=i*SrSSKJr SSKJrJrJr SSKJrJ r J r J r SSK J r JrJrJrJrJrJrJrJrJr SSKJrJrJr \(a SSKJr SSKJr "S S \5r/S Qr g ) z1PII detection and handling middleware for agents.) annotations) TYPE_CHECKINGAnyLiteral) AIMessage AnyMessage HumanMessage ToolMessage) PIIDetectionErrorPIIMatch RedactionRuleResolvedRedactionRuleapply_strategydetect_credit_card detect_email detect_ipdetect_mac_address detect_url)AgentMiddleware AgentState hook_config)Callable)Runtimec^\rSrSrSrSSSSSS.SU4Sjjjr\SS j5rSS jr\ "S /S 9SS j5r SSjr Sr U=r $) PIIMiddlewareazDetect and handle Personally Identifiable Information (PII) in agent conversations. This middleware detects common PII types and applies configurable strategies to handle them. It can detect emails, credit cards, IP addresses, MAC addresses, and URLs in both user input and agent output. Built-in PII types: - `email`: Email addresses - `credit_card`: Credit card numbers (validated with Luhn algorithm) - `ip`: IP addresses (validated with stdlib) - `mac_address`: MAC addresses - `url`: URLs (both `http`/`https` and bare URLs) Strategies: - `block`: Raise an exception when PII is detected - `redact`: Replace PII with `[REDACTED_TYPE]` placeholders - `mask`: Partially mask PII (e.g., `****-****-****-1234` for credit card) - `hash`: Replace PII with deterministic hash (e.g., ``) Strategy Selection Guide: | Strategy | Preserves Identity? | Best For | | -------- | ------------------- | --------------------------------------- | | `block` | N/A | Avoid PII completely | | `redact` | No | General compliance, log sanitization | | `mask` | No | Human readability, customer service UIs | | `hash` | Yes (pseudonymous) | Analytics, debugging | Example: ```python from langchain.agents.middleware import PIIMiddleware from langchain.agents import create_agent # Redact all emails in user input agent = create_agent( "openai:gpt-5", middleware=[ PIIMiddleware("email", strategy="redact"), ], ) # Use different strategies for different PII types agent = create_agent( "openai:gpt-4o", middleware=[ PIIMiddleware("credit_card", strategy="mask"), PIIMiddleware("url", strategy="redact"), PIIMiddleware("ip", strategy="hash"), ], ) # Custom PII type with regex agent = create_agent( "openai:gpt-5", middleware=[ PIIMiddleware("api_key", detector=r"sk-[a-zA-Z0-9]{32}", strategy="block"), ], ) ``` redactNTF)strategydetectorapply_to_inputapply_to_outputapply_to_tool_resultsc$>[TU]5 X@lXPlX`l[ UUUS9R 5UlURRUlURRUl URRUl g)aLInitialize the PII detection middleware. Args: pii_type: Type of PII to detect. Can be a built-in type (`email`, `credit_card`, `ip`, `mac_address`, `url`) or a custom type name. strategy: How to handle detected PII: * `block`: Raise PIIDetectionError when PII is detected * `redact`: Replace with `[REDACTED_TYPE]` placeholders * `mask`: Partially mask PII (show last few characters) * `hash`: Replace with deterministic hash (format: ``) detector: Custom detector function or regex pattern. * If `Callable`: Function that takes content string and returns list of PIIMatch objects * If `str`: Regex pattern to match PII * If `None`: Uses built-in detector for the pii_type apply_to_input: Whether to check user messages before model call. apply_to_output: Whether to check AI messages after model call. apply_to_tool_results: Whether to check tool result messages after tool execution. Raises: ValueError: If pii_type is not built-in and no detector is provided. )pii_typerrN) super__init__r r!r"r resolve_resolved_ruler$rr)selfr$rrr r!r" __class__s o/home/dmtnaga/Documents/work/airagagent/rag_env/lib/python3.13/site-packages/langchain/agents/middleware/pii.pyr&PIIMiddleware.__init__[sJ ,.%:"5B6  ')  ++44 ++44 ++44 cNURRSURS3$)zName of the middleware.[])r*__name__r$)r)s r+namePIIMiddleware.names&..))*!DMM?!< +(++*//3O 3B/#'L  % %K3x=1,b"5hk955"#K6 &{QH >A"+C!#{33#&'//$"%h&6&6"7/3/D/DW/M, &$+6$/'{{!))1)>)> ++:Q'+ -?0  - -r-cUR(dgUSnU(dgSnSn[[U5S- SS5H"nX6n[U[5(dMUnUn O UbU(aUR (dg[ UR 5nURU5upU (dg[ U URURURS9n [U5n XU'SU 0$)a-Check AI messages for PII after model invocation. Args: state: The current agent state. runtime: The langgraph runtime. Returns: Updated state with PII handled according to strategy, or None if no PII detected. Raises: PIIDetectionError: If PII is detected and strategy is "block". Nr=r>r?)r5r@r2 tool_calls) r!rCrDrErr5rFr8r@r2rVrB) r)rGrHr= last_ai_msgrPrMrQr5rNr6rOrIs r+ after_modelPIIMiddleware.after_models"##$  s8}q("b1A+C#y))!   2  k9L9Lk))*#44W= $~~!!"--  H~ $3[!L))r-)r(r r!r"rr$r)r$zALiteral['email', 'credit_card', 'ip', 'mac_address', 'url'] | strrz*Literal['block', 'redact', 'mask', 'hash']rz,Callable[[str], list[PIIMatch]] | str | Noner boolr!rZr"rZreturnNone)r[rF)r5rFr[ztuple[str, list[PIIMatch]])rGrrHrr[zdict[str, Any] | None)r1 __module__ __qualname____firstlineno____doc__r&propertyr2r8rrSrX__static_attributes__ __classcell__)r*s@r+rrs;B@HAE# %&+25S25= 25 ? 25  2525 $25 2525h=="eW%[[[  [&[z8*8*8*  8*8*r-r)r rrrrrrN)!r` __future__rtypingrrrlangchain_core.messagesrrr r &langchain.agents.middleware._redactionr r r rrrrrrr!langchain.agents.middleware.typesrrrcollections.abcrlanggraph.runtimerr__all__r-r+rmsN7"..TT   WV()U*OU*p r-