reorder prompt sections: task-first with dynamic TOC (#513)

* reorder prompt sections: task-first with dynamic TOC

put the actual task at the top of the prompt for primacy, add a
dynamic table of contents, and push system/runtime metadata to the end.

new section order: TOC → YOUR TASK → PROCEDURE → EVENT CONTEXT →
SYSTEM → LEARNINGS → RUNTIME

Made-with: Cursor

* enforce clean working tree: continue session if agent leaves uncommitted changes

after each agent run, check `git status --porcelain`. if dirty, resume
the same session with instructions to commit on a new branch, push, and
open a PR. retries up to 3 times before giving up.

- claude code: capture session_id from result event, use --resume <id>
- opencode: use --continue to resume the last session
- remove --no-session-persistence from claude (needed for --resume)
- update Task mode to clarify branch/push/PR is the default finalize step

Made-with: Cursor

* log full prompt in collapsible group for debugging

Made-with: Cursor

* fix: format tool refs in buildCommitPrompt via formatMcpToolRef

* enforce clean git status: general instructions, stop hook, and Task mode

Made-with: Cursor

* fix: rename stale titleBody references after body leak fix

Made-with: Cursor

---------

Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>

agents/claude.ts

@@ -15,7 +15,7 @@ import { execFileSync } from "node:child_process";
 import { mkdirSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
 import { performance } from "node:perf_hooks";
-import { ghPullfrogMcpName } from "../external.ts";
+import { pullfrogMcpName } from "../external.ts";
 
 import { getIdleMs, markActivity } from "../utils/activity.ts";
 import { log } from "../utils/cli.ts";
@@ -31,6 +31,9 @@ import {
   type AgentRunContext,
   type AgentUsage,
   agent,
+  buildCommitPrompt,
+  getGitStatus,
+  MAX_COMMIT_RETRIES,
   MAX_STDERR_LINES,
 } from "./shared.ts";
 
@@ -53,7 +56,7 @@ function writeMcpConfig(ctx: AgentRunContext): string {
     configPath,
     JSON.stringify({
       mcpServers: {
-        [ghPullfrogMcpName]: { type: "http", url: ctx.mcpServerUrl },
+        [pullfrogMcpName]: { type: "http", url: ctx.mcpServerUrl },
       },
     })
   );
@@ -177,12 +180,15 @@ type RunParams = {
   todoTracker?: TodoTracker | undefined;
 };
 
-async function runClaude(params: RunParams): Promise<AgentResult> {
+type ClaudeRunResult = AgentResult & { sessionId?: string | undefined };
+
+async function runClaude(params: RunParams): Promise<ClaudeRunResult> {
   const startTime = performance.now();
   let eventCount = 0;
   const thinkingTimer = new ThinkingTimer();
 
   let finalOutput = "";
+  let sessionId: string | undefined;
   let accumulatedTokens = { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 };
   let tokensLogged = false;
 
@@ -271,6 +277,7 @@ async function runClaude(params: RunParams): Promise<AgentResult> {
       }
     },
     result: (event: ClaudeResultEvent) => {
+      if (event.session_id) sessionId = event.session_id;
       const subtype = event.subtype || "unknown";
       const numTurns = event.num_turns || 0;
 
@@ -431,7 +438,13 @@ async function runClaude(params: RunParams): Promise<AgentResult> {
       );
       log.debug(`stdout: ${result.stdout?.substring(0, 500)}`);
       log.debug(`stderr: ${result.stderr?.substring(0, 500)}`);
-      return { success: false, output: finalOutput || output, error: errorMessage, usage };
+      return {
+        success: false,
+        output: finalOutput || output,
+        error: errorMessage,
+        usage,
+        sessionId,
+      };
     }
 
     if (eventCount === 0 && lastProviderError) {
@@ -440,10 +453,11 @@ async function runClaude(params: RunParams): Promise<AgentResult> {
         output: finalOutput || output,
         error: `provider error: ${lastProviderError}`,
         usage,
+        sessionId,
       };
     }
 
-    return { success: true, output: finalOutput || output, usage };
+    return { success: true, output: finalOutput || output, usage, sessionId };
   } catch (error) {
     params.todoTracker?.cancel();
     const duration = performance.now() - startTime;
@@ -471,6 +485,7 @@ async function runClaude(params: RunParams): Promise<AgentResult> {
       output: finalOutput || output,
       error: `${errorMessage} [${diagnosis}]`,
       usage: buildUsage(),
+      sessionId,
     };
   }
 }
@@ -557,17 +572,15 @@ export const claude = agent({
 
     installManagedSettings();
 
-    const args = [
+    // base args shared between initial run and continue runs
+    const baseArgs = [
       cliPath,
-      "-p",
-      ctx.instructions.full,
       "--output-format",
       "stream-json",
       "--dangerously-skip-permissions",
       "--mcp-config",
       mcpConfigPath,
       "--verbose",
-      "--no-session-persistence",
       "--effort",
       effort,
       "--disallowedTools",
@@ -576,7 +589,7 @@ export const claude = agent({
     ];
 
     if (model) {
-      args.push("--model", model);
+      baseArgs.push("--model", model);
     }
 
     // agent process gets full env — needs LLM API keys, PATH, locale, etc.
@@ -589,15 +602,35 @@ export const claude = agent({
     const repoDir = process.cwd();
 
     log.info(`» effort: ${effort}`);
-    log.debug(`» starting Pullfrog (Claude Code): node ${args.join(" ")}`);
+    log.debug(`» starting Pullfrog (Claude Code): node ${baseArgs.join(" ")}`);
     log.debug(`» working directory: ${repoDir}`);
 
-    return runClaude({
-      label: "Pullfrog",
-      args,
-      cwd: repoDir,
-      env,
-      todoTracker: ctx.todoTracker,
+    const runParams = { label: "Pullfrog", cwd: repoDir, env, todoTracker: ctx.todoTracker };
+
+    let result = await runClaude({
+      ...runParams,
+      args: [...baseArgs, "-p", ctx.instructions.full],
     });
+
+    // post-run: if the working tree is dirty, resume the session and ask the agent to commit
+    for (let attempt = 0; attempt < MAX_COMMIT_RETRIES; attempt++) {
+      if (!result.success || !result.sessionId) break;
+      const status = getGitStatus();
+      if (!status) break;
+
+      log.info(`» dirty working tree (attempt ${attempt + 1}/${MAX_COMMIT_RETRIES}):\n${status}`);
+      result = await runClaude({
+        ...runParams,
+        args: [
+          ...baseArgs,
+          "-p",
+          buildCommitPrompt("claude", status),
+          "--resume",
+          result.sessionId,
+        ],
+      });
+    }
+
+    return result;
   },
 });

agents/opentoad.ts

@@ -16,7 +16,7 @@ import { execFileSync } from "node:child_process";
 import { mkdirSync } from "node:fs";
 import { join } from "node:path";
 import { performance } from "node:perf_hooks";
-import { ghPullfrogMcpName } from "../external.ts";
+import { pullfrogMcpName } from "../external.ts";
 import { modelAliases } from "../models.ts";
 import { getIdleMs, markActivity } from "../utils/activity.ts";
 import { log } from "../utils/cli.ts";
@@ -32,6 +32,9 @@ import {
   type AgentRunContext,
   type AgentUsage,
   agent,
+  buildCommitPrompt,
+  getGitStatus,
+  MAX_COMMIT_RETRIES,
   MAX_STDERR_LINES,
 } from "./shared.ts";
 
@@ -66,7 +69,7 @@ function buildSecurityConfig(ctx: AgentRunContext, model: string | undefined): s
       skill: "allow",
     },
     mcp: {
-      [ghPullfrogMcpName]: { type: "remote", url: ctx.mcpServerUrl },
+      [pullfrogMcpName]: { type: "remote", url: ctx.mcpServerUrl },
     },
   };
 
@@ -627,7 +630,8 @@ export const opentoad = agent({
       agent: "opencode",
     });
 
-    const args = ["run", ctx.instructions.full, "--format", "json", "--print-logs"];
+    // base args shared between initial run and continue runs
+    const baseArgs = ["run", "--format", "json", "--print-logs"];
 
     // OPENCODE_PERMISSION has absolute highest precedence (merged after managed/MDM configs).
     // external_directory gates ALL native filesystem tools (Read, Write, Edit, Glob, Grep, etc.)
@@ -647,16 +651,35 @@ export const opentoad = agent({
 
     const repoDir = process.cwd();
 
-    log.debug(`» starting Pullfrog (OpenCode): ${cliPath} ${args.join(" ")}`);
+    log.debug(`» starting Pullfrog (OpenCode): ${cliPath} ${baseArgs.join(" ")}`);
     log.debug(`» working directory: ${repoDir}`);
 
-    return runOpenCode({
+    const runParams = {
       label: "Pullfrog",
       cliPath,
-      args,
       cwd: repoDir,
       env,
       todoTracker: ctx.todoTracker,
+    };
+
+    let result = await runOpenCode({
+      ...runParams,
+      args: [...baseArgs, ctx.instructions.full],
     });
+
+    // post-run: if the working tree is dirty, continue the session and ask the agent to commit
+    for (let attempt = 0; attempt < MAX_COMMIT_RETRIES; attempt++) {
+      if (!result.success) break;
+      const status = getGitStatus();
+      if (!status) break;
+
+      log.info(`» dirty working tree (attempt ${attempt + 1}/${MAX_COMMIT_RETRIES}):\n${status}`);
+      result = await runOpenCode({
+        ...runParams,
+        args: [...baseArgs, "--continue", buildCommitPrompt("opentoad", status)],
+      });
+    }
+
+    return result;
   },
 });

agents/shared.ts

@@ -1,3 +1,5 @@
+import { execFileSync } from "node:child_process";
+import type { AgentId } from "../external.ts";
 import { log } from "../utils/cli.ts";
 import type { ResolvedInstructions } from "../utils/instructions.ts";
 import type { ResolvedPayload } from "../utils/payload.ts";
@@ -6,6 +8,31 @@ import type { TodoTracker } from "../utils/todoTracking.ts";
 // maximum number of stderr lines to keep in the rolling buffer during agent execution
 export const MAX_STDERR_LINES = 20;
 
+// ── post-run commit enforcement ─────────────────────────────────────────────────
+
+export const MAX_COMMIT_RETRIES = 3;
+
+export function getGitStatus(): string {
+  try {
+    return execFileSync("git", ["status", "--porcelain"], {
+      encoding: "utf-8",
+      timeout: 10_000,
+    }).trim();
+  } catch {
+    return "";
+  }
+}
+
+export function buildCommitPrompt(_agentId: AgentId, status: string): string {
+  return [
+    `UNCOMMITTED CHANGES — the working tree is dirty. push all changes to a pull request (new or existing). \`git status\` must be clean before you finish.`,
+    "",
+    "```",
+    status,
+    "```",
+  ].join("\n");
+}
+
 /**
  * token/cost usage data from a single agent run
  */
@@ -42,7 +69,7 @@ export interface AgentRunContext {
 }
 
 export interface Agent {
-  name: string;
+  name: AgentId;
   install: (token?: string) => Promise<string>;
   run: (ctx: AgentRunContext) => Promise<AgentResult>;
 }