feat(onboarding): context-seed pipeline (Stage 3) - #442
Merged
Conversation
#436) - Allowlist-driven file scanner (data-driven roots + filenames) - Secret redaction at read time (expanded SECRET_PATTERNS) - Size-capped reads (50KB default, truncated flag) - Fact extractor: profile identity + memory cards from markdown/JSON configs - writeSeeds: group-selectable materialization via appendOnboardingEvent - 27 unit tests covering AC1-AC11 - WIP: score-stage wiring and integration test deferred
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (4)
📝 WalkthroughWalkthroughThe change adds an opt-in ChangesContext-seed onboarding
Estimated code review effort: 3 (Moderate) | ~25 minutes Possibly related issues
Possibly related PRs
Suggested reviewers: Sequence Diagram(s)sequenceDiagram
participant User
participant Overture
participant ContextSeed
participant OnboardingEvents
User->>Overture: accept or decline context scanning
alt accepted
Overture->>ContextSeed: scan allowlisted files
ContextSeed-->>Overture: redacted grouped preview
User->>Overture: select seed groups
Overture->>ContextSeed: write selected seeds
ContextSeed->>OnboardingEvents: append onboarding events
else declined
Overture->>Overture: skip file reads
end
Overture->>OnboardingEvents: record onboarding completion
✨ Finishing Touches 💡 1🛠️ Fix failing CI checks 💡
📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
- Add context_seed stage to SCORE.md frontmatter (optional, with opt-in question) - Add Stage 3 body instructions: opt-in, scan, preview, confirm, constraints - Regenerate golden parity files - Completion marker moves after Stage 3 (Stages 4-8 in subsequent slices)
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.
Summary
Implements #436 — the context-seed pipeline that scans allowlisted AI-tool configs, redacts secrets, extracts profile facts and memory cards, and writes them through the existing onboarding event pipeline.
What's included
src/context_seed.ts— pure Node module (no VS Code deps):SCAN_ALLOWLIST: data-driven config of scan roots + filenamesresolveAllowlist(): returns only existing files from the allowlistreadAndRedact(): size-capped read with secret redaction at read timeredactSecrets(): expanded SECRET_PATTERNS (sk- keys, AWS, Bearer, PEM, generic key=value)extractFacts(): conservative fact extraction from markdown/JSON configs → profile + memory cardswriteSeeds(): group-selectable materialization viaappendOnboardingEvent()Acceptance Criteria coverage
Status: WIP (draft)
The core logic layer is complete and tested (27 tests). Remaining for full closure:
appendOnboardingEvent+ distiller triggerCloses #436
Summary by CodeRabbit
New Features
Bug Fixes