--workspace is required with no environment fall-back: this process runs
unsandboxed, and a status run that quietly picked a workspace is one nobody
can audit. --check exits 1 on a stale cache, distinct from 2 for a failed run.
Byte-stability is measured, not asserted: the CLI is run twice under two
PYTHONHASHSEED values and the bytes compared, in both output formats. The
write boundary gets two digest tests rather than one -- without --oppdater
every byte stays put, with it exactly the diverging case's four cached keys
move and logg.jsonl, the body and every other file are byte-identical.
Co-Authored-By: Claude <claude-opus-5>
Eight cases, one per build-brief 6 state, dated relative to 2026-09-15. One
of them (havbris) carries frontmatter that deliberately disagrees with its
log, so the derived-truth rule has a fixture instead of only a docstring. One
(vaeroy-sjomat) is named for an employer with ae, o-slash and a-ring, so the
ASCII path rule has teeth on macOS NFD.
Six beslutninger.jsonl fixtures for M6's counting rules are written now, in
M2, because the store is append-only: type, skjema, delscore and vekt_hash
have to be right at the first write or they are wrong forever.
Co-Authored-By: Claude <claude-opus-5>
Iron Law deviation, stated rather than hidden: these tests passed on the
first run. The silence computation landed in 4669cc3 because neste_frist is
one of Step 17's four cached keys and is derived from the same thresholds --
the plan entangles the two steps, so the code could not be written in the
order the steps are numbered. What this file adds is the boundary evidence:
13/14/15, 6/7/8, 9/10/11, an autoreply that must not move the clock, and the
H9 distinction between no inbound RECORDED and no inbound existing.
Co-Authored-By: Claude <claude-opus-5>
Status derives from logg.jsonl alone; sak.md frontmatter is a cache and the
log wins where they disagree (risk H3). --oppdater is the only writer of the
four cached keys, and it leaves a key alone when the derivation is None --
neste_frist in vurderer/soker is the operator's application deadline and no
refresh may eat it.
Two rows of the plan's table are not 5.3 events. Decision ja and operator
close reach the case log as the decision-log records build-brief 5.7 already
mirrors there, so the event enum stays closed at eleven.
Co-Authored-By: Claude <claude-opus-5>
jobbsok could not start on stock Windows. `.mcp.json` named `bash` as the
command, and the five entry points behind it reached for grep, sed, find, awk,
zip and unzip. `bootstrap.sh` built the virtualenv, so a Windows adopter could
not even reach an interpreter. Two adopters are waiting and neither is
guaranteed to be on macOS, so this is the install, not a rough edge.
The Python layer was already clean -- no /tmp, no /usr, no os.uname, no home
directory assumption -- so only the shell layer moved. Behaviour is carried
over unchanged; the deliberate exceptions are listed in docs/.
THE ONE OPEN DECISION, AND WHY IT WAS FORCED
How does .mcp.json start an interpreter without a POSIX shell, when it is
called python3 on macOS and python or py on Windows? Measured against the
installed CLI, not assumed:
- The plugin mcpServers stdio schema has NO platform-conditional form. A
config carrying invented windows/darwin/platform keys was accepted and the
keys were silently discarded -- it fails quietly, not loudly.
- ${VAR:-default} IS expanded, in command, args and env.
- ${VAR} without a default is not safe: unset, it is passed through
unexpanded, so the spawn would try to run a program named ${VAR}.
- Windows spawns with shell:false, so a .py path as command is out.
- No single literal works. On this Mac, python and py are not on PATH.
So the default form is the only lever the schema offers:
"${JOBBSOK_LAUNCH_PYTHON:-python3}". macOS and Linux keep working with nothing
set; Windows sets one variable and needs no shell.
A SECOND VARIABLE, NOT A REUSE OF JOBBSOK_PYTHON
JOBBSOK_PYTHON names the interpreter to SERVE on: the launcher treats it as an
explicit operator choice, so it wins over the bootstrapped virtualenv. A
Windows adopter setting it merely to spell `python` would silently bypass that
virtualenv and serve WITHOUT the ingestion guard. JOBBSOK_LAUNCH_PYTHON only
says how to start the launcher. A test asserts the two never collapse into one.
O4 IS LEFT STANDING
The launcher still gates on the interpreter's version rather than on the guard
being importable. That is the shell version's semantics carried over on
purpose: harmless while nothing writes, a defect from M2, and an M2 decision.
VERIFY
- pytest tests/ -> 124 passed, exit 0 (was 112)
- grep -c '"command": "bash"' .mcp.json -> 0
- git ls-files 'scripts/*.sh' -> 0
- README install block names Windows, and neither WSL nor Git Bash
- server started end to end exactly as .mcp.json expands, and answered
initialize and tools/list
- the ported probe checker reproduces the shell version's output and exits 0
NOT MEASURED, AND NOT ASSUMED
Nothing here has ever run on Windows. Whether Cowork on Windows bridges to a
host-side stdio MCP as it does on this Mac is unmeasured -- docs/cowork-probe.md
covered macOS only. docs/cross-platform-port.md says what a Windows probe would
have to measure, and records two findings left deliberately untouched.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Plan Step 3. Verify green: `.venv/bin/python -m pytest tests/test_paths.py` ->
8 passed, exit 0. Full suite: 11 passed.
Test first, and RED was observed before a line of paths.py existed
(ModuleNotFoundError on collection).
Two measured risks drive the design, not one.
Risk C6 -- the host-side server runs unsandboxed with caller-supplied paths.
safe_join resolves BOTH operands with os.path.realpath before comparing, so
lexical traversal and symlink escape fall to the same check; a lexical check on
the joined string would have called the symlink case safe. The comparison is
component-aware, so a sibling whose name merely prefixes the root is outside.
Escape raises; it never clamps to an adjacent path.
Risk H8 -- macOS hands back NFD. slug normalises to NFC first, so a decomposed
name and its composed twin produce one slug rather than two directories. The
test asserts that equality on a real NFC/NFD pair, not on a lookalike.
No implicit default workspace: --workspace, else JOBBSOK_WORKSPACE, else a
`workspace:` line in ${CLAUDE_PLUGIN_DATA}/jobbsok.conf, else WorkspaceUnresolved.
Guessing at the operator's home directory is the one behaviour this module must
not have. This tightens build-brief section 5's `~/jobbsok-workspace` default
into an explicit order; the deviation is recorded in the plan's Assumptions.
scaffold is idempotent by only creating what is absent -- an existing
beslutninger.jsonl is never truncated. It is append-only, and a scaffold that
emptied it would destroy the decision log. The test proves this by populating
the workspace and asserting a byte-identical snapshot across a second run.
Collision rule is documented and tested: -2, then -3, counting up.
sak_id carries no `taken` parameter. An earlier draft had one; no step and no
test requires it, so it was unproven code and was removed rather than kept.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Plan Step 2. Verify green: `bash scripts/bootstrap.sh && .venv/bin/python -m
pytest tests/test_toolchain.py` -> 3 passed, exit 0.
Test first, and the RED was demonstrated rather than assumed: run against a
venv carrying pytest and the guard but not pytest-socket, the third test fails
with ModuleNotFoundError while the other two pass. The test discriminates.
pyproject.toml declares the dependencies as a PEP 735 group rather than an
installable distribution -- nothing here needs a build backend, since the tests
import from scripts/ via pytest's pythonpath. Measured before choosing it: pip
26.2.1 on this machine supports `install --group`, and bootstrap upgrades pip
first, so a pip too old fails loudly instead of silently skipping the guard.
The guard is pinned to the exact tag v1.3.0 and is not vendored. Verified the
tag resolves and the package exposes __version__ == "1.3.0"; that equality is
what the test asserts, not the pip metadata.
addopts carries --disable-socket and --strict-markers, which is why the
`network` marker is declared: with strict markers an undeclared marker would
make `-m 'not network'` an error rather than a filter, and the offline
guarantee would quietly stop being tested.
bootstrap.sh builds under ${CLAUDE_PLUGIN_DATA} when set (survives a plugin
update) and falls back to the repo-root .venv for development -- risk H2. It
refuses an interpreter below 3.10 instead of building on it, because python3
here can resolve to 3.9.6 under a GUI-spawned process.
Exercised, not just written: re-running is idempotent (exit 0); --med-xlsx
installs the extra (openpyxl 3.1.5 importable); an unknown argument exits 2
with usage; a missing JOBBSOK_PYTHON interpreter refuses loudly. bash 3.2-clean
(system /bin/bash 3.2.57 -n passes) and ASCII-only.
.gitignore needed no change: `.venv/` was already on line 12 from the initial
commit, and `git check-ignore -v .venv` confirms it matches.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Plan Step 1. Builds the probe vehicle and the checklist; does NOT answer it.
The four questions all require the operator in a live Cowork session on this
Mac, and that is a fact about the measurement rather than a caveat: measured
2026-09-04, the session mode is not readable from disk (cowork_settings.json
carries only extraKnownMarketplaces; the desktop config carries
coworkNetworkMode and a trusted-folder list, neither states where a session
runs), and the other three each need a plugin installed in a live session.
The step's Verify is therefore RED on purpose and stays red until the operator
answers:
test "$(grep -cE '...' docs/cowork-probe.md)" = 4 -> exit 1 (0 of 4 matched)
Validated in both directions: a fully answered copy exits 0, a copy with three
of four answered exits 1. The gate can pass, so its failure means something.
Probe vehicle: jobbsok-probe, exactly four files under
tests/fixtures/cowork-probe/ -- manifest, skills/probe-versjon/SKILL.md,
.mcp.json declaring the stdio server probe-tools, and probe_tools.py (standard
library only). Smoke-tested from Claude Code: initialize handshake completes,
tools/list returns probe_ping, tools/call returns an interpreter version, an
unknown tool name is rejected. What is NOT verified is whether Cowork ever
starts it -- that is the question.
Archive is built from an explicit four-file include list, never zip -r over the
repo root; verified to contain no .git, STATE.md, .venv or .claude/ entry.
The degradation branch for each possible nei is written down now, before any
answer is known, so it is not decided under pressure later.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
De to maskinelle sjekkene paa at planrevisjonen holder laa i en scratchpad og
var i ferd med aa bli borte (samme naeromkomst som oekt 2s script). Flyttet inn
i repoet, gjort sted-uavhengige (repo-roten resolveres fra $0) og med en guard
naar plan.md/brief.md mangler -- de er local-only paa denne offentlige remoten,
og «fant ingenting» skal ikke lese som «alt groent» (exit 2, ikke 0).
Kjoert fra tests/plan-gates/ etter flyttingen:
brief_criteria.sh PASS=33 FAIL=0
stale_text.sh PASS=12 FAIL=0
Negativkontroll: mot en tom plan gir brief_criteria.sh PASS=6 FAIL=27 og exit 1,
og manglende fil gir SKIP + exit 2. Gaten kan altsaa feile.
PM-autorisert forsteg (amendment til ordre 20260904T150903Z), utenfor planens
sesjon-1-gjerde.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
