mirror of
https://github.com/jparkerweb/plan2code.git
synced 2026-09-17 16:22:23 -07:00
jparkerweb
c2579a7b6a
Bot now acts as an authentic QA agent instead of rubber-stamping every question and step. - intelligent-responder answers AskUserQuestion via LLM using current observations (tools used, files created, errors) instead of keyword matching; auto-responder removed. - evaluator runs after each step with step-specific criteria (prompts/evaluation-criteria.ts), produces 0-100 score plus strengths/weaknesses/critical issues. Avg <60 blocks finalization. - observation-collector captures tool_use, file writes, errors, and question reasoning; session-runner falls back to scraping tool_use blocks when canUseTool doesn't fire and dedupes both sources. - Bot writes BOT-EVALUATION.md and BOT-NOTES.md for metrics analysis. - Idea generator: 12 categories instead of CLI/web-app coin flip, stronger seed adherence, less developer-tool bias. - Init step now writes a minimal AGENTS.md stub instead of running the full init skill, avoiding hallucinated architecture before plan. - Implement step uses Read/Write/Edit/Glob/Grep directly instead of a Skill sub-session that produced no visible tool observations. - bin: add --help, accept --idea="value" form, strip surrounding quotes; evaluator maxTurns 3 -> 30; warn when parser misses SCORE.
78 lines
2.5 KiB
TypeScript
78 lines
2.5 KiB
TypeScript
import { query } from '@anthropic-ai/claude-agent-sdk';
|
|
import { createIntelligentResponder } from './intelligent-responder.js';
|
|
import type { BotConfig, ExecutionObservation, StepName } from './types.js';
|
|
import type { ObservationCollector } from './observation-collector.js';
|
|
|
|
export interface SessionOptions {
|
|
prompt: string;
|
|
config: BotConfig;
|
|
step: StepName;
|
|
maxTurns?: number;
|
|
collector: ObservationCollector;
|
|
}
|
|
|
|
export interface SessionResult {
|
|
sessionId: string | null;
|
|
output: string;
|
|
success: boolean;
|
|
duration: number;
|
|
observations: ExecutionObservation;
|
|
}
|
|
|
|
export async function runSession(options: SessionOptions): Promise<SessionResult> {
|
|
const { prompt, config, step, maxTurns = 50, collector } = options;
|
|
const startTime = Date.now();
|
|
let output = '';
|
|
let sessionId: string | null = null;
|
|
|
|
try {
|
|
const session = query({
|
|
prompt,
|
|
options: {
|
|
cwd: config.projectDir,
|
|
maxTurns,
|
|
permissionMode: 'bypassPermissions',
|
|
allowDangerouslySkipPermissions: true,
|
|
canUseTool: createIntelligentResponder(config, step, collector),
|
|
systemPrompt: { type: 'preset', preset: 'claude_code' },
|
|
settingSources: ['project'],
|
|
},
|
|
});
|
|
|
|
for await (const message of session) {
|
|
// Record all messages for observations
|
|
collector.recordMessage(message);
|
|
|
|
if (message.type === 'assistant') {
|
|
sessionId = message.session_id ?? sessionId;
|
|
for (const block of message.message.content) {
|
|
if (block.type === 'text') {
|
|
output += block.text + '\n';
|
|
} else if (block.type === 'tool_use') {
|
|
// Capture tool invocations from the message stream as a fallback
|
|
// in case canUseTool doesn't fire (e.g., Skill sub-sessions)
|
|
collector.recordToolUse(
|
|
block.name,
|
|
block.input as Record<string, unknown>,
|
|
undefined,
|
|
true
|
|
);
|
|
}
|
|
}
|
|
} else if (message.type === 'result') {
|
|
sessionId = message.session_id ?? sessionId;
|
|
}
|
|
}
|
|
|
|
const duration = Date.now() - startTime;
|
|
const hasOutput = output.trim().length > 0;
|
|
const observations = collector.finalize();
|
|
return { sessionId, output, success: hasOutput, duration, observations };
|
|
} catch (error) {
|
|
const duration = Date.now() - startTime;
|
|
const errorMsg = error instanceof Error ? error.message : String(error);
|
|
const observations = collector.finalize();
|
|
return { sessionId, output, success: false, duration, observations };
|
|
}
|
|
}
|