Fix handoff_request extractor truncating nested payloads at the first }
`HANDOFF_RE` used a non-greedy `.*?\}`, so the match ended at the first closing brace. Every real `handoff_request` nests objects (`payload`, and `payload.params`), so the captured substring was truncated mid-object and `json.loads` raised — `extract_handoff` rejected every well-formed handoff as `invalid_json` before the target allowlist and schema validators ever ran. In practice the cross-agent handoff path did not function for any realistic payload. Replace the full-match regex with a start anchor (`HANDOFF_START_RE`) and extract the complete object with `json.JSONDecoder().raw_decode`, which is string- and brace-nesting aware and returns exactly one complete JSON value plus its end offset. Multi-line payloads now parse as well. The audit log's `raw_len` field, previously `len(m.group(0))`, is now derived from the decoded object's span (`end - m.start()`), and its three later uses on the target/schema/params rejection paths are updated to the new variable. Downstream validation — target allowlist, payload and per-intent schemas, sanitize/frame — is unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
cd76401457
commit
88c8906831
1 changed files with 20 additions and 10 deletions
|
|
@ -138,9 +138,15 @@ HANDOFF_PAYLOAD_SCHEMA = {
|
|||
},
|
||||
}
|
||||
|
||||
HANDOFF_RE = re.compile(
|
||||
r'\{"type":\s*"handoff_request".*?\}', re.DOTALL
|
||||
)
|
||||
# Matches the START of a handoff_request object only. The full object —
|
||||
# which always contains nested objects (`payload`, and `payload.params`) —
|
||||
# is then extracted with json.JSONDecoder().raw_decode in extract_handoff.
|
||||
# A plain regex cannot do this safely: a non-greedy `.*?\}` stops at the
|
||||
# first `}` and truncates every real payload, while a greedy `.*\}`
|
||||
# over-captures across any later `}` in the stream. raw_decode is string-
|
||||
# and nesting-aware, so it returns exactly one complete JSON value.
|
||||
HANDOFF_START_RE = re.compile(r'\{\s*"type"\s*:\s*"handoff_request"')
|
||||
_JSON_DECODER = json.JSONDecoder()
|
||||
|
||||
# Denylist for instruction-like phrasing. Low-assurance; see docstring.
|
||||
_DENY_PREFIX = ("#", ">", "---", "System:", "Assistant:", "Human:",
|
||||
|
|
@ -242,30 +248,34 @@ def extract_handoff(text: str, source_agent: str = "unknown") -> dict | None:
|
|||
Returns a dict with target_agent, intent, params, and pre-rendered
|
||||
steering_input, or None if any gate fails. Every attempt is logged.
|
||||
"""
|
||||
m = HANDOFF_RE.search(text)
|
||||
m = HANDOFF_START_RE.search(text)
|
||||
if not m:
|
||||
return None
|
||||
raw = m.group(0)
|
||||
try:
|
||||
obj = json.loads(raw)
|
||||
obj, end = _JSON_DECODER.raw_decode(text, m.start())
|
||||
except json.JSONDecodeError:
|
||||
audit_log({"source": source_agent, "result": "reject",
|
||||
"reason": "invalid_json", "raw_len": len(raw)})
|
||||
"reason": "invalid_json",
|
||||
"raw_len": len(text) - m.start()})
|
||||
return None
|
||||
# Length of the decoded handoff object, for the audit log on any
|
||||
# later rejection. raw_decode returns the end offset of the parsed
|
||||
# value; the old m.group(0) string no longer exists.
|
||||
raw_len = end - m.start()
|
||||
|
||||
target = obj.get("target_agent")
|
||||
payload = obj.get("payload")
|
||||
if target not in ALLOWED_TARGETS:
|
||||
audit_log({"source": source_agent, "target": target,
|
||||
"result": "reject", "reason": "target_not_allowlisted",
|
||||
"raw_len": len(raw)})
|
||||
"raw_len": raw_len})
|
||||
return None
|
||||
try:
|
||||
jsonschema.validate(instance=payload, schema=HANDOFF_PAYLOAD_SCHEMA)
|
||||
except jsonschema.ValidationError as e:
|
||||
audit_log({"source": source_agent, "target": target,
|
||||
"result": "reject", "reason": f"schema: {e.message}",
|
||||
"raw_len": len(raw)})
|
||||
"raw_len": raw_len})
|
||||
return None
|
||||
|
||||
intent = payload["intent"]
|
||||
|
|
@ -273,7 +283,7 @@ def extract_handoff(text: str, source_agent: str = "unknown") -> dict | None:
|
|||
if not _validate_params(intent, params):
|
||||
audit_log({"source": source_agent, "target": target, "intent": intent,
|
||||
"result": "reject", "reason": "params_schema",
|
||||
"raw_len": len(raw)})
|
||||
"raw_len": raw_len})
|
||||
return None
|
||||
|
||||
raw_event = payload.get("event", "") or ""
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue