feat(code): add Hooks v2 capability snapshots - #4916
Merged
Johannes du Plessis (johannes117) merged 4 commits intoJul 22, 2026
Merged
feat(code): add Hooks v2 capability snapshots#4916Johannes du Plessis (johannes117) merged 4 commits into
Johannes du Plessis (johannes117) merged 4 commits into
Conversation
Contributor
There was a problem hiding this comment.
The PR introduces a Hooks v2 loading module that includes project-scoped hook configs by default, which could allow a malicious repository to execute arbitrary commands via hook handlers — however, this new loader is not yet wired into the live app dispatch path, which still uses the legacy user-only loader.
Freeze validated hook configuration into deterministic session snapshots backed by one event capability registry.
Johannes du Plessis (johannes117)
force-pushed
the
johannes117/code/dcd-70-hooks-capabilities
branch
from
July 21, 2026 23:19
4d9b10f to
32e7e97
Compare
Alexander Olsen (aolsenjazz)
requested changes
Jul 22, 2026
Johannes du Plessis (johannes117)
requested a review
from Alexander Olsen (aolsenjazz)
July 22, 2026 20:03
Johannes du Plessis (johannes117)
enabled auto-merge (squash)
July 22, 2026 20:04
Alexander Olsen (aolsenjazz)
approved these changes
Jul 22, 2026
Alexander Olsen (aolsenjazz)
left a comment
Contributor
There was a problem hiding this comment.
remaining questiosn were answered in slack
| snapshot_id: str | ||
|
|
||
|
|
||
| def project_hooks_path(cwd: Path) -> Path: |
Contributor
There was a problem hiding this comment.
I guess another concern I have here is when running from I non-project root - wdyt? any concerns here?
| snapshot_id: str | ||
|
|
||
|
|
||
| def project_hooks_path(cwd: Path) -> Path: |
Contributor
There was a problem hiding this comment.
e.g. I often run dcode from ~/workspace
Johannes du Plessis (johannes117)
disabled auto-merge
July 22, 2026 20:06
Johannes du Plessis (johannes117)
enabled auto-merge (squash)
July 22, 2026 20:06
Johannes du Plessis (johannes117)
deleted the
johannes117/code/dcd-70-hooks-capabilities
branch
July 22, 2026 20:10
Johannes du Plessis (johannes117)
added a commit
that referenced
this pull request
Jul 23, 2026
Depends on #4916 Related DCD-70 Hooks v2 command handlers now execute with event-aware policies, bounded terminal output, sanitized environments, and complete process cleanup. --- This is 2/3 in the DCD-70 stack. - Applies plain-output, exit-code, continuation, permission, and deferred-field policies without discarding sibling diagnostics. - Validates terminal sequences and removes ambient secret and telemetry environment values. - Cleans up complete process groups on timeout or cancellation and maps native/MCP tool calls only from trustworthy metadata. - Keeps materialized filesystem paths outside domain and transport state. <details> <summary>Test plan</summary> - `uv run --group test pytest tests/unit_tests/hooks` — 95 passed at this stack layer - `make lint` </details> <!-- branch-stack-start --> ------------------------- - main - **fix(code): harden Hooks v2 command execution** 👈 - #4918 - #4971 <sup>[Stack](https://www.git-town.com/how-to/proposal-breadcrumb.html) generated by [Git Town](https://github.com/git-town/git-town)</sup> <!-- branch-stack-end -->
Mason Daugherty (mdrxy)
pushed a commit
that referenced
this pull request
Jul 24, 2026
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. The published GitHub release body is extracted from the merged `CHANGELOG.md` by `release.yml`, not from this PR description._ --- ## [0.1.46](deepagents-code==0.1.45...deepagents-code==0.1.46) (2026-07-24) ### Highlights - Auto mode is now generally available. [#4957](#4957) - Added configurable Auto goal-criteria acceptance. [#4940](#4940) - Improved Auto behavior by authorizing actions from active goal/rubric directives, avoiding redundant approval prompts, showing the enable notice only on first global enable, deduplicating classifier-unavailable transcript spam, logging underlying classifier failures, and reporting classifier timeout budgets. [#5017](#5017) [#4993](#4993) [#5012](#5012) [#5013](#5013) [#5011](#5011) [#5025](#5025) - Added Hooks v2 capability snapshots and session transcripts, and hardened Hooks v2 command execution. [#4916](#4916) [#4918](#4918) [#4917](#4917) - Raised the agent recursion limit to 2000 and made it configurable. [#4994](#4994) ### Improvements and fixes - Let the rubric grader inspect working-directory files, show rubric grader defaults, and improved `/rubric` help and empty-state messaging. [#4835](#4835) [#4966](#4966) [#5015](#5015) - Unified goal activation signaling. [#4980](#4980) - Made Version, Model, and CWD copyable in the Debug Console. [#4975](#4975) - Improved `config get` output when a key is missing. [#4976](#4976) - Aborted YOLO launch on `Ctrl+C`/`Ctrl+D` and made the YOLO warning friendlier for new users. [#4953](#4953) [#4950](#4950) - Updated LangSmith handling: secret redaction is disabled by default, `/trace` now flags empty env overrides that shadow the LangSmith key, and the default US endpoint is no longer treated as a custom target. [#4970](#4970) [#4996](#4996) [#5022](#5022) - Injected OpenAI `prompt_cache_key` for any OpenAI-provider endpoint. [#4995](#4995) - Improved tool and schema presentation: finished calls stay on the live tool-group line, first-party tool schemas now include field descriptions, and `web_search`/`fetch_url` tool descriptions were trimmed. [#4927](#4927) [#5019](#5019) [#5016](#5016) - Omitted `plugins/` and `conversation_history/` from the `/agent` picker. [#4991](#4991) - Made selector modal backdrop dimming consistent. [#4990](#4990) - Restored the `"Server log preserved at:"` notice on exit. [#4999](#4999) - Used the SDK pin as the effective editable version. [#4949](#4949) _End release notes preview._ --- > [!NOTE] > A **New Contributors** section is appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 2). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>
Marcelo5444
pushed a commit
to Marcelo5444/deepagents
that referenced
this pull request
Jul 30, 2026
Related DCD-70 Hooks v2 now validates and freezes configuration into deterministic session snapshots backed by one authoritative event capability registry. --- This is 1/3 in the DCD-70 stack. - Defines event ownership, matching, timeout, output, and aggregation capabilities. - Loads project and user configuration in stable precedence order with semantic-only legacy migration. - Computes canonical snapshot hashes and rejects unsupported matcher or handler combinations before execution. <details> <summary>Test plan</summary> - `uv run --group test pytest tests/unit_tests/hooks` — 81 passed at this stack layer - `make lint` </details> <!-- branch-stack-start --> ------------------------- - main - **johannes117/code/dcd-70-hooks-capabilities** 👈 - [johannes117/code/dcd-70-hooks-execution](langchain-ai#4917) - [johannes117/code/dcd-70-hooks-transcripts](langchain-ai#4918) <sup>[Stack](https://www.git-town.com/how-to/proposal-breadcrumb.html) generated by [Git Town](https://github.com/git-town/git-town)</sup> <!-- branch-stack-end -->
Marcelo5444
pushed a commit
to Marcelo5444/deepagents
that referenced
this pull request
Jul 30, 2026
Depends on langchain-ai#4916 Related DCD-70 Hooks v2 command handlers now execute with event-aware policies, bounded terminal output, sanitized environments, and complete process cleanup. --- This is 2/3 in the DCD-70 stack. - Applies plain-output, exit-code, continuation, permission, and deferred-field policies without discarding sibling diagnostics. - Validates terminal sequences and removes ambient secret and telemetry environment values. - Cleans up complete process groups on timeout or cancellation and maps native/MCP tool calls only from trustworthy metadata. - Keeps materialized filesystem paths outside domain and transport state. <details> <summary>Test plan</summary> - `uv run --group test pytest tests/unit_tests/hooks` — 95 passed at this stack layer - `make lint` </details> <!-- branch-stack-start --> ------------------------- - main - **fix(code): harden Hooks v2 command execution** 👈 - langchain-ai#4918 - langchain-ai#4971 <sup>[Stack](https://www.git-town.com/how-to/proposal-breadcrumb.html) generated by [Git Town](https://github.com/git-town/git-town)</sup> <!-- branch-stack-end -->
Marcelo5444
pushed a commit
to Marcelo5444/deepagents
that referenced
this pull request
Jul 30, 2026
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. The published GitHub release body is extracted from the merged `CHANGELOG.md` by `release.yml`, not from this PR description._ --- ## [0.1.46](langchain-ai/deepagents@deepagents-code==0.1.45...deepagents-code==0.1.46) (2026-07-24) ### Highlights - Auto mode is now generally available. [langchain-ai#4957](langchain-ai#4957) - Added configurable Auto goal-criteria acceptance. [langchain-ai#4940](langchain-ai#4940) - Improved Auto behavior by authorizing actions from active goal/rubric directives, avoiding redundant approval prompts, showing the enable notice only on first global enable, deduplicating classifier-unavailable transcript spam, logging underlying classifier failures, and reporting classifier timeout budgets. [langchain-ai#5017](langchain-ai#5017) [langchain-ai#4993](langchain-ai#4993) [langchain-ai#5012](langchain-ai#5012) [langchain-ai#5013](langchain-ai#5013) [langchain-ai#5011](langchain-ai#5011) [langchain-ai#5025](langchain-ai#5025) - Added Hooks v2 capability snapshots and session transcripts, and hardened Hooks v2 command execution. [langchain-ai#4916](langchain-ai#4916) [langchain-ai#4918](langchain-ai#4918) [langchain-ai#4917](langchain-ai#4917) - Raised the agent recursion limit to 2000 and made it configurable. [langchain-ai#4994](langchain-ai#4994) ### Improvements and fixes - Let the rubric grader inspect working-directory files, show rubric grader defaults, and improved `/rubric` help and empty-state messaging. [langchain-ai#4835](langchain-ai#4835) [langchain-ai#4966](langchain-ai#4966) [langchain-ai#5015](langchain-ai#5015) - Unified goal activation signaling. [langchain-ai#4980](langchain-ai#4980) - Made Version, Model, and CWD copyable in the Debug Console. [langchain-ai#4975](langchain-ai#4975) - Improved `config get` output when a key is missing. [langchain-ai#4976](langchain-ai#4976) - Aborted YOLO launch on `Ctrl+C`/`Ctrl+D` and made the YOLO warning friendlier for new users. [langchain-ai#4953](langchain-ai#4953) [langchain-ai#4950](langchain-ai#4950) - Updated LangSmith handling: secret redaction is disabled by default, `/trace` now flags empty env overrides that shadow the LangSmith key, and the default US endpoint is no longer treated as a custom target. [langchain-ai#4970](langchain-ai#4970) [langchain-ai#4996](langchain-ai#4996) [langchain-ai#5022](langchain-ai#5022) - Injected OpenAI `prompt_cache_key` for any OpenAI-provider endpoint. [langchain-ai#4995](langchain-ai#4995) - Improved tool and schema presentation: finished calls stay on the live tool-group line, first-party tool schemas now include field descriptions, and `web_search`/`fetch_url` tool descriptions were trimmed. [langchain-ai#4927](langchain-ai#4927) [langchain-ai#5019](langchain-ai#5019) [langchain-ai#5016](langchain-ai#5016) - Omitted `plugins/` and `conversation_history/` from the `/agent` picker. [langchain-ai#4991](langchain-ai#4991) - Made selector modal backdrop dimming consistent. [langchain-ai#4990](langchain-ai#4990) - Restored the `"Server log preserved at:"` notice on exit. [langchain-ai#4999](langchain-ai#4999) - Used the SDK pin as the effective editable version. [langchain-ai#4949](langchain-ai#4949) _End release notes preview._ --- > [!NOTE] > A **New Contributors** section is appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 2). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Related DCD-70
Hooks v2 now validates and freezes configuration into deterministic session snapshots backed by one authoritative event capability registry.
This is 1/3 in the DCD-70 stack.
Test plan
uv run --group test pytest tests/unit_tests/hooks— 81 passed at this stack layermake lintStack generated by Git Town