Files
shockbot/main.ts
T
David Blass 64f2238316 Repo Intelligence: agent-managed per-repo learnings with revision history (#487)
* add repo learnings feature with edit history

introduces a new "Learnings" section in the repo console where agents can
persist operational knowledge (setup steps, test commands, conventions) at
the end of runs via an MCP tool. users can also edit learnings manually.

- add `learnings` field to Repo model and `LearningsRevision` audit table
- add `update_learnings` MCP tool for agents to persist repo knowledge
- integrate learnings into prompt assembly as REPO LEARNINGS section
- add learnings step to mode guidance (Build, AddressReviews, Plan, Fix, Task)
- add PATCH /api/repo/[owner]/[repo]/learnings endpoint (JWT auth)
- add GET /api/repo/[owner]/[repo]/learnings/history endpoint (Clerk auth)
- add LearningsSection component with textarea, save-on-blur, and history modal
- record revision history with actor tracking (agent vs user) and pruning (50 max)
- gate UI behind owner === "pullfrog" for internal dogfooding

Made-with: Cursor

* fix prisma enum import path for LearningsActor

Made-with: Cursor

* simplify learnings schema: remove LearningsActor enum, store model name directly

the actor/actorName split was unnecessary — learnings are only written by
agents so the revision table just needs a model column. removes all user
editing concepts from schema, API, and frontend.

Made-with: Cursor

* fix migration: add separate migration instead of rewriting existing one

restores original learnings_revisions migration and adds a new migration
that drops actor/actorName columns, backfills model from actorName, and
drops the LearningsActor enum.

Made-with: Cursor

* polish learnings feature: rename to Repo Intelligence, fix atomicity, fix review skip

- rename user-facing "learnings" to "Repo Intelligence" (UI, prompt section, wiki, sidebar)
- simplify description to "Automatically discovered by the agent across runs."
- wrap repo.update + revision create in $transaction for atomicity
- refactor recordLearningsRevision to pruneLearningsRevisions (prune-only)
- fix empty review skip: don't block APPROVE reviews with no body
- fix broken docs anchor: #free-options → #free-models
- update agent guidance to require flat bullet list format with pruning
- add accessibility: aria-expanded, sr-only loading, output element
- add chevron rotation, stale data clear on modal close, max-h scroll
- trim + length-limit model field, remove type cast, restore pre-existing comment
- update wiki prompt examples with actual bullet-formatted content
- update model test snapshot

Made-with: Cursor

* fix stale free model name in docs, rename utility file to match export

- docs/keys.mdx: MiMo V2 Flash → MiMo V2 Pro (matches model code change)
- rename recordLearningsRevision.ts → pruneLearningsRevisions.ts

Made-with: Cursor

* Add skill, .neon

* polish learnings UI and remove verbose log

- learnings code block: read-only appearance with muted text, copy button, rounded corners
- history modal: full-width rows with cursor-pointer, chevron moved to right, no preview text
- drop noisy update_learnings log line

Made-with: Cursor

* inject learningsStep into all modes, drop seed script, soften revision styling

Made-with: Cursor

* Drop seed

---------

Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
2026-03-25 19:15:43 +00:00

414 lines
14 KiB
TypeScript

// changes to tool permissions should be reflected in wiki/granular-tools.md
import * as core from "@actions/core";
import {
initToolState,
startMcpHttpServer,
type ToolContext,
type ToolState,
} from "./mcp/server.ts";
import { computeModes } from "./modes.ts";
import {
type ActivityTimeout,
createProcessOutputActivityTimeout,
DEFAULT_ACTIVITY_CHECK_INTERVAL_MS,
DEFAULT_ACTIVITY_TIMEOUT_MS,
} from "./utils/activity.ts";
import { resolveAgent } from "./utils/agent.ts";
import { apiFetch } from "./utils/apiFetch.ts";
import { validateAgentApiKey } from "./utils/apiKeys.ts";
import { resolveBody } from "./utils/body.ts";
import { formatUsageSummary, log, writeSummary } from "./utils/cli.ts";
import { reportErrorToComment } from "./utils/errorReport.ts";
import { onExitSignal } from "./utils/exitHandler.ts";
import { resolveGit, setGitAuthServer } from "./utils/gitAuth.ts";
import { startGitAuthServer } from "./utils/gitAuthServer.ts";
import { createOctokit, writeGitHubUsageSummaryToFile } from "./utils/github.ts";
import { resolveInstructions } from "./utils/instructions.ts";
import { executeLifecycleHook } from "./utils/lifecycle.ts";
import { normalizeEnv } from "./utils/normalizeEnv.ts";
import { resolvePayload, resolvePromptInput } from "./utils/payload.ts";
import { postReviewCleanup } from "./utils/reviewCleanup.ts";
import { handleAgentResult } from "./utils/run.ts";
import { resolveRunContextData } from "./utils/runContextData.ts";
import { createTempDirectory, setupGit } from "./utils/setup.ts";
import { killTrackedChildren } from "./utils/subprocess.ts";
import { parseTimeString, TIMEOUT_DISABLED } from "./utils/time.ts";
import { Timer } from "./utils/timer.ts";
import { getJobToken, resolveTokens } from "./utils/token.ts";
import { resolveRun } from "./utils/workflow.ts";
export { Inputs } from "./utils/payload.ts";
export interface MainResult {
success: boolean;
output?: string | undefined;
error?: string | undefined;
result?: string | undefined;
}
function resolveOutputSchema(): Record<string, unknown> | undefined {
const raw = core.getInput("output_schema");
if (!raw) return undefined;
let parsed: unknown;
try {
parsed = JSON.parse(raw);
} catch {
throw new Error(`invalid output_schema: not valid JSON`);
}
if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) {
throw new Error(`invalid output_schema: must be a JSON object`);
}
log.info("» structured output schema provided — output will be required");
return parsed as Record<string, unknown>;
}
import type { ResolvedPayload } from "./utils/payload.ts";
interface OidcCredentials {
requestUrl: string;
requestToken: string;
}
async function mintProxyKey(ctx: { oidcCredentials: OidcCredentials }): Promise<string | null> {
try {
process.env.ACTIONS_ID_TOKEN_REQUEST_URL = ctx.oidcCredentials.requestUrl;
process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN = ctx.oidcCredentials.requestToken;
const oidcToken = await core.getIDToken("pullfrog-api");
delete process.env.ACTIONS_ID_TOKEN_REQUEST_URL;
delete process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN;
const response = await apiFetch({
path: "/api/proxy-token",
method: "POST",
headers: { Authorization: `Bearer ${oidcToken}` },
});
if (!response.ok) {
log.warning(`proxy key mint failed (${response.status})`);
return null;
}
const data = (await response.json()) as { key: string };
return data.key;
} catch (error) {
log.warning(`proxy key mint error: ${error instanceof Error ? error.message : String(error)}`);
return null;
} finally {
delete process.env.ACTIONS_ID_TOKEN_REQUEST_URL;
delete process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN;
}
}
async function resolveProxyModel(ctx: {
payload: ResolvedPayload;
oss: boolean;
proxyModel?: string | undefined;
oidcCredentials: OidcCredentials | null;
}): Promise<void> {
// env override = BYOK escape hatch, don't proxy
if (process.env.PULLFROG_MODEL?.trim()) return;
// OSS: server decided the model
if (ctx.oss && ctx.proxyModel) {
if (!ctx.oidcCredentials) {
log.warning("» oss repo but no OIDC credentials available — skipping proxy");
return;
}
const key = await mintProxyKey({ oidcCredentials: ctx.oidcCredentials });
if (!key) return;
process.env.OPENROUTER_API_KEY = key;
core.setSecret(key);
ctx.payload.proxyModel = ctx.proxyModel;
log.info(`» proxy: oss → ${ctx.proxyModel}`);
return;
}
// managed billing will add its path here later
}
async function writeJobSummary(toolState: ToolState): Promise<void> {
const usageSummary = formatUsageSummary(toolState.usageEntries);
const summaryParts = [toolState.lastProgressBody, usageSummary].filter(Boolean);
if (summaryParts.length > 0) {
await writeSummary(summaryParts.join("\n\n"));
}
}
export async function main(): Promise<MainResult> {
// normalize env var names to uppercase (handles case-insensitive workflow files)
normalizeEnv();
// write usage summary on SIGINT/SIGTERM so the worker can read it after sandbox.exec
const usageSummaryPath = process.env.PULLFROG_USAGE_SUMMARY_PATH;
if (usageSummaryPath) {
onExitSignal(() => writeGitHubUsageSummaryToFile(usageSummaryPath));
}
const timer = new Timer();
let activityTimeout: ActivityTimeout | null = null;
// parse prompt early to extract progressCommentId for toolState
const resolvedPromptInput = resolvePromptInput();
const toolState = initToolState({
progressCommentId:
typeof resolvedPromptInput !== "string" ? resolvedPromptInput.progressCommentId : undefined,
});
// resolve and fingerprint git binary before any agent code runs
resolveGit();
// get job token for initial API calls
const jobToken = getJobToken();
const initialOctokit = createOctokit(jobToken);
const runContext = await resolveRunContextData({ octokit: initialOctokit, token: jobToken });
timer.checkpoint("runContextData");
// resolve payload to determine shell permission
const payload = resolvePayload(resolvedPromptInput, runContext.repoSettings);
toolState.model = payload.model;
// resolve tokens first — acquireNewToken needs OIDC env vars for token exchange
await using tokenRef = await resolveTokens({ push: payload.push });
// stash OIDC credentials in memory before wiping from process.env
// the agent's shell commands can't access JS variables, so this is safe
const oidcCredentials: OidcCredentials | null =
process.env.ACTIONS_ID_TOKEN_REQUEST_URL && process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN
? {
requestUrl: process.env.ACTIONS_ID_TOKEN_REQUEST_URL,
requestToken: process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN,
}
: null;
// clear OIDC env vars in restricted mode to prevent agent from minting tokens
if (payload.shell !== "enabled") {
delete process.env.ACTIONS_ID_TOKEN_REQUEST_URL;
delete process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN;
}
// proxy decision: mint an OpenRouter key for OSS repos (or later, managed billing)
await resolveProxyModel({
payload,
oss: runContext.oss,
proxyModel: runContext.proxyModel,
oidcCredentials,
});
// create octokit with MCP token for GitHub API calls
const octokit = createOctokit(tokenRef.mcpToken);
const runInfo = await resolveRun({ octokit });
let toolContext: ToolContext | undefined;
try {
if (payload.cwd && process.cwd() !== payload.cwd) {
process.chdir(payload.cwd);
}
// resolve body - fetches body_html and converts to markdown if images present
// this ensures agents receive markdown with working signed image URLs
const originalBody = payload.event.body;
const resolvedBody = await resolveBody({
event: payload.event,
octokit,
repo: runContext.repo,
});
if (resolvedBody !== originalBody) {
payload.event.body = resolvedBody;
// also update prompt if original body was included there
if (originalBody && payload.prompt.includes(originalBody)) {
payload.prompt = payload.prompt.replace(originalBody, resolvedBody ?? "");
}
}
const tmpdir = createTempDirectory();
await using gitAuthServer = await startGitAuthServer(tmpdir);
setGitAuthServer(gitAuthServer);
const agent = resolveAgent();
validateAgentApiKey({
agent,
model: payload.proxyModel ?? payload.model,
owner: runContext.repo.owner,
name: runContext.repo.name,
});
await setupGit({
gitToken: tokenRef.gitToken,
owner: runContext.repo.owner,
name: runContext.repo.name,
octokit,
toolState,
shell: payload.shell,
postCheckoutScript: runContext.repoSettings.postCheckoutScript,
});
timer.checkpoint("git");
// execute setup lifecycle hook (runs once at initialization)
await executeLifecycleHook({
event: "setup",
script: runContext.repoSettings.setupScript,
});
timer.checkpoint("lifecycleHooks::setup");
const modes = [...computeModes(), ...runContext.repoSettings.modes];
const outputSchema = resolveOutputSchema();
// mcpServerUrl and tmpdir are set after server starts
toolContext = {
repo: runContext.repo,
payload,
octokit,
githubInstallationToken: tokenRef.mcpToken,
gitToken: tokenRef.gitToken,
apiToken: runContext.apiToken,
modes,
postCheckoutScript: runContext.repoSettings.postCheckoutScript,
prApproveEnabled: runContext.repoSettings.prApproveEnabled,
modeInstructions: runContext.repoSettings.modeInstructions,
toolState,
runId: runInfo.runId,
jobId: runInfo.jobId,
mcpServerUrl: "",
tmpdir,
};
await using mcpHttpServer = await startMcpHttpServer(toolContext, { outputSchema });
toolContext.mcpServerUrl = mcpHttpServer.url;
log.info(`» MCP server started at ${mcpHttpServer.url}`);
timer.checkpoint("mcpServer");
const instructions = resolveInstructions({
payload,
repo: runContext.repo,
modes,
outputSchema,
learnings: runContext.repoSettings.learnings,
});
// log instructions as soon as they are fully resolved
const logParts = [
instructions.eventInstructions
? `EVENT-LEVEL INSTRUCTIONS:\n${instructions.eventInstructions}`
: null,
instructions.user ? `USER REQUEST:\n${instructions.user}` : null,
instructions.event,
].filter(Boolean);
log.box(logParts.join("\n\n---\n\n"), {
title: "Instructions",
});
// run agent, optionally with timeout enforcement
activityTimeout = createProcessOutputActivityTimeout({
timeoutMs: DEFAULT_ACTIVITY_TIMEOUT_MS,
checkIntervalMs: DEFAULT_ACTIVITY_CHECK_INTERVAL_MS,
});
activityTimeout.promise.catch(() => {}); // prevent unhandled rejection if agent wins race
const agentPromise = agent.run({
payload,
mcpServerUrl: mcpHttpServer.url,
tmpdir,
instructions,
});
// timeout enforcement: default is 1 hour, but can be overridden via flags in the prompt:
// - --timeout=2h (or any duration like "--timeout=30m", "--timeout=1h30m") to set a custom timeout
// - --notimeout to disable timeout entirely
let result: Awaited<typeof agentPromise>;
if (payload.timeout === TIMEOUT_DISABLED) {
result = await Promise.race([agentPromise, activityTimeout.promise]);
} else {
const parsed = payload.timeout ? parseTimeString(payload.timeout) : null;
if (payload.timeout && parsed === null) {
log.warning(`invalid timeout format "${payload.timeout}", using default 1h`);
}
const timeoutMs = parsed ?? 3600000;
const actualTimeout = parsed !== null ? payload.timeout : "1h";
let timeoutId: NodeJS.Timeout | undefined;
const timeoutPromise = new Promise<never>((_, reject) => {
timeoutId = setTimeout(() => {
reject(new Error(`agent run timed out after ${actualTimeout}`));
}, timeoutMs);
});
timeoutPromise.catch(() => {}); // prevent unhandled rejection if agent wins race
try {
result = await Promise.race([agentPromise, timeoutPromise, activityTimeout.promise]);
} finally {
clearTimeout(timeoutId);
}
}
// accumulate top-level agent usage
if (result.usage) {
toolState.usageEntries.push(result.usage);
}
// validate this before writing job summary to avoid masking the error
if (outputSchema && !toolState.output) {
throw new Error(
"output_schema was provided but agent did not call set_output — structured output is required"
);
}
// post-agent review cleanup: reportReviewNodeId → follow-up dispatch → delete progress comment.
// runs after the agent exits so ordering is architecturally guaranteed (no LLM involvement).
// best-effort: cleanup failures must not turn a successful agent run into a failure.
if (toolContext) {
await postReviewCleanup(toolContext).catch((error) => {
log.debug(`post-review cleanup failed: ${error}`);
});
}
await writeJobSummary(toolState);
// emit structured output marker for test validation
if (toolState.output) {
log.info(`::pullfrog-output::${Buffer.from(toolState.output).toString("base64")}`);
core.setOutput("result", toolState.output);
}
return await handleAgentResult({
result,
toolState,
silent: payload.event.silent ?? false,
});
} catch (error) {
const errorMessage = error instanceof Error ? error.message : "unknown error occurred";
killTrackedChildren();
log.error(errorMessage);
// best-effort summary — don't mask the original error
try {
await writeJobSummary(toolState);
} catch {}
try {
await reportErrorToComment({ toolState, error: errorMessage });
} catch {
// error reporting failed, but don't let it mask the original error
}
// best-effort review cleanup (e.g., agent timed out after submitting a review)
if (toolContext) {
await postReviewCleanup(toolContext).catch((error) => {
log.debug(`post-review cleanup failed: ${error}`);
});
}
return {
success: false,
error: errorMessage,
};
} finally {
activityTimeout?.stop();
if (usageSummaryPath) {
await writeGitHubUsageSummaryToFile(usageSummaryPath);
}
}
}