chore(deps): update LangChain Deep Agents Code to 0.1.55

[prekshivyas]

Summary

Updates LangChain Deep Agents Code from 0.1.34 to 0.1.55 using the sealed NemoPin migration evidence. This PR remains draft for human review.

Related Issue

No issue closure is claimed by this draft.

Changes

• Applies only paths authorized by sha256:296dd3487f41b6db94cf6cba42daf8e08bc1f9bb864ecc5f613f60c48f7bfe7a.
• Migrates the exact base 5bb69ed66947fbd2fab6133748866567eb520692 across 21 adjacent release ranges.
• Changed paths: agents/langchain-deepagents-code/Dockerfile, agents/langchain-deepagents-code/Dockerfile.base, agents/langchain-deepagents-code/dcode-wrapper.sh, agents/langchain-deepagents-code/dependency-review.md, agents/langchain-deepagents-code/manifest.yaml, agents/langchain-deepagents-code/patch-managed-deepagents-code.py, agents/langchain-deepagents-code/profile-plugin/pyproject.toml, agents/langchain-deepagents-code/profile-plugin/src/nemoclaw_deepagents_profile/__init__.py, agents/langchain-deepagents-code/progressive_tool_disclosure.py, agents/langchain-deepagents-code/requirements.in, agents/langchain-deepagents-code/requirements.lock, agents/langchain-deepagents-code/start.sh, agents/langchain-deepagents-code/validate-nemotron-ultra-profile.py, agents/langchain-deepagents-code/validate-observability.py, agents/langchain-deepagents-code/validate-progressive-tool-disclosure.py, docs/deployment/set-up-mcp-bridge.mdx, docs/get-started/quickstart-langchain-deepagents-code.mdx, src/lib/actions/sandbox/rebuild-flow-helpers.test.ts, src/lib/agent/base-image.test.ts, src/lib/agent/deep-agents-code-base-image.test.ts, src/lib/agent/onboard-terminal-fixtures.test.ts, src/lib/agent/onboard-terminal-fixtures.ts, src/lib/agent/onboard-terminal.test.ts, src/lib/onboard.ts, src/lib/onboard/created-sandbox-finalization.test.ts, src/lib/onboard/dcode-selection-drift.test.ts, src/lib/onboard/dcode-selection-drift.ts, src/lib/onboard/machine/handlers/sandbox-checkpoint-crash-recovery.test.ts, src/lib/onboard/machine/handlers/sandbox.ts, src/lib/onboard/sandbox-lifecycle.test.ts, src/lib/onboard/sandbox-lifecycle.ts, src/lib/sandbox-base-image-agent-resolution.test.ts, src/lib/sandbox-base-image-release-resolution.test.ts, src/lib/sandbox-base-image/resolution-key.test.ts, test/Dockerfile.dcode-profile-missing-dependencies, test/cli/connect-terminal-agent.test.ts, test/deepagents-code-tui-startup-check.test.ts, test/e2e/e2e-cloud-experimental/checks/03-deepagents-code-nemotron-ultra-profile.sh, test/e2e/e2e-cloud-experimental/checks/04-deepagents-code-fresh-reonboard.sh, test/e2e/e2e-cloud-experimental/checks/10-deepagents-code-tui-startup.sh, test/e2e/e2e-cloud-experimental/checks/12-deepagents-code-thread-auto-approval.sh, test/e2e/lib/select-authorized-chat-model.mts, test/e2e/live/mcp-bridge-servers.ts, test/e2e/support/authorized-chat-model-selection.test.ts, test/e2e/support/platform-parity-cloud-experimental.test.ts, test/fixtures/deepagents-progressive-disclosure-harness.py, test/fixtures/langchain-deepagents-code/server.py, test/helpers/langchain-deepagents-code-patch-fixture.ts, test/issue-5667-hosted-inference-model-namespace.test.ts, test/langchain-deepagents-code-direct-module-patch.test.ts, test/langchain-deepagents-code-image.test.ts, test/langchain-deepagents-code-nemotron-profile-plugin.test.ts, test/langchain-deepagents-code-progressive-tool-disclosure.test.ts, test/mcp-bridge-servers.test.ts, test/onboard-mcp-observability-redirect.test.ts, test/onboard-prepared-build-context.test.ts, test/onboard-terminal-dashboard.test.ts

Release ranges

Range	Commits	State	Concerns
0.1.34 → 0.1.35	bd9bafaad3f5 → 09daab5772ff	published	1
0.1.35 → 0.1.36	09daab5772ff → 2f56309d821d	published	1
0.1.36 → 0.1.37	2f56309d821d → def6369aed1a	published	2
0.1.37 → 0.1.38	def6369aed1a → 4338671aa1d9	published	4
0.1.38 → 0.1.39	4338671aa1d9 → 8eb909a59b82	published	1
0.1.39 → 0.1.40	8eb909a59b82 → 019489edb9c0	published	6
0.1.40 → 0.1.41	019489edb9c0 → d46a2cb033b8	published	4
0.1.41 → 0.1.42	d46a2cb033b8 → 18679a1a88a3	published	3
0.1.42 → 0.1.43	18679a1a88a3 → e14e0adcbe78	published	2
0.1.43 → 0.1.44	e14e0adcbe78 → 2b9cd08f0492	published	5
0.1.44 → 0.1.45	2b9cd08f0492 → 7794b61a6e76	published	4
0.1.45 → 0.1.46	7794b61a6e76 → efa86c51fedd	published	1
0.1.46 → 0.1.47	efa86c51fedd → 8aa29ddc2833	published	3
0.1.47 → 0.1.48	8aa29ddc2833 → 803b8329db7d	published	3
0.1.48 → 0.1.49	803b8329db7d → 44910bc2ef3f	published	0
0.1.49 → 0.1.50	44910bc2ef3f → 63adb9645687	published	2
0.1.50 → 0.1.51	63adb9645687 → d2b663fca277	published	0
0.1.51 → 0.1.52	d2b663fca277 → b428644d31dd	published	3
0.1.52 → 0.1.53	b428644d31dd → 0bd15dc0e1c5	published	2
0.1.53 → 0.1.54	0bd15dc0e1c5 → 81258067f4c7	published	0
0.1.54 → 0.1.55	81258067f4c7 → 80fe3d3cbcd2	published	9

Concern dispositions

Concern	Surface	Planned disposition	Failure prevented	Remaining gate
langchain-deep-agents-code-0.1.34..0.1.35-lifecycle-state-1	lifecycle state	test	0.1.55 reports lifecycle state: ### Features - Added a /context usage report for inspecting context consumption ([#5407](langchain-ai/deepagents#5407...	none
langchain-deep-agents-code-0.1.35..0.1.36-lifecycle-state-1	lifecycle state	test	0.1.54 reports lifecycle state: ### Features - Added Meta muse-spark-1.2 to the model switcher (#5389). - Improved di...	none
langchain-deep-agents-code-0.1.36..0.1.37-lifecycle-state-1	lifecycle state	test	0.1.53 reports lifecycle state: ### Features - Added pricing coverage with Baseten built-in overrides and local fallback overrides when genai-prices is missing data ([#5312](h...	none
langchain-deep-agents-code-0.1.36..0.1.37-runtime-topology-2	runtime topology	test	0.1.53 reports runtime topology: ### Features - Added pricing coverage with Baseten built-in overrides and local fallback overrides when genai-prices is missing data ([#5312](...	none
langchain-deep-agents-code-0.1.37..0.1.38-compatibility-change-1	compatibility change	test	0.1.52 reports compatibility change: ### Features - Hooks v2 is now generally available, with support for loading hooks from installed plugins. ([#5307](https://github.com/langc...	none
langchain-deep-agents-code-0.1.37..0.1.38-configuration-2	configuration	test	0.1.52 reports configuration: ### Features - Hooks v2 is now generally available, with support for loading hooks from installed plugins. ([#5307](https://github.com/langchain-ai...	none
langchain-deep-agents-code-0.1.37..0.1.38-execution-control-3	execution control	guard	0.1.52 reports execution control: ### Features - Hooks v2 is now generally available, with support for loading hooks from installed plugins. ([#5307](https://github.com/langchai...	none
langchain-deep-agents-code-0.1.37..0.1.38-lifecycle-state-4	lifecycle state	test	0.1.52 reports lifecycle state: ### Features - Hooks v2 is now generally available, with support for loading hooks from installed plugins. ([#5307](https://github.com/langchain-...	none
langchain-deep-agents-code-0.1.38..0.1.39-configuration-1	configuration	test	0.1.51 reports configuration: ### Features - The status bar and usage view now show the running session cost. (#5036) -...	none
langchain-deep-agents-code-0.1.39..0.1.40-compatibility-change-1	compatibility change	test	0.1.50 reports compatibility change: ### Highlights - Added project hooks workspace trust and expanded Hooks v2 support with client and server lifecycle events plus runtime feed...	none
langchain-deep-agents-code-0.1.39..0.1.40-execution-control-2	execution control	guard	0.1.50 reports execution control: ### Highlights - Added project hooks workspace trust and expanded Hooks v2 support with client and server lifecycle events plus runtime feedbac...	none
langchain-deep-agents-code-0.1.39..0.1.40-lifecycle-state-3	lifecycle state	test	0.1.50 reports lifecycle state: ### Highlights - Added project hooks workspace trust and expanded Hooks v2 support with client and server lifecycle events plus runtime feedback ...	none
langchain-deep-agents-code-0.1.39..0.1.40-packaging-artifact-4	packaging artifact	test	0.1.50 reports packaging artifact: ### Highlights - Added project hooks workspace trust and expanded Hooks v2 support with client and server lifecycle events plus runtime feedba...	none
langchain-deep-agents-code-0.1.39..0.1.40-runtime-topology-5	runtime topology	test	0.1.50 reports runtime topology: ### Highlights - Added project hooks workspace trust and expanded Hooks v2 support with client and server lifecycle events plus runtime feedback...	none
langchain-deep-agents-code-0.1.39..0.1.40-security-identity-6	security identity	guard	0.1.50 reports security identity: ### Highlights - Added project hooks workspace trust and expanded Hooks v2 support with client and server lifecycle events plus runtime feedbac...	none
langchain-deep-agents-code-0.1.40..0.1.41-compatibility-change-1	compatibility change	test	0.1.49 reports compatibility change: ### Features - Added recognition for LangSmith Gateway credentials. (#5042) - Adde...	none
langchain-deep-agents-code-0.1.40..0.1.41-execution-control-2	execution control	guard	0.1.49 reports execution control: ### Features - Added recognition for LangSmith Gateway credentials. (#5042) - Added s...	none
langchain-deep-agents-code-0.1.40..0.1.41-lifecycle-state-3	lifecycle state	test	0.1.49 reports lifecycle state: ### Features - Added recognition for LangSmith Gateway credentials. (#5042) - Added sla...	none
langchain-deep-agents-code-0.1.40..0.1.41-runtime-topology-4	runtime topology	test	0.1.49 reports runtime topology: ### Features - Added recognition for LangSmith Gateway credentials. (#5042) - Added sl...	none
langchain-deep-agents-code-0.1.41..0.1.42-compatibility-change-1	compatibility change	test	0.1.48 reports compatibility change: ### Features - Added Fireworks kimi-k3, GLM-5.2-Fast, and Kimi-K3 to model selection and recommended models. ([#5082](https://github.com/l...	none
langchain-deep-agents-code-0.1.41..0.1.42-execution-control-2	execution control	guard	0.1.48 reports execution control: ### Features - Added Fireworks kimi-k3, GLM-5.2-Fast, and Kimi-K3 to model selection and recommended models. ([#5082](https://github.com/lang...	none
langchain-deep-agents-code-0.1.41..0.1.42-lifecycle-state-3	lifecycle state	test	0.1.48 reports lifecycle state: ### Features - Added Fireworks kimi-k3, GLM-5.2-Fast, and Kimi-K3 to model selection and recommended models. ([#5082](https://github.com/langch...	none
langchain-deep-agents-code-0.1.42..0.1.43-compatibility-change-1	compatibility change	test	0.1.47 reports compatibility change: ### Features - Added yolo mode to the Shift+Tab approval cycle (#5035). - Show...	none
langchain-deep-agents-code-0.1.42..0.1.43-execution-control-2	execution control	guard	0.1.47 reports execution control: ### Features - Added yolo mode to the Shift+Tab approval cycle (#5035). - Show th...	none
langchain-deep-agents-code-0.1.43..0.1.44-compatibility-change-1	compatibility change	test	0.1.46 reports compatibility change: ### Highlights - Auto mode is now generally available. #4957 - Added configurable ...	none
langchain-deep-agents-code-0.1.43..0.1.44-configuration-2	configuration	test	0.1.46 reports configuration: ### Highlights - Auto mode is now generally available. #4957 - Added configurable Auto go...	none
langchain-deep-agents-code-0.1.43..0.1.44-execution-control-3	execution control	guard	0.1.46 reports execution control: ### Highlights - Auto mode is now generally available. #4957 - Added configurable Aut...	none
langchain-deep-agents-code-0.1.43..0.1.44-protocol-schema-4	protocol schema	test	0.1.46 reports protocol schema: ### Highlights - Auto mode is now generally available. #4957 - Added configurable Auto ...	none
langchain-deep-agents-code-0.1.43..0.1.44-security-identity-5	security identity	guard	0.1.46 reports security identity: ### Highlights - Auto mode is now generally available. #4957 - Added configurable Aut...	none
langchain-deep-agents-code-0.1.44..0.1.45-compatibility-change-1	compatibility change	test	0.1.45 reports compatibility change: ### Features - Added the Hooks v2 execution engine and typed hooks data models ([#4880](langchain-ai/deepagents#48...	none
langchain-deep-agents-code-0.1.44..0.1.45-execution-control-2	execution control	guard	0.1.45 reports execution control: ### Features - Added the Hooks v2 execution engine and typed hooks data models (#4880...	none
langchain-deep-agents-code-0.1.44..0.1.45-lifecycle-state-3	lifecycle state	test	0.1.45 reports lifecycle state: ### Features - Added the Hooks v2 execution engine and typed hooks data models (#4880, ...	none
langchain-deep-agents-code-0.1.44..0.1.45-packaging-artifact-4	packaging artifact	test	0.1.45 reports packaging artifact: ### Features - Added the Hooks v2 execution engine and typed hooks data models ([#4880](langchain-ai/deepagents#4880...	none
langchain-deep-agents-code-0.1.45..0.1.46-runtime-topology-1	runtime topology	test	0.1.44 reports runtime topology: ### Bug Fixes - Improved approval handling by hiding the Auto option when it isn't eligible and moving Auto mode path checks off the event loo...	none
langchain-deep-agents-code-0.1.46..0.1.47-compatibility-change-1	compatibility change	test	0.1.43 reports compatibility change: ### Features - Added classifier-backed Auto approval mode behind DEEPAGENTS_CODE_EXPERIMENTAL=1 ([#4804](https://github.com/langchain-ai/d...	none
langchain-deep-agents-code-0.1.46..0.1.47-execution-control-2	execution control	guard	0.1.43 reports execution control: ### Features - Added classifier-backed Auto approval mode behind DEEPAGENTS_CODE_EXPERIMENTAL=1 ([#4804](https://github.com/langchain-ai/deep...	none
langchain-deep-agents-code-0.1.46..0.1.47-lifecycle-state-3	lifecycle state	test	0.1.43 reports lifecycle state: ### Features - Added classifier-backed Auto approval mode behind DEEPAGENTS_CODE_EXPERIMENTAL=1 ([#4804](https://github.com/langchain-ai/deepag...	none
langchain-deep-agents-code-0.1.47..0.1.48-compatibility-change-1	compatibility change	test	0.1.42 reports compatibility change: ### Features - Plugins are now generally available. (#4797) - Added search to the ...	none
langchain-deep-agents-code-0.1.47..0.1.48-execution-control-2	execution control	guard	0.1.42 reports execution control: ### Features - Plugins are now generally available. (#4797) - Added search to the plu...	none
langchain-deep-agents-code-0.1.47..0.1.48-lifecycle-state-3	lifecycle state	test	0.1.42 reports lifecycle state: ### Features - Plugins are now generally available. (#4797) - Added search to the plugi...	none
langchain-deep-agents-code-0.1.49..0.1.50-compatibility-change-1	compatibility change	test	0.1.40 reports compatibility change: ### Features - Added plugin marketplace support (#4554). - Added an “always allow”...	none
langchain-deep-agents-code-0.1.49..0.1.50-execution-control-2	execution control	guard	0.1.40 reports execution control: ### Features - Added plugin marketplace support (#4554). - Added an “always allow” op...	none
langchain-deep-agents-code-0.1.51..0.1.52-compatibility-change-1	compatibility change	test	0.1.38 reports compatibility change: ### Features * Improve /goal criteria UX (#4694) ([06f46ff](https://github.com/l...	none
langchain-deep-agents-code-0.1.51..0.1.52-configuration-2	configuration	test	0.1.38 reports configuration: ### Features * Improve /goal criteria UX (#4694) ([06f46ff](https://github.com/langchai...	none
langchain-deep-agents-code-0.1.51..0.1.52-lifecycle-state-3	lifecycle state	test	0.1.38 reports lifecycle state: ### Features * Improve /goal criteria UX (#4694) ([06f46ff](https://github.com/langch...	none
langchain-deep-agents-code-0.1.52..0.1.53-configuration-1	configuration	test	0.1.37 reports configuration: ### Features * Add Meta model provider (#4650) ([70829c5](https://github.com/langchain-ai...	none
langchain-deep-agents-code-0.1.52..0.1.53-security-identity-2	security identity	guard	0.1.37 reports security identity: ### Features * Add Meta model provider (#4650) ([70829c5](https://github.com/langchai...	none
langchain-deep-agents-code-0.1.54..0.1.55-compatibility-change-1	compatibility change	test	0.1.35 reports compatibility change: ### Features * Restore interrupted prompt to input on ESC (#4544) ([fccf037](https...	none
langchain-deep-agents-code-0.1.54..0.1.55-configuration-2	configuration	test	0.1.35 reports configuration: ### Features * Restore interrupted prompt to input on ESC (#4544) ([fccf037](https://gith...	none
langchain-deep-agents-code-0.1.54..0.1.55-execution-control-3	execution control	guard	0.1.35 reports execution control: ### Features * Restore interrupted prompt to input on ESC (#4544) ([fccf037](https://...	none
langchain-deep-agents-code-0.1.54..0.1.55-lifecycle-state-4	lifecycle state	test	0.1.35 reports lifecycle state: ### Features * Restore interrupted prompt to input on ESC (#4544) ([fccf037](https://gi...	none
langchain-deep-agents-code-0.1.54..0.1.55-protocol-schema-5	protocol schema	test	0.1.35 reports protocol schema: ### Features * Restore interrupted prompt to input on ESC (#4544) ([fccf037](https://gi...	none
langchain-deep-agents-code-0.1.54..0.1.55-code-impact-configuration-1	mapped configuration	test	The exact-ref diff reports configuration changes in .pre-commit-config.yaml, libs/acp/deepagents_acp/server.py, libs/acp/tests/test_agent.py. Mapped NemoClaw examples: src/lib/a...	none
langchain-deep-agents-code-0.1.54..0.1.55-code-impact-contract-or-schema-2	mapped contract or schema	test	The exact-ref diff reports contract or schema changes in libs/acp/deepagents_acp/_version.py, libs/acp/deepagents_acp/server.py, libs/code/deepagents_code/_ask_user_types.py. Ma...	none
langchain-deep-agents-code-0.1.54..0.1.55-code-impact-security-3	mapped security	test	The exact-ref diff reports security changes in libs/code/deepagents_code/_cli_context.py, libs/code/deepagents_code/_env_vars.py, libs/code/deepagents_code/_repository_bounds.py...	none
langchain-deep-agents-code-0.1.54..0.1.55-code-impact-test-4	mapped test	test	The exact-ref diff reports test changes in libs/acp/tests/chat_model.py, libs/acp/tests/test_agent.py, libs/code/tests/integration_tests/benchmarks/test_local_context_benchmarks...	none

Immutable artifacts

Artifact	SHA-256
deepagents_code-0.1.55-py3-none-any.whl	3a0d3e332f132d0e…
deepagents_code-0.1.55.tar.gz	91c30b62cb96d5e8…

Validation receipt

Gate	Current result
targeted	Pending on this exact draft head
full-e2e	Pending on this exact draft head

Type of Change

• Code change (feature, bug fix, or refactor)
• Code change with doc updates
• Doc only (prose changes, no code sample modifications)
• Doc only (includes code sample changes)

Quality Gates

• Tests added or updated for changed behavior
• Existing tests cover changed behavior — justification:
• Tests not applicable — justification:
• Docs updated for user-facing behavior changes
• Docs not applicable — justification:
• Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging)
• Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification: exact-head review passed at chore(deps): update LangChain Deep Agents Code to 0.1.55 #8620 (review).
• Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue:

Documentation Writer Review

• Documentation writer subagent reviewed the completed changes
• Result: docs-updated
• Evidence: docs/deployment/set-up-mcp-bridge.mdx and docs/get-started/quickstart-langchain-deepagents-code.mdx accurately document the changed Deep Agents Code behavior and versions. The documented deepagents-code 0.1.55 and deepagents 0.7.5 versions match the manifest, inputs, lockfile, and profile plugin. npm run docs passed with 0 errors and two pre-existing Fern warnings.
• Agent: Codex Desktop

DGX Station Hardware Evidence

• Tested on DGX Station
• Tested commit:
• Station profile/scenario:
• Result:
• Supporting evidence:

Verification

• PR description includes a Signed-off-by: line and every commit appears as Verified in GitHub
• Normal pre-commit, commit-msg, and pre-push hooks passed, or npm run validate:pr passed after refreshing origin/main when hooks were skipped or unavailable
• Targeted behavior tests pass for the current change set, or tests are marked not applicable above — command/result or justification:
• Applicable broad gate passed — npm test for broad runtime/test-harness changes; npm run check for repo-wide validation/coverage changes — command/result:
• Quality Gates section completed with required justifications or waivers
• No secrets, API keys, or credentials committed
• npm run docs builds without warnings (doc changes only)
• Doc pages follow the style guide (doc changes only)
• New doc pages include SPDX header and frontmatter (new pages only)

---

Signed-off-by: Prekshi Vyas prekshiv@nvidia.com

[copy-pr-bot]

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 6c6f16c5-7e29-484d-af21-bbf87ec4d00a

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

PR Review Advisor — Informational

Advisor assessment: Informational / low confidence
Next action: No advisor follow-up needed.
Findings: 0 blockers · 0 warnings · 0 suggestions
Status: PR review advisor failed: PR review advisor SDK execution failed: session: terminology-review-analysis omitted required analysis; turn: terminology-review-analysis: terminology-review-analysis omitted required analysis

Model lanes

• GPT-5.6 Terra (primary): Failed
• Nemotron 3 Ultra (second opinion): Failed

Second-opinion terminology and E2E selections are advisory. Live E2E does not run automatically for pull requests.

E2E guidance

Advisory only. A maintainer can dispatch the default E2E suite for the commit under review.

Recommended E2E: managed-image-protected-runtime

Manual-only E2E: cloud-onboard, managed-image-multiarch-startup, security-posture, hermes-e2e, onboard-repair, onboard-resume, ubuntu-repo-cloud-langchain-deepagents-code, cloud-inference, full-e2e, openshell-gateway-upgrade
The manual PR workflow does not run these selectors for the commit under review. Run them from reviewed code on main.

Workflow run details

This automated review informs maintainers. Warnings and suggestions do not require a response. A maintainer decides whether to merge.

[prekshivyas]

Reviewed exact draft head a800a7f. This is my own PR, so GitHub does not permit an independent approval or request-changes review from this account.

The sealed migration record is unusually complete: it enumerates all 20 adjacent releases, pins the 0.1.54 wheel/sdist and resolved lock graph, records downstream patches and guards, updates the version selectors coherently, and links exact-head managed-image and Deep Agents E2E evidence including the six auto-approval checks. I did not find a new snapshot-specific security defect beyond the recorded migration controls.

This draft is not ready to leave draft state now. GitHub reports the branch as CONFLICTING/DIRTY against current main; required commit-lint, DCO, documentation-receipt, and maintainer-edit checks are cancelled, and both advisor lanes failed without producing a review. Resolve the current-base conflicts without weakening the migration guards, rerun the dependency concern audit and exact-head CI/E2E on the resulting head, refresh the documentation-writer receipt, complete the unchecked Quality Gates line, and obtain an independent maintainer review. The trailing quoted NemoPatch status block in the PR body should also be cleaned up before readiness.

Security review of this snapshot:

• Input validation: PASS — model-selection, profile, disclosure, and patch fixtures cover the changed upstream contracts.
• Authentication and authorization: PASS — auto-approval changes remain explicitly gated and exact-head E2E covers the six cases.
• Secrets and sensitive data: PASS — no credential material is added to runtime selectors, patches, docs, or evidence.
• Injection risks: PASS — dependency installation and patching remain hash/shape guarded rather than accepting runtime fragments.
• Data exposure and privacy: PASS — MCP/observability changes retain existing redaction and route boundaries.
• Cryptography: PASS — package and lock identities are recorded with immutable hashes.
• Dependencies and supply chain: WARNING — the snapshot evidence is strong, but it must be reconciled and re-audited after resolving current-main conflicts.
• System security: PASS for this snapshot — image patching, startup, approval, lifecycle, and protected-runtime tests cover the changed surfaces.
• Testing and verification: FAIL for readiness — the branch conflicts with current main, required checks are cancelled, automated advisors failed, and independent review is still absent.

Files reviewed: the complete 58-file dependency, image, patch, startup, onboarding/lifecycle, workflow, documentation, fixture, integration, and E2E snapshot diff plus its sealed release/concern record.

[prekshivyas]

Gate review of commit f473c25e9ca5806a97cae25b58c0a551f953cb42.

This is not an approval or a completed dependency-security acceptance. The PR is correctly draft, currently conflicts with the base branch, and has failed required checks. The CLI failure is the same existing src/lib/actions/sandbox/stop.test.ts timeout seen on unrelated commits, but both review-advisor lanes also failed and the exact migration still requires the stated human review of the sealed patch-walker evidence and 0.1.34-to-0.1.55 dependency behavior.

Security gate status: secrets PASS from the reviewed diff/metadata; input validation, authorization, error handling, and configuration require completion of the dependency migration review; dependencies BLOCKED; cryptography N/A; security tests BLOCKED; system security BLOCKED by conflict and red CI.

I cannot formally approve a PR authored by this GitHub account. Rebase/resolve the conflicts, refresh the migration evidence against current main, complete the dependency-sensitive review, and obtain a green latest-commit gate before taking this out of draft.

[prekshivyas]

Reviewed exact head 789b74f. No new blocking finding in the exact-head delta.

The staging QA failure was real: the recorded staging source carried Deep Agents Code 0.1.34 / SDK 0.7.0a6 while the PR profile requires 0.1.55 / 0.7.5. The latest fix preserves the recorded staging tree but overlays only the exact candidate-owned Dockerfile, lockfile, and required patch after regular-file/non-symlink shape checks; it also validates the candidate base build arguments. The workflow contract passes 19/19 and diff check passes.

Documentation review is exact and passes: docs/deployment/set-up-mcp-bridge.mdx and docs/get-started/quickstart-langchain-deepagents-code.mdx accurately describe the changed versions and behavior, and the docs build passes. I cannot approve this PR because it is my own and remains a draft; CI is still running.