mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 21:19:18 +00:00
* v0.41.15.0 feat: conversation parser cathedral + progressive-batch primitive (closes #1461) Replaces PR #1461's single-format Telegram regex with a 12-pattern built-in registry covering iMessage/Slack, Telegram (×2), Discord (×2), WhatsApp (×2 locales), Signal, Matrix/Element, IRC (×2), Teams. Each pattern is hand-vetted from public format docs (signal-cli, DiscordChatExporter, Telegram Desktop, WhatsApp export docs, Element matrix-archive, irssi/weechat defaults); module-load validation runs test_positive[] + test_negative[] for every pattern at startup so a typo makes gbrain refuse to start. PR #1461 contributor's BRACKET_TIME_RX + cleanSpeaker survive verbatim as the `telegram-bracket` built-in pattern + DEFAULT_SPEAKER_CLEAN export. All 33 of their test cases pass against the new orchestrator. Three layers per page (orchestrator chooses): 1. Built-in pattern registry (zero-cost, deterministic) 2. User-declared simple_pattern via config (deferred to v0.42+) 3. Opt-IN LLM polish + fallback (privacy-first; chat content goes to Anthropic only when user explicitly enables) D18 priority scoring picks the highest-match-rate pattern across the first 10 lines (not first-wins) so overlapping formats don't silently mis-route. D5 multi_line per-pattern + D11 quick_reject prefix screen + D19 timezone_policy per-pattern complete the registry shape. Companion: src/core/progressive-batch/ primitive (rule of three satisfied across 12+ ad-hoc cost-prompt sites). Wintermute-inspired ramp shape (trial 10 → 100 → 500 → full with verification at each stage), productionized with verifier+policy injection (callers describe HOW TO MEASURE SUCCESS, not WHEN TO WAIT FOR CTRL-C). D3 fail-closed budget gate: null tracker + null Policy.maxCostUsd → abort_cost_cap reason='no_budget_safety_net'. D20 discriminated Verifier union (output_count | idempotent_mutation | noop). extract-conversation-facts is the one proven consumer in v0.41.15.0; 9-site retrofit deferred to v0.41.16.0+ per TODOS.md. Codex outside-voice review absorbed 8 substantive findings: - Privacy posture (LLM polish/fallback flipped to opt-IN) - ReDoS theater (dropped arbitrary user regex; v0.42+ uses RE2) - LLM-inferred-regex persistence as silent-corruption machine - Pattern priority scoring across first 10 lines - Timezone policy on every PatternEntry - Verifier shape discriminated union - Behavior parity for sites that "jumped straight to full" - Real-corpus-redacted fixture gap (v0.42+ TODO) CI gates: - bun run check:conversation-parser (13 fixtures, --no-llm, deterministic) - bun run check:fixture-privacy (banned-token grep) Doctor surfaces 3 new checks: conversation_format_coverage, progressive_batch_audit_health, conversation_parser_probe_health. Tests: 198/198 across primitive + parser + LLM + nightly probe + eval CLI + debug CLI + doctor checks + migration v97 round-trip + E2E parser ↔ engine integration. Real bug caught + fixed during gap audit: IdempotentMutationVerifier was comparing absolute mutated-count vs per-stage expected (failed silently on stage 2+); now uses per-stage delta semantics matching OutputCountVerifier. Schema migration v97: conversation_parser_llm_cache table with (content_sha256, model_id, call_shape) composite key. NO inferred_patterns table (D17: silent-corruption machine). Plan + 23 decisions + codex outside-voice absorption at ~/.claude/plans/system-instruction-you-are-working-cuddly-hollerith.md. Co-Authored-By: garrytan-agents (PR #1461) <noreply@github.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(check-privacy): allowlist scripts/check-fixture-privacy.sh The new sibling privacy guard literally names the banned tokens in its BANNED_TOKENS array — same meta-exception that check-privacy.sh itself gets. Without this allowlist entry, bun run verify rejects the file post-merge because the banned name appears in the rule-definition script. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: renumber v0.41.15.0 → v0.41.16.0 (queue drift) Mechanical rename across all surfaces: VERSION, package.json, CHANGELOG (header + body refs), CLAUDE.md, TODOS.md, src/core/ migrate.ts (migration v98 comment), all src/core/conversation-parser/* and src/core/progressive-batch/* file headers, all test/ headers, scripts/check-privacy.sh allowlist comment, llms-full.txt regenerated. Audit clean: VERSION + package.json + CHANGELOG header all show 0.41.16.0. verify 24/24, touched tests 179/179. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: garrytan-agents (PR #1461) <noreply@github.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
198 lines
6.1 KiB
TypeScript
198 lines
6.1 KiB
TypeScript
/**
|
|
* v0.41.16.0 — `gbrain conversation-parser` debug CLI tests.
|
|
*
|
|
* Pins:
|
|
* - list-builtins prints all 12 patterns + accepts --json
|
|
* - validate emits "deferred to v0.42+" notice (v1 has no compiler)
|
|
* - scan errors without engine
|
|
* - --help works
|
|
*
|
|
* Pure-function tests; no engine, no DB.
|
|
*/
|
|
|
|
import { describe, expect, test, beforeEach, afterEach } from 'bun:test';
|
|
import { mkdtempSync, writeFileSync } from 'node:fs';
|
|
import { tmpdir } from 'node:os';
|
|
import { join } from 'node:path';
|
|
import { runConversationParser } from '../src/commands/conversation-parser.ts';
|
|
import { BUILTIN_PATTERNS } from '../src/core/conversation-parser/builtins.ts';
|
|
|
|
// Capture process.stdout.write + process.stderr.write + process.exit.
|
|
function captureStdio() {
|
|
const out: string[] = [];
|
|
const err: string[] = [];
|
|
let exitCode: number | null = null;
|
|
const origOut = process.stdout.write.bind(process.stdout);
|
|
const origErr = process.stderr.write.bind(process.stderr);
|
|
const origExit = process.exit.bind(process);
|
|
process.stdout.write = ((chunk: string | Uint8Array) => {
|
|
out.push(typeof chunk === 'string' ? chunk : Buffer.from(chunk).toString());
|
|
return true;
|
|
}) as typeof process.stdout.write;
|
|
process.stderr.write = ((chunk: string | Uint8Array) => {
|
|
err.push(typeof chunk === 'string' ? chunk : Buffer.from(chunk).toString());
|
|
return true;
|
|
}) as typeof process.stderr.write;
|
|
// process.exit throws to short-circuit; tests catch and inspect.
|
|
process.exit = ((code?: number) => {
|
|
exitCode = code ?? 0;
|
|
throw new Error(`PROCESS_EXIT:${exitCode}`);
|
|
}) as typeof process.exit;
|
|
return {
|
|
out,
|
|
err,
|
|
getExitCode: () => exitCode,
|
|
restore: () => {
|
|
process.stdout.write = origOut;
|
|
process.stderr.write = origErr;
|
|
process.exit = origExit;
|
|
},
|
|
};
|
|
}
|
|
|
|
describe('runConversationParser — help', () => {
|
|
test('--help prints usage', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['--help']);
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
const text = cap.out.join('');
|
|
expect(text).toContain('Usage: gbrain conversation-parser');
|
|
expect(text).toContain('scan');
|
|
expect(text).toContain('list-builtins');
|
|
expect(text).toContain('validate');
|
|
});
|
|
|
|
test('no subcommand prints help', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, []);
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
expect(cap.out.join('')).toContain('Usage: gbrain conversation-parser');
|
|
});
|
|
});
|
|
|
|
describe('runConversationParser — list-builtins', () => {
|
|
test('human output includes all 12 pattern ids', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['list-builtins']);
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
const text = cap.out.join('');
|
|
for (const pattern of BUILTIN_PATTERNS) {
|
|
expect(text).toContain(pattern.id);
|
|
}
|
|
expect(text).toContain(`${BUILTIN_PATTERNS.length} built-in patterns`);
|
|
});
|
|
|
|
test('--json output is stable schema', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['list-builtins', '--json']);
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
const json = JSON.parse(cap.out.join('').trim());
|
|
expect(json.schema_version).toBe(1);
|
|
expect(json.total).toBe(BUILTIN_PATTERNS.length);
|
|
expect(json.patterns).toHaveLength(BUILTIN_PATTERNS.length);
|
|
expect(json.patterns[0].id).toBe('imessage-slack');
|
|
expect(json.patterns[0].date_source).toBeDefined();
|
|
expect(json.patterns[0].time_format).toBeDefined();
|
|
expect(json.patterns[0].timezone_policy).toBeDefined();
|
|
expect(json.patterns[0].regex).toBeDefined();
|
|
});
|
|
});
|
|
|
|
describe('runConversationParser — validate', () => {
|
|
test('emits deferred notice (v0.42+ scope)', async () => {
|
|
const dir = mkdtempSync(join(tmpdir(), 'cv-parser-cli-'));
|
|
const path = join(dir, 'pattern.json');
|
|
writeFileSync(path, '{}');
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['validate', path]);
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
expect(cap.out.join('')).toContain('deferred to v0.42+');
|
|
});
|
|
|
|
test('--json validate emits structured deferred envelope', async () => {
|
|
const dir = mkdtempSync(join(tmpdir(), 'cv-parser-cli-'));
|
|
const path = join(dir, 'pattern.json');
|
|
writeFileSync(path, '{}');
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['validate', path, '--json']);
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
const json = JSON.parse(cap.out.join('').trim());
|
|
expect(json.schema_version).toBe(1);
|
|
expect(json.status).toBe('deferred');
|
|
expect(json.todo_ref).toContain('v0.41.16.0');
|
|
});
|
|
|
|
test('exits 2 on missing file path', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['validate']);
|
|
} catch (e) {
|
|
expect((e as Error).message).toBe('PROCESS_EXIT:2');
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
expect(cap.getExitCode()).toBe(2);
|
|
});
|
|
|
|
test('exits 2 on nonexistent file', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, [
|
|
'validate',
|
|
'/nonexistent/path.json',
|
|
]);
|
|
} catch (e) {
|
|
expect((e as Error).message).toBe('PROCESS_EXIT:2');
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
expect(cap.getExitCode()).toBe(2);
|
|
});
|
|
});
|
|
|
|
describe('runConversationParser — scan', () => {
|
|
test('exits 2 when engine is null (scan requires brain)', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['scan', 'some-slug']);
|
|
} catch (e) {
|
|
expect((e as Error).message).toBe('PROCESS_EXIT:2');
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
expect(cap.getExitCode()).toBe(2);
|
|
});
|
|
});
|
|
|
|
describe('runConversationParser — unknown subcommand', () => {
|
|
test('exits 2 with hint', async () => {
|
|
const cap = captureStdio();
|
|
try {
|
|
await runConversationParser(null, ['bogus-cmd']);
|
|
} catch (e) {
|
|
expect((e as Error).message).toBe('PROCESS_EXIT:2');
|
|
} finally {
|
|
cap.restore();
|
|
}
|
|
expect(cap.err.join('')).toContain('unknown subcommand');
|
|
});
|
|
});
|