From 67220a14eafbf7bdf3565498362e81eb0c22fb7d Mon Sep 17 00:00:00 2001 From: john Date: Wed, 9 Sep 2026 22:08:39 +0800 Subject: [PATCH] fix(goose-v149): block unattended real LLM smokes by default Prevent phase2/phase3/all reruns from burning DashScope tokens unless GOOSE_V149_ALLOW_REAL_LLM=1 is explicitly set with human approval. Co-authored-by: Cursor --- docs/goose-v149-canary-runbook.md | 20 +++++--- docs/goose-v149-phase3-closeout.md | 2 + docs/goose-v149-real-llm-gate.md | 50 +++++++++++++++++++ scripts/check-goosed-v149-all.mjs | 2 + scripts/check-goosed-v149-cost-smoke.mjs | 3 ++ scripts/check-goosed-v149-deepseek-tools.mjs | 3 ++ scripts/check-goosed-v149-harness.mjs | 4 ++ scripts/check-goosed-v149-memory-chat.mjs | 2 + scripts/check-goosed-v149-memory-loop.mjs | 3 ++ ...check-goosed-v149-memory-verbal-recall.mjs | 2 + .../check-goosed-v149-multiturn-provider.mjs | 4 ++ scripts/check-goosed-v149-page-e2e.mjs | 2 + scripts/check-goosed-v149-portal-resume.mjs | 2 + scripts/check-goosed-v149-portal-smoke.mjs | 2 + scripts/check-goosed-v149-provider.mjs | 4 ++ scripts/check-goosed-v149-reply-smoke.mjs | 4 ++ scripts/goose-v149-canary.mjs | 2 + scripts/goose-v149-real-llm-gate.mjs | 40 +++++++++++++++ scripts/goose-v149-real-llm-gate.test.mjs | 29 +++++++++++ scripts/run-goosed-v149-local.sh | 6 +++ scripts/run-goosed-v149-missing-evidence.mjs | 2 + scripts/run-goosed-v149-phase2.mjs | 2 + scripts/run-goosed-v149-phase3.mjs | 2 + 23 files changed, 184 insertions(+), 8 deletions(-) create mode 100644 docs/goose-v149-real-llm-gate.md create mode 100644 scripts/goose-v149-real-llm-gate.mjs create mode 100644 scripts/goose-v149-real-llm-gate.test.mjs diff --git a/docs/goose-v149-canary-runbook.md b/docs/goose-v149-canary-runbook.md index 8c6a1f0..fe8a31a 100644 --- a/docs/goose-v149-canary-runbook.md +++ b/docs/goose-v149-canary-runbook.md @@ -1,5 +1,7 @@ # Goose v1.49 本地 Canary 运行手册 +> **2026-09-09 收口**：默认禁止真实 LLM 聚合 smoke（`check-goosed-v149-all` / phase2 / phase3 等）。见 [goose-v149-real-llm-gate.md](./goose-v149-real-llm-gate.md)。仅 `GOOSE_V149_ALLOW_REAL_LLM=1` + 明确批准后可跑。 + > 范围：仅本机 loopback（`:18049` vs `:18006`），**禁止**连接 103/105 或修改生产 launchd。 > 决策表：[TKMIND_V1_49_MIGRATION.md](../TKMIND_V1_49_MIGRATION.md) @@ -20,7 +22,8 @@ Memory 在 canary 期间保持 legacy owner（MySQL `h5_user_memory_items`）， ```bash bash scripts/build-goosed-v149-local.sh bash scripts/ensure-goose-v149-local-db.sh -bash scripts/run-goosed-v149-local.sh # 另开终端，监听 :18049 +# 默认已禁用；须明确批准： +GOOSE_V149_ALLOW_REAL_LLM=1 bash scripts/run-goosed-v149-local.sh # 另开终端，监听 :18049 curl -sk https://127.0.0.1:18049/status # → ok ``` @@ -64,14 +67,15 @@ pnpm dev ## 验证 ```bash -# Phase 2 聚合（推荐日常） -node scripts/run-goosed-v149-phase2.mjs +# 以下默认 BLOCKED；须 GOOSE_V149_ALLOW_REAL_LLM=1 且有人值守，禁止 Agent 循环重跑： +# node scripts/run-goosed-v149-phase2.mjs +# node scripts/run-goosed-v149-phase3.mjs +# node scripts/check-goosed-v149-all.mjs -# Phase 3 收口（合并前） -node scripts/run-goosed-v149-phase3.mjs - -# 单项 / 全量 smoke -node scripts/check-goosed-v149-all.mjs +# 无 LLM 的对照 / 单测（推荐日常）： +node --test scripts/goose-v149-canary.test.mjs +node scripts/compare-goose-v149-message-sanitize.mjs +node scripts/compare-goose-v149-memory-manifest.mjs node scripts/check-goosed-v149-memory-loop.mjs node scripts/check-goosed-v149-portal-smoke.mjs # 主 Portal 重启后 node scripts/check-goosed-v149-canary-portal.mjs # 隔离 :8083 diff --git a/docs/goose-v149-phase3-closeout.md b/docs/goose-v149-phase3-closeout.md index c43aafb..57c5eed 100644 --- a/docs/goose-v149-phase3-closeout.md +++ b/docs/goose-v149-phase3-closeout.md @@ -1,6 +1,8 @@ # Goose v1.49 Phase 3 收口清单 > **本阶段不授权 103/105 操作。** 仅整理证据、回滚路径与合并前闸门。 +> +> **2026-09-09**：本机真实 LLM 聚合 smoke 已默认禁用，见 [goose-v149-real-llm-gate.md](./goose-v149-real-llm-gate.md)。`run-goosed-v149-phase3.mjs` 须 `GOOSE_V149_ALLOW_REAL_LLM=1` 且用户明确批准，禁止 Agent 循环重跑。 > 决策表：[TKMIND_V1_49_MIGRATION.md](../TKMIND_V1_49_MIGRATION.md) · Phase 2 台账：[goose-v149-phase2-evidence.md](./goose-v149-phase2-evidence.md) ## 聚合验证入口 diff --git a/docs/goose-v149-real-llm-gate.md b/docs/goose-v149-real-llm-gate.md new file mode 100644 index 0000000..184d0ef --- /dev/null +++ b/docs/goose-v149-real-llm-gate.md @@ -0,0 +1,50 @@ +# Goose v1.49 真实 LLM 测试闸门（2026-09-09 收口） + +## 背景 + +本机 `:18049` v1.49 回归（`check-goosed-v149-all` / `run-goosed-v149-phase3` 等）在一天内可创建 **1000+** Goose session、消耗 **1 亿+** DashScope token，主要来自： + +- Portal smoke / resume（完整 Agent 多轮 + 工具） +- Page E2E（苏州一日游等生页场景） +- Memory loop / chat + +**默认禁止**再跑这类会调用真实模型的聚合 smoke；只允许显式 opt-in。 + +## 默认行为（收口后） + +| 动作 | 无 opt-in | `GOOSE_V149_ALLOW_REAL_LLM=1` | +|------|-----------|--------------------------------| +| `bash scripts/run-goosed-v149-local.sh` | **拒绝启动** | 允许 | +| `node scripts/check-goosed-v149-all.mjs` | **立即退出 2** | 允许 | +| `node scripts/run-goosed-v149-phase2.mjs` | **立即退出 2** | 允许 | +| `node scripts/run-goosed-v149-phase3.mjs` | **立即退出 2** | 允许 | +| `node scripts/run-goosed-v149-missing-evidence.mjs` | **立即退出 2** | 允许 | +| 单测 / message sanitize / memory manifest 对照 | 仍允许 | 仍允许 | + +Portal / page / resume smoke 在未 opt-in 时还会被强制 `*_SKIP=1`（即使单独跑子脚本）。 + +## 显式批准后再跑（一次性） + +```bash +# 1. 仅在需要时启动 v1.49 goosed +GOOSE_V149_ALLOW_REAL_LLM=1 bash scripts/run-goosed-v149-local.sh + +# 2. 另开终端，跑指定检查（勿循环 / 勿 CI 默认开启） +GOOSE_V149_ALLOW_REAL_LLM=1 node scripts/check-goosed-v149-reply-smoke.mjs +``` + +**禁止**：Agent/Cursor 在未获用户明确批准时设置 `GOOSE_V149_ALLOW_REAL_LLM=1` 或循环重跑 phase2/phase3。 + +## 推荐替代 + +- 合并前优先：`node --test scripts/goose-v149-canary.test.mjs`、`compare-goose-v149-message-sanitize.mjs`、`compare-goose-v149-memory-manifest.mjs` +- 必须验证 Portal 集成时：单次、有人值守、先确认 DashScope 配额 + +## 回滚 Canary + +若主 Portal 曾切到 `:18049`： + +```bash +bash scripts/switch-goose-v149-canary.sh rollback +# 重启 pnpm dev +``` diff --git a/scripts/check-goosed-v149-all.mjs b/scripts/check-goosed-v149-all.mjs index 968035c..76f8b69 100644 --- a/scripts/check-goosed-v149-all.mjs +++ b/scripts/check-goosed-v149-all.mjs @@ -8,12 +8,14 @@ import path from 'node:path'; import { fileURLToPath } from 'node:url'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { gooseV149PortalAgentEnv, waitForAgentRunWorkerIdle, } from './goose-v149-worker-idle.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('check-goosed-v149-all.mjs'); const checkEnv = prepareGooseV149CheckEnv({ ...process.env }, root); const checks = [ diff --git a/scripts/check-goosed-v149-cost-smoke.mjs b/scripts/check-goosed-v149-cost-smoke.mjs index fd6c9e4..c30fdfc 100644 --- a/scripts/check-goosed-v149-cost-smoke.mjs +++ b/scripts/check-goosed-v149-cost-smoke.mjs @@ -11,6 +11,9 @@ import { fileURLToPath } from 'node:url'; import { normalizeTokenState } from '../billing.mjs'; import { enrichTokenStateForBilling, resolveBillingTokenState } from '../billing-token-state.mjs'; import { collectReplyEvents, createV149Client } from './goose-v149-sse.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-cost-smoke.mjs'); const memindRoot = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); diff --git a/scripts/check-goosed-v149-deepseek-tools.mjs b/scripts/check-goosed-v149-deepseek-tools.mjs index 5bbfd4e..0ae9b30 100644 --- a/scripts/check-goosed-v149-deepseek-tools.mjs +++ b/scripts/check-goosed-v149-deepseek-tools.mjs @@ -9,6 +9,9 @@ import { randomUUID } from 'node:crypto'; import { fileURLToPath } from 'node:url'; import { collectReplyEvents, createV149Client } from './goose-v149-sse.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-deepseek-tools.mjs'); const memindRoot = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); diff --git a/scripts/check-goosed-v149-harness.mjs b/scripts/check-goosed-v149-harness.mjs index 7d3493f..0f7a27b 100644 --- a/scripts/check-goosed-v149-harness.mjs +++ b/scripts/check-goosed-v149-harness.mjs @@ -4,6 +4,10 @@ */ import { Agent, fetch } from 'undici'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-harness.mjs'); + const port = process.env.GOOSE_V149_PORT || '18049'; const host = process.env.GOOSE_V149_HOST || '127.0.0.1'; const secret = process.env.GOOSE_SERVER__SECRET_KEY || 'local-v149-dev-secret'; diff --git a/scripts/check-goosed-v149-memory-chat.mjs b/scripts/check-goosed-v149-memory-chat.mjs index 149b647..b42d5d6 100644 --- a/scripts/check-goosed-v149-memory-chat.mjs +++ b/scripts/check-goosed-v149-memory-chat.mjs @@ -10,6 +10,7 @@ import { createConversationMemoryService } from '../conversation-memory.mjs'; import { createMemoryV2 } from '../memory-v2.mjs'; import { createDbPool } from '../db.mjs'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { createReporter, loginViaApi, @@ -19,6 +20,7 @@ import { } from './scenario-test-lib.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('check-goosed-v149-memory-chat.mjs'); prepareGooseV149CheckEnv(process.env, root); const baseUrl = resolvePortalBase(Number(process.env.H5_PORT ?? 8081)); diff --git a/scripts/check-goosed-v149-memory-loop.mjs b/scripts/check-goosed-v149-memory-loop.mjs index 91b50cc..bb9d271 100644 --- a/scripts/check-goosed-v149-memory-loop.mjs +++ b/scripts/check-goosed-v149-memory-loop.mjs @@ -8,6 +8,9 @@ import mysql from 'mysql2/promise'; import { createConversationMemoryService } from '../conversation-memory.mjs'; import { createMemoryV2 } from '../memory-v2.mjs'; import { loadMemindEnvFiles } from './memind-runtime-profile.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-memory-loop.mjs'); const BLOCKED_DB_HOSTS = ['58.38.22.103', '120.26.184.105', 'rds.aliyuncs.com']; const MARKER = `goose-v149-memory-loop-${Date.now()}`; diff --git a/scripts/check-goosed-v149-memory-verbal-recall.mjs b/scripts/check-goosed-v149-memory-verbal-recall.mjs index b05339f..ab6519d 100644 --- a/scripts/check-goosed-v149-memory-verbal-recall.mjs +++ b/scripts/check-goosed-v149-memory-verbal-recall.mjs @@ -9,6 +9,7 @@ import { fileURLToPath } from 'node:url'; import { createDbPool } from '../db.mjs'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { createReporter, extractAssistantTexts, @@ -20,6 +21,7 @@ import { } from './scenario-test-lib.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('check-goosed-v149-memory-verbal-recall.mjs'); prepareGooseV149CheckEnv(process.env, root); const baseUrl = resolvePortalBase(Number(process.env.H5_PORT ?? 8081)); diff --git a/scripts/check-goosed-v149-multiturn-provider.mjs b/scripts/check-goosed-v149-multiturn-provider.mjs index ff44c27..ee5ddf1 100644 --- a/scripts/check-goosed-v149-multiturn-provider.mjs +++ b/scripts/check-goosed-v149-multiturn-provider.mjs @@ -6,6 +6,10 @@ import { randomUUID } from 'node:crypto'; import { Readable } from 'node:stream'; import { Agent, fetch } from 'undici'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-multiturn-provider.mjs'); + const port = process.env.GOOSE_V149_PORT || '18049'; const host = process.env.GOOSE_V149_HOST || '127.0.0.1'; const secret = process.env.GOOSE_SERVER__SECRET_KEY || 'local-v149-dev-secret'; diff --git a/scripts/check-goosed-v149-page-e2e.mjs b/scripts/check-goosed-v149-page-e2e.mjs index 9db92f3..cdbabb6 100644 --- a/scripts/check-goosed-v149-page-e2e.mjs +++ b/scripts/check-goosed-v149-page-e2e.mjs @@ -8,6 +8,7 @@ import { fileURLToPath } from 'node:url'; import { buildChatSkillPrompt } from '../chat-skills.mjs'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { createReporter, extractAssistantTexts, @@ -20,6 +21,7 @@ import { } from './scenario-test-lib.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('check-goosed-v149-page-e2e.mjs'); prepareGooseV149CheckEnv(process.env, root); const baseUrl = resolvePortalBase(Number(process.env.H5_PORT ?? 8081)); diff --git a/scripts/check-goosed-v149-portal-resume.mjs b/scripts/check-goosed-v149-portal-resume.mjs index 758213b..bff4c9c 100644 --- a/scripts/check-goosed-v149-portal-resume.mjs +++ b/scripts/check-goosed-v149-portal-resume.mjs @@ -7,6 +7,7 @@ import path from 'node:path'; import { fileURLToPath } from 'node:url'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { waitForAgentRunWorkerIdle } from './goose-v149-worker-idle.mjs'; import { createReporter, @@ -16,6 +17,7 @@ import { } from './scenario-test-lib.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('check-goosed-v149-portal-resume.mjs'); prepareGooseV149CheckEnv(process.env, root); const baseUrl = resolvePortalBase(Number(process.env.H5_PORT ?? 8081)); diff --git a/scripts/check-goosed-v149-portal-smoke.mjs b/scripts/check-goosed-v149-portal-smoke.mjs index c6b66fc..629641a 100644 --- a/scripts/check-goosed-v149-portal-smoke.mjs +++ b/scripts/check-goosed-v149-portal-smoke.mjs @@ -9,10 +9,12 @@ import { execFileSync } from 'node:child_process'; import { fileURLToPath } from 'node:url'; import { applyGooseV149CanaryBlockEnv, describeGooseCanaryConfig } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { loadMemindEnvFiles } from './memind-runtime-profile.mjs'; import { waitForRunTerminal } from './scenario-test-lib.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('check-goosed-v149-portal-smoke.mjs'); loadMemindEnvFiles(root, process.env); applyGooseV149CanaryBlockEnv(process.env, root); diff --git a/scripts/check-goosed-v149-provider.mjs b/scripts/check-goosed-v149-provider.mjs index 7e5f964..d288d80 100644 --- a/scripts/check-goosed-v149-provider.mjs +++ b/scripts/check-goosed-v149-provider.mjs @@ -12,6 +12,10 @@ import { fileURLToPath } from 'node:url'; import { Readable } from 'node:stream'; import { Agent, fetch } from 'undici'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-provider.mjs'); + const memindRoot = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); function loadEnvFile(filePath) { diff --git a/scripts/check-goosed-v149-reply-smoke.mjs b/scripts/check-goosed-v149-reply-smoke.mjs index 0e89c15..2ddceea 100644 --- a/scripts/check-goosed-v149-reply-smoke.mjs +++ b/scripts/check-goosed-v149-reply-smoke.mjs @@ -7,6 +7,10 @@ import { randomUUID } from 'node:crypto'; import { Readable } from 'node:stream'; import { Agent, fetch } from 'undici'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; + +enforceRealLlmGate('check-goosed-v149-reply-smoke.mjs'); + const port = process.env.GOOSE_V149_PORT || '18049'; const host = process.env.GOOSE_V149_HOST || '127.0.0.1'; const secret = process.env.GOOSE_SERVER__SECRET_KEY || 'local-v149-dev-secret'; diff --git a/scripts/goose-v149-canary.mjs b/scripts/goose-v149-canary.mjs index 38d9dcc..7ed4ed3 100644 --- a/scripts/goose-v149-canary.mjs +++ b/scripts/goose-v149-canary.mjs @@ -7,6 +7,7 @@ import path from 'node:path'; import { fileURLToPath } from 'node:url'; import { createCanaryPolicy, resolveCanaryTarget } from '../release-gate/canary-routing.mjs'; +import { applyRealLlmSkipDefaults } from './goose-v149-real-llm-gate.mjs'; import { loadMemindEnvFiles } from './memind-runtime-profile.mjs'; const memindRoot = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); @@ -78,6 +79,7 @@ export function prepareGooseV149CheckEnv(env = process.env, rootDir = memindRoot loadMemindEnvFiles(rootDir, env); applyGooseV149CanaryBlockEnv(env, rootDir); applyLocalScenarioCredentials(env); + applyRealLlmSkipDefaults(env); const canary = resolveGooseApiTargetsFromEnv(env); if (canary?.mode && canary.mode !== 'off' && env.GOOSE_V149_MEMORY_DRIFT_REFRESH_AFTER_SMOKE == null) { env.GOOSE_V149_MEMORY_DRIFT_REFRESH_AFTER_SMOKE = '1'; diff --git a/scripts/goose-v149-real-llm-gate.mjs b/scripts/goose-v149-real-llm-gate.mjs new file mode 100644 index 0000000..7fe4071 --- /dev/null +++ b/scripts/goose-v149-real-llm-gate.mjs @@ -0,0 +1,40 @@ +/** + * Hard gate: block unattended Goose v1.49 smoke that calls real LLM providers. + * Bulk portal/page/memory smokes can consume 100M+ tokens/day on DashScope. + * + * Opt-in only: + * GOOSE_V149_ALLOW_REAL_LLM=1 node scripts/check-goosed-v149-all.mjs + * + * See docs/goose-v149-real-llm-gate.md + */ + +export const REAL_LLM_GATE_ENV = 'GOOSE_V149_ALLOW_REAL_LLM'; + +export function isRealLlmAllowed(env = process.env) { + return String(env[REAL_LLM_GATE_ENV] ?? '') === '1'; +} + +export function realLlmGateMessage(source) { + return [ + `GOOSE_V149_REAL_LLM_BLOCKED: ${source}`, + 'Unattended v1.49 smokes that call real LLM providers are disabled by default.', + 'They previously consumed ~150M tokens/day on local DashScope during phase3 reruns.', + `To run once with explicit approval: ${REAL_LLM_GATE_ENV}=1 `, + 'See docs/goose-v149-real-llm-gate.md', + ].join('\n'); +} + +export function enforceRealLlmGate(source, env = process.env) { + if (isRealLlmAllowed(env)) return; + console.error(realLlmGateMessage(source)); + process.exit(2); +} + +/** Force skip flags for the heaviest portal/page smokes unless explicitly allowed. */ +export function applyRealLlmSkipDefaults(env = process.env) { + if (isRealLlmAllowed(env)) return env; + env.GOOSE_V149_PORTAL_SMOKE_SKIP = '1'; + env.GOOSE_V149_PAGE_E2E_SKIP = '1'; + env.GOOSE_V149_PORTAL_RESUME_SKIP = env.GOOSE_V149_PORTAL_RESUME_SKIP ?? '1'; + return env; +} diff --git a/scripts/goose-v149-real-llm-gate.test.mjs b/scripts/goose-v149-real-llm-gate.test.mjs new file mode 100644 index 0000000..7e528de --- /dev/null +++ b/scripts/goose-v149-real-llm-gate.test.mjs @@ -0,0 +1,29 @@ +import assert from 'node:assert/strict'; +import test from 'node:test'; + +import { + applyRealLlmSkipDefaults, + isRealLlmAllowed, + realLlmGateMessage, +} from './goose-v149-real-llm-gate.mjs'; + +test('real LLM smokes blocked unless GOOSE_V149_ALLOW_REAL_LLM=1', () => { + assert.equal(isRealLlmAllowed({}), false); + assert.equal(isRealLlmAllowed({ GOOSE_V149_ALLOW_REAL_LLM: '1' }), true); +}); + +test('applyRealLlmSkipDefaults forces portal/page/resume skip when blocked', () => { + const env = applyRealLlmSkipDefaults({}); + assert.equal(env.GOOSE_V149_PORTAL_SMOKE_SKIP, '1'); + assert.equal(env.GOOSE_V149_PAGE_E2E_SKIP, '1'); + assert.equal(env.GOOSE_V149_PORTAL_RESUME_SKIP, '1'); +}); + +test('applyRealLlmSkipDefaults leaves skip flags unset when allowed', () => { + const env = applyRealLlmSkipDefaults({ GOOSE_V149_ALLOW_REAL_LLM: '1' }); + assert.equal(env.GOOSE_V149_PORTAL_SMOKE_SKIP, undefined); +}); + +test('gate message mentions opt-in env', () => { + assert.match(realLlmGateMessage('test'), /GOOSE_V149_ALLOW_REAL_LLM=1/); +}); diff --git a/scripts/run-goosed-v149-local.sh b/scripts/run-goosed-v149-local.sh index 77d4b26..46b0115 100755 --- a/scripts/run-goosed-v149-local.sh +++ b/scripts/run-goosed-v149-local.sh @@ -3,6 +3,12 @@ # Does not touch 103 production ports 18006-18014 or Portal 8081. set -euo pipefail +if [[ "${GOOSE_V149_ALLOW_REAL_LLM:-}" != "1" ]]; then + echo "[goose-v149] REAL_LLM_BLOCKED: run-goosed-v149-local.sh disabled by default (see docs/goose-v149-real-llm-gate.md)" >&2 + echo "[goose-v149] To start once with explicit approval: GOOSE_V149_ALLOW_REAL_LLM=1 bash scripts/run-goosed-v149-local.sh" >&2 + exit 2 +fi + ROOT="$(cd "$(dirname "$0")/.." && pwd)" GOOSED_ROOT="${GOOSED_V149_ROOT:-/Users/john/Project/tkmind_go-v149}" PORT="${GOOSE_V149_PORT:-18049}" diff --git a/scripts/run-goosed-v149-missing-evidence.mjs b/scripts/run-goosed-v149-missing-evidence.mjs index 5023f69..4de498e 100644 --- a/scripts/run-goosed-v149-missing-evidence.mjs +++ b/scripts/run-goosed-v149-missing-evidence.mjs @@ -9,8 +9,10 @@ import { fileURLToPath } from 'node:url'; import { loadMemindEnvFiles } from './memind-runtime-profile.mjs'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('run-goosed-v149-missing-evidence.mjs'); const checkEnv = prepareGooseV149CheckEnv({ ...process.env }, root); if (!String(checkEnv.GOOSE_V149_MEMORY_VERBAL_FORCE_DEEP ?? '').trim()) { checkEnv.GOOSE_V149_MEMORY_VERBAL_FORCE_DEEP = '0'; diff --git a/scripts/run-goosed-v149-phase2.mjs b/scripts/run-goosed-v149-phase2.mjs index 5bbb45f..1bffb93 100644 --- a/scripts/run-goosed-v149-phase2.mjs +++ b/scripts/run-goosed-v149-phase2.mjs @@ -9,8 +9,10 @@ import { fileURLToPath } from 'node:url'; import { loadMemindEnvFiles } from './memind-runtime-profile.mjs'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('run-goosed-v149-phase2.mjs'); const checkEnv = prepareGooseV149CheckEnv({ ...process.env }, root); const checks = [ diff --git a/scripts/run-goosed-v149-phase3.mjs b/scripts/run-goosed-v149-phase3.mjs index b4c6b82..05e94da 100644 --- a/scripts/run-goosed-v149-phase3.mjs +++ b/scripts/run-goosed-v149-phase3.mjs @@ -9,12 +9,14 @@ import path from 'node:path'; import { fileURLToPath } from 'node:url'; import { prepareGooseV149CheckEnv } from './goose-v149-canary.mjs'; +import { enforceRealLlmGate } from './goose-v149-real-llm-gate.mjs'; import { gooseV149PortalAgentEnv, waitForAgentRunWorkerIdle, } from './goose-v149-worker-idle.mjs'; const root = path.join(path.dirname(fileURLToPath(import.meta.url)), '..'); +enforceRealLlmGate('run-goosed-v149-phase3.mjs'); const checkEnv = prepareGooseV149CheckEnv({ ...process.env }, root); const checks = [