test(827): capture Gate0 runtime evidence
This commit is contained in:
ms-lead-reviewer
350
docs/compaction-refresh/probes/pi_gate0_extension.ts
Normal file
350
docs/compaction-refresh/probes/pi_gate0_extension.ts
Normal file
@@ -0,0 +1,350 @@
|
||||
import type { ExtensionAPI } from '@earendil-works/pi-coding-agent';
|
||||
import { Type } from 'typebox';
|
||||
import { createHash, randomUUID } from 'node:crypto';
|
||||
import { readFileSync, appendFileSync, statSync } from 'node:fs';
|
||||
import net from 'node:net';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { resolve } from 'node:path';
|
||||
|
||||
const SELF = resolve(fileURLToPath(import.meta.url).split('?')[0]!);
|
||||
const LOG = process.env['GATE0_PI_LOG'];
|
||||
const CONTEXT_BLOCK =
|
||||
process.env['GATE0_PI_CONTEXT_BLOCK'] ??
|
||||
[
|
||||
'GATE0_PI_ATOMIC_BEGIN',
|
||||
'segment-01=alpha-7e31',
|
||||
'segment-02=middle-9c42',
|
||||
'segment-03=omega-5b83',
|
||||
'GATE0_PI_ATOMIC_END',
|
||||
].join('\n');
|
||||
|
||||
let sequence = 0;
|
||||
|
||||
function sha(value: string | Buffer): string {
|
||||
return createHash('sha256').update(value).digest('hex');
|
||||
}
|
||||
|
||||
function procStarttime(): number {
|
||||
const text = readFileSync(`/proc/${process.pid}/stat`, 'utf8');
|
||||
const close = text.lastIndexOf(')');
|
||||
const fields = text.slice(close + 2).trim().split(/\s+/);
|
||||
return Number(fields[19]);
|
||||
}
|
||||
|
||||
function log(event: string, details: Record<string, unknown> = {}): void {
|
||||
if (!LOG) return;
|
||||
sequence += 1;
|
||||
appendFileSync(
|
||||
LOG,
|
||||
`${JSON.stringify({ seq: sequence, event, pid: process.pid, starttime_ticks: procStarttime(), ...details })}\n`,
|
||||
);
|
||||
}
|
||||
|
||||
function argvExtensions(): string[] {
|
||||
const result: string[] = [];
|
||||
for (let i = 0; i < process.argv.length; i += 1) {
|
||||
if (process.argv[i] === '--extension' || process.argv[i] === '-e') {
|
||||
const candidate = process.argv[i + 1];
|
||||
if (candidate) result.push(resolve(candidate));
|
||||
}
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
interface SourceValidation {
|
||||
ok: boolean;
|
||||
reason: string;
|
||||
fragment?: string;
|
||||
}
|
||||
|
||||
function validateSources(): SourceValidation {
|
||||
const manifestPath = process.env['GATE0_SOURCE_MANIFEST'];
|
||||
if (!manifestPath) return { ok: true, reason: 'no-manifest-probe-disabled' };
|
||||
try {
|
||||
const manifest = JSON.parse(readFileSync(manifestPath, 'utf8')) as {
|
||||
maxBytes: number;
|
||||
fragments: Array<{ path: string; sha256: string }>;
|
||||
};
|
||||
for (const fragment of manifest.fragments) {
|
||||
let fileStat;
|
||||
try {
|
||||
fileStat = statSync(fragment.path);
|
||||
} catch {
|
||||
return { ok: false, reason: 'missing', fragment: fragment.path };
|
||||
}
|
||||
if (!fileStat.isFile()) {
|
||||
return { ok: false, reason: 'not-regular-file', fragment: fragment.path };
|
||||
}
|
||||
if (fileStat.size > manifest.maxBytes) {
|
||||
return { ok: false, reason: 'oversize', fragment: fragment.path };
|
||||
}
|
||||
const bytes = readFileSync(fragment.path);
|
||||
if (sha(bytes) !== fragment.sha256) {
|
||||
return { ok: false, reason: 'hash-mismatch', fragment: fragment.path };
|
||||
}
|
||||
}
|
||||
return { ok: true, reason: 'all-fragments-valid' };
|
||||
} catch (error) {
|
||||
return { ok: false, reason: `manifest-error:${error instanceof Error ? error.name : 'unknown'}` };
|
||||
}
|
||||
}
|
||||
|
||||
function brokerRequest(payload: Record<string, unknown>): Promise<Record<string, unknown>> {
|
||||
const socketPath = process.env['GATE0_GENERATION_SOCKET'];
|
||||
if (!socketPath) return Promise.resolve({ skipped: true });
|
||||
return new Promise((resolvePromise, reject) => {
|
||||
const socket = net.createConnection(socketPath);
|
||||
let buffer = '';
|
||||
socket.setEncoding('utf8');
|
||||
socket.on('connect', () => socket.write(`${JSON.stringify(payload)}\n`));
|
||||
socket.on('data', (chunk) => {
|
||||
buffer += chunk;
|
||||
const newline = buffer.indexOf('\n');
|
||||
if (newline < 0) return;
|
||||
socket.end();
|
||||
resolvePromise(JSON.parse(buffer.slice(0, newline)) as Record<string, unknown>);
|
||||
});
|
||||
socket.on('error', reject);
|
||||
});
|
||||
}
|
||||
|
||||
function markerPaths(value: unknown, path = '$'): string[] {
|
||||
const matches: string[] = [];
|
||||
if (typeof value === 'string') {
|
||||
if (value.includes(CONTEXT_BLOCK)) matches.push(path);
|
||||
return matches;
|
||||
}
|
||||
if (Array.isArray(value)) {
|
||||
value.forEach((item, index) => matches.push(...markerPaths(item, `${path}[${index}]`)));
|
||||
return matches;
|
||||
}
|
||||
if (value && typeof value === 'object') {
|
||||
for (const [key, item] of Object.entries(value as Record<string, unknown>)) {
|
||||
matches.push(...markerPaths(item, `${path}.${key}`));
|
||||
}
|
||||
}
|
||||
return matches;
|
||||
}
|
||||
|
||||
function assistantToolIds(message: unknown): string[] {
|
||||
if (!message || typeof message !== 'object') return [];
|
||||
const candidate = message as { role?: string; content?: unknown };
|
||||
if (candidate.role !== 'assistant' || !Array.isArray(candidate.content)) return [];
|
||||
return candidate.content
|
||||
.filter(
|
||||
(block): block is { type: 'toolCall'; id: string } =>
|
||||
Boolean(
|
||||
block &&
|
||||
typeof block === 'object' &&
|
||||
(block as { type?: string }).type === 'toolCall' &&
|
||||
typeof (block as { id?: unknown }).id === 'string',
|
||||
),
|
||||
)
|
||||
.map((block) => block.id);
|
||||
}
|
||||
|
||||
function assistantText(message: unknown): string {
|
||||
if (!message || typeof message !== 'object') return '';
|
||||
const candidate = message as { role?: string; content?: unknown };
|
||||
if (candidate.role !== 'assistant' || !Array.isArray(candidate.content)) return '';
|
||||
return candidate.content
|
||||
.filter(
|
||||
(block): block is { type: 'text'; text: string } =>
|
||||
Boolean(
|
||||
block &&
|
||||
typeof block === 'object' &&
|
||||
(block as { type?: string }).type === 'text' &&
|
||||
typeof (block as { text?: unknown }).text === 'string',
|
||||
),
|
||||
)
|
||||
.map((block) => block.text)
|
||||
.join('');
|
||||
}
|
||||
|
||||
export default function register(pi: ExtensionAPI) {
|
||||
const localProviderUrl = process.env['GATE0_LOCAL_PROVIDER_URL'];
|
||||
if (localProviderUrl) {
|
||||
pi.registerProvider('gate0-local', {
|
||||
baseUrl: localProviderUrl,
|
||||
apiKey: 'gate0-probe-not-a-secret',
|
||||
api: 'openai-completions',
|
||||
models: [
|
||||
{
|
||||
id: 'gate0-model',
|
||||
name: 'Gate0 deterministic local model',
|
||||
reasoning: false,
|
||||
input: ['text'],
|
||||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||||
contextWindow: 32_000,
|
||||
maxTokens: 1_024,
|
||||
},
|
||||
],
|
||||
});
|
||||
}
|
||||
|
||||
const extensions = argvExtensions();
|
||||
const lastPosition = extensions.length > 0 && extensions.at(-1) === SELF;
|
||||
interface RequestCycle {
|
||||
nonce: string;
|
||||
verified: boolean;
|
||||
sourceReason: string;
|
||||
}
|
||||
let buildingCycle: RequestCycle | undefined;
|
||||
const inFlightCycles: RequestCycle[] = [];
|
||||
const toolNonce = new Map<string, { nonce: string; verified: boolean; sourceReason: string }>();
|
||||
|
||||
pi.on('session_start', async (event) => {
|
||||
const broker = await brokerRequest({ action: 'lifecycle', phase: 'start', reason: event.reason });
|
||||
log('session_start', {
|
||||
reason: event.reason,
|
||||
extensions,
|
||||
self: SELF,
|
||||
lastPosition,
|
||||
gateState: lastPosition ? 'UNVERIFIED_READY' : 'CLOSED_NOT_LAST',
|
||||
broker,
|
||||
});
|
||||
});
|
||||
|
||||
pi.on('session_shutdown', async (event) => {
|
||||
const broker = await brokerRequest({ action: 'lifecycle', phase: 'shutdown', reason: event.reason });
|
||||
log('session_shutdown', { reason: event.reason, broker });
|
||||
});
|
||||
|
||||
pi.on('context', async (event) => {
|
||||
const validation = validateSources();
|
||||
buildingCycle = {
|
||||
nonce: randomUUID(),
|
||||
sourceReason: validation.reason,
|
||||
verified: lastPosition && validation.ok,
|
||||
};
|
||||
const inputJson = JSON.stringify(event.messages);
|
||||
const injected = {
|
||||
role: 'custom' as const,
|
||||
customType: 'gate0-context',
|
||||
content: CONTEXT_BLOCK,
|
||||
display: false,
|
||||
timestamp: Date.now(),
|
||||
};
|
||||
const outputMessages = buildingCycle.verified
|
||||
? [...event.messages, injected]
|
||||
: [...event.messages];
|
||||
const outputPrefix = outputMessages.slice(0, event.messages.length);
|
||||
const sourceBroker = validation.ok
|
||||
? { action: 'none', reason: 'source-valid' }
|
||||
: await brokerRequest({ action: 'source-invalid', reason: validation.reason });
|
||||
log('context_return', {
|
||||
requestNonce: buildingCycle.nonce,
|
||||
sourceValidation: validation,
|
||||
sourceBroker,
|
||||
lastPosition,
|
||||
promotion: false,
|
||||
injectionDecision: buildingCycle.verified ? 'ONE_ATOMIC_AGENT_MESSAGE' : 'REFUSED',
|
||||
inputCount: event.messages.length,
|
||||
outputCount: outputMessages.length,
|
||||
prefixHashBefore: sha(inputJson),
|
||||
prefixHashAfter: sha(JSON.stringify(outputPrefix)),
|
||||
prefixPreservedByReturn: sha(inputJson) === sha(JSON.stringify(outputPrefix)),
|
||||
blockLength: CONTEXT_BLOCK.length,
|
||||
blockSha256: sha(CONTEXT_BLOCK),
|
||||
});
|
||||
return { messages: outputMessages };
|
||||
});
|
||||
|
||||
pi.on('before_provider_request', async (event) => {
|
||||
const paths = markerPaths(event.payload);
|
||||
const cycle = buildingCycle;
|
||||
buildingCycle = undefined;
|
||||
if (cycle) inFlightCycles.push(cycle);
|
||||
log('before_provider_request', {
|
||||
requestNonce: cycle?.nonce,
|
||||
inFlightDepth: inFlightCycles.length,
|
||||
markerOccurrences: paths.length,
|
||||
markerPaths: paths,
|
||||
finalPayloadValid: Boolean(cycle?.verified && paths.length === 1),
|
||||
});
|
||||
});
|
||||
|
||||
pi.on('after_provider_response', async (event) => {
|
||||
const cycle = inFlightCycles[0];
|
||||
log('after_provider_response', {
|
||||
requestNonce: cycle?.nonce,
|
||||
status: event.status,
|
||||
assistantContentAvailableAtThisHook: false,
|
||||
timing: 'headers/status before stream consumption',
|
||||
});
|
||||
});
|
||||
|
||||
pi.on('message_end', async (event) => {
|
||||
const role = (event.message as { role?: string }).role;
|
||||
const ids = assistantToolIds(event.message);
|
||||
const text = assistantText(event.message);
|
||||
const cycle = role === 'assistant' ? inFlightCycles.shift() : undefined;
|
||||
if (ids.length > 0 && cycle) {
|
||||
for (const id of ids) {
|
||||
toolNonce.set(id, {
|
||||
nonce: cycle.nonce,
|
||||
verified: cycle.verified,
|
||||
sourceReason: cycle.sourceReason,
|
||||
});
|
||||
}
|
||||
}
|
||||
log('message_end', {
|
||||
role,
|
||||
assistantContentObserved: role === 'assistant',
|
||||
requestNonce: cycle?.nonce,
|
||||
inFlightDepthAfter: inFlightCycles.length,
|
||||
toolCallIds: ids,
|
||||
nonceMappings: ids.map((id) => ({ toolCallId: id, requestNonce: cycle?.nonce })),
|
||||
exactContextBlockCopied: text.includes(CONTEXT_BLOCK),
|
||||
assistantTextSha256: text ? sha(text) : null,
|
||||
});
|
||||
});
|
||||
|
||||
pi.on('tool_call', async (event) => {
|
||||
const mapping = toolNonce.get(event.toolCallId);
|
||||
const allowed = Boolean(lastPosition && mapping?.verified);
|
||||
log('tool_call', {
|
||||
toolCallId: event.toolCallId,
|
||||
toolName: event.toolName,
|
||||
mapping: mapping ?? null,
|
||||
allowed,
|
||||
reason: !lastPosition
|
||||
? 'closed-not-last'
|
||||
: !mapping
|
||||
? 'unknown-tool-call-id'
|
||||
: !mapping.verified
|
||||
? `unverified-source:${mapping.sourceReason}`
|
||||
: 'exact-tool-call-id-mapped-to-verified-request-nonce',
|
||||
});
|
||||
if (!allowed) return { block: true, reason: 'Gate0 probe refused unverified tool batch' };
|
||||
});
|
||||
|
||||
pi.on('agent_settled', async () => {
|
||||
log('agent_settled', { retainedNonceMappingsBeforeClear: toolNonce.size });
|
||||
toolNonce.clear();
|
||||
});
|
||||
|
||||
pi.registerTool({
|
||||
name: 'gate0_nonce_probe',
|
||||
label: 'Gate0 Nonce Probe',
|
||||
description: 'Gate0-only harmless tool used to prove toolCallId to request-nonce correlation.',
|
||||
parameters: Type.Object({ label: Type.String() }),
|
||||
async execute(toolCallId, params) {
|
||||
const broker = await brokerRequest({ action: 'promote-probe' });
|
||||
log('tool_execute', { toolCallId, label: params.label, broker });
|
||||
return {
|
||||
content: [{ type: 'text', text: `gate0_nonce_probe executed for ${params.label}` }],
|
||||
details: { harmless: true },
|
||||
};
|
||||
},
|
||||
});
|
||||
|
||||
pi.registerCommand('gate0-reload', {
|
||||
description: 'Trigger a real same-PID Pi extension/runtime reload.',
|
||||
handler: async (_args, ctx) => {
|
||||
log('reload_command_before');
|
||||
await ctx.reload();
|
||||
return;
|
||||
},
|
||||
});
|
||||
}
|
||||
Reference in New Issue
Block a user