Skip to content

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

feat: persist scan lifecycle and model metadata (#264)

mldangelo-oai802393289979
diff --git a/sdk/typescript/_bundled_plugin/mcp/mcp-app.html.br b/sdk/typescript/_bundled_plugin/mcp/mcp-app.html.br
index cef73321d..1e6c2518a 100644
Binary files a/sdk/typescript/_bundled_plugin/mcp/mcp-app.html.br and b/sdk/typescript/_bundled_plugin/mcp/mcp-app.html.br differ
diff --git a/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-000 b/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-000
index 74662af1c..571dcb132 100644
Binary files a/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-000 and b/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-000 differ
diff --git a/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-001 b/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-001
index 74aedd5f8..4a38b9224 100644
Binary files a/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-001 and b/sdk/typescript/_bundled_plugin/mcp/server.mjs.br.part-001 differ
diff --git a/sdk/typescript/_bundled_plugin/scripts/deep_scan_workbench.py b/sdk/typescript/_bundled_plugin/scripts/deep_scan_workbench.py
index 6f52950d1..2a573d01c 100644
--- a/sdk/typescript/_bundled_plugin/scripts/deep_scan_workbench.py
+++ b/sdk/typescript/_bundled_plugin/scripts/deep_scan_workbench.py
@@ -40,6 +40,8 @@ def register_subcommands(subparsers: Any, positive_int: Callable[[str], int]) ->
begin_deep_scan.add_argument("--user-context")
begin_deep_scan.add_argument("--scan-root")
begin_deep_scan.add_argument("--claim-token")
+ begin_deep_scan.add_argument("--model")
+ begin_deep_scan.add_argument("--reasoning-effort")
begin_deep_scan.add_argument("--available-parallelism", type=positive_int)
begin_deep_scan.add_argument("--workflow-version", default=DEEP_SCAN_WORKFLOW_VERSION)
@@ -324,7 +326,7 @@ def independent_review_progress(
connection: sqlite3.Connection, scan_id: str
) -> dict[str, int | str] | None:
run = connection.execute(
- "SELECT completion_sequence, updated_at FROM deep_scan_runs WHERE scan_id = ?",
+ "SELECT completion_sequence, phase, updated_at FROM deep_scan_runs WHERE scan_id = ?",
(scan_id,),
).fetchone()
if run is None:
@@ -342,6 +344,7 @@ def independent_review_progress(
return {
"active": int(active),
"completed": int(run["completion_sequence"]),
+ "consolidating": run["phase"] == "reducing",
"updatedAt": str(run["updated_at"]),
}
@@ -569,6 +572,18 @@ def begin_deep_scan_for_scan(
)
if scan["mode"] != "deep":
raise SystemExit("Deep Scan orchestration requires a scan in deep mode.")
+ model = optional_text(args.model, maximum=200)
+ reasoning_effort = optional_text(args.reasoning_effort, maximum=32)
+ if model is not None or reasoning_effort is not None:
+ connection.execute(
+ """
+ UPDATE scans
+ SET model = COALESCE(?, model), reasoning_effort = COALESCE(?, reasoning_effort)
+ WHERE id = ?
+ """,
+ (model, reasoning_effort, scan_id),
+ )
+ connection.commit()
existing = connection.execute(
"SELECT scan_id FROM deep_scan_runs WHERE scan_id = ?", (scan_id,)
).fetchone()
@@ -681,6 +696,8 @@ def begin_deep_scan_for_target(
raise SystemExit("The scan artifact directory must be outside the selected target.")
target_root.mkdir(parents=True, exist_ok=True)
user_context = optional_text(args.user_context)
+ model = optional_text(args.model, maximum=200)
+ reasoning_effort = optional_text(args.reasoning_effort, maximum=32)
workspace_id = str(uuid.uuid4())
scan_id = str(uuid.uuid4())
timestamp = now()
@@ -715,10 +732,10 @@ def begin_deep_scan_for_target(
INSERT INTO scans (
id, workspace_id, target_id, target_path, target_revision, target_snapshot_digest,
target_device, target_inode, scope, mode, user_context,
- deep_scan_owner_thread_id, scan_dir, status, phase, handoff_status,
- started_at, created_at, updated_at
- ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, 'deep', ?, ?, ?, 'running', 'preflight',
- 'delivered', ?, ?, ?)
+ deep_scan_owner_thread_id, scan_dir, model, reasoning_effort, status, phase,
+ handoff_status, started_at, created_at, updated_at
+ ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, 'deep', ?, ?, ?, ?, ?,
+ 'running', 'preflight', 'delivered', ?, ?, ?)
""",
(
scan_id,
@@ -733,6 +750,8 @@ def begin_deep_scan_for_target(
user_context,
thread_id,
str(scan_dir),
+ model,
+ reasoning_effort,
timestamp,
timestamp,
timestamp,
@@ -1114,6 +1133,14 @@ def claim_deep_scan_dedup(
"UPDATE deep_scan_runs SET phase = 'reducing', updated_at = ? WHERE scan_id = ?",
(timestamp, scan_id),
)
+ connection.execute(
+ """
+ UPDATE scan_progress
+ SET deep_review_pass = COALESCE(deep_review_pass, 0) + 1, updated_at = ?
+ WHERE scan_id = ?
+ """,
+ (timestamp, scan_id),
+ )
connection.commit()
except BaseException:
connection.rollback()
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_cli.py b/sdk/typescript/_bundled_plugin/scripts/workbench_cli.py
index 8e0c38e98..7ffbeb13e 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_cli.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_cli.py
@@ -113,6 +113,8 @@ def parse_args(description: str) -> argparse.Namespace:
start_scan = subparsers.add_parser("start-scan")
start_scan.add_argument("--workspace-id", required=True)
start_scan.add_argument("--scan-root")
+ start_scan.add_argument("--model")
+ start_scan.add_argument("--reasoning-effort")
disable_setup_ui = subparsers.add_parser("disable-setup-ui")
disable_setup_ui.add_argument("--workspace-id", required=True)
@@ -129,6 +131,8 @@ def parse_args(description: str) -> argparse.Namespace:
start_prompt_only_scan.add_argument("--diff-head-revision")
start_prompt_only_scan.add_argument("--diff-content-digest")
start_prompt_only_scan.add_argument("--scan-root")
+ start_prompt_only_scan.add_argument("--model")
+ start_prompt_only_scan.add_argument("--reasoning-effort")
deep_scan.register_subcommands(subparsers, positive_int)
@@ -209,6 +213,8 @@ def parse_args(description: str) -> argparse.Namespace:
update_progress.add_argument("--reportable-findings-count", type=non_negative_int)
update_progress.add_argument("--deep-review-pass", type=positive_int)
update_progress.add_argument("--claim-token")
+ update_progress.add_argument("--model")
+ update_progress.add_argument("--reasoning-effort")
prepare_scan_completion = subparsers.add_parser("prepare-scan-completion")
prepare_scan_completion.add_argument("--scan-id", required=True)
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_db.py b/sdk/typescript/_bundled_plugin/scripts/workbench_db.py
index 70c6a3cd9..004be062d 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_db.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_db.py
@@ -79,6 +79,7 @@ from workbench_constants import (
SQLITE_RETRY_ATTEMPTS,
)
from workbench_feedback import get_scan_feedback
+from workbench_remediation import remediation_claim_is_active
from workbench_scan_start import (
archive_scan,
compact_timestamp,
@@ -137,23 +138,6 @@ def stale_claim_before(seconds: int = CLAIM_LEASE_SECONDS) -> str:
)
-def remediation_claim_is_active(remediation: sqlite3.Row) -> bool:
- if remediation["pending_action_claim_token"] is None:
- return False
- delivered_at = remediation["pending_action_delivered_at"]
- claimed_at = delivered_at or remediation["pending_action_claimed_at"]
- if not isinstance(claimed_at, str):
- return True
- try:
- parsed = datetime.fromisoformat(claimed_at)
- if parsed.tzinfo is None:
- return True
- except ValueError:
- return True
- lease_seconds = DELIVERED_ACTION_LEASE_SECONDS if delivered_at else CLAIM_LEASE_SECONDS
- return parsed > datetime.now(timezone.utc) - timedelta(seconds=lease_seconds)
-
-
def state_dir() -> Path:
state_dir = os.environ.get("CODEX_SECURITY_STATE_DIR")
if state_dir:
@@ -1172,6 +1156,8 @@ def start_scan(connection: sqlite3.Connection, args: argparse.Namespace) -> dict
target_summary=target_summary,
scope_file_count=scope_file_count,
timestamp=timestamp,
+ model=args.model,
+ reasoning_effort=args.reasoning_effort,
)
if manages_transaction:
connection.commit()
@@ -1309,6 +1295,8 @@ def start_prompt_only_scan(
scope_file_count=scope_file_count,
timestamp=timestamp,
handoff_status="delivered",
+ model=args.model,
+ reasoning_effort=args.reasoning_effort,
)
connection.commit()
except BaseException:
@@ -3004,6 +2992,7 @@ def scan_result(
progress_result["independentReviews"] = {
"active": independent_reviews["active"],
"completed": independent_reviews["completed"],
+ "consolidating": independent_reviews["consolidating"],
}
return {
"artifacts": artifacts,
@@ -3024,8 +3013,10 @@ def scan_result(
"handoffClaimToken": scan["handoff_claim_token"],
"handoffStatus": scan["handoff_status"],
"mode": scan["mode"],
+ "model": scan["model"],
"diffTarget": stored_diff_target(scan),
"progress": progress_result,
+ "reasoningEffort": scan["reasoning_effort"],
"remediationAvailable": remediation_available,
"remediationUnavailableReason": remediation_unavailable_reason,
"reportAvailable": "markdownReport" in artifacts,
@@ -3647,13 +3638,9 @@ def main() -> None:
read_coverage=coverage_for_comparison,
)
elif args.command == "list-global-findings":
- result = native_indexes.list_global_findings(
- connection, args, read_coverage=coverage_for_comparison
- )
+ result = native_indexes.list_global_findings(connection, args)
elif args.command == "list-repositories":
- result = native_indexes.list_repositories(
- connection, args, read_coverage=coverage_for_comparison
- )
+ result = native_indexes.list_repositories(connection, args)
elif args.command == "list-findings":
result = list_findings(connection, args)
elif args.command == "update-progress":
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_native_indexes.py b/sdk/typescript/_bundled_plugin/scripts/workbench_native_indexes.py
index af424a67e..80e825fe6 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_native_indexes.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_native_indexes.py
@@ -4,7 +4,7 @@ import argparse
import sqlite3
import sys
from collections import Counter
-from collections.abc import Callable, Iterator
+from collections.abc import Iterator
from itertools import islice
from pathlib import Path
from typing import Any
@@ -19,14 +19,12 @@ from workbench_validation import bounded_output_text
def list_global_findings(
connection: sqlite3.Connection,
args: argparse.Namespace,
- *,
- read_coverage: Callable[[sqlite3.Row], dict[str, Any]],
) -> dict[str, Any]:
limit = min(args.limit, FINDINGS_PAGE_MAX)
query = args.query.strip().casefold() if args.query else ""
findings = (
row
- for row in _active_findings(connection, read_coverage)
+ for row in _indexed_findings(connection)
if (args.target_id is None or row["target_id"] == args.target_id)
and (args.severity is None or row["severity"] == args.severity)
and (args.status is None or row["status"] == args.status)
@@ -72,23 +70,8 @@ def list_global_findings(
}
-def _active_findings(
- connection: sqlite3.Connection,
- read_coverage: Callable[[sqlite3.Row], dict[str, Any]],
-) -> Iterator[sqlite3.Row]:
- completed_scans_by_target: dict[str, list[sqlite3.Row]] = {}
- for scan in connection.execute(
- """
- SELECT *
- FROM scans
- WHERE status = 'complete' AND seal_manifest_digest IS NOT NULL
- ORDER BY started_at DESC, id DESC
- """
- ):
- completed_scans_by_target.setdefault(scan["target_id"], []).append(scan)
-
- coverage_by_scan_id: dict[str, dict[str, Any]] = {}
- rows = connection.execute(
+def _indexed_findings(connection: sqlite3.Connection) -> Iterator[sqlite3.Row]:
+ yield from connection.execute(
"""
WITH ranked_findings AS (
SELECT
@@ -97,7 +80,6 @@ def _active_findings(
occurrences.severity,
occurrences.created_at,
scans.id AS scan_id,
- scans.started_at AS scan_started_at,
scans.target_id,
targets.current_path AS target_path,
scans.scope,
@@ -146,35 +128,11 @@ def _active_findings(
selected_findings.occurrence_id
""",
)
- for row in rows:
- resolved = False
- for scan in completed_scans_by_target.get(row["target_id"], ()):
- if (scan["started_at"], scan["id"]) <= (
- row["scan_started_at"],
- row["scan_id"],
- ):
- break
- coverage = coverage_by_scan_id.get(scan["id"])
- if coverage is None:
- coverage = read_coverage(scan)
- coverage_by_scan_id[scan["id"]] = coverage
- if scan_history.scan_covers_path(
- scan,
- target_id=row["target_id"],
- path=row["location_path"],
- coverage=coverage,
- ):
- resolved = True
- break
- if not resolved:
- yield row
def list_repositories(
connection: sqlite3.Connection,
args: argparse.Namespace | None = None,
- *,
- read_coverage: Callable[[sqlite3.Row], dict[str, Any]],
) -> dict[str, Any]:
scans = scan_history.list_scans(connection)["scans"]
scans_by_id = {scan["scanId"]: scan for scan in scans}
@@ -190,9 +148,7 @@ def list_repositories(
latest_scan_by_target.setdefault(row["target_id"], scans_by_id[row["id"]])
open_findings_by_target = Counter(
- row["target_id"]
- for row in _active_findings(connection, read_coverage)
- if row["status"] == "open"
+ row["target_id"] for row in _indexed_findings(connection) if row["status"] == "open"
)
targets = {row["id"]: row for row in connection.execute("SELECT * FROM security_targets")}
repositories = [
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_progress.py b/sdk/typescript/_bundled_plugin/scripts/workbench_progress.py
index 5bf13d8c4..cd6c29f95 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_progress.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_progress.py
@@ -10,7 +10,7 @@ from typing import Any, Callable
sys.path.insert(0, str(Path(__file__).resolve().parent))
from workbench.handoff import require_current_continuation
from workbench_constants import PHASES
-from workbench_validation import require_uuid
+from workbench_validation import optional_text, require_uuid
MAX_PREFLIGHT_ISSUES_JSON_BYTES = 64 * 1024
MAX_PREFLIGHT_ISSUES = 32
@@ -86,6 +86,8 @@ def update_progress(
scan_context: Callable[[sqlite3.Connection, str], dict[str, Any]],
) -> dict[str, Any]:
scan_id = require_uuid(args.scan_id, "scan-id")
+ model = optional_text(args.model, maximum=200)
+ reasoning_effort = optional_text(args.reasoning_effort, maximum=32)
serialized_preflight_issues = preflight_issues_json(args.preflight_issues_json)
connection.execute("BEGIN IMMEDIATE")
try:
@@ -189,10 +191,11 @@ def update_progress(
updated = connection.execute(
"""
UPDATE scans
- SET phase = COALESCE(?, phase), updated_at = ?
+ SET phase = COALESCE(?, phase), model = COALESCE(?, model),
+ reasoning_effort = COALESCE(?, reasoning_effort), updated_at = ?
WHERE id = ? AND status = 'running'
""",
- (args.phase, timestamp, scan["id"]),
+ (args.phase, model, reasoning_effort, timestamp, scan["id"]),
)
if updated.rowcount != 1:
raise SystemExit("Only a running scan can update progress.")
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_remediation.py b/sdk/typescript/_bundled_plugin/scripts/workbench_remediation.py
index ffb661aa1..afb1c6c98 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_remediation.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_remediation.py
@@ -5,15 +5,33 @@ from __future__ import annotations
import argparse
import sqlite3
import sys
-from datetime import datetime, timezone
+from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any
# Some plugin hosts launch Python with safe-path isolation enabled.
sys.path.insert(0, str(Path(__file__).resolve().parent))
+from workbench_constants import CLAIM_LEASE_SECONDS, DELIVERED_ACTION_LEASE_SECONDS
from workbench_validation import require_occurrence, require_uuid
+def remediation_claim_is_active(remediation: sqlite3.Row) -> bool:
+ if remediation["pending_action_claim_token"] is None:
+ return False
+ delivered_at = remediation["pending_action_delivered_at"]
+ claimed_at = delivered_at or remediation["pending_action_claimed_at"]
+ if not isinstance(claimed_at, str):
+ return True
+ try:
+ parsed = datetime.fromisoformat(claimed_at)
+ if parsed.tzinfo is None:
+ return True
+ except ValueError:
+ return True
+ lease_seconds = DELIVERED_ACTION_LEASE_SECONDS if delivered_at else CLAIM_LEASE_SECONDS
+ return parsed > datetime.now(timezone.utc) - timedelta(seconds=lease_seconds)
+
+
def register_cancel_finding_remediation_request(subparsers: Any) -> None:
parser = subparsers.add_parser("cancel-finding-remediation-request")
parser.add_argument("--occurrence-id", required=True)
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_scan_history.py b/sdk/typescript/_bundled_plugin/scripts/workbench_scan_history.py
index c92f14901..514e9d763 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_scan_history.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_scan_history.py
@@ -225,6 +225,7 @@ def list_scans(
"findingCount": row["finding_count"],
"handoffStatus": row["handoff_status"],
"mode": row["mode"],
+ "model": row["model"],
"parentScanId": row["parent_scan_id"],
"progress": {
"candidates": {"reportable": row["reportable_findings_count"]},
@@ -238,6 +239,7 @@ def list_scans(
"updatedAt": row["progress_updated_at"],
},
"recipeAvailable": row["recipe_json"] is not None,
+ "reasoningEffort": row["reasoning_effort"],
"scanDir": row["scan_dir"],
"scanId": row["id"],
"scope": row["scope"],
diff --git a/sdk/typescript/_bundled_plugin/scripts/workbench_scan_start.py b/sdk/typescript/_bundled_plugin/scripts/workbench_scan_start.py
index 103b1e654..4d5819c65 100644
--- a/sdk/typescript/_bundled_plugin/scripts/workbench_scan_start.py
+++ b/sdk/typescript/_bundled_plugin/scripts/workbench_scan_start.py
@@ -22,6 +22,7 @@ from workbench_target import (
git_revision,
worktree_content_digest,
)
+from workbench_validation import optional_text
def safe_segment(value: str) -> str:
@@ -161,6 +162,8 @@ def insert_running_scan(
scope_file_count: int,
timestamp: str,
handoff_status: str = "pending",
+ model: str | None = None,
+ reasoning_effort: str | None = None,
scan_dir: Path | None = None,
) -> str:
revision = target_identity[0]
@@ -178,10 +181,10 @@ def insert_running_scan(
id, workspace_id, target_id, target_path, target_revision, target_snapshot_digest,
target_device, target_inode, scope, mode, user_context,
deep_scan_owner_thread_id, diff_target_kind, diff_base_revision,
- diff_head_revision, diff_content_digest, target_summary, scan_dir, status, phase,
- handoff_status, started_at, created_at, updated_at
- ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 'running', 'preflight',
- ?, ?, ?, ?)
+ diff_head_revision, diff_content_digest, target_summary, scan_dir, model,
+ reasoning_effort, status, phase, handoff_status, started_at, created_at, updated_at
+ ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?,
+ 'running', 'preflight', ?, ?, ?, ?)
""",
(
scan_id,
@@ -199,6 +202,8 @@ def insert_running_scan(
diff_target.get("contentDigest") if diff_target else None,
target_summary,
str(scan_dir),
+ optional_text(model, maximum=200),
+ optional_text(reasoning_effort, maximum=32),
handoff_status,
timestamp,
timestamp,
diff --git a/sdk/typescript/tests-ts/deep-scan-workbench.test.ts b/sdk/typescript/tests-ts/deep-scan-workbench.test.ts
index b5c6a80a6..1e49734e6 100644
--- a/sdk/typescript/tests-ts/deep-scan-workbench.test.ts
+++ b/sdk/typescript/tests-ts/deep-scan-workbench.test.ts
@@ -31,7 +31,7 @@ const deepScanOwnershipProbe = [
"deep_scan.now = lambda: 'after'",
"deep_scan.deep_scan_result = lambda database, value, *, start_disposition=None: {'startDisposition': start_disposition}",
"try:",
- " result = deep_scan.begin_deep_scan_for_scan(connection, scan_id, 'requesting-thread', argparse.Namespace(claim_token=case['suppliedToken']))",
+ " result = deep_scan.begin_deep_scan_for_scan(connection, scan_id, 'requesting-thread', argparse.Namespace(claim_token=case['suppliedToken'], model=None, reasoning_effort=None))",
"except SystemExit as error:",
" accepted, message, result = False, str(error), None",
"else:",
diff --git a/sdk/typescript/tests-ts/scan-recovery.test.ts b/sdk/typescript/tests-ts/scan-recovery.test.ts
index 77d93cd8a..8bb89af6a 100644
--- a/sdk/typescript/tests-ts/scan-recovery.test.ts
+++ b/sdk/typescript/tests-ts/scan-recovery.test.ts
@@ -937,4 +937,30 @@ describe("malformed scan artifact recovery", () => {
await expect(completeScan(fixture)).rejects.toThrow("inventoryStrategy");
expect(await readFile(path, "utf8")).toBe(original);
});
+
+ test.each(["complete-scan", "prepare-scan-completion"] as const)(
+ "keeps a repairable %s contract failure resumable",
+ async (command) => {
+ const fixture = await startDraftScan();
+ const path = join(fixture.scanDir, "coverage.json");
+ const document = await readJson<CoverageDocument>(path);
+ const validInventoryStrategy = document.inventoryStrategy;
+ document.inventoryStrategy = "";
+ await writeJson(path, document);
+
+ await expect(
+ workbench(fixture, [command, "--scan-id", fixture.scanId]),
+ ).rejects.toThrow("inventoryStrategy");
+ const pending = await workbench(fixture, [
+ "get-scan",
+ "--scan-id",
+ fixture.scanId,
+ ]);
+ expect((pending["scan"] as ScanSummary).progress.status).toBe("running");
+
+ document.inventoryStrategy = validInventoryStrategy;
+ await writeJson(path, document);
+ expect((await completeScan(fixture)).findingCount).toBe(1);
+ },
+ );
});