fix(discover): more representative goal set, drop the no-plan card - #76
Closed
enricopiovesan wants to merge 1 commit into
Closed
fix(discover): more representative goal set, drop the no-plan card#76enricopiovesan wants to merge 1 commit into
enricopiovesan wants to merge 1 commit into
Conversation
Feedback: the examples weren't representative and the "no structural path" card read as broken. Replace the three goals with ones that all produce a real successful run: - "Score how uncertain a reporting period is" — the summary.aggregate -> uncertainty.score chain (the only pure_read multi-node chain that exists in the registry today; period.finalize can't be forced into it since summary's inputs are already satisfiable from the facts, so the blurb no longer over-claims three). - "Price a quote" — core.calculate-price@1.2.0. - "Check a card number" — validation.validate-luhn@1.2.0 (tangible, executes in-browser fine despite a local-only preferred target). The no-plan renderNoPlan path stays as defensive handling if a live goal ever returns zero candidates. E2E: the no-plan spec is replaced by a validate-luhn plan+execute spec. npm test 5/5 (+1 skip); CHECK_REGISTRY green; build clean; test:e2e 2/2; all three goals browser-verified to terminal: succeeded. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
enricopiovesan
added a commit
that referenced
this pull request
Sep 10, 2026
…o-plan card (#77) Feedback: the examples weren't representative and the no-plan card read as broken. New three-goal set, all real: - "Price a quote" — core.calculate-price@1.2.0 (goal 1, auto-plans on load). - "Review a document for approval" — doc-approval.analyze -> doc-approval.recommend, a named-reference-app 2-capability governed chain (document text -> extracted type/parties/amounts/confidence -> approve-or-route recommendation + rationale). Verified: browserLocalPlan chains analyze -> recommend from a {document} fact. EXECUTES once doc-approval.analyze@1.4.0 / recommend@1.4.0 land on the live catalog with a pure_read risk class (traverse-framework/registry#424, #425); until then this card plans and then fails closed on the authorization check. - "Check a card number" — validation.validate-luhn@1.2.0. Dropped: the abstract uncertainty.score chain and the no-plan card. renderNoPlan stays as defensive handling for a live goal that returns zero candidates. Supersedes the still-open #76 (same intent, better multi-cap example). E2E updated: goal-1 (price) + luhn plan+execute; doc-approval spec added when the registry PRs merge. npm test 5/5 (+1 skip), test:e2e 2/2, build clean. Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
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.
Feedback on #75: the three example goals weren't representative, and the "no structural path" card read as broken.
Change
summary.aggregate → uncertainty.score(2-node chain; the blurb no longer claims 3, sinceperiod.finalizecan't be forced into it)core.calculate-price@1.2.0validation.validate-luhn@1.2.0, tangible, executes fineAll three now produce a real successful run. The
renderNoPlanpath stays as defensive handling if a live goal ever returns zero candidates.Note on chain depth
I scanned all 117 structurally-pure capabilities: the deepest real composable chains in the registry today are 3 nodes (
period → summary → uncertainty,traverse-starter.process → summarize → visual.parameter-map), and only the first ispure_read-classified. Deeper/richer multi-capability examples need Traverse to publish capabilities that compose more deeply — tracked separately. Designing a good multi-capability showcase workflow is the next conversation.Verification
npm test5/5 (+1 networked skip) ·CHECK_REGISTRYgreen · build clean ·test:e2e2/2 (chain goal + validate-luhn) · all three goals browser-verified toterminal: succeeded.🤖 Generated with Claude Code