Repository navigation
Add Claude Agent SDK samples - #403
Merged
Merged
Conversation
patbeqo
force-pushed
the
claude-agent-sdk-samples
branch
from
October 27, 2026 21:13
2cce724 to
b0c0239
Compare
patbeqo
force-pushed
the
claude-agent-sdk-samples
branch
from
October 29, 2026 00:24
b0c0239 to
b5492bf
Compare
patbeqo
force-pushed
the
claude-agent-sdk-samples
branch
from
October 29, 2026 00:55
b5492bf to
7a09333
Compare
Each sample now finishes its turn after its Worker stops mid-turn: it resumes the session at the turn's prompt with resume_session_at and sends Claude Code's own continue message, so a pending tool approval is asked again. - Capture the prompt's UUID with replay-user-messages, as the Claude Agent SDK docs do, instead of CLAUDE_CODE_RESUME_INTERRUPTED_TURN. - Drop the custom transport sample's guard, process wrapper and find_saved_turn Activity. - Run each Worker with worker.run(), like the other AI integration samples. - Describe Worker restarts once, in the samples README. - Pin the plugin to the commit that supports this.
patbeqo
marked this pull request as ready for review
October 30, 2026 21:42
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
brianstrauch
approved these changes
Oct 30, 2026
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 83e9e5dbe4
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
patbeqo
enabled auto-merge (squash)
October 30, 2026 22:14
patbeqo
disabled auto-merge
October 31, 2026 21:28
tconley1428
approved these changes
Nov 2, 2026
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.
Adds
claude_agent_sdk_plugin/, samples for the Claude Agent SDK integration. Each Workflow is plain Claude Agent SDK code with aTemporalTransport, and every sample runs offline against a scripted API, so no key is needed. They usetemporalio-claude-agent-sdkfrom PyPI.agent_chattools@toolcomputed in the Workflow and one that runs an Activity.streaminghuman_in_the_loopcan_use_toolwaits durably on an Update: approve, deny or cancel.structured_outputfork_sessionmulti_agentplugin_with_custom_transportConnector.open_telemetryTesting
ruff,mypyand the 24 offline tests pass. Every sample ran against the real model. Every sample's Worker was also stopped mid-turn and restarted, and each resumed with the correct result.