fix(security): enable guard_agent_created by default

.github/workflows/supply-chain-audit.yml

@@ -47,14 +47,17 @@ jobs:
           HEAD="${{ github.event.pull_request.head.sha }}"
 
           # Added lines only, excluding lockfiles.
-          DIFF=$(git diff "$BASE".."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
+          # Three-dot diff (base...head) diffs from the merge base to HEAD,
+          # so only changes introduced by this PR are included — not changes
+          # that landed on main after the PR branched off.
+          DIFF=$(git diff "$BASE"..."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
 
           FINDINGS=""
 
           # --- .pth files (auto-execute on Python startup) ---
           # The exact mechanism used in the litellm supply chain attack:
           # https://github.com/BerriAI/litellm/issues/24512
-          PTH_FILES=$(git diff --name-only "$BASE".."$HEAD" | grep '\.pth$' || true)
+          PTH_FILES=$(git diff --name-only "$BASE"..."$HEAD" | grep '\.pth$' || true)
           if [ -n "$PTH_FILES" ]; then
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: .pth file added or modified
@@ -97,7 +100,7 @@ jobs:
 
           # --- Install-hook files (setup.py/sitecustomize/usercustomize/__init__.pth) ---
           # These execute during pip install or interpreter startup.
-          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(^|/)(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
+          SETUP_HITS=$(git diff --name-only "$BASE"..."$HEAD" | grep -E '(^|/)(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
           if [ -n "$SETUP_HITS" ]; then
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: Install-hook file added or modified
@@ -158,7 +161,7 @@ jobs:
           HEAD="${{ github.event.pull_request.head.sha }}"
 
           # Only check added lines in pyproject.toml
-          ADDED=$(git diff "$BASE".."$HEAD" -- pyproject.toml | grep '^+' | grep -v '^+++' || true)
+          ADDED=$(git diff "$BASE"..."$HEAD" -- pyproject.toml | grep '^+' | grep -v '^+++' || true)
 
           if [ -z "$ADDED" ]; then
             echo "found=false" >> "$GITHUB_OUTPUT"

.github/workflows/tests.yml

@@ -23,11 +23,22 @@ concurrency:
 jobs:
   test:
     runs-on: ubuntu-latest
-    timeout-minutes: 60
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        slice: [1, 2, 3, 4, 5, 6]
     steps:
       - name: Checkout code
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
+      - name: Restore duration cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        with:
+          path: test_durations.json
+          # Single stable key. main always overwrites, PRs always find it.
+          key: test-durations
+
       - name: Install ripgrep (prebuilt binary)
         run: |
           set -euo pipefail
@@ -54,7 +65,7 @@ jobs:
           source .venv/bin/activate
           uv pip install -e ".[all,dev]"
 
-      - name: Run tests
+      - name: Run tests (slice ${{ matrix.slice }}/6)
         # Per-file isolation via scripts/run_tests_parallel.py: discovers
         # every test_*.py file under tests/ (excluding integration/ + e2e/),
         # then runs `python -m pytest <file>` in a freshly-spawned subprocess
@@ -72,15 +83,61 @@ jobs:
         # state across files, which is exactly the leakage we wanted to
         # fix. ThreadPoolExecutor + subprocess.run is ~60 lines and does
         # the job with cleaner semantics.
+        #
+        # Matrix slicing (--slice I/N): files are distributed across 6
+        # jobs by cached duration (LPT algorithm) so each job gets
+        # roughly equal wall time. Without a cache, files default to 2s
+        # estimate and get split roughly evenly by count — still correct,
+        # just not perfectly balanced.
         run: |
           source .venv/bin/activate
-          python scripts/run_tests_parallel.py
+          python scripts/run_tests_parallel.py --slice ${{ matrix.slice }}/6
         env:
           # Ensure tests don't accidentally call real APIs
           OPENROUTER_API_KEY: ""
           OPENAI_API_KEY: ""
           NOUS_API_KEY: ""
 
+      - name: Upload per-slice durations
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
+        with:
+          name: test-durations-slice-${{ matrix.slice }}
+          path: test_durations.json
+          retention-days: 1
+
+  # Merge per-slice duration data into a single cache, so future runs
+  # (including PRs) get balanced slicing.
+  save-durations:
+    needs: test
+    if: always() && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download all slice durations
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c  # v8.0.1
+        with:
+          pattern: test-durations-slice-*
+          path: durations
+          merge-multiple: true
+
+      - name: Merge into single durations file
+        run: |
+          python3 -c "
+          import json, glob, os
+          merged = {}
+          for f in glob.glob('durations/*test_durations.json'):
+            with open(f) as fh:
+              merged.update(json.load(fh))
+          with open('test_durations.json', 'w') as fh:
+            json.dump(merged, fh, indent=2, sort_keys=True)
+          print(f'Merged {len(merged)} file durations')
+          "
+
+      - name: Save merged duration cache
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        with:
+          path: test_durations.json
+          key: test-durations
+
   e2e:
     runs-on: ubuntu-latest
     timeout-minutes: 15
@@ -121,4 +178,4 @@ jobs:
         env:
           OPENROUTER_API_KEY: ""
           OPENAI_API_KEY: ""
-          NOUS_API_KEY: ""
+          NOUS_API_KEY: ""

.gitignore

@@ -18,6 +18,7 @@ __pycache__/web_tools.cpython-310.pyc
 logs/
 data/
 .pytest_cache/
+test_durations.json
 .pytest-cache/
 tmp/
 temp_vision_images/

README.md

@@ -79,6 +79,27 @@ hermes doctor       # Diagnose any issues
 
 📖 **[Full documentation →](https://hermes-agent.nousresearch.com/docs/)**
 
+---
+
+## Skip the API-key collection — Nous Portal
+
+Hermes works with whatever provider you want — that's not changing. But if you'd rather not collect five separate API keys for the model, web search, image generation, TTS, and a cloud browser, **[Nous Portal](https://portal.nousresearch.com)** covers all of them under one subscription:
+
+- **300+ models** — pick any of them with `/model <name>`
+- **Tool Gateway** — web search (Firecrawl), image generation (FAL), text-to-speech (OpenAI), cloud browser (Browser Use), all routed through your sub. No extra accounts.
+
+One command from a fresh install:
+
+```bash
+hermes setup --portal
+```
+
+That logs you in via OAuth, sets Nous as your provider, and turns on the Tool Gateway. Check what's wired up any time with `hermes portal status`. Full details on the [Tool Gateway docs page](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway).
+
+You can still bring your own keys per-tool whenever you want — the gateway is per-backend, not all-or-nothing.
+
+---
+
 ## CLI vs Messaging Quick Reference
 
 Hermes has two entry points: start the terminal UI with `hermes`, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.

README.zh-CN.md

@@ -65,6 +65,27 @@ hermes doctor       # 诊断问题
 
 📖 **[完整文档 →](https://hermes-agent.nousresearch.com/docs/)**
 
+---
+
+## 省去到处收集 API Key — Nous Portal
+
+Hermes 始终允许你使用任意服务商，这点不会改变。但如果你不想为模型、网页搜索、图像生成、TTS、云浏览器分别去申请五个不同的 API Key，**[Nous Portal](https://portal.nousresearch.com)** 用一个订阅就能覆盖全部：
+
+- **300+ 模型** — 用 `/model <name>` 随时切换
+- **Tool Gateway** — 网页搜索（Firecrawl）、图像生成（FAL）、文本转语音（OpenAI）、云浏览器（Browser Use），全部通过订阅托管。无需额外注册任何账户。
+
+全新安装时一条命令即可：
+
+```bash
+hermes setup --portal
+```
+
+它会通过 OAuth 登录、把 Nous 设为推理服务商，并启用 Tool Gateway。随时用 `hermes portal status` 查看路由状态。完整说明见 [Tool Gateway 文档](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway)。
+
+你随时可以按工具单独切回自己的 API Key — Gateway 是按工具粒度生效的，不是一刀切。
+
+---
+
 ## CLI 与消息平台 快速对照
 
 Hermes 有两种入口：用 `hermes` 启动终端 UI，或运行网关从 Telegram、Discord、Slack、WhatsApp、Signal 或 Email 与之对话。进入对话后，许多斜杠命令在两种界面中通用。

agent/agent_init.py

@@ -607,6 +607,31 @@ def init_agent(
             # Falling back would send Anthropic credentials to third-party endpoints (Fixes #1739, #minimax-401).
             _is_native_anthropic = agent.provider == "anthropic"
             effective_key = (api_key or resolve_anthropic_token() or "") if _is_native_anthropic else (api_key or "")
+
+            # MiniMax OAuth issues short-lived (~15-min) access tokens. The
+            # Anthropic SDK caches ``api_key`` as a static string at client
+            # construction time, so a session that resolves the bearer once
+            # at startup will keep sending the same token until MiniMax
+            # returns 401 mid-session. Swap the static string for a callable
+            # token provider — ``build_anthropic_client`` recognizes the
+            # callable and installs an httpx event hook that mints a fresh
+            # bearer per outbound request (re-reading auth.json so a refresh
+            # persisted by another process is visible immediately).
+            # The cached refresh path is a no-op when the token still has
+            # ``MINIMAX_OAUTH_REFRESH_SKEW_SECONDS`` of life left, so steady-
+            # state cost is one file read + one timestamp compare per request.
+            if agent.provider == "minimax-oauth" and isinstance(effective_key, str) and effective_key:
+                try:
+                    from hermes_cli.auth import build_minimax_oauth_token_provider
+                    effective_key = build_minimax_oauth_token_provider()
+                except Exception as _mm_exc:  # noqa: BLE001 — never block startup on this
+                    import logging as _logging
+                    _logging.getLogger(__name__).warning(
+                        "MiniMax OAuth: failed to install per-request token provider "
+                        "(%s); falling back to static bearer that will expire ~15min in.",
+                        _mm_exc,
+                    )
+
             agent.api_key = effective_key
             agent._anthropic_api_key = effective_key
             agent._anthropic_base_url = base_url
@@ -618,7 +643,7 @@ def init_agent(
             # that cause 401/403 on their endpoints.  Guards #1739 and
             # the third-party identity-injection bug.
             from agent.anthropic_adapter import _is_oauth_token as _is_oat
-            agent._is_anthropic_oauth = _is_oat(effective_key) if _is_native_anthropic else False
+            agent._is_anthropic_oauth = _is_oat(effective_key) if (_is_native_anthropic and isinstance(effective_key, str)) else False
             agent._anthropic_client = build_anthropic_client(effective_key, base_url, timeout=_provider_timeout)
             # No OpenAI client needed for Anthropic mode
             agent.client = None

agent/agent_runtime_helpers.py

@@ -617,9 +617,28 @@ def recover_with_credential_pool(
         # existing entitlement keyword set in ``_is_entitlement_failure``.
         # Any 403 against ``xai-oauth`` is treated as entitlement here so
         # the refresh loop can't spin in those cases either.
+        #
+        # Exception (#29344): xAI's ``[WKE=unauthenticated:...]`` suffix and
+        # the ``OAuth2 access token could not be validated`` phrasing are
+        # xAI's authoritative "this is a stale token, not entitlement"
+        # signal.  When either fires we must NOT apply the catch-all
+        # override — refresh is the recoverable path for these bodies, and
+        # blanket-classifying them as entitlement was the bug that left
+        # long-running TUI sessions stuck on stale tokens until the user
+        # exited and reopened.
         is_entitlement = agent._is_entitlement_failure(error_context, status_code)
         if not is_entitlement and status_code == 403 and (agent.provider or "") == "xai-oauth":
-            is_entitlement = True
+            _disambiguator_haystack = " ".join(
+                str(error_context.get(k) or "").lower()
+                for k in ("message", "reason", "code", "error")
+                if isinstance(error_context, dict)
+            )
+            _is_xai_auth_failure = (
+                "[wke=unauthenticated:" in _disambiguator_haystack
+                or "oauth2 access token could not be validated" in _disambiguator_haystack
+            )
+            if not _is_xai_auth_failure:
+                is_entitlement = True
         if is_entitlement:
             _ra().logger.info(
                 "Credential %s — entitlement-shaped 403 from %s; "
@@ -1064,10 +1083,7 @@ def dump_api_request_debug(
 
         timestamp = datetime.now().strftime("%Y%m%d_%H%M%S_%f")
         dump_file = agent.logs_dir / f"request_dump_{agent.session_id}_{timestamp}.json"
-        dump_file.write_text(
-            json.dumps(dump_payload, ensure_ascii=False, indent=2, default=str),
-            encoding="utf-8",
-        )
+        atomic_json_write(dump_file, dump_payload, default=str)
 
         agent._vprint(f"{agent.log_prefix}🧾 Request debug dump written to: {dump_file}")
 
@@ -1352,14 +1368,30 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
         # API key — falling back would send Anthropic credentials to third-party endpoints.
         _is_native_anthropic = new_provider == "anthropic"
         effective_key = (api_key or agent.api_key or resolve_anthropic_token() or "") if _is_native_anthropic else (api_key or agent.api_key or "")
+
+        # MiniMax OAuth: swap static string for a per-request callable token
+        # provider so the rebuilt client survives 15-min token expiry. See
+        # the matching block in agent_init.py for the full rationale.
+        if new_provider == "minimax-oauth" and isinstance(effective_key, str) and effective_key:
+            try:
+                from hermes_cli.auth import build_minimax_oauth_token_provider
+                effective_key = build_minimax_oauth_token_provider()
+            except Exception as _mm_exc:  # noqa: BLE001
+                import logging as _logging
+                _logging.getLogger(__name__).warning(
+                    "MiniMax OAuth: failed to install per-request token provider "
+                    "on switch (%s); using static bearer.",
+                    _mm_exc,
+                )
+
         agent.api_key = effective_key
         agent._anthropic_api_key = effective_key
         agent._anthropic_base_url = base_url or getattr(agent, "_anthropic_base_url", None)
         agent._anthropic_client = build_anthropic_client(
             effective_key, agent._anthropic_base_url,
             timeout=get_provider_request_timeout(agent.provider, agent.model),
         )
-        agent._is_anthropic_oauth = _is_oauth_token(effective_key) if _is_native_anthropic else False
+        agent._is_anthropic_oauth = _is_oauth_token(effective_key) if (_is_native_anthropic and isinstance(effective_key, str)) else False
         agent.client = None
         agent._client_kwargs = {}
     else:
@@ -2116,33 +2148,56 @@ def apply_pending_steer_to_tool_results(agent, messages: list, num_tool_msgs: in
 
 
 def force_close_tcp_sockets(client: Any) -> int:
-    """Force-close underlying TCP sockets to prevent CLOSE-WAIT accumulation.
-
-    When a provider drops a connection mid-stream, httpx's ``client.close()``
-    performs a graceful shutdown which leaves sockets in CLOSE-WAIT until the
-    OS times them out (often minutes).  This method walks the httpx transport
-    pool and issues ``socket.shutdown(SHUT_RDWR)`` + ``socket.close()`` to
-    force an immediate TCP RST, freeing the file descriptors.
-
-    Returns the number of sockets force-closed.
+    """Abort in-flight TCP I/O by shutting down sockets WITHOUT closing FDs.
+
+    When a provider drops a connection mid-stream — or the user issues an
+    interrupt — we want to unblock httpx's reader/writer immediately rather
+    than waiting for the kernel's per-connection timeout. ``shutdown(SHUT_RDWR)``
+    achieves that: it sends FIN, breaks any pending ``recv``/``send`` with EOF
+    or ``EPIPE``, but does NOT release the file descriptor.
+
+    Historically this helper also called ``socket.close()`` so the FD got
+    released immediately, but that's unsafe when (as is the case for both the
+    interrupt-abort path and stale-call kill path) the helper runs on a
+    different thread than the one driving the request:
+
+      * The Python ``socket.socket`` we close here is the SAME object held by
+        httpx's pool, so closing it via Python sets its ``_fd`` to -1 and
+        future operations on that Python object fail safely.
+      * BUT the SSL wrapper (``ssl.SSLSocket``'s underlying OpenSSL ``BIO``)
+        caches the raw integer FD. Once ``os.close(fd)`` runs, the kernel may
+        immediately recycle that integer to the next ``open()`` call — e.g.
+        the kanban dispatcher opening ``kanban.db``.
+      * The owning worker thread then unwinds httpx, the SSL layer flushes a
+        pending TLS record, and the encrypted bytes get written into the
+        wrong file (issue #29507: 24-byte TLS application-data record
+        clobbering SQLite header bytes 5..28).
+
+    The fix is to let the owning thread own the close. ``shutdown()`` from any
+    thread is FD-safe; ``close()`` is not. The httpx connection's own close
+    path — which runs from the worker thread when it unwinds — will release
+    the FD via the same ``socket.socket`` object, and because Python's socket
+    close atomically swaps ``_fd`` to -1 *before* issuing ``os.close``, there
+    is no FD-aliasing window when only one thread closes.
+
+    Returns the number of sockets shut down. (Field kept as
+    ``tcp_force_closed=N`` in the log line for backwards-compatible parsing.)
     """
     import socket as _socket
 
-    closed = 0
+    shutdown_count = 0
     try:
         for sock in _iter_pool_sockets(client):
             try:
                 sock.shutdown(_socket.SHUT_RDWR)
             except OSError:
+                # Already shut down / not connected / FD invalid — all benign.
                 pass
-            try:
-                sock.close()
-            except OSError:
-                pass
-            closed += 1
+            # IMPORTANT (#29507): do NOT call sock.close() here. See docstring.
+            shutdown_count += 1
     except Exception as exc:
         _ra().logger.debug("Force-close TCP sockets sweep error: %s", exc)
-    return closed
+    return shutdown_count