feat: standardize PR creation instructions to match BashTool format

Update PR creation instructions in generateDefaultPrompt and generateSimplePrompt
to be consistent with the comprehensive BashTool PR workflow:

- Add steps to run git log and git diff to understand full commit history
- Require analyzing ALL commits, not just the latest
- Enforce structured PR body format with ## Summary (1-3 bullet points)
  and ## Test plan (checklist) sections

action.yml

@@ -127,6 +127,9 @@ outputs:
   structured_output:
     description: "JSON string containing all structured output fields when --json-schema is provided in claude_args. Use fromJSON() to parse: fromJSON(steps.id.outputs.structured_output).field_name"
     value: ${{ steps.claude-code.outputs.structured_output }}
+  session_id:
+    description: "The Claude Code session ID that can be used with --resume to continue this conversation"
+    value: ${{ steps.claude-code.outputs.session_id }}
 
 runs:
   using: "composite"

base-action/action.yml

@@ -82,6 +82,9 @@ outputs:
   structured_output:
     description: "JSON string containing all structured output fields when --json-schema is provided in claude_args (use fromJSON() or jq to parse)"
     value: ${{ steps.run_claude.outputs.structured_output }}
+  session_id:
+    description: "The Claude Code session ID that can be used with --resume to continue this conversation"
+    value: ${{ steps.run_claude.outputs.session_id }}
 
 runs:
   using: "composite"

base-action/src/run-claude.ts

@@ -124,6 +124,36 @@ export function prepareRunConfig(
   };
 }
 
+/**
+ * Parses session_id from execution file and sets GitHub Action output
+ * Exported for testing
+ */
+export async function parseAndSetSessionId(
+  executionFile: string,
+): Promise<void> {
+  try {
+    const content = await readFile(executionFile, "utf-8");
+    const messages = JSON.parse(content) as {
+      type: string;
+      subtype?: string;
+      session_id?: string;
+    }[];
+
+    // Find the system.init message which contains session_id
+    const initMessage = messages.find(
+      (m) => m.type === "system" && m.subtype === "init",
+    );
+
+    if (initMessage?.session_id) {
+      core.setOutput("session_id", initMessage.session_id);
+      core.info(`Set session_id: ${initMessage.session_id}`);
+    }
+  } catch (error) {
+    // Don't fail the action if session_id extraction fails
+    core.warning(`Failed to extract session_id: ${error}`);
+  }
+}
+
 /**
  * Parses structured_output from execution file and sets GitHub Action outputs
  * Only runs if --json-schema was explicitly provided in claude_args
@@ -368,6 +398,9 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
 
     core.setOutput("execution_file", EXECUTION_FILE);
 
+    // Extract and set session_id
+    await parseAndSetSessionId(EXECUTION_FILE);
+
     // Parse and set structured outputs only if user provided --json-schema in claude_args
     if (hasJsonSchema) {
       try {

base-action/test/structured-output.test.ts

@@ -4,7 +4,10 @@ import { describe, test, expect, afterEach, beforeEach, spyOn } from "bun:test";
 import { writeFile, unlink } from "fs/promises";
 import { tmpdir } from "os";
 import { join } from "path";
-import { parseAndSetStructuredOutputs } from "../src/run-claude";
+import {
+  parseAndSetStructuredOutputs,
+  parseAndSetSessionId,
+} from "../src/run-claude";
 import * as core from "@actions/core";
 
 // Mock execution file path
@@ -35,16 +38,19 @@ async function createMockExecutionFile(
 // Spy on core functions
 let setOutputSpy: any;
 let infoSpy: any;
+let warningSpy: any;
 
 beforeEach(() => {
   setOutputSpy = spyOn(core, "setOutput").mockImplementation(() => {});
   infoSpy = spyOn(core, "info").mockImplementation(() => {});
+  warningSpy = spyOn(core, "warning").mockImplementation(() => {});
 });
 
 describe("parseAndSetStructuredOutputs", () => {
   afterEach(async () => {
     setOutputSpy?.mockRestore();
     infoSpy?.mockRestore();
+    warningSpy?.mockRestore();
     try {
       await unlink(TEST_EXECUTION_FILE);
     } catch {
@@ -156,3 +162,66 @@ describe("parseAndSetStructuredOutputs", () => {
     );
   });
 });
+
+describe("parseAndSetSessionId", () => {
+  afterEach(async () => {
+    setOutputSpy?.mockRestore();
+    infoSpy?.mockRestore();
+    warningSpy?.mockRestore();
+    try {
+      await unlink(TEST_EXECUTION_FILE);
+    } catch {
+      // Ignore if file doesn't exist
+    }
+  });
+
+  test("should extract session_id from system.init message", async () => {
+    const messages = [
+      { type: "system", subtype: "init", session_id: "test-session-123" },
+      { type: "result", cost_usd: 0.01 },
+    ];
+    await writeFile(TEST_EXECUTION_FILE, JSON.stringify(messages));
+
+    await parseAndSetSessionId(TEST_EXECUTION_FILE);
+
+    expect(setOutputSpy).toHaveBeenCalledWith("session_id", "test-session-123");
+    expect(infoSpy).toHaveBeenCalledWith("Set session_id: test-session-123");
+  });
+
+  test("should handle missing session_id gracefully", async () => {
+    const messages = [
+      { type: "system", subtype: "init" },
+      { type: "result", cost_usd: 0.01 },
+    ];
+    await writeFile(TEST_EXECUTION_FILE, JSON.stringify(messages));
+
+    await parseAndSetSessionId(TEST_EXECUTION_FILE);
+
+    expect(setOutputSpy).not.toHaveBeenCalled();
+  });
+
+  test("should handle missing system.init message gracefully", async () => {
+    const messages = [{ type: "result", cost_usd: 0.01 }];
+    await writeFile(TEST_EXECUTION_FILE, JSON.stringify(messages));
+
+    await parseAndSetSessionId(TEST_EXECUTION_FILE);
+
+    expect(setOutputSpy).not.toHaveBeenCalled();
+  });
+
+  test("should handle malformed JSON gracefully with warning", async () => {
+    await writeFile(TEST_EXECUTION_FILE, "{ invalid json");
+
+    await parseAndSetSessionId(TEST_EXECUTION_FILE);
+
+    expect(setOutputSpy).not.toHaveBeenCalled();
+    expect(warningSpy).toHaveBeenCalled();
+  });
+
+  test("should handle non-existent file gracefully with warning", async () => {
+    await parseAndSetSessionId("/nonexistent/file.json");
+
+    expect(setOutputSpy).not.toHaveBeenCalled();
+    expect(warningSpy).toHaveBeenCalled();
+  });
+});

examples/test-failure-analysis.yml

@@ -53,7 +53,6 @@ jobs:
           fromJSON(steps.detect.outputs.structured_output).confidence >= 0.7
         env:
           GH_TOKEN: ${{ github.token }}
-          HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
         run: |
           OUTPUT='${{ steps.detect.outputs.structured_output }}'
           CONFIDENCE=$(echo "$OUTPUT" | jq -r '.confidence')
@@ -65,7 +64,7 @@ jobs:
           echo "Triggering automatic retry..."
 
           gh workflow run "${{ github.event.workflow_run.name }}" \
-            --ref "$HEAD_BRANCH"
+            --ref "${{ github.event.workflow_run.head_branch }}"
 
       # Low confidence flaky detection - skip retry
       - name: Low confidence detection
@@ -84,14 +83,13 @@ jobs:
         if: github.event.workflow_run.event == 'pull_request'
         env:
           GH_TOKEN: ${{ github.token }}
-          HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
         run: |
           OUTPUT='${{ steps.detect.outputs.structured_output }}'
           IS_FLAKY=$(echo "$OUTPUT" | jq -r '.is_flaky')
           CONFIDENCE=$(echo "$OUTPUT" | jq -r '.confidence')
           SUMMARY=$(echo "$OUTPUT" | jq -r '.summary')
 
-          pr_number=$(gh pr list --head "$HEAD_BRANCH" --json number --jq '.[0].number')
+          pr_number=$(gh pr list --head "${{ github.event.workflow_run.head_branch }}" --json number --jq '.[0].number')
 
           if [ -n "$pr_number" ]; then
             if [ "$IS_FLAKY" = "true" ]; then

src/create-prompt/index.ts

@@ -563,9 +563,22 @@ ${getCommitInstructions(eventData, githubData, context, useCommitSigning)}
 ${
   eventData.claudeBranch
     ? `
-When done with changes, provide a PR link:
+When done with changes:
+1. Run git log origin/${eventData.baseBranch}..HEAD and git diff origin/${eventData.baseBranch}...HEAD to understand ALL commits
+2. Draft a PR summary analyzing ALL changes (not just the latest commit)
+3. Provide a PR link:
 [Create a PR](${GITHUB_SERVER_URL}/${context.repository}/compare/${eventData.baseBranch}...${eventData.claudeBranch}?quick_pull=1&title=<url-encoded-title>&body=<url-encoded-body>)
-Use THREE dots (...) between branches. URL-encode all parameters.`
+Use THREE dots (...) between branches. URL-encode all parameters.
+PR body format:
+## Summary
+<1-3 bullet points>
+
+## Test plan
+<Checklist of testing TODOs>
+
+Fixes #<issue-number>
+
+Generated with [Claude Code](https://claude.ai/code)`
     : ""
 }
 
@@ -743,8 +756,13 @@ ${eventData.eventName === "issue_comment" || eventData.eventName === "pull_reque
       - Mark each subtask as completed as you progress.${getCommitInstructions(eventData, githubData, context, useCommitSigning)}
       ${
         eventData.claudeBranch
-          ? `- Provide a URL to create a PR manually in this format:
-        [Create a PR](${GITHUB_SERVER_URL}/${context.repository}/compare/${eventData.baseBranch}...<branch-name>?quick_pull=1&title=<url-encoded-title>&body=<url-encoded-body>)
+          ? `- When creating a pull request, follow these steps:
+        1. Use git log and git diff to understand the full commit history for the current branch (from the time it diverged from the base branch):
+           - Run: git log origin/${eventData.baseBranch}..HEAD
+           - Run: git diff origin/${eventData.baseBranch}...HEAD
+        2. Analyze ALL changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request), and draft a pull request summary
+        3. Provide a URL to create a PR manually in this format:
+           [Create a PR](${GITHUB_SERVER_URL}/${context.repository}/compare/${eventData.baseBranch}...<branch-name>?quick_pull=1&title=<url-encoded-title>&body=<url-encoded-body>)
         - IMPORTANT: Use THREE dots (...) between branch names, not two (..)
           Example: ${GITHUB_SERVER_URL}/${context.repository}/compare/main...feature-branch (correct)
           NOT: ${GITHUB_SERVER_URL}/${context.repository}/compare/main..feature-branch (incorrect)
@@ -752,10 +770,16 @@ ${eventData.eventName === "issue_comment" || eventData.eventName === "pull_reque
           Example: Instead of "fix: update welcome message", use "fix%3A%20update%20welcome%20message"
         - The target-branch should be '${eventData.baseBranch}'.
         - The branch-name is the current branch: ${eventData.claudeBranch}
-        - The body should include:
-          - A clear description of the changes
-          - Reference to the original ${eventData.isPR ? "PR" : "issue"}
-          - The signature: "Generated with [Claude Code](https://claude.ai/code)"
+        - The PR body MUST follow this format:
+          ## Summary
+          <1-3 bullet points summarizing the changes>
+
+          ## Test plan
+          <Bulleted markdown checklist of TODOs for testing the pull request>
+
+          Fixes #<issue-number>
+
+          Generated with [Claude Code](https://claude.ai/code)
         - Just include the markdown link with text "Create a PR" - do not add explanatory text before it like "You can create a PR using this link"`
           : ""
       }