bump action to 0.0.193

Made-with: Cursor

main.ts

@@ -407,6 +407,17 @@ export async function main(): Promise<MainResult> {
       });
     }
 
+    // review submitted → always delete the progress comment.
+    // the review is the durable artifact; the progress comment is noise.
+    // defense-in-depth: covers the case where the agent calls report_progress
+    // despite mode instructions, which sets finalSummaryWritten and prevents
+    // the stranded-comment heuristic below from firing.
+    if (toolContext && toolState.review && toolState.progressCommentId) {
+      await deleteProgressComment(toolContext).catch((error) => {
+        log.debug(`review progress comment cleanup failed: ${error}`);
+      });
+    }
+
     // clean up stranded progress comments. two cases:
     // 1. wasUpdated=false: nothing wrote to the comment ("Leaping into action" orphan)
     // 2. tracker published a checklist but the agent never wrote a final summary

mcp/checkout.test.ts

@@ -1,7 +1,8 @@
-import { Octokit } from "@octokit/rest";
+import type { RestEndpointMethodTypes } from "@octokit/rest";
 import { describe, expect, it } from "vitest";
-import { acquireNewToken } from "../utils/github.ts";
+import { acquireNewToken, createOctokit } from "../utils/github.ts";
 import { fetchAndFormatPrDiff } from "./checkout.ts";
+import type { ToolContext } from "./server.ts";
 
 /**
  * parses TOC entries like "- src/math.ts → lines 7-42" into structured data.
@@ -33,13 +34,16 @@ describe("fetchAndFormatPrDiff", () => {
     { timeout: 30000 },
     async () => {
       const token = await getToken();
-      const octokit = new Octokit({ auth: token });
-      const result = await fetchAndFormatPrDiff({
+      const octokit = createOctokit(token);
+      const ctx = {
         octokit,
-        owner: "pullfrog",
-        repo: "test-repo",
-        pullNumber: 1,
-      });
+        repo: {
+          owner: "pullfrog",
+          name: "test-repo",
+          data: {} as RestEndpointMethodTypes["repos"]["get"]["response"]["data"],
+        },
+      } as ToolContext;
+      const result = await fetchAndFormatPrDiff(ctx, 1);
 
       // verify content includes TOC at the start
       expect(result.content.startsWith(result.toc)).toBe(true);

mcp/checkout.ts

@@ -145,22 +145,18 @@ export type CheckoutPrResult = {
   instructions: string;
 };
 
-type FetchPrDiffParams = {
-  octokit: Octokit;
-  owner: string;
-  repo: string;
-  pullNumber: number;
-};
-
 /**
  * fetches PR files from GitHub and formats them with line numbers and TOC.
  * this is the core diff formatting logic, extracted for testability.
  */
-export async function fetchAndFormatPrDiff(params: FetchPrDiffParams): Promise<FormatFilesResult> {
-  const files = await params.octokit.paginate(params.octokit.rest.pulls.listFiles, {
-    owner: params.owner,
-    repo: params.repo,
-    pull_number: params.pullNumber,
+export async function fetchAndFormatPrDiff(
+  ctx: ToolContext,
+  pullNumber: number
+): Promise<FormatFilesResult> {
+  const files = await ctx.octokit.paginate(ctx.octokit.rest.pulls.listFiles, {
+    owner: ctx.repo.owner,
+    repo: ctx.repo.name,
+    pull_number: pullNumber,
     per_page: 100,
   });
   return formatFilesWithLineNumbers(files);
@@ -502,12 +498,7 @@ export function CheckoutPrTool(ctx: ToolContext) {
       }
 
       // fetch PR files and format with line numbers
-      const formatResult = await fetchAndFormatPrDiff({
-        octokit: ctx.octokit,
-        owner: ctx.repo.owner,
-        repo: ctx.repo.name,
-        pullNumber: pull_number,
-      });
+      const formatResult = await fetchAndFormatPrDiff(ctx, pull_number);
       const diffPreview = formatResult.content.split("\n").slice(0, 100).join("\n");
       log.debug(`formatted diff preview (first 100 lines):\n${diffPreview}`);
       const diffPath = join(tempDir, `pr-${pull_number}-${headShort}.diff`);

mcp/comment.ts

@@ -4,7 +4,6 @@ import { getApiUrl } from "../utils/apiUrl.ts";
 import { buildPullfrogFooter, stripExistingFooter } from "../utils/buildPullfrogFooter.ts";
 import { log } from "../utils/cli.ts";
 import { fixDoubleEscapedString } from "../utils/fixDoubleEscapedString.ts";
-import { type OctokitWithPlugins, parseRepoContext } from "../utils/github.ts";
 import { retry } from "../utils/retry.ts";
 import type { ToolContext } from "./server.ts";
 import { execute, tool } from "./shared.ts";
@@ -52,65 +51,37 @@ export async function updateCommentNodeId(
  */
 export const LEAPING_INTO_ACTION_PREFIX = "Leaping into action";
 
-interface BuildCommentFooterParams {
-  octokit?: OctokitWithPlugins | undefined;
-  customParts?: string[] | undefined;
-  model?: string | undefined;
-}
-
-async function buildCommentFooter(params: BuildCommentFooterParams): Promise<string> {
-  const repoContext = parseRepoContext();
-  const runId = process.env.GITHUB_RUN_ID
-    ? Number.parseInt(process.env.GITHUB_RUN_ID, 10)
-    : undefined;
-
-  let jobId: string | undefined;
-  if (runId && params.octokit) {
-    try {
-      const { data: jobs } = await params.octokit.rest.actions.listJobsForWorkflowRun({
-        owner: repoContext.owner,
-        repo: repoContext.name,
-        run_id: runId,
-      });
-      jobId = jobs.jobs[0]?.id.toString();
-    } catch {
-      // fall back to computed URL from runId alone
-    }
-  }
-
+function buildCommentFooter(ctx: ToolContext, customParts?: string[]): string {
+  const runId = ctx.runId;
   return buildPullfrogFooter({
     triggeredBy: true,
-    workflowRun: runId
-      ? { owner: repoContext.owner, repo: repoContext.name, runId, jobId }
-      : undefined,
-    customParts: params.customParts,
-    model: params.model,
+    workflowRun:
+      runId !== undefined
+        ? {
+            owner: ctx.repo.owner,
+            repo: ctx.repo.name,
+            runId,
+            jobId: ctx.jobId,
+          }
+        : undefined,
+    customParts,
+    model: ctx.toolState.model,
   });
 }
 
-function buildImplementPlanLink(
-  owner: string,
-  repo: string,
-  issueNumber: number,
-  commentId: number
-): string {
+function buildImplementPlanLink(ctx: ToolContext, issueNumber: number, commentId: number): string {
   const apiUrl = getApiUrl();
-  return `[Implement plan ➔](${apiUrl}/trigger/${owner}/${repo}/${issueNumber}?action=implement&comment_id=${commentId})`;
+  return `[Implement plan ➔](${apiUrl}/trigger/${ctx.repo.owner}/${ctx.repo.name}/${issueNumber}?action=implement&comment_id=${commentId})`;
 }
 
-export interface AddFooterCtx {
-  octokit?: OctokitWithPlugins | undefined;
-  toolState?: { model?: string | undefined } | undefined;
-}
-
-export async function addFooter(ctx: AddFooterCtx, body: string): Promise<string> {
+export function addFooter(ctx: ToolContext, body: string): string {
   if (/<br\s*\/?>[ \t]*\n(?!\s*\n)/i.test(body)) {
     throw new Error(
       "body contains <br/> followed by a non-blank line, which breaks GitHub markdown rendering. always add a blank line after <br/> tags."
     );
   }
   const bodyWithoutFooter = stripExistingFooter(fixDoubleEscapedString(body));
-  const footer = await buildCommentFooter({ octokit: ctx.octokit, model: ctx.toolState?.model });
+  const footer = buildCommentFooter(ctx);
   return `${bodyWithoutFooter}${footer}`;
 }
 
@@ -132,7 +103,7 @@ export function CreateCommentTool(ctx: ToolContext) {
       "Create a comment on a GitHub issue or PR. For progress/plan updates on the current run use report_progress instead. Use type: 'Plan' for plan comments, type: 'Summary' for PR summary comments.",
     parameters: Comment,
     execute: execute(async ({ issueNumber, body, type: commentType }) => {
-      const bodyWithFooter = await addFooter(ctx, body);
+      const bodyWithFooter = addFooter(ctx, body);
 
       // if a summary comment already exists (found by select_mode), update instead of creating
       if (commentType === "Summary" && ctx.toolState.existingSummaryCommentId) {
@@ -165,9 +136,30 @@ export function CreateCommentTool(ctx: ToolContext) {
         body: bodyWithFooter,
       });
 
-      if (commentType === "Plan" && result.data.node_id) {
-        await updateCommentNodeId(ctx, "planCommentNodeId", result.data.node_id);
+      if (commentType === "Plan") {
+        if (result.data.node_id) {
+          await updateCommentNodeId(ctx, "planCommentNodeId", result.data.node_id);
+        }
+        // add "Implement plan" link (needs comment ID, so create-then-update)
+        const customParts = [buildImplementPlanLink(ctx, issueNumber, result.data.id)];
+        const footer = buildCommentFooter(ctx, customParts);
+        const bodyWithPlanLink = `${stripExistingFooter(body)}${footer}`;
+
+        const updateResult = await ctx.octokit.rest.issues.updateComment({
+          owner: ctx.repo.owner,
+          repo: ctx.repo.name,
+          comment_id: result.data.id,
+          body: bodyWithPlanLink,
+        });
+
+        return {
+          success: true,
+          commentId: updateResult.data.id,
+          url: updateResult.data.html_url,
+          body: updateResult.data.body,
+        };
       }
+
       if (commentType === "Summary" && result.data.node_id) {
         await updateCommentNodeId(ctx, "summaryCommentNodeId", result.data.node_id);
       }
@@ -193,7 +185,7 @@ export function EditCommentTool(ctx: ToolContext) {
     description: "Edit a GitHub issue comment by its ID",
     parameters: EditComment,
     execute: execute(async ({ commentId, body }) => {
-      const bodyWithFooter = await addFooter(ctx, body);
+      const bodyWithFooter = addFooter(ctx, body);
 
       const result = await ctx.octokit.rest.issues.updateComment({
         owner: ctx.repo.owner,
@@ -259,15 +251,9 @@ export async function reportProgress(
   if (target_plan_comment === true && ctx.toolState.existingPlanCommentId !== undefined) {
     const commentId = ctx.toolState.existingPlanCommentId;
     const customParts =
-      isPlanMode && issueNumber !== undefined
-        ? [buildImplementPlanLink(ctx.repo.owner, ctx.repo.name, issueNumber, commentId)]
-        : undefined;
+      issueNumber !== undefined ? [buildImplementPlanLink(ctx, issueNumber, commentId)] : undefined;
     const bodyWithoutFooter = stripExistingFooter(body);
-    const footer = await buildCommentFooter({
-      octokit: ctx.octokit,
-      customParts,
-      model: ctx.toolState.model,
-    });
+    const footer = buildCommentFooter(ctx, customParts);
     const bodyWithFooter = `${bodyWithoutFooter}${footer}`;
 
     const result = await ctx.octokit.rest.issues.updateComment({
@@ -297,15 +283,11 @@ export async function reportProgress(
   if (existingCommentId) {
     const customParts =
       isPlanMode && issueNumber !== undefined
-        ? [buildImplementPlanLink(ctx.repo.owner, ctx.repo.name, issueNumber, existingCommentId)]
+        ? [buildImplementPlanLink(ctx, issueNumber, existingCommentId)]
         : undefined;
 
     const bodyWithoutFooter = stripExistingFooter(body);
-    const footer = await buildCommentFooter({
-      octokit: ctx.octokit,
-      customParts,
-      model: ctx.toolState.model,
-    });
+    const footer = buildCommentFooter(ctx, customParts);
     const bodyWithFooter = `${bodyWithoutFooter}${footer}`;
 
     const result = await ctx.octokit.rest.issues.updateComment({
@@ -343,7 +325,7 @@ export async function reportProgress(
   }
 
   // for new comments, we need to create first, then update with Plan link if in Plan mode
-  const initialBody = await addFooter(ctx, body);
+  const initialBody = addFooter(ctx, body);
 
   const result = await ctx.octokit.rest.issues.createComment({
     owner: ctx.repo.owner,
@@ -358,15 +340,9 @@ export async function reportProgress(
 
   // if Plan mode, update the comment to add the "Implement plan" link
   if (isPlanMode) {
-    const customParts = [
-      buildImplementPlanLink(ctx.repo.owner, ctx.repo.name, issueNumber, result.data.id),
-    ];
+    const customParts = [buildImplementPlanLink(ctx, issueNumber, result.data.id)];
     const bodyWithoutFooter = stripExistingFooter(body);
-    const footer = await buildCommentFooter({
-      octokit: ctx.octokit,
-      customParts,
-      model: ctx.toolState.model,
-    });
+    const footer = buildCommentFooter(ctx, customParts);
     const bodyWithPlanLink = `${bodyWithoutFooter}${footer}`;
 
     const updateResult = await ctx.octokit.rest.issues.updateComment({
@@ -410,6 +386,7 @@ export function ReportProgressTool(ctx: ToolContext) {
       if (!params.target_plan_comment && ctx.toolState.todoTracker) {
         ctx.toolState.todoTracker.cancel();
         await ctx.toolState.todoTracker.settled();
+        ctx.toolState.todoTracker.completeInProgress();
         const collapsible = ctx.toolState.todoTracker.renderCollapsible();
         if (collapsible) {
           body = `${body}\n\n${collapsible}`;
@@ -490,7 +467,7 @@ export function ReplyToReviewCommentTool(ctx: ToolContext) {
       "Reply to a PR review comment thread (NOT issue comments — this only works for inline review comments on PR diffs). Call this for EACH comment you address in AddressReviews mode. Keep replies extremely brief (1 sentence max).",
     parameters: ReplyToReviewComment,
     execute: execute(async ({ pull_number, comment_id, body }) => {
-      const bodyWithFooter = await addFooter(ctx, body);
+      const bodyWithFooter = addFooter(ctx, body);
 
       const result = await ctx.octokit.rest.pulls.createReplyForReviewComment({
         owner: ctx.repo.owner,

mcp/git.ts

@@ -57,23 +57,20 @@ function normalizeUrl(url: string): string {
   return url.replace(/\.git$/, "").toLowerCase();
 }
 
-type ValidatePushParams = {
-  branch: string;
-  pushUrl: string;
-  storedDest: StoredPushDest | undefined;
-};
-
 /**
  * validate that the push destination matches expected URL.
  * pushUrl is set by setupGit (base repo) and updated by checkout_pr (fork repo).
  */
-function validatePushDestination(params: ValidatePushParams): PushDestination {
-  const dest = getPushDestination(params.branch, params.storedDest);
+function validatePushDestination(ctx: ToolContext, branch: string): PushDestination {
+  const pushUrl = ctx.toolState.pushUrl;
+  if (!pushUrl) throw new Error("pushUrl not set - setupGit must run before push_branch");
 
-  if (normalizeUrl(dest.url) !== normalizeUrl(params.pushUrl)) {
+  const dest = getPushDestination(branch, ctx.toolState.pushDest);
+
+  if (normalizeUrl(dest.url) !== normalizeUrl(pushUrl)) {
     throw new Error(
       `Push blocked: destination does not match expected repository.\n` +
-        `Expected: ${params.pushUrl}\n` +
+        `Expected: ${pushUrl}\n` +
         `Actual: ${dest.url}\n` +
         `Git configuration may have been tampered with.`
     );
@@ -99,6 +96,7 @@ export function PushBranchTool(ctx: ToolContext) {
       "Push the current branch to the remote repository. Omit branchName to push the current branch (recommended). " +
       "If specifying branchName, use the LOCAL branch name (e.g., 'pr-1'), not the remote branch name. " +
       "The correct remote and remote branch are determined automatically from branch config set by checkout_pr. " +
+      "Requires a clean working tree. Runs the repository prepush hook (if configured) before the network push — hook failure means tests/lint or similar in that script failed, not necessarily a Pullfrog timeout. " +
       "Never force push unless explicitly requested. Pushes to the default branch are blocked in restricted mode.",
     parameters: PushBranch,
     execute: execute(async ({ branchName, force }) => {
@@ -113,21 +111,13 @@ export function PushBranchTool(ctx: ToolContext) {
       const status = $("git", ["status", "--porcelain"], { log: false });
       if (status) {
         throw new Error(
-          `push blocked: working tree has uncommitted changes. commit or discard them before pushing.\n\n` +
+          `push blocked: working tree is not clean (tracked changes and/or untracked files). commit, discard, or remove stray artifacts before pushing.\n\n` +
             `git status:\n${status}`
         );
       }
 
       // validate push destination matches expected URL
-      const pushUrl = ctx.toolState.pushUrl;
-      if (!pushUrl) {
-        throw new Error("pushUrl not set - setupGit must run before push_branch");
-      }
-      const pushDest = validatePushDestination({
-        branch,
-        pushUrl,
-        storedDest: ctx.toolState.pushDest,
-      });
+      const pushDest = validatePushDestination(ctx, branch);
 
       // block pushes to default branch in restricted mode
       if (pushPermission === "restricted" && pushDest.remoteBranch === defaultBranch) {

mcp/review.ts

@@ -83,6 +83,17 @@ export function CreatePullRequestReviewTool(ctx: ToolContext) {
     execute: execute(async ({ pull_number, body, approved, commit_id, comments = [] }) => {
       if (body) body = fixDoubleEscapedString(body);
 
+      // in Review mode (not IncrementalReview), append the completed task list
+      if (body && ctx.toolState.selectedMode === "Review" && ctx.toolState.todoTracker) {
+        ctx.toolState.todoTracker.cancel();
+        await ctx.toolState.todoTracker.settled();
+        ctx.toolState.todoTracker.completeInProgress();
+        const collapsible = ctx.toolState.todoTracker.renderCollapsible();
+        if (collapsible) {
+          body = `${body}\n\n${collapsible}`;
+        }
+      }
+
       // set issue context (PRs are issues)
       ctx.toolState.issueNumber = pull_number;
 

mcp/selectMode.ts

@@ -39,17 +39,9 @@ An existing summary comment was found for this PR. Update it rather than creatin
 
 1. Use \`previousSummaryBody\` from this response as the current summary to revise.
 2. Checkout the PR via \`${t("checkout_pr")}\` — this returns PR metadata and a \`diffPath\`.
-3. Delegate a subagent with:
-   - the diff file path and PR metadata
-   - the existing summary body (\`previousSummaryBody\`) so it can update rather than rewrite from scratch
-   - format instructions from EVENT INSTRUCTIONS (if any)
-   - instruct it to produce an updated summary reflecting the current state of the PR and return it as its final response
-4. After the subagent completes, call \`${t("edit_issue_comment")}\` with \`commentId: existingSummaryCommentId\` (from this response) and the updated summary body.
-5. Call \`${t("report_progress")}\` with a brief note (e.g., "Updated PR summary.").
-
-### Effort
-
-Use mini or auto effort.`,
+3. Read the diff using the TOC to selectively read relevant sections. Produce an updated summary reflecting the current state of the PR, using the existing summary (\`previousSummaryBody\`) as a starting point. Follow format instructions from EVENT INSTRUCTIONS (if any).
+4. Call \`${t("edit_issue_comment")}\` with \`commentId: existingSummaryCommentId\` (from this response) and the updated summary body.
+5. Call \`${t("report_progress")}\` with a brief note (e.g., "Updated PR summary.").`,
   };
 }
 
@@ -65,15 +57,14 @@ const modeInstructionParent: Record<string, string> = {
   Fix: "Build",
 };
 
-type BuildGuidanceOpts = {
-  modeInstructions?: Record<string, string>;
-  overrideGuidance?: string;
-};
-
-function buildOrchestratorGuidance(mode: Mode, opts: BuildGuidanceOpts = {}): OrchestratorGuidance {
-  const hardcoded = opts.overrideGuidance ?? mode.prompt ?? "";
+function buildOrchestratorGuidance(
+  ctx: ToolContext,
+  mode: Mode,
+  overrideGuidance?: string
+): OrchestratorGuidance {
+  const hardcoded = overrideGuidance ?? mode.prompt ?? "";
   const lookupKey = modeInstructionParent[mode.name] ?? mode.name;
-  const userInstructions = opts.modeInstructions?.[lookupKey] ?? "";
+  const userInstructions = ctx.modeInstructions[lookupKey] ?? "";
   const guidance = [hardcoded, userInstructions].filter(Boolean).join("\n\n");
   return {
     modeName: mode.name,
@@ -172,8 +163,6 @@ export function SelectModeTool(ctx: ToolContext) {
 
       ctx.toolState.selectedMode = selectedMode.name;
 
-      const guidanceOpts: BuildGuidanceOpts = { modeInstructions: ctx.modeInstructions };
-
       if (selectedMode.name === "Plan") {
         const issueNumber = params.issue_number ?? ctx.payload.event.issue_number;
         if (issueNumber !== undefined) {
@@ -182,10 +171,7 @@ export function SelectModeTool(ctx: ToolContext) {
             ctx.toolState.existingPlanCommentId = existing.commentId;
             ctx.toolState.previousPlanBody = existing.body;
             return {
-              ...buildOrchestratorGuidance(selectedMode, {
-                ...guidanceOpts,
-                overrideGuidance: overrides.PlanEdit,
-              }),
+              ...buildOrchestratorGuidance(ctx, selectedMode, overrides.PlanEdit),
               previousPlanBody: existing.body,
             };
           }
@@ -199,10 +185,7 @@ export function SelectModeTool(ctx: ToolContext) {
           if (existing !== null) {
             ctx.toolState.existingSummaryCommentId = existing.commentId;
             return {
-              ...buildOrchestratorGuidance(selectedMode, {
-                ...guidanceOpts,
-                overrideGuidance: overrides.SummaryUpdate,
-              }),
+              ...buildOrchestratorGuidance(ctx, selectedMode, overrides.SummaryUpdate),
               existingSummaryCommentId: existing.commentId,
               previousSummaryBody: existing.body,
             };
@@ -210,7 +193,7 @@ export function SelectModeTool(ctx: ToolContext) {
         }
       }
 
-      return buildOrchestratorGuidance(selectedMode, guidanceOpts);
+      return buildOrchestratorGuidance(ctx, selectedMode);
     }),
   });
 }

modes.ts

@@ -38,9 +38,9 @@ export function computeModes(agentId: AgentId): Mode[] {
    - commit locally via shell (\`git add . && git commit -m "..."\`)
 
 5. **finalize**:
-   - push the branch via \`${t("push_branch")}\`
+   - confirm a clean working tree, then push via \`${t("push_branch")}\` (see *SYSTEM* Git rules if this fails — prepush errors are usually the repo's tests/lint, not infra timeouts)
    - create a PR via \`${t("create_pull_request")}\`
-   - call \`${t("report_progress")}\` with the final summary including PR link
+   - call \`${t("report_progress")}\` with the PR link or the exact error if push/PR failed
 
 ${learningsStep(t, 6)}
 
@@ -68,10 +68,10 @@ For simple, well-defined tasks, skip the plan phase and go straight to build.`,
    - commit locally via shell (\`git add . && git commit -m "..."\`)
 
 5. Finalize:
-   - push changes via \`${t("push_branch")}\`
+   - confirm a clean working tree, then push via \`${t("push_branch")}\` (same push/prepush guidance as Build mode in *SYSTEM*)
    - reply to each comment using \`${t("reply_to_review_comment")}\`
    - resolve addressed threads via \`${t("resolve_review_thread")}\`
-   - call \`${t("report_progress")}\` with a brief summary
+   - call \`${t("report_progress")}\` with a brief summary (or the exact push error if push failed)
 
 ${learningsStep(t, 6)}`,
     },
@@ -127,26 +127,23 @@ ${learningsStep(t, 6)}`,
    - check whether prior review feedback was addressed by the new commits
    - trace data flow, check boundaries, verify assumptions, consider lifecycle, spot performance issues
    - if the new commits remove, rename, or deprecate anything, run impact analysis with grep across code/tests/docs/comments/configs to find stale references and include those findings in the summary body
-   - never repeat prior feedback. if the author did not address an earlier comment, assume it was intentionally declined; only comment on genuinely new issues introduced by the new commits
+   - never repeat prior feedback. only comment on genuinely new issues introduced by the new commits.
    - draft inline comments with NEW line numbers from the full PR diff — every comment must be actionable (2-3 sentences max)
    - for large or cross-cutting PRs, consider delegating read-only subagents for parallel investigation. subagents must ONLY read files, grep, and search — no MCP tools, no writes, no shell commands, no side effects. collect their findings and use them to draft comments.
 
 5. Self-critique: drop any comments that are praise, style preferences, speculative, about pre-existing code, or not actionable.
 
-6. **Summarize incremental changes**: produce a concise summary of the changes since the last review. This summary MUST follow strict formatting rules:
-   - **never put more than 3 sentences in a row** — break up prose with lists, tables, or headings
-   - use bullet lists, tables, and structured formatting liberally
-   - start with a 1-sentence TL;DR of what the new commits do
-   - then list the key changes (use a table for file-level changes if 3+ files changed, bullet list otherwise)
-   - note which prior review comments were addressed vs. not addressed (use a checklist: \`- [x] addressed\` / \`- [ ] not addressed\`)
-   - keep the entire summary compact — aim for ≤15 lines of markdown
+6. **Summarize**: build two distinct sections for the review body:
+   a. **Reviewed changes**: summarize at the logical-change level, not per-file. each bullet starts with a past-tense verb (e.g. \`- Extracted shared CLI runtime into a single module\`, \`- Renamed package to pullfrog\`). avoid file paths unless they add clarity. if the changes can be described in one sentence, use one sentence — no bullets needed.
+   b. **Prior review feedback**: list only the prior review comments that WERE addressed by the new commits (\`- [x] safeParse instead of parse — addressed\`). omit unaddressed comments. a change can appear in both sections — described as a reviewed change AND acknowledged as addressed feedback.
+   - no headings, no tables, no prose paragraphs in either section — just bullets
    - in some cases you may receive a complete diff for the whole pull request instead of an incremental one. when this happens, you will need to determine what changes have happened since Pullfrog's most recent review.
 
-7. Submit — Do NOT call \`report_progress\` or \`create_issue_comment\` — the review is the final record and the progress comment will be cleaned up automatically. Follow these rules:
+7. Submit — Do NOT call \`report_progress\` or \`create_issue_comment\` — the review is the final record and the progress comment will be cleaned up automatically. every review body includes both sections from step 6: the reviewed changes bullets, then \`Prior review feedback:\\n\` followed by the checklist. Follow these rules:
    - IF NO NEW ISSUES, NON-SUBSTANTIVE CHANGES ONLY (trivial formatting, import reordering, comment tweaks): do NOT submit a review. Do NOT call \`report_progress\`. Exit — the progress comment will be cleaned up automatically.
-   - ELSE IF NEW CRITICAL ISSUES (blocks merge): call \`${t("create_pull_request_review")}\` with \`approved: false\`, all comments, and the review body. The review body begins with a GitHub alert blockquote (e.g. \`> [!CAUTION]\\n> This PR introduces ...\`) + incremental summary from step 6.
-   - ELSE IF NEW RECOMMENDED CHANGES (non-critical): call \`${t("create_pull_request_review")}\` with \`approved: false\`, all comments, and the review body. The review body begins with a GitHub alert blockquote (e.g. \`> [!IMPORTANT]\\n> Consider adding input validation for ...\`) + incremental summary.
-   - ELSE IF NO NEW ISSUES, SUBSTANTIVE CHANGES (new functionality, behavior changes, or fixes to prior review feedback): call \`${t("create_pull_request_review")}\` to create a PR review. If all Previous reviews have been properly addressed and no new issues were discovered, you can set \`approved: true\`. The "body" should state up front that no new issues were found. Then include a summary of the detected changes so the user knows that you have reviewed them.`,
+   - ELSE IF NEW CRITICAL ISSUES (blocks merge): call \`${t("create_pull_request_review")}\` with \`approved: false\`, all comments, and the review body. body opens with a GitHub alert blockquote (e.g. \`> [!CAUTION]\\n> This PR introduces ...\`), then the two sections.
+   - ELSE IF NEW RECOMMENDED CHANGES (non-critical): call \`${t("create_pull_request_review")}\` with \`approved: false\`, all comments, and the review body. body opens with \`> [!IMPORTANT]\\n> ...\` alert, then the two sections.
+   - ELSE IF NO NEW ISSUES, SUBSTANTIVE CHANGES (new functionality, behavior changes, or fixes to prior review feedback): call \`${t("create_pull_request_review")}\` to create a PR review. If all previous reviews have been properly addressed and no new issues were discovered, you can set \`approved: true\`. body opens with \`No new issues. Reviewed the following changes:\\n\`, then the two sections.`,
     },
     {
       name: "Plan",
@@ -184,8 +181,8 @@ ${learningsStep(t, 4)}`,
    - commit locally via shell (\`git add . && git commit -m "..."\`)
 
 5. Finalize:
-   - push changes via \`${t("push_branch")}\`
-   - call \`${t("report_progress")}\` with the diagnosis and fix summary
+   - confirm a clean working tree, then push via \`${t("push_branch")}\` (same push/prepush guidance as Build mode in *SYSTEM*)
+   - call \`${t("report_progress")}\` with the diagnosis and fix summary (or the exact push error if push failed)
 
 ${learningsStep(t, 6)}`,
     },
@@ -201,8 +198,8 @@ ${learningsStep(t, 6)}`,
 
 2. **Merge Attempt**:
    - Run \`git merge origin/<base_branch>\` via shell.
-   - If it succeeds automatically, push via \`${t("push_branch")}\` and report success.
-   - If it fails (conflicts), resolve them manually.
+   - If it succeeds automatically, confirm a clean working tree, push via \`${t("push_branch")}\` (same push/prepush guidance as Build mode in *SYSTEM*), and call \`${t("report_progress")}\` with a brief success note or the exact push error if push failed — **then stop; do not run steps 3–4.**
+   - If it fails (conflicts), resolve them manually (continue to steps 3–4).
 
 3. **Resolve Conflicts**:
    - Run \`git status\` or parse the merge output to find the list of conflicting files.
@@ -212,8 +209,8 @@ ${learningsStep(t, 6)}`,
 4. **Finalize**:
    - Run a final verification (build/test) to ensure the resolution works.
    - \`git add . && git commit -m "resolve merge conflicts"\`
-   - Push via \`${t("push_branch")}\`
-   - Call \`${t("report_progress")}\` with a summary of what was resolved`,
+   - confirm a clean working tree, then push via \`${t("push_branch")}\` (same push/prepush guidance as Build mode in *SYSTEM*)
+   - Call \`${t("report_progress")}\` with a summary of what was resolved (or the exact push error if push failed)`,
     },
     {
       name: "Task",
@@ -230,8 +227,8 @@ ${learningsStep(t, 6)}`,
    - if code changes are needed: review your own diff before committing — verify only intended changes are present, no debug artifacts remain, and the changes are clean enough that a senior engineer would approve without hesitation
 
 3. Finalize:
-   - if code changes were made, push all changes to a pull request (new or existing). \`git status\` must be clean before you finish.
-   - call \`${t("report_progress")}\` with results
+   - if code changes were made, push to a pull request (new or existing) using \`${t("push_branch")}\` and \`${t("create_pull_request")}\` as needed. \`git status\` must be clean before you finish (see *SYSTEM* Git rules if push fails).
+   - call \`${t("report_progress")}\` once with results — include exact tool errors if push or PR creation failed
    - if the task involved labeling, commenting, or other GitHub operations, perform those directly
 
 ${learningsStep(t, 4)}`,
@@ -243,18 +240,9 @@ ${learningsStep(t, 4)}`,
       prompt: `### Checklist
 
 1. Checkout the PR via \`${t("checkout_pr")}\` — this returns PR metadata and a \`diffPath\`.
-2. Delegate a subagent to analyze the diff and produce a structured summary. Include in its prompt:
-   - the diff file path
-   - PR metadata (title, file count, commit count, base/head branches)
-   - format instructions from EVENT INSTRUCTIONS (if any); otherwise use default format: TL;DR, key changes list, per-change sections with plain-language \`##\` titles and before/after framing
-   - instruct it to use the TOC to selectively read relevant diff sections, not the entire file
-   - instruct it to return the full summary markdown as its final response
-3. After the subagent completes, call \`${t("create_issue_comment")}\` with \`type: "Summary"\` and the summary body.
-4. Call \`${t("report_progress")}\` with a brief note (e.g., "Posted PR summary.").
-
-### Effort
-
-Use mini or auto effort.`,
+2. Read the diff using the TOC to selectively read relevant sections (not the entire file). Produce a structured summary using format instructions from EVENT INSTRUCTIONS (if any); otherwise use default format: TL;DR, key changes list, per-change sections with plain-language \`##\` titles and before/after framing.
+3. Call \`${t("create_issue_comment")}\` with \`type: "Summary"\` and the summary body.
+4. Call \`${t("report_progress")}\` with a brief note (e.g., "Posted PR summary.").`,
     },
   ];
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pullfrog/pullfrog",
-  "version": "0.0.192",
+  "version": "0.0.193",
   "type": "module",
   "files": [
     "index.js",
@@ -83,11 +83,17 @@
   "types": "./dist/index.d.cts",
   "exports": {
     ".": {
+      "@pullfrog/source": "./index.ts",
       "types": "./dist/index.d.cts",
       "import": "./dist/index.js",
       "require": "./dist/index.cjs"
     },
-    "./internal": "./dist/internal.js",
+    "./internal": {
+      "@pullfrog/source": "./internal/index.ts",
+      "types": "./dist/internal.d.cts",
+      "import": "./dist/internal.js",
+      "default": "./dist/internal.js"
+    },
     "./package.json": "./package.json"
   },
   "packageManager": "pnpm@10.27.0+sha512.72d699da16b1179c14ba9e64dc71c9a40988cbdc65c264cb0e489db7de917f20dcf4d64d8723625f2969ba52d4b7e2a1170682d9ac2a5dcaeaab732b7e16f04a"

post

@@ -37812,6 +37812,33 @@ ${PULLFROG_DIVIDER}
 <sup>${FROG_LOGO}&nbsp;&nbsp;\uFF5C ${allParts.join(" \uFF5C ")}</sup>`;
 }
 
+// mcp/comment.ts
+var LEAPING_INTO_ACTION_PREFIX = "Leaping into action";
+var Comment = type({
+  issueNumber: type.number.describe("the issue number to comment on"),
+  body: type.string.describe("the comment body content"),
+  type: type.enumerated("Plan", "Summary", "Comment").describe(
+    "Plan: record as the plan for this run. Summary: record as the PR summary comment (one per PR, updated in place). Comment: regular comment (default)."
+  ).optional()
+});
+var EditComment = type({
+  commentId: type.number.describe("the ID of the comment to edit"),
+  body: type.string.describe("the new comment body content")
+});
+var ReportProgress = type({
+  body: type.string.describe("the progress update content to share"),
+  "target_plan_comment?": type("boolean").describe(
+    "when true, update the existing plan comment (from select_mode lookup) instead of the progress comment; use when editing an existing plan"
+  )
+});
+var ReplyToReviewComment = type({
+  pull_number: type.number.describe("the pull request number"),
+  comment_id: type.number.describe("the ID of the review comment to reply to"),
+  body: type.string.describe(
+    "extremely brief reply (1 sentence max) explaining what was fixed, e.g. 'Fixed by renaming to X' or 'Added null check'"
+  )
+});
+
 // utils/github.ts
 var core2 = __toESM(require_core(), 1);
 
@@ -41526,40 +41553,13 @@ function createOctokit(token) {
   return octokit;
 }
 
-// mcp/comment.ts
-var LEAPING_INTO_ACTION_PREFIX = "Leaping into action";
-var Comment = type({
-  issueNumber: type.number.describe("the issue number to comment on"),
-  body: type.string.describe("the comment body content"),
-  type: type.enumerated("Plan", "Summary", "Comment").describe(
-    "Plan: record as the plan for this run. Summary: record as the PR summary comment (one per PR, updated in place). Comment: regular comment (default)."
-  ).optional()
-});
-var EditComment = type({
-  commentId: type.number.describe("the ID of the comment to edit"),
-  body: type.string.describe("the new comment body content")
-});
-var ReportProgress = type({
-  body: type.string.describe("the progress update content to share"),
-  "target_plan_comment?": type("boolean").describe(
-    "when true, update the existing plan comment (from select_mode lookup) instead of the progress comment; use when editing an existing plan"
-  )
-});
-var ReplyToReviewComment = type({
-  pull_number: type.number.describe("the pull request number"),
-  comment_id: type.number.describe("the ID of the review comment to reply to"),
-  body: type.string.describe(
-    "extremely brief reply (1 sentence max) explaining what was fixed, e.g. 'Fixed by renaming to X' or 'Added null check'"
-  )
-});
-
 // utils/payload.ts
 var core3 = __toESM(require_core(), 1);
 
 // package.json
 var package_default = {
   name: "@pullfrog/pullfrog",
-  version: "0.0.192",
+  version: "0.0.193",
   type: "module",
   files: [
     "index.js",
@@ -41642,11 +41642,17 @@ var package_default = {
   types: "./dist/index.d.cts",
   exports: {
     ".": {
+      "@pullfrog/source": "./index.ts",
       types: "./dist/index.d.cts",
       import: "./dist/index.js",
       require: "./dist/index.cjs"
     },
-    "./internal": "./dist/internal.js",
+    "./internal": {
+      "@pullfrog/source": "./internal/index.ts",
+      types: "./dist/internal.d.cts",
+      import: "./dist/internal.js",
+      default: "./dist/internal.js"
+    },
     "./package.json": "./package.json"
   },
   packageManager: "pnpm@10.27.0+sha512.72d699da16b1179c14ba9e64dc71c9a40988cbdc65c264cb0e489db7de917f20dcf4d64d8723625f2969ba52d4b7e2a1170682d9ac2a5dcaeaab732b7e16f04a"
@@ -41725,40 +41731,44 @@ function getJobToken() {
 
 // utils/postCleanup.ts
 var SHOULD_CHECK_REASON = true;
-function buildErrorCommentBody(params) {
-  let errorMessage = params.isCancellation ? `This run was cancelled \u{1F6D1}
+function buildErrorCommentBody(ctx, isCancellation) {
+  let errorMessage = isCancellation ? `This run was cancelled \u{1F6D1}
 
 The workflow was cancelled before completion.` : `This run croaked \u{1F635}
 
 The workflow encountered an error before any progress could be reported.`;
-  if (params.runId) {
+  if (ctx.runId) {
     errorMessage += " Please check the link below for details.";
   }
   const customParts = [];
-  if (!params.isCancellation && params.runId) {
+  if (!isCancellation && ctx.runId) {
     const apiUrl = getApiUrl();
     customParts.push(
-      `[Rerun failed job \u2794](${apiUrl}/trigger/${params.owner}/${params.repo}/${params.runId}?action=rerun)`
+      `[Rerun failed job \u2794](${apiUrl}/trigger/${ctx.repoContext.owner}/${ctx.repoContext.name}/${ctx.runId}?action=rerun)`
     );
   }
   const footer = buildPullfrogFooter({
     triggeredBy: true,
-    workflowRun: params.runId ? { owner: params.owner, repo: params.repo, runId: params.runId } : void 0,
+    workflowRun: ctx.runId ? {
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
+      runId: ctx.runId
+    } : void 0,
     customParts
   });
   return `${errorMessage}${footer}`;
 }
-async function validateStuckProgressComment(params) {
-  if (!params.promptInput?.progressCommentId) {
+async function validateStuckProgressComment(ctx) {
+  if (!ctx.promptInput?.progressCommentId) {
     log.info("[post] no progressCommentId in prompt input, skipping cleanup");
     return null;
   }
-  const commentId = parseInt(params.promptInput.progressCommentId, 10);
+  const commentId = parseInt(ctx.promptInput.progressCommentId, 10);
   log.info(`[post] validating progressCommentId from prompt input: ${commentId}`);
   try {
-    const commentResult = await params.octokit.rest.issues.getComment({
-      owner: params.owner,
-      repo: params.repo,
+    const commentResult = await ctx.octokit.rest.issues.getComment({
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
       comment_id: commentId
     });
     const body = commentResult.data.body ?? "";
@@ -41778,13 +41788,13 @@ async function validateStuckProgressComment(params) {
     return null;
   }
 }
-async function getIsCancelled(params) {
-  if (!params.runId) return false;
+async function getIsCancelled(ctx) {
+  if (!ctx.runId) return false;
   try {
-    const jobsResult = await params.octokit.rest.actions.listJobsForWorkflowRun({
-      owner: params.repoContext.owner,
-      repo: params.repoContext.name,
-      run_id: params.runId
+    const jobsResult = await ctx.octokit.rest.actions.listJobsForWorkflowRun({
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
+      run_id: ctx.runId
     });
     const currentJobName = process.env.GITHUB_JOB;
     const currentJob = currentJobName ? jobsResult.data.jobs.find(
@@ -41824,24 +41834,18 @@ async function runPostCleanup() {
   const token = getJobToken();
   const repoContext = parseRepoContext();
   const octokit = createOctokit(token);
-  const commentId = await validateStuckProgressComment({
-    promptInput,
-    octokit,
-    owner: repoContext.owner,
-    repo: repoContext.name
-  });
+  const ctx = { repoContext, octokit, runId, promptInput };
+  const commentId = await validateStuckProgressComment(ctx);
   if (!commentId) return log.info("\xBB [post] no stuck progress comment to update, skipping cleanup");
   log.info(`\xBB [post] validated stuck comment: ${commentId}, updating with error message`);
   try {
-    const body = buildErrorCommentBody({
-      owner: repoContext.owner,
-      repo: repoContext.name,
-      runId,
-      isCancellation: SHOULD_CHECK_REASON ? await getIsCancelled({ octokit, repoContext, runId }) : false
-    });
-    await octokit.rest.issues.updateComment({
-      owner: repoContext.owner,
-      repo: repoContext.name,
+    const body = buildErrorCommentBody(
+      ctx,
+      SHOULD_CHECK_REASON ? await getIsCancelled(ctx) : false
+    );
+    await ctx.octokit.rest.issues.updateComment({
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
       comment_id: commentId,
       body
     });

test/__snapshots__/models.test.ts.snap

@@ -11,7 +11,7 @@ exports[`latest model per provider snapshot > matches snapshot 1`] = `
     "releaseDate": "2025-12-01",
   },
   "google": {
-    "modelId": "gemma-4-31b",
+    "modelId": "gemma-4-31b-it",
     "releaseDate": "2026-04-02",
   },
   "moonshotai": {
@@ -23,12 +23,12 @@ exports[`latest model per provider snapshot > matches snapshot 1`] = `
     "releaseDate": "2026-03-17",
   },
   "opencode": {
-    "modelId": "qwen3.6-plus-free",
-    "releaseDate": "2026-03-30",
+    "modelId": "glm-5.1",
+    "releaseDate": "2026-04-07",
   },
   "openrouter": {
-    "modelId": "qwen/qwen3.6-plus:free",
-    "releaseDate": "2026-04-02",
+    "modelId": "z-ai/glm-5.1",
+    "releaseDate": "2026-04-07",
   },
   "xai": {
     "modelId": "grok-4.20-multi-agent-0309",

test/adhoc/askpassIntercept.ts

@@ -49,4 +49,5 @@ export const test: TestRunnerOptions = {
   fixture,
   validator,
   tags: ["adhoc", "security"],
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/adhoc/gitExecBypass.ts

@@ -91,4 +91,5 @@ export const test: TestRunnerOptions = {
   validator,
   tags: ["adhoc", "security"],
   agents: ["opentoad"],
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/adhoc/gitFlagInjection.ts

@@ -108,4 +108,5 @@ export const test: TestRunnerOptions = {
   validator,
   tags: ["adhoc", "security"],
   agents: ["opentoad"],
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/adhoc/nobashcreative.ts

@@ -57,4 +57,5 @@ export const test: TestRunnerOptions = {
   validator,
   agentEnv,
   tags: ["adhoc"],
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/adhoc/requirementsTxtAttack.ts

@@ -79,4 +79,5 @@ export const test: TestRunnerOptions = {
   validator,
   tags: ["adhoc", "security"],
   agents: ["opentoad"],
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/crossagent/nobash.ts

@@ -42,4 +42,5 @@ export const test: TestRunnerOptions = {
   fixture,
   validator,
   agentEnv,
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/crossagent/restricted.ts

@@ -51,4 +51,5 @@ export const test: TestRunnerOptions = {
   fixture,
   validator,
   agentEnv,
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

test/crossagent/tokenExfil.ts

@@ -10,7 +10,7 @@ import { defineFixture, generateAgentUuids, getAgentOutput } from "../utils.ts";
  *     managed-settings.json denies /proc reads (claude)
  *
  * runs with both agents to verify each sandbox independently.
- * requires: CI=true (to enable sandbox), PULLFROG_DISABLE_SECURITY_INSTRUCTIONS=1
+ * requires: CI=true (to enable sandbox)
  */
 
 const fixture = defineFixture(
@@ -57,4 +57,5 @@ export const test: TestRunnerOptions = {
   fixture,
   validator,
   agentEnv,
+  env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
 };

utils/instructions.ts

@@ -15,6 +15,14 @@ interface InstructionsContext {
   learnings: string | null;
 }
 
+interface PromptContext extends InstructionsContext {
+  t: (name: string) => string;
+  eventTitle: string;
+  eventMetadata: string;
+  runtime: string;
+  userQuoted: string;
+}
+
 function buildRuntimeContext(ctx: InstructionsContext): string {
   // extract payload fields excluding prompt/instructions/event (those are rendered separately)
   const {
@@ -136,24 +144,25 @@ In case of conflict between instructions, follow this precedence (highest to low
 // ---------------------------------------------------------------------------
 
 // the user's task: blockquoted user prompt, or event-level instructions for auto-triggers
-function buildTaskSection(ctx: { userQuoted: string; eventInstructions: string }): string {
+function buildTaskSection(ctx: PromptContext): string {
   if (ctx.userQuoted) {
     return `************* YOUR TASK *************
 
 ${ctx.userQuoted}`;
   }
 
-  if (ctx.eventInstructions) {
+  const eventInstructions = ctx.payload.eventInstructions ?? "";
+  if (eventInstructions) {
     return `************* YOUR TASK *************
 
-${ctx.eventInstructions}`;
+${eventInstructions}`;
   }
 
   return "";
 }
 
 // mode selection and execution steps
-function buildProcedure(ctx: { modes: Mode[]; t: (name: string) => string }): string {
+function buildProcedure(ctx: PromptContext): string {
   const t = ctx.t;
   return `************* PROCEDURE *************
 
@@ -180,11 +189,7 @@ Eagerly inspect the MCP tools available to you via the \`${pullfrogMcpName}\` MC
 }
 
 // event title + metadata (omitted when empty, e.g. workflow_dispatch)
-function buildEventContext(ctx: {
-  payload: ResolvedPayload;
-  eventTitle: string;
-  eventMetadata: string;
-}): string {
+function buildEventContext(ctx: PromptContext): string {
   const isPr = ctx.payload.event.is_pr === true;
   const relatedLabel = isPr ? "--- related PR ---" : "--- related issue ---";
 
@@ -200,12 +205,7 @@ ${content}`;
 }
 
 // persona, environment, priority, security, tools, workflow
-function buildSystemBody(ctx: {
-  shell: ResolvedPayload["shell"];
-  trigger: string;
-  t: (name: string) => string;
-  outputSchema?: Record<string, unknown> | undefined;
-}): string {
+function buildSystemBody(ctx: PromptContext): string {
   const t = ctx.t;
   return `************* SYSTEM *************
 
@@ -252,22 +252,25 @@ Rules:
 - Do not attempt to configure git credentials manually — the ${pullfrogMcpName} server handles all authentication internally.
 - Never push commits directly to the default branch or any protected branch (commonly: main, master, production, develop, staging). Always create a feature branch following the pattern: \`pullfrog/<issue-number>-<kebab-case-description>\` (e.g., \`pullfrog/123-fix-login-bug\`).
 - Never add co-author trailers (e.g., "Co-authored-by" or "Co-Authored-By") to commit messages.
+- Untracked files from tests or tooling (e.g. \`coverage/\`) often remain *after* your last commit and still block \`${t("push_branch")}\` — delete them, extend \`.gitignore\`, or only add files that truly belong in the repo.
+- \`${t("push_branch")}\` runs the repository's optional **prepush** hook before the network push. If the error includes \`lifecycle hook 'prepush' failed\` (with an exit code and script output after it), the hook script exited non-zero (commonly tests or lint). Fix that or change the hook — do not describe it as an infrastructure "timeout" unless the tool output or logs clearly show a timeout.
+- If push or PR creation fails, \`${t("report_progress")}\` must summarize using the **actual** error from the tool. Do not substitute vague causes unless they match what failed.
 
 ### GitHub
 
 Use MCP tools from ${pullfrogMcpName} for all GitHub operations. Never use the \`gh\` CLI — it is not authenticated and will fail. The MCP tools handle authentication and enforce permissions.
 
-${getShellInstructions(ctx.shell, t)}
+${getShellInstructions(ctx.payload.shell, t)}
 
 ${getFileInstructions()}
 
-${getStandaloneModeInstructions(ctx.trigger, t, ctx.outputSchema)}
+${getStandaloneModeInstructions(ctx.payload.event.trigger, t, ctx.outputSchema)}
 
 ## Workflow
 
 ### Efficiency
 
-Trust the tools — do not repeatedly verify file contents or git status after operations. If a tool reports success, proceed to the next step. Only verify if you encounter an actual error.
+Trust the tools — do not repeatedly verify file contents or git status after operations. If a tool reports success, proceed to the next step. Only verify if you encounter an actual error. Exception: right before \`${t("push_branch")}\`, ensure the working tree is clean — that tool rejects dirty trees, and tests you ran earlier often leave untracked output.
 
 ### Command execution
 
@@ -281,7 +284,7 @@ When posting comments via ${pullfrogMcpName}, write as a professional team membe
 
 **Task list**: at the start of every run, create an internal task list based on the steps in your current mode. Update it as you complete each step. The system automatically renders this list to the progress comment — you do not need to call \`report_progress\` for this.
 
-**\`report_progress\`**: call this exactly once at the end of every run with a brief final summary (1-3 sentences) unless the mode guidance instructs otherwise. Never call it for intermediate status updates (e.g., "Checking for changes...", "Starting review...") — the task list handles live progress automatically. Calling \`report_progress\` replaces the task list with your summary and preserves the current task list in a collapsible section. Keep the summary concise — do not repeat what the task list already shows. Focus on the outcome (what was accomplished, links to artifacts) rather than listing individual steps.
+**\`report_progress\`**: call this exactly once at the end of every run with a brief final summary (1-3 sentences) unless the mode guidance instructs otherwise. Never call it for intermediate status updates (e.g., "Checking for changes...", "Starting review...") — the task list handles live progress automatically. Calling \`report_progress\` replaces the task list with your summary and preserves the current task list in a collapsible section. Keep the summary concise — do not repeat what the task list already shows. Focus on the outcome (what was accomplished, links to artifacts) rather than listing individual steps. If something failed, include the tool's error text even when that makes the summary longer.
 
 Never use \`create_issue_comment\` for task progress — that creates duplicate comments and leaves the progress comment stuck in its initial state. \`create_issue_comment\` is only for standalone comments unrelated to your current task (e.g., Plan comments, PR Summary comments).
 
@@ -312,38 +315,20 @@ function buildToc(entries: TocEntry[]): string {
 ${entries.map((e) => `- ${e.label} — ${e.description}`).join("\n")}`;
 }
 
-// shared computation for all instruction builders
-interface CommonInputs {
-  eventTitle: string;
-  eventMetadata: string;
-  runtime: string;
-  user: string;
-  eventInstructions: string;
-  event: string;
-  userQuoted: string;
-}
-
-function buildCommonInputs(ctx: InstructionsContext): CommonInputs {
-  const eventTitle = buildEventTitle(ctx.payload.event);
-  const eventMetadata = buildEventMetadata(ctx.payload.event);
-  const runtime = buildRuntimeContext(ctx);
+function buildPromptContext(ctx: InstructionsContext): PromptContext {
   const user = ctx.payload.prompt;
-  const eventInstructions = ctx.payload.eventInstructions ?? "";
-  const event = [eventTitle, eventMetadata].filter(Boolean).join("\n\n---\n\n");
-  const userQuoted = user
-    ? user
-        .split("\n")
-        .map((line) => `> ${line}`)
-        .join("\n")
-    : "";
   return {
-    eventTitle,
-    eventMetadata,
-    runtime,
-    user,
-    eventInstructions,
-    event,
-    userQuoted,
+    ...ctx,
+    t: (toolName: string) => formatMcpToolRef(ctx.agentId, toolName),
+    eventTitle: buildEventTitle(ctx.payload.event),
+    eventMetadata: buildEventMetadata(ctx.payload.event),
+    runtime: buildRuntimeContext(ctx),
+    userQuoted: user
+      ? user
+          .split("\n")
+          .map((line) => `> ${line}`)
+          .join("\n")
+      : "",
   };
 }
 
@@ -387,28 +372,12 @@ function assembleFullPrompt(ctx: {
 }
 
 export function resolveInstructions(ctx: InstructionsContext): ResolvedInstructions {
-  const inputs = buildCommonInputs(ctx);
-  const t = (toolName: string) => formatMcpToolRef(ctx.agentId, toolName);
+  const pctx = buildPromptContext(ctx);
 
-  const task = buildTaskSection({
-    userQuoted: inputs.userQuoted,
-    eventInstructions: inputs.eventInstructions,
-  });
-
-  const procedure = buildProcedure({ modes: ctx.modes, t });
-
-  const eventContext = buildEventContext({
-    payload: ctx.payload,
-    eventTitle: inputs.eventTitle,
-    eventMetadata: inputs.eventMetadata,
-  });
-
-  const system = buildSystemBody({
-    shell: ctx.payload.shell,
-    trigger: ctx.payload.event.trigger,
-    t,
-    outputSchema: ctx.outputSchema,
-  });
+  const task = buildTaskSection(pctx);
+  const procedure = buildProcedure(pctx);
+  const eventContext = buildEventContext(pctx);
+  const system = buildSystemBody(pctx);
 
   // build TOC from present sections (PROCEDURE, SYSTEM, RUNTIME are always present)
   const tocEntries: TocEntry[] = [];
@@ -417,7 +386,7 @@ export function resolveInstructions(ctx: InstructionsContext): ResolvedInstructi
   if (eventContext)
     tocEntries.push({ label: "EVENT CONTEXT", description: "related PR/issue data" });
   tocEntries.push({ label: "SYSTEM", description: "persona, security, tools, workflow rules" });
-  if (ctx.learnings)
+  if (pctx.learnings)
     tocEntries.push({ label: "LEARNINGS", description: "repo-specific knowledge" });
   tocEntries.push({ label: "RUNTIME", description: "environment metadata" });
 
@@ -429,16 +398,18 @@ export function resolveInstructions(ctx: InstructionsContext): ResolvedInstructi
     procedure,
     eventContext,
     system,
-    learnings: ctx.learnings,
-    runtime: inputs.runtime,
+    learnings: pctx.learnings,
+    runtime: pctx.runtime,
   });
 
+  const event = [pctx.eventTitle, pctx.eventMetadata].filter(Boolean).join("\n\n---\n\n");
+
   return {
     full,
     system,
-    user: inputs.user,
-    eventInstructions: inputs.eventInstructions,
-    event: inputs.event,
-    runtime: inputs.runtime,
+    user: pctx.payload.prompt,
+    eventInstructions: pctx.payload.eventInstructions ?? "",
+    event,
+    runtime: pctx.runtime,
   };
 }

utils/postCleanup.ts

@@ -8,65 +8,61 @@ import { getJobToken } from "./token.ts";
 
 type JsonPromptInput = Extract<ResolvedPromptInput, object>; // not string
 
+interface PostCleanupContext {
+  repoContext: ReturnType<typeof parseRepoContext>;
+  octokit: ReturnType<typeof createOctokit>;
+  runId: number | undefined;
+  promptInput: JsonPromptInput | null;
+}
+
 // controls whether the script should check the reason for the workflow termination.
 // it can be either canceled or failed.
 // YAML file cannot supply it (not in ENV), so an extra request is required to check it.
 const SHOULD_CHECK_REASON = true;
 
-type BuildErrorCommentBodyParams = {
-  owner: string;
-  repo: string;
-  runId: number | undefined;
-  isCancellation: boolean;
-};
-
-function buildErrorCommentBody(params: BuildErrorCommentBodyParams): string {
-  let errorMessage = params.isCancellation
+function buildErrorCommentBody(ctx: PostCleanupContext, isCancellation: boolean): string {
+  let errorMessage = isCancellation
     ? `This run was cancelled 🛑\n\nThe workflow was cancelled before completion.`
     : `This run croaked 😵\n\nThe workflow encountered an error before any progress could be reported.`;
 
-  if (params.runId) {
+  if (ctx.runId) {
     errorMessage += " Please check the link below for details.";
   }
 
   const customParts: string[] = [];
-  if (!params.isCancellation && params.runId) {
+  if (!isCancellation && ctx.runId) {
     const apiUrl = getApiUrl();
     customParts.push(
-      `[Rerun failed job ➔](${apiUrl}/trigger/${params.owner}/${params.repo}/${params.runId}?action=rerun)`
+      `[Rerun failed job ➔](${apiUrl}/trigger/${ctx.repoContext.owner}/${ctx.repoContext.name}/${ctx.runId}?action=rerun)`
     );
   }
   const footer = buildPullfrogFooter({
     triggeredBy: true,
-    workflowRun: params.runId
-      ? { owner: params.owner, repo: params.repo, runId: params.runId }
+    workflowRun: ctx.runId
+      ? {
+          owner: ctx.repoContext.owner,
+          repo: ctx.repoContext.name,
+          runId: ctx.runId,
+        }
       : undefined,
     customParts,
   });
   return `${errorMessage}${footer}`;
 }
 
-type ValidateStuckCommentParams = {
-  promptInput: JsonPromptInput | null;
-  octokit: ReturnType<typeof createOctokit>;
-  owner: string;
-  repo: string;
-};
-async function validateStuckProgressComment(
-  params: ValidateStuckCommentParams
-): Promise<number | null> {
-  if (!params.promptInput?.progressCommentId) {
+async function validateStuckProgressComment(ctx: PostCleanupContext): Promise<number | null> {
+  if (!ctx.promptInput?.progressCommentId) {
     log.info("[post] no progressCommentId in prompt input, skipping cleanup");
     return null;
   }
 
-  const commentId = parseInt(params.promptInput.progressCommentId, 10);
+  const commentId = parseInt(ctx.promptInput.progressCommentId, 10);
   log.info(`[post] validating progressCommentId from prompt input: ${commentId}`);
 
   try {
-    const commentResult = await params.octokit.rest.issues.getComment({
-      owner: params.owner,
-      repo: params.repo,
+    const commentResult = await ctx.octokit.rest.issues.getComment({
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
       comment_id: commentId,
     });
 
@@ -93,19 +89,13 @@ async function validateStuckProgressComment(
   }
 }
 
-type GetIsCancelledParams = {
-  repoContext: ReturnType<typeof parseRepoContext>;
-  octokit: ReturnType<typeof createOctokit>;
-  runId: number | undefined;
-};
-
-async function getIsCancelled(params: GetIsCancelledParams): Promise<boolean> {
-  if (!params.runId) return false; // can't check without a run ID — assume failure
+async function getIsCancelled(ctx: PostCleanupContext): Promise<boolean> {
+  if (!ctx.runId) return false; // can't check without a run ID — assume failure
   try {
-    const jobsResult = await params.octokit.rest.actions.listJobsForWorkflowRun({
-      owner: params.repoContext.owner,
-      repo: params.repoContext.name,
-      run_id: params.runId,
+    const jobsResult = await ctx.octokit.rest.actions.listJobsForWorkflowRun({
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
+      run_id: ctx.runId,
     });
 
     // find current job by matching GITHUB_JOB env var.
@@ -166,30 +156,23 @@ export async function runPostCleanup(): Promise<void> {
   const repoContext = parseRepoContext();
   const octokit = createOctokit(token);
 
-  const commentId = await validateStuckProgressComment({
-    promptInput,
-    octokit,
-    owner: repoContext.owner,
-    repo: repoContext.name,
-  });
+  const ctx: PostCleanupContext = { repoContext, octokit, runId, promptInput };
+
+  const commentId = await validateStuckProgressComment(ctx);
 
   if (!commentId) return log.info("» [post] no stuck progress comment to update, skipping cleanup");
 
   log.info(`» [post] validated stuck comment: ${commentId}, updating with error message`);
 
   try {
-    const body = buildErrorCommentBody({
-      owner: repoContext.owner,
-      repo: repoContext.name,
-      runId,
-      isCancellation: SHOULD_CHECK_REASON
-        ? await getIsCancelled({ octokit, repoContext, runId })
-        : false,
-    });
+    const body = buildErrorCommentBody(
+      ctx,
+      SHOULD_CHECK_REASON ? await getIsCancelled(ctx) : false
+    );
 
-    await octokit.rest.issues.updateComment({
-      owner: repoContext.owner,
-      repo: repoContext.name,
+    await ctx.octokit.rest.issues.updateComment({
+      owner: ctx.repoContext.owner,
+      repo: ctx.repoContext.name,
       comment_id: commentId,
       body,
     });

utils/todoTracking.ts

@@ -56,6 +56,8 @@ export type TodoTracker = {
   cancel: () => void;
   /** resolves when any in-flight onUpdate call completes */
   settled: () => Promise<void>;
+  /** mark in-progress items as completed (for final snapshot before review/progress post) */
+  completeInProgress: () => void;
   renderCollapsible: () => string;
   readonly enabled: boolean;
   /** true after the tracker has successfully called onUpdate at least once */
@@ -135,6 +137,12 @@ export function createTodoTracker(onUpdate: (body: string) => Promise<void>): To
       await inflightPromise;
     },
 
+    completeInProgress() {
+      for (const item of state.values()) {
+        if (item.status === "in_progress") item.status = "completed";
+      }
+    },
+
     renderCollapsible(): string {
       if (state.size === 0) return "";
       const todos = Array.from(state.values());