feat: add financial governance evaluators (spend limits + transaction policy)

Implements the financial governance evaluator proposed in #129, following
the technical guidance from @lan17:

1. Decoupled from data source — SpendStore protocol with pluggable backends
   (InMemorySpendStore included, PostgreSQL/Redis via custom implementation)
2. No new tables in core agent control — self-contained contrib package
3. Context-aware limits — channel/agent/session overrides via evaluate metadata
4. Python SDK compatible — standard Evaluator interface, works with both
   server and SDK evaluation engine

Two evaluators:
- financial_governance.spend_limit: Cumulative spend tracking with
  per-transaction caps and rolling period budgets
- financial_governance.transaction_policy: Static policy enforcement
  (currency allowlists, recipient blocklists, amount bounds)

53 tests passing.

Closes #129

Signed-off-by: up2itnow0822 <up2itnow0822@users.noreply.github.com>
Signed-off-by: up2itnow0822 <up2itnow0822@gmail.com>
Signed-off-by: up2itnow0822 <up2itnow0822@users.noreply.github.com>

Author: up2itnow0822

evaluators/contrib/financial-governance/README.md

@@ -0,0 +1,156 @@
+# Financial Governance Evaluators for Agent Control
+
+Evaluators that enforce financial spend limits and transaction policies for autonomous AI agents.
+
+As agents transact autonomously via protocols like [x402](https://github.com/coinbase/x402) and payment layers like [agentpay-mcp](https://github.com/AI-Agent-Economy/agentpay-mcp), enterprises need governance over what agents spend. These evaluators bring financial policy enforcement into the Agent Control framework.
+
+## Evaluators
+
+### `financial_governance.spend_limit`
+
+Tracks cumulative agent spend and enforces rolling budget limits. Stateful — records approved transactions and checks new ones against accumulated spend.
+
+- **Per-transaction cap** — reject any single payment above a threshold
+- **Rolling period budget** — reject payments that would exceed a time-windowed budget
+- **Context-aware overrides** — different limits per channel, agent, or session via evaluate metadata
+- **Pluggable storage** — abstract `SpendStore` protocol with built-in `InMemorySpendStore`; bring your own PostgreSQL, Redis, etc.
+
+### `financial_governance.transaction_policy`
+
+Static policy checks with no state tracking. Enforces structural rules on individual transactions.
+
+- **Currency allowlist** — only permit specific currencies (e.g., `["USDC", "USDT"]`)
+- **Recipient blocklist/allowlist** — control which addresses an agent can pay
+- **Amount bounds** — minimum and maximum per-transaction limits
+
+## Installation
+
+```bash
+# From the repo root (development)
+cd evaluators/contrib/financial-governance
+pip install -e ".[dev]"
+```
+
+## Configuration
+
+### Spend Limit
+
+```yaml
+evaluators:
+  - type: financial_governance.spend_limit
+    config:
+      max_per_transaction: 100.0    # Max USDC per single payment
+      max_per_period: 1000.0        # Rolling 24h budget
+      period_seconds: 86400         # Budget window (default: 24 hours)
+      currency: USDC                # Currency to govern
+```
+
+### Transaction Policy
+
+```yaml
+evaluators:
+  - type: financial_governance.transaction_policy
+    config:
+      allowed_currencies: [USDC, USDT]
+      blocked_recipients: ["0xDEAD..."]
+      allowed_recipients: ["0xALICE...", "0xBOB..."]
+      min_amount: 0.01
+      max_amount: 5000.0
+```
+
+## Input Data Schema
+
+Both evaluators expect a dict with these fields:
+
+```python
+{
+    "amount": 50.0,              # required — transaction amount
+    "currency": "USDC",          # required — payment currency
+    "recipient": "0xABC...",     # required — payment recipient
+    # optional context (used for channel-specific overrides and logging)
+    "channel": "slack-trading",
+    "agent_id": "agent-42",
+    "session_id": "sess-abc",
+    # optional per-call limit overrides (spend_limit evaluator only)
+    "channel_max_per_transaction": 50.0,
+    "channel_max_per_period": 200.0,
+}
+```
+
+Result convention: `matched=True` means the transaction **violates** the policy.
+
+## Context-Aware Limits
+
+The spend limit evaluator supports channel-specific overrides via the data dict, implementing per-context policies without separate evaluator instances:
+
+```python
+# Base policy: $1000/day max, $100/tx max
+# But the "experimental" channel gets tighter limits:
+result = await evaluator.evaluate({
+    "amount": 75.0,
+    "currency": "USDC",
+    "recipient": "0xABC",
+    "channel": "experimental",
+    "channel_max_per_transaction": 50.0,   # override: $50 cap for this channel
+    "channel_max_per_period": 200.0,       # override: $200/day for this channel
+})
+```
+
+## Custom SpendStore
+
+The `SpendStore` protocol requires two methods. Implement them for your backend:
+
+```python
+from agent_control_evaluator_financial_governance.spend_limit import (
+    SpendStore,
+    SpendLimitConfig,
+    SpendLimitEvaluator,
+)
+
+class PostgresSpendStore:
+    """Example: PostgreSQL-backed spend tracking."""
+
+    def __init__(self, connection_string: str):
+        self._conn = connect(connection_string)
+
+    def record_spend(self, amount: float, currency: str, metadata: dict | None = None) -> None:
+        self._conn.execute(
+            "INSERT INTO agent_spend (amount, currency, metadata, recorded_at) VALUES (%s, %s, %s, NOW())",
+            (amount, currency, json.dumps(metadata)),
+        )
+
+    def get_spend(self, currency: str, since_timestamp: float) -> float:
+        row = self._conn.execute(
+            "SELECT COALESCE(SUM(amount), 0) FROM agent_spend WHERE currency = %s AND recorded_at >= to_timestamp(%s)",
+            (currency, since_timestamp),
+        ).fetchone()
+        return float(row[0])
+
+# Use it:
+store = PostgresSpendStore("postgresql://...")
+evaluator = SpendLimitEvaluator(config, store=store)
+```
+
+## Running Tests
+
+```bash
+cd evaluators/contrib/financial-governance
+pip install -e ".[dev]"
+pytest tests/ -v
+```
+
+## Design Decisions
+
+1. **Decoupled from data source** — The `SpendStore` protocol means no new tables in core Agent Control. Bring your own persistence.
+2. **Context-aware limits** — Override keys in the evaluate data dict allow per-channel, per-agent, or per-session limits without multiple evaluator instances.
+3. **Python SDK compatible** — Uses the standard evaluator interface; works with both the server and the Python SDK evaluation engine.
+4. **Fail-open on errors** — Missing or malformed data returns `matched=False` with an `error` field, following Agent Control conventions.
+
+## Related Projects
+
+- [x402](https://github.com/coinbase/x402) — HTTP 402 payment protocol
+- [agentpay-mcp](https://github.com/up2itnow0822/agentpay-mcp) — MCP server for non-custodial agent payments
+
+## License
+
+Apache-2.0 — see [LICENSE](../../../LICENSE).

evaluators/contrib/financial-governance/pyproject.toml

@@ -0,0 +1,55 @@
+[project]
+name = "agent-control-evaluator-financial-governance"
+version = "0.1.0"
+description = "Financial governance evaluators for agent-control — spend limits and transaction policy enforcement"
+readme = "README.md"
+requires-python = ">=3.12"
+license = { text = "Apache-2.0" }
+authors = [{ name = "agent-control contributors" }]
+keywords = ["agent-control", "evaluator", "financial", "spend-limit", "x402", "agentpay"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries",
+]
+dependencies = [
+    "agent-control-evaluators>=3.0.0",
+    "agent-control-models>=3.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0.0",
+    "pytest-asyncio>=0.23.0",
+    "pytest-cov>=4.0.0",
+    "ruff>=0.1.0",
+    "mypy>=1.8.0",
+]
+
+[project.entry-points."agent_control.evaluators"]
+"financial_governance.spend_limit" = "agent_control_evaluator_financial_governance.spend_limit:SpendLimitEvaluator"
+"financial_governance.transaction_policy" = "agent_control_evaluator_financial_governance.transaction_policy:TransactionPolicyEvaluator"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/agent_control_evaluator_financial_governance"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "F", "I"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+
+[tool.uv.sources]
+agent-control-evaluators = { path = "../../builtin", editable = true }
+agent-control-models = { path = "../../../models", editable = true }

evaluators/contrib/financial-governance/src/agent_control_evaluator_financial_governance/__init__.py

@@ -0,0 +1,46 @@
+"""Financial governance evaluators for agent-control.
+
+Provides two evaluators for enforcing financial policy on AI agent transactions:
+
+- ``financial_governance.spend_limit``: Tracks cumulative spend against rolling
+  period budgets and per-transaction caps.
+- ``financial_governance.transaction_policy``: Static policy checks — allowlists,
+  blocklists, amount bounds, and permitted currencies.
+
+Both evaluators are registered automatically when this package is installed and
+the ``agent_control.evaluators`` entry point group is discovered.
+
+Example usage in an agent-control control config::
+
+    {
+      "condition": {
+        "selector": {"path": "*"},
+        "evaluator": {
+          "name": "financial_governance.spend_limit",
+          "config": {
+            "max_per_transaction": 100.0,
+            "max_per_period": 1000.0,
+            "period_seconds": 86400,
+            "currency": "USDC"
+          }
+        }
+      },
+      "action": {"decision": "deny"}
+    }
+"""
+
+from agent_control_evaluator_financial_governance.spend_limit import (
+    SpendLimitConfig,
+    SpendLimitEvaluator,
+)
+from agent_control_evaluator_financial_governance.transaction_policy import (
+    TransactionPolicyConfig,
+    TransactionPolicyEvaluator,
+)
+
+__all__ = [
+    "SpendLimitEvaluator",
+    "SpendLimitConfig",
+    "TransactionPolicyEvaluator",
+    "TransactionPolicyConfig",
+]

evaluators/contrib/financial-governance/src/agent_control_evaluator_financial_governance/spend_limit/__init__.py

@@ -0,0 +1,12 @@
+"""Spend-limit evaluator package."""
+
+from .config import SpendLimitConfig
+from .evaluator import SpendLimitEvaluator
+from .store import InMemorySpendStore, SpendStore
+
+__all__ = [
+    "SpendLimitEvaluator",
+    "SpendLimitConfig",
+    "SpendStore",
+    "InMemorySpendStore",
+]

evaluators/contrib/financial-governance/src/agent_control_evaluator_financial_governance/spend_limit/config.py

@@ -0,0 +1,68 @@
+"""Configuration model for the spend-limit evaluator."""
+
+from __future__ import annotations
+
+from pydantic import Field, field_validator
+
+from agent_control_evaluators import EvaluatorConfig
+
+
+class SpendLimitConfig(EvaluatorConfig):
+    """Configuration for :class:`~.evaluator.SpendLimitEvaluator`.
+
+    All monetary fields are expressed in the units of *currency*.
+
+    Attributes:
+        max_per_transaction: Hard cap on any single transaction amount.  A
+            transaction whose ``amount`` exceeds this value is blocked
+            regardless of accumulated period spend.  Set to ``0.0`` to disable.
+        max_per_period: Maximum total spend allowed within the rolling
+            *period_seconds* window.  Set to ``0.0`` to disable.
+        period_seconds: Length of the rolling budget window in seconds.
+            Defaults to ``86400`` (24 hours).
+        currency: Currency symbol this policy applies to (e.g. ``"USDC"``).
+            Transactions whose currency does not match are passed through as
+            *not matched* (i.e. allowed).
+
+    Example config dict::
+
+        {
+          "max_per_transaction": 500.0,
+          "max_per_period": 5000.0,
+          "period_seconds": 86400,
+          "currency": "USDC"
+        }
+    """
+
+    max_per_transaction: float = Field(
+        default=0.0,
+        ge=0.0,
+        description=(
+            "Per-transaction spend cap in *currency* units. "
+            "0.0 means no per-transaction limit."
+        ),
+    )
+    max_per_period: float = Field(
+        default=0.0,
+        ge=0.0,
+        description=(
+            "Maximum cumulative spend allowed in the rolling period window. "
+            "0.0 means no period limit."
+        ),
+    )
+    period_seconds: int = Field(
+        default=86_400,
+        ge=1,
+        description="Rolling budget window length in seconds (default: 86400 = 24 h).",
+    )
+    currency: str = Field(
+        ...,
+        min_length=1,
+        description="Currency symbol this policy applies to (e.g. 'USDC', 'ETH').",
+    )
+
+    @field_validator("currency")
+    @classmethod
+    def normalize_currency(cls, v: str) -> str:
+        """Normalize currency symbol to upper-case for consistent comparison."""
+        return v.upper()