refactor delegation system, add PR summary comments, and improve code quality (#334)
* refactor delegation system and add PR summary comments Delegation system: - replace mode-based delegation with select_mode → delegate two-step flow - orchestrator crafts self-contained subagent prompts (clean context — no system/repo/event instructions leak) - add role-based tool filtering via FastMCP authenticate hook (?role=subagent hides orchestrator-only tools) - add select_mode tool for orchestrator guidance per mode - add ask_question tool for lightweight research subagents - extract shared subagent lifecycle into subagent.ts (create, complete, stdout, instructions) - route set_output to per-subagent state when activeSubagentId is set - track per-subagent state (SubagentState Map) replacing boolean delegationActive flag - capture and aggregate AgentUsage across all agents (claude, codex, gemini, opencode) - write usage summary table to GitHub job summary - block built-in subagent spawning (Task for Claude, Task(*) for Cursor) - increase activity timeout from 60s to 300s (subagent thinking phases) - fix gh CLI misguidance in system prompt — explicitly forbid usage PR summary comments: - add prSummaryComment trigger (DB schema + migrations + Zod + UI toggle) - dispatch mini-effort summary job alongside PR review on pr.created - add update_pull_request_body MCP tool - add defaultEffort option to webhook dispatch Hardening: - rewrite delegate/selectMode tests with simulated state management - add toolFiltering.test.ts for role extraction, canAccess, set_output routing - remove non-null assertions for PULLFROG_TEMP_DIR (proper error throws) - use fetchWithRetry for direct tarball downloads - DRY fix for rate limit check in test runner Co-authored-by: Cursor <cursoragent@cursor.com> * fix: add type keyword to Effort import in handleWebhook.ts Co-authored-by: Cursor <cursoragent@cursor.com> * clean up delegation system, improve code quality across the codebase - simplify delegate tool to instructions + effort params with subagent lifecycle in subagent.ts - add select_mode and ask_question orchestrator-only tools with canAccess filtering - replace delegate.test.ts/selectMode.test.ts with toolFiltering.test.ts (live MCP integration) - add set_output routing for subagent context and AgentUsage tracking across all agents - add PR summary comment trigger (schema, UI, webhook dispatch with silent flag) - add update_pull_request_body MCP tool - fix changed-agents.sh to always include claude canary for non-agent action changes - fix cursor pagination bug in getSelectedInstallationReposPage - remove destructuring patterns, inline type definitions, and unsafe type casts - replace non-null assertions with explicit checks in install.ts - convert multi-param functions to single param objects (postCleanup, runActionLocal, etc.) - use isHttpError helper in API routes instead of catch-any patterns - add adhoc test fixtures for delegation scenarios (context isolation, error handling, synthesis, etc.) Co-authored-by: Cursor <cursoragent@cursor.com> * no subagent mutation, one mcp per subagent * address review feedback: parallel-safe usage tracking, subagent isolation, minor improvements * fix subagent state isolation: replace Object.freeze with shallow copy Object.freeze throws TypeErrors when subagent tools (checkout_pr, report_progress) write scalar properties to toolState. A shallow copy achieves the same isolation for scalar fields while allowing tools to work normally. Shared references (subagents Map, usageEntries array) remain shared for coordination. --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
This commit is contained in:
committed by
pullfrog[bot]
parent
a90743e9fe
commit
cfd38d82fc
+107
-86
@@ -12,7 +12,7 @@ import { installFromGithub } from "../utils/install.ts";
|
||||
import { spawn } from "../utils/subprocess.ts";
|
||||
import { ThinkingTimer } from "../utils/timer.ts";
|
||||
import { getGitHubInstallationToken } from "../utils/token.ts";
|
||||
import { type AgentRunContext, agent } from "./shared.ts";
|
||||
import { type AgentRunContext, type AgentUsage, agent } from "./shared.ts";
|
||||
|
||||
// effort configuration: model + thinking level
|
||||
// thinkingLevel is set via settings.json modelConfig.generateContentConfig.thinkingConfig
|
||||
@@ -105,91 +105,108 @@ function isTransientApiError(output: string): boolean {
|
||||
const MAX_ATTEMPTS = 2;
|
||||
const RETRY_DELAY_MS = 5_000;
|
||||
|
||||
let assistantMessageBuffer = "";
|
||||
|
||||
const messageHandlers = {
|
||||
init: (_event: GeminiInitEvent) => {
|
||||
log.debug(JSON.stringify(_event, null, 2));
|
||||
// initialization event - no logging needed
|
||||
assistantMessageBuffer = "";
|
||||
},
|
||||
message: (event: GeminiMessageEvent) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
if (event.role === "assistant" && event.content?.trim()) {
|
||||
if (event.delta) {
|
||||
// accumulate delta messages
|
||||
assistantMessageBuffer += event.content;
|
||||
} else {
|
||||
// final message - log it
|
||||
const message = event.content.trim();
|
||||
if (message) {
|
||||
log.box(message, { title: "Gemini" });
|
||||
}
|
||||
assistantMessageBuffer = "";
|
||||
}
|
||||
} else if (event.role === "assistant" && !event.delta && assistantMessageBuffer.trim()) {
|
||||
// if we have buffered content and get a non-delta message, log the buffer
|
||||
log.box(assistantMessageBuffer.trim(), { title: "Gemini" });
|
||||
assistantMessageBuffer = "";
|
||||
}
|
||||
},
|
||||
tool_use: (event: GeminiToolUseEvent, thinkingTimer: ThinkingTimer) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
if (event.tool_name) {
|
||||
thinkingTimer.markToolCall();
|
||||
log.toolCall({
|
||||
toolName: event.tool_name,
|
||||
input: event.parameters || {},
|
||||
});
|
||||
}
|
||||
},
|
||||
tool_result: (event: GeminiToolResultEvent, thinkingTimer: ThinkingTimer) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
thinkingTimer.markToolResult();
|
||||
if (event.status === "error") {
|
||||
const errorMsg =
|
||||
typeof event.output === "string" ? event.output : JSON.stringify(event.output);
|
||||
log.info(`Tool call failed: ${errorMsg}`);
|
||||
} else if (event.output) {
|
||||
// log successful tool result so it appears in output
|
||||
const outputStr =
|
||||
typeof event.output === "string" ? event.output : JSON.stringify(event.output);
|
||||
log.debug(`tool output: ${outputStr}`);
|
||||
}
|
||||
},
|
||||
result: async (event: GeminiResultEvent) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
// log any remaining buffered assistant message
|
||||
if (assistantMessageBuffer.trim()) {
|
||||
log.box(assistantMessageBuffer.trim(), { title: "Gemini" });
|
||||
assistantMessageBuffer = "";
|
||||
}
|
||||
|
||||
if (event.status === "success" && event.stats) {
|
||||
const stats = event.stats;
|
||||
const rows: Array<Array<{ data: string; header?: boolean } | string>> = [
|
||||
[
|
||||
{ data: "Input Tokens", header: true },
|
||||
{ data: "Output Tokens", header: true },
|
||||
{ data: "Total Tokens", header: true },
|
||||
{ data: "Tool Calls", header: true },
|
||||
{ data: "Duration (ms)", header: true },
|
||||
],
|
||||
[
|
||||
String(stats.input_tokens || 0),
|
||||
String(stats.output_tokens || 0),
|
||||
String(stats.total_tokens || 0),
|
||||
String(stats.tool_calls || 0),
|
||||
String(stats.duration_ms || 0),
|
||||
],
|
||||
];
|
||||
log.table(rows);
|
||||
} else if (event.status === "error") {
|
||||
log.error(`Gemini CLI failed: ${JSON.stringify(event)}`);
|
||||
}
|
||||
},
|
||||
// run-local state container — passed to handlers via closure for parallel-safe runs
|
||||
type GeminiRunState = {
|
||||
assistantMessageBuffer: string;
|
||||
usage: AgentUsage | null;
|
||||
};
|
||||
|
||||
function createMessageHandlers(runState: GeminiRunState) {
|
||||
return {
|
||||
init: (_event: GeminiInitEvent) => {
|
||||
log.debug(JSON.stringify(_event, null, 2));
|
||||
// initialization event - no logging needed
|
||||
runState.assistantMessageBuffer = "";
|
||||
},
|
||||
message: (event: GeminiMessageEvent) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
if (event.role === "assistant" && event.content?.trim()) {
|
||||
if (event.delta) {
|
||||
// accumulate delta messages
|
||||
runState.assistantMessageBuffer += event.content;
|
||||
} else {
|
||||
// final message - log it
|
||||
const message = event.content.trim();
|
||||
if (message) {
|
||||
log.box(message, { title: "Gemini" });
|
||||
}
|
||||
runState.assistantMessageBuffer = "";
|
||||
}
|
||||
} else if (
|
||||
event.role === "assistant" &&
|
||||
!event.delta &&
|
||||
runState.assistantMessageBuffer.trim()
|
||||
) {
|
||||
// if we have buffered content and get a non-delta message, log the buffer
|
||||
log.box(runState.assistantMessageBuffer.trim(), { title: "Gemini" });
|
||||
runState.assistantMessageBuffer = "";
|
||||
}
|
||||
},
|
||||
tool_use: (event: GeminiToolUseEvent, thinkingTimer: ThinkingTimer) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
if (event.tool_name) {
|
||||
thinkingTimer.markToolCall();
|
||||
log.toolCall({
|
||||
toolName: event.tool_name,
|
||||
input: event.parameters || {},
|
||||
});
|
||||
}
|
||||
},
|
||||
tool_result: (event: GeminiToolResultEvent, thinkingTimer: ThinkingTimer) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
thinkingTimer.markToolResult();
|
||||
if (event.status === "error") {
|
||||
const errorMsg =
|
||||
typeof event.output === "string" ? event.output : JSON.stringify(event.output);
|
||||
log.info(`Tool call failed: ${errorMsg}`);
|
||||
} else if (event.output) {
|
||||
// log successful tool result so it appears in output
|
||||
const outputStr =
|
||||
typeof event.output === "string" ? event.output : JSON.stringify(event.output);
|
||||
log.debug(`tool output: ${outputStr}`);
|
||||
}
|
||||
},
|
||||
result: async (event: GeminiResultEvent) => {
|
||||
log.debug(JSON.stringify(event, null, 2));
|
||||
// log any remaining buffered assistant message
|
||||
if (runState.assistantMessageBuffer.trim()) {
|
||||
log.box(runState.assistantMessageBuffer.trim(), { title: "Gemini" });
|
||||
runState.assistantMessageBuffer = "";
|
||||
}
|
||||
|
||||
if (event.status === "success" && event.stats) {
|
||||
const stats = event.stats;
|
||||
|
||||
runState.usage = {
|
||||
agent: "gemini",
|
||||
inputTokens: stats.input_tokens ?? 0,
|
||||
outputTokens: stats.output_tokens ?? 0,
|
||||
};
|
||||
|
||||
const rows: Array<Array<{ data: string; header?: boolean } | string>> = [
|
||||
[
|
||||
{ data: "Input Tokens", header: true },
|
||||
{ data: "Output Tokens", header: true },
|
||||
{ data: "Total Tokens", header: true },
|
||||
{ data: "Tool Calls", header: true },
|
||||
{ data: "Duration (ms)", header: true },
|
||||
],
|
||||
[
|
||||
String(stats.input_tokens || 0),
|
||||
String(stats.output_tokens || 0),
|
||||
String(stats.total_tokens || 0),
|
||||
String(stats.tool_calls || 0),
|
||||
String(stats.duration_ms || 0),
|
||||
],
|
||||
];
|
||||
log.table(rows);
|
||||
} else if (event.status === "error") {
|
||||
log.error(`Gemini CLI failed: ${JSON.stringify(event)}`);
|
||||
}
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
async function installGemini(githubInstallationToken?: string): Promise<string> {
|
||||
return await installFromGithub({
|
||||
owner: "google-gemini",
|
||||
@@ -227,7 +244,8 @@ export const gemini = agent({
|
||||
for (let attempt = 1; attempt <= MAX_ATTEMPTS; attempt++) {
|
||||
let finalOutput = "";
|
||||
let stdoutBuffer = "";
|
||||
assistantMessageBuffer = "";
|
||||
const runState: GeminiRunState = { assistantMessageBuffer: "", usage: null };
|
||||
const messageHandlers = createMessageHandlers(runState);
|
||||
const thinkingTimer = new ThinkingTimer();
|
||||
|
||||
try {
|
||||
@@ -235,7 +253,7 @@ export const gemini = agent({
|
||||
cmd: "node",
|
||||
args: [cliPath, ...args],
|
||||
env: process.env,
|
||||
activityTimeout: 0, // disabled: process-level timeout in main.ts handles this (subprocess timeout would kill orchestrator during delegation)
|
||||
activityTimeout: 0, // process-level activity timeout (5min) is the single authority
|
||||
onStdout: async (chunk) => {
|
||||
const text = chunk.toString();
|
||||
finalOutput += text;
|
||||
@@ -297,6 +315,7 @@ export const gemini = agent({
|
||||
success: false,
|
||||
error: errorMessage,
|
||||
output: finalOutput || result.stdout || "",
|
||||
usage: runState.usage ?? undefined,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -306,6 +325,7 @@ export const gemini = agent({
|
||||
return {
|
||||
success: true,
|
||||
output: finalOutput,
|
||||
usage: runState.usage ?? undefined,
|
||||
};
|
||||
} catch (error) {
|
||||
const errorMessage = error instanceof Error ? error.message : String(error);
|
||||
@@ -324,6 +344,7 @@ export const gemini = agent({
|
||||
success: false,
|
||||
error: errorMessage,
|
||||
output: finalOutput || "",
|
||||
usage: runState.usage ?? undefined,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user