fix(harness): run-keyed run-scoped state files — CONC-A1 (same-domain runs corrupted shared deploy-count)
All checks were successful
continuous-integration/drone/push Build is passing

The four CCCI state files (deploys countfile, opstate, deps, depskip) were keyed
by app domain in shared /tmp. A second run of the same domain executes its main()
preamble + deploy_app's pre-lock _record_deploy BEFORE blocking at the app lock,
so it reset/polluted the live first run's counter (false DG4.1 deploy-count=2,
build 279) and the first run's end-of-run os.remove crashed the second
(FileNotFoundError, build 281). Masked pre-restructure by the end-to-end recipe
flock. Now keyed by run id + harness pid via _run_state_path(); children receive
exact paths via the CCCI_*_FILE env vars, so domain keying was never load-bearing.

tests/concurrency/test_run_state.py: path-invariant cases + a real-process
regression (helpers.py deploy-count-run) reproducing the live interleaving —
verified to FAIL under simulated shared keying. docs/concurrency.md §3 updated.
This commit is contained in:
autonomic-bot
2026-06-10 08:16:09 +00:00
parent e1c4198c08
commit b6e12ef428
4 changed files with 135 additions and 8 deletions

View File

@ -138,6 +138,17 @@ def _gitea_token() -> str | None:
return tok or None
def _run_state_path(name: str) -> str:
"""Run-scoped state file in the tempdir, keyed by run id + harness pid — NEVER by app domain.
A second run of the SAME domain overlaps this process (its main() preamble executes before it
blocks at the app lock inside deploy_app), so domain-keyed files get reset/removed under the
live run: M2(c) double-!testme produced a false DG4.1 deploy-count=2 in run 1 and a countfile
FileNotFoundError crash in run 2. Children never re-derive these paths — they receive them
via the CCCI_*_FILE env vars, so the key only has to be unique per harness process."""
rid = results_mod.run_id()
return os.path.join(tempfile.gettempdir(), f"ccci-{name}-{rid}-{os.getpid()}")
def setup_run_abra_dir() -> str:
"""P3: build + export this run's PER-RUN ABRA_DIR — structural isolation of recipe trees.
@ -619,15 +630,15 @@ def run_quick(
flush=True,
)
statefile = os.path.join(tempfile.gettempdir(), f"ccci-opstate-{domain}.json")
statefile = _run_state_path("opstate") + ".json"
with open(statefile, "w") as f:
json.dump({}, f)
os.environ["CCCI_OP_STATE_FILE"] = statefile
depsfile = os.path.join(tempfile.gettempdir(), f"ccci-deps-{domain}.json")
depsfile = _run_state_path("deps") + ".json"
with open(depsfile, "w") as f:
json.dump({}, f)
os.environ["CCCI_DEPS_FILE"] = depsfile
skipfile = os.path.join(tempfile.gettempdir(), f"ccci-depskip-{domain}.txt")
skipfile = _run_state_path("depskip") + ".txt"
with contextlib.suppress(OSError):
os.remove(skipfile)
os.environ["CCCI_DEPS_SKIP_REPORT"] = skipfile
@ -927,7 +938,7 @@ def main() -> int:
hook = discovery.install_steps(recipe, repo_local)
# Deploy-count guard (DG4.1): exactly one deploy_app() per run.
countfile = os.path.join(tempfile.gettempdir(), f"ccci-deploys-{domain}")
countfile = _run_state_path("deploys")
with open(countfile, "w") as f:
f.write("0")
os.environ["CCCI_DEPLOY_COUNT_FILE"] = countfile
@ -943,7 +954,7 @@ def main() -> int:
# Run-scoped op state (HC3): the orchestrator records op results (pre-upgrade identity, backup
# snapshot_id) here for the assertion tiers (generic + overlay) to read via generic.op_state().
statefile = os.path.join(tempfile.gettempdir(), f"ccci-opstate-{domain}.json")
statefile = _run_state_path("opstate") + ".json"
with open(statefile, "w") as f:
json.dump({}, f)
os.environ["CCCI_OP_STATE_FILE"] = statefile
@ -954,12 +965,12 @@ def main() -> int:
# cannot break the generic-tier signal. The `setup_custom_tests` step deploys each dep + runs
# `tests/<recipe>/setup_custom_tests.sh` to wire OIDC env via in-place redeploy.
# `$CCCI_DEPS_FILE` is written with the full creds dict the hook script needs (jq-readable).
depsfile = os.path.join(tempfile.gettempdir(), f"ccci-deps-{domain}.json")
depsfile = _run_state_path("deps") + ".json"
with open(depsfile, "w") as f:
json.dump({}, f)
os.environ["CCCI_DEPS_FILE"] = depsfile
# F2-11: conftest appends the count of requires_deps tests it skips (deps-not-ready) here.
skipfile = os.path.join(tempfile.gettempdir(), f"ccci-depskip-{domain}.txt")
skipfile = _run_state_path("depskip") + ".txt"
with contextlib.suppress(OSError):
os.remove(skipfile)
os.environ["CCCI_DEPS_SKIP_REPORT"] = skipfile