improve: solve-issue — add mandatory verification and escalation steps
Fixes hallucination issues observed in thread 06F7FSTXQGY3D5CY5YPQFK2Y3W: 1. Developer self-verification (critical): Added step 12 requiring mandatory verification of branch, file existence, and git status before reporting done status. Prevents hallucinated completions without actual tool execution. 2. Reviewer hard-check enforcement (critical): Added critical warning and step 0 requiring cd/pwd verification before review. Prevents false rejections based on assumptions without actual path checks. 3. Test debugging escalation (medium): Added structured debugging guidance with escalation path after 3 test cycles. Prevents infinite retry loops by providing strategy and fail-fast guidance. Also added 3 test cases to verify the new procedure steps exist. Based on change plan 9EVZPDTS16PMG analyzing execution anomalies that resulted in 58% waste (13 of 23 minutes). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -103,4 +103,46 @@ describe("solve-issue workflow: tea pr create worktree fix", () => {
|
||||
expect(committedVariant).toBeDefined();
|
||||
expect(committedVariant.required).toContain("$status");
|
||||
});
|
||||
|
||||
test("developer procedure should include mandatory verification step", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
const developerProcedure = workflow.roles.developer?.procedure;
|
||||
expect(developerProcedure).toBeDefined();
|
||||
|
||||
// Verify the procedure includes mandatory verification step
|
||||
expect(developerProcedure).toContain("MANDATORY VERIFICATION");
|
||||
expect(developerProcedure).toContain("git branch --show-current");
|
||||
expect(developerProcedure).toContain("git status");
|
||||
expect(developerProcedure).toMatch(/ls -la|verify.*exist/i);
|
||||
});
|
||||
|
||||
test("reviewer procedure should enforce worktree path verification", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
const reviewerProcedure = workflow.roles.reviewer?.procedure;
|
||||
expect(reviewerProcedure).toBeDefined();
|
||||
|
||||
// Verify the procedure includes critical enforcement
|
||||
expect(reviewerProcedure).toContain("CRITICAL");
|
||||
expect(reviewerProcedure).toMatch(/cd.*pwd/);
|
||||
expect(reviewerProcedure).toContain(
|
||||
"Do NOT report results without running the actual commands",
|
||||
);
|
||||
});
|
||||
|
||||
test("developer procedure should include test debugging escalation", async () => {
|
||||
const yamlContent = await readFile(workflowPath, "utf-8");
|
||||
const workflow = parse(yamlContent) as WorkflowPayload;
|
||||
|
||||
const developerProcedure = workflow.roles.developer?.procedure;
|
||||
expect(developerProcedure).toBeDefined();
|
||||
|
||||
// Verify the procedure includes test failure guidance
|
||||
expect(developerProcedure).toMatch(/tests fail.*first run/i);
|
||||
expect(developerProcedure).toMatch(/3 test cycles|after 3 attempts/i);
|
||||
expect(developerProcedure).toContain("$status=failed");
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user