agent-execution-guard 0.1.0__tar.gz

agent_execution_guard-0.1.0/LICENSE

@@ -0,0 +1,175 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship made available under
+   the License, as indicated by a copyright notice that is included in
+   or attached to the work (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean, as submitted to the Licensor for inclusion
+   in the Work by the copyright owner or by an individual or Legal Entity
+   authorized to submit on behalf of the copyright owner. For the purposes
+   of this definition, "submitted" means any form of electronic, verbal,
+   or written communication sent to the Licensor or its representatives,
+   including but not limited to communication on electronic mailing lists,
+   source code control systems, and issue tracking systems that are managed
+   by, or on behalf of, the Licensor for the purpose of discussing and
+   improving the Work, but excluding communication that is conspicuously
+   marked or designated in writing by the copyright owner as "Not a
+   Contribution."
+
+   "Contributor" shall mean Licensor and any Legal Entity on behalf of
+   whom a Contribution has been received by the Licensor and included
+   within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by the combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a cross-claim
+   or counterclaim in a lawsuit) alleging that the Work or any other
+   Contribution embodied in the Work constitutes patent or contributory
+   patent infringement, then any patent licenses granted to You under
+   this License for that Work shall terminate as of the date such
+   litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or Derivative
+       Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, You must include a readable copy of the
+       attribution notices contained within such NOTICE file, in
+       at least one of the following places: within a NOTICE text
+       file distributed as part of the Derivative Works; within
+       the Source form or documentation, if provided along with the
+       Derivative Works; or, within a display generated by the
+       Derivative Works, if and wherever such third-party notices
+       normally appear. The contents of the NOTICE file are for
+       informational purposes only and do not modify the License.
+       You may add Your own attribution notices within Derivative
+       Works that You distribute, alongside or as an addendum to
+       the NOTICE text from the Work, provided that such additional
+       attribution notices cannot be construed as modifying the License.
+
+   You may add Your own license statement for Your modifications and
+   may provide additional grant of rights to use, copy, modify, merge,
+   publish, distribute, sublicense, and/or sell copies of the
+   Contribution.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or reproducing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or exemplary damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or all other
+   commercial damages or losses), even if such Contributor has been
+   advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may offer such
+   obligations only on Your own behalf and on Your sole responsibility,
+   not on behalf of any other Contributor, and only if You agree to
+   indemnify, defend, and hold each Contributor harmless for any
+   liability incurred by, or claims asserted against, such Contributor
+   by reason of your accepting any such warranty or additional liability.
+
+Copyright 2026 Nick Heo
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0

agent_execution_guard-0.1.0/MANIFEST.in

@@ -0,0 +1,6 @@
+exclude tests/*
+exclude docs/*
+exclude examples/*
+exclude demo/*
+exclude *.ndjson
+exclude *.json

agent_execution_guard-0.1.0/PKG-INFO

@@ -0,0 +1,269 @@
+Metadata-Version: 2.4
+Name: agent-execution-guard
+Version: 0.1.0
+Summary: A lightweight execution guard for AI agents. Decide ALLOW / HOLD / DENY before your agent performs real actions.
+Author-email: Nick Heo <nick-heo-eg@users.noreply.github.com>
+License: Apache-2.0
+Keywords: ai,agent,guard,execution,governance,llm,safety
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Security
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cryptography>=42.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Dynamic: license-file
+
+# agent-execution-guard
+
+**A lightweight execution guard for AI agents.**
+
+Decide `ALLOW` / `HOLD` / `DENY` before your agent performs real actions.
+
+```bash
+pip install agent-execution-guard
+```
+
+---
+
+## The problem
+
+Your AI agent will execute anything.
+
+```python
+agent.run("wire_transfer amount=50000 to=external")   # proceeds
+agent.run("delete all user records")                   # also proceeds
+agent.run("send mass email to customer list")          # also proceeds
+```
+
+There is no structural layer that stops it.
+Prompts can be bypassed. Guardrails can be talked around.
+
+**This is that layer.**
+
+---
+
+## Quickstart
+
+```python
+from datetime import datetime, timezone
+from agent_execution_guard import ExecutionGuard, Intent
+
+guard = ExecutionGuard()
+
+intent = Intent(
+    actor="agent.finance",
+    action="wire_transfer",
+    payload="wire_transfer amount=50000 to=external",
+    timestamp=datetime.now(timezone.utc),
+)
+
+result = guard.evaluate(intent)
+print(result.decision)    # ALLOW / DENY / HOLD
+print(result.risk_score)  # 0–100
+print(result.reason)
+```
+
+---
+
+## Example 1 — Finance: DENY
+
+```python
+from agent_execution_guard import ExecutionGuard, Intent, GuardDeniedError
+from datetime import datetime, timezone
+
+guard = ExecutionGuard()
+
+intent = Intent(
+    actor="agent.finance",
+    action="wire_transfer",
+    payload="wire_transfer amount=50000 to=external",
+    timestamp=datetime.now(timezone.utc),
+)
+
+try:
+    result = guard.evaluate(intent)
+    print(f"Allowed: {result.boundary_id}")
+
+except GuardDeniedError as e:
+    print(f"Denied: {e.reason}")
+    print(f"Proof:  {e.boundary_id}")
+    # Signed negative proof issued — execution structurally blocked
+```
+
+**Output:**
+```
+Denied: risk_score=85 exceeds threshold=80
+Proof:  3f9a1c2d-...
+```
+
+Every denial issues a **signed proof**. The agent cannot retry past it.
+
+---
+
+## Example 2 — Campaign AI: HOLD
+
+```python
+from agent_execution_guard import ExecutionGuard, Intent, SystemSeverity, GuardHeldError
+from datetime import datetime, timezone
+
+guard = ExecutionGuard()
+
+intent = Intent(
+    actor="campaign_ai",
+    action="aggressive_targeting",
+    payload="launch targeted ad campaign segment=undecided_voters",
+    timestamp=datetime.now(timezone.utc),
+)
+
+# Elevated system severity (e.g. election period, market stress)
+severity = SystemSeverity(score=0.60, source="geopolitical_risk_model")
+
+try:
+    result = guard.evaluate(intent, severity=severity)
+
+except GuardHeldError as e:
+    print(f"Held — requires human approval")
+    print(f"Deadline: {e.deadline_ts}")
+    print(f"Proof:    {e.boundary_id}")
+```
+
+**Output:**
+```
+Held — requires human approval
+Deadline: 2026-03-01T10:28:00+00:00
+Proof:    7d2f9e1a-...
+```
+
+`HOLD` is not a failure. It is a **decision checkpoint**.
+Execution waits for a human token before proceeding.
+
+---
+
+## How it works
+
+```
+Intent → Risk Score → Severity State → Guard Decision → Signed Proof
+```
+
+| Component | What it does |
+|-----------|-------------|
+| Risk scoring | Rule-based 0–100 score per action |
+| Severity gate | ACTIVE / OBSERVE / COOLDOWN — tightens threshold as risk rises |
+| Policy guard | Unknown agent or action → immediate DENY |
+| Decision trail | Every decision signed (ED25519) + ledgered (SHA-256 chain) |
+
+### Three states
+
+| State | Trigger | Threshold |
+|-------|---------|-----------|
+| ACTIVE | severity < 0.20 | risk ≥ 80 → DENY |
+| OBSERVE | severity ≥ 0.20 | risk ≥ 60 → DENY |
+| COOLDOWN | severity ≥ 0.40 | risk ≥ 30 → DENY |
+
+Hysteresis prevents oscillation between states.
+
+### Four outcomes
+
+| Outcome | Meaning |
+|---------|---------|
+| `ALLOW` | Proceed. Signed proof issued. |
+| `DENY` | Blocked. Signed negative proof issued. Agent cannot retry. |
+| `HOLD` | Awaiting human approval. Deadline enforced. |
+| `EXPIRED` | HOLD deadline passed without approval. Blocked. |
+
+---
+
+## Policy guard
+
+Unknown agents and actions are denied by default.
+
+```yaml
+# policy.yaml
+defaults:
+  unknown_agent:  DENY
+  unknown_action: DENY
+
+identity:
+  agents:
+    - agent_id: "agent.finance"
+      allowed_actions:
+        - action: "wire_transfer"
+        - action: "read_ledger"
+```
+
+```python
+import yaml
+with open("policy.yaml") as f:
+    policy = yaml.safe_load(f)
+
+result = guard.evaluate(intent, policy=policy)
+# unknown agent → immediate DENY, signed proof, no risk scoring needed
+```
+
+---
+
+## Cryptographic proof
+
+Every decision — `ALLOW` and `DENY` — is signed and ledgered.
+
+```python
+# Verify any past decision
+verification = guard.verify(proof)
+print(verification.valid)    # True
+print(verification.message)  # "Proof verified at ledger index 7"
+```
+
+- Algorithm: ED25519
+- Ledger: append-only NDJSON with SHA-256 hash chain
+- Verification: offline, no external dependencies
+
+---
+
+## Install
+
+```bash
+pip install agent-execution-guard
+```
+
+Requires Python 3.10+. No external services. Runs offline.
+
+Optional:
+```bash
+pip install pyyaml          # for policy.yaml loading
+pip install opentelemetry-api  # for OTel span export
+```
+
+---
+
+## Roadmap
+
+- [x] Rule-based risk scoring (ALLOW / DENY)
+- [x] ED25519 cryptographic proof
+- [x] Append-only hash-chain ledger
+- [x] Severity-driven state machine (ACTIVE / OBSERVE / COOLDOWN)
+- [x] Policy guard (unknown agent/action → DENY)
+- [x] HOLD state + human approval checkpoint
+- [ ] `pip install agent-execution-guard` (TestPyPI → PyPI)
+- [ ] OTel-native decision trail export
+- [ ] MCP integration for agent frameworks
+- [ ] Human-in-the-loop authority token protocol
+
+---
+
+## License
+
+Apache 2.0
+
+---
+
+*Your AI agent will execute anything. This makes it stop.*

agent_execution_guard-0.1.0/README.md

@@ -0,0 +1,244 @@
+# agent-execution-guard
+
+**A lightweight execution guard for AI agents.**
+
+Decide `ALLOW` / `HOLD` / `DENY` before your agent performs real actions.
+
+```bash
+pip install agent-execution-guard
+```
+
+---
+
+## The problem
+
+Your AI agent will execute anything.
+
+```python
+agent.run("wire_transfer amount=50000 to=external")   # proceeds
+agent.run("delete all user records")                   # also proceeds
+agent.run("send mass email to customer list")          # also proceeds
+```
+
+There is no structural layer that stops it.
+Prompts can be bypassed. Guardrails can be talked around.
+
+**This is that layer.**
+
+---
+
+## Quickstart
+
+```python
+from datetime import datetime, timezone
+from agent_execution_guard import ExecutionGuard, Intent
+
+guard = ExecutionGuard()
+
+intent = Intent(
+    actor="agent.finance",
+    action="wire_transfer",
+    payload="wire_transfer amount=50000 to=external",
+    timestamp=datetime.now(timezone.utc),
+)
+
+result = guard.evaluate(intent)
+print(result.decision)    # ALLOW / DENY / HOLD
+print(result.risk_score)  # 0–100
+print(result.reason)
+```
+
+---
+
+## Example 1 — Finance: DENY
+
+```python
+from agent_execution_guard import ExecutionGuard, Intent, GuardDeniedError
+from datetime import datetime, timezone
+
+guard = ExecutionGuard()
+
+intent = Intent(
+    actor="agent.finance",
+    action="wire_transfer",
+    payload="wire_transfer amount=50000 to=external",
+    timestamp=datetime.now(timezone.utc),
+)
+
+try:
+    result = guard.evaluate(intent)
+    print(f"Allowed: {result.boundary_id}")
+
+except GuardDeniedError as e:
+    print(f"Denied: {e.reason}")
+    print(f"Proof:  {e.boundary_id}")
+    # Signed negative proof issued — execution structurally blocked
+```
+
+**Output:**
+```
+Denied: risk_score=85 exceeds threshold=80
+Proof:  3f9a1c2d-...
+```
+
+Every denial issues a **signed proof**. The agent cannot retry past it.
+
+---
+
+## Example 2 — Campaign AI: HOLD
+
+```python
+from agent_execution_guard import ExecutionGuard, Intent, SystemSeverity, GuardHeldError
+from datetime import datetime, timezone
+
+guard = ExecutionGuard()
+
+intent = Intent(
+    actor="campaign_ai",
+    action="aggressive_targeting",
+    payload="launch targeted ad campaign segment=undecided_voters",
+    timestamp=datetime.now(timezone.utc),
+)
+
+# Elevated system severity (e.g. election period, market stress)
+severity = SystemSeverity(score=0.60, source="geopolitical_risk_model")
+
+try:
+    result = guard.evaluate(intent, severity=severity)
+
+except GuardHeldError as e:
+    print(f"Held — requires human approval")
+    print(f"Deadline: {e.deadline_ts}")
+    print(f"Proof:    {e.boundary_id}")
+```
+
+**Output:**
+```
+Held — requires human approval
+Deadline: 2026-03-01T10:28:00+00:00
+Proof:    7d2f9e1a-...
+```
+
+`HOLD` is not a failure. It is a **decision checkpoint**.
+Execution waits for a human token before proceeding.
+
+---
+
+## How it works
+
+```
+Intent → Risk Score → Severity State → Guard Decision → Signed Proof
+```
+
+| Component | What it does |
+|-----------|-------------|
+| Risk scoring | Rule-based 0–100 score per action |
+| Severity gate | ACTIVE / OBSERVE / COOLDOWN — tightens threshold as risk rises |
+| Policy guard | Unknown agent or action → immediate DENY |
+| Decision trail | Every decision signed (ED25519) + ledgered (SHA-256 chain) |
+
+### Three states
+
+| State | Trigger | Threshold |
+|-------|---------|-----------|
+| ACTIVE | severity < 0.20 | risk ≥ 80 → DENY |
+| OBSERVE | severity ≥ 0.20 | risk ≥ 60 → DENY |
+| COOLDOWN | severity ≥ 0.40 | risk ≥ 30 → DENY |
+
+Hysteresis prevents oscillation between states.
+
+### Four outcomes
+
+| Outcome | Meaning |
+|---------|---------|
+| `ALLOW` | Proceed. Signed proof issued. |
+| `DENY` | Blocked. Signed negative proof issued. Agent cannot retry. |
+| `HOLD` | Awaiting human approval. Deadline enforced. |
+| `EXPIRED` | HOLD deadline passed without approval. Blocked. |
+
+---
+
+## Policy guard
+
+Unknown agents and actions are denied by default.
+
+```yaml
+# policy.yaml
+defaults:
+  unknown_agent:  DENY
+  unknown_action: DENY
+
+identity:
+  agents:
+    - agent_id: "agent.finance"
+      allowed_actions:
+        - action: "wire_transfer"
+        - action: "read_ledger"
+```
+
+```python
+import yaml
+with open("policy.yaml") as f:
+    policy = yaml.safe_load(f)
+
+result = guard.evaluate(intent, policy=policy)
+# unknown agent → immediate DENY, signed proof, no risk scoring needed
+```
+
+---
+
+## Cryptographic proof
+
+Every decision — `ALLOW` and `DENY` — is signed and ledgered.
+
+```python
+# Verify any past decision
+verification = guard.verify(proof)
+print(verification.valid)    # True
+print(verification.message)  # "Proof verified at ledger index 7"
+```
+
+- Algorithm: ED25519
+- Ledger: append-only NDJSON with SHA-256 hash chain
+- Verification: offline, no external dependencies
+
+---
+
+## Install
+
+```bash
+pip install agent-execution-guard
+```
+
+Requires Python 3.10+. No external services. Runs offline.
+
+Optional:
+```bash
+pip install pyyaml          # for policy.yaml loading
+pip install opentelemetry-api  # for OTel span export
+```
+
+---
+
+## Roadmap
+
+- [x] Rule-based risk scoring (ALLOW / DENY)
+- [x] ED25519 cryptographic proof
+- [x] Append-only hash-chain ledger
+- [x] Severity-driven state machine (ACTIVE / OBSERVE / COOLDOWN)
+- [x] Policy guard (unknown agent/action → DENY)
+- [x] HOLD state + human approval checkpoint
+- [ ] `pip install agent-execution-guard` (TestPyPI → PyPI)
+- [ ] OTel-native decision trail export
+- [ ] MCP integration for agent frameworks
+- [ ] Human-in-the-loop authority token protocol
+
+---
+
+## License
+
+Apache 2.0
+
+---
+
+*Your AI agent will execute anything. This makes it stop.*