Repository navigation
docs(agents): say the agent prompts are frozen and edited in the wizard - #530
Closed
edwinyjlim wants to merge 1 commit into
Closed
edwinyjlim wants to merge 1 commit into
edwinyjlim wants to merge 1 commit into
Conversation
Co-Authored-By: Claude <noreply@anthropic.com>
12 of 13 tasks
🧙 Wizard CIRun the Wizard CI and test your changes against wizard-workbench example apps by replying with a GitHub comment using one of the following commands: Test all apps:
Test all apps in a directory:
Test an individual app:
Show more apps
Test against a wizard branch:
Add Results will be posted here when complete. |
This was referenced Nov 13, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replaced by #532, the same change on its own, based on
main.Summary
The note at the top of
context/agents/README.mdnow says the agent prompts are frozen: the wizard reads its own copy atsrc/programs/<id>/agent/, and a prompt is edited there. This copy stays published, unchanged, for wizard versions that fetch their prompts.Merge this when
wizard-agent-dagreaches 100%.Stack
The second half of the migration, behind
wizard-agent-dag-skills. The first half, behindwizard-agent-dag, is in context-mill 1.65.0 (#447) and wizard 2.94.0 (PostHog/wizard#1551 to PostHog/wizard#1554).variant.json.main. Adds files and tags only.integration-<step>.main, on its own. Documentation only. Merges whenwizard-agent-dagreaches 100%.wizard-agent-dag-skillson, a task reads the step skill from B, completed from the pack from A.main. Does nothing while the flag is off.A and B are one GitHub stack and merge together. They only add files, skills and tags, and no run reads them until the flag is on.
Rollout
wizard-agent-dag-skillsis a percentage flag, independent ofwizard-agent-dag. Turning it off returns every run to the skills it reads today, and a run pinned to a context-mill release reads those throughout.check:bundle-diff --additiveandcheck:repackaged-skillson the release buildpnpm verify:repackaged-skillsagainst the release, and a workbench run with the flag on compared with one with it off. The error tracking difference on Nuxt, described in PostHog/wizard#1559, is settledorchestrator_skillstag: run success, task failures, and anyorchestrator repackaged skill unavailableC merges on its own, when
wizard-agent-dagreaches 100%.Test plan
🤖 Generated with Claude Code