Docs/simpleagents builder hitl evals - #66
Merged
Merged
Conversation
…lippy Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
…native results Co-authored-by: Cursor <cursoragent@cursor.com>
…and typed output Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Ensures human_input form nodes always expose a concrete JSON object on the
wire so TypedDict clients see `{ }` instead of a missing key.
Co-authored-by: Cursor <cursoragent@cursor.com>
Restores the pre-rename wire type name for backward compatibility and keeps Client stub comments aligned with WorkflowRunOutputWire. Co-authored-by: Cursor <cursoragent@cursor.com>
…e review Refactors the spec-hitl orchestrator for clearer terminal UX, carries messages across HITL resumes, and extends the invoice approve/reject workflow with LLM follow-ups plus a rejection-reason text pause. Co-authored-by: Cursor <cursoragent@cursor.com>
Adds feature bullets plus simpleagents-builder checklist and pattern notes for human_input loops, eval datasets, and handler signatures. Co-authored-by: Cursor <cursoragent@cursor.com>
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (8)
📒 Files selected for processing (85)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
…stem_prompt Replace config.prompt and append_prompt_as_user with explicit user/system prompts, validate messages_path vs user_input_prompt, and expose both in resolved_llm_input telemetry. Co-authored-by: Cursor <cursoragent@cursor.com>
Match workflow YAML semantics: optional node_system_prompt, append user prompt into message history when using input.messages path. Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Align the steps-based Wasm runner with llm_call user_input_prompt and optional node_system_prompt so YAML fixtures validate and complete(). Co-authored-by: Cursor <cursoragent@cursor.com>
Criterion runtime benchmarks still embedded legacy prompt keys; deserialization failed after strict llm_call config migration. Co-authored-by: Cursor <cursoragent@cursor.com>
![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: dd01d3a826
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".
Comment on lines
+93
to
+98
| if let Some(user_prompt) = user_input_prompt { | ||
| assembled.push(Message::user(user_prompt)); | ||
| } else { | ||
| return Err(format!( | ||
| "llm_call '{}' requires user_input_prompt when messages_path is not provided", | ||
| request.node_id |
There was a problem hiding this comment.
This branch hard-fails whenever messages_path is unset and user_input_prompt is empty, even if node_system_prompt is provided. That makes the new node_system_prompt field unusable as a standalone input source, so workflows that intentionally send only a system instruction now fail with requires user_input_prompt instead of executing. If system-only calls are meant to be supported, this check should accept node_system_prompt as sufficient input.
Useful? React with 👍 / 👎.
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
1 participant
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.
No description provided.