Add dlp.outbound_on_match policy (block | redact | supervise)

Give each egress route a policy for what the proxy does when an outbound
DLP detector matches a token, defaulting to the supervise flow added in
the previous commit. The goal is cutting false-positive friction without
weakening default-deny.

- redact: scrub the matched value(s) from the body, non-host headers, and
  path/query via redact_tokens, then re-scan. Forward if clean; fail
  closed with a 403 if a match remains on a surface redaction can't
  rewrite (the hostname, or a unicode-evasion token). For routes where a
  token-shaped value is noise the upstream doesn't need.
- block: the original hard 403, never overridable.
- supervise (default, unset): hold the request for operator approval.

Structural blocks (CRLF, no safelist-able value) stay hard 403s under
every policy.

Threads outbound_on_match from the bottle manifest (manifest_egress)
through the resolved EgressRoute and rendered routes.yaml (egress.py) to
the addon's Route (egress_addon_core), and round-trips it via the
list-egress-routes introspection endpoint. The allow/egress-block tool
descriptions document the new key.

Tests: manifest parse/validation, core parse/validation, full
manifest->render->addon round-trip for redact. README + PRD 0062 updated.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HnvBjPZC5V7qeQpFbQdDmS

bot_bottle/egress.py

@@ -95,6 +95,7 @@ def egress_manifest_routes(
             git_fetch=r.GitFetch,
             outbound_detectors=r.OutboundDetectors,
             inbound_detectors=r.InboundDetectors,
+            outbound_on_match=r.OutboundOnMatch,
         ))
     return tuple(out)
 
@@ -177,7 +178,11 @@ def _route_to_yaml_fields(r: Route) -> dict[str, object]:
         fields["matches"] = matches_data
     if r.git_fetch:
         fields["git"] = {"fetch": True}
-    if r.outbound_detectors is not None or r.inbound_detectors is not None:
+    if (
+        r.outbound_detectors is not None
+        or r.inbound_detectors is not None
+        or r.outbound_on_match
+    ):
         dlp: dict[str, object] = {}
         if r.outbound_detectors is not None:
             dlp["outbound_detectors"] = (
@@ -189,6 +194,8 @@ def _route_to_yaml_fields(r: Route) -> dict[str, object]:
                 False if not r.inbound_detectors
                 else list(r.inbound_detectors)
             )
+        if r.outbound_on_match:
+            dlp["outbound_on_match"] = r.outbound_on_match
         fields["dlp"] = dlp
     return fields
 
@@ -260,6 +267,8 @@ def egress_render_routes(
                 elif isinstance(dv, list):
                     items_str = ", ".join(f'"{x}"' for x in dv)
                     lines.append(f"      {dk}: [{items_str}]")
+                elif isinstance(dv, str):
+                    lines.append(f'      {dk}: "{dv}"')
     return "\n".join(lines) + "\n"
 
 

bot_bottle/egress_addon.py

@@ -17,7 +17,11 @@ from mitmproxy import http  # type: ignore[import-not-found]  # pylint: disable=
 from egress_addon_core import (  # type: ignore[import-not-found]  # pylint: disable=import-error
     LOG_BLOCKS,
     LOG_FULL,
+    DEFAULT_OUTBOUND_ON_MATCH,
+    ON_MATCH_BLOCK,
+    ON_MATCH_REDACT,
     Config,
+    Route,
     ScanResult,
     build_inbound_scan_text,
     build_outbound_scan_text,
@@ -189,37 +193,11 @@ class EgressAddon:
         # Hostname is included to catch DNS-tunnelling exfiltration attempts.
         route = match_route(self.config.routes, flow.request.pretty_host)
         if route is not None:
-            body = flow.request.get_text(strict=False) or ""
-            # Re-scan after each operator approval so a second, un-approved
-            # token in the same request is still caught (PRD 0062).
-            while True:
-                scan_text = build_outbound_scan_text(
-                    flow.request.pretty_host,
-                    request_path,
-                    query,
-                    outbound_scan_headers(route, dict(flow.request.headers)),
-                    body,
-                )
-                dlp_result = scan_outbound(
-                    route, scan_text, os.environ, safe_tokens=self.safe_tokens,
-                )
-                if dlp_result is None or dlp_result.severity != "block":
-                    break
-                # Token blocks (a match with a safelist-able value) can be
-                # routed to the operator; structural blocks (CRLF, matched="")
-                # and any block when supervise is disabled stay hard 403s.
-                if dlp_result.matched and self._supervise_available():
-                    approved = await self._supervise_token_block(
-                        flow, request_path, dlp_result,
-                    )
-                    if approved:
-                        continue  # re-scan; matched value now in safe_tokens
-                    return  # _supervise_token_block wrote the 403 response
-                ctx = self._req_ctx(flow)
-                if dlp_result.context:
-                    ctx = {**ctx, "context": dlp_result.context}
-                self._block(flow, f"egress DLP: {dlp_result.reason}", ctx=ctx)
+            if not await self._handle_outbound_dlp(flow, route):
                 return
+            # The redact policy may have rewritten the request line; recompute
+            # the path/query the git checks below rely on.
+            request_path, _, query = flow.request.path.partition("?")
 
         if is_git_push_request(request_path, query):
             self._block(
@@ -269,6 +247,110 @@ class EgressAddon:
         if self.config.log >= LOG_FULL:
             self._log_request(flow)
 
+    def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
+        ctx = self._req_ctx(flow)
+        if result.context:
+            ctx = {**ctx, "context": result.context}
+        self._block(flow, f"egress DLP: {result.reason}", ctx=ctx)
+
+    async def _handle_outbound_dlp(
+        self,
+        flow: http.HTTPFlow,
+        route: Route,
+    ) -> bool:
+        """Scan the outbound request and apply the route's on-match policy
+        (PRD 0062). Returns True if the request may be forwarded, False if a
+        403 response has been written to `flow`.
+
+        Loops so the supervise policy can re-scan after each approval — a
+        second, un-approved token in the same request is still caught."""
+        while True:
+            request_path, _, query = flow.request.path.partition("?")
+            body = flow.request.get_text(strict=False) or ""
+            scan_text = build_outbound_scan_text(
+                flow.request.pretty_host,
+                request_path,
+                query,
+                outbound_scan_headers(route, dict(flow.request.headers)),
+                body,
+            )
+            result = scan_outbound(
+                route, scan_text, os.environ, safe_tokens=self.safe_tokens,
+            )
+            if result is None or result.severity != "block":
+                return True
+
+            # Structural blocks (CRLF, no safelist-able value) are always a
+            # hard 403, regardless of the route's on-match policy.
+            if not result.matched:
+                self._block_dlp(flow, result)
+                return False
+
+            policy = route.outbound_on_match or DEFAULT_OUTBOUND_ON_MATCH
+
+            if policy == ON_MATCH_REDACT:
+                if self._redact_outbound(flow, route):
+                    if self.config.log >= LOG_BLOCKS:
+                        sys.stderr.write(json.dumps({
+                            "event": "egress_redacted",
+                            "reason": f"egress DLP: {result.reason}",
+                            **self._req_ctx(flow),
+                        }) + "\n")
+                    return True
+                self._block(
+                    flow,
+                    f"egress DLP: {result.reason}; redaction could not remove "
+                    "all matches (e.g. a match in the hostname)",
+                    ctx=self._req_ctx(flow),
+                )
+                return False
+
+            if policy == ON_MATCH_BLOCK:
+                self._block_dlp(flow, result)
+                return False
+
+            # supervise (default): hold the request for operator approval.
+            # Fall back to a hard 403 when supervise isn't wired for the bottle.
+            if not self._supervise_available():
+                self._block_dlp(flow, result)
+                return False
+            approved = await self._supervise_token_block(flow, request_path, result)
+            if not approved:
+                return False  # _supervise_token_block wrote the 403 response
+            # loop: the approved value is now in safe_tokens; re-scan.
+
+    def _redact_outbound(self, flow: http.HTTPFlow, route: Route) -> bool:
+        """Scrub detected tokens from the mutable request surfaces (body,
+        headers, path/query) and re-scan. Returns True if the request is now
+        clean; False if a block-severity match remains on a surface redaction
+        cannot rewrite (the hostname) so the caller fails closed."""
+        body = flow.request.get_text(strict=False)
+        if body:
+            redacted_body = redact_tokens(body, env=os.environ)
+            if redacted_body != body:
+                flow.request.text = redacted_body
+        for name, value in list(flow.request.headers.items()):
+            if name.lower() == "host":
+                continue  # routing-critical; never a legitimate token
+            redacted = redact_tokens(value, env=os.environ)
+            if redacted != value:
+                flow.request.headers[name] = redacted
+        redacted_path = redact_tokens(flow.request.path, env=os.environ)
+        if redacted_path != flow.request.path:
+            flow.request.path = redacted_path
+
+        request_path, _, query = flow.request.path.partition("?")
+        new_body = flow.request.get_text(strict=False) or ""
+        scan_text = build_outbound_scan_text(
+            flow.request.pretty_host,
+            request_path,
+            query,
+            outbound_scan_headers(route, dict(flow.request.headers)),
+            new_body,
+        )
+        result = scan_outbound(route, scan_text, os.environ)
+        return result is None or result.severity != "block"
+
     async def _supervise_token_block(
         self,
         flow: http.HTTPFlow,

bot_bottle/egress_addon_core.py

@@ -37,6 +37,15 @@ VALID_METHODS = frozenset({
 OUTBOUND_DETECTOR_NAMES = frozenset({"token_patterns", "known_secrets"})
 INBOUND_DETECTOR_NAMES = frozenset({"naive_injection_detection"})
 
+# Per-route policy for what the proxy does when an outbound DLP detector
+# matches a token (PRD 0062).
+ON_MATCH_BLOCK = "block"          # hard 403, never overridable
+ON_MATCH_REDACT = "redact"        # scrub the matched value, forward the request
+ON_MATCH_SUPERVISE = "supervise"  # queue for operator approval, hold the request
+OUTBOUND_ON_MATCH_VALUES = (ON_MATCH_BLOCK, ON_MATCH_REDACT, ON_MATCH_SUPERVISE)
+# Unset resolves to supervise (fall back to block when supervise is not wired).
+DEFAULT_OUTBOUND_ON_MATCH = ON_MATCH_SUPERVISE
+
 
 @dataclass(frozen=True)
 class PathMatch:
@@ -69,6 +78,8 @@ class Route:
     git_fetch: bool = False
     outbound_detectors: tuple[str, ...] | None = None
     inbound_detectors: tuple[str, ...] | None = None
+    # "" means unset → DEFAULT_OUTBOUND_ON_MATCH. See OUTBOUND_ON_MATCH_VALUES.
+    outbound_on_match: str = ""
 
 
 LOG_OFF = 0    # no logging
@@ -223,12 +234,12 @@ def _parse_detectors(
     idx: int,
     host: str,
     raw_dict: dict[str, object],
-) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None]:
+) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None, str]:
     """Parse the optional `dlp` block on a route, returning
-    (outbound_detectors, inbound_detectors)."""
+    (outbound_detectors, inbound_detectors, outbound_on_match)."""
     dlp_raw = raw_dict.get("dlp")
     if dlp_raw is None:
-        return None, None
+        return None, None, ""
     label = f"route[{idx}] ({host})"
     if not isinstance(dlp_raw, dict):
         raise ValueError(f"{label}: 'dlp' must be an object")
@@ -265,13 +276,24 @@ def _parse_detectors(
     outbound = _parse_detector_field("outbound_detectors", OUTBOUND_DETECTOR_NAMES)
     inbound = _parse_detector_field("inbound_detectors", INBOUND_DETECTOR_NAMES)
 
+    on_match = ""
+    on_match_raw = dlp.get("outbound_on_match")
+    if on_match_raw is not None:
+        if not isinstance(on_match_raw, str) or on_match_raw not in OUTBOUND_ON_MATCH_VALUES:
+            raise ValueError(
+                f"{label}: dlp.outbound_on_match must be one of "
+                f"{', '.join(OUTBOUND_ON_MATCH_VALUES)} (got {on_match_raw!r})"
+            )
+        on_match = on_match_raw
+
     for k in dlp:
-        if k not in ("outbound_detectors", "inbound_detectors"):
+        if k not in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
             raise ValueError(
                 f"{label}: dlp has unknown key {k!r}; accepted keys "
-                f"are 'outbound_detectors', 'inbound_detectors'"
+                f"are 'outbound_detectors', 'inbound_detectors', "
+                f"'outbound_on_match'"
             )
-    return outbound, inbound
+    return outbound, inbound, on_match
 
 
 def parse_routes(payload: object) -> tuple[Route, ...]:
@@ -342,7 +364,7 @@ def _parse_one(idx: int, raw: object) -> Route:
                 )
 
     # dlp detectors
-    outbound_detectors, inbound_detectors = _parse_detectors(
+    outbound_detectors, inbound_detectors, outbound_on_match = _parse_detectors(
         idx, host, raw_dict,
     )
 
@@ -361,6 +383,7 @@ def _parse_one(idx: int, raw: object) -> Route:
         git_fetch=git_fetch,
         outbound_detectors=outbound_detectors,
         inbound_detectors=inbound_detectors,
+        outbound_on_match=outbound_on_match,
     )
 
 
@@ -409,6 +432,8 @@ def route_to_yaml_dict(r: Route) -> dict[str, object]:
         dlp["outbound_detectors"] = list(r.outbound_detectors)
     if r.inbound_detectors is not None:
         dlp["inbound_detectors"] = list(r.inbound_detectors)
+    if r.outbound_on_match:
+        dlp["outbound_on_match"] = r.outbound_on_match
     if dlp:
         d["dlp"] = dlp
     return d
@@ -781,6 +806,11 @@ __all__ = [
     "route_to_yaml_dict",
     "LOG_FULL",
     "LOG_OFF",
+    "ON_MATCH_BLOCK",
+    "ON_MATCH_REDACT",
+    "ON_MATCH_SUPERVISE",
+    "OUTBOUND_ON_MATCH_VALUES",
+    "DEFAULT_OUTBOUND_ON_MATCH",
     "Config",
     "Decision",
     "HeaderMatch",

bot_bottle/manifest_egress.py

@@ -21,6 +21,9 @@ VALID_METHODS = frozenset({
 OUTBOUND_DETECTOR_NAMES = frozenset({"token_patterns", "known_secrets"})
 INBOUND_DETECTOR_NAMES = frozenset({"naive_injection_detection"})
 
+# What the proxy does on an outbound token match (PRD 0062).
+OUTBOUND_ON_MATCH_VALUES = ("block", "redact", "supervise")
+
 
 def validate_egress_routes(
     bottle_name: str,
@@ -67,6 +70,7 @@ class ManifestEgressRoute:
     GitFetch: bool = False
     OutboundDetectors: tuple[str, ...] | None = None
     InboundDetectors: tuple[str, ...] | None = None
+    OutboundOnMatch: str = ""
 
     @classmethod
     def from_dict(cls, bottle_name: str, idx: int, raw: object) -> "ManifestEgressRoute":
@@ -161,8 +165,9 @@ class ManifestEgressRoute:
         # --- dlp ---
         outbound_detectors: tuple[str, ...] | None = None
         inbound_detectors: tuple[str, ...] | None = None
+        outbound_on_match = ""
         if "dlp" in d:
-            outbound_detectors, inbound_detectors = _parse_dlp_block(
+            outbound_detectors, inbound_detectors, outbound_on_match = _parse_dlp_block(
                 label, d.get("dlp"),
             )
 
@@ -201,6 +206,7 @@ class ManifestEgressRoute:
             GitFetch=git_fetch,
             OutboundDetectors=outbound_detectors,
             InboundDetectors=inbound_detectors,
+            OutboundOnMatch=outbound_on_match,
         )
 
 
@@ -323,7 +329,7 @@ def _parse_header_match(
 def _parse_dlp_block(
     route_label: str,
     raw: object,
-) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None]:
+) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None, str]:
     label = f"{route_label} dlp"
     d = as_json_object(raw, label)
 
@@ -358,13 +364,24 @@ def _parse_dlp_block(
     outbound = _parse_field("outbound_detectors", OUTBOUND_DETECTOR_NAMES)
     inbound = _parse_field("inbound_detectors", INBOUND_DETECTOR_NAMES)
 
+    on_match = ""
+    on_match_raw = d.get("outbound_on_match")
+    if on_match_raw is not None:
+        if not isinstance(on_match_raw, str) or on_match_raw not in OUTBOUND_ON_MATCH_VALUES:
+            raise ManifestError(
+                f"{label} outbound_on_match must be one of "
+                f"{', '.join(OUTBOUND_ON_MATCH_VALUES)} (got {on_match_raw!r})"
+            )
+        on_match = on_match_raw
+
     for k in d:
-        if k not in ("outbound_detectors", "inbound_detectors"):
+        if k not in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
             raise ManifestError(
                 f"{label} has unknown key {k!r}; accepted keys are "
-                f"'outbound_detectors', 'inbound_detectors'"
+                f"'outbound_detectors', 'inbound_detectors', "
+                f"'outbound_on_match'"
             )
-    return outbound, inbound
+    return outbound, inbound, on_match
 
 
 LOG_LEVELS = frozenset({0, 1, 2})

bot_bottle/supervise_server.py

@@ -187,6 +187,7 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
                         "  dlp:  (optional DLP scanner overrides)\n"
                         "    outbound_detectors: [token_patterns, known_secrets]\n"
                         "    inbound_detectors: [naive_injection_detection]\n"
+                        "    outbound_on_match: block|redact|supervise  (default supervise)\n"
                         "Omit any key that should use its default. "
                         "`list-egress-routes` returns routes in this same format."
                     ),
@@ -228,6 +229,7 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
                         "  dlp:  (optional DLP scanner overrides)\n"
                         "    outbound_detectors: [token_patterns, known_secrets]\n"
                         "    inbound_detectors: [naive_injection_detection]\n"
+                        "    outbound_on_match: block|redact|supervise  (default supervise)\n"
                         "Omit any key that should use its default. "
                         "`list-egress-routes` returns routes in this same format."
                     ),