fix(gsd): enforce backtick file paths in task plan IO sections (#1548)

* fix(gsd): enforce backtick file paths in task plan IO sections

The reactive task graph (ADR-004) derives dependencies from backtick-wrapped
file paths in ## Inputs and ## Expected Output sections. Without concrete
paths, the graph is ambiguous and falls back to sequential execution.

Changes:
- task-plan.md template: add comments explaining paths are machine-parsed
- plan-slice.md prompt: explicitly instruct planner to write backtick file
  paths in IO sections, add self-audit check for path presence
- observability-validator.ts: new validation rules missing_output_file_paths
  (warning) and missing_input_file_paths (info) catch plans without paths
- plan-quality-validator.test.ts: 4 new test cases for IO path validation

* fix(ci): increase max_tokens and add JSON parse error handling in ai-triage

max_tokens: 300 was too low, causing truncated JSON responses from Claude
that failed to parse. Bumped to 1024 and added try/catch with raw text
logging for easier debugging.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.github/workflows/ai-triage.yml

@@ -105,7 +105,7 @@ jobs:
               },
               body: JSON.stringify({
                 model: 'claude-haiku-4-5-20251001',
-                max_tokens: 300,
+                max_tokens: 1024,
                 messages: [{ role: 'user', content: prompt }]
               })
             });
@@ -126,7 +126,13 @@ jobs:
               return;
             }
 
-            const result = JSON.parse(jsonMatch[0]);
+            let result;
+            try {
+              result = JSON.parse(jsonMatch[0]);
+            } catch (e) {
+              core.setFailed(`JSON parse error: ${e.message}\nRaw text: ${text}`);
+              return;
+            }
             core.info(`Triage result: ${JSON.stringify(result, null, 2)}`);
 
             // Apply labels

src/resources/extensions/gsd/observability-validator.ts

@@ -235,6 +235,33 @@ export function validateTaskPlanContent(file: string, content: string): Validati
     }
   }
 
+  // Rule: Inputs and Expected Output should contain backtick-wrapped file paths
+  const inputsSection = getSection(content, "Inputs", 2);
+  const outputSection = getSection(content, "Expected Output", 2);
+  const backtickPathPattern = /`[^`]*[./][^`]*`/;
+
+  if (outputSection === null || !backtickPathPattern.test(outputSection)) {
+    issues.push({
+      severity: "warning",
+      scope: "task-plan",
+      file,
+      ruleId: "missing_output_file_paths",
+      message: "Task plan `## Expected Output` is missing or has no backtick-wrapped file paths.",
+      suggestion: "List concrete output file paths in backticks (e.g. `src/types.ts`). These are machine-parsed to derive task dependencies.",
+    });
+  }
+
+  if (inputsSection !== null && inputsSection.trim().length > 0 && !backtickPathPattern.test(inputsSection)) {
+    issues.push({
+      severity: "info",
+      scope: "task-plan",
+      file,
+      ruleId: "missing_input_file_paths",
+      message: "Task plan `## Inputs` has content but no backtick-wrapped file paths.",
+      suggestion: "List input file paths in backticks (e.g. `src/config.json`). These are machine-parsed to derive task dependencies.",
+    });
+  }
+
   // ── Observability rules (gated by runtime relevance) ──
 
   const relevant = textSuggestsObservabilityRelevant(content);

src/resources/extensions/gsd/prompts/plan-slice.md

@@ -61,13 +61,14 @@ Then:
    - a concrete, action-oriented title
    - the inline task entry fields defined in the plan.md template (Why / Files / Do / Verify / Done when)
    - a matching task plan file with description, steps, must-haves, verification, inputs, and expected output
+   - **Inputs and Expected Output must list concrete backtick-wrapped file paths** (e.g. `` `src/types.ts` ``). These are machine-parsed to derive task dependencies — vague prose without paths breaks parallel execution. Every task must have at least one output file path.
    - Observability Impact section **only if the task touches runtime boundaries, async flows, or error paths** — omit it otherwise
 6. Write `{{outputPath}}`
 7. Write individual task plans in `{{slicePath}}/tasks/`: `T01-PLAN.md`, `T02-PLAN.md`, etc.
 8. **Self-audit the plan.** Walk through each check — if any fail, fix the plan files before moving on:
     - **Completion semantics:** If every task were completed exactly as written, the slice goal/demo should actually be true.
     - **Requirement coverage:** Every must-have in the slice maps to at least one task. No must-have is orphaned. If `REQUIREMENTS.md` exists, every Active requirement this slice owns maps to at least one task.
-    - **Task completeness:** Every task has steps, must-haves, verification, inputs, and expected output — none are blank or vague.
+    - **Task completeness:** Every task has steps, must-haves, verification, inputs, and expected output — none are blank or vague. Inputs and Expected Output list backtick-wrapped file paths, not prose descriptions.
     - **Dependency correctness:** Task ordering is consistent. No task references work from a later task.
     - **Key links planned:** For every pair of artifacts that must connect, there is an explicit step that wires them.
     - **Scope sanity:** Target 2–5 steps and 3–8 files per task. 10+ steps or 12+ files — must split. Each task must be completable in a single fresh context window.

src/resources/extensions/gsd/templates/task-plan.md

@@ -42,11 +42,19 @@ estimated_files: {{estimatedFiles}}
 
 ## Inputs
 
+<!-- Every input MUST be a backtick-wrapped file path. These paths are machine-parsed to
+     derive task dependencies — vague descriptions without paths break dependency detection.
+     For the first task in a slice with no prior task outputs, list the existing source files
+     this task reads or modifies. -->
+
 - `{{filePath}}` — {{whatThisTaskNeedsFromPriorWork}}
-- {{priorTaskSummaryInsight}}
 
 ## Expected Output
 
-<!-- This task should produce a real increment toward making the slice goal/demo true. A full slice plan should not be able to mark every task complete while the claimed slice behavior still does not work at the stated proof level. -->
+<!-- Every output MUST be a backtick-wrapped file path — the specific files this task creates
+     or modifies. These paths are machine-parsed to derive task dependencies.
+     This task should produce a real increment toward making the slice goal/demo true. A full
+     slice plan should not be able to mark every task complete while the claimed slice behavior
+     still does not work at the stated proof level. -->
 
-- `{{filePath}}` — {{whatThisTaskShouldProduceOrModify}}
+- `{{filePath}}` — {{whatThisTaskCreatesOrModifies}}

src/resources/extensions/gsd/tests/plan-quality-validator.test.ts

@@ -360,4 +360,115 @@ console.log('\n=== Clean slice plan: no plan-quality issues ===');
   assertEq(planQualityIssues.length, 0, 'clean slice plan produces no empty_task_entry issues');
 }
 
+// ═══════════════════════════════════════════════════════════════════════════
+// validateTaskPlanContent — missing output file paths
+// ═══════════════════════════════════════════════════════════════════════════
+
+console.log('\n=== validateTaskPlanContent: missing output file paths ===');
+{
+  const content = `# T01: Some Task
+
+## Description
+
+Do something.
+
+## Steps
+
+1. Do the thing
+
+## Verification
+
+- Check it works
+
+## Expected Output
+
+This task produces the main output.
+`;
+
+  const issues = validateTaskPlanContent('T01-PLAN.md', content);
+  const outputIssues = issues.filter(i => i.ruleId === 'missing_output_file_paths');
+  assertTrue(outputIssues.length >= 1, 'Expected Output without file paths triggers missing_output_file_paths');
+}
+
+console.log('\n=== validateTaskPlanContent: valid output file paths ===');
+{
+  const content = `# T01: Some Task
+
+## Description
+
+Do something.
+
+## Steps
+
+1. Do the thing
+
+## Verification
+
+- Check it works
+
+## Expected Output
+
+- \`src/types.ts\` — New type definitions
+`;
+
+  const issues = validateTaskPlanContent('T01-PLAN.md', content);
+  const outputIssues = issues.filter(i => i.ruleId === 'missing_output_file_paths');
+  assertEq(outputIssues.length, 0, 'Expected Output with file paths does not trigger warning');
+}
+
+console.log('\n=== validateTaskPlanContent: missing input file paths (info severity) ===');
+{
+  const content = `# T01: Some Task
+
+## Description
+
+Do something.
+
+## Steps
+
+1. Do the thing
+
+## Verification
+
+- Check it works
+
+## Inputs
+
+Prior task summary insights about the architecture.
+
+## Expected Output
+
+- \`src/output.ts\` — Output file
+`;
+
+  const issues = validateTaskPlanContent('T01-PLAN.md', content);
+  const inputIssues = issues.filter(i => i.ruleId === 'missing_input_file_paths');
+  assertTrue(inputIssues.length >= 1, 'Inputs without file paths triggers missing_input_file_paths');
+  if (inputIssues.length > 0) {
+    assertEq(inputIssues[0].severity, 'info', 'missing_input_file_paths is info severity (not warning)');
+  }
+}
+
+console.log('\n=== validateTaskPlanContent: no Expected Output section at all ===');
+{
+  const content = `# T01: Some Task
+
+## Description
+
+Do something.
+
+## Steps
+
+1. Do the thing
+
+## Verification
+
+- Check it works
+`;
+
+  const issues = validateTaskPlanContent('T01-PLAN.md', content);
+  const outputIssues = issues.filter(i => i.ruleId === 'missing_output_file_paths');
+  assertTrue(outputIssues.length >= 1, 'Missing Expected Output section triggers missing_output_file_paths');
+}
+
 report();