feat(ai): durcissement phase F (#79) - rate limit, redaction, OpenAPI/MCP, E2E

backend/tools/api.py

@@ -17,11 +17,22 @@ from backend.tools.context import (
     ToolMode,
     ToolNotFoundError,
     ToolPermissionError,
+    ToolRateLimitError,
     ToolRisk,
     ToolScope,
     ToolValidationError,
     resolve_safe_path,
 )
+from backend.tools.ratelimit import (
+    check_and_record as check_tool_rate_limit,
+)
+from backend.tools.ratelimit import (
+    get_status as get_tool_rate_limit_status,
+)
+from backend.tools.ratelimit import (
+    reset as reset_tool_rate_limit,
+)
+from backend.tools.redaction import redact_payload
 from backend.tools.registry import (
     ToolSpec,
     call_tool,
@@ -39,15 +50,20 @@ __all__ = [
     "ToolMode",
     "ToolNotFoundError",
     "ToolPermissionError",
+    "ToolRateLimitError",
     "ToolResult",
     "ToolRisk",
     "ToolScope",
     "ToolSpec",
     "ToolValidationError",
     "call_tool",
+    "check_tool_rate_limit",
     "get_tool",
+    "get_tool_rate_limit_status",
     "get_tool_schemas",
     "list_tools",
+    "redact_payload",
+    "reset_tool_rate_limit",
     "resolve_safe_path",
     "tool",
 ]

backend/tools/context.py

@@ -102,6 +102,21 @@ class ToolConfirmationRequired(ToolError):
         return payload
 
 
+class ToolRateLimitError(ToolError):
+    """Raised when an identity exceeds its tool-call rate limit (Phase F)."""
+
+    code = "rate_limited"
+
+    def __init__(self, tool: str, retry_after: int = 0, message: str | None = None):
+        super().__init__(
+            message or f"Rate limit exceeded for tool '{tool}'",
+            code="rate_limited",
+            details={"tool": tool, "retry_after": retry_after},
+        )
+        self.tool = tool
+        self.retry_after = retry_after
+
+
 @dataclass
 class ToolContext:
     """Carries the caller identity and execution options for a tool call.
@@ -126,6 +141,21 @@ class ToolContext:
     def username(self) -> str:
         return self.user.get("username", "unknown")
 
+    @property
+    def rate_limit_identity(self) -> str:
+        """Identity used by the per-token/per-tool rate limiter.
+
+        Prefers the JWT id (``_token_jti``, attached by the auth middleware),
+        then an explicit ``token_id`` in :attr:`metadata`, then the user id and
+        finally the username. This yields per-token limiting when a token id is
+        available and per-account limiting otherwise.
+        """
+        token_id = self.metadata.get("token_id") or self.user.get("_token_jti")
+        if token_id:
+            return f"token:{token_id}"
+        user_id = self.user.get("id") or self.user.get("username")
+        return f"user:{user_id or 'anonymous'}"
+
     def has_vault_access(self, vault: str) -> bool:
         """Return True if the caller may access *vault*."""
         return bool(vault) and check_vault_access(vault, self.user)

backend/tools/ratelimit.py

@@ -0,0 +1,153 @@
+"""Rate limiting for the AI tool layer (Phase F).
+
+Complements the IP-based login limiter (``backend.ratelimit``) with a
+per-identity, per-tool sliding-window limiter applied to every tool call,
+whether it originates from the in-app assistant or the MCP server.
+
+Two counters are maintained per identity:
+
+* a **global** counter (all tools combined), capped by
+  ``OBSIGATE_TOOL_RATE_LIMIT``;
+* a **per-tool** counter, capped by ``OBSIGATE_TOOL_RATE_LIMIT_PER_TOOL``
+  (defaults to the global cap) so a single expensive tool cannot consume the
+  whole budget.
+
+The window length is ``OBSIGATE_TOOL_RATE_WINDOW`` seconds (default 60).
+
+The identity is the token JTI when available (``_token_jti`` attached by the
+auth middleware), otherwise the user id/username. This gives "per token / per
+tool" limiting while remaining meaningful for anonymous/disabled-auth mode.
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+import time
+from collections import deque
+from typing import Any
+
+logger = logging.getLogger("obsigate.tools.ratelimit")
+
+# --- Configuration (read at call time so tests can monkeypatch env) ---
+DEFAULT_RATE_LIMIT = 60
+DEFAULT_RATE_WINDOW = 60
+
+
+def _env_int(name: str, default: int) -> int:
+    try:
+        return int(os.environ.get(name, str(default)))
+    except (TypeError, ValueError):
+        return default
+
+
+def _global_limit() -> int:
+    return _env_int("OBSIGATE_TOOL_RATE_LIMIT", DEFAULT_RATE_LIMIT)
+
+
+def _per_tool_limit() -> int:
+    return _env_int("OBSIGATE_TOOL_RATE_LIMIT_PER_TOOL", _global_limit())
+
+
+def _window() -> int:
+    return max(1, _env_int("OBSIGATE_TOOL_RATE_WINDOW", DEFAULT_RATE_WINDOW))
+
+
+# --- In-memory store: {counter_key: deque[timestamp]} ---
+_calls: dict[str, deque] = {}
+
+
+def _identity_key(identity: str | None) -> str:
+    return identity or "anonymous"
+
+
+def _counter_key(identity: str | None, tool: str | None) -> str:
+    base = _identity_key(identity)
+    return f"{base}\x00{tool}" if tool else base
+
+
+def _prune(entries: deque, now: float, window: int) -> None:
+    cutoff = now - window
+    while entries and entries[0] <= cutoff:
+        entries.popleft()
+
+
+def check_and_record(identity: str | None, tool: str, *, now: float | None = None) -> tuple[bool, int]:
+    """Record one call and report whether it is allowed.
+
+    Args:
+        identity: Rate-limit identity (token JTI or username).
+        tool: Tool name (used for the per-tool counter).
+        now: Optional timestamp override (tests).
+
+    Returns:
+        ``(allowed, retry_after)``. When ``allowed`` is False, ``retry_after``
+        is the number of seconds until the oldest call leaves the window.
+    """
+    now = time.time() if now is None else now
+    window = _window()
+    global_limit = _global_limit()
+    tool_limit = _per_tool_limit()
+
+    global_entries = _calls.setdefault(_counter_key(identity, None), deque())
+    tool_entries = _calls.setdefault(_counter_key(identity, tool), deque())
+    _prune(global_entries, now, window)
+    _prune(tool_entries, now, window)
+
+    if len(global_entries) >= global_limit or len(tool_entries) >= tool_limit:
+        oldest = min(
+            global_entries[0] if len(global_entries) >= global_limit else now,
+            tool_entries[0] if len(tool_entries) >= tool_limit else now,
+        )
+        retry_after = max(1, int(oldest + window - now) + 1)
+        logger.warning(f"Tool rate limit exceeded for '{_identity_key(identity)}' on '{tool}'")
+        return False, retry_after
+
+    global_entries.append(now)
+    tool_entries.append(now)
+    return True, 0
+
+
+def remaining(identity: str | None, tool: str | None = None) -> int:
+    """Return the number of calls still allowed in the current window."""
+    now = time.time()
+    window = _window()
+    if tool:
+        entries = _calls.get(_counter_key(identity, tool))
+        if entries is None:
+            return _per_tool_limit()
+        _prune(entries, now, window)
+        return max(0, _per_tool_limit() - len(entries))
+    entries = _calls.get(_counter_key(identity, None))
+    if entries is None:
+        return _global_limit()
+    _prune(entries, now, window)
+    return max(0, _global_limit() - len(entries))
+
+
+def reset(identity: str | None = None) -> None:
+    """Clear rate-limit state (all identities, or a single one)."""
+    if identity is None:
+        _calls.clear()
+        return
+    prefix = f"{_identity_key(identity)}\x00"
+    for key in [k for k in _calls if k == _identity_key(identity) or k.startswith(prefix)]:
+        del _calls[key]
+
+
+def get_status(identity: str | None = None) -> dict[str, Any]:
+    """Diagnostic snapshot of the limiter (for tests / admin tooling)."""
+    if identity is None:
+        return {
+            "tracked_identities": len({k.split("\x00", 1)[0] for k in _calls}),
+            "global_limit": _global_limit(),
+            "per_tool_limit": _per_tool_limit(),
+            "window_seconds": _window(),
+        }
+    return {
+        "identity": _identity_key(identity),
+        "remaining_global": remaining(identity),
+        "global_limit": _global_limit(),
+        "per_tool_limit": _per_tool_limit(),
+        "window_seconds": _window(),
+    }

backend/tools/redaction.py

@@ -0,0 +1,39 @@
+"""Secret redaction for tool results (Phase F).
+
+Tool results are fed back to the LLM (in-app agent loop) or returned to an
+external MCP client, so they must never leak credentials. ``read_file`` and
+``read_file_raw`` already redact through the shared file service, but other
+tools (``diff_backup``, ``search_*``) return content that has not been through
+the redactor. This module applies :func:`backend.secret_redactor.redact` to
+every string in a tool payload, recursively.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+from backend.secret_redactor import redact
+
+_MAX_DEPTH = 12
+
+
+def redact_payload(payload: Any, _depth: int = 0) -> Any:
+    """Return a copy of *payload* with every string secret-redacted.
+
+    Walks dicts, lists and tuples; scalars are returned unchanged. Strings are
+    run through :func:`backend.secret_redactor.redact`. A recursion cap avoids
+    pathological/cyclic structures (tool results are JSON-serialisable, so
+    cycles should not occur, but the guard keeps this safe).
+    """
+    if _depth > _MAX_DEPTH:
+        return payload
+    if isinstance(payload, str):
+        redacted, count = redact(payload)
+        return redacted if count else payload
+    if isinstance(payload, dict):
+        return {key: redact_payload(value, _depth + 1) for key, value in payload.items()}
+    if isinstance(payload, list):
+        return [redact_payload(item, _depth + 1) for item in payload]
+    if isinstance(payload, tuple):
+        return tuple(redact_payload(item, _depth + 1) for item in payload)
+    return payload

backend/tools/registry.py

@@ -26,10 +26,13 @@ from backend.tools.context import (
     ToolError,
     ToolNotFoundError,
     ToolPermissionError,
+    ToolRateLimitError,
     ToolRisk,
     ToolScope,
     ToolValidationError,
 )
+from backend.tools.ratelimit import check_and_record
+from backend.tools.redaction import redact_payload
 from backend.tools.schemas import ToolResult
 
 logger = logging.getLogger("obsigate.tools.registry")
@@ -186,6 +189,12 @@ def call_tool(
         _audit(ctx, spec, arguments, ok=False, error=error.code)
         raise error from e
 
+    allowed, retry_after = check_and_record(ctx.rate_limit_identity, spec.name)
+    if not allowed:
+        rate_error = ToolRateLimitError(spec.name, retry_after)
+        _audit(ctx, spec, arguments, ok=False, error=rate_error.code)
+        raise rate_error
+
     vault = getattr(params, "vault", None)
     if spec.requires_vault and vault:
         try:
@@ -223,4 +232,6 @@ def call_tool(
     duration_ms = round((time.perf_counter() - started) * 1000, 2)
     logger.debug(f"Tool '{name}' ok in {duration_ms}ms")
     _audit(ctx, spec, arguments, ok=True)
-    return ToolResult(ok=True, data=data)
+    # Never forward raw secrets to the model (defense in depth: some tools —
+    # diffs, search snippets — return content that was not pre-redacted).
+    return ToolResult(ok=True, data=redact_payload(data))

backend/tools/service.py

@@ -11,6 +11,7 @@ confirmation mechanism (two-step propose/apply).
 from __future__ import annotations
 
 import logging
+import os
 from typing import Any
 
 from backend.indexer import get_backlinks as _get_backlinks
@@ -90,8 +91,9 @@ from backend.tools.schemas import (
 
 logger = logging.getLogger("obsigate.tools.service")
 
-# Maximum file size returned by ``read_file`` (bytes).
-TOOL_MAX_READ_BYTES = 200_000
+# Maximum file size returned by ``read_file`` (bytes). Quota configurable via
+# ``BOOKSLM_MAX_TOOL_READ_BYTES``.
+TOOL_MAX_READ_BYTES = int(os.environ.get("BOOKSLM_MAX_TOOL_READ_BYTES", "200000"))
 
 
 # ── C1. Vaults / navigation ────────────────────────────────────────────────