@openai/codex-security 0.6.0 → 0.8.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +76 -39
- package/_bundled_plugin/.mcp.json +1 -0
- package/_bundled_plugin/examples/completed-scan/findings.json +34 -34
- package/_bundled_plugin/examples/completed-scan/report.md +22 -31
- package/_bundled_plugin/examples/completed-scan/scan-manifest.json +27 -29
- package/_bundled_plugin/examples/{completed-scan → legacy-completed-scan}/coverage.json +1 -0
- package/_bundled_plugin/examples/legacy-completed-scan/findings.json +57 -0
- package/_bundled_plugin/examples/legacy-completed-scan/report.md +98 -0
- package/_bundled_plugin/examples/legacy-completed-scan/scan-manifest.json +43 -0
- package/_bundled_plugin/mcp/helpers.mjs.br.part-000 +0 -0
- package/_bundled_plugin/mcp/helpers.mjs.br.part-001 +0 -0
- package/_bundled_plugin/mcp/native/THIRD_PARTY_NOTICES.txt +1 -1
- package/_bundled_plugin/mcp/native/darwin-arm64/unix.node +0 -0
- package/_bundled_plugin/mcp/native/darwin-x64/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-arm64-gnu/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-arm64-musl/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-x64-gnu/unix.node +0 -0
- package/_bundled_plugin/mcp/native/win32-arm64/windows.node +0 -0
- package/_bundled_plugin/mcp/native/win32-x64/windows.node +0 -0
- package/_bundled_plugin/mcp/server.mjs.br.part-000 +0 -0
- package/_bundled_plugin/mcp/server.mjs.br.part-001 +0 -0
- package/_bundled_plugin/mcp/server.mjs.br.part-002 +0 -0
- package/_bundled_plugin/references/access-advisory.md +11 -0
- package/_bundled_plugin/references/core-scan.md +30 -77
- package/_bundled_plugin/references/final-report.md +50 -184
- package/_bundled_plugin/references/scan-artifacts.md +5 -5
- package/_bundled_plugin/references/scan-contract.md +12 -12
- package/_bundled_plugin/references/scan-prologue.md +1 -1
- package/_bundled_plugin/references/scan-runtime.md +1 -5
- package/_bundled_plugin/references/threat-model.md +33 -41
- package/_bundled_plugin/schemas/coverage.schema.json +12 -1
- package/_bundled_plugin/schemas/scan-manifest.schema.json +37 -11
- package/_bundled_plugin/schemas/tools/deep-reducer.schema.json +38 -1
- package/_bundled_plugin/schemas/tools/scan-draft.schema.json +5 -5
- package/_bundled_plugin/scripts/deep_scan_config.py +39 -39
- package/_bundled_plugin/scripts/deep_scan_workbench.py +146 -86
- package/_bundled_plugin/scripts/finalize_scan_contract.py +249 -76
- package/_bundled_plugin/scripts/report_projection.py +49 -17
- package/_bundled_plugin/scripts/review_state.py +68 -0
- package/_bundled_plugin/scripts/threat_model_projection.py +4 -2
- package/_bundled_plugin/scripts/validate_scan_contract.py +1 -2
- package/_bundled_plugin/scripts/windows_scan_local_files.py +43 -14
- package/_bundled_plugin/scripts/workbench/retained_coverage.py +3230 -0
- package/_bundled_plugin/scripts/workbench/retained_records.py +627 -0
- package/_bundled_plugin/scripts/workbench/saved_coverage.py +651 -8
- package/_bundled_plugin/scripts/workbench/saved_outputs.py +72 -0
- package/_bundled_plugin/scripts/workbench/saved_sources.py +730 -0
- package/_bundled_plugin/scripts/workbench_cli.py +3 -0
- package/_bundled_plugin/scripts/workbench_constants.py +0 -1
- package/_bundled_plugin/scripts/workbench_coverage_receipts.py +479 -0
- package/_bundled_plugin/scripts/workbench_db.py +55 -171
- package/_bundled_plugin/scripts/workbench_feedback.py +0 -1
- package/_bundled_plugin/scripts/workbench_finding_workflows.py +51 -9
- package/_bundled_plugin/scripts/workbench_native_indexes.py +56 -44
- package/_bundled_plugin/scripts/workbench_saved_results.py +808 -2389
- package/_bundled_plugin/scripts/workbench_scan_history.py +77 -7
- package/_bundled_plugin/scripts/workbench_schema.py +1 -1
- package/_bundled_plugin/scripts/workbench_source_scopes.py +4 -1
- package/_bundled_plugin/scripts/workbench_target.py +142 -17
- package/_bundled_plugin/scripts/workbench_validation.py +9 -2
- package/_bundled_plugin/shared/workbench-history-repairs.json +21 -0
- package/_bundled_plugin/shared/workbench-migrations.json +28 -0
- package/_bundled_plugin/skills/assess-patch-risk/SKILL.md +3 -14
- package/_bundled_plugin/skills/assess-patch-risk/references/windows-validation.md +14 -0
- package/_bundled_plugin/skills/attack-path-analysis/SKILL.md +38 -103
- package/_bundled_plugin/skills/attack-path-analysis/references/attack-path-facts.md +11 -73
- package/_bundled_plugin/skills/attack-path-analysis/references/severity-policy.md +57 -116
- package/_bundled_plugin/skills/deep-security-scan/SKILL.md +28 -51
- package/_bundled_plugin/skills/define-security-policy/SKILL.md +9 -9
- package/_bundled_plugin/skills/finding-discovery/SKILL.md +26 -140
- package/_bundled_plugin/skills/fix-finding/SKILL.md +9 -28
- package/_bundled_plugin/skills/propose-security-hardening/SKILL.md +28 -218
- package/_bundled_plugin/skills/propose-security-hardening/references/proposal-format.md +29 -424
- package/_bundled_plugin/skills/publish-findings/SKILL.md +32 -24
- package/_bundled_plugin/skills/publish-findings/references/wiz-import.md +64 -0
- package/_bundled_plugin/skills/security-diff-scan/SKILL.md +12 -12
- package/_bundled_plugin/skills/security-scan/SKILL.md +29 -17
- package/_bundled_plugin/skills/security-scan/references/desktop-scan.md +11 -17
- package/_bundled_plugin/skills/security-scan/references/scan-artifacts-and-ledger.md +52 -69
- package/_bundled_plugin/skills/threat-model/SKILL.md +16 -9
- package/_bundled_plugin/skills/track-findings/SKILL.md +1 -1
- package/_bundled_plugin/skills/triage-finding/SKILL.md +5 -15
- package/_bundled_plugin/skills/triage-finding/references/ticket-intake.md +6 -6
- package/_bundled_plugin/skills/validation/SKILL.md +42 -104
- package/_bundled_plugin/skills/validation/references/validation-guidance.md +21 -106
- package/_bundled_plugin/skills/verify-fix/SKILL.md +4 -2
- package/_bundled_plugin/skills/vulnerability-writeup/SKILL.md +21 -159
- package/_bundled_plugin/skills/vulnerability-writeup/references/report-format.md +18 -60
- package/dist/api.d.ts +5 -3
- package/dist/api.d.ts.map +1 -1
- package/dist/api.js +359 -53
- package/dist/api.js.map +1 -1
- package/dist/auth.d.ts.map +1 -1
- package/dist/auth.js +4 -1
- package/dist/auth.js.map +1 -1
- package/dist/cli.d.ts +2 -2
- package/dist/cli.d.ts.map +1 -1
- package/dist/cli.js +696 -430
- package/dist/cli.js.map +1 -1
- package/dist/cloud-publish.d.ts.map +1 -1
- package/dist/cloud-publish.js +2 -23
- package/dist/cloud-publish.js.map +1 -1
- package/dist/component-scan.d.ts +8 -2
- package/dist/component-scan.d.ts.map +1 -1
- package/dist/component-scan.js +2 -0
- package/dist/component-scan.js.map +1 -1
- package/dist/contract.d.ts +5 -2
- package/dist/contract.d.ts.map +1 -1
- package/dist/contract.js +93 -45
- package/dist/contract.js.map +1 -1
- package/dist/cost.d.ts +18 -0
- package/dist/cost.d.ts.map +1 -1
- package/dist/cost.js +107 -12
- package/dist/cost.js.map +1 -1
- package/dist/coverage-presentation.d.ts +6 -0
- package/dist/coverage-presentation.d.ts.map +1 -0
- package/dist/coverage-presentation.js +34 -0
- package/dist/coverage-presentation.js.map +1 -0
- package/dist/custom-publish.js +2 -2
- package/dist/custom-publish.js.map +1 -1
- package/dist/custom-validation-prompt.js +5 -5
- package/dist/custom-validation-prompt.js.map +1 -1
- package/dist/custom-validation.d.ts.map +1 -1
- package/dist/custom-validation.js +47 -19
- package/dist/custom-validation.js.map +1 -1
- package/dist/deduplication/checkpointed-review.d.ts.map +1 -1
- package/dist/deduplication/checkpointed-review.js +3 -1
- package/dist/deduplication/checkpointed-review.js.map +1 -1
- package/dist/deduplication/codex-review.d.ts.map +1 -1
- package/dist/deduplication/codex-review.js +2 -2
- package/dist/deduplication/codex-review.js.map +1 -1
- package/dist/deduplication/deduplication-prompts.d.ts +1 -0
- package/dist/deduplication/deduplication-prompts.d.ts.map +1 -1
- package/dist/deduplication/deduplication-prompts.js +3 -0
- package/dist/deduplication/deduplication-prompts.js.map +1 -1
- package/dist/deduplication/records-protocol.d.ts.map +1 -1
- package/dist/deduplication/records-protocol.js +21 -1
- package/dist/deduplication/records-protocol.js.map +1 -1
- package/dist/deduplication/scan.d.ts.map +1 -1
- package/dist/deduplication/scan.js +9 -7
- package/dist/deduplication/scan.js.map +1 -1
- package/dist/endor-findings.d.ts +4 -3
- package/dist/endor-findings.d.ts.map +1 -1
- package/dist/endor-findings.js +16 -11
- package/dist/endor-findings.js.map +1 -1
- package/dist/external-findings-import.d.ts.map +1 -1
- package/dist/external-findings-import.js +13 -5
- package/dist/external-findings-import.js.map +1 -1
- package/dist/external-findings-local.d.ts +1 -0
- package/dist/external-findings-local.d.ts.map +1 -1
- package/dist/external-findings-local.js +14 -3
- package/dist/external-findings-local.js.map +1 -1
- package/dist/external-findings-publish.d.ts +2 -1
- package/dist/external-findings-publish.d.ts.map +1 -1
- package/dist/external-findings-publish.js +64 -28
- package/dist/external-findings-publish.js.map +1 -1
- package/dist/external-findings-read.d.ts +12 -1
- package/dist/external-findings-read.d.ts.map +1 -1
- package/dist/external-findings-read.js +25 -6
- package/dist/external-findings-read.js.map +1 -1
- package/dist/external-findings.d.ts +2 -0
- package/dist/external-findings.d.ts.map +1 -1
- package/dist/external-findings.js.map +1 -1
- package/dist/external-import-contract.d.ts +7 -1
- package/dist/external-import-contract.d.ts.map +1 -1
- package/dist/external-import-contract.js +63 -31
- package/dist/external-import-contract.js.map +1 -1
- package/dist/external-imports-feature.d.ts +6 -0
- package/dist/external-imports-feature.d.ts.map +1 -0
- package/dist/external-imports-feature.js +51 -0
- package/dist/external-imports-feature.js.map +1 -0
- package/dist/finding-workflow.d.ts +24 -5
- package/dist/finding-workflow.d.ts.map +1 -1
- package/dist/finding-workflow.js +24 -9
- package/dist/finding-workflow.js.map +1 -1
- package/dist/github-advisories.d.ts.map +1 -1
- package/dist/github-advisories.js +3 -1
- package/dist/github-advisories.js.map +1 -1
- package/dist/github-findings.d.ts +4 -3
- package/dist/github-findings.d.ts.map +1 -1
- package/dist/github-findings.js +16 -14
- package/dist/github-findings.js.map +1 -1
- package/dist/host-protocol.d.ts +1 -1
- package/dist/host-protocol.d.ts.map +1 -1
- package/dist/host-protocol.js +2 -2
- package/dist/host-protocol.js.map +1 -1
- package/dist/hosted-remediation.d.ts.map +1 -1
- package/dist/hosted-remediation.js +19 -2
- package/dist/hosted-remediation.js.map +1 -1
- package/dist/hosted-scan.d.ts +1 -1
- package/dist/hosted-scan.d.ts.map +1 -1
- package/dist/hosted-scan.js +0 -6
- package/dist/hosted-scan.js.map +1 -1
- package/dist/import-scan.js +17 -17
- package/dist/import-scan.js.map +1 -1
- package/dist/index.d.ts +4 -3
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +2 -1
- package/dist/index.js.map +1 -1
- package/dist/knowledge-base.d.ts +1 -0
- package/dist/knowledge-base.d.ts.map +1 -1
- package/dist/knowledge-base.js +20 -8
- package/dist/knowledge-base.js.map +1 -1
- package/dist/mock-scan.d.ts +1 -2
- package/dist/mock-scan.d.ts.map +1 -1
- package/dist/mock-scan.js +12 -17
- package/dist/mock-scan.js.map +1 -1
- package/dist/models.d.ts +10 -1
- package/dist/models.d.ts.map +1 -1
- package/dist/models.js.map +1 -1
- package/dist/multiscan.d.ts.map +1 -1
- package/dist/multiscan.js +1 -6
- package/dist/multiscan.js.map +1 -1
- package/dist/native-json-findings.d.ts +30 -0
- package/dist/native-json-findings.d.ts.map +1 -0
- package/dist/native-json-findings.js +114 -0
- package/dist/native-json-findings.js.map +1 -0
- package/dist/opengrep-findings.d.ts +10 -0
- package/dist/opengrep-findings.d.ts.map +1 -0
- package/dist/opengrep-findings.js +198 -0
- package/dist/opengrep-findings.js.map +1 -0
- package/dist/owner-evidence.d.ts +2 -0
- package/dist/owner-evidence.d.ts.map +1 -1
- package/dist/owner-evidence.js +2 -1
- package/dist/owner-evidence.js.map +1 -1
- package/dist/patch-tui.d.ts.map +1 -1
- package/dist/patch-tui.js +2 -0
- package/dist/patch-tui.js.map +1 -1
- package/dist/publication.js +1 -2
- package/dist/publication.js.map +1 -1
- package/dist/publish.d.ts +2 -0
- package/dist/publish.d.ts.map +1 -1
- package/dist/publish.js +1 -1
- package/dist/publish.js.map +1 -1
- package/dist/record.d.ts +1 -0
- package/dist/record.d.ts.map +1 -1
- package/dist/record.js +10 -0
- package/dist/record.js.map +1 -1
- package/dist/remediation.d.ts +1 -25
- package/dist/remediation.d.ts.map +1 -1
- package/dist/remediation.js +3 -24
- package/dist/remediation.js.map +1 -1
- package/dist/result.d.ts +5 -3
- package/dist/result.d.ts.map +1 -1
- package/dist/result.js +9 -6
- package/dist/result.js.map +1 -1
- package/dist/runtime.d.ts.map +1 -1
- package/dist/runtime.js +7 -7
- package/dist/runtime.js.map +1 -1
- package/dist/scan-dashboard.d.ts +5 -3
- package/dist/scan-dashboard.d.ts.map +1 -1
- package/dist/scan-dashboard.js +79 -26
- package/dist/scan-dashboard.js.map +1 -1
- package/dist/scan-history-renderer.d.ts.map +1 -1
- package/dist/scan-history-renderer.js +9 -3
- package/dist/scan-history-renderer.js.map +1 -1
- package/dist/scan-owner-suggestions.d.ts +1 -1
- package/dist/scan-owner-suggestions.d.ts.map +1 -1
- package/dist/scan-owner-suggestions.js +4 -4
- package/dist/scan-owner-suggestions.js.map +1 -1
- package/dist/scan-usage-display.d.ts +8 -0
- package/dist/scan-usage-display.d.ts.map +1 -0
- package/dist/scan-usage-display.js +46 -0
- package/dist/scan-usage-display.js.map +1 -0
- package/dist/scanner-import.d.ts +1 -1
- package/dist/scanner-import.d.ts.map +1 -1
- package/dist/scanner-import.js +7 -3
- package/dist/scanner-import.js.map +1 -1
- package/dist/security-policy.d.ts.map +1 -1
- package/dist/security-policy.js +17 -22
- package/dist/security-policy.js.map +1 -1
- package/dist/semgrep-findings.d.ts +4 -3
- package/dist/semgrep-findings.d.ts.map +1 -1
- package/dist/semgrep-findings.js +22 -89
- package/dist/semgrep-findings.js.map +1 -1
- package/dist/skill-authentication.d.ts +18 -0
- package/dist/skill-authentication.d.ts.map +1 -0
- package/dist/skill-authentication.js +82 -0
- package/dist/skill-authentication.js.map +1 -0
- package/dist/snyk-findings.d.ts +5 -4
- package/dist/snyk-findings.d.ts.map +1 -1
- package/dist/snyk-findings.js +18 -17
- package/dist/snyk-findings.js.map +1 -1
- package/dist/suggest-owners.d.ts +4 -1
- package/dist/suggest-owners.d.ts.map +1 -1
- package/dist/suggest-owners.js +53 -21
- package/dist/suggest-owners.js.map +1 -1
- package/dist/targets.d.ts.map +1 -1
- package/dist/targets.js +4 -1
- package/dist/targets.js.map +1 -1
- package/dist/wiz-csv.d.ts +2 -1
- package/dist/wiz-csv.d.ts.map +1 -1
- package/dist/wiz-csv.js +3 -3
- package/dist/wiz-csv.js.map +1 -1
- package/dist/wiz-findings.d.ts +2 -1
- package/dist/wiz-findings.d.ts.map +1 -1
- package/dist/wiz-findings.js +27 -23
- package/dist/wiz-findings.js.map +1 -1
- package/docs/classify-severity-records.md +3 -4
- package/docs/cli.md +171 -41
- package/docs/dedupe-records.md +15 -1
- package/docs/findings-service.md +119 -118
- package/docs/hosted-remediation.md +19 -17
- package/docs/hosted-scans.md +37 -11
- package/package.json +9 -9
- package/_bundled_plugin/scripts/generate_in_scope_files.py +0 -277
- package/_bundled_plugin/scripts/generate_rank_input.py +0 -350
- package/_bundled_plugin/scripts/rank_preview.py +0 -129
package/docs/cli.md
CHANGED
|
@@ -23,6 +23,28 @@ findings file in local scan history, use
|
|
|
23
23
|
GitHub import returns upstream alerts for validation; file import saves findings
|
|
24
24
|
without running security analysis.
|
|
25
25
|
|
|
26
|
+
## Find a workflow
|
|
27
|
+
|
|
28
|
+
- [Sign in or configure a provider](#authentication).
|
|
29
|
+
- [Scan a repository or selected paths](#scan-options-and-output),
|
|
30
|
+
[configure a Deep Scan](#configure-deep-scans), or
|
|
31
|
+
[save project settings](#project-files).
|
|
32
|
+
- [Review one system across repositories](#review-one-system-across-repositories)
|
|
33
|
+
or [run independent bulk scans](#bulk-scans).
|
|
34
|
+
- [Import vendor findings locally](#import-vendor-findings-locally),
|
|
35
|
+
[save findings as a scan](#import-findings-as-a-saved-scan), or
|
|
36
|
+
[retrieve GitHub alerts](#import-alerts-from-the-cli).
|
|
37
|
+
- [Inspect saved scans and rerun them](#scan-history-and-reruns),
|
|
38
|
+
[classify severity](#classify-finding-severity), or
|
|
39
|
+
[suggest owners](#suggest-finding-owners).
|
|
40
|
+
- [Validate and patch findings](#validate-and-patch-findings) or
|
|
41
|
+
[verify an existing fix](#verify-fixes).
|
|
42
|
+
- [Publish to Cloud](#publish-findings-to-cloud) or
|
|
43
|
+
[Linear](#publish-completed-scans-to-linear), or [export results](#exports-and-ci).
|
|
44
|
+
- [Draft a security policy](#generate-a-security-policy).
|
|
45
|
+
- [Use a hosted executor](#hosted-standard-scan) or
|
|
46
|
+
[run bulk scans in containers](#containerized-bulk-scans).
|
|
47
|
+
|
|
26
48
|
## Authentication
|
|
27
49
|
|
|
28
50
|
Sign in with ChatGPT, or supply an API key for CI:
|
|
@@ -404,6 +426,11 @@ codex-security scan . --owner-suggestions
|
|
|
404
426
|
codex-security scan . --output-dir /path/outside/repository/results --dry-run
|
|
405
427
|
```
|
|
406
428
|
|
|
429
|
+
`--path` selects files or directories. The scan summary and saved scan details
|
|
430
|
+
show requested paths and exclusions. `coverage.deferred` records unfinished
|
|
431
|
+
requested work separately from optional `coverage.openQuestions` follow-up.
|
|
432
|
+
Human-readable output quotes ambiguous paths, while JSON retains their original strings.
|
|
433
|
+
|
|
407
434
|
Whole-codebase and path scans also accept ordinary directories, including SVN
|
|
408
435
|
working copies. Their source inventories exclude `.git` and `.svn` metadata.
|
|
409
436
|
|
|
@@ -412,12 +439,20 @@ changes. Both require Git. Deep scans support whole repositories and path scopes
|
|
|
412
439
|
Working-tree snapshots include untracked nested Git repositories. Initialized submodules must
|
|
413
440
|
be clean and at the commit recorded by the parent.
|
|
414
441
|
|
|
442
|
+
Committed-diff scans require a clean, full checkout at the requested head
|
|
443
|
+
revision, including when using `--validate`. A different checkout revision or
|
|
444
|
+
local changes are rejected before scanning; check out the requested head and
|
|
445
|
+
commit or stash local changes before retrying.
|
|
446
|
+
|
|
415
447
|
`--owner-suggestions` writes optional `owner-suggestions.json` after a completed
|
|
416
448
|
committed Git scan, using the same checkout, model, and reasoning effort. Owner
|
|
417
449
|
errors leave the base scan completed. The JSON result includes
|
|
418
450
|
`ownerSuggestionsPath` or `ownerSuggestionsError`; the sealed findings and
|
|
419
451
|
manifest stay unchanged. This option is unsupported for working-tree and
|
|
420
|
-
directory snapshots
|
|
452
|
+
directory snapshots. It works with `--max-cost`: hints are recorded within the
|
|
453
|
+
existing scan execution and budget, and the report is finalized without another
|
|
454
|
+
model call. Missing hints abstain; invalid hints produce per-finding owner errors.
|
|
455
|
+
Use the separate `suggest-owners` command for explicit owner-only jobs.
|
|
421
456
|
|
|
422
457
|
Repeat `--knowledge-base PATH` for context: UTF-8 text files (including JSON and
|
|
423
458
|
SARIF), PDF, DOCX, or directories. Directory traversal skips other binary files;
|
|
@@ -471,7 +506,7 @@ or JSONL output produce:
|
|
|
471
506
|
With `--full-output`, the error appears under `error` in an `ok: false` envelope.
|
|
472
507
|
If the scan target changed, the error explains that the results no longer
|
|
473
508
|
represent the current checkout. Retained sealed results remain available under
|
|
474
|
-
`data`, including their manifest, findings,
|
|
509
|
+
`data`, including their manifest, findings, review summary, scan directory, and report
|
|
475
510
|
path. Unsealed or invalid artifacts are not included. This also applies to
|
|
476
511
|
`scans rerun` and `scans resume`.
|
|
477
512
|
For `scans rerun` and `scans resume`, `--filter-output` applies to retained `data`;
|
|
@@ -487,6 +522,38 @@ Diagnostics stay on stderr. Each command's `--schema --format json` describes
|
|
|
487
522
|
its successful output and failure codes.
|
|
488
523
|
See [Exports and CI](#exports-and-ci) for exit codes and CI examples.
|
|
489
524
|
|
|
525
|
+
### Follow-up finding validation
|
|
526
|
+
|
|
527
|
+
Scans already validate findings against local source. Add `--validate` to run
|
|
528
|
+
the existing standalone validation workflow for each reported finding after
|
|
529
|
+
the scan, using the same selected Cyber access program. Validation has read-only
|
|
530
|
+
filesystem access with network and web search disabled. Each assessment uses a
|
|
531
|
+
separate evidence directory; the combined report is saved as
|
|
532
|
+
`<scan-dir>/validation.md`, or a uniquely suffixed report
|
|
533
|
+
if that path already exists. Each completed assessment is saved immediately;
|
|
534
|
+
failed or interrupted runs retain the partial report. JSON scan output includes
|
|
535
|
+
the execution status, completed assessment count, and report path. Completion means the assessments finished,
|
|
536
|
+
not that every finding was confirmed. A scan with no findings needs no second
|
|
537
|
+
pass.
|
|
538
|
+
|
|
539
|
+
With `--workflow-id`, retries reuse completed assessments for unchanged findings,
|
|
540
|
+
source, validation settings, and saved evidence. Missing or changed evidence
|
|
541
|
+
causes validation to run again, as do older assessments without recorded evidence
|
|
542
|
+
fingerprints. By default, regeneration uses a new evidence directory. An explicit
|
|
543
|
+
SDK validation `outputDir` reuses an assessment only when it points to the same
|
|
544
|
+
evidence directory. A different destination starts a new assessment. The requested
|
|
545
|
+
directory must be empty when regenerating; existing files are never overwritten.
|
|
546
|
+
When `--knowledge-base` is supplied, the scan and all follow-up assessments use
|
|
547
|
+
one captured copy of those documents. A workflow retry must use the same document
|
|
548
|
+
contents. Use a new workflow ID if they changed or if the workflow was created
|
|
549
|
+
before document snapshots were bound to follow-up validation.
|
|
550
|
+
|
|
551
|
+
The report is supplemental: its assessments are not applied to the saved
|
|
552
|
+
findings or the `--fail-on-severity` decision. Validation failures exit with
|
|
553
|
+
`2` while retaining the completed scan. The additional model calls are not
|
|
554
|
+
cost-tracked, so `--validate` cannot be combined with `--max-cost` (including a
|
|
555
|
+
configured scan cost limit), `--dry-run`, or `--mock`.
|
|
556
|
+
|
|
490
557
|
### Understand scan scope and follow-up work
|
|
491
558
|
|
|
492
559
|
A completed scan means the requested workflow finished. It does not mean every
|
|
@@ -739,16 +806,9 @@ not to planning, result matching, or the total campaign.
|
|
|
739
806
|
|
|
740
807
|
### Configure deep scans
|
|
741
808
|
|
|
742
|
-
```
|
|
743
|
-
|
|
744
|
-
|
|
745
|
-
workers: 2,
|
|
746
|
-
subagents: 0,
|
|
747
|
-
stopAfterNoNew: 3,
|
|
748
|
-
stopAfterConsecutiveErrors: 2,
|
|
749
|
-
maxDiscoveryRuns: 10,
|
|
750
|
-
maxTimeMinutes: 90,
|
|
751
|
-
});
|
|
809
|
+
```bash
|
|
810
|
+
codex-security scan . --mode deep --workers 2 --subagents 0 \
|
|
811
|
+
--stop-after-no-new 3 --max-discovery-runs 10 --max-time 90
|
|
752
812
|
```
|
|
753
813
|
|
|
754
814
|
For `scan --mode deep`, `--workers` controls discovery concurrency and
|
|
@@ -757,11 +817,13 @@ For `scan --mode deep`, `--workers` controls discovery concurrency and
|
|
|
757
817
|
or duration. At the deadline, discovery stops; the scan then combines and returns
|
|
758
818
|
completed findings.
|
|
759
819
|
|
|
820
|
+
For TypeScript, see the [SDK Deep Scan example](../README.md#configure-deep-scans).
|
|
821
|
+
|
|
760
822
|
Use project-file `scan.deep` settings or legacy
|
|
761
823
|
`$CODEX_HOME/codex-security/config.toml` defaults. Counts must be positive except
|
|
762
824
|
that `subagents` can be zero. Discovery time accepts positive fractional minutes;
|
|
763
|
-
its default and maximum
|
|
764
|
-
advisory allowance,
|
|
825
|
+
its default and maximum are 5760 minutes (96 hours). Unlike Standard's
|
|
826
|
+
advisory allowance, the Deep discovery limit is enforced. Resuming a
|
|
765
827
|
Deep scan keeps its original deadline; rerunning starts a new scan.
|
|
766
828
|
`--max-time-hours`, SDK `maxTimeHours`, project `scan.deep.max_time_hours`, and
|
|
767
829
|
legacy TOML `deep_scan.max_time_hours` remain deprecated Deep-only aliases in
|
|
@@ -877,26 +939,27 @@ For filesystem and approval behavior, see the
|
|
|
877
939
|
|
|
878
940
|
### Environment variables
|
|
879
941
|
|
|
880
|
-
| Variable | Effect
|
|
881
|
-
| --------------------------------------------------------------------------- |
|
|
882
|
-
| `OPENAI_API_KEY`, `CODEX_API_KEY` | Scan credentials; the first takes precedence.
|
|
883
|
-
| `
|
|
884
|
-
| `
|
|
885
|
-
| `
|
|
886
|
-
| `
|
|
887
|
-
| `
|
|
888
|
-
| `
|
|
889
|
-
| `
|
|
890
|
-
| `
|
|
891
|
-
| `
|
|
892
|
-
| `
|
|
893
|
-
| `
|
|
894
|
-
| `
|
|
895
|
-
| `
|
|
896
|
-
| `
|
|
897
|
-
| `
|
|
898
|
-
| `
|
|
899
|
-
| `
|
|
942
|
+
| Variable | Effect |
|
|
943
|
+
| --------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
|
|
944
|
+
| `OPENAI_API_KEY`, `CODEX_API_KEY` | Scan credentials; the first takes precedence. |
|
|
945
|
+
| `CODEX_SECURITY_ENABLE_EXTERNAL_IMPORTS` | Set to `1` to enable vendor finding imports, imported-findings readback, and GitHub advisory acquisition; disabled otherwise. |
|
|
946
|
+
| `CODEX_SECURITY_STATE_DIR` | Private history, database, and default artifacts. |
|
|
947
|
+
| `CODEX_SECURITY_PROJECT_CONFIG` | Selected project file; `-c` overrides it. |
|
|
948
|
+
| `CODEX_HOME` | Ambient Codex home; default `~/.codex`. |
|
|
949
|
+
| `CODEX_CLI_PATH` | Codex executable for login, setup, scans, and workers. |
|
|
950
|
+
| `PYTHON` | Python interpreter unless an explicit option overrides it. |
|
|
951
|
+
| `CODEX_SECURITY_LOG_LEVEL` | CLI diagnostics; `debug` enables verbose output. |
|
|
952
|
+
| `LOG_LEVEL` | Fallback if `CODEX_SECURITY_LOG_LEVEL` is unset or blank. |
|
|
953
|
+
| `CODEX_SECURITY_LINEAR_TEAM`, `CODEX_SECURITY_LINEAR_PROJECT` | Default publication destination. |
|
|
954
|
+
| `CODEX_SECURITY_LINEAR_API_KEY` | Linear personal API key. |
|
|
955
|
+
| `CODEX_SECURITY_CLOUD_BASE_URL` | Cloud API root for discovery, imports, and scan publication. Defaults to `https://chatgpt.com/backend-api/aardvark`. |
|
|
956
|
+
| `CODEX_SECURITY_CLOUD_WEB_URL` | Cloud app URL for repository links when an alternate deployment serves its UI separately. |
|
|
957
|
+
| `CODEX_SECURITY_EMBEDDINGS_URL` | Local dedupe and findings service embeddings endpoint. |
|
|
958
|
+
| `GH_HOST` | GitHub Enterprise host for bulk discovery. |
|
|
959
|
+
| `CODEX_SECURITY_NO_UPDATE_NOTICE`, `NO_UPDATE_NOTIFIER` | Disable interactive update notices. |
|
|
960
|
+
| `CODEX_SECURITY_NPM_REGISTRY`, `npm_config_registry`, `NPM_CONFIG_REGISTRY` | Update registry, in precedence order. |
|
|
961
|
+
| `CI` | Disable interactive update notices. |
|
|
962
|
+
| `NO_COLOR`, `TERM` | Disable colored history when `NO_COLOR` is defined or `TERM=dumb`. |
|
|
900
963
|
|
|
901
964
|
Custom Codex executables need thread source attribution for `exec` and
|
|
902
965
|
`app-server` (Codex 0.149.1+). On Windows, use a native `.exe` or `.com`;
|
|
@@ -961,6 +1024,14 @@ work could not be measured, including in-flight turns or missing earlier attempt
|
|
|
961
1024
|
The parent can continue after report completion, so final CLI tokens can exceed
|
|
962
1025
|
the saved measurement window.
|
|
963
1026
|
|
|
1027
|
+
During a scan, progress shows when Codex reported the displayed token and cost
|
|
1028
|
+
totals, in UTC. If the report has no timestamp, progress says so.
|
|
1029
|
+
In-flight requests may add tokens and cost after that time. When Codex supplies
|
|
1030
|
+
account allowance, progress shows the percentage used in each reported window
|
|
1031
|
+
and the time of that reading. On a short terminal, resize the window or press
|
|
1032
|
+
`d` to scroll through the full readings in Details. With ChatGPT authentication,
|
|
1033
|
+
progress also says when Codex has yet to report allowance.
|
|
1034
|
+
|
|
964
1035
|
`usage.accountRateLimits` saves the latest observed account-wide readings with
|
|
965
1036
|
their own timestamps, window durations, and reset times. These are historical
|
|
966
1037
|
observations, not a live allowance check or scan-only consumption. Empty readings
|
|
@@ -1197,6 +1268,26 @@ Supply the validation prompt again when rerunning.
|
|
|
1197
1268
|
|
|
1198
1269
|
## Import vendor findings locally
|
|
1199
1270
|
|
|
1271
|
+
Use the [scanner file import schema and capability guide](https://github.com/openai/codex-security/blob/main/docs/scanner-imports/schema-guide.md) to compare provider identities, mapped evidence and destination behavior before selecting a report.
|
|
1272
|
+
|
|
1273
|
+
External finding imports are disabled by default. Opt in for the current shell:
|
|
1274
|
+
|
|
1275
|
+
```bash
|
|
1276
|
+
export CODEX_SECURITY_ENABLE_EXTERNAL_IMPORTS=1
|
|
1277
|
+
```
|
|
1278
|
+
|
|
1279
|
+
In PowerShell, use `$env:CODEX_SECURITY_ENABLE_EXTERNAL_IMPORTS = '1'`.
|
|
1280
|
+
Only `1` enables the feature. Without it, `publish findings`, `findings imported`,
|
|
1281
|
+
and `import github-advisories` are absent from command help and schemas and cannot
|
|
1282
|
+
run. The SDK's external publication, local import/readback, and advisory
|
|
1283
|
+
acquisition APIs require the same flag in their effective environment. An explicit
|
|
1284
|
+
`dependencies.environment` is used instead of the process environment. Pure
|
|
1285
|
+
normalizers and file readers remain available as library utilities.
|
|
1286
|
+
|
|
1287
|
+
This flag does not affect `publish scan`, `publish check`, `scan import`, or the
|
|
1288
|
+
existing `import github` alert collector. Disabling it retains previously imported
|
|
1289
|
+
records; enable it again to read them with `findings imported`.
|
|
1290
|
+
|
|
1200
1291
|
Prefer the provider's supported native JSON from its CLI, plugin, or API. Native
|
|
1201
1292
|
reports can retain details omitted by SARIF. Use SARIF or CSV as compatibility
|
|
1202
1293
|
inputs only for providers and report profiles that support them. A JSON API
|
|
@@ -1214,6 +1305,7 @@ repository path instead of a Cloud repository ID or URL. Supported inputs includ
|
|
|
1214
1305
|
Wiz findings, [Snyk Open Source JSON and SARIF](#import-snyk-open-source-findings),
|
|
1215
1306
|
[Endor Labs Finding JSON and SARIF](#import-endor-labs-findings),
|
|
1216
1307
|
[Semgrep Code JSON and SARIF](https://github.com/openai/codex-security/blob/main/docs/scanner-imports/semgrep.md),
|
|
1308
|
+
[OpenGrep native JSON](https://github.com/openai/codex-security/blob/main/docs/scanner-imports/opengrep.md),
|
|
1217
1309
|
and [saved GitHub alerts and GHSA advisories](#import-github-findings-locally-or-to-cloud):
|
|
1218
1310
|
|
|
1219
1311
|
```bash
|
|
@@ -1246,8 +1338,18 @@ Repeated imports update the same record by repository, provider, source key, and
|
|
|
1246
1338
|
source finding ID. The result reports created, updated, and unchanged counts.
|
|
1247
1339
|
Keep the source key stable across exports. Records omitted from a later selection
|
|
1248
1340
|
remain stored; omission does not resolve or delete a finding. Excluded records
|
|
1249
|
-
are reported, and an import with exclusions exits with status 1.
|
|
1250
|
-
|
|
1341
|
+
are reported, and an import with exclusions exits with status 1. Both destinations
|
|
1342
|
+
read the same vendor formats; Cloud's field, size and nesting limits do not apply
|
|
1343
|
+
to local file imports.
|
|
1344
|
+
|
|
1345
|
+
For OpenGrep, use `--provider opengrep` and supply `--source-repository-url`.
|
|
1346
|
+
The reader supports native JSON and gzip for both destinations. It uses the
|
|
1347
|
+
existing `semgrep` source-provider contract while retaining `OpenGrep` as the
|
|
1348
|
+
scanner origin; keep a stable OpenGrep-specific source key. Review report
|
|
1349
|
+
diagnostics as well as findings: import completion does not establish scan
|
|
1350
|
+
coverage. The [OpenGrep guide](https://github.com/openai/codex-security/blob/main/docs/scanner-imports/opengrep.md)
|
|
1351
|
+
covers evidence identity, empty reports, and assessing an imported finding with
|
|
1352
|
+
the existing SDK validator.
|
|
1251
1353
|
|
|
1252
1354
|
`scan import --json` and `scan import --csv` remain separate commands for importing
|
|
1253
1355
|
Codex Security's findings schema as a saved scan; they do not accept vendor
|
|
@@ -1366,6 +1468,8 @@ network findings are not supported by this repository importer. Cloud destinatio
|
|
|
1366
1468
|
currently support connected GitHub and GitHub Enterprise repositories, including
|
|
1367
1469
|
custom Enterprise hostnames. Named Wiz exports do not add other VCS destinations.
|
|
1368
1470
|
|
|
1471
|
+
#### Select findings and a destination
|
|
1472
|
+
|
|
1369
1473
|
Use an authorized [Wiz MCP](https://www.wiz.io/blog/introducing-wiz-mcp) or Wiz API
|
|
1370
1474
|
connection to acquire findings and save the supported native JSON. A configured
|
|
1371
1475
|
plugin may provide that connection; an official Codex plugin is not a prerequisite.
|
|
@@ -1412,6 +1516,8 @@ gzip-compressed JSON or CSV are accepted; gzip is detected regardless of the
|
|
|
1412
1516
|
filename extension. **Raw Event** on Code & Build Scans contains scan metadata
|
|
1413
1517
|
rather than findings.
|
|
1414
1518
|
|
|
1519
|
+
#### Configure an alternate Cloud deployment
|
|
1520
|
+
|
|
1415
1521
|
For an alternate Cloud deployment, set `CODEX_SECURITY_CLOUD_BASE_URL` to its
|
|
1416
1522
|
API root before previewing or uploading, for example
|
|
1417
1523
|
`https://cloud.example.test/backend-api/aardvark`. Remote APIs require HTTPS;
|
|
@@ -1432,6 +1538,8 @@ the return link; all API requests still use `CODEX_SECURITY_CLOUD_BASE_URL`.
|
|
|
1432
1538
|
For custom API destinations without a configured app URL, completion retains
|
|
1433
1539
|
the manual navigation guidance rather than guessing a UI host or port.
|
|
1434
1540
|
|
|
1541
|
+
#### Preview and publish
|
|
1542
|
+
|
|
1435
1543
|
Preview the selection and destination:
|
|
1436
1544
|
|
|
1437
1545
|
```bash
|
|
@@ -1457,6 +1565,8 @@ exclusions. `--dry-run --format json` retains all normalized findings and comple
|
|
|
1457
1565
|
evidence for inspection. A prompt explicitly includes any records that will be
|
|
1458
1566
|
skipped.
|
|
1459
1567
|
|
|
1568
|
+
#### Package vulnerability inputs
|
|
1569
|
+
|
|
1460
1570
|
Native package input can be a Wiz JSON vulnerability report, a vulnerability
|
|
1461
1571
|
finding, an array, a complete `data.vulnerabilityFindings.nodes` response, or JSONL
|
|
1462
1572
|
with one package record per line. The repository package-vulnerability CSV
|
|
@@ -1507,6 +1617,8 @@ fetch from Wiz, assess findings, or change vendor or Cloud triage decisions.
|
|
|
1507
1617
|
Findings from external network scans are excluded from this package vulnerability
|
|
1508
1618
|
mapping.
|
|
1509
1619
|
|
|
1620
|
+
#### SAST, repository secrets, and IaC inputs
|
|
1621
|
+
|
|
1510
1622
|
For SAST, repository secrets, and IaC, save the documented JSON API collection:
|
|
1511
1623
|
|
|
1512
1624
|
| Finding family | Collection | Raw occurrence identity |
|
|
@@ -1565,6 +1677,8 @@ collection:
|
|
|
1565
1677
|
}
|
|
1566
1678
|
```
|
|
1567
1679
|
|
|
1680
|
+
#### Preserved evidence
|
|
1681
|
+
|
|
1568
1682
|
The adapters preserve each selected raw node exactly in `source_data`. Typed
|
|
1569
1683
|
`evidence.details` carries `kind`, verified `repository`, vendor `source_status`,
|
|
1570
1684
|
and family-specific evidence:
|
|
@@ -1583,6 +1697,8 @@ does not establish that it is deployed. Precise original timestamps remain in
|
|
|
1583
1697
|
`source_updated_at` field. SAST creation time and IaC last-seen time are not update
|
|
1584
1698
|
timestamps.
|
|
1585
1699
|
|
|
1700
|
+
#### Convert CSV reports
|
|
1701
|
+
|
|
1586
1702
|
Native SAST and secret report downloads can be CSV, including gzip-compressed
|
|
1587
1703
|
CSV. Those CSV profiles are not parsed directly. Convert a selected report with a reviewed mapping
|
|
1588
1704
|
for its actual column headers into normalized JSONL, preserving each original row
|
|
@@ -1607,6 +1723,8 @@ Inputs must be valid UTF-8. Integer-valued evidence outside JavaScript's safe
|
|
|
1607
1723
|
integer range is rejected; export those values as strings to preserve them
|
|
1608
1724
|
exactly. Invalid records appear in `excluded` with their source ID and reason.
|
|
1609
1725
|
|
|
1726
|
+
#### Resume interrupted imports
|
|
1727
|
+
|
|
1610
1728
|
Requests contain at most 100 findings and respect the Cloud payload limits.
|
|
1611
1729
|
Before uploading, the publisher saves request IDs and bodies privately under
|
|
1612
1730
|
the configured Codex Security state directory. After an uncertain response,
|
|
@@ -1618,6 +1736,8 @@ API endpoint, not a link to the Cloud UI. A reset
|
|
|
1618
1736
|
retires the old request without republishing; review and explicitly approve a
|
|
1619
1737
|
fresh invocation.
|
|
1620
1738
|
|
|
1739
|
+
#### Results and exit codes
|
|
1740
|
+
|
|
1621
1741
|
Results distinguish completion from partial or interrupted work:
|
|
1622
1742
|
|
|
1623
1743
|
| Status | Exit code | Meaning |
|
|
@@ -1768,7 +1888,7 @@ The [records protocol](classify-severity-records.md) accepts immutable Markdown
|
|
|
1768
1888
|
report snapshots and delegates model execution to the host.
|
|
1769
1889
|
|
|
1770
1890
|
For saved findings, use exactly one of `--scan` (ID, prefix, or `latest`) and `--scan-dir`.
|
|
1771
|
-
Omitting `--rubric` runs classification with the [built-in severity rubric](
|
|
1891
|
+
Omitting `--rubric` runs classification with the [built-in severity rubric](https://github.com/openai/codex-security/blob/main/sdk/typescript/src/default-severity-rubric.ts).
|
|
1772
1892
|
It evaluates attacker access, boundary crossing, additional harm, and evidence for
|
|
1773
1893
|
Critical, High, Medium, Low, and Informational findings. Confidence remains separate
|
|
1774
1894
|
from severity; missing proof alone does not justify a downgrade. An explicit
|
|
@@ -2278,6 +2398,9 @@ installation fails. The installer respects `core.hooksPath`.
|
|
|
2278
2398
|
|
|
2279
2399
|
## Import GitHub findings locally or to Cloud
|
|
2280
2400
|
|
|
2401
|
+
Local and Cloud ingestion require the [external-import opt-in](#import-vendor-findings-locally).
|
|
2402
|
+
The existing alert collector remains available without it.
|
|
2403
|
+
|
|
2281
2404
|
Acquire code-scanning findings with the existing `import github` collector and
|
|
2282
2405
|
save its complete JSON output. In Codex, the official
|
|
2283
2406
|
[GitHub Codex plugin](https://github.com/openai/plugins/tree/main/plugins/github)
|
|
@@ -2369,6 +2492,8 @@ import file directly. Read records with `listLocalExternalFindings({ repository
|
|
|
2369
2492
|
|
|
2370
2493
|
### Import GHSA advisories separately
|
|
2371
2494
|
|
|
2495
|
+
Set `CODEX_SECURITY_ENABLE_EXTERNAL_IMPORTS=1` before using this command or its SDK API.
|
|
2496
|
+
|
|
2372
2497
|
**Importing a GHSA advisory does not establish an installed dependency or
|
|
2373
2498
|
applicability to the destination repository.** Repository advisories are
|
|
2374
2499
|
disclosures maintained by a repository; global advisories describe affected
|
|
@@ -2705,6 +2830,11 @@ for `patch`. Omit it or use `--verification-mode standard` for the default check
|
|
|
2705
2830
|
Results include evidence and `fixed`, `still_vulnerable`, or `inconclusive` status.
|
|
2706
2831
|
`--json` returns structured output. Exit codes are `0` when all findings are
|
|
2707
2832
|
fixed, `1` when any remain vulnerable, and `2` for inconclusive/failed checks.
|
|
2833
|
+
Authentication and execution failures print diagnostics on stderr and return
|
|
2834
|
+
`status: "failed"`, `code: "VERIFICATION_FAILED"`, and `message` with `--json`
|
|
2835
|
+
or `--format jsonl`. With JSON/JSONL `--full-output`, failures use an `ok: false`
|
|
2836
|
+
error envelope. Other formats retain stderr-only failures. Interruptions retain
|
|
2837
|
+
exit codes `130` and `143` without a result.
|
|
2708
2838
|
|
|
2709
2839
|
## Command discovery and integrations
|
|
2710
2840
|
|
|
@@ -2721,6 +2851,10 @@ scan, triage, patch, and verification workflows, see the
|
|
|
2721
2851
|
For local findings storage, deduplication, and custom endpoints, see the
|
|
2722
2852
|
[findings guide](findings-service.md).
|
|
2723
2853
|
|
|
2854
|
+
### Hosted Standard scan
|
|
2855
|
+
|
|
2856
|
+
`codex-security scan --host` runs one versioned JSON-RPC invocation with an explicit host executor. Use it alone; it never performs local inference. See [the hosted scan protocol](hosted-scans.md) for input, filesystem, artifact, usage, and cancellation requirements.
|
|
2857
|
+
|
|
2724
2858
|
## Containerized bulk scans
|
|
2725
2859
|
|
|
2726
2860
|
Create `repositories.csv` as described under [Bulk scans](#bulk-scans), then run
|
|
@@ -2760,7 +2894,3 @@ capabilities, no-new-privileges, and seccomp policy. Hosts that permit nested us
|
|
|
2760
2894
|
namespaces do not need it. The legacy Landlock fallback is unsupported.
|
|
2761
2895
|
See the [Docker guide](https://github.com/openai/codex-security/blob/main/docker/README.md)
|
|
2762
2896
|
for deployment and source-build instructions.
|
|
2763
|
-
|
|
2764
|
-
### Hosted Standard scan
|
|
2765
|
-
|
|
2766
|
-
`codex-security scan --host` runs one versioned JSON-RPC invocation with an explicit host executor. Use it alone; it never performs local inference. See [the hosted scan protocol](hosted-scans.md) for input, filesystem, artifact, usage, and cancellation requirements.
|
package/docs/dedupe-records.md
CHANGED
|
@@ -190,7 +190,7 @@ For failure or an inconclusive review, send an explicit error:
|
|
|
190
190
|
}
|
|
191
191
|
```
|
|
192
192
|
|
|
193
|
-
|
|
193
|
+
A host error ends the review without another submission. Invalid model
|
|
194
194
|
answers, missing decisions, and host errors make the whole batch unresolved;
|
|
195
195
|
previous successful reviews in that run do not become persistence decisions.
|
|
196
196
|
The existing algorithm treats a validated `DISTINCT` as a nonmatch, when
|
|
@@ -203,6 +203,20 @@ severity-based representative selection are reused. No local review checkpoints
|
|
|
203
203
|
are read or written in records mode. Local saved-scan execution retains its
|
|
204
204
|
existing tool-submission validation and workflow checkpoints.
|
|
205
205
|
|
|
206
|
+
### Continuing a review
|
|
207
|
+
|
|
208
|
+
A `review.run` request with `supportsContinuation: true` can receive the result
|
|
209
|
+
`{"status":"missing_submission"}`. Send this only after verifying that the
|
|
210
|
+
original turn completed without a pending decision or blocker. Keep that
|
|
211
|
+
review session open. The CLI then sends one `review.continue` request with a
|
|
212
|
+
fresh JSON-RPC ID and `params: {requestId, prompt}`. The request ID in the
|
|
213
|
+
parameters identifies the original review. Submit the prompt in the same
|
|
214
|
+
session and reply on the new JSON-RPC ID. The correction omits
|
|
215
|
+
`supportsContinuation`, so the host releases the session after that turn. A second missing submission ends
|
|
216
|
+
the review as unresolved. A pending tool call uses the original turn and
|
|
217
|
+
requires no correction. An uncertain outcome or explicit blocker follows the
|
|
218
|
+
existing error path. Hosts without continuation support can ignore the field.
|
|
219
|
+
|
|
206
220
|
## Final response and persistence
|
|
207
221
|
|
|
208
222
|
```json
|