From 730d52bcd0c55c74290efd31afd5b32e827abbdf Mon Sep 17 00:00:00 2001 From: huanghuoguoguo <60681390+huanghuoguoguo@users.noreply.github.com> Date: Wed, 15 Jul 2026 08:35:52 +0800 Subject: [PATCH] fix(agent-runner): close sandbox skill authoring flow --- docs/agent-runner-pluginization/STATUS.md | 7 +- skills/scripts/e2e/pipeline-debug-chat.mjs | 28 ++++++- skills/scripts/e2e/reset-sandbox-skill.mjs | 76 +++++++++++++++++++ skills/skills.index.json | 10 ++- ...box-skill-authoring-edit-existing-e2e.yaml | 16 ++-- .../pkg/api/http/service/monitoring.py | 6 +- .../pkg/provider/tools/loaders/native.py | 35 +++++---- .../pkg/provider/tools/loaders/skill.py | 12 +++ .../provider/tools/loaders/skill_authoring.py | 7 +- .../api/service/test_monitoring_service.py | 48 ++++++++++++ tests/unit_tests/provider/test_skill_tools.py | 42 ++++++++++ .../provider/test_tool_manager_native.py | 57 +++++++++++++- 12 files changed, 313 insertions(+), 31 deletions(-) create mode 100644 skills/scripts/e2e/reset-sandbox-skill.mjs create mode 100644 tests/unit_tests/api/service/test_monitoring_service.py diff --git a/docs/agent-runner-pluginization/STATUS.md b/docs/agent-runner-pluginization/STATUS.md index 1ece8013a..4692c5bf1 100644 --- a/docs/agent-runner-pluginization/STATUS.md +++ b/docs/agent-runner-pluginization/STATUS.md @@ -2,7 +2,7 @@ 本文档是 `docs/agent-runner-pluginization/` 的状态事实源。协议 schema 仍以 [PROTOCOL_V1.md](./PROTOCOL_V1.md) 为准；测试步骤以 [AGENT_RUNNER_QA_GUIDE.md](./AGENT_RUNNER_QA_GUIDE.md) 为准；安全发布门槛以 [SECURITY_HARDENING.md](./SECURITY_HARDENING.md) 为准。 -状态快照日期：2026-07-12。 +状态快照日期：2026-07-15。 ## 实现状态 @@ -15,7 +15,7 @@ | Result payload validation | Done | Wire 保持 `{type, data}`；Host 对投递/副作用类 payload 严格校验，tool-call telemetry 宽松，未知 type 忽略并 warning。 | | Old built-in runners | Done | 旧 `src/langbot/pkg/provider/runners/*` 与 `RequestRunner` 路径已从本分支删除。 | | Official runner manifests | Done | `local-agent`、ACP / Claude Code / Codex 外部 harness runner、外部服务 runner 已重新声明真实生效的 LangBot resource permissions。 | -| Skill 链路 | Unit-pass; WebUI smoke pending | 已按 **skill 全 tool 化** 收敛：发现走 `list_skills` / `langbot_list_assets` 和 skill resources；`activate` / `register_skill` 走统一 tool 授权；`skill_authoring` capability 降级为便捷开关。`activate` 现在会 best-effort 写入 conversation-scope `host.activated_skills`，后续 run 通过当前 pipeline-visible skill cache 恢复，语义为 last-write-wins。 | +| Skill 链路 | Unit-pass; WebUI E2E pass | 已按 **skill 全 tool 化** 收敛：发现走 `list_skills` / `langbot_list_assets` 和 skill resources；`activate` / `register_skill` 走统一 tool 授权；`skill_authoring` capability 降级为便捷开关。`activate` 会 best-effort 写入 conversation-scope `host.activated_skills`，后续 run 通过当前 pipeline-visible skill cache 恢复。新注册 Skill 在当前 Query 内立即获得临时可见性；Docker `exec` 产生的宿主侧不可写文件由 `write` / `edit` 回退到 Box 执行。2026-07-15 真实 LocalAgent Debug Chat 已完成创建、注册、同 Query 激活、编辑和执行闭环。 | | Runtime Control Plane v2 foundation | Partial | Host-owned `AgentRun` / `AgentRunEvent` ledger、orchestrator 自动建账、result event persistence、run get/list/event page/cancel/append/finalize actions 已落地；`agent_run:admin` / `runtime:admin` 控制权限、最小 runtime register/heartbeat/list/reconcile 和 run claim/renew/release 原语已落地。完整 Agent Platform 产品形态、daemon supervisor、任务唤醒/长轮询/WebSocket、分布式 runtime 管控仍未完成。 | | Security boundary | Done | 当前口径降级为轻量边界：LangBot 保护自身持有资源；external harness 的 OS / process / network / workspace 风险由用户或部署环境承担；managed sandbox 不是当前承诺。 | | Steering control path | Done | claim 异常不再逃逸 consumer loop；queue 有上限；未 pull 的 claimed 输入在 run 结束时写 `steering.dropped` 审计终态。 | @@ -37,7 +37,7 @@ | Runner | 状态 | 最近证据 | | --- | --- | --- | -| `plugin:langbot-team/LocalAgent/default` | Unit-pass; Marketplace UI pass | 2026-07-12 隔离 first-run 实例从真实 AgentRunner catalog 安装 `langbot-team/LocalAgent` 0.1.0，Host 注册 `plugin:langbot-team/LocalAgent/default`，Wizard 自动选中并解锁后续操作。此项不替代带真实模型的 Debug Chat 能力验收。 | +| `plugin:langbot-team/LocalAgent/default` | Unit-pass; Marketplace UI pass; Debug Chat E2E pass | 2026-07-12 隔离 first-run 实例从真实 AgentRunner catalog 安装 `langbot-team/LocalAgent` 0.1.0，Host 注册 `plugin:langbot-team/LocalAgent/default`，Wizard 自动选中并解锁后续操作。2026-07-15 `local-agent-functional-20260715-skill-edit-final` 使用真实 `gpt-5.5` 完成 Skill 创建、注册、同 Query 激活、已激活包编辑与脚本执行；三阶段 UI、浏览器诊断和结构化文件系统检查全部通过，p95 18.8 秒、错误率 0。 | | `plugin:langbot-team/ACPAgentRunner/default` / `plugin:langbot-team/ClaudeCodeAgent/default` / `plugin:langbot-team/CodexAgent/default` | Unit-pass; E2E pending | 通过 runner 仓库单测覆盖 session、run_id 注入和 LangBot MCP gateway；真实 harness E2E 取决于对应运行环境、CLI/daemon 可用性和 provider 登录态。 | | Dify / n8n / Coze / DashScope / Langflow / Tbox / DeerFlow / WeKnora | Unit-pass; credential smoke optional | 2026-06-13 plugin layout / parser tests 通过；真实服务凭据 smoke 非每轮必跑。 | @@ -46,6 +46,7 @@ | 范围 | 状态 | 最近证据 | | --- | --- | --- | | LangBot Runtime Control Plane v2 foundation | Unit-pass; EBA release gate 5/5 pass | 2026-07-12 `eba-functional-20260712-release-gate-rerun` 通过 Quick Start 场景筛选、隔离实例 Runner Marketplace 安装、Runner 健康状态、事件路由 dry-run / 合成派发，以及真实 OneBot `group.member_joined` → Agent → `send_group_msg` 链路。 | +| Host Skill / native tool integration | Unit-pass; WebUI E2E pass | 2026-07-15 provider / native / Skill / monitoring 定向测试 67 项通过，Skills CLI 104 项通过；真实 Debug Chat 验证 `register_skill` 后同 Query `activate` 成功，监控工具调用不再把 SQL 行误取为字符串，结构化 JSON 文件检查不依赖格式空格。 | | SDK AgentRunner control entities / proxy | Unit-pass | 2026-06-23 SDK `tests/api/entities/builtin/agent_runner`、`tests/api/proxies`、`tests/api/test_agent_tools_mcp_bridge.py`、`tests/runtime/plugin/test_mgr_agent_runner.py`、`tests/runtime/test_pull_api_handlers.py`、`tests/runtime/io/handlers/test_plugin_handler.py`、EBA event entities 和 message tests 通过，覆盖 typed entities、AgentRunAPIProxy、MCP bridge、runtime manager 与 pull API handlers。 | ## 历史高价值记录 diff --git a/skills/scripts/e2e/pipeline-debug-chat.mjs b/skills/scripts/e2e/pipeline-debug-chat.mjs index 7d96b4c2e..fffd303c0 100755 --- a/skills/scripts/e2e/pipeline-debug-chat.mjs +++ b/skills/scripts/e2e/pipeline-debug-chat.mjs @@ -239,6 +239,7 @@ async function runFilesystemChecks(checks) { } const contains = textList(check.contains); const notContains = textList(check.not_contains || check.notContains); + const expectedJson = check.json_equals ?? check.jsonEquals; const expectedExitCode = Number.isInteger(check.exit_code) ? check.exit_code : Number.isInteger(check.expected_exit_code) @@ -257,18 +258,31 @@ async function runFilesystemChecks(checks) { } const missing = contains.filter((needle) => !text.includes(needle)); const forbidden = notContains.filter((needle) => text.includes(needle)); + let jsonError = ""; + let jsonMatches = null; + if (expectedJson !== undefined) { + try { + jsonMatches = JSON.stringify(sortJson(JSON.parse(text))) === JSON.stringify(sortJson(expectedJson)); + if (!jsonMatches) jsonError = "JSON content does not match json_equals."; + } catch (error) { + jsonMatches = false; + jsonError = `Invalid JSON: ${error.message}`; + } + } + const failed = missing.length > 0 || forbidden.length > 0 || jsonMatches === false; results.push({ index, - status: missing.length || forbidden.length ? "fail" : "pass", + status: failed ? "fail" : "pass", type: "file", path, missing, forbidden, + json_matches: jsonMatches, reason: missing.length ? `Missing expected text: ${missing.join(", ")}` : forbidden.length ? `Found forbidden text: ${forbidden.join(", ")}` - : "", + : jsonError, }); continue; } @@ -310,6 +324,16 @@ async function runFilesystemChecks(checks) { }; } +function sortJson(value) { + if (Array.isArray(value)) return value.map(sortJson); + if (!value || typeof value !== "object") return value; + return Object.fromEntries( + Object.keys(value) + .sort() + .map((key) => [key, sortJson(value[key])]), + ); +} + function pipelineIdFromUrl(url) { if (!url) return ""; try { diff --git a/skills/scripts/e2e/reset-sandbox-skill.mjs b/skills/scripts/e2e/reset-sandbox-skill.mjs new file mode 100644 index 000000000..6480d7181 --- /dev/null +++ b/skills/scripts/e2e/reset-sandbox-skill.mjs @@ -0,0 +1,76 @@ +#!/usr/bin/env node + +import { env } from "node:process"; +import { + apiJson, + ensureEvidence, + evidencePaths, + loadEnvFiles, + resetAndAuthLocalUser, + writeResult, +} from "./lib/langbot-e2e.mjs"; + +const DEFAULT_LOCAL_PASSWORD = "LangBotE2ELocalPass!2026"; +const caseId = "reset-sandbox-skill"; + +await loadEnvFiles(); +const paths = evidencePaths(caseId); +await ensureEvidence(paths); + +const nameArgument = process.argv.find((argument) => argument.startsWith("--name=")); +const skillName = nameArgument?.slice("--name=".length).trim() || ""; +const backendUrl = env.LANGBOT_BACKEND_URL || ""; +const result = { + source: "setup_automation", + case_id: caseId, + run_id: paths.runId, + status: "fail", + reason: "", + skill_name: skillName, + existed: false, + deleted: false, + evidence_collected: ["api_diagnostic"], +}; + +try { + if (!backendUrl) throw new Error("LANGBOT_BACKEND_URL is not configured."); + if (!skillName || !/^[A-Za-z0-9_-]+$/.test(skillName)) { + throw new Error("--name must contain only letters, numbers, hyphens, or underscores."); + } + + const user = env.LANGBOT_E2E_LOGIN_USER || ""; + if (!user) throw new Error("LANGBOT_E2E_LOGIN_USER is required."); + const password = env.LANGBOT_E2E_LOGIN_PASSWORD || DEFAULT_LOCAL_PASSWORD; + const auth = await resetAndAuthLocalUser({ backendUrl, user, password }); + const listed = await apiJson(backendUrl, "/api/v1/skills", { token: auth.token }); + if (listed.status >= 400 || listed.json.code !== 0) { + throw new Error(listed.json.msg || `Skill listing failed with HTTP ${listed.status}.`); + } + + result.existed = (listed.json.data?.skills || []).some((skill) => skill?.name === skillName); + if (result.existed) { + const deleted = await apiJson( + backendUrl, + `/api/v1/skills/${encodeURIComponent(skillName)}`, + { method: "DELETE", token: auth.token }, + ); + if (deleted.status >= 400 || deleted.json.code !== 0) { + throw new Error(deleted.json.msg || `Skill deletion failed with HTTP ${deleted.status}.`); + } + result.deleted = true; + } + + result.status = "pass"; + result.reason = result.deleted + ? `Removed stale sandbox skill ${skillName}.` + : `Sandbox skill ${skillName} was already absent.`; +} catch (error) { + result.status = /ECONNREFUSED|fetch failed|not configured|required/.test(error.message) + ? "env_issue" + : "fail"; + result.reason = error.message; +} + +await writeResult(paths, result); +console.log(JSON.stringify(result, null, 2)); +process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1); diff --git a/skills/skills.index.json b/skills/skills.index.json index 3e51bd308..2e047d737 100644 --- a/skills/skills.index.json +++ b/skills/skills.index.json @@ -1621,8 +1621,14 @@ "edit" ], "automation": "scripts/e2e/pipeline-debug-chat.mjs", - "setup_automation": [], - "setup_provides_env": [], + "setup_automation": [ + "node:scripts/e2e/ensure-local-agent-pipeline.mjs --write-env", + "node:scripts/e2e/reset-sandbox-skill.mjs --name=lb-skill-edit-regression" + ], + "setup_provides_env": [ + "LANGBOT_LOCAL_AGENT_PIPELINE_URL", + "LANGBOT_LOCAL_AGENT_PIPELINE_NAME" + ], "evidence_required": [ "ui", "backend_log", diff --git a/skills/skills/langbot-testing/cases/sandbox-skill-authoring-edit-existing-e2e.yaml b/skills/skills/langbot-testing/cases/sandbox-skill-authoring-edit-existing-e2e.yaml index af4c383a3..34590804f 100644 --- a/skills/skills/langbot-testing/cases/sandbox-skill-authoring-edit-existing-e2e.yaml +++ b/skills/skills/langbot-testing/cases/sandbox-skill-authoring-edit-existing-e2e.yaml @@ -32,9 +32,15 @@ automation_env: - LANGBOT_LOCAL_AGENT_PIPELINE_NAME automation_pipeline_url_env: LANGBOT_LOCAL_AGENT_PIPELINE_URL automation_pipeline_name_env: LANGBOT_LOCAL_AGENT_PIPELINE_NAME -automation_expected_text: "UPDATED_MARKER_EDIT_REGRESSION" -automation_prompts_json: '[{"prompt":"Skill name is lb-skill-edit-regression. Use exactly one exec tool call with workdir=/workspace. In that single command, remove old /workspace/lb-skill-edit-regression, create SKILL.md, scripts/use.py, and data/input.json. The JSON must contain numbers [1,2,3,4], factors [2,3,4], and marker CREATE_MARKER_EDIT_REGRESSION. The Python script must read data/input.json relative to __file__ and print exactly SANDBOX_SKILL_CREATE_OK sum=10 product=24 marker=CREATE_MARKER_EDIT_REGRESSION. Run python3 /workspace/lb-skill-edit-regression/scripts/use.py in the same command. After the exec succeeds, final answer exactly CREATE_OK:lb-skill-edit-regression.","expected_text":"CREATE_MARKER_EDIT_REGRESSION","response_timeout_ms":"180000"},{"prompt":"Continue with the same skill name lb-skill-edit-regression. Strictly call register_skill with path=/workspace/lb-skill-edit-regression and name=lb-skill-edit-regression, then call activate with skill_name=lb-skill-edit-regression. Do not call exec, read, write, edit, grep, or ls in this step. After both tools succeed, final answer exactly REGISTER_ACTIVATE_OK:lb-skill-edit-regression.","expected_text":"REGISTER_ACTIVATE_OK:lb-skill-edit-regression","response_timeout_ms":"180000"},{"prompt":"Continue with the same activated skill lb-skill-edit-regression. Use exactly one exec tool call with workdir=/workspace/.skills/lb-skill-edit-regression. In that single exec command, run exactly this shell logic: set -e; overwrite SKILL.md with a heading and UPDATED_MARKER_EDIT_REGRESSION; overwrite data/input.json with numbers [5,6], factors [7,8], and marker UPDATED_MARKER_EDIT_REGRESSION; overwrite scripts/use.py so it reads data/input.json relative to __file__ and prints exactly SANDBOX_SKILL_MODIFIED_OK sum=11 product=56 marker=UPDATED_MARKER_EDIT_REGRESSION; run python3 scripts/use.py. Do not write exit(1). Do not call find, ls, read, grep as separate tools. If the single exec exits successfully and prints SANDBOX_SKILL_MODIFIED_OK, do not call more tools. Final answer exactly E2E_OK:lb-skill-edit-regression:SANDBOX_SKILL_MODIFIED_OK.","expected_text":"UPDATED_MARKER_EDIT_REGRESSION","response_timeout_ms":"240000"}]' -automation_filesystem_checks_json: '[{"path":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression/SKILL.md","contains":"UPDATED_MARKER_EDIT_REGRESSION"},{"path":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression/data/input.json","contains":["UPDATED_MARKER_EDIT_REGRESSION","\"numbers\": [5, 6]","\"factors\": [7, 8]"]},{"path":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression/scripts/use.py","contains":["SANDBOX_SKILL_MODIFIED_OK"],"not_contains":["SANDBOX_SKILL_CREATE_OK","exit(1)"]},{"argv":["python3","scripts/use.py"],"cwd":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression","stdout_contains":"SANDBOX_SKILL_MODIFIED_OK sum=11 product=56 marker=UPDATED_MARKER_EDIT_REGRESSION","exit_code":0}]' +automation_expected_text: "E2E_OK:lb-skill-edit-regression:SANDBOX_SKILL_MODIFIED_OK" +automation_prompts_json: '[{"prompt":"Skill name is lb-skill-edit-regression. Use exactly one exec tool call with workdir=/workspace. In that single command, remove old /workspace/lb-skill-edit-regression, create SKILL.md, scripts/use.py, and data/input.json. The JSON must contain numbers [1,2,3,4], factors [2,3,4], and marker CREATE_MARKER_EDIT_REGRESSION. The Python script must read data/input.json relative to __file__ and print exactly SANDBOX_SKILL_CREATE_OK sum=10 product=24 marker=CREATE_MARKER_EDIT_REGRESSION. Run python3 /workspace/lb-skill-edit-regression/scripts/use.py in the same command. After the exec succeeds, final answer exactly CREATE_OK:lb-skill-edit-regression.","expected_text":"CREATE_OK:lb-skill-edit-regression","response_timeout_ms":"180000"},{"prompt":"Continue with the same skill name lb-skill-edit-regression. Strictly call register_skill with path=/workspace/lb-skill-edit-regression and name=lb-skill-edit-regression, then call activate with skill_name=lb-skill-edit-regression. Do not call exec, read, write, edit, grep, or ls in this step. After both tools succeed, final answer exactly REGISTER_ACTIVATE_OK:lb-skill-edit-regression.","expected_text":"REGISTER_ACTIVATE_OK:lb-skill-edit-regression","response_timeout_ms":"180000"},{"prompt":"Continue with the same activated skill lb-skill-edit-regression. Use exactly one exec tool call with workdir=/workspace/.skills/lb-skill-edit-regression. In that single exec command, run exactly this shell logic: set -e; overwrite SKILL.md with a heading and UPDATED_MARKER_EDIT_REGRESSION; overwrite data/input.json with numbers [5,6], factors [7,8], and marker UPDATED_MARKER_EDIT_REGRESSION; overwrite scripts/use.py so it reads data/input.json relative to __file__ and prints exactly SANDBOX_SKILL_MODIFIED_OK sum=11 product=56 marker=UPDATED_MARKER_EDIT_REGRESSION; run python3 scripts/use.py. Do not write exit(1). Do not call find, ls, read, grep as separate tools. If the single exec exits successfully and prints SANDBOX_SKILL_MODIFIED_OK, do not call more tools. Final answer exactly E2E_OK:lb-skill-edit-regression:SANDBOX_SKILL_MODIFIED_OK.","expected_text":"E2E_OK:lb-skill-edit-regression:SANDBOX_SKILL_MODIFIED_OK","response_timeout_ms":"240000"}]' +setup_automation: + - "node:scripts/e2e/ensure-local-agent-pipeline.mjs --write-env" + - "node:scripts/e2e/reset-sandbox-skill.mjs --name=lb-skill-edit-regression" +setup_provides_env: + - LANGBOT_LOCAL_AGENT_PIPELINE_URL + - LANGBOT_LOCAL_AGENT_PIPELINE_NAME +automation_filesystem_checks_json: '[{"path":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression/SKILL.md","contains":"UPDATED_MARKER_EDIT_REGRESSION"},{"path":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression/data/input.json","json_equals":{"numbers":[5,6],"factors":[7,8],"marker":"UPDATED_MARKER_EDIT_REGRESSION"}},{"path":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression/scripts/use.py","contains":["SANDBOX_SKILL_MODIFIED_OK"],"not_contains":["SANDBOX_SKILL_CREATE_OK","exit(1)"]},{"argv":["python3","scripts/use.py"],"cwd":"${LANGBOT_REPO}/data/box/skills/lb-skill-edit-regression","stdout_contains":"SANDBOX_SKILL_MODIFIED_OK sum=11 product=56 marker=UPDATED_MARKER_EDIT_REGRESSION","exit_code":0}]' automation_stream_output: "0" automation_reset_debug_chat: "1" automation_response_timeout_ms: "420000" @@ -48,9 +54,9 @@ steps: - "Run the automation prompt or the equivalent prompt pattern from references/sandbox-skill-authoring.md." - "Capture the visible final response, backend logs, and the registered skill-store files." checks: - - "UI: A Bot message, not only the user prompt, contains UPDATED_MARKER_EDIT_REGRESSION." + - "UI: A Bot message, not only the user prompt, contains E2E_OK:lb-skill-edit-regression:SANDBOX_SKILL_MODIFIED_OK." - "Logs: The model called exec, register_skill, activate, then a second exec whose workdir is /workspace/.skills/lb-skill-edit-regression." - - "Logs: The second exec stdout contains SANDBOX_SKILL_MODIFIED_OK and GREP_ALL_OK or equivalent grep success." + - "Logs: The second exec stdout contains SANDBOX_SKILL_MODIFIED_OK." - "Automation: Filesystem checks pass for the registered skill-store files under LANGBOT_REPO/data/box/skills/lb-skill-edit-regression." - "Skill store: SKILL.md and data/input.json contain UPDATED_MARKER_EDIT_REGRESSION." - "Skill store: scripts/use.py is the modified script and prints SANDBOX_SKILL_MODIFIED_OK sum=11 product=56 marker=UPDATED_MARKER_EDIT_REGRESSION." diff --git a/src/langbot/pkg/api/http/service/monitoring.py b/src/langbot/pkg/api/http/service/monitoring.py index 46a352ad1..e4b61e70d 100644 --- a/src/langbot/pkg/api/http/service/monitoring.py +++ b/src/langbot/pkg/api/http/service/monitoring.py @@ -169,7 +169,7 @@ class MonitoringService: ) row = result.first() if row: - return row[0] + return row if not session_id: return None @@ -188,7 +188,7 @@ class MonitoringService: result = await self.ap.persistence_mgr.execute_async(user_query) row = result.first() if row: - return row[0] + return row any_query = ( sqlalchemy.select(persistence_monitoring.MonitoringMessage) @@ -198,7 +198,7 @@ class MonitoringService: ) result = await self.ap.persistence_mgr.execute_async(any_query) row = result.first() - return row[0] if row else None + return row # ========== Recording Methods ========== diff --git a/src/langbot/pkg/provider/tools/loaders/native.py b/src/langbot/pkg/provider/tools/loaders/native.py index 7f5ee4226..6a4421a85 100644 --- a/src/langbot/pkg/provider/tools/loaders/native.py +++ b/src/langbot/pkg/provider/tools/loaders/native.py @@ -574,9 +574,13 @@ else: ) if self._should_use_box_workspace_files(selected_skill): return await self._write_workspace_via_box(path, content, parameters, query) - os.makedirs(os.path.dirname(host_path), exist_ok=True) try: + os.makedirs(os.path.dirname(host_path), exist_ok=True) self._write_host_file(host_path, content, parameters) + except PermissionError: + if selected_skill is None and hasattr(self.ap.box_service, 'execute_tool'): + return await self._write_workspace_via_box(path, content, parameters, query) + raise except ValueError as exc: return {'ok': False, 'error': str(exc)} self._refresh_skill_from_disk(selected_skill) @@ -625,18 +629,23 @@ else: ) if self._should_use_box_workspace_files(selected_skill): return await self._edit_workspace_via_box(path, old_string, new_string, query) - if not os.path.isfile(host_path): - return {'ok': False, 'error': f'File not found: {path}'} - with open(host_path, 'r', encoding='utf-8', errors='replace') as f: - content = f.read() - count = content.count(old_string) - if count == 0: - return {'ok': False, 'error': 'old_string not found in file.'} - if count > 1: - return {'ok': False, 'error': f'old_string matches {count} locations; provide a more unique string.'} - new_content = content.replace(old_string, new_string, 1) - with open(host_path, 'w', encoding='utf-8') as f: - f.write(new_content) + try: + if not os.path.isfile(host_path): + return {'ok': False, 'error': f'File not found: {path}'} + with open(host_path, 'r', encoding='utf-8', errors='replace') as f: + content = f.read() + count = content.count(old_string) + if count == 0: + return {'ok': False, 'error': 'old_string not found in file.'} + if count > 1: + return {'ok': False, 'error': f'old_string matches {count} locations; provide a more unique string.'} + new_content = content.replace(old_string, new_string, 1) + with open(host_path, 'w', encoding='utf-8') as f: + f.write(new_content) + except PermissionError: + if selected_skill is None and hasattr(self.ap.box_service, 'execute_tool'): + return await self._edit_workspace_via_box(path, old_string, new_string, query) + raise self._refresh_skill_from_disk(selected_skill) return {'ok': True, 'path': path} diff --git a/src/langbot/pkg/provider/tools/loaders/skill.py b/src/langbot/pkg/provider/tools/loaders/skill.py index d013e25e4..582836186 100644 --- a/src/langbot/pkg/provider/tools/loaders/skill.py +++ b/src/langbot/pkg/provider/tools/loaders/skill.py @@ -49,6 +49,18 @@ def get_visible_skill(ap: app.Application, query: pipeline_query.Query, skill_na return get_visible_skills(ap, query).get(skill_name) +def register_created_skill_visibility(query: pipeline_query.Query, skill_name: str) -> None: + """Make a newly registered skill visible for the current Query only.""" + if not skill_name: + return + if getattr(query, 'variables', None) is None: + query.variables = {} + + bound_skills = query.variables.get(PIPELINE_BOUND_SKILLS_KEY) + if isinstance(bound_skills, list) and skill_name not in bound_skills: + bound_skills.append(skill_name) + + def get_activated_skills(query: pipeline_query.Query) -> dict[str, dict]: if query.variables is None: return {} diff --git a/src/langbot/pkg/provider/tools/loaders/skill_authoring.py b/src/langbot/pkg/provider/tools/loaders/skill_authoring.py index e6c5ecef5..c2d27b24f 100644 --- a/src/langbot/pkg/provider/tools/loaders/skill_authoring.py +++ b/src/langbot/pkg/provider/tools/loaders/skill_authoring.py @@ -67,7 +67,7 @@ class SkillToolLoader(loader.ToolLoader): if name == ACTIVATE_SKILL_TOOL_NAME: return await self._invoke_activate_skill(parameters, query) if name == REGISTER_SKILL_TOOL_NAME: - return await self._invoke_register_skill(parameters) + return await self._invoke_register_skill(parameters, query) raise ValueError(f'Unknown skill tool: {name}') async def shutdown(self): @@ -121,8 +121,10 @@ class SkillToolLoader(loader.ToolLoader): 'content': result_content, } - async def _invoke_register_skill(self, parameters: dict) -> typing.Any: + async def _invoke_register_skill(self, parameters: dict, query) -> typing.Any: """Register a skill from sandbox directory to data/skills/.""" + from . import skill as skill_loader + sandbox_path = str(parameters.get('path', '') or '').strip() if not sandbox_path: raise ValueError('path is required') @@ -153,6 +155,7 @@ class SkillToolLoader(loader.ToolLoader): 'package_root': host_path, } ) + skill_loader.register_created_skill_visibility(query, skill_name) return { 'registered': True, diff --git a/tests/unit_tests/api/service/test_monitoring_service.py b/tests/unit_tests/api/service/test_monitoring_service.py new file mode 100644 index 000000000..911d809d9 --- /dev/null +++ b/tests/unit_tests/api/service/test_monitoring_service.py @@ -0,0 +1,48 @@ +from __future__ import annotations + +from types import SimpleNamespace +from unittest.mock import AsyncMock, Mock + +import pytest + +from langbot.pkg.api.http.service.monitoring import MonitoringService + + +class _MonitoringMessageRow: + """Match the Row shape returned by Core connections for ORM selects.""" + + id = 'message-1' + bot_id = 'bot-1' + bot_name = 'QA Bot' + pipeline_id = 'pipeline-1' + pipeline_name = 'QA Pipeline' + session_id = 'person_1' + + def __getitem__(self, index: int) -> str: + assert index == 0 + return self.id + + +@pytest.mark.asyncio +async def test_record_tool_call_uses_full_monitoring_message_row_for_context(): + message_row = _MonitoringMessageRow() + select_result = Mock(first=Mock(return_value=message_row)) + insert_result = Mock() + persistence_mgr = SimpleNamespace( + execute_async=AsyncMock(side_effect=[select_result, insert_result]), + ) + service = MonitoringService(SimpleNamespace(persistence_mgr=persistence_mgr)) + + await service.record_tool_call( + tool_name='exec', + tool_source='native', + duration=12, + message_id='message-1', + ) + + insert_statement = persistence_mgr.execute_async.await_args_list[1].args[0] + values = insert_statement.compile().params + assert values['bot_id'] == 'bot-1' + assert values['pipeline_id'] == 'pipeline-1' + assert values['session_id'] == 'person_1' + assert values['message_id'] == 'message-1' diff --git a/tests/unit_tests/provider/test_skill_tools.py b/tests/unit_tests/provider/test_skill_tools.py index bd2838787..bedfdbde8 100644 --- a/tests/unit_tests/provider/test_skill_tools.py +++ b/tests/unit_tests/provider/test_skill_tools.py @@ -440,6 +440,48 @@ class TestSkillToolLoader: assert result['skill_name'] == 'cloned-skill' assert result['source_path'] == '/workspace/repo' + @pytest.mark.asyncio + async def test_registered_skill_can_be_activated_in_same_query(self): + from langbot.pkg.provider.tools.loaders.skill import PIPELINE_BOUND_SKILLS_KEY + from langbot.pkg.provider.tools.loaders.skill_authoring import ( + ACTIVATE_SKILL_TOOL_NAME, + REGISTER_SKILL_TOOL_NAME, + SkillToolLoader, + ) + + with tempfile.TemporaryDirectory() as tmpdir: + repo_dir = os.path.join(tmpdir, 'repo') + os.makedirs(repo_dir) + created = _make_skill_data(name='cloned-skill', package_root=os.path.realpath(repo_dir)) + ap = _make_ap() + ap.box_service = SimpleNamespace(default_workspace=tmpdir, available=True) + ap.skill_mgr = SimpleNamespace(skills={'existing': _make_skill_data(name='existing')}) + + async def create_skill(_data): + ap.skill_mgr.skills['cloned-skill'] = created + return created + + ap.skill_service = SimpleNamespace( + scan_directory_async=AsyncMock(return_value=created), + create_skill=AsyncMock(side_effect=create_skill), + ) + query = SimpleNamespace(variables={PIPELINE_BOUND_SKILLS_KEY: ['existing']}) + loader = SkillToolLoader(ap) + + await loader.invoke_tool( + REGISTER_SKILL_TOOL_NAME, + {'path': '/workspace/repo', 'name': 'cloned-skill'}, + query, + ) + activated = await loader.invoke_tool( + ACTIVATE_SKILL_TOOL_NAME, + {'skill_name': 'cloned-skill'}, + query, + ) + + assert query.variables[PIPELINE_BOUND_SKILLS_KEY] == ['existing', 'cloned-skill'] + assert activated['activated'] is True + @pytest.mark.asyncio async def test_register_skill_rejects_workspace_escape(self): from langbot.pkg.provider.tools.loaders.skill_authoring import ( diff --git a/tests/unit_tests/provider/test_tool_manager_native.py b/tests/unit_tests/provider/test_tool_manager_native.py index 7d8c0e2d5..97b85b34e 100644 --- a/tests/unit_tests/provider/test_tool_manager_native.py +++ b/tests/unit_tests/provider/test_tool_manager_native.py @@ -4,7 +4,7 @@ import base64 import os import tempfile from types import SimpleNamespace -from unittest.mock import AsyncMock, Mock +from unittest.mock import AsyncMock, Mock, patch import pytest @@ -236,6 +236,32 @@ async def test_write_creates_subdirectories(): assert f.read() == 'nested' +@pytest.mark.asyncio +async def test_write_falls_back_to_box_for_container_owned_workspace_file(): + with tempfile.TemporaryDirectory() as tmpdir: + box_service = SimpleNamespace( + available=True, + default_workspace=tmpdir, + execute_tool=AsyncMock( + return_value={ + 'ok': True, + 'stdout': '{"ok": true, "path": "/workspace/root-owned.txt"}', + } + ), + ) + loader = NativeToolLoader(SimpleNamespace(box_service=box_service, logger=Mock())) + loader._write_host_file = Mock(side_effect=PermissionError) + + result = await loader.invoke_tool( + 'write', + {'path': '/workspace/root-owned.txt', 'content': 'updated'}, + _make_query(), + ) + + assert result == {'ok': True, 'path': '/workspace/root-owned.txt'} + box_service.execute_tool.assert_awaited_once() + + @pytest.mark.asyncio async def test_read_binary_file_as_base64_chunk(): with tempfile.TemporaryDirectory() as tmpdir: @@ -326,6 +352,35 @@ async def test_edit_replaces_unique_string(): assert f.read() == 'def foo():\n return 42\n' +@pytest.mark.asyncio +async def test_edit_falls_back_to_box_for_container_owned_workspace_file(): + with tempfile.TemporaryDirectory() as tmpdir: + path = os.path.join(tmpdir, 'root-owned.txt') + with open(path, 'w') as f: + f.write('before') + box_service = SimpleNamespace( + available=True, + default_workspace=tmpdir, + execute_tool=AsyncMock( + return_value={ + 'ok': True, + 'stdout': '{"ok": true, "path": "/workspace/root-owned.txt"}', + } + ), + ) + loader = NativeToolLoader(SimpleNamespace(box_service=box_service, logger=Mock())) + + with patch('builtins.open', side_effect=PermissionError): + result = await loader.invoke_tool( + 'edit', + {'path': '/workspace/root-owned.txt', 'old_string': 'before', 'new_string': 'after'}, + _make_query(), + ) + + assert result == {'ok': True, 'path': '/workspace/root-owned.txt'} + box_service.execute_tool.assert_awaited_once() + + @pytest.mark.asyncio async def test_edit_rejects_ambiguous_match(): with tempfile.TemporaryDirectory() as tmpdir: