Merge remote-tracking branch 'upstream/master'

# Please enter a commit message to explain why this merge is necessary,
# especially if it merges an updated upstream into a topic branch.
#
# Lines starting with '#' will be ignored, and an empty message aborts
# the commit.

agent/chat/service.py

@@ -49,6 +49,16 @@ class ChatService:
             agent.model.channel_type = channel_type or ""
             agent.model.session_id = session_id or ""
 
+        # Build a context so context-aware tools (e.g. scheduler) can resolve the
+        # receiver/session. This streaming path bypasses agent_bridge.agent_reply,
+        # so the attach step that normally happens there must be done here too.
+        context = self._build_context(query, session_id, channel_type)
+        self._attach_context_aware_tools(agent, context)
+
+        # Mark this session as mid-run so the self-evolution idle scan does not
+        # fire concurrently when a single turn runs longer than idle_minutes.
+        self._mark_run_active(agent, True)
+
         # State shared between the event callback and this method
         state = _StreamState()
 
@@ -199,6 +209,8 @@ class ChatService:
                     logger.info("[ChatService] Cleared agent message history after executor recovery")
             raise
         finally:
+            # Clear the mid-run flag so idle scans can review this session again.
+            self._mark_run_active(agent, False)
             # Release cancel token to keep the registry bounded.
             if session_id:
                 try:
@@ -268,10 +280,68 @@ class ChatService:
         # Execute post-process tools
         agent._execute_post_process_tools()
 
+        # Record this user turn for the self-evolution idle trigger. This
+        # streaming path bypasses agent_bridge.agent_reply, so the activity must
+        # be noted here, otherwise idle scans never see any signal to evolve.
+        self._note_evolution_turn(agent, context)
+
         logger.info(f"[ChatService] Agent run completed: session={session_id}")
 
 
 
+    @staticmethod
+    def _build_context(query: str, session_id: str, channel_type: str):
+        """Build a Context for tool resolution on the streaming chat path.
+
+        receiver falls back to session_id; the scheduler's delivery keys on
+        session_id as the receiver.
+        """
+        from bridge.context import Context, ContextType
+        # Pass an explicit kwargs dict: Context's default kwargs is a shared
+        # mutable default, so omitting it would leak fields across sessions.
+        ctx = Context(ContextType.TEXT, query, kwargs={})
+        ctx["session_id"] = session_id
+        ctx["receiver"] = session_id
+        ctx["isgroup"] = False
+        ctx["channel_type"] = channel_type or ""
+        return ctx
+
+    @staticmethod
+    def _attach_context_aware_tools(agent, context):
+        """Attach the current context to tools that need it (scheduler)."""
+        try:
+            if not (context and getattr(agent, "tools", None)):
+                return
+            for tool in agent.tools:
+                if tool.name == "scheduler":
+                    from agent.tools.scheduler.integration import attach_scheduler_to_tool
+                    attach_scheduler_to_tool(tool, context)
+                    break
+        except Exception as e:
+            logger.warning(f"[ChatService] Failed to attach context to scheduler: {e}")
+
+    @staticmethod
+    def _mark_run_active(agent, active):
+        """Toggle the self-evolution mid-run flag for this session's agent."""
+        try:
+            from agent.evolution.trigger import mark_run_active
+            mark_run_active(agent, active)
+        except Exception:
+            pass
+
+    @staticmethod
+    def _note_evolution_turn(agent, context):
+        """Record a user turn so the self-evolution idle trigger has signal."""
+        try:
+            from agent.evolution.trigger import note_user_turn
+            ch = (context.get("channel_type") or "") if context else ""
+            rcv = (context.get("receiver") or "") if context else ""
+            is_group = bool(context.get("isgroup")) if context else False
+            # Only single chats get a proactive push target; group push is noisy.
+            note_user_turn(agent, channel_type=ch, receiver=(rcv if not is_group else ""))
+        except Exception:
+            pass
+
     @staticmethod
     def _persist_messages(session_id: str, new_messages: list, channel_type: str = ""):
         try:

agent/evolution/executor.py

@@ -424,6 +424,11 @@ def run_evolution_for_session(
             enable_skills=True,
             runtime_info=getattr(agent, "runtime_info", None),
         )
+        # Mark this as a restricted review agent so runtime MCP reconciliation
+        # (ToolManager.sync_mcp_into_agent) will NOT silently re-inject MCP tools
+        # that _select_tools()/_guard_tools() intentionally withheld. Without this
+        # flag the review boundary would be re-opened on the first LLM turn.
+        review_agent._evolution_restricted = True
         # Reuse the live model so it follows the user's configured model.
         review_agent.model = agent.model
         # Inject the evolution task brief AFTER the full system prompt: the agent

agent/evolution/prompts.py

@@ -130,17 +130,11 @@ them. When their signal is clear, act; do not be shy here.
 
 - Nothing worth evolving -> output exactly `[SILENT]` and nothing else.
 - Otherwise, after performing the edits, output a short user-facing summary in
-  the SAME LANGUAGE the user speaks in the conversation. Write it for an ordinary user, in plain
+  the SAME LANGUAGE the user speaks in the conversation transcript. Write it for an ordinary user, in plain
   everyday words — NOT a developer report. No need to expose internal details
-  (file names/paths, system mechanics, etc.). Tell the user, briefly:
-    1) that you just did a self-learning pass,
-    2) what you learned and what you changed in THIS pass ("remembered X" /
-       "improved the <name> skill" / "finished <task>").
-  Keep it to 1-3 lines. Generic shape (do not copy domain words):
-    "I just did a self-learning pass.
-     - Learned: <what you learned>
-     - Changed: <remembered it / improved the <name> skill / finished <task>>
-     Reply 'undo the last learning' if this is wrong."
+  (file names/paths, system mechanics, etc.). Briefly speak directly TO the user, telling them that you just did a self-learning pass,
+  what you learned, and what you changed in THIS pass. Keep it clear and focused on the key changes (a few lines), and let
+  the user know they can undo it.
 """
 
 
@@ -157,6 +151,11 @@ def build_review_user_message(transcript: str, protected_skills: list = None) ->
             "\n\nPROTECTED skills (built-in — never edit these): "
             f"{names}\n"
         )
+    try:
+        from common import i18n
+        lang_name = "中文" if i18n.is_zh() else "English"
+    except Exception:
+        lang_name = "中文"
     return (
         "Here is the conversation transcript that just went idle. Review it per "
         "your instructions. Acting is the exception: the main value is fixing or "
@@ -164,6 +163,7 @@ def build_review_user_message(transcript: str, protected_skills: list = None) ->
         "rare last resorts — stay [SILENT] unless there is a clear, durable signal "
         "not already covered."
         f"{protected_note}\n"
+        f"The summary should preferably be written in: {lang_name}\n"
         "<transcript>\n"
         f"{transcript}\n"
         "</transcript>"

agent/evolution/trigger.py

@@ -73,6 +73,20 @@ def note_user_turn(agent, channel_type: str = "", receiver: str = "") -> None:
         pass
 
 
+def mark_run_active(agent, active: bool) -> None:
+    """Flag whether the agent is mid-run, so idle scans skip a busy session.
+
+    Without this, a single run that lasts longer than idle_minutes would let
+    the scanner fire an evolution pass concurrently with the live turn.
+    """
+    try:
+        agent._evo_run_active = bool(active)
+        if active:
+            agent._evo_last_active = time.time()
+    except Exception:
+        pass
+
+
 def start_evolution_trigger(agent_bridge) -> None:
     """Start the idle-scan thread once per process (idempotent)."""
     if getattr(agent_bridge, "_evolution_trigger_started", False):
@@ -105,6 +119,10 @@ def _scan_once(agent_bridge, cfg) -> None:
     sessions = list(getattr(agent_bridge, "agents", {}).items())
     for session_id, agent in sessions:
         try:
+            # Skip sessions whose agent is mid-run: a long turn must not be
+            # reviewed while it is still producing the answer.
+            if getattr(agent, "_evo_run_active", False):
+                continue
             last_active = getattr(agent, "_evo_last_active", 0)
             turns = int(getattr(agent, "_evo_turns", 0))
             # Enough signal = enough turns OR enough context pressure.

agent/memory/embedding/provider.py

@@ -7,10 +7,14 @@ Supports multiple OpenAI-compatible embedding vendors:
   - dashscope  (Aliyun Tongyi text-embedding-v4)
   - doubao     (ByteDance Doubao Seed1.5 / large-text on Volcengine Ark)
   - zhipu      (ZhipuAI embedding-3)
+  - custom     (any OpenAI-compatible endpoint)
 
 Vendor keys here intentionally match the project's bot_type constants in
 common.const (OPENAI, LINKAI, QWEN_DASHSCOPE, DOUBAO, ZHIPU_AI).
 
+Custom providers (bot_type "custom" or "custom:<id>") reuse the same
+OpenAI-compatible REST client with user-supplied api_key / api_base.
+
 All providers share a single OpenAI-compatible REST client. Vendor-specific
 behaviors (truncation, query instruction prefix) are configured via metadata.
 """
@@ -138,6 +142,22 @@ EMBEDDING_VENDORS = {
         "query_instruction": "",
         "max_batch_size": 64,
     },
+    # Custom provider — any OpenAI-compatible /embeddings endpoint. The
+    # user must supply api_key + api_base + model via the web console
+    # (stored in custom_providers list or legacy custom_api_key / custom_api_base).
+    # Dimensions defaults to 1024 but can be overridden via config's
+    # embedding_dimensions. No dim-param support assumption — safest
+    # default for unknown endpoints.
+    "custom": {
+        "default_base_url": "",
+        "default_model": "",
+        "default_dimensions": 1024,
+        "supports_dim_param": False,
+        "needs_client_truncate": False,
+        "needs_client_normalize": True,
+        "query_instruction": "",
+        "max_batch_size": 64,
+    },
 }
 
 
@@ -472,10 +492,19 @@ def create_embedding_provider(
         )
 
     final_dim = dimensions if (dimensions and dimensions > 0) else meta["default_dimensions"]
+    resolved_model = model or meta["default_model"]
+    resolved_base = api_base or meta["default_base_url"]
+    # Custom providers require explicit api_base and model — they cannot
+    # fall back to OpenAI defaults like built-in vendors do.
+    if provider == "custom":
+        if not resolved_base:
+            raise ValueError("Custom embedding provider requires an api_base URL")
+        if not resolved_model:
+            raise ValueError("Custom embedding provider requires a model name")
     return OpenAIEmbeddingProvider(
-        model=model or meta["default_model"],
+        model=resolved_model,
         api_key=api_key,
-        api_base=api_base or meta["default_base_url"],
+        api_base=resolved_base,
         extra_headers=extra_headers,
         dimensions=final_dim,
         supports_dim_param=meta["supports_dim_param"],

agent/tools/bash/bash.py

@@ -24,6 +24,8 @@ class Bash(BaseTool):
     _IS_WIN = sys.platform == "win32"
     _PROGRESS_MAX_BYTES = 4 * 1024
     _PROGRESS_INTERVAL = 0.5
+    # cmd.exe command line limit is ~8191 chars; rewrite python -c above this.
+    _WIN_CMD_SAFE_LEN = 7000
 
     name: str = "bash"
     description: str = f"""Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last {DEFAULT_MAX_LINES} lines or {DEFAULT_MAX_BYTES // 1024}KB (whichever is hit first). If truncated, full output is saved to a temp file.
@@ -111,19 +113,35 @@ SAFETY:
             else:
                 logger.debug(f"[Bash] Process User: {os.environ.get('USERNAME', os.environ.get('USER', 'unknown'))}")
             
+            # Temp script written for long `python -c` commands (Windows only),
+            # cleaned up after execution.
+            temp_script_path = None
+
             # On Windows, convert $VAR references to %VAR% for cmd.exe
             if self._IS_WIN:
                 env["PYTHONIOENCODING"] = "utf-8"
                 command = self._convert_env_vars_for_windows(command, dotenv_vars)
+                # cmd.exe has an ~8191 char command line limit. Long
+                # `python -c "..."` commands silently fail, so spill the inline
+                # code into a temp .py file and run that instead.
+                if len(command) > self._WIN_CMD_SAFE_LEN:
+                    command, temp_script_path = self._rewrite_long_python_c(command)
                 if command and not command.strip().lower().startswith("chcp"):
                     command = f"chcp 65001 >nul 2>&1 && {command}"
 
-            result = self._run_streaming(
-                command,
-                timeout,
-                env,
-                dotenv_vars,
-            )
+            try:
+                result = self._run_streaming(
+                    command,
+                    timeout,
+                    env,
+                    dotenv_vars,
+                )
+            finally:
+                if temp_script_path:
+                    try:
+                        os.remove(temp_script_path)
+                    except OSError:
+                        pass
             
             logger.debug(f"[Bash] Exit code: {result.returncode}")
             logger.debug(f"[Bash] Stdout length: {len(result.stdout)}")
@@ -391,3 +409,43 @@ SAFETY:
             return m.group(0)
 
         return re.sub(r'\$\{(\w+)\}|\$(\w+)', replace_match, command)
+
+    @staticmethod
+    def _rewrite_long_python_c(command: str):
+        """
+        Rewrite `python -c "<code>"` into `python <tempfile>` to bypass the
+        cmd.exe command line length limit on Windows.
+
+        Returns (new_command, temp_file_path). On any parse failure the original
+        command and None are returned, so behavior is unchanged when unmatched.
+        """
+        # Match: <python|python3|py> [flags] -c "<code>" (single or double quoted)
+        m = re.search(
+            r'^(?P<prefix>.*?\b(?:python3?|py)\b[^\n]*?\s-c\s+)'
+            r'(?P<quote>["\'])(?P<code>.*)(?P=quote)\s*(?P<suffix>.*)$',
+            command,
+            re.DOTALL,
+        )
+        if not m:
+            return command, None
+
+        quote = m.group("quote")
+        code = m.group("code")
+        # Reverse common shell-level escaping of the quote char inside the code.
+        code = code.replace("\\" + quote, quote)
+
+        try:
+            fd, path = tempfile.mkstemp(suffix=".py", prefix="bash-pyc-")
+            with os.fdopen(fd, "w", encoding="utf-8") as f:
+                f.write(code)
+        except OSError:
+            return command, None
+
+        prefix = m.group("prefix")
+        # Drop the trailing "-c " from the prefix, keep the interpreter + flags.
+        interp = re.sub(r'\s-c\s+$', ' ', prefix).rstrip()
+        suffix = m.group("suffix").strip()
+        new_command = f'{interp} "{path}"'
+        if suffix:
+            new_command += f' {suffix}'
+        return new_command, path

agent/tools/browser/browser_tool.py

@@ -15,15 +15,24 @@ Launch modes (configured under `tools.browser` in config.json):
   - fresh: Set `persistent` to false to fall back to a clean context every run.
 """
 
+import ipaddress
 import json
 import os
+import socket
 from typing import Dict, Any, Optional
+from urllib.parse import urlparse
 
 from agent.tools.base_tool import BaseTool, ToolResult
 from agent.tools.browser.browser_service import BrowserService
 from common.log import logger
 
 
+# Cloud-metadata endpoints worth blocking even though they are not link-local.
+# (169.254.169.254 — AWS/GCP/Azure IMDS — is already covered by is_link_local;
+# fd00:ec2::254 is the AWS IPv6 IMDS address.)
+_CLOUD_METADATA_IPS = frozenset({ipaddress.ip_address("fd00:ec2::254")})
+
+
 class BrowserTool(BaseTool):
     """Single tool exposing all browser actions via an 'action' parameter."""
 
@@ -121,6 +130,61 @@ class BrowserTool(BaseTool):
         BrowserTool._shared_service = self._service
         return self._service
 
+    def _allow_private_targets(self) -> bool:
+        """Whether the link-local / cloud-metadata guard is disabled.
+
+        Defaults to False (guard active). Loopback and RFC1918/LAN targets are
+        always reachable so local dev servers work out of the box; this opt-out
+        only lifts the remaining block on link-local / cloud-metadata targets,
+        for an operator who deliberately needs them, by setting
+        ``allow_private_targets: true`` under ``tools.browser`` in config.json.
+        """
+        return bool(self.config.get("allow_private_targets", False))
+
+    @staticmethod
+    def _validate_url_safe(url: str) -> None:
+        """Reject URLs that target link-local / cloud-metadata addresses (SSRF guard).
+
+        Resolves the hostname to its IP address(es) and blocks any that are
+        link-local (169.254.0.0/16 — which includes the 169.254.169.254
+        cloud-metadata endpoint — and IPv6 fe80::/10) or a known IPv6
+        cloud-metadata address. Also rejects URLs with no host, non-HTTP(S)
+        schemes, or hosts that fail DNS resolution.
+
+        Loopback and RFC1918/LAN targets are intentionally left reachable:
+        unlike the vision/web_fetch tools, the browser legitimately opens local
+        pages (a dev server on ``localhost`` / ``127.0.0.1`` / a LAN IP), so a
+        blanket "block all internal" policy would break that core workflow.
+
+        Raises:
+            ValueError: if the URL targets a disallowed address.
+        """
+        parsed = urlparse(url)
+        if parsed.scheme not in ("http", "https"):
+            raise ValueError(f"Unsupported URL scheme: {parsed.scheme}")
+
+        hostname = parsed.hostname
+        if not hostname:
+            raise ValueError("URL has no hostname")
+
+        try:
+            # Resolve all addresses for the hostname.
+            addr_infos = socket.getaddrinfo(hostname, None, socket.AF_UNSPEC, socket.SOCK_STREAM)
+        except socket.gaierror:
+            raise ValueError(f"Cannot resolve hostname: {hostname}")
+
+        for family, _, _, _, sockaddr in addr_infos:
+            ip_str = sockaddr[0]
+            ip = ipaddress.ip_address(ip_str)
+            # Block only the high-risk targets — link-local (incl. the
+            # 169.254.169.254 cloud-metadata endpoint) and the IPv6 metadata
+            # address. Loopback and RFC1918/LAN stay reachable for local dev.
+            if ip.is_link_local or ip in _CLOUD_METADATA_IPS:
+                raise ValueError(
+                    f"URL resolves to a link-local / cloud-metadata address "
+                    f"({ip_str}), request blocked for security"
+                )
+
     def execute(self, args: Dict[str, Any]) -> ToolResult:
         action = args.get("action", "").strip().lower()
         if not action:
@@ -148,6 +212,16 @@ class BrowserTool(BaseTool):
         # Only auto-prepend https:// for bare hosts; preserve file://, about:, data:, etc.
         if "://" not in url and not url.startswith(("about:", "data:")):
             url = "https://" + url
+        # SSRF guard: for http(s) targets, reject hosts that resolve to
+        # link-local / cloud-metadata addresses before the browser navigates
+        # (and then auto-snapshots the page back to the model). Loopback and
+        # RFC1918/LAN are allowed so local dev servers work. Non-HTTP schemes
+        # (about:/data:/file:/chrome:) are not network-egress targets here.
+        if url.split(":", 1)[0].lower() in ("http", "https") and not self._allow_private_targets():
+            try:
+                self._validate_url_safe(url)
+            except ValueError as e:
+                return ToolResult.fail(f"Error: {e}")
         timeout = args.get("timeout", 30000)
         service = self._get_service()
         result = service.navigate(url, timeout=timeout)

agent/tools/memory/memory_get.py

@@ -4,6 +4,8 @@ Memory get tool
 Allows agents to read specific sections from memory files
 """
 
+import os
+
 from agent.tools.base_tool import BaseTool
 
 
@@ -87,8 +89,13 @@ class MemoryGetTool(BaseTool):
             
             file_path = (workspace_dir / path).resolve()
             workspace_resolved = workspace_dir.resolve()
-            
-            if not str(file_path).startswith(str(workspace_resolved) + '/') and file_path != workspace_resolved:
+
+            # Use os.path.realpath + os.sep for cross-platform path validation.
+            # str(Path).startswith(str + '/') fails on Windows where Path uses
+            # backslashes — see MemoryService._resolve_path for the same pattern.
+            real_file = os.path.realpath(str(file_path))
+            real_workspace = os.path.realpath(str(workspace_resolved))
+            if real_file != real_workspace and not real_file.startswith(real_workspace + os.sep):
                 return ToolResult.fail(f"Error: Access denied: path outside workspace")
             
             if not file_path.exists():

agent/tools/scheduler/task_store.py

@@ -182,8 +182,15 @@ class TaskStore:
         if enabled_only:
             task_list = [t for t in task_list if t.get("enabled", True)]
         
-        # Sort by next_run_at
-        task_list.sort(key=lambda t: t.get("next_run_at", float('inf')))
+        # Sort by enabled status (enabled first), then by next_run_at
+        def sort_key(t):
+            enabled = t.get("enabled", True)
+            next_run = t.get("next_run_at", "")
+            # Enabled tasks first (0), disabled tasks second (1)
+            # Then sort by next_run_at (empty string sorts last)
+            return (0 if enabled else 1, next_run if next_run else "9999-12-31")
+        
+        task_list.sort(key=sort_key)
         
         return task_list
     

agent/tools/tool_manager.py

@@ -523,6 +523,16 @@ class ToolManager:
         if agent is None or not hasattr(agent, "tools"):
             return ([], [])
 
+        # Never re-inject MCP tools into a restricted Self-Evolution review agent.
+        # The review agent is created with a deliberately reduced, workspace-guarded
+        # toolset; silently re-adding configured MCP tools here would bypass that
+        # policy boundary (see agent/evolution/executor.py). The flag may live on
+        # the agent itself (Agent) or on the wrapping stream executor's .agent.
+        if getattr(agent, "_evolution_restricted", False) or getattr(
+            getattr(agent, "agent", None), "_evolution_restricted", False
+        ):
+            return ([], [])
+
         from agent.tools.mcp.mcp_tool import McpTool
         current = self._mcp_tool_instances
         registry_names = set(current.keys())

agent/tools/utils/__init__.py

@@ -20,6 +20,11 @@ from .diff import (
     FuzzyMatchResult
 )
 
+from .url_safety import (
+    validate_url_safe,
+    assert_public_ip
+)
+
 __all__ = [
     'truncate_head',
     'truncate_tail',
@@ -36,5 +41,7 @@ __all__ = [
     'normalize_for_fuzzy_match',
     'fuzzy_find_text',
     'generate_diff_string',
-    'FuzzyMatchResult'
+    'FuzzyMatchResult',
+    'validate_url_safe',
+    'assert_public_ip'
 ]

agent/tools/utils/url_safety.py

@@ -0,0 +1,66 @@
+"""
+Shared SSRF guard utilities for tools that fetch model-supplied URLs.
+
+A URL is only considered safe when it uses an http/https scheme, has a
+hostname, that hostname resolves, and every resolved address is a public
+(internet-routable) address. Loopback, private (RFC1918 / ULA), link-local
+(incl. the 169.254.169.254 cloud-metadata endpoint) and otherwise reserved
+addresses are rejected, for both IPv4 and IPv6.
+"""
+
+import ipaddress
+import socket
+from urllib.parse import urlparse
+
+
+def _is_blocked_ip(ip: "ipaddress._BaseAddress") -> bool:
+    """Return True if the address is not safe to connect to (non-public)."""
+    return (
+        ip.is_private
+        or ip.is_loopback
+        or ip.is_link_local
+        or ip.is_reserved
+        or ip.is_multicast
+        or ip.is_unspecified
+    )
+
+
+def assert_public_ip(ip_str: str) -> None:
+    """Raise ValueError if the given literal IP is a non-public address.
+
+    Used to re-validate the concrete address a redirect resolved to.
+    """
+    ip = ipaddress.ip_address(ip_str)
+    if _is_blocked_ip(ip):
+        raise ValueError(
+            f"URL resolves to a non-public address ({ip_str}), "
+            f"request blocked for security"
+        )
+
+
+def validate_url_safe(url: str) -> None:
+    """Reject URLs that target private/loopback/link-local addresses (SSRF guard).
+
+    Resolves the hostname to its IP address(es) and blocks any that fall
+    into non-public ranges. Also rejects URLs with no host, non-HTTP(S)
+    schemes, or hosts that fail DNS resolution.
+
+    Raises:
+        ValueError: if the URL targets a disallowed address.
+    """
+    parsed = urlparse(url)
+    if parsed.scheme not in ("http", "https"):
+        raise ValueError(f"Unsupported URL scheme: {parsed.scheme}")
+
+    hostname = parsed.hostname
+    if not hostname:
+        raise ValueError("URL has no hostname")
+
+    try:
+        # Resolve all addresses for the hostname.
+        addr_infos = socket.getaddrinfo(hostname, None, socket.AF_UNSPEC, socket.SOCK_STREAM)
+    except socket.gaierror:
+        raise ValueError(f"Cannot resolve hostname: {hostname}")
+
+    for family, _, _, _, sockaddr in addr_infos:
+        assert_public_ip(sockaddr[0])

agent/tools/vision/vision.py

@@ -17,18 +17,16 @@ Provider resolution:
 """
 
 import base64
-import ipaddress
 import os
-import socket
 import subprocess
 import tempfile
 from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional
-from urllib.parse import urlparse
 
 import requests
 
 from agent.tools.base_tool import BaseTool, ToolResult
+from agent.tools.utils.url_safety import validate_url_safe
 from common import const
 from common.log import logger
 from config import conf
@@ -333,6 +331,12 @@ class Vision(BaseTool):
           - None       : unknown provider id, or the bot can't be created.
                          Caller falls through to model-name-based routing.
         """
+        # Custom OpenAI-compatible providers — read credentials from
+        # custom_providers list, same pattern as embedding.
+        if provider_id.startswith("custom:"):
+            p = self._build_custom_provider(provider_id, user_model)
+            return [p] if p else None
+
         display_name = _PROVIDER_ID_TO_DISPLAY.get(provider_id)
         if not display_name:
             return None
@@ -598,6 +602,34 @@ class Vision(BaseTool):
             model_override=preferred_model,
         )
 
+    def _build_custom_provider(self, provider_id: str, preferred_model: Optional[str] = None) -> Optional[VisionProvider]:
+        """Build a VisionProvider from a custom:<id> entry in custom_providers.
+        Uses the standard OpenAI /chat/completions endpoint — any
+        OpenAI-compatible multimodal endpoint works."""
+        from models.custom_provider import parse_custom_bot_type, get_custom_providers, _find_provider_by_id
+        _, custom_id = parse_custom_bot_type(provider_id)
+        if not custom_id:
+            return None
+        entry = _find_provider_by_id(get_custom_providers(), custom_id)
+        if not entry:
+            logger.warning(f"[Vision] custom provider '{provider_id}' not found in custom_providers")
+            return None
+        api_key = (entry.get("api_key") or "").strip()
+        api_base = (entry.get("api_base") or "").strip()
+        if not api_key or not api_base:
+            logger.warning(f"[Vision] custom provider '{provider_id}' missing api_key or api_base")
+            return None
+        model = preferred_model or entry.get("model") or ""
+        if not model:
+            logger.warning(f"[Vision] custom provider '{provider_id}' has no model configured")
+            return None
+        return VisionProvider(
+            name=entry.get("name") or provider_id,
+            api_key=api_key,
+            api_base=self._ensure_v1(api_base.rstrip("/")),
+            model_override=model,
+        )
+
     def _call_via_bot(self, model: str, question: str, image_content: dict,
                       provider: Optional[VisionProvider] = None) -> ToolResult:
         """
@@ -665,31 +697,13 @@ class Vision(BaseTool):
         into non-public ranges.  Also rejects URLs with no host, non-HTTP(S)
         schemes, or hosts that fail DNS resolution.
 
+        Delegates to the shared ``agent.tools.utils.url_safety`` helper so the
+        same guard protects every tool that fetches model-supplied URLs.
+
         Raises:
             ValueError: if the URL targets a disallowed address.
         """
-        parsed = urlparse(url)
-        if parsed.scheme not in ("http", "https"):
-            raise ValueError(f"Unsupported URL scheme: {parsed.scheme}")
-
-        hostname = parsed.hostname
-        if not hostname:
-            raise ValueError("URL has no hostname")
-
-        try:
-            # Resolve all addresses for the hostname.
-            addr_infos = socket.getaddrinfo(hostname, None, socket.AF_UNSPEC, socket.SOCK_STREAM)
-        except socket.gaierror:
-            raise ValueError(f"Cannot resolve hostname: {hostname}")
-
-        for family, _, _, _, sockaddr in addr_infos:
-            ip_str = sockaddr[0]
-            ip = ipaddress.ip_address(ip_str)
-            if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
-                raise ValueError(
-                    f"URL resolves to a non-public address ({ip_str}), "
-                    f"request blocked for security"
-                )
+        validate_url_safe(url)
 
     def _build_image_content(self, image: str) -> dict:
         """

agent/tools/web_fetch/web_fetch.py

@@ -16,11 +16,15 @@ import requests
 
 from agent.tools.base_tool import BaseTool, ToolResult
 from agent.tools.utils.truncate import truncate_head, format_size
+from agent.tools.utils.url_safety import validate_url_safe
 from common.log import logger
 
 
 DEFAULT_TIMEOUT = 30
 MAX_FILE_SIZE = 50 * 1024 * 1024  # 50MB
+# Cap on how many redirects we follow; each hop's target is re-validated
+# against the SSRF guard so a public URL cannot bounce us into an internal one.
+MAX_REDIRECTS = 10
 
 DEFAULT_HEADERS = {
     "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36",
@@ -107,23 +111,65 @@ class WebFetch(BaseTool):
         if parsed.scheme not in ("http", "https"):
             return ToolResult.fail("Error: Invalid URL (must start with http:// or https://)")
 
+        # SSRF guard: reject URLs that resolve to private/loopback/link-local/
+        # cloud-metadata addresses before any request is issued.
+        try:
+            validate_url_safe(url)
+        except ValueError as e:
+            return ToolResult.fail(f"Error: {e}")
+
         if _is_document_url(url):
             return self._fetch_document(url)
 
         return self._fetch_webpage(url)
 
+    # ---- Safe request helper ----
+
+    @staticmethod
+    def _safe_get(url: str, **kwargs) -> requests.Response:
+        """Issue a GET request while re-validating every redirect hop (SSRF guard).
+
+        Auto-redirect is disabled and each hop is followed manually so the
+        target of every redirect is re-resolved and checked against the SSRF
+        guard. This prevents a public URL from 3xx-bouncing into a private,
+        loopback, link-local or cloud-metadata address. ``kwargs`` are passed
+        through to ``requests.get`` (e.g. ``stream``).
+
+        Raises:
+            ValueError: if any hop resolves to a non-public address.
+        """
+        kwargs.pop("allow_redirects", None)
+        current = url
+        for _ in range(MAX_REDIRECTS + 1):
+            response = requests.get(
+                current,
+                headers=DEFAULT_HEADERS,
+                timeout=DEFAULT_TIMEOUT,
+                allow_redirects=False,
+                **kwargs,
+            )
+            if not response.is_redirect and not response.is_permanent_redirect:
+                return response
+
+            location = response.headers.get("Location")
+            if not location:
+                return response
+
+            # Resolve the redirect target relative to the current URL, then
+            # re-validate it before following.
+            current = requests.compat.urljoin(current, location)
+            validate_url_safe(current)
+            response.close()
+
+        raise ValueError(f"Too many redirects (>{MAX_REDIRECTS})")
+
     # ---- Web page fetching ----
 
     def _fetch_webpage(self, url: str) -> ToolResult:
         """Fetch and extract readable text from an HTML web page."""
         parsed = urlparse(url)
         try:
-            response = requests.get(
-                url,
-                headers=DEFAULT_HEADERS,
-                timeout=DEFAULT_TIMEOUT,
-                allow_redirects=True,
-            )
+            response = self._safe_get(url)
             response.raise_for_status()
         except requests.Timeout:
             return ToolResult.fail(f"Error: Request timed out after {DEFAULT_TIMEOUT}s")
@@ -131,6 +177,8 @@ class WebFetch(BaseTool):
             return ToolResult.fail(f"Error: Failed to connect to {parsed.netloc}")
         except requests.HTTPError as e:
             return ToolResult.fail(f"Error: HTTP {e.response.status_code} for URL: {url}")
+        except ValueError as e:
+            return ToolResult.fail(f"Error: {e}")
         except Exception as e:
             return ToolResult.fail(f"Error: Failed to fetch URL: {e}")
 
@@ -158,13 +206,7 @@ class WebFetch(BaseTool):
         logger.info(f"[WebFetch] Downloading document: {url} -> {local_path}")
 
         try:
-            response = requests.get(
-                url,
-                headers=DEFAULT_HEADERS,
-                timeout=DEFAULT_TIMEOUT,
-                stream=True,
-                allow_redirects=True,
-            )
+            response = self._safe_get(url, stream=True)
             response.raise_for_status()
 
             content_length = int(response.headers.get("Content-Length", 0))
@@ -191,6 +233,9 @@ class WebFetch(BaseTool):
             return ToolResult.fail(f"Error: Failed to connect to {parsed.netloc}")
         except requests.HTTPError as e:
             return ToolResult.fail(f"Error: HTTP {e.response.status_code} for URL: {url}")
+        except ValueError as e:
+            self._cleanup_file(local_path)
+            return ToolResult.fail(f"Error: {e}")
         except Exception as e:
             self._cleanup_file(local_path)
             return ToolResult.fail(f"Error: Failed to download file: {e}")