feat: integrate optional Herdr workflow with user-owned routing - #5
Merged
Conversation
Uh oh!
There was an error while loading. Please reload this page.
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 freeto 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Herdr collaboration currently depends on instance-specific instructions. This adds an optional repository-local workflow and an editable
docs/agent-routing.mdTODO template so users choose the agent, model, thinking, approval policy and fallback for each work category. No model is prescribed; separate executor and evaluator instances may use the same model.The workflow covers task-linked handoffs, same-tab panes, isolated writer worktrees, bounded waits, recovery and evidence collection. Unresolved required routing stops that handoff, explicit session choices are reused, and Herdr lifecycle states never imply task acceptance. Initialization installs the skill, scenario rubric and Claude compatibility link while preserving the existing refusal to overwrite customized files.
Validation: all 84 tests pass (root 31, task-board 11, task-plan 17, plan-go 25), plus context, publication and whitespace checks. An independent Codex reviewer repeated the checks and evaluated six fixed scenarios. Real Herdr 0.8.0 split/start/prompt/wait/read mechanics were observed during this task; scenario decisions are bounded text evaluations, not live fault injection. Local pinned secret scanning was unavailable (installed 8.30.0 versus required 8.24.2); CI runs the pinned scanner.
This is an optional skill and Markdown policy, with no runtime service, scheduler, routing parser or automatic grader.