Skip to content

[DevOps]: Schedule diagnostics linking on Chrysalis and Spin #367

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tomvothecoder merged 2 commits into from
Oct 6, 2026
Merged

[DevOps]: Schedule diagnostics linking on Chrysalis and Spin #367

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
719aec7
[DevOps]: Schedule diagnostics linking on Chrysalis and Spin
tomvothecoder Oct 5, 2026
568be43
[DevOps]: Add Make targets for manual diagnostics scans
tomvothecoder Oct 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 30 additions & 0 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,8 @@ help:
@echo " make v3-diagnostics-dry-run SIMBOARD_ROOT=<path> env=<dev|prod> # Reconcile Chrysalis v3 diagnostics without writes"
@echo " make v3-diagnostics-apply SIMBOARD_ROOT=<path> env=<dev|prod> # Backfill and link Chrysalis v3 diagnostics"
@echo " Optional: case_name=<exact-case-name> to retry one v3 diagnostics case"
@echo " make diagnostics-dry-run SIMBOARD_ROOT=<path> site=<site> env=<dev|prod> # Discover published diagnostics offline"
@echo " make diagnostics-apply SIMBOARD_ROOT=<path> site=<site> env=<dev|prod> # Link published diagnostics to existing cases"
@echo ""

@echo "Frontend:"
Expand Down Expand Up @@ -186,6 +188,34 @@ V3_ENV_INITIALIZER := $(INGESTION_OPERATIONS_DIR)/initialize_v3_environment.sh
V3_ENV_TEMPLATE := $(BACKEND_DIR)/app/scripts/ingestion/v3_data/lcrc-v3.env.example
INGESTION_PROVISION_SCRIPT := $(INGESTION_OPERATIONS_DIR)/provision_operations.sh
INGESTION_REFRESH_SCRIPT := $(INGESTION_OPERATIONS_DIR)/refresh_repository.sh
DIAGNOSTICS_LAUNCHER := backend/app/scripts/ingestion/sites/site_ingestion_launcher.sh

.PHONY: diagnostics-dry-run diagnostics-apply

# Use the host launcher for its protected API configuration, locks, and logs.
# Dry scans select an environment for log/lock naming but never load credentials.
diagnostics-dry-run diagnostics-apply:
@if [ -z "$(SIMBOARD_ROOT)" ] || [ -z "$(site)" ] || [ -z "$(env)" ]; then \
echo "Usage: make $@ SIMBOARD_ROOT=<path> site=<site> env=<dev|prod>" >&2; \
exit 1; \
fi; \
case "$(site)" in *[!a-z0-9_-]*) echo "site must contain only lowercase letters, digits, underscores, or hyphens" >&2; exit 1 ;; esac; \
if [ ! -r "$(INGESTION_SITE_CONFIGS_DIR)/$(site).config" ]; then \
echo "Site configuration not readable: $(INGESTION_SITE_CONFIGS_DIR)/$(site).config" >&2; \
exit 1; \
fi; \
if [ "$(env)" != "dev" ] && [ "$(env)" != "prod" ]; then \
echo "env must be dev or prod" >&2; \
exit 1; \
fi; \
SIMBOARD_ROOT="$(SIMBOARD_ROOT)" SIMBOARD_ENV_FILE="$(SIMBOARD_ROOT)/operations/env.$(env).sh" \
SIMBOARD_SITE_CONFIG="$(CURDIR)/$(INGESTION_SITE_CONFIGS_DIR)/$(site).config" \
DRY_RUN=$(if $(filter diagnostics-dry-run,$@),true,false) \
bash "$(DIAGNOSTICS_LAUNCHER)" "$(site)" diagnostics || { \
exit_code=$$?; \
echo "Diagnostics launcher failed (exit $$exit_code). If a run log was created, check $(SIMBOARD_ROOT)/operations/raw_logs/simboard-diagnostics-$(site)-env.$(env).sh-*.log" >&2; \
exit "$$exit_code"; \
}

operations-provision:
@if [ -z "$(SIMBOARD_ROOT)" ]; then \
Expand Down
179 changes: 137 additions & 42 deletions backend/app/scripts/ingestion/diagnostics_link_scanner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
import posixpath
import re
import time
import traceback
from dataclasses import dataclass
from datetime import datetime, timezone
from pathlib import Path
Expand Down Expand Up @@ -36,17 +37,27 @@ class Candidate:
fingerprint: str


def run(included_case_paths: set[Path] | None = None) -> int:
"""Scan the archive, optionally limited to root-relative case paths."""
configured_machine = os.environ.get("MACHINE_NAME", "").strip()
if not configured_machine:
raise ValueError("MACHINE_NAME is required")
@dataclass
class ScanProgress:
"""Track the active phase and candidate for fatal-error reporting."""

machine = canonicalize_machine_name(configured_machine)
archive = _resolve_archive(machine)
root = Path(archive.root)
dry_run = os.environ.get("DRY_RUN", "true").lower() in {"1", "true", "yes"}
phase: str = "configuration"
candidate_path: str | None = None


@dataclass(frozen=True)
class ScannerConfig:
"""Runtime settings shared by discovery and linking."""

machine: str
archive: DiagnosticsArchive
dry_run: bool
api_base: str
token: str


def run(included_case_paths: set[Path] | None = None) -> int:
"""Scan optional root-relative case paths and always report exit counters."""
summary = {
"discovered_candidates": 0,
"dry_run_candidates": 0,
Expand All @@ -55,51 +66,142 @@ def run(included_case_paths: set[Path] | None = None) -> int:
"submitted_links": 0,
"failed_link_submissions": 0,
}
progress = ScanProgress()
outcome = "failed"
try:
result = _run_scan(summary, progress, included_case_paths)
outcome = "completed" if result == 0 else "failed"
return result
except Exception as exc:
# Do not log exception messages/locals: HTTP errors may contain URLs,
# credentials or response bodies. Keep frame locations for diagnosis.
frames = traceback.extract_tb(exc.__traceback__)
_log_event(
"diagnostics_scanner_failed",
{
"phase": progress.phase,
"archive_relative_case_path": progress.candidate_path,
"error_type": type(exc).__name__,
"traceback_frames": [
f"{Path(frame.filename).name}:{frame.lineno}:{frame.name}"
for frame in frames
],
},
)
return 1
finally:
_log_event("diagnostics_scanner_completed", {**summary, "outcome": outcome})


def _build_scanner_config() -> ScannerConfig:
"""Resolve the reviewed archive and validate the scheduler settings."""
configured_machine = os.environ.get("MACHINE_NAME", "").strip()
if not configured_machine:
raise ValueError("MACHINE_NAME is required")

machine = canonicalize_machine_name(configured_machine)
archive = _resolve_archive(machine)
dry_run_value = os.environ.get("DRY_RUN", "true").strip().lower()
if dry_run_value not in {"1", "true", "yes", "on", "0", "false", "no", "off"}:
raise ValueError("DRY_RUN must be a boolean")
dry_run = dry_run_value in {"1", "true", "yes", "on"}
_log_event(
"diagnostics_scanner_startup_configuration",
{
"machine_name": machine,
"archive_root": str(root),
"archive_root": archive.root,
"public_base_url": _sanitize_url(archive.public_base_url),
"dry_run": dry_run,
"has_api_base_url": bool(os.environ.get("SIMBOARD_API_BASE_URL")),
"has_api_token": bool(os.environ.get("SIMBOARD_API_TOKEN")),
},
)

candidates = _discover(root, archive.public_base_url, machine, included_case_paths)
summary["discovered_candidates"] = len(candidates)
_log_event("diagnostics_scanner_discovery_completed", summary.copy())
api_base = ""
token = ""
if not dry_run:
api_base = os.environ["SIMBOARD_API_BASE_URL"].rstrip("/")
token = os.environ["SIMBOARD_API_TOKEN"]
if not api_base or not token:
raise ValueError("Live scans require API configuration")
return ScannerConfig(
machine=machine,
archive=archive,
dry_run=dry_run,
api_base=api_base,
token=token,
)

if dry_run:
for candidate in candidates:
relative = candidate.path.parent.relative_to(root).as_posix()
summary["dry_run_candidates"] += 1
_log_event(
"diagnostics_scanner_dry_run_candidate",
{
"archive_relative_case_path": relative,
"settings_filename": candidate.settings.name,
"fingerprint": candidate.fingerprint,
},
)
_log_event("diagnostics_scanner_dry_run_completed", summary.copy())
_log_event("diagnostics_scanner_completed", summary.copy())

return 0
def _run_scan(
summary: dict[str, int],
progress: ScanProgress,
included_case_paths: set[Path] | None = None,
) -> int:
"""Discover candidates, then log a dry run or link them through the API."""
config = _build_scanner_config()
root = Path(config.archive.root)
progress.phase = "discovery"
candidates = _discover(
root, config.archive.public_base_url, config.machine, included_case_paths
)
summary["discovered_candidates"] = len(candidates)
_log_event("diagnostics_scanner_discovery_completed", summary.copy())
if config.dry_run:
_log_dry_run(candidates, root, summary, progress)
else:
_link_candidates(candidates, config, summary, progress)
if summary["deferred_state_lookups"] or summary["failed_link_submissions"]:
return 1
return 0
Comment thread
tomvothecoder marked this conversation as resolved.

api_base = os.environ["SIMBOARD_API_BASE_URL"].rstrip("/")
token = os.environ["SIMBOARD_API_TOKEN"]
headers = {"Authorization": f"Bearer {token}"}

def _log_dry_run(
candidates: list[Candidate],
root: Path,
summary: dict[str, int],
progress: ScanProgress,
) -> None:
"""Report discovered candidates without opening an API client."""
progress.phase = "dry_run"
for candidate in candidates:
relative = candidate.path.parent.relative_to(root).as_posix()
progress.candidate_path = relative
summary["dry_run_candidates"] += 1
_log_event(
"diagnostics_scanner_dry_run_candidate",
{
"archive_relative_case_path": relative,
"settings_filename": candidate.settings.name,
"fingerprint": candidate.fingerprint,
},
)
_log_event("diagnostics_scanner_dry_run_completed", summary.copy())


def _link_candidates(
candidates: list[Candidate],
config: ScannerConfig,
summary: dict[str, int],
progress: ScanProgress,
) -> None:
"""Skip unchanged candidates and submit new links, counting API failures."""
root = Path(config.archive.root)
headers = {"Authorization": f"Bearer {config.token}"}
progress.phase = "api_client"
with httpx.Client(timeout=30) as client:
for candidate in candidates:
relative = candidate.path.parent.relative_to(root).as_posix()
progress.candidate_path = relative
progress.phase = "state_lookup"

state = _request_with_retry(
client.get,
f"{api_base}/api/v1/diagnostics/scanner-state",
params={"machine": machine, "archive_relative_case_path": relative},
f"{config.api_base}/api/v1/diagnostics/scanner-state",
params={
"machine": config.machine,
"archive_relative_case_path": relative,
},
headers=headers,
)
_log_event(
Expand Down Expand Up @@ -137,6 +239,7 @@ def run(included_case_paths: set[Path] | None = None) -> int:
)
continue

progress.phase = "link_submission"
payload = {
"caseName": candidate.values["case_name"],
"machine": candidate.values["machine"],
Expand All @@ -158,11 +261,10 @@ def run(included_case_paths: set[Path] | None = None) -> int:

response = _request_with_retry(
client.post,
f"{api_base}/api/v1/diagnostics/scanner/link",
f"{config.api_base}/api/v1/diagnostics/scanner/link",
json=payload,
headers=headers,
)

if response is None or response.status_code != 204:
summary["failed_link_submissions"] += 1
_log_event(
Expand All @@ -184,13 +286,6 @@ def run(included_case_paths: set[Path] | None = None) -> int:
},
)

_log_event("diagnostics_scanner_completed", summary)

if summary["deferred_state_lookups"] or summary["failed_link_submissions"]:
return 1

return 0


def _resolve_archive(machine_name: str) -> DiagnosticsArchive:
canonical_machine_name = canonicalize_machine_name(machine_name)
Expand Down
Loading
Loading