Files
AgentCompany/src/main/agent-runtime/runtime-bridge.ts
T
ZacharyZhang-NY 02ba887610 fix(runtime): stop gating pi tool calls; Co-Founder approvals live at API layer
The Co-Founder beforeToolCall hook (introduced in 77f81a7) gated every
non-readonly pi tool call as a `dangerous_command` approval. Because
agents call `POST /api/companies/:id/messages`, `/agents` (hire), and
every other company mutation via bash→node/curl, the first bash call in
every Co-Founder run got parked on a 30-minute approval timeout. Users
observed it as "agents never talk to each other" and "every bash command
waits for approval"; both symptoms are the same bug.

The business-level approval flow (`hire_agent`, `document_review`,
`plan_review`, etc. in execution-policy.ts) already gates the events
users actually care about, at the HTTP route layer where the event
originates (routes-agents.ts:368 for hiring, document routes for
deliverables). Stacking a pi-level hook on top was duplicate gating with
the wrong taxonomy.

Removed:
- src/main/agent-runtime/approval-hook.ts (entire file, 137 LOC)
- `beforeToolCall` conditional in worker-runner.ts and the
  corresponding RPC method in worker-types.ts and runtime-bridge.ts
- `approvalHook` field + `resolveApproval` callback + shutdown
  `cancelAll` in runtime-bridge.ts / service-graph-pi-runtime.ts /
  wire-api-server.ts

Unchanged:
- `dangerous_command` approval type itself (still used by automation
  workflows and routes-misc.ts)
- CEO mode (already never attached the hook)
- All business-level approval types and their wiring
2026-04-17 19:11:04 -04:00

381 lines
15 KiB
TypeScript

import type { AgentMessage } from "@mariozechner/pi-agent-core";
import type { AppDatabase } from "@main/database";
import type { DesktopEvent } from "@shared/types";
import { ensureTaskThread } from "@main/thread-integration/thread-helpers";
import { SqliteSessionStore } from "./sqlite-session-store";
import { CostWriter } from "./cost-writer";
import type { CredentialResolver } from "@main/credentials";
import { getConnectorDefinition } from "@main/connectors";
import { projectInboxMessageToPi } from "./inbox-projection";
/**
* Projects a pi AgentEvent to a human-readable log line for the Console.
* See pi-mono-reference/packages/agent/src/types.ts `AgentEvent` for the
* canonical union shape; this projection handles every type that carries
* user-visible activity.
*/
function projectAgentEventToLogChunk(
event: { type: string } & Record<string, unknown>,
): { stream: "stdout" | "stderr"; chunk: string } | null {
switch (event.type) {
case "agent_start":
return { stream: "stdout", chunk: "\n[agent:start]\n" };
case "turn_start":
return { stream: "stdout", chunk: "\n" };
case "turn_end":
return { stream: "stdout", chunk: "\n" };
case "message_start": {
const message = event.message as { role?: string; content?: unknown } | undefined;
if (message?.role === "user") {
const body = extractMessageText(message);
if (!body) return null;
return { stream: "stdout", chunk: `[user] ${body}\n` };
}
return null;
}
case "message_update": {
// Streaming assistant deltas — `assistantMessageEvent.type` carries
// the intra-turn stream protocol from pi-ai (text_delta /
// thinking_delta / toolcall_start / ...). We surface text and
// thinking deltas verbatim so the Console shows live output.
const inner = event.assistantMessageEvent as
| ({ type?: string; delta?: string; content?: string } & Record<string, unknown>)
| undefined;
if (!inner) return null;
if (inner.type === "text_delta" && typeof inner.delta === "string" && inner.delta.length > 0) {
return { stream: "stdout", chunk: inner.delta };
}
if (inner.type === "thinking_delta" && typeof inner.delta === "string" && inner.delta.length > 0) {
return { stream: "stdout", chunk: inner.delta };
}
return null;
}
case "message_end": {
// The final assistant message is already fully rendered via
// preceding message_update deltas; emit a trailing newline so the
// next turn starts on its own line.
return { stream: "stdout", chunk: "\n" };
}
case "tool_execution_start": {
const toolName = typeof event.toolName === "string" ? event.toolName : "tool";
const argsPreview = summariseJson(event.args, 200);
return { stream: "stdout", chunk: `\n[tool:${toolName}] ${argsPreview}\n` };
}
case "tool_execution_end": {
const toolName = typeof event.toolName === "string" ? event.toolName : "tool";
const isError = event.isError === true;
const resultPreview = summariseJson(event.result, 300);
const tag = isError ? "tool:error" : "tool:done";
return { stream: isError ? "stderr" : "stdout", chunk: `[${tag}:${toolName}] ${resultPreview}\n` };
}
case "agent_end":
return { stream: "stdout", chunk: "\n[agent:end]\n" };
default:
return null;
}
}
/**
* Pulls plain text out of a pi AgentMessage's content array. User messages
* carry `content: [{ type: "text", text: "..." }]` per pi's AgentMessage
* schema; other content types (image, tool_result, etc.) are ignored here.
*/
function extractMessageText(message: { content?: unknown }): string {
const content = message.content;
if (typeof content === "string") return content;
if (!Array.isArray(content)) return "";
const parts: string[] = [];
for (const block of content) {
if (block && typeof block === "object" && (block as { type?: string }).type === "text") {
const text = (block as { text?: string }).text;
if (typeof text === "string") parts.push(text);
}
}
return parts.join("");
}
function summariseJson(value: unknown, maxLength: number): string {
if (value === undefined || value === null) return "";
try {
const json = typeof value === "string" ? value : JSON.stringify(value);
if (json.length <= maxLength) return json;
return `${json.slice(0, maxLength - 3)}...`;
} catch {
return "<unserialisable>";
}
}
export interface RuntimeBridgeDeps {
db: AppDatabase;
emitEvent: (event: DesktopEvent) => void;
logger: {
info: (...args: unknown[]) => void;
warn: (...args: unknown[]) => void;
error: (...args: unknown[]) => void;
};
credentialResolver: CredentialResolver;
}
interface ActiveRunContext {
runId: string;
agentId: string;
companyId: string;
taskId: string | null;
connectorId: string;
modelId: string;
taskSessionId: string;
}
/**
* Single owner of pi runtime side-effects in main.
*
* - Forwards `agent-event` from the worker to the renderer (push channel).
* - Persists each `message_end` message via `SqliteSessionStore`.
* - Calls `CostWriter` for assistant messages with usage.
*
* Co-Founder mode's human-review gates live at the API endpoint layer
* (hire_agent / document_review approvals created by `routes-*.ts`), not
* at the pi tool-call layer; the worker constructs `Agent` without a
* `beforeToolCall` hook in either mode.
*/
export class RuntimeBridge {
private readonly costWriter: CostWriter;
private readonly activeRuns = new Map<string, ActiveRunContext>();
private readonly sessionStores = new Map<string, SqliteSessionStore>();
constructor(private readonly deps: RuntimeBridgeDeps) {
this.costWriter = new CostWriter({ db: deps.db });
}
private registerActiveRun(context: ActiveRunContext): void {
this.activeRuns.set(context.runId, context);
this.getOrCreateStore(context.taskSessionId);
}
/**
* Evicts the per-run `activeRuns` context and the per-session store cache.
* Callers must invoke after a `run-finished` worker message so the maps
* stay bounded by concurrent-run count rather than process lifetime.
*/
releaseRunResources(runId: string): void {
const ctx = this.activeRuns.get(runId);
this.activeRuns.delete(runId);
if (ctx) this.sessionStores.delete(ctx.taskSessionId);
}
private getOrCreateStore(taskSessionId: string): SqliteSessionStore {
const existing = this.sessionStores.get(taskSessionId);
if (existing) return existing;
const store = new SqliteSessionStore(this.deps.db, taskSessionId);
this.sessionStores.set(taskSessionId, store);
return store;
}
/**
* Resolve a display name for an agent id used in inbox header lines.
* Falls back to the id when the lookup fails so the transcript remains
* unambiguous instead of silently rendering "undefined".
*/
private resolveAgentName(agentId: string): string {
try {
const name = this.deps.db.findAgentName(agentId);
if (name && name.length > 0) return name;
} catch (error) {
this.deps.logger.warn(
`[runtime-bridge] agent name lookup failed for ${agentId}: ${error instanceof Error ? error.message : String(error)}`,
);
}
return agentId;
}
/** Receives an `agent-event` envelope from the worker; emits to renderer. */
handleAgentEvent(envelope: {
runId: string;
agentId: string;
companyId: string;
taskId: string | null;
emittedAt: string;
event: { type: string } & Record<string, unknown>;
}): void {
this.deps.emitEvent({
type: "agent-event",
runId: envelope.runId,
agentId: envelope.agentId,
companyId: envelope.companyId,
taskId: envelope.taskId,
emittedAt: envelope.emittedAt,
event: envelope.event,
});
const logChunk = projectAgentEventToLogChunk(envelope.event);
if (logChunk) {
this.deps.emitEvent({
type: "run-log",
runId: envelope.runId,
stream: logChunk.stream,
chunk: logChunk.chunk,
});
}
if (envelope.event.type === "message_end") {
const ctx = this.activeRuns.get(envelope.runId);
const messageRaw = envelope.event.message as
| { role?: string; usage?: unknown; content?: unknown; toolCallId?: string }
| undefined;
if (ctx && messageRaw?.role === "assistant" && messageRaw.usage) {
try {
this.costWriter.observeAssistantMessage({
runId: ctx.runId,
companyId: ctx.companyId,
agentId: ctx.agentId,
taskId: ctx.taskId,
connectorId: ctx.connectorId,
modelId: ctx.modelId,
usage: messageRaw.usage as never,
});
} catch (error) {
// Cost writer fails closed (RUNTIME-105) — surface the failure
// loudly so operators can see a pricing catalog break, but let
// the run continue so the agent's work is not lost. The missing
// row means budget enforcement under-counts this message; a
// repeated failure in the same run is still visible in logs.
this.deps.logger.error(
`[runtime-bridge] cost recording failed for run ${ctx.runId}: ${error instanceof Error ? error.message : String(error)}`,
);
}
}
this.recordThreadEvent(envelope, messageRaw);
}
}
/**
* Project the pi `message_end` event into the task thread as a
* `conversation_events` row so renderer thread views stay live.
* Best-effort: thread persistence failures must not interrupt the run.
*/
private recordThreadEvent(
envelope: { runId: string; agentId: string; companyId: string; taskId: string | null },
message: { role?: string; content?: unknown; toolCallId?: string } | undefined,
): void {
if (!envelope.taskId || !message?.role) return;
let task: { title: string } | null = null;
try {
task = this.deps.db.getTask(envelope.taskId);
} catch (err) {
this.deps.logger.warn(`[runtime-bridge] getTask failed for ${envelope.taskId} in recordThreadEvent:`, err instanceof Error ? err.message : String(err));
return;
}
if (!task) return;
try {
const thread = ensureTaskThread(this.deps.db, envelope.taskId, envelope.companyId, task.title);
const body = extractTextBody(message.content);
const actorType: "agent" | "user" | "system" = message.role === "user"
? "user"
: message.role === "assistant"
? "agent"
: "system";
this.deps.db.addThreadEvent({
threadId: thread.id,
actorId: envelope.agentId,
actorType,
eventType: message.role === "toolResult" ? "system_note" : "message",
body: body.length > 4000 ? `${body.slice(0, 3997)}...` : body,
metadataJson: JSON.stringify({ runId: envelope.runId, role: message.role }),
});
} catch (error) {
this.deps.logger.warn(
`[runtime-bridge] failed to project agent-event into thread for task ${envelope.taskId}: ${
error instanceof Error ? error.message : String(error)
}`,
);
}
}
/** Handles RPC requests issued by the worker (`rpc-request` envelope). */
async handleRpc(request: {
rpcId: string;
method: "persistMessage" | "prepareRun";
runId: string;
payload: unknown;
}): Promise<{ ok: true; result: unknown } | { ok: false; error: string }> {
try {
if (request.method === "persistMessage") {
const payload = request.payload as { taskSessionId: string; message: AgentMessage };
this.getOrCreateStore(payload.taskSessionId).appendMessage(payload.message);
return { ok: true, result: undefined };
}
if (request.method === "prepareRun") {
const payload = request.payload as {
connectorId: string;
taskSessionId: string;
agentId: string;
companyId: string;
taskId: string | null;
modelId: string;
};
this.registerActiveRun({
runId: request.runId,
agentId: payload.agentId,
companyId: payload.companyId,
taskId: payload.taskId,
connectorId: payload.connectorId,
modelId: payload.modelId,
taskSessionId: payload.taskSessionId,
});
const definition = getConnectorDefinition(payload.connectorId);
const resolved = await this.deps.credentialResolver.resolve(payload.connectorId);
// Project any pending inbox messages into the session transcript
// *before* loading priorMessages — the recipient must observe them
// as plain user turns in its context, and the transcript row is
// the single source of memory (recentMessages prompt block is
// gone). Append fails closed: if persistence throws, the inbox
// row stays unread and we surface the error so the worker aborts.
const store = this.getOrCreateStore(payload.taskSessionId);
const inboxRecords = this.deps.db.listAgentInboxUnread(payload.companyId, payload.agentId);
for (const record of inboxRecords) {
const projected = projectInboxMessageToPi(record, {
getAgentName: (id) => this.resolveAgentName(id),
});
store.appendMessage(projected);
}
if (inboxRecords.length > 0) {
this.deps.db.markAgentInboxDelivered(
payload.agentId,
inboxRecords.map((r) => r.id),
);
}
const priorMessages = store.loadMessages();
return {
ok: true,
result: {
provider: definition.provider,
apiKey: resolved.apiKey,
extraEnv: resolved.extraEnv ?? {},
priorMessages,
},
};
}
return { ok: false, error: `Unknown RPC method: ${(request as { method: string }).method}` };
} catch (error) {
return { ok: false, error: error instanceof Error ? error.message : String(error) };
}
}
}
/** Best-effort textual rendering of a pi message's content for thread rows. */
function extractTextBody(content: unknown): string {
if (typeof content === "string") return content;
if (!Array.isArray(content)) return "";
const parts: string[] = [];
for (const block of content) {
if (!block || typeof block !== "object") continue;
const obj = block as { type?: string; text?: string; thinking?: string; name?: string };
if (obj.type === "text" && typeof obj.text === "string") parts.push(obj.text);
else if (obj.type === "thinking" && typeof obj.thinking === "string") parts.push(`[thinking] ${obj.thinking}`);
else if (obj.type === "toolCall" && typeof obj.name === "string") parts.push(`[tool:${obj.name}]`);
}
return parts.join("\n").trim();
}