feat(privacy): refuse untrusted intake without a grant

.codegraph/.gitignore

@@ -0,0 +1,5 @@
+# CodeGraph data files — local to each machine, not for committing.
+# Ignore everything in .codegraph/ except this file itself, so transient
+# files (the database, daemon.pid, sockets, logs) never show up in git.
+*
+!.gitignore

ARCHITECTURE.md

@@ -61,6 +61,7 @@ boundaries above remain the target modular MSA architecture.
 | `tepp_simulation` | known-truth temporal/event data generation |
 | `validation_core` | RMSE, bias, coverage, graph, and Monte Carlo metrics |
 | `tepp_api` | versioned DTO, schema, and export contracts |
+| `intake_authorization` | untrusted intake fails closed without a grant; bounds are not authorization |
 
 No crate exposes placeholder production behavior in Task 1. This prevents an
 empty façade from becoming a de facto public API before its invariants and tests

CHANGELOG.md

@@ -6,6 +6,11 @@ All notable changes to TEPP are documented here. The format follows Keep a Chang
 
 ### Added
 
+- `provider_receipt` disclosure receipt: records provider field codes and
+  purpose-bound receipt metadata without persisting source text or source
+  identity (ADR 0009).
+- `intake_authorization` identity gate: documents, serialized records, checkpoints, and LLM outputs cannot be accepted without a purpose-bound grant; size/identity/provenance bounds are not that grant; recovered grant-presence flags match known truth at a higher computed rate than accepting every intake (ADR 0009).
+- `persistence_postgres` retention/deletion/legal-hold (migration `0007`): policy rows, legal holds that block completed deletion, evidence tombstones without raw-source restore, analysis exclusion only for `logical_revocation`/`identity_tombstone` (not `cache_export_removal`), and deletion requests bound to the cited retention policy's tenant/class/purpose.
 - `tepp_api` adaptive orchestration router (ADR 0010): versioned `direct`/`verify`/`committee`/`conductor`/`abstain` selection from CPU `f64` risk, ambiguity, evidence, and token-budget inputs; recorded stages, recursion, decomposition, access lists, and role-specific reasoning effort; fail-closed document-controlled policy/access/credentials; LLM plans remain proposals under deterministic statistical authority; comparable-budget ablation requires a direct baseline; credential-free contextual-orchestrator binding. Live NIM HTTP remains accepted-target.
 - `tepp_api` purpose-bound provider-payload minimization: time-bounded `PurposeGrant` evaluation, fail-closed expired/not-yet-valid/inverted/cross-tenant/impossible-calendar denial, semantic UTC calendar validation, refusal to copy identity mappings into model-provider payloads or ordinary logs, preservation of opaque analytical identifiers and membership roles (no blanket PII mask), a separately authorized scientific re-identification path, and an internally bound FIPS 180-4 SHA-256 audit digest appended through `ReidentificationAuditSink` before disclosure.
 - `persistence_postgres` backup/restore integrity: restored snapshots stay unusable until tenant, canonical `SHA-256`, knowledge-cutoff eligibility, temporal window order, and append-only triggers revalidate; SQL probes raise `restore integrity failed` (ADR 0013).

Cargo.toml

@@ -11,6 +11,8 @@ members = [
     "crates/tepp_simulation",
     "crates/validation_core",
     "crates/tepp_api",
+    "crates/provider_receipt",
+    "crates/intake_authorization",
 ]
 default-members = [
     "crates/evidence_core",
@@ -23,6 +25,8 @@ default-members = [
     "crates/tepp_simulation",
     "crates/validation_core",
     "crates/tepp_api",
+    "crates/provider_receipt",
+    "crates/intake_authorization",
 ]
 
 [workspace.package]

README.md

@@ -7,7 +7,7 @@ implemented in Rust.
 ## Current implementation state
 
 This branch establishes the Task 1 Rust workspace and quality-gate foundation.
-The ten bounded crates compile independently but intentionally expose no
+The twelve bounded crates compile independently but intentionally expose no
 placeholder production APIs. Domain behavior begins in Task 2 with immutable
 evidence identifiers and source records.
 
@@ -22,6 +22,8 @@ crates/corpus_split
 crates/tepp_simulation
 crates/validation_core
 crates/tepp_api
+crates/provider_receipt
+crates/intake_authorization
 ```
 
 ## Local verification

crates/intake_authorization/Cargo.toml

@@ -0,0 +1,17 @@
+[package]
+name = "intake_authorization"
+description = "Untrusted intake fails closed without a grant; bounds are not authorization."
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+repository.workspace = true
+homepage.workspace = true
+readme.workspace = true
+keywords.workspace = true
+categories.workspace = true
+publish = false
+
+[lints]
+workspace = true

crates/intake_authorization/src/error.rs

@@ -0,0 +1,55 @@
+//! Fail-closed intake-authorization errors.
+
+use std::fmt;
+
+/// A fail-closed intake-authorization error.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+#[non_exhaustive]
+pub enum IntakeAuthorizationError {
+    /// Intake was attempted without a purpose-bound grant.
+    MissingGrant,
+    /// Size, identity, or provenance bounds were treated as authorization.
+    BoundsAreNotAuthorization,
+    /// A recovery slice was empty or length-mismatched.
+    InvalidIntakePayload,
+}
+
+impl fmt::Display for IntakeAuthorizationError {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let message = match self {
+            Self::MissingGrant => "untrusted intake requires a purpose-bound grant",
+            Self::BoundsAreNotAuthorization => {
+                "identity, provenance, size, and depth bounds are not authorization"
+            }
+            Self::InvalidIntakePayload => "invalid intake-authorization payload",
+        };
+        formatter.write_str(message)
+    }
+}
+
+impl std::error::Error for IntakeAuthorizationError {}
+
+#[cfg(test)]
+mod tests {
+    use super::IntakeAuthorizationError;
+
+    #[test]
+    fn error_messages_are_stable() {
+        for (error, message) in [
+            (
+                IntakeAuthorizationError::MissingGrant,
+                "untrusted intake requires a purpose-bound grant",
+            ),
+            (
+                IntakeAuthorizationError::BoundsAreNotAuthorization,
+                "identity, provenance, size, and depth bounds are not authorization",
+            ),
+            (
+                IntakeAuthorizationError::InvalidIntakePayload,
+                "invalid intake-authorization payload",
+            ),
+        ] {
+            assert_eq!(error.to_string(), message);
+        }
+    }
+}

crates/intake_authorization/src/intake.rs

@@ -0,0 +1,152 @@
+//! Grant presence required at untrusted intake.
+
+use crate::IntakeAuthorizationError;
+
+/// Closed vocabulary of untrusted inbound kinds that require a grant.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+pub enum IntakeKind {
+    /// External document bytes.
+    Document,
+    /// Serialized domain or wire record.
+    SerializedRecord,
+    /// Model checkpoint or artifact bytes.
+    ModelCheckpoint,
+    /// LLM or agent output.
+    LlmOutput,
+}
+
+impl IntakeKind {
+    /// Return the stable wire intake-kind name.
+    #[must_use]
+    pub const fn wire_name(self) -> &'static str {
+        match self {
+            Self::Document => "document",
+            Self::SerializedRecord => "serialized_record",
+            Self::ModelCheckpoint => "model_checkpoint",
+            Self::LlmOutput => "llm_output",
+        }
+    }
+
+    /// Parse a stable wire intake-kind name.
+    ///
+    /// # Errors
+    ///
+    /// Returns [`IntakeAuthorizationError::InvalidIntakePayload`] for
+    /// unrecognized names.
+    pub fn from_wire_name(name: &str) -> Result<Self, IntakeAuthorizationError> {
+        match name {
+            "document" => Ok(Self::Document),
+            "serialized_record" => Ok(Self::SerializedRecord),
+            "model_checkpoint" => Ok(Self::ModelCheckpoint),
+            "llm_output" => Ok(Self::LlmOutput),
+            _ => Err(IntakeAuthorizationError::InvalidIntakePayload),
+        }
+    }
+}
+
+/// Whether a purpose-bound grant is present at intake.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+pub enum GrantPresence {
+    /// A grant exists for this intake.
+    Present,
+    /// No grant exists for this intake.
+    Absent,
+}
+
+/// Refuse untrusted intake that has no purpose-bound grant.
+///
+/// Cross-purpose reuse of a present grant is owned by `purpose_authorization`.
+/// Identity, provenance, size, and depth are owned by `payload_bound`.
+///
+/// # Errors
+///
+/// Returns [`IntakeAuthorizationError::MissingGrant`] when `grant` is
+/// [`GrantPresence::Absent`].
+pub fn refuse_intake_without_grant(
+    kind: IntakeKind,
+    grant: GrantPresence,
+) -> Result<(), IntakeAuthorizationError> {
+    let _ = kind.wire_name();
+    match grant {
+        GrantPresence::Absent => Err(IntakeAuthorizationError::MissingGrant),
+        GrantPresence::Present => Ok(()),
+    }
+}
+
+/// Refuse to treat size, identity, or provenance bounds as authorization.
+///
+/// # Errors
+///
+/// Always returns [`IntakeAuthorizationError::BoundsAreNotAuthorization`].
+pub fn refuse_bounds_as_authorization() -> Result<(), IntakeAuthorizationError> {
+    Err(IntakeAuthorizationError::BoundsAreNotAuthorization)
+}
+
+/// Fraction of recovered grant-presence flags that match known truth.
+///
+/// # Errors
+///
+/// Returns [`IntakeAuthorizationError::InvalidIntakePayload`] when either
+/// slice is empty or the lengths differ.
+pub fn identity_recovery_rate(
+    truth: &[bool],
+    decided: &[bool],
+) -> Result<f64, IntakeAuthorizationError> {
+    if truth.is_empty() || truth.len() != decided.len() {
+        return Err(IntakeAuthorizationError::InvalidIntakePayload);
+    }
+    let mut matches = 0_u32;
+    for (truth_flag, decided_flag) in truth.iter().zip(decided) {
+        if truth_flag == decided_flag {
+            matches += 1;
+        }
+    }
+    Ok(f64::from(matches) / truth.len() as f64)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{
+        GrantPresence, IntakeKind, identity_recovery_rate, refuse_bounds_as_authorization,
+        refuse_intake_without_grant,
+    };
+    use crate::IntakeAuthorizationError;
+
+    #[test]
+    fn local_branches_cover_kinds_grants_and_payloads() {
+        for kind in [
+            IntakeKind::Document,
+            IntakeKind::SerializedRecord,
+            IntakeKind::ModelCheckpoint,
+            IntakeKind::LlmOutput,
+        ] {
+            assert_eq!(
+                refuse_intake_without_grant(kind, GrantPresence::Absent),
+                Err(IntakeAuthorizationError::MissingGrant)
+            );
+            refuse_intake_without_grant(kind, GrantPresence::Present).expect("present");
+            assert_eq!(
+                IntakeKind::from_wire_name(kind.wire_name()).expect("round-trip"),
+                kind
+            );
+        }
+        assert_eq!(
+            refuse_bounds_as_authorization(),
+            Err(IntakeAuthorizationError::BoundsAreNotAuthorization)
+        );
+        assert_eq!(
+            IntakeKind::from_wire_name("trusted"),
+            Err(IntakeAuthorizationError::InvalidIntakePayload)
+        );
+        let matched = identity_recovery_rate(&[true], &[true]).expect("rate");
+        assert!((matched - 1.0).abs() < f64::EPSILON);
+        assert_eq!(
+            identity_recovery_rate(&[], &[]),
+            Err(IntakeAuthorizationError::InvalidIntakePayload)
+        );
+        assert_eq!(
+            identity_recovery_rate(&[true], &[]),
+            Err(IntakeAuthorizationError::InvalidIntakePayload)
+        );
+    }
+}

crates/intake_authorization/src/lib.rs

@@ -0,0 +1,24 @@
+#![forbid(unsafe_code)]
+#![deny(missing_docs)]
+#![allow(clippy::cast_precision_loss)]
+//! Untrusted intake fails closed without a grant; bounds are not authorization.
+//!
+//! Documents, serialized records, checkpoints, and LLM outputs require a
+//! purpose-bound grant at the intake boundary. Passing size or identity
+//! bounds is not that grant (ADR 0009; AGENTS.md).
+
+mod error;
+mod intake;
+
+/// Fail-closed intake-authorization errors.
+pub use error::IntakeAuthorizationError;
+/// Whether a purpose-bound grant is present at intake.
+pub use intake::GrantPresence;
+/// Closed vocabulary of untrusted inbound kinds that require a grant.
+pub use intake::IntakeKind;
+/// Fraction of recovered grant-presence flags that match known truth.
+pub use intake::identity_recovery_rate;
+/// Refuse to treat size, identity, or provenance bounds as authorization.
+pub use intake::refuse_bounds_as_authorization;
+/// Refuse untrusted intake that has no purpose-bound grant.
+pub use intake::refuse_intake_without_grant;

crates/intake_authorization/tests/crate_contract.rs

@@ -0,0 +1,7 @@
+//! Integration contract for the `intake_authorization` package identity.
+
+#[test]
+fn package_identity_is_stable() {
+    let observed = std::hint::black_box(env!("CARGO_PKG_NAME"));
+    assert_eq!(observed, "intake_authorization");
+}