Files
shockbot/external.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

290 lines
8.7 KiB
TypeScript

/**
* ⚠️ LIMITED IMPORTS - this file is imported by Next.js and must avoid pulling in backend code.
* All shared constants, types, and data used by both the Next.js app and the action runtime live here.
* Other files in action/ re-export from this file for backward compatibility.
*/
// mcp name constant
export const pullfrogMcpName = "pullfrog";
/** @see {@link file://./agents/shared.ts} Agent interface that uses this type */
export type AgentId = "claude" | "opencode";
/**
* format a tool name the way each agent's MCP client presents it to the model.
* claude code: mcp__pullfrog__select_mode
* opencode: pullfrog_select_mode
*/
export function formatMcpToolRef(agentId: AgentId, toolName: string): string {
switch (agentId) {
case "claude":
return `mcp__${pullfrogMcpName}__${toolName}`;
case "opencode":
return `${pullfrogMcpName}_${toolName}`;
default:
return agentId satisfies never;
}
}
// model alias registry lives in models.ts — re-exported here for shared access
export type { ModelAlias, ModelProvider, ProviderConfig } from "./models.ts";
export {
getModelEnvVars,
getModelProvider,
getProviderDisplayName,
modelAliases,
parseModel,
providers,
resolveCliModel,
resolveDisplayAlias,
resolveModelSlug,
resolveOpenRouterModel,
} from "./models.ts";
// tool permission types shared with server dispatch
export type ToolPermission = "disabled" | "enabled";
export type ShellPermission = "disabled" | "restricted" | "enabled";
export type PushPermission = "disabled" | "restricted" | "enabled";
// workflow yml permissions for GITHUB_TOKEN
export type WorkflowPermissionValue = "read" | "write" | "none";
export type WorkflowIdTokenPermissionValue = "write" | "none";
export interface WorkflowPermissions {
actions?: WorkflowPermissionValue;
attestations?: WorkflowPermissionValue;
checks?: WorkflowPermissionValue;
contents?: WorkflowPermissionValue;
deployments?: WorkflowPermissionValue;
discussions?: WorkflowPermissionValue;
"id-token"?: WorkflowIdTokenPermissionValue;
issues?: WorkflowPermissionValue;
models?: WorkflowPermissionValue;
packages?: WorkflowPermissionValue;
pages?: WorkflowPermissionValue;
"pull-requests"?: WorkflowPermissionValue;
"repository-projects"?: WorkflowPermissionValue;
"security-events"?: WorkflowPermissionValue;
statuses?: WorkflowPermissionValue;
}
// permission level for the author who triggered the event
// matches GitHub's permission levels: admin > write > maintain > triage > read > none
export type AuthorPermission = "admin" | "maintain" | "write" | "triage" | "read" | "none";
// base interface for common payload event fields
interface BasePayloadEvent {
issue_number?: number;
is_pr?: boolean;
branch?: string;
/** title of the issue/PR (or contextual title for comments) */
title?: string;
/** primary content for this trigger (issue body, PR body, comment body, review body, etc.) */
body?: string | null;
comment_id?: number;
review_id?: number;
review_state?: string;
thread?: any;
pull_request?: any;
check_suite?: {
id: number;
head_sha: string;
head_branch: string | null;
status: string | null;
conclusion: string | null;
url: string;
};
comment_ids?: number[] | "all";
/** permission level of the user who triggered this event */
authorPermission?: AuthorPermission;
/** when true, runs silently without progress comments (e.g., auto-labeling) */
silent?: boolean;
[key: string]: any;
}
interface PullRequestOpenedEvent extends BasePayloadEvent {
trigger: "pull_request_opened";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
}
interface PullRequestReadyForReviewEvent extends BasePayloadEvent {
trigger: "pull_request_ready_for_review";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
}
interface PullRequestReviewRequestedEvent extends BasePayloadEvent {
trigger: "pull_request_review_requested";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
}
interface PullRequestReviewSubmittedEvent extends BasePayloadEvent {
trigger: "pull_request_review_submitted";
issue_number: number;
is_pr: true;
review_id: number;
/** review body is the primary content */
body: string | null;
review_state: string;
branch: string;
}
interface PullRequestReviewCommentCreatedEvent extends BasePayloadEvent {
trigger: "pull_request_review_comment_created";
issue_number: number;
is_pr: true;
title: string;
comment_id: number;
/** comment body is the primary content (null if already in prompt) */
body: string | null;
thread?: any;
branch: string;
}
interface IssuesOpenedEvent extends BasePayloadEvent {
trigger: "issues_opened";
issue_number: number;
title: string;
body: string | null;
}
interface IssuesAssignedEvent extends BasePayloadEvent {
trigger: "issues_assigned";
issue_number: number;
title: string;
body: string | null;
}
interface IssuesLabeledEvent extends BasePayloadEvent {
trigger: "issues_labeled";
issue_number: number;
title: string;
body: string | null;
}
interface IssueCommentCreatedEvent extends BasePayloadEvent {
trigger: "issue_comment_created";
comment_id: number;
/** distinguishes this from PR review comments (which use pull_request_review_comment_created) */
comment_type: "issue";
/** comment body is the primary content (null if already in prompt) */
body: string | null;
issue_number: number;
// PR-specific fields (only present when is_pr is true)
is_pr?: true;
branch?: string;
title?: string;
}
interface CheckSuiteCompletedEvent extends BasePayloadEvent {
trigger: "check_suite_completed";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
pull_request: any;
branch: string;
check_suite: {
id: number;
head_sha: string;
head_branch: string | null;
status: string | null;
conclusion: string | null;
url: string;
};
}
interface WorkflowDispatchEvent extends BasePayloadEvent {
trigger: "workflow_dispatch";
}
interface FixReviewEvent extends BasePayloadEvent {
trigger: "fix_review";
issue_number: number;
is_pr: true;
review_id: number;
/** when true, only address comments the triggerer approved with 👍 (vs all comments) */
approved_only?: boolean | undefined;
}
interface ImplementPlanEvent extends BasePayloadEvent {
trigger: "implement_plan";
issue_number: number;
plan_comment_id: number;
/** plan content is the primary content (null if already in prompt) */
body: string | null;
}
interface PullRequestSynchronizeEvent extends BasePayloadEvent {
trigger: "pull_request_synchronize";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
/** SHA before the push -- used to compute incremental range-diff between PR versions */
before_sha: string;
}
interface UnknownEvent extends BasePayloadEvent {
trigger: "unknown";
}
// discriminated union for payload event based on trigger
// note: all events use issue_number for consistency (PRs are issues in GitHub's API)
export type PayloadEvent =
| PullRequestOpenedEvent
| PullRequestReadyForReviewEvent
| PullRequestSynchronizeEvent
| PullRequestReviewRequestedEvent
| PullRequestReviewSubmittedEvent
| PullRequestReviewCommentCreatedEvent
| IssuesOpenedEvent
| IssuesAssignedEvent
| IssuesLabeledEvent
| IssueCommentCreatedEvent
| CheckSuiteCompletedEvent
| WorkflowDispatchEvent
| FixReviewEvent
| ImplementPlanEvent
| UnknownEvent;
// writeable payload type for building payloads
export interface WriteablePayload {
"~pullfrog": true;
/** semantic version of the payload to ensure compatibility */
version: string;
/** provider/model slug (e.g. "anthropic/claude-opus") */
model?: string | undefined;
/** the user's actual request (body if @pullfrog tagged) */
prompt: string;
/** github username of the human who triggered this workflow run */
triggerer?: string | undefined;
/** event-level instructions for this trigger type (flag-expanded server-side) */
eventInstructions?: string | undefined;
/** event data from webhook payload - discriminated union based on trigger field */
event: PayloadEvent;
/** timeout for agent run (e.g., "10m", "1h30m") - defaults to "1h" */
timeout?: string | undefined;
/** working directory for the agent */
cwd?: string | undefined;
/** pre-created progress comment (ID + type) for updating status */
progressComment?: { id: string; type: "issue" | "review" } | undefined;
/** when true, seed the PR summary tmpfile + persist edits at run end */
generateSummary?: boolean | undefined;
}
// immutable payload type for agent execution
export type Payload = Readonly<WriteablePayload>;