hermes-bsd/tests/tools
Jaaneek a0c031299b feat(web): add xAI Web Search provider plugin
Adds a new bundled web search provider plugin backed by xAI's agentic
Web Search tool (server-side `web_search` on the Responses API). Slots
in alongside the existing Firecrawl / Tavily / Exa / Brave / SearXNG /
DDGS providers; opt in via `web.backend: xai` (or auto-selected by the
registry's single-provider shortcut when it's the only available web
provider, matching every other backend's behavior).

Reuses the existing xAI HTTP credential plumbing (`tools/xai_http.py`)
so it works with both `hermes auth login xai-oauth` (SuperGrok OAuth)
and `XAI_API_KEY` — no new credential paths, no new env vars, no new
setup-wizard prompts. The existing `xai_grok` post_setup hook handles
credential collection.

Reference: https://docs.x.ai/developers/tools/web-search

Provider behavior
-----------------
- Sends a structured prompt to Grok with `tools=[{"type": "web_search"}]`
  enabled and `include=["no_inline_citations"]`, then parses results
  from a `{"results": [...]}` JSON block (primary), falling back to
  `url_citation` annotations (secondary) and the top-level `citations`
  list (last-ditch). Annotation fallback falls through to citations
  when no rows are extractable, so future annotation types xAI may
  add don't silently mask real data.
- HTTP 200 + `{"error": {...}}` envelopes (model-overload, refusal)
  are surfaced as failures rather than masked as success-with-empty-
  results.
- HTTP 401 on the OAuth path triggers a single `force_refresh=True`
  retry — closes two gaps the resolver's proactive JWT-exp shortcut
  doesn't cover: opaque (non-JWT) access tokens and mid-window
  revocation. Env-var (`XAI_API_KEY`) credentials never retry; they
  can't be refreshed and an immediate retry would just burn quota.
- `is_available()` is a cheap probe (env var OR auth.json read), never
  invokes the OAuth resolver — required by the ABC contract because
  it runs on every `hermes tools` repaint and at tool-registration time.
- Class docstring documents the LLM-in-a-trench-coat trust model so
  callers piping untrusted input into `web_search` know returned URLs
  are model-generated and should be validated before fetching.

Config (`config.yaml`):

    web:
      backend: xai
      xai:
        model: grok-4.3         # optional, defaults to grok-4.3
        allowed_domains:        # optional, max 5 — mutex with excluded_domains
          - arxiv.org
        excluded_domains:       # optional, max 5
          - example-spam.com
        timeout: 90             # optional, seconds

Files
-----
- plugins/web/xai/plugin.yaml          (new) plugin manifest
- plugins/web/xai/__init__.py          (new) register(ctx) hook
- plugins/web/xai/provider.py          (new) XAIWebSearchProvider impl
- tools/xai_http.py                    (+47) has_xai_credentials()
                                            cheap-probe helper +
                                            keyword-only force_refresh
                                            arg on resolve_xai_http_
                                            credentials() (backwards
                                            compatible; all 9 other
                                            call sites unaffected)
- tools/web_tools.py                   (+11) "xai" added to configured-
                                            backend set + branch in
                                            _is_backend_available()
- tests/tools/test_web_providers_xai.py (new, 39 tests) covers
                                        identity, cheap-probe semantics,
                                        JSON / annotation / citations
                                        parse paths, request payload
                                        shape, error envelopes, OAuth
                                        force-refresh-on-401 retry,
                                        env-var-no-retry guard, 500-not-
                                        retried guard, refresh-returns-
                                        same-token guard, OAuth runtime
                                        resolution, and backend wiring.

Tests
-----
- 39 xai-suite passes
- 79 sibling web-provider tests (brave-free, ddgs, searxng, base) pass
- 119 cross-suite tests for other xai_http callers (transcription,
  x_search, tts) pass — verifies the new keyword-only arg is BC
- scripts/check-windows-footguns.py: clean on all 5 modified files

No edits to run_agent.py, cli.py, gateway/, toolsets, config schema,
plugin core, or auth core.
2026-05-19 19:27:34 -07:00
..
__init__.py
test_accretion_caps.py
test_ansi_strip.py
test_approval.py Inspired by Claude Code: tighten dangerous-command detection (#26829) 2026-05-16 01:24:25 -07:00
test_approval_heartbeat.py
test_approval_plugin_hooks.py
test_base_environment.py
test_browser_camofox.py
test_browser_camofox_persistence.py feat(browser): support externally managed Camofox sessions 2026-05-12 15:14:49 -07:00
test_browser_camofox_state.py feat(browser): support externally managed Camofox sessions 2026-05-12 15:14:49 -07:00
test_browser_cdp_override.py
test_browser_cdp_tool.py
test_browser_chromium_check.py fix(install): skip browser download when system chromium exists 2026-05-13 22:07:02 -07:00
test_browser_cleanup.py
test_browser_cloud_fallback.py
test_browser_cloud_provider_cache.py
test_browser_console.py
test_browser_content_none_guard.py
test_browser_eval_supervisor_path.py perf(browser): route browser_console eval through supervisor's persistent CDP WS (180x faster) (#23226) 2026-05-10 07:37:55 -07:00
test_browser_hardening.py
test_browser_homebrew_paths.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_browser_hybrid_routing.py
test_browser_lightpanda.py
test_browser_orphan_reaper.py
test_browser_secret_exfil.py
test_browser_ssrf_local.py
test_browser_supervisor.py perf(browser): route browser_console eval through supervisor's persistent CDP WS (180x faster) (#23226) 2026-05-10 07:37:55 -07:00
test_browser_supervisor_healthcheck.py
test_budget_config.py
test_checkpoint_manager.py
test_clarify_gateway.py fix(gateway): enable text-intercept for multi-choice clarify fallback (#25567) 2026-05-14 07:59:12 -07:00
test_clarify_tool.py
test_clipboard.py fix(clipboard): reject non-png clipboard images when png normalization fails 2026-05-13 22:54:21 -07:00
test_code_execution.py
test_code_execution_modes.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_code_execution_windows_env.py
test_command_guards.py
test_computer_use.py fix(agent): keep image tool results from poisoning text-only sessions 2026-05-14 14:52:15 -07:00
test_config_null_guard.py
test_credential_files.py
test_credential_pool_env_fallback.py
test_cron_approval_mode.py
test_cron_prompt_injection.py
test_cronjob_tools.py fix(cron): allow emoji ZWJ sequences in prompts 2026-05-19 00:10:43 -07:00
test_daytona_environment.py fix(daytona): migrate legacy-sandbox lookup to cursor-based list() (#24587) 2026-05-12 16:31:46 -07:00
test_debug_helpers.py
test_delegate.py test(delegation): add regression test for runtime missing 'provider' key 2026-05-17 11:40:05 -07:00
test_delegate_composite_toolsets.py
test_delegate_subagent_timeout_diagnostic.py
test_delegate_toolset_scope.py
test_discord_tool.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_docker_environment.py
test_docker_find.py
test_dockerfile_node_modules_perms.py
test_dockerfile_pid1_reaping.py fix(docker): preload messaging gateway deps 2026-05-17 11:51:46 -07:00
test_env_passthrough.py
test_feishu_tools.py
test_file_operations.py ci(tests): add pytest-timeout 60s hard cap to break suite-teardown deadlock (#28861) 2026-05-19 17:27:24 -07:00
test_file_operations_edge_cases.py
test_file_ops_cwd_tracking.py
test_file_read_guards.py
test_file_staleness.py
test_file_state_registry.py
test_file_sync.py
test_file_sync_back.py
test_file_sync_perf.py
test_file_tools.py
test_file_tools_container_config.py
test_file_tools_live.py
test_file_write_safety.py
test_force_dangerous_override.py
test_fuzzy_match.py
test_hardline_blocklist.py fix(terminal): block sudo -S password guessing when SUDO_PASSWORD is not set 2026-05-11 06:56:30 -07:00
test_heartbeat_stale_thresholds.py
test_hidden_dir_filter.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_homeassistant_tool.py
test_image_generation.py
test_image_generation_env.py feat(image-gen): actionable setup message when no FAL backend is reachable (#26222) 2026-05-15 01:33:13 -07:00
test_image_generation_plugin_dispatch.py
test_init_session_cwd_respect.py
test_interrupt.py
test_kanban_codex_lane_skill.py docs: add kanban codex lane skill 2026-05-18 21:01:14 -07:00
test_kanban_tools.py feat(kanban): stamp originating ACP session_id on tasks 2026-05-18 21:15:21 -07:00
test_lazy_deps.py fix(update): refresh lazy-installed backends on hermes update (#25766) 2026-05-14 08:03:40 -07:00
test_llm_content_none_guard.py feat(session_search): single-shape tool with discovery, scroll, browse — no LLM (#27590) 2026-05-17 23:28:45 -07:00
test_local_background_child_hang.py
test_local_env_blocklist.py
test_local_env_cwd_recovery.py
test_local_env_windows_msys.py fix(windows): stop spamming cwd-missing + tirith-spawn warnings on every terminal call 2026-05-15 16:25:31 -07:00
test_local_interrupt_cleanup.py
test_local_shell_init.py
test_local_tempdir.py
test_managed_browserbase_and_modal.py fix(browser): self-review pass — dead-import, log levels, future-proofing 2026-05-17 04:04:15 -07:00
test_managed_media_gateways.py
test_managed_modal_environment.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_managed_tool_gateway.py
test_mcp_cancelled_error_propagation.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_mcp_circuit_breaker.py
test_mcp_dynamic_discovery.py
test_mcp_empty_error_message.py
test_mcp_image_content.py
test_mcp_invalid_url.py fix(mcp): validate remote URLs up-front with a clear error (#27105) 2026-05-16 13:06:56 -07:00
test_mcp_oauth.py fix(mcp-oauth): print SSH tunnel hint in _redirect_handler 2026-05-17 02:29:37 -07:00
test_mcp_oauth_bidirectional.py
test_mcp_oauth_cold_load_expiry.py
test_mcp_oauth_integration.py
test_mcp_oauth_manager.py
test_mcp_oauth_metadata.py
test_mcp_probe.py fix(async): close unscheduled coroutines in all threadsafe bridges (#26584) 2026-05-15 14:00:01 -07:00
test_mcp_reconnect_signal.py
test_mcp_sse_transport.py
test_mcp_stability.py fix(mcp): use module-level time so test patches do not race background sleepers 2026-05-17 13:33:26 -07:00
test_mcp_structured_content.py fix(async): close unscheduled coroutines in all threadsafe bridges (#26584) 2026-05-15 14:00:01 -07:00
test_mcp_tool.py fix(mcp): prevent parallel-safe prefix collisions 2026-05-17 11:41:26 -07:00
test_mcp_tool_401_handling.py
test_mcp_tool_issue_948.py
test_mcp_tool_session_expired.py
test_mcp_utility_capability_gating.py
test_memory_tool.py
test_memory_tool_import_fallback.py
test_memory_tool_schema.py
test_microsoft_graph_auth.py
test_microsoft_graph_client.py
test_mixture_of_agents_tool.py
test_modal_bulk_upload.py
test_modal_sandbox_fixes.py
test_modal_snapshot_isolation.py
test_notify_on_complete.py
test_osv_check.py
test_parse_env_var.py
test_patch_parser.py
test_process_registry.py fix(tests): catch up 25 stale tests after recent merges (#28626) 2026-05-19 01:28:32 -07:00
test_read_loop_detection.py
test_registry.py test(ci): stabilize shared optional dependency baselines 2026-05-13 17:32:22 -07:00
test_resolve_path.py
test_schema_sanitizer.py fix(xai-responses): strip enum values containing '/' from tool schemas 2026-05-18 10:37:35 -07:00
test_search_hidden_dirs.py
test_send_message_missing_platforms.py
test_send_message_telegram_proxy.py test+release: align send_message mocks for MessageEntity import; map @fonhal 2026-05-18 22:19:50 -07:00
test_send_message_tool.py test(send_message): add thread-not-found retry tests for Telegram topics 2026-05-18 22:32:00 -07:00
test_session_search.py feat(session_search): single-shape tool with discovery, scroll, browse — no LLM (#27590) 2026-05-17 23:28:45 -07:00
test_shared_container_task_id.py
test_signal_media.py
test_singularity_preflight.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_skill_env_passthrough.py
test_skill_improvements.py
test_skill_manager_tool.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_skill_provenance.py
test_skill_size_limits.py
test_skill_usage.py
test_skill_view_path_check.py
test_skill_view_traversal.py
test_skills_guard.py
test_skills_hub.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_skills_hub_browse_sh.py fix(browse-sh): fetch SKILL.md via /api/skills/{slug}+skillMdUrl 2026-05-19 14:17:38 -07:00
test_skills_hub_clawhub.py
test_skills_sync.py
test_skills_tool.py fix(tools): refuse skill_view name collisions instead of guessing 2026-05-13 13:29:28 -07:00
test_slash_confirm.py
test_spotify_client.py
test_ssh_bulk_upload.py
test_ssh_environment.py
test_symlink_prefix_confusion.py
test_sync_back_backends.py
test_terminal_compound_background.py
test_terminal_config_env_sync.py
test_terminal_exit_semantics.py
test_terminal_foreground_timeout_cap.py
test_terminal_none_command_guard.py
test_terminal_output_transform_hook.py
test_terminal_requirements.py
test_terminal_task_cwd.py
test_terminal_timeout_output.py
test_terminal_tool.py
test_terminal_tool_pty_fallback.py
test_terminal_tool_requirements.py
test_threaded_process_handle.py
test_tirith_security.py fix(tirith): suppress .app lookalike_tld false positives in warn verdicts 2026-05-18 10:20:07 -07:00
test_todo_tool.py
test_tool_backend_helpers.py
test_tool_output_limits.py
test_tool_result_storage.py
test_transcription.py test(ci): stabilize shared optional dependency baselines 2026-05-13 17:32:22 -07:00
test_transcription_dotenv_fallback.py fix(tests): stabilize xai env and provider parity 2026-05-17 11:55:25 -07:00
test_transcription_tools.py fix(security): reduce unnecessary shell=True in subprocess calls 2026-05-13 10:31:22 -07:00
test_tts_command_providers.py
test_tts_dotenv_fallback.py fix(xai-http): preserve ~/.hermes/.env fallback and XAI_STT_BASE_URL precedence 2026-05-15 12:11:32 -07:00
test_tts_gemini.py
test_tts_kittentts.py test(ci): stabilize shared optional dependency baselines 2026-05-13 17:32:22 -07:00
test_tts_max_text_length.py
test_tts_mistral.py fix(deps): unbreak [all] install — drop mistralai while PyPI quarantined (#24205) 2026-05-11 23:02:15 -07:00
test_tts_opus_routing.py fix(tts): keep native audio outside Telegram voice delivery 2026-05-18 22:29:45 -07:00
test_tts_piper.py
test_tts_speed.py fix(tts): align MiniMax TTS defaults with current API and add GroupId support 2026-05-13 22:04:28 -07:00
test_url_safety.py fix(url_safety): block IPv4-mapped IPv6 addresses to prevent SSRF bypass 2026-05-18 10:51:15 -07:00
test_vercel_sandbox_environment.py
test_video_analyze.py
test_video_generation_dispatch.py feat(video_gen): unified video_generate tool with pluggable provider backends (#25126) 2026-05-13 16:39:41 -07:00
test_video_generation_dynamic_schema.py feat(video_gen): unified video_generate tool with pluggable provider backends (#25126) 2026-05-13 16:39:41 -07:00
test_video_generation_tool_surface_matrix.py feat(video_gen): unified video_generate tool with pluggable provider backends (#25126) 2026-05-13 16:39:41 -07:00
test_vision_native_fast_path.py fix(dashboard): UI polish — modals, layout, consistency, test fixes 2026-05-12 13:59:22 -04:00
test_vision_tools.py
test_voice_cli_integration.py test(voice_cli): drop stale ≥1 requirement for force=True error _vprint calls 2026-05-17 13:09:24 -07:00
test_voice_mode.py
test_watch_patterns.py
test_web_providers.py fix(web): preserve top-level error envelope on unconfigured systems 2026-05-13 22:31:28 -07:00
test_web_providers_brave_free.py refactor(web): remove legacy in-tree provider modules 2026-05-13 22:31:28 -07:00
test_web_providers_ddgs.py refactor(web): remove legacy in-tree provider modules 2026-05-13 22:31:28 -07:00
test_web_providers_searxng.py refactor(web): remove legacy in-tree provider modules 2026-05-13 22:31:28 -07:00
test_web_providers_xai.py feat(web): add xAI Web Search provider plugin 2026-05-19 19:27:34 -07:00
test_web_tools_config.py refactor(web): dispatch all three tools through web_search_registry 2026-05-13 22:31:28 -07:00
test_web_tools_tavily.py
test_website_policy.py feat(web): firecrawl plugin natively supports crawl; delete legacy inline path 2026-05-13 22:31:28 -07:00
test_windows_compat.py
test_windows_native_support.py feat(security): supply-chain advisory checker + lazy-install framework + tiered install fallback (#24220) 2026-05-12 01:02:25 -07:00
test_write_deny.py
test_x_search_tool.py feat(x_search): gated X (Twitter) search tool with OAuth-or-API-key auth (#26763) 2026-05-16 00:58:27 -07:00
test_yolo_mode.py
test_zombie_process_cleanup.py ci(tests): add pytest-timeout 60s hard cap to break suite-teardown deadlock (#28861) 2026-05-19 17:27:24 -07:00