option 2) ──
# rootfs ships a VENDORED snapshot of the pi-extensions skill at
# /usr/local/share/pi-devbox/skills/pi-extensions/ (the "floor" — guarantees the
# skill is always in the image). The pi-extensions PACKAGE repo now co-locates
# the canonical skill under skill/, so here — after the pinned clone — we copy
# that over the snapshot. Result: a normal build ships the fresh, package-owned
# copy (pinned + recorded in the manifest via PI_EXTENSIONS_REF); a build whose
# ref predates the skill, or a fork pointing at a mirror without it, still ships
# the committed snapshot. The skill calls ./evaluate-extension-usage.py, so it
# is copied alongside. Idempotent and cache-safe (depends only on the clone).
RUN if [ -f /opt/pi-extensions/skill/SKILL.md ]; then \
      cp /opt/pi-extensions/skill/SKILL.md \
         /usr/local/share/pi-devbox/skills/pi-extensions/SKILL.md && \
      if [ -f /opt/pi-extensions/skill/evaluate-extension-usage.py ]; then \
        cp /opt/pi-extensions/skill/evaluate-extension-usage.py \
           /usr/local/share/pi-devbox/skills/pi-extensions/evaluate-extension-usage.py ; \
      fi && \
      echo "refreshed pi-extensions skill from package @ $(cd /opt/pi-extensions && git rev-parse --short HEAD)" ; \
    else \
      echo "pi-extensions package has no skill/ at this ref — keeping vendored snapshot" ; \
    fi

# ── pi-devbox awareness: append our pointer to the global AGENTS.md ──
# pi loads a SINGLE global instruction file (~/.pi/agent/AGENTS.md), which
# pi-toolkit's install.sh re-symlinks to /opt/pi-toolkit/pi-global-AGENTS.md on
# every container start. There is no second global slot, and that file is
# root-owned (not writable by the runtime user), so we compose at BUILD time:
# append the pi-devbox managed block to pi-toolkit's file here, after the clone.
# Idempotent via a marker grep so a rebuilt layer never double-appends. This
# makes every container proactively aware of the pi-devbox-environment skill;
# the snippet itself is gated (only fires when /usr/local/lib/pi-devbox exists).
RUN if [ -f /opt/pi-toolkit/pi-global-AGENTS.md ] && \
       ! grep -q 'pi-devbox:managed-block' /opt/pi-toolkit/pi-global-AGENTS.md; then \
      printf '\n' >> /opt/pi-toolkit/pi-global-AGENTS.md && \
      cat /usr/local/share/pi-devbox/pi-global-AGENTS.append.md >> /opt/pi-toolkit/pi-global-AGENTS.md && \
      echo "appended pi-devbox block to pi-global-AGENTS.md" ; \
    else \
      echo "pi-devbox block already present or pi-global-AGENTS.md missing (skipped)" ; \
    fi

# ── Optional: pi-studio (:latest-studio variant) ─────────────────────
# pi-studio (omaclaren/pi-studio) is a pi-package + theme providing a
# two-pane browser workspace: prompt/response editor, KaTeX/Mermaid live
# preview, and tmux-backed literate REPLs. Off by default; the studio
# variant sets INSTALL_STUDIO=true.
#
# Vendored to /opt/pi-studio and registered at container start by
# entrypoint-user.sh via `pi install /opt/pi-studio` — the SAME pattern
# as pi-fork / pi-observational-memory above. We deliberately do NOT run
# `pi install <git-url>` at build time: that writes into ~/.pi/agent,
# which is a named volume, so a build-time install collides with / is
# shadowed by the volume on first run. Vendoring to /opt (an image layer)
# + a runtime local-path install keeps it on the image and idempotent.
#
# No build step is needed: pi-studio ships its browser bundle prebuilt in
# git (client/studio-client.js) and pi loads index.ts directly; its
# package.json scripts are only test/typecheck. So we just fetch + install
# the 3 prod deps (@earendil-works/pi-ai, @sinclair/typebox, ws).
#
# PI_STUDIO_REF is CI-resolved to a commit SHA to defeat the registry-
# buildcache cache-hit footgun (see the PI_VERSION note above).
ARG INSTALL_STUDIO=false
ARG PI_STUDIO_REPO=https://github.com/omaclaren/pi-studio.git
ARG PI_STUDIO_REF=main
# PI_STUDIO_VERSION is the human-readable tag (e.g. v0.9.36) that PI_STUDIO_REF
# was resolved from; recorded as a label below for at-a-glance identification.
# Only meaningful for the studio variant (default `none` otherwise).
#
# v1.8.13 — READ THIS BEFORE REASONING ABOUT WHICH pi-studio SHIPS. Neither
# default below survives a CI build. `resolve-versions` in
# .gitea/workflows/docker-publish.yml passes BOTH as build-args (studio_ref and
# studio_tag), and it deliberately selects the newest STABLE semver tag: its
# filter is `^v?[0-9]+\.[0-9]+\.[0-9]+$`, which excludes pre-releases. So a
# PUBLISHED v1.8.13 studio image contains pi-studio v0.9.59 (commit 9eed84f,
# = refs/tags/v0.9.59^{}), NOT the v0.9.60-rc.0 that `main` currently points at
# (658536f). The `main` default here only applies to a local `docker build`
# that passes no studio args.
#
# That upstream-tag-over-main choice is intentional and documented at the
# resolve step: pi-studio keeps tagging every version but stopped publishing
# GitHub Releases at v0.5.55 and pushes freely to main, so pinning main risked
# baking half-finished commits that land after a tag.
#
# Corrected here on 2026-09-06 after reading the run-639 resolve-versions
# output: the v1.8.13 audit had recorded "RC adopted deliberately" and set this
# ARG to v0.9.60-rc.0, which was measured at the wrong layer — a Dockerfile
# default cannot answer "what will CI publish?" when CI overrides it. Left at
# `none` rather than pinned to a tag, because a hardcoded pre-release here goes
# stale the moment main moves and would re-tell the same lie to the next reader.
# Consequence worth keeping: the RC's opt-in Studio network binding is NOT in
# any published v1.8.13 image, so it needs no audit for this release.
ARG PI_STUDIO_VERSION=none
RUN if [ "${INSTALL_STUDIO}" = "true" ]; then \
      set -e; \
      # Same prune + cache purge as the main install RUN — see the comments there.
      # They have to be redefined because shell functions do not survive across
      # layers, and they have to run in THIS layer because pi-studio's npm install
      # happens here: deleting in a later RUN would leave the bytes in this layer
      # and shrink nothing. pi-studio pulls its own pi-coding-agent copy, so it is
      # a third ~274 MB site on top of the two in the non-studio variant — and its
      # npm install refills /root/.npm, which the main RUN emptied in ITS layer.
      prune_foreign_natives() { \
        arch="$(node -p process.arch)"; \
        find /usr/lib/node_modules /opt -type d -regex '.*/@esbuild/[^/]+' \
             ! -name "linux-$arch" -prune -exec rm -rf {} + ; \
        find /usr/lib/node_modules /opt -type d -regex '.*/@mariozechner/clipboard-[^/]+' \
             ! -name "clipboard-linux-$arch-gnu" ! -name "clipboard-linux-$arch-musl" \
             -prune -exec rm -rf {} + ; \
        echo "native platform dirs kept: $(find /usr/lib/node_modules /opt -type d \( -regex '.*/@esbuild/[^/]+' -o -regex '.*/@mariozechner/clipboard-[^/]+' \) -printf '%f\n' 2>/dev/null | sort | uniq -c | tr '\n' ' ')"; \
      }; \
      purge_build_caches() { \
        npm cache clean --force >/dev/null 2>&1 || true; \
        rm -rf /root/.npm; \
      }; \
      rm -rf /opt/pi-studio && mkdir -p /opt/pi-studio && \
      git -C /opt/pi-studio init -q && \
      git -C /opt/pi-studio remote add origin "${PI_STUDIO_REPO}" && \
      ok=0; for i in 1 2 3 4 5; do \
        if git -C /opt/pi-studio fetch --depth 1 origin "${PI_STUDIO_REF}" && \
           git -C /opt/pi-studio checkout -q FETCH_HEAD; then ok=1; break; fi; \
        echo "git fetch pi-studio@${PI_STUDIO_REF} failed (attempt $i/5), retrying in $((i*5))s..."; \
        sleep $((i*5)); \
      done; \
      [ "$ok" = "1" ] && \
      (cd /opt/pi-studio && npm install --omit=dev --no-audit --no-fund) && \
      prune_foreign_natives && \
      purge_build_caches && \
      echo "pi-studio at $(cd /opt/pi-studio && git rev-parse --short HEAD)"; \
    fi

# STUDIO_PORT: advisory default consumed by docker-compose port publishing
# and the recommended `/studio --no-browser --port "$STUDIO_PORT"` launch.
# Harmless in the non-studio variant. NOTE: pi-studio hard-binds the server
# to 127.0.0.1 inside the container (index.ts: .listen(port,"127.0.0.1")),
# so reaching it from a browser needs a loopback bridge or host networking —
# see the "Using pi-studio" section in README.md.
ENV STUDIO_PORT=8765

# ── Optional: Go toolchain ───────────────────────────────────────────
# Off by default; opt in for users who run Go tools inside the devbox.
ARG INSTALL_GO=false
ARG GO_VERSION=latest
RUN if [ "${INSTALL_GO}" = "true" ]; then \
      GOARCH=$(case "${TARGETARCH}" in amd64) echo "amd64" ;; arm64) echo "arm64" ;; *) echo "amd64" ;; esac) && \
      V="${GO_VERSION}" && \
      if [ "$V" = "latest" ]; then \
        V=$(curl -fsSL --retry 5 --retry-delay 5 --retry-all-errors "https://go.dev/dl/?mode=json" | \
            awk -F'"' '/"version":/ { sub(/^go/,"",$4); print $4; exit }'); \
      fi && \
      [ -n "$V" ] && \
      echo "Installing Go ${V}" && \
      curl -fsSL --retry 5 --retry-delay 5 --retry-all-errors "https://go.dev/dl/go${V}.linux-${GOARCH}.tar.gz" | tar -C /usr/local -xz && \
      ln -s /usr/local/go/bin/go /usr/local/bin/go && \
      ln -s /usr/local/go/bin/gofmt /usr/local/bin/gofmt; \
    fi

# ── Build provenance: OCI labels + on-disk build manifest ────────────
# Records exactly which pi version and companion-repo commits were baked
# into THIS image, so a published tag is self-describing and reproducible
# after the fact (CI logs rotate; a released image must not depend on
# them). Previously the resolved SHAs only ever reached the CI build log.
#
# These ARGs are declared LAST, immediately before the layer that uses
# them, so a changing BUILD_DATE / RELEASE_TAG / SOURCE_REVISION never
# invalidates the expensive pi-install / clone layers above.
ARG RELEASE_TAG=dev
ARG BUILD_DATE=
ARG SOURCE_REVISION=
# MEMPALACE_TOOLKIT_REF is consumed in Dockerfile.base; re-declared here
# only so its intended ref lands in the label set alongside the others.
ARG MEMPALACE_TOOLKIT_REF=main
# ── Vendored skill provenance ─────────────────────────────────────────
# The vendored mempalace SKILL.md is the ONLY baked artefact with no /opt
# clone behind it: its upstream (the skillset repo) is PRIVATE, so the
# image cannot clone it and CI cannot resolve its HEAD (see VENDORED.md).
# Consequence through v1.8.7: the snapshot was ANONYMOUS — nothing in the
# image or the repo recorded which skillset commit it was taken from, so
# the only staleness check available was a hand-maintained phrase canary in
# scripts/smoke-test.sh, which by construction can only detect "older than
# what I remembered to pin", never "older than skillset main".
#
# Recording the ref costs nothing and makes the question answerable. It is
# deliberately a plain ARG DEFAULT rather than a CI-resolved output:
#   * the value is a fact about the committed snapshot, so it belongs in
#     the tree next to it — not in a workflow that a local `docker build`
#     never runs (same reasoning as MEMPALACE_VERSION living in
#     Dockerfile.base rather than being duplicated in docker-publish.yml);
#   * CI therefore needs NO new build-arg at any of its four
#     Dockerfile.variant call sites (smoke, smoke-studio, build-variant,
#     build-variant-studio) — a plumbing change that is easy to
#     under-apply to only two of them;
#   * and it needs no credential for a private repo.
# Bump it with scripts/vendor-mempalace-skill.sh, which refreshes the file
# and rewrites this line together, so the pair cannot drift apart by hand.
# This ARG lives in Dockerfile.variant ON PURPOSE: Dockerfile.base and
# rootfs/ are both hashed into base_tag, so recording provenance here costs
# no ~67-minute base rebuild. (scripts/check-base-hash.sh scans only
# Dockerfile.base, so no folding into the base hash is required — nor would
# it be correct, since this ARG changes nothing about the base's contents.)
ARG SKILLSET_SNAPSHOT_REF=e9e45f7acdde490c3b5d24ce5f508bff8785c2c7

# Dockerfile.base sets description="pi-devbox — base image (variant-independent)"
# and every variant INHERITS it, so both published images used to advertise
# themselves on Docker Hub as the base image. A LABEL cannot branch on
# INSTALL_STUDIO, so the description arrives as a build-arg: CI passes the
# variant-specific string (see docker-publish.yml), and the default below keeps
# a plain `docker build -f Dockerfile.variant` honest rather than misleading.
ARG IMAGE_TITLE="pi-devbox"
ARG IMAGE_DESCRIPTION="pi-devbox — development container for the pi coding agent"

LABEL org.opencontainers.image.version="${RELEASE_TAG}" \
      org.opencontainers.image.revision="${SOURCE_REVISION}" \
      org.opencontainers.image.created="${BUILD_DATE}" \
      org.opencontainers.image.title="${IMAGE_TITLE}" \
      org.opencontainers.image.description="${IMAGE_DESCRIPTION}" \
      description="${IMAGE_DESCRIPTION}" \
      se.jordbo.pi-devbox.pi-version="${PI_VERSION}" \
      se.jordbo.pi-devbox.pi-toolkit-ref="${PI_TOOLKIT_REF}" \
      se.jordbo.pi-devbox.pi-extensions-ref="${PI_EXTENSIONS_REF}" \
      se.jordbo.pi-devbox.pi-fork-ref="${PI_FORK_REF}" \
      se.jordbo.pi-devbox.pi-obsmem-ref="${PI_OBSMEM_REF}" \
      se.jordbo.pi-devbox.pi-atelier-ref="${PI_ATELIER_REF}" \
      se.jordbo.pi-devbox.pi-atelier-version="${PI_ATELIER_VERSION}" \
      se.jordbo.pi-devbox.mempalace-toolkit-ref="${MEMPALACE_TOOLKIT_REF}" \
      se.jordbo.pi-devbox.pi-studio-ref="${PI_STUDIO_REF}" \
      se.jordbo.pi-devbox.pi-studio-version="${PI_STUDIO_VERSION}" \
      se.jordbo.pi-devbox.skillset-snapshot-ref="${SKILLSET_SNAPSHOT_REF}"

# The manifest is written from GROUND TRUTH — the actual checked-out HEAD
# of each /opt clone and the live `pi --version` — not merely the intended
# build-args. That way it also exposes a clone that silently resolved to
# something other than the requested ref. pi-studio is present only in the
# studio variant (JSON null otherwise).
RUN set -e; \
    mkdir -p /etc/pi-devbox; \
    rev() { git -C "$1" rev-parse HEAD 2>/dev/null || echo "unknown"; }; \
    PI_V="$(pi --version 2>/dev/null | head -n1 | tr -d '\r\n')"; \
    # mempalace CORE (the PyPI package behind the MCP tools) is installed in
    # Dockerfile.base via `uv tool install`, so no /opt clone reveals it and
    # until v1.8.6 the manifest could not answer "which palace shipped here?" —
    # a palace bug could not be correlated to an image, which is precisely the
    # correlation this file exists to provide. Read from the INSTALLED BINARY,
    # not from ARG MEMPALACE_VERSION, per the ground-truth rule above: that is
    # what catches an install which resolved to something other than the pin.
    # `mempalace --version` prints "MemPalace 3.7.1" — NAME-PREFIXED, unlike
    # pi's bare "0.84.2" — hence the $NF pick rather than a straight read. The
    # leading-digit test then rejects usage/error text (a renamed flag prints a
    # usage block) and degrades to JSON null, so this can never fail the build.
    MP_V="$(mempalace --version 2>/dev/null | head -n1 | tr -d '\r' | awk '{print $NF}')"; \
    case "$MP_V" in [0-9]*) MP_CORE="\"${MP_V}\"" ;; *) MP_CORE='null' ;; esac; \
    STUDIO_REV='null'; \
    if [ -d /opt/pi-studio/.git ]; then STUDIO_REV="\"$(rev /opt/pi-studio)\""; fi; \
    # The vendored skill snapshot's fingerprint is MEASURED here, not passed
    # in as a build-arg, per the ground-truth rule above: SKILLSET_SNAPSHOT_REF
    # is a CLAIM about which skillset commit the file came from, while this
    # hash is what the image actually ships. Recorded together they let any
    # reader with the skillset checked out — which on this fleet is every
    # host, since all four compose stacks mount it — verify the claim at
    # RUNTIME, without CI ever needing access to the private repo. Degrades
    # to JSON null rather than failing the build if the directory is absent;
    # the smoke assertion is what turns that into a loud failure.
    #
    # Hashes the whole DIRECTORY, not just SKILL.md: a single-file hash
    # answers "did this one file change", not "is the live copy the same
    # skill" — a live checkout that added or edited a SIBLING file (a
    # reference/ doc, a helper script) would still report "identical to
    # baked snapshot" against a file-only hash. pi-extensions already ships
    # two files for exactly this reason (SKILL.md + evaluate-extension-usage.py),
    # so this is not a hypothetical. Deterministic over `find | sort`, never
    # readdir order: relative paths + per-file sha256, folded into one hash.
    # pi-devbox-version mirrors this exact pipeline over the live directory so
    # the two sides are comparable — if you change this, change that too.
    tree_sha256() { \
      ( cd "$1" && find . -type f -print | LC_ALL=C sort | xargs -r sha256sum ) 2>/dev/null | sha256sum | cut -d' ' -f1; \
    }; \
    SKILL_SNAP='null'; \
    _snap_dir=/usr/local/share/pi-devbox/skills/mempalace; \
    if [ -d "$_snap_dir" ] && [ -n "$(find "$_snap_dir" -type f -print -quit)" ]; then \
      SKILL_SNAP="\"$(tree_sha256 "$_snap_dir")\""; \
    fi; \
    # ── WHICH pi-extensions skill copy actually shipped ──
    # Closes the silent-fallback hole. The refresh step above is guarded by
    # `[ -f /opt/pi-extensions/skill/SKILL.md ]`, so a build whose clone predates
    # the co-located skill (or a fork pointing at a mirror without it) keeps the
    # vendored floor and still succeeds — GREEN, with nothing anywhere recording
    # that a snapshot shipped instead of the package copy. Measured 2026-09-10:
    # the floor had been stale since 2026-07-30, so that fallback would have
    # shipped a six-week-old skill silently. The floor is fresh now and gated by
    # the skill-floor CI job, but "the fallback is currently harmless" is not the
    # same as "you can tell which copy you got", and only the second survives.
    #
    # MEASURED, never claimed, per the ground-truth rule above: the branch
    # condition is re-derived from the same test the refresh step used, and the
    # served bytes are then compared against the clone. A build-arg could not
    # express this at all, since the outcome depends on the clone's contents.
    #   package        served bytes == the clone's skill/  (the normal path)
    #   vendored-floor the clone has no skill/ at this ref  (fallback shipped)
    #   divergent      both exist but differ — e.g. the clone ships SKILL.md but
    #                  not evaluate-extension-usage.py, so the served directory is
    #                  a MIX of package and floor. Worth its own value: it is the
    #                  one state neither of the other two names honestly.
    # No OCI label mirrors this, deliberately: LABEL cannot take a value computed
    # in a RUN, and a label fed from an ARG would be exactly the claim-not-
    # measurement this block exists to avoid.
    _px_dir=/usr/local/share/pi-devbox/skills/pi-extensions; \
    PIEXT_SRC='null'; PIEXT_HASH='null'; \
    if [ -d "$_px_dir" ] && [ -n "$(find "$_px_dir" -type f -print -quit)" ]; then \
      PIEXT_HASH="\"$(tree_sha256 "$_px_dir")\""; \
      if [ -f /opt/pi-extensions/skill/SKILL.md ]; then \
        if [ "$(tree_sha256 "$_px_dir")" = "$(tree_sha256 /opt/pi-extensions/skill)" ]; then \
          PIEXT_SRC='"package"'; \
        else \
          PIEXT_SRC='"divergent"'; \
        fi; \
      else \
        PIEXT_SRC='"vendored-floor"'; \
      fi; \
    fi; \
    { \
      echo '{'; \
      echo "  \"release_tag\": \"${RELEASE_TAG}\","; \
      echo "  \"build_date\": \"${BUILD_DATE}\","; \
      echo "  \"source_revision\": \"${SOURCE_REVISION}\","; \
      echo "  \"pi_version\": \"${PI_V}\","; \
      # Sibling of pi_version, NOT a member of components{}: that map holds git
      # SHAs and `pi-devbox-version` renders it with .value[0:12], which would
      # silently truncate a longer version string.
      echo "  \"mempalace_version\": ${MP_CORE},"; \
      # Siblings, NOT members of components{}, for two independent reasons:
      # that map means "HEAD of a clone present in this image" and the
      # skillset is not cloned here (calling it a component would be a
      # lie a future reader would act on), and `pi-devbox-version` renders
      # every components{} value with .value[0:12] — which would truncate
      # a 64-hex sha256 into something that looks like a short commit.
      # Named `_tree_sha256`, not `_sha256`: it measures every file under the
      # vendored skill directory, not one file — see tree_sha256() above.
      echo "  \"skillset_snapshot_ref\": \"${SKILLSET_SNAPSHOT_REF}\","; \
      echo "  \"skillset_snapshot_tree_sha256\": ${SKILL_SNAP},"; \
      echo "  \"pi_extensions_skill_source\": ${PIEXT_SRC},"; \
      echo "  \"pi_extensions_skill_tree_sha256\": ${PIEXT_HASH},"; \
      echo "  \"components\": {"; \
      echo "    \"pi-toolkit\": \"$(rev /opt/pi-toolkit)\","; \
      echo "    \"pi-extensions\": \"$(rev /opt/pi-extensions)\","; \
      echo "    \"pi-fork\": \"$(rev /opt/pi-fork)\","; \
      echo "    \"pi-observational-memory\": \"$(rev /opt/pi-observational-memory)\","; \
      echo "    \"pi-atelier\": \"$(rev /opt/pi-atelier)\","; \
      echo "    \"mempalace-toolkit\": \"$(rev /opt/mempalace-toolkit)\","; \
      echo "    \"pi-studio\": ${STUDIO_REV}"; \
      echo "  }"; \
      echo '}'; \
    } > /etc/pi-devbox/build-manifest.json; \
    echo "── build manifest ──"; cat /etc/pi-devbox/build-manifest.json

# WORKDIR / ENTRYPOINT / CMD inherited from base.