Files
shockbot/utils/payload.ts
T
Colin McDonnell e4e93ea6d3 PR summary as agent-edited tmpfile snapshot (#568)
* PR summary as agent-edited tmpfile snapshot

Replaces the comment-based PR summary path (and the in-progress
update_pr_summary tool from #534) with a snapshot file the agent edits in
place during Review / IncrementalReview / pr-summary Task runs.

The server seeds the tmpfile with the previous snapshot (incremental) or a
stable scaffold (first run), exposes the path via select_mode, and reads it
back at end-of-run to persist to WorkflowRun.summarySnapshot and (when the
prSummaryComment toggle is on) splice into the PR description body.

Why a tmpfile rather than a tool call: incremental snapshot edits are
output-token-cheap when the agent uses native file-editing tools, and
range-diff cleanly across runs because section headings are stable. The
agent never has to regurgitate the full snapshot to update it.

Gating: snapshot generation is opt-in via either prSummaryComment="enabled"
(splice into PR body) or prReReview="enabled" (snapshot feeds future
incremental review runs as context). Users who disable both pay nothing
end-to-end — no seeding, DB write, or body splice.

Behavior changes:
- Drop the Summarize mode and the Summary comment type entirely; the
  rolling summary is no longer a separate run shape.
- pull_request_synchronize with re-review off and summary on still
  dispatches a silent pr-summary Task, but it edits the snapshot file
  instead of posting a fresh comment.
- /api/repo/.../pr/.../summary-comment now returns
  { snapshot: string | null } from the DB instead of fetching a comment via
  GraphQL. URL kept stable so deployed older actions degrade gracefully.
- summaryCommentNodeId is retained on WorkflowRun for legacy data and a
  future backfill of pre-snapshot comment-based summaries.

Supersedes #534. The commit-tool/sub-agent direction in that PR is
abandoned in favor of this file-based shape.

* address review pass #1: synchronize fallback, splice idempotency, docs

* address review pass #2: in-flight skip should not race summary fallback

* address review pass #3: signal-handler flush, doc clarifications

* address review pass #4: in-flight persist promise + bounded body-splice timeout

* address review pass #5: defensive catch on persist worker, doc nit

* add summary-stale post-run gate

When generateSummary is set, we capture the bytes of the seeded snapshot
file and pass them to the agent's post-run loop alongside the file path.
After each agent attempt, the loop diffs the current file against the
seed; if they're byte-identical the agent never touched it, and we nudge
once via a resume turn (similar to the dirty-tree gate, but soft and
fire-once so smaller models that legitimately decide no edit is warranted
don't burn the retry budget).

Mostly defends against forgetful smaller models on the Review path —
their mode prompt asks them to edit the snapshot file, but the
multi-step instruction can fall through when the diff is large.

* trigger: retry vercel preview build

* fix(action): drop unused re-export that pulled node:fs/promises into next bundle

action/internal/index.ts was re-exporting DEFAULT_PR_SUMMARY_INSTRUCTIONS
from action/utils/prSummary.ts, but nothing in the next.js app imports
it. prSummary.ts uses node:fs/promises, and pullfrog/internal is aliased
into the next bundle by next.config.ts, which made turbopack try to
resolve node:fs/promises in client chunks and fail with:

  the chunking context (unknown) does not support external modules
  (request: node:fs/promises)

drop the re-export — selectMode.ts (the only real consumer) already
imports it directly from action/utils/prSummary.ts.

* firewall PR summary snapshot from user instructions; resurrect rich format for Review

The agent-internal snapshot (the markdown file the agent edits in place across
runs) is exclusively durable context for future agent runs — user-supplied
summarization instructions warp it and degrade that context. Drop the
prSummaryCommentInstructions read path end-to-end:

- handleWebhook: stop reading prSummaryCommentInstructions, stop passing
  prSummaryInstructions through dispatch options
- action payload + ToolState + selectMode addendum: drop the instructions
  appendix; the snapshot prompt is fixed, not user-shaped
- TriggersSettings: drop the InstructionsEditor for prSummaryCommentInstructions
- prSummary.ts: reframe DEFAULT_PR_SUMMARY_INSTRUCTIONS as agent-targeted
  (durable context, not human-facing prose)

Prisma columns (prSummaryComment, prSummaryCommentInstructions) and the
matching zod schema entry stay for graceful retreat.

Separately, resurrect PR_SUMMARY_FORMAT (deleted along with the Summarize mode
in the original PR) and wire it into Review mode only. Initial PR reviews now
include a structured summary section in the review body using the rich format
(TL;DR, key changes, ## sections with before/after, file-link trails).
IncrementalReview keeps its existing terser bullet-list shape since re-review
bodies are deltas, not introductions. The user-facing review summary and the
agent-internal snapshot are deliberately separate artifacts with separate
prompts and zero shared content.

* address review comments: prompt self-consistency + stale-doc cleanup

PR 568 self-review (4232488109) flagged a self-contradiction the firewall
commit introduced and three stale doc references that survived.

- action/modes.ts: Review-mode step 2's trivial-PR shortcut said `submit
  "Reviewed — no issues found." per step 5`, but step 5's rewrite removed
  exactly that preamble. Aligned both: trivial PRs and no-actionable-issues
  PRs now produce a body that opens with "No new issues found." followed by
  the PR summary, so the user gets the headline up front and still sees what
  was reviewed.
- docs/pr-reviews.mdx: dropped the "customize the summary style with Summary
  instructions in the console" sentence (the editor was removed in the
  firewall commit). Replaced with a note that the snapshot uses Pullfrog's
  built-in format and is not user-customizable.
- wiki/prompt.md, wiki/modes.md: rewrote the snapshot-prompt entries to
  reflect the firewall — DEFAULT_PR_SUMMARY_INSTRUCTIONS is the entire
  prompt, prSummaryCommentInstructions is no longer wired in.

* drop orphaned prSummaryCommentInstructions column

Prod audit (455 repos): 5 non-null rows on a single account, all containing the
literal placeholder text from the InstructionsEditor we removed in the firewall
commit. No account has an intentional preference set, so silent-ignore (the
keep-for-retreat option) costs us nothing meaningful while leaving an orphan
column in the schema. Drop it.

- prisma/schema.prisma: remove the column
- prisma/migrations/20260506000000_drop_pr_summary_comment_instructions:
  ALTER TABLE ... DROP COLUMN
- utils/schemas/triggers.ts: drop the matching zod entry

* drop body splicing; snapshot is internal-only

User-visible PR summarization continues to ship in Review and IncrementalReview
review bodies (which already render PR_SUMMARY_FORMAT and "Reviewed changes"
respectively). The snapshot tmpfile is now purely durable cross-run agent
context — seed, edit-in-place, save to DB, feed the next run. Massive
simplification: the body splice mechanics, the two-toggle gating matrix, the
summaryHandlingCovered race tracking, and the synchronize summary-only Task
fallback all go away.

Code:
- prSummary.ts: drop splice/strip/marker code (`splicePrSummary`,
  `stripExistingSummaryBlock`, `buildSummaryBlock`, `extractPrSummary`,
  PULLFROG_SUMMARY_START/END). keep scaffold, instructions, seed/read.
- main.ts: rename persistAndPostSummary -> persistSummary; collapse to a
  single DB PATCH. drop pulls.get/pulls.update, drop AbortSignal timeout,
  drop in-flight promise machinery, drop prSummaryToBody plumbing.
- ToolState: add summarySeed (replaces local var in main.ts so persist can
  compare). drop prSummaryToBody and summaryPersistInFlight.
- persistSummary now compares against the seed and skips the DB write
  with a warning when unchanged — saving the seed verbatim is either a
  no-op or persists the placeholder scaffold, neither useful.
- postRun.ts: when summary-stale is the only failing gate and the resume
  turn itself fails, restore the pre-resume successful result and break.
  symmetric with the existing reflection-failure preservation. summary-stale
  can no longer flip a successful run to failed.

Webhook:
- pull_request_opened: generateSummary follows prReReview only (the snapshot
  has no consumer when re-review is off).
- pull_request_synchronize: collapses to "if prReReview enabled, dispatch
  IncrementalReview". the summaryHandlingCovered flag, the same-SHA/in-flight
  coordination it was protecting, and the summary-only Task fallback all
  delete cleanly.

UI / config:
- drop SummarizePRsTrigger (the toggle gated body splice; with that gone
  it has no behavior). drop sidebar entry, console import, Text icon import.
- drop prSummaryComment from triggers zod schema, prisma schema, preview
  settings script.

Migration: squash the two existing migrations into one timestamped
20260507000000_pr_summary_snapshot covering all three column changes
(add summarySnapshot on workflow_runs, drop prSummaryCommentInstructions
and prSummaryComment on repos). repo convention is one migration per PR.

Action: bump 0.0.203 -> 0.0.205 (payload contract changed: prSummaryToBody
removed; main is at 0.0.204).

Out-of-diff cleanup:
- review.ts:190 + review.test.ts:651 — "Reviewed — no issues found." ->
  "No new issues found." to match the canonical body in modes.ts.

Verified: pnpm typecheck clean, pnpm lint clean, postRun + review tests
pass, dev DB reset against production and the squashed migration applied
cleanly (summarySnapshot present, prSummaryComment / prSummaryCommentInstructions
both gone).

* re-orient snapshot toward functional summary; drop prior-review-feedback section

Empirical audit on preview-568 PR #5 showed the snapshot IS load-bearing
for the orchestrator: lens-dispatch prompts on incremental runs carried
forward context from the snapshot's risk register (e.g. "the JSDoc
explicitly scopes to code points — do not flag grapheme-cluster issues"
on the surrogate-pair fix run, "consistency with native padStart" on the
padStart-added run). The orchestrator was reading the snapshot, reasoning
about it, and using it to anti-prime / focus subagents — exactly the
high-leverage path. My earlier "snapshot is write-only" claim was wrong.

The shape, however, was steering it toward review-history-log instead of
functional summary. This commit re-orients:

- prSummary.ts: replace the four-section scaffold (~580 chars of placeholder
  italics under "What this PR does / Key changes / Risk / Reviewed in prior
  runs") with a minimal seed (~150 chars: just a header + a one-line
  comment about what the file is for). different PRs warrant different
  organization; forcing a refactor and a feature into the same template
  is procrustean. minimal seed also makes the unchanged-from-seed gate
  in persistSummary more sensitive.

- selectMode.ts addendum: rewrite around three principles. (1) the snapshot
  is a FUNCTIONAL summary of what the PR does and the risks it carries,
  not a chronological review log — commit history can already be
  reconstructed from list_pull_request_reviews. (2) the orchestrator should
  USE the snapshot during triage and dispatch — concrete example given of
  carrying snapshot context into subagent lens prompts. (3) structure is
  the agent's call; stable headings make snapshots range-diff cleanly when
  they fit, but riff when they don't.

- modes.ts IncrementalReview: drop the "Prior review feedback" checklist
  from the user-facing review body (step 6b gone, step 7 ELSE IFs cleaned
  up). It duplicated content that's already covered by the Reviewed-changes
  bullets and tracked durably in the snapshot for the next agent run; in
  the user-facing body it was noise. step 3 still fetches prior reviews
  but its role is now just filtering aggregation in step 5, not rendering.

- AGENTS.md: codify "no follow-ups" rule. when an issue is identified
  during code review, fix it in this PR — PR scope does not constrain
  quality. follow-up TODOs are forbidden as a substitute for doing the
  work now.

Empirical evidence supporting the re-orientation:

- Run 25568912293 (PR#5 incr1, surrogate-pair fix): orchestrator's
  correctness lens dispatch said "Do NOT flag grapheme-cluster issues
  — the JSDoc scopes to code points." The grapheme-cluster framing was
  not in the diff; it was downstream of the snapshot's prior risk-section
  framing of truncate's contract. Snapshot influencing dispatch.

- Run 25569054779 (PR#5 incr2, padStart added): orchestrator's correctness
  lens dispatch enumerated edge cases including "consistency with native
  String.prototype.padStart contract" and "fill = multi-code-point string
  (e.g. emoji)". Both threads carried over from the snapshot's prior
  truncate code-point-vs-code-unit discussion. Snapshot informing the
  shape of what was looked for.

The cost of maintaining the snapshot (~800 tokens, ~$0.005/run) is
trivially affordable when it materially improves orchestrator triage
on the 1-5 lenses dispatched per review.
2026-05-08 19:28:24 +00:00

176 lines
6.4 KiB
TypeScript

import { isAbsolute, resolve } from "node:path";
import * as core from "@actions/core";
import { type } from "arktype";
import type { AuthorPermission, PayloadEvent } from "../external.ts";
import packageJson from "../package.json" with { type: "json" };
import type { RepoSettings } from "./runContext.ts";
import { validateCompatibility } from "./versioning.ts";
// tool permission enum types for inputs
const ShellPermissionInput = type.enumerated("disabled", "restricted", "enabled");
const PushPermissionInput = type.enumerated("disabled", "restricted", "enabled");
// schema for JSON payload passed via prompt (internal dispatch invocation)
// note: permissions are intentionally NOT included here to prevent injection attacks
// permissions are derived from event.authorPermission instead
export const JsonPayload = type({
"~pullfrog": "true",
version: "string",
"model?": "string | undefined",
prompt: "string",
"triggerer?": "string | undefined",
"eventInstructions?": "string",
"event?": "object",
"timeout?": "string | undefined",
"progressComment?": type({
id: "string",
type: "'issue' | 'review'",
}).or("undefined"),
"generateSummary?": "boolean | undefined",
});
// permission levels that indicate collaborator status (have push access)
const COLLABORATOR_PERMISSIONS: AuthorPermission[] = ["admin", "maintain", "write"];
// check if the event author has collaborator-level permissions
function isCollaborator(event: PayloadEvent): boolean {
const perm = event.authorPermission;
return perm !== undefined && COLLABORATOR_PERMISSIONS.includes(perm);
}
// inputs schema - action inputs from core.getInput()
// note: tool permissions use .or("undefined") because getInput() || undefined
// explicitly sets the property to undefined when empty, which is different from
// the property being absent. arktype's "prop?" means "optional to include" but
// if included, must match the type - so we need to explicitly allow undefined.
export const Inputs = type({
prompt: "string",
"model?": type.string.or("undefined"),
"timeout?": type.string.or("undefined"),
"push?": PushPermissionInput.or("undefined"),
"shell?": ShellPermissionInput.or("undefined"),
"cwd?": type.string.or("undefined"),
"output_schema?": type.string.or("undefined"),
});
export type Inputs = typeof Inputs.infer;
function isPayloadEvent(value: unknown): value is PayloadEvent {
return typeof value === "object" && value !== null && "trigger" in value;
}
function resolveCwd(cwd: string | undefined): string | undefined {
const workspace = process.env.GITHUB_WORKSPACE;
if (!cwd) return workspace;
if (isAbsolute(cwd)) return cwd;
return workspace ? resolve(workspace, cwd) : cwd;
}
export type ResolvedPromptInput = string | typeof JsonPayload.infer;
export function resolvePromptInput(): ResolvedPromptInput {
const prompt = core.getInput("prompt", { required: true });
let parsed: unknown;
try {
parsed = JSON.parse(prompt);
} catch {
// JSON parse error is fine (plain text prompt)
return prompt;
}
if (!parsed || typeof parsed !== "object" || !("~pullfrog" in parsed)) {
// if it doesn't look like a pullfrog payload, return the plain text prompt
return prompt;
}
// validation errors should propagate
const jsonPayload = JsonPayload.assert(parsed);
validateCompatibility(jsonPayload.version, packageJson.version);
return jsonPayload;
}
function resolveNonPromptInputs() {
return Inputs.omit("prompt").assert({
model: core.getInput("model") || undefined,
timeout: core.getInput("timeout") || undefined,
cwd: core.getInput("cwd") || undefined,
push: core.getInput("push") || undefined,
shell: core.getInput("shell") || undefined,
});
}
const isPullfrog = (actor: string | null | undefined): boolean => {
actor = actor?.replace("[bot]", "");
return !!actor && (actor === "pullfrog" || actor === "pullfrogdev");
};
export function resolvePayload(
resolvedPromptInput: ResolvedPromptInput,
repoSettings: RepoSettings
) {
const [prompt, jsonPayload] =
typeof resolvedPromptInput !== "string"
? [resolvedPromptInput.prompt, resolvedPromptInput]
: [resolvedPromptInput, undefined];
const inputs = resolveNonPromptInputs();
// resolve event - use type guard for jsonPayload.event, fallback to unknown trigger
const rawEvent = jsonPayload?.event;
const event: PayloadEvent = isPayloadEvent(rawEvent) ? rawEvent : { trigger: "unknown" };
const model = jsonPayload?.model ?? inputs.model ?? repoSettings.model ?? undefined;
// determine shell permission - strictest setting wins
// precedence: disabled > restricted > enabled
// non-collaborators always get at least "restricted"
const isNonCollaborator = !isCollaborator(event);
const repoShell = repoSettings.shell ?? "restricted";
const inputShell = inputs.shell;
// resolve shell: start with repo setting, then apply restrictions
let resolvedShell = repoShell;
// input can only make it stricter (disabled > restricted > enabled)
if (inputShell === "disabled") {
resolvedShell = "disabled";
} else if (inputShell === "restricted" && resolvedShell === "enabled") {
resolvedShell = "restricted";
}
// non-collaborators get at least "restricted" (can't have "enabled")
if (isNonCollaborator && resolvedShell === "enabled") {
resolvedShell = "restricted";
}
// build payload - precedence: inputs > repoSettings > fallbacks
// note: modes are NOT in payload - they come from repoSettings in main()
return {
"~pullfrog": true as const,
version: jsonPayload?.version ?? packageJson.version,
model,
prompt,
triggerer:
jsonPayload?.triggerer ??
// it's not a common use case but GITHUB_ACTOR can be a user when the workflow is manually triggered by a user through GitHub Actions UI
(!isPullfrog(process.env.GITHUB_ACTOR) ? process.env.GITHUB_ACTOR : undefined),
eventInstructions: jsonPayload?.eventInstructions,
event,
timeout: inputs.timeout ?? jsonPayload?.timeout,
cwd: resolveCwd(inputs.cwd),
progressComment: jsonPayload?.progressComment,
generateSummary: jsonPayload?.generateSummary,
// permissions: inputs > repoSettings > fallbacks
push: inputs.push ?? repoSettings.push ?? "restricted",
shell: resolvedShell,
// set by proxy logic in main.ts when routing through OpenRouter
proxyModel: undefined as string | undefined,
};
}
export type ResolvedPayload = ReturnType<typeof resolvePayload>;