diff --git a/.github/workflows/README.md b/.github/workflows/README.md index b6fa99a..ca31eb6 100644 --- a/.github/workflows/README.md +++ b/.github/workflows/README.md @@ -14,7 +14,7 @@ The reusable workflow declares the expected typed review artifacts for Docs Agen The target repository grants `contents: write`, `pull-requests: write`, and `issues: write`. Docs Agent forwards the caller-scoped `${{ github.token }}` to WP Codebox for same-repository publication, so consumers do not configure `ACCESS_TOKEN`. `OPENAI_API_KEY` is an optional workflow secret and is required only for a live OpenAI run; skipped and dry-run calls do not require it. `EXTERNAL_PACKAGE_SOURCE_POLICY` remains a separate required v1 JSON secret. Migrate its value to the exact one-line JSON in the root README: it authorizes the selected Docs Agent package, the pinned Agents API component, the pinned PHP AI Client overlay, and the checksum-pinned OpenAI provider artifact. Both secrets are forwarded to WP Codebox without serialization into the task descriptor. -Docs Agent consumes the released [WP Codebox v0.12.14](https://github.com/Automattic/wp-codebox/releases/tag/v0.12.14) workflow and passes the matching `wp_codebox_release_ref: v0.12.14` input. WP Codebox validates that the paired tags match, resolves the release tag, verifies its package version, materializes the declared native runtime closure, and executes the selected imported package identity. It seeds a sandbox-local copy-on-write workspace and exposes the workspace tools only inside that sandbox. WP Codebox applies the returned bounded patch to the host workspace, runs validation and verification there, then publishes approved host changes. Provider artifacts retain only canonical runtime-source provenance: uploads contain allowlisted review artifacts, controlled workflow envelopes, and provenance metadata, never prepared source bytes. Before persisting workflow results or artifact uploads, WP Codebox sanitizes private runtime paths from nested values, object keys, diagnostics, and command arguments. Lifecycle failures publish a normalized failed result even when artifact preparation cannot complete. Diagnostic messages that name runtime classes remain reviewable; PHP-shaped runtime source remains blocked even under a reviewer-safe extension. See [WP Codebox #1767](https://github.com/Automattic/wp-codebox/issues/1767), [WP Codebox #1784](https://github.com/Automattic/wp-codebox/issues/1784), [WP Codebox #1782](https://github.com/Automattic/wp-codebox/pull/1782), and [WP Codebox #1785](https://github.com/Automattic/wp-codebox/pull/1785). Regression reference: [run `29311239264`](https://github.com/Automattic/build-with-wordpress/actions/runs/29311239264). +Docs Agent consumes the released [WP Codebox v0.12.16](https://github.com/Automattic/wp-codebox/releases/tag/v0.12.16) workflow and passes the matching `wp_codebox_release_ref: v0.12.16` input. WP Codebox validates that the paired tags match, resolves the release tag, verifies its package version, materializes the declared native runtime closure, and executes the selected imported package identity. It creates a secret-filtered external seed snapshot and passes it through canonical `task_input.workspaces` for the sandbox-local copy-on-write workspace. Canonical changed-files and patch references become actionable host-workspace changes; WP Codebox applies the bounded patch, runs validation and verification, then publishes approved host changes. Provider artifacts retain only canonical runtime-source and seed provenance: uploads contain allowlisted review artifacts, controlled workflow envelopes, and provenance metadata, never prepared source bytes or temporary snapshot paths. Before persisting workflow results or artifact uploads, WP Codebox sanitizes private runtime paths from nested values, object keys, diagnostics, and command arguments. Lifecycle and downstream failures retain normalized runtime evidence in their normalized failed result, even when artifact preparation cannot complete. Diagnostic messages that name runtime classes remain reviewable; PHP-shaped runtime source remains blocked even under a reviewer-safe extension. See [WP Codebox #1767](https://github.com/Automattic/wp-codebox/issues/1767), [WP Codebox #1786](https://github.com/Automattic/wp-codebox/issues/1786), [WP Codebox #1788](https://github.com/Automattic/wp-codebox/issues/1788), and [WP Codebox #1790](https://github.com/Automattic/wp-codebox/pull/1790). Regression references: [workspace handoff run `29324157852`](https://github.com/Automattic/build-with-wordpress/actions/runs/29324157852), [snapshot topology run `29324563665`](https://github.com/Automattic/build-with-wordpress/actions/runs/29324563665), [v0.12.16 verification run `29337623896`](https://github.com/Automattic/wp-codebox/actions/runs/29337623896), and [release run `29342892920`](https://github.com/Automattic/wp-codebox/actions/runs/29342892920). ## Docs Agent Runner Recipe diff --git a/.github/workflows/maintain-docs.yml b/.github/workflows/maintain-docs.yml index 768b5cb..cb1baa8 100644 --- a/.github/workflows/maintain-docs.yml +++ b/.github/workflows/maintain-docs.yml @@ -249,9 +249,9 @@ jobs: contents: write pull-requests: write issues: write - uses: Automattic/wp-codebox/.github/workflows/run-agent-task.yml@v0.12.14 + uses: Automattic/wp-codebox/.github/workflows/run-agent-task.yml@v0.12.16 with: - wp_codebox_release_ref: v0.12.14 + wp_codebox_release_ref: v0.12.16 external_package_source: ${{ needs.prepare.outputs.external_package_source }} runtime_sources: ${{ needs.prepare.outputs.runtime_sources }} workload_id: docs-agent-${{ inputs.audience }}-${{ inputs.run_kind }} diff --git a/.github/workflows/validate.yml b/.github/workflows/validate.yml index 4b99314..88edd4f 100644 --- a/.github/workflows/validate.yml +++ b/.github/workflows/validate.yml @@ -17,7 +17,7 @@ jobs: uses: actions/checkout@v4 with: repository: Automattic/wp-codebox - ref: v0.12.14 + ref: v0.12.16 path: .wp-codebox - name: Validate Docs Agent env: diff --git a/tests/validate-docs-agent-packages.php b/tests/validate-docs-agent-packages.php index 6647980..d78bae9 100644 --- a/tests/validate-docs-agent-packages.php +++ b/tests/validate-docs-agent-packages.php @@ -91,11 +91,11 @@ $transitional_homeboy_extensions_workflow = 'uses: Extra-Chill/homeboy-extensions/.github/workflows/runtime-agent-full-run.yml@main'; $forbidden_docs_agent_codebox_workflow = 'uses: Automattic/wp-codebox/.github/workflows/docs-agent-runner.yml@main'; -$generic_codebox_agent_task_workflow = 'uses: Automattic/wp-codebox/.github/workflows/run-agent-task.yml@v0.12.14'; +$generic_codebox_agent_task_workflow = 'uses: Automattic/wp-codebox/.github/workflows/run-agent-task.yml@v0.12.16'; $assert( ! str_contains( $maintain_docs_workflow, $transitional_homeboy_extensions_workflow ), 'maintain-docs.yml must not call Homeboy Extensions directly.' ); $assert( ! str_contains( $maintain_docs_workflow, $forbidden_docs_agent_codebox_workflow ), 'maintain-docs.yml must not call a Codebox-owned Docs Agent wrapper.' ); $assert( str_contains( $maintain_docs_workflow, $generic_codebox_agent_task_workflow ), 'maintain-docs.yml must call the generic Codebox agent-task workflow.' ); -$assert( str_contains( $maintain_docs_workflow, 'wp_codebox_release_ref: v0.12.14' ), 'maintain-docs.yml must pass the matching WP Codebox release tag.' ); +$assert( str_contains( $maintain_docs_workflow, 'wp_codebox_release_ref: v0.12.16' ), 'maintain-docs.yml must pass the matching WP Codebox release tag.' ); $workflow_blocked_runtime_fragments = array_values( array_diff( $blocked_runtime_fragments, array( 'wp-codebox', 'Automattic/wp-codebox', 'OPENAI_API_KEY' ) ) ); $workflow_internal_fragments = array_merge( $workflow_blocked_runtime_fragments, array( 'homeboy_extensions_ref:', 'runtime_ref:', 'runtime_ref }}', 'runtime_provider:', 'runtime_provider }}', 'runtime_profile:', 'runtime_profile }}', 'runtime_profiles:', 'runtime_profiles }}', 'runtime_execution:', 'runtime_execution }}', 'runtime_config:', 'runtime_config }}', 'component_contracts:', 'component_contracts }}', 'ability_requirements:', 'ability_requirements }}', 'runtime_components:', 'runtime_components }}', 'runtime_mounts:', 'runtime_mounts }}', 'required_abilities:', 'required_abilities }}', 'extra_wp_config_defines:' ) ); @@ -132,7 +132,7 @@ foreach ( array( 'Docs Agent Runner Recipe', 'portable recipe', 'Docs Agent owns the native package' ) as $migration_note_text ) { $assert( str_contains( $workflow_readme, $migration_note_text ), "Workflow README missing agent runtime note: {$migration_note_text}" ); } -$assert( str_contains( $workflow_readme, 'v0.12.14' ), 'Workflow README must record the WP Codebox release tag.' ); +$assert( str_contains( $workflow_readme, 'v0.12.16' ), 'Workflow README must record the WP Codebox release tag.' ); $assert( str_contains( $workflow_readme, 'Diagnostic messages that name runtime classes remain reviewable' ), 'Workflow README must document diagnostic-versus-source detection.' ); $assert( str_contains( $workflow_readme, 'allowlisted review artifacts' ), 'Workflow README must document the WP Codebox upload allowlist.' ); $assert( str_contains( $workflow_readme, 'normalized failed result' ), 'Workflow README must document normalized WP Codebox failures.' ); diff --git a/tests/validate-wp-codebox-run-agent-task-contract.php b/tests/validate-wp-codebox-run-agent-task-contract.php index 0ec9274..fb407d5 100644 --- a/tests/validate-wp-codebox-run-agent-task-contract.php +++ b/tests/validate-wp-codebox-run-agent-task-contract.php @@ -70,6 +70,10 @@ $assert( true === ( $release['sandbox_local_copy_on_write_workspace_tools'] ?? null ), 'WP Codebox release fixture must cover sandbox-local copy-on-write workspace tools.' ); $assert( true === ( $release['host_patch_apply_verification_publication'] ?? null ), 'WP Codebox release fixture must cover host patch apply, verification, and publication.' ); $assert( true === ( $release['provenance_only_uploads'] ?? null ), 'WP Codebox release fixture must cover provenance-only uploads.' ); +$assert( true === ( $release['canonical_task_input_workspace_handoff'] ?? null ), 'WP Codebox release fixture must cover canonical task_input workspace handoff.' ); +$assert( true === ( $release['external_secret_filtered_seed_snapshot'] ?? null ), 'WP Codebox release fixture must cover external secret-filtered workspace seed snapshots.' ); +$assert( true === ( $release['actionable_patch_normalization'] ?? null ), 'WP Codebox release fixture must cover actionable patch normalization.' ); +$assert( true === ( $release['failure_evidence_preserved'] ?? null ), 'WP Codebox release fixture must preserve normalized runtime evidence on failures.' ); $native_result_path = $release['native_result_path'] ?? null; $workflow_result_path = $release['workflow_result_path'] ?? null; $assert( '.codebox/native-agent-task-result.json' === $native_result_path, 'WP Codebox release fixture must declare the controlled native result path.' ); @@ -237,14 +241,20 @@ $assert( str_contains( $producer_sanitizer, 'if (descriptor.role === "provider_plugin" && Array.isArray(descriptor.metadata?.providers)) provenance.providers = descriptor.metadata.providers' ), 'WP Codebox provenance artifacts must retain the canonical provider allowlist.' ); $assert( str_contains( $producer_execute, 'sanitizeRuntimeSourceValue(nativeRuntimeResult, privateRuntimeSourceRootForSanitization)' ), 'WP Codebox must sanitize private runtime paths from native task results before persistence.' ); $assert( str_contains( $producer_execute, 'forbiddenRoots: [workspace, artifactsPath]' ) && str_contains( $producer_execute, 'const privatePreparationRoot = privateRuntimeSourceRoot ? join(privateRuntimeSourceRoot, "prepared-runtime-sources") : ""' ), 'WP Codebox must keep private runtime sources outside the workspace and artifact roots.' ); -$assert( str_contains( $producer_upload, 'sanitizeRuntimeSourceJson(text, runtimeSourceRoots)' ), 'WP Codebox must sanitize private runtime paths from artifact uploads.' ); +$assert( str_contains( $producer_upload, 'sanitizeRuntimeSourceJson(text, privateUploadRoots)' ), 'WP Codebox must sanitize private runtime and workspace paths from artifact uploads.' ); $assert( str_contains( $producer_sanitizer, 'RUNTIME_SOURCE_PLACEHOLDER = "[runtime-source]"' ), 'WP Codebox must replace private runtime paths with the published placeholder.' ); $assert( str_contains( $producer_sanitizer, 'PRIVATE_RUNTIME_SOURCE_FIELDS = new Set(["source_package_root"])' ), 'WP Codebox must remove private runtime source-root fields.' ); $assert( str_contains( $producer_execute, 'ability: "wp-codebox/run-runtime-package"' ) && str_contains( $producer_execute, 'imported_agent: materializedPackage.identity' ), 'WP Codebox must execute and preserve the imported package identity.' ); -$assert( str_contains( $producer_execute, 'mode: "readwrite", sourceMode: "repo-backed", seed: { type: "directory", source: workspace' ), 'WP Codebox must seed a sandbox-local copy-on-write workspace from the target repository.' ); -$assert( str_contains( $producer_execute, 'applyRunnerWorkspacePatch({ artifactRoot: artifactsPath, artifactRefs: refs, workspaceRoot: workspace, writablePaths:' ), 'WP Codebox must apply the sandbox patch to the host workspace through its bounded patch contract.' ); +$assert( str_contains( $producer_execute, 'mode: "readwrite", sourceMode: "repo-backed", seed: { type: "directory", source: runnerWorkspaceSeedSnapshot.source' ), 'WP Codebox must seed a sandbox-local copy-on-write workspace from the external target-repository snapshot.' ); +$assert( str_contains( $producer_execute, 'task_input: {' ) && str_contains( $producer_execute, 'workspaces: runnerWorkspaceSeedSnapshot ?' ), 'WP Codebox must hand runner workspaces through canonical task_input.workspaces.' ); +$assert( str_contains( $producer_execute, 'createRunnerWorkspaceSeedSnapshot(workspace)' ) && str_contains( $producer_execute, 'seed: { type: "directory", source: runnerWorkspaceSeedSnapshot.source' ), 'WP Codebox must seed runner workspaces from an external snapshot.' ); +$assert( str_contains( $producer_execute, 'runner_workspace_seed: runnerWorkspaceSeedSnapshot.provenance' ) && str_contains( $producer_execute, 'RUNNER_WORKSPACE_SEED_EXCLUDES' ), 'WP Codebox must retain seed provenance while applying the published exclusions.' ); +$assert( str_contains( $producer_execute, 'applyRunnerWorkspacePatch({ artifactRoot: artifactsPath, artifactRefs: refs, workspaceRoot: workspace, writablePaths })' ), 'WP Codebox must apply the sandbox patch to the host workspace through its bounded patch contract.' ); +$assert( str_contains( $producer_execute, '.filter((ref) => ref.kind === "codebox-patch" || ref.kind === "codebox-changed-files")' ), 'WP Codebox must treat canonical patch and changed-file references as actionable workspace evidence.' ); $assert( str_contains( $producer_execute, 'verifyRunnerWorkspaceIntegrity(workspaceApply.integrity)' ) && str_contains( $producer_execute, 'publishRunnerWorkspace' ), 'WP Codebox must verify host-applied changes before publication.' ); +$assert( str_contains( $producer_execute, 'runtime_result: redact(runtimeRecord)' ) && str_contains( $producer_execute, '...(downstreamFailure ? { failure:' ), 'WP Codebox must retain normalized runtime evidence when downstream execution fails.' ); $assert( str_contains( $producer_upload, 'function runtimeProvenance(request)' ) && str_contains( $producer_upload, 'runtime-provenance.json' ), 'WP Codebox uploads must retain runtime provenance without prepared source content.' ); +$assert( str_contains( $producer_upload, 'function compactNativeInput(text)' ) && str_contains( $producer_upload, 'Temporary runner workspace seed paths must never be persisted in artifact uploads.' ), 'WP Codebox uploads must preserve seed provenance without exposing secret-filtered snapshot paths.' ); $assert( (string) $upload_regression_run === ( $producer_upload_regression['run_id'] ?? null ), 'WP Codebox upload regression fixture must match the recorded run.' ); $assert( (string) $diagnostic_regression_run === ( $producer_diagnostic_regression['run_id'] ?? null ), 'WP Codebox diagnostic regression fixture must match the recorded run.' ); $diagnostic = $producer_diagnostic_regression['result']['diagnostics'][0] ?? null; @@ -253,7 +263,7 @@ $assert( in_array( '.codebox/agent-task-request.json', $producer_upload_regression['observed']['uploaded'] ?? array(), true ), 'WP Codebox upload regression fixture must retain the controlled request upload.' ); $assert( ! array_intersect( array( 'MODEL_PROVIDER_SECRET_1', 'MODEL_PROVIDER_SECRET_2', 'MODEL_PROVIDER_SECRET_3', 'MODEL_PROVIDER_SECRET_4', 'MODEL_PROVIDER_SECRET_5' ), array_keys( $caller_secrets ) ), 'Docs Agent must forward only the OPENAI_API_KEY provider secret name.' ); -$assert( str_contains( $workflow, 'output_projections="$(jq -cn --arg path \'metadata.runner_workspace_publication.url\' --argjson required "$success_requires_pr" \'{docs_agent_publication:{path:$path,required:$required}}\')"' ), 'Docs Agent must define the v0.12.14 publication projection descriptor.' ); +$assert( str_contains( $workflow, 'output_projections="$(jq -cn --arg path \'metadata.runner_workspace_publication.url\' --argjson required "$success_requires_pr" \'{docs_agent_publication:{path:$path,required:$required}}\')"' ), 'Docs Agent must define the v0.12.16 publication projection descriptor.' ); $docs_projections = array( 'docs_agent_publication' => array( 'path' => 'metadata.runner_workspace_publication.url', @@ -263,7 +273,7 @@ $publication_descriptor = $docs_projections['docs_agent_publication'] ?? null; $assert( is_array( $publication_descriptor ), 'Docs Agent must define the docs_agent_publication projection descriptor.' ); $publication_path = $publication_descriptor['path'] ?? null; -$assert( 'metadata.runner_workspace_publication.url' === $publication_path, 'Docs Agent publication projection must use the v0.12.14 runner workspace publication URL path.' ); +$assert( 'metadata.runner_workspace_publication.url' === $publication_path, 'Docs Agent publication projection must use the v0.12.16 runner workspace publication URL path.' ); $producer_request_fixture = $read_json( rtrim( $wp_codebox_dir, '/' ) . '/contracts/agent-task-workflow-request.fixture.json' ); $producer_projection_paths = array_values( $producer_request_fixture['outputs']['projections'] ?? array() ); diff --git a/tests/wp-codebox-release.fixture.json b/tests/wp-codebox-release.fixture.json index 4e1a6bf..bd0011e 100644 --- a/tests/wp-codebox-release.fixture.json +++ b/tests/wp-codebox-release.fixture.json @@ -1,7 +1,7 @@ { - "tag": "v0.12.14", - "package_version": "0.12.14", - "run": "29311239264", + "tag": "v0.12.16", + "package_version": "0.12.16", + "run": "29342892920", "diagnostic_regression_run": "29307978522", "upload_regression_run": "29306539573", "successful_noop_optional_artifacts": true, @@ -17,6 +17,10 @@ "sandbox_local_copy_on_write_workspace_tools": true, "host_patch_apply_verification_publication": true, "provenance_only_uploads": true, + "canonical_task_input_workspace_handoff": true, + "external_secret_filtered_seed_snapshot": true, + "actionable_patch_normalization": true, + "failure_evidence_preserved": true, "native_result_path": ".codebox/native-agent-task-result.json", "workflow_result_path": ".codebox/agent-task-workflow-result.json" }