@pmelab/gtd 48.0.0 → 50.0.0

package/src/workflows/feature/severity-sorted-review.feature

@@ -0,0 +1,197 @@
+@inmem
+Feature: the final review lists what matters most first
+
+  Before the review rests, the judge rates every chunk the reviewer wrote — a
+  walkthrough chunk or a carried quality finding — on the same four questions
+  as a human's note (`build.review.ranking`): critical (security, or a one-way
+  door), should (a contract, or a new concept), could. The review lists them
+  in that order, security before one-way doors, each led by its tier and
+  reason. A chunk the judge cannot rate is critical, so it is shown first.
+
+  Background:
+    Given the shipped workflows, as gtd install scaffolds them
+    And an environment variable "GTD_QUALITYREVIEWS" set to "correctness"
+    And an environment variable "GTD_FLAGMODE" set to "false"
+    And a file "src/calc.ts" with:
+      """
+      export const add = (a: number, b: number) => a + b
+      """
+    And the working tree is committed as "feat: add calculator"
+    And a file "TODO.md" with:
+      """
+      # Add subtract
+
+      subtract(a, b) returns the difference.
+      """
+    And step "unwind" changes nothing
+    And step "start-gate.check" changes nothing
+    And step "design.triage" writes ".gtd/REQUIREMENTS.md" with:
+      """
+      # Requirements
+
+      ## Acceptance Criteria
+
+      - AC-1: subtract(a, b) returns a - b.
+      """
+    And step "design.gate.answer" changes nothing
+    And step "seam.naive" writes "src/calc.test.ts" with:
+      """
+      it("[AC-1] subtracts", () => {})
+      """
+    And step "seam.naive" writes "src/calc.ts" with:
+      """
+      export const add = (a: number, b: number) => a + b
+      export const subtract = (a: number, b: number) => a - b
+      """
+    And step "seam.check" changes nothing
+    And step "implement.applying" runs its script
+    And step "implement.health.check" changes nothing
+    And step "implement.closing" runs its script
+    And judge step "implement.coverage" answers:
+      """
+      [{"id":"AC-1","answer":"yes","p":0.9}]
+      """
+    And step "build.quality.correctness.reviewing" writes ".gtd/QUALITY.md" with:
+      """
+      # Quality
+
+      ## AC-1 ignores floating point
+
+      Should subtract round? The criterion does not say.
+      """
+    And judge step "build.quality.triage" answers:
+      """
+      [{"id":"Q1","answer":"design","p":0.9}]
+      """
+    And step "build.quality.sorting" runs its script
+    And step "build.quality.closing" runs its script
+    And step "build.review.carrying" runs its script
+
+  Scenario: security and one-way doors come first, a carried finding sorted among the rest
+    Given step "build.review.reviewing" writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract
+
+      The new export.
+
+      - [ ] ./src/calc.ts#2-2 — subtract(a, b)
+
+      ## Session token
+
+      - [ ] ./src/calc.ts#1-1 — reads the caller's token
+
+      ## AC-1 ignores floating point
+
+      - [ ] ./src/calc.ts#2-2 — returns the raw difference
+
+      ## Saved format
+
+      - [ ] ./src/calc.ts#1-2 — what callers persist
+      """
+    And judge step "build.review.ranking" answers:
+      """
+      [{"id":"C1.security","answer":"no","p":0.9},{"id":"C1.reversibility","answer":"two-way","p":0.9},{"id":"C1.blastRadius","answer":"local","p":0.9},{"id":"C1.newConcept","answer":"no","p":0.9},{"id":"C2.security","answer":"yes","p":0.9},{"id":"C2.reversibility","answer":"two-way","p":0.9},{"id":"C2.blastRadius","answer":"module","p":0.9},{"id":"C2.newConcept","answer":"no","p":0.9},{"id":"C3.security","answer":"no","p":0.9},{"id":"C3.reversibility","answer":"two-way","p":0.9},{"id":"C3.blastRadius","answer":"contract","p":0.9},{"id":"C3.newConcept","answer":"no","p":0.9},{"id":"C4.security","answer":"no","p":0.9},{"id":"C4.reversibility","answer":"one-way","p":0.9},{"id":"C4.blastRadius","answer":"contract","p":0.9},{"id":"C4.newConcept","answer":"no","p":0.9}]
+      """
+    When the process is driven
+    Then the process rests at "build.review.await-review"
+    And ".gtd/REVIEW.md" contains:
+      """
+      ## Session token
+
+      _critical: security_
+
+      - [ ] ./src/calc.ts#1-1 — reads the caller's token
+
+      ## Saved format
+
+      _critical: one-way door_
+
+      - [ ] ./src/calc.ts#1-2 — what callers persist
+
+      ## AC-1 ignores floating point
+
+      _should: contract_
+
+      Should subtract round? The criterion does not say.
+      """
+    And ".gtd/REVIEW.md" contains:
+      """
+      - [ ] _your answer_
+
+      ## Subtract
+
+      _could_
+
+      The new export.
+      """
+    And the commit "gtd(judge): build.review.ranking → build.review.carrying" has a body containing "Gtd-Judge:"
+    And the commit subjects end with:
+      """
+      gtd(agent): build.review.reviewing → build.review.ranking
+      gtd(judge): build.review.ranking → build.review.carrying
+      gtd(check): build.review.carrying → build.review.await-review
+      """
+
+  Scenario: a chunk the judge is unsure about is listed as critical
+    Given step "build.review.reviewing" writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract
+
+      The new export.
+
+      - [ ] ./src/calc.ts#2-2 — subtract(a, b)
+
+      ## Session token
+
+      - [ ] ./src/calc.ts#1-1 — reads the caller's token
+
+      ## AC-1 ignores floating point
+
+      - [ ] ./src/calc.ts#2-2 — returns the raw difference
+
+      ## Saved format
+
+      - [ ] ./src/calc.ts#1-2 — what callers persist
+      """
+    And judge step "build.review.ranking" answers:
+      """
+      [{"id":"C1.security","answer":"no","p":0.9},{"id":"C1.reversibility","answer":"two-way","p":0.9},{"id":"C1.blastRadius","answer":"local","p":0.9},{"id":"C1.newConcept","answer":"no","p":0.9},{"id":"C2.security","answer":"no","p":0.4},{"id":"C2.reversibility","answer":"two-way","p":0.9},{"id":"C2.blastRadius","answer":"local","p":0.9},{"id":"C2.newConcept","answer":"no","p":0.9},{"id":"C3.security","answer":"no","p":0.9},{"id":"C3.reversibility","answer":"two-way","p":0.9},{"id":"C3.blastRadius","answer":"contract","p":0.9},{"id":"C3.newConcept","answer":"no","p":0.9},{"id":"C4.security","answer":"no","p":0.9},{"id":"C4.reversibility","answer":"two-way","p":0.9},{"id":"C4.blastRadius","answer":"local","p":0.9},{"id":"C4.newConcept","answer":"yes","p":0.9}]
+      """
+    When the process is driven
+    Then the process rests at "build.review.await-review"
+    And ".gtd/REVIEW.md" contains:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Session token
+
+      _critical: judge unsure_
+      """
+    And ".gtd/REVIEW.md" contains:
+      """
+      ## AC-1 ignores floating point
+
+      _should: contract_
+      """
+    And ".gtd/REVIEW.md" contains:
+      """
+      ## Saved format
+
+      _should: new concept_
+      """
+    And ".gtd/REVIEW.md" contains:
+      """
+      ## Subtract
+
+      _could_
+      """

package/src/workflows/feature/slice-findings.feature

@@ -70,7 +70,11 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
     And step "build.quality.sorting" runs its script
     And step "build.quality.closing" runs its script
     And step "build.health.check" changes nothing
-    And step "build.review.composing" runs its script
+    And step "build.review.carrying" runs its script
+    And judge step "build.review.ranking" answers:
+      """
+      []
+      """
 
   Scenario: a finding questioning a criterion reaches the final review, never the fixer
     Given step "build.quality.correctness.reviewing" writes ".gtd/QUALITY.md" with:
@@ -85,6 +89,25 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       """
       [{"id":"Q1","answer":"design","p":0.9}]
       """
+    And step "build.review.reviewing" writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract and multiply
+
+      - [ ] ./src/sub.test.ts#1-1 — subtract
+      - [ ] ./src/mul.test.ts#1-1 — multiply
+
+      ## AC-1 ignores floating point
+
+      - [ ] ./src/sub.test.ts#1-1 — where it applies
+
+      ## AC-1 ignores floating point (2)
+
+      - [ ] ./src/sub.test.ts#1-1 — where it applies
+      """
     When the process is driven
     Then the process rests at "build.review.await-review"
     And no commit body contains "build.fix.quality.fixing"
@@ -93,6 +116,8 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       """
       ## AC-1 ignores floating point
 
+      _critical: judge unsure_
+
       _From slice 1, lens correctness._
 
       Should subtract round? The criterion does not say.
@@ -101,6 +126,8 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       """
       ## AC-1 ignores floating point (2)
 
+      _critical: judge unsure_
+
       _From slice 2, lens correctness._
       """
     And the commit subjects end with:
@@ -117,8 +144,10 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       gtd(check): implement.closing → build.quality.correctness.reviewing
       gtd(agent): build.quality.correctness.reviewing → build.quality.triage
       gtd(judge): build.quality.triage → build.quality.sorting
-      gtd(check): build.quality.sorting → build.review.composing
-      gtd(check): build.review.composing → build.review.await-review
+      gtd(check): build.quality.sorting → build.review.reviewing
+      gtd(agent): build.review.reviewing → build.review.ranking
+      gtd(judge): build.review.ranking → build.review.carrying
+      gtd(check): build.review.carrying → build.review.await-review
       """
 
   Scenario: a mechanical finding the fix cap leaves in an early slice is carried, never escalated
@@ -135,6 +164,25 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       [{"id":"Q1","answer":"mechanical","p":0.9}]
       """
     And step "build.fix.quality.fixing" changes nothing
+    And step "build.review.reviewing" writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract and multiply
+
+      - [ ] ./src/sub.test.ts#1-1 — subtract
+      - [ ] ./src/mul.test.ts#1-1 — multiply
+
+      ## subtract has no negative test
+
+      - [ ] ./src/sub.test.ts#1-1 — where it applies
+
+      ## subtract has no negative test (2)
+
+      - [ ] ./src/sub.test.ts#1-1 — where it applies
+      """
     When the process is driven
     Then the process rests at "build.review.await-review"
     And no commit body contains "build.health.describe"
@@ -142,6 +190,8 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       """
       ## subtract has no negative test
 
+      _critical: judge unsure_
+
       _From slice 1, lens correctness._
 
       _The fixer left this unresolved._
@@ -168,8 +218,10 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       gtd(agent): build.fix.quality.fixing
       gtd(agent): build.fix.quality.fixing → build.health.check
       gtd(check): build.health.check → build.quality.closing
-      gtd(check): build.quality.closing → build.review.composing
-      gtd(check): build.review.composing → build.review.await-review
+      gtd(check): build.quality.closing → build.review.reviewing
+      gtd(agent): build.review.reviewing → build.review.ranking
+      gtd(judge): build.review.ranking → build.review.carrying
+      gtd(check): build.review.carrying → build.review.await-review
       """
 
   Scenario: the final review lists every slice's fixes with their commits
@@ -190,6 +242,17 @@ Feature: every slice's quality lap is triaged, and its leftovers wait for the re
       it("subtracts a larger number", () => {})
       """
     And step "build.fix.quality.fixing" deletes ".gtd/QUALITY.md"
+    And step "build.review.reviewing" writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract and multiply
+
+      - [ ] ./src/sub.test.ts#1-1 — subtract
+      - [ ] ./src/mul.test.ts#1-1 — multiply
+      """
     When the process is driven
     Then the process rests at "build.review.await-review"
     And ".gtd/REVIEW.md" contains ", slice 1, lens correctness)"

package/src/workflows/feature/slicing.feature

@@ -51,7 +51,7 @@ Feature: a change with more criteria than the cap is built in coarse slices
       [{"id":"AC-1","answer":"yes","p":0.9},{"id":"AC-2","answer":"yes","p":0.9}]
       """
     When the process is driven
-    Then the process rests at "build.review.composing"
+    Then the process rests at "build.review.reviewing"
     And the commit subjects end with:
       """
       gtd(human): design.gate.answer → seam.naive
@@ -60,7 +60,7 @@ Feature: a change with more criteria than the cap is built in coarse slices
       gtd(check): implement.applying → implement.health.check
       gtd(check): implement.health.check → implement.coverage
       gtd(judge): implement.coverage → implement.closing
-      gtd(check): implement.closing → build.review.composing
+      gtd(check): implement.closing → build.review.reviewing
       """
     And the output lines of gtd "slices" start with:
       """
@@ -112,7 +112,7 @@ Feature: a change with more criteria than the cap is built in coarse slices
       [{"id":"AC-2","answer":"yes","p":0.9}]
       """
     When the process is driven
-    Then the process rests at "build.review.composing"
+    Then the process rests at "build.review.reviewing"
     And the commit subjects end with:
       """
       gtd(agent): design.triage → design.gate.answer
@@ -129,7 +129,7 @@ Feature: a change with more criteria than the cap is built in coarse slices
       gtd(check): implement.applying → implement.health.check
       gtd(check): implement.health.check → implement.coverage
       gtd(judge): implement.coverage → implement.closing
-      gtd(check): implement.closing → build.review.composing
+      gtd(check): implement.closing → build.review.reviewing
       """
     And the output lines of gtd "slices" start with:
       """
@@ -268,7 +268,7 @@ Feature: a change with more criteria than the cap is built in coarse slices
       """
     When gtd lands
     And the process is driven
-    Then the process rests at "build.review.composing"
+    Then the process rests at "build.review.reviewing"
     And the commit subjects end with:
       """
       gtd(human): seam.steer → seam.naive
@@ -277,7 +277,7 @@ Feature: a change with more criteria than the cap is built in coarse slices
       gtd(check): implement.applying → implement.health.check
       gtd(check): implement.health.check → implement.coverage
       gtd(judge): implement.coverage → implement.closing
-      gtd(check): implement.closing → build.review.composing
+      gtd(check): implement.closing → build.review.reviewing
       """
     And ".gtd/REQUIREMENTS.md" does not exist
     And ".gtd/SLICES.md" does not exist

package/src/workflows/feature/standards.feature

@@ -67,7 +67,35 @@ Feature: the review learns standards from the human's answers
       Calculators read better as classes.
       """
     And step "build.quality.sorting" runs its script
-    And step "build.review.composing" runs its script
+    And step "build.review.reviewing" writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract
+
+      - [ ] ./src/calc.ts#2-2 — subtract(a, b)
+      """
+    And step "build.review.reviewing", when prompted with "- `## subtract has no class`", writes ".gtd/REVIEW.md" with:
+      """
+      # Review: abc1234
+
+      <!-- base: 0000000 -->
+
+      ## Subtract
+
+      - [ ] ./src/calc.ts#2-2 — subtract(a, b)
+
+      ## subtract has no class
+
+      - [ ] ./src/calc.ts#2-2 — a plain function
+      """
+    And step "build.review.carrying" runs its script
+    And judge step "build.review.ranking" answers:
+      """
+      []
+      """
     And judge step "build.quality.triage" answers:
       """
       [{"id":"Q1","answer":"design","p":0.9}]