Compare commits

..

7 Commits

Author SHA1 Message Date
didericis-codex 0a7e166b35 fix(tests): remove unused dlp entropy import
lint / lint (push) Successful in 2m8s
test / unit (pull_request) Successful in 40s
test / integration (pull_request) Successful in 23s
2026-06-24 23:09:11 -04:00
didericis-claude a920203730 fix(dlp): skip projection passes when exact variant is safe-listed
When a supervisor-approved safe-token exactly matched an env secret
(Pass 1), Passes 2 & 3 (alnum projection) still ran and re-blocked on
the same value.  Track whether any variant was found-and-approved and
skip the projection passes for that secret in that case.
2026-06-24 23:09:11 -04:00
didericis-claude e02fab15d0 docs(prd): flip prd-new-strengthen-outbound-exfil-detection Draft → Active
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-24 23:09:11 -04:00
didericis-claude 11cf12188d feat(egress): inject per-session canary token into sidecar and agent environments
EgressPlan gains a `canary: str` field (default "") populated in Egress.prepare()
using secrets.token_urlsafe(32).  Each launched bottle:

  - sidecar receives EGRESS_TOKEN_CANARY=<value> (literal env entry, scanned by
    existing known-secrets detector without any detector code changes)
  - agent receives BOT_BOTTLE_CANARY=<value> (visible fake secret that signals
    exfiltration with zero false positives if it appears in outbound traffic)

Docker compose and macos-container backends updated; smolmachines shares docker
compose and so picks this up automatically.  Unit tests cover canary uniqueness,
detection via scan_known_secrets, and EgressPlan backward-compat default.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-24 23:09:11 -04:00
didericis-claude 701df6cb2f feat(dlp): fragmentation resistance, entropy detector, broadened known-value scan
- _alnum_projection(): strip non-alphanumeric chars for separator-injection detection
- scan_known_secrets() gains two extra passes per secret after exact-variant matching:
  alnum-projection exact match (catches hyphens/spaces between secret chars) and a
  sliding-window partial-match scan (catches chunked substrings ≥ PARTIAL_MATCH_MIN_LEN)
- scan_known_secrets() accepts sensitive_prefixes param (default ("EGRESS_TOKEN_",))
  so redact_tokens and call-sites can extend the scanned env-var prefix set
- scan_entropy() warn-only detector flagging windows with Shannon entropy ≥ 5.5 bits/char
- "entropy" added to OUTBOUND_DETECTOR_NAMES; scan_outbound opts it in only when
  explicitly listed in dlp.outbound_detectors (never part of the default "all" set)
- scan_outbound reads BOT_BOTTLE_SENSITIVE_PREFIXES from environ to extend
  scan_known_secrets beyond EGRESS_TOKEN_* without schema changes
- Binary bodies decoded via latin-1 fallback (bijective byte↔codepoint) instead
  of utf-8 errors=replace, preserving ASCII secret strings in binary payloads

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-24 23:09:11 -04:00
didericis-claude ea6bc5a170 docs: draft PRD prd-new for strengthen-outbound-exfil-detection
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-24 23:09:11 -04:00
didericis ecaae708f7 feat(provider): support startup args settings
test / unit (pull_request) Successful in 41s
test / integration (pull_request) Successful in 26s
lint / lint (push) Successful in 2m12s
test / unit (push) Successful in 41s
test / integration (push) Successful in 26s
Update Quality Badges / update-badges (push) Successful in 2m9s
2026-06-24 22:51:27 -04:00
7 changed files with 122 additions and 9 deletions
+9
View File
@@ -371,6 +371,15 @@ def build_agent_provision_plan(
)
def provider_startup_args(
provider_settings: dict[str, object] | None,
) -> tuple[str, ...]:
raw = (provider_settings or {}).get("startup_args", ())
if not isinstance(raw, (list, tuple)):
return ()
return tuple(arg for arg in raw if isinstance(arg, str))
def prompt_args(
prompt_mode: PromptMode,
prompt_path: str | None,
+4 -1
View File
@@ -20,6 +20,7 @@ from ...agent_provider import (
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from ...backend.docker import util as docker_mod
from ...egress import EgressRoute
@@ -115,8 +116,9 @@ class ClaudeAgentProvider(AgentProvider):
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del forward_host_credentials, host_env, provider_settings
del forward_host_credentials, host_env
resolved_guest_env = dict(guest_env or {})
startup_args = provider_startup_args(provider_settings)
guest_home = self.guest_home
trusted_path = trusted_project_path or guest_home
@@ -199,6 +201,7 @@ class ClaudeAgentProvider(AgentProvider):
env_vars=env_vars,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=startup_args,
dirs=dirs,
files=tuple(files),
egress_routes=egress_routes,
+4 -1
View File
@@ -22,6 +22,7 @@ from ...agent_provider import (
AgentProvisionCommand,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from .codex_auth import codex_host_access_token, write_codex_dummy_auth_file
from ...egress import CODEX_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
@@ -79,8 +80,9 @@ class CodexAgentProvider(AgentProvider):
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del auth_token, label, color, provider_settings
del auth_token, label, color
resolved_guest_env = dict(guest_env or {})
startup_args = provider_startup_args(provider_settings)
guest_home = self.guest_home
trusted_path = trusted_project_path or guest_home
@@ -163,6 +165,7 @@ class CodexAgentProvider(AgentProvider):
env_vars=env_vars,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=startup_args,
dirs=tuple(dirs),
files=tuple(files),
pre_copy=tuple(pre_copy),
+3
View File
@@ -21,6 +21,7 @@ from ...agent_provider import (
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from ...egress import EgressRoute
from ...log import die, info
@@ -199,6 +200,7 @@ class PiAgentProvider(AgentProvider):
models_payload, base_url, api_key_env, models, provider_name = (
_pi_models_json(settings)
)
extra_startup_args = provider_startup_args(provider_settings)
models_file = state_dir / "pi-models.json"
models_file.write_text(json.dumps(models_payload, indent=2) + "\n")
models_file.chmod(0o600)
@@ -219,6 +221,7 @@ class PiAgentProvider(AgentProvider):
startup_args=(
"--models",
",".join(f"{provider_name}/{model}" for model in models),
*extra_startup_args,
),
dirs=(AgentProvisionDir(f"{guest_home}/.pi/agent"),),
files=(AgentProvisionFile(models_file, _models_path(guest_home)),),
+28 -6
View File
@@ -199,13 +199,10 @@ def _parse_provider_settings(
) -> dict[str, object]:
if raw is None:
return {}
if template != "pi":
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings is only "
"supported for template 'pi'"
)
settings = as_json_object(raw, f"bottle '{bottle_name}' agent_provider.settings")
allowed = {
common_allowed = {"startup_args"}
pi_allowed = {
"provider",
"base_url",
"api",
@@ -218,12 +215,37 @@ def _parse_provider_settings(
"supports_developer_role",
"supports_reasoning_effort",
}
if template == "pi":
allowed = common_allowed | pi_allowed
elif template in ("claude", "codex"):
allowed = common_allowed
elif template not in PROVIDER_TEMPLATES:
return dict(settings)
else:
allowed = common_allowed
for key in settings:
if key not in allowed:
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings has unknown "
f"key {key!r}; allowed: {', '.join(sorted(allowed))}"
)
startup_args = settings.get("startup_args")
if startup_args is not None:
if not isinstance(startup_args, list):
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings.startup_args "
f"must be an array of strings"
)
for i, arg in enumerate(startup_args):
if not isinstance(arg, str) or not arg:
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings."
f"startup_args[{i}] must be a non-empty string"
)
if template != "pi":
return dict(settings)
for key in ("provider", "base_url", "api", "api_key", "api_key_env"):
value = settings.get(key)
if value is not None and (not isinstance(value, str) or not value):
+46
View File
@@ -168,6 +168,34 @@ class TestAgentProviderRuntime(unittest.TestCase):
self.assertEqual("~/.claude/statusline.sh", settings["statusLine"]["command"])
self.assertEqual("custom:bot-bottle-research-ui", settings["theme"])
def test_claude_plan_uses_startup_args_from_provider_settings(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
plan = build_agent_provision_plan(
template="claude",
dockerfile="",
state_dir=Path(tmp),
instance_name="bot-bottle-test",
prompt_file=Path(tmp) / "prompt.txt",
provider_settings={
"startup_args": ["--model", "opus"],
},
)
self.assertEqual(("--model", "opus"), plan.startup_args)
def test_codex_plan_uses_startup_args_from_provider_settings(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
plan = build_agent_provision_plan(
template="codex",
dockerfile="",
state_dir=Path(tmp),
instance_name="bot-bottle-test",
prompt_file=Path(tmp) / "prompt.txt",
provider_settings={
"startup_args": ["--model", "gpt-5-codex"],
},
)
self.assertEqual(("--model", "gpt-5-codex"), plan.startup_args)
def test_codex_forward_host_credentials_populates_egress_routes(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
home = Path(tmp) / "host-codex"
@@ -394,6 +422,24 @@ class TestAgentProviderRuntime(unittest.TestCase):
self.assertNotIn("OPENROUTER_API_KEY", plan.guest_env)
self.assertTrue(provider["compat"]["supportsReasoningEffort"])
def test_pi_plan_appends_startup_args_from_provider_settings(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
plan = build_agent_provision_plan(
template="pi",
dockerfile="",
state_dir=Path(tmp),
instance_name="bot-bottle-test",
prompt_file=Path(tmp) / "prompt.txt",
provider_settings={
"models": ["qwen3:14b"],
"startup_args": ["--no-stream"],
},
)
self.assertEqual(
("--models", "ollama/qwen3:14b", "--no-stream"),
plan.startup_args,
)
def test_pi_prompt_mode_appends_system_prompt_interactively(self):
self.assertEqual(
["--append-system-prompt", "/home/node/.bot-bottle-prompt.txt"],
+28 -1
View File
@@ -167,13 +167,40 @@ class TestAgentProviderHostCredentials(unittest.TestCase):
},
})
def test_settings_rejected_for_claude(self):
def test_startup_args_allowed_for_claude(self):
b = _provider_config_bottle({
"template": "claude",
"settings": {"startup_args": ["--model", "opus"]},
})
self.assertEqual(
{"startup_args": ["--model", "opus"]},
b.agent_provider.settings,
)
def test_startup_args_allowed_for_codex(self):
b = _provider_config_bottle({
"template": "codex",
"settings": {"startup_args": ["--model", "gpt-5-codex"]},
})
self.assertEqual(
{"startup_args": ["--model", "gpt-5-codex"]},
b.agent_provider.settings,
)
def test_provider_specific_settings_still_rejected_for_claude(self):
with self.assertRaises(ManifestError):
_provider_config_bottle({
"template": "claude",
"settings": {"models": ["qwen2.5-coder:7b"]},
})
def test_startup_args_must_be_string_array(self):
with self.assertRaises(ManifestError):
_provider_config_bottle({
"template": "codex",
"settings": {"startup_args": ["--model", 42]},
})
def test_settings_models_must_be_non_empty_string_array(self):
with self.assertRaises(ManifestError):
_provider_config_bottle({