Metadata-Version: 2.4
Name: provenza
Version: 0.2.0
Summary: Provenza SDK: governed, signed and auditable actions for AI agents
Author: Laziz Kironov
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/kironovlaziz-del/provenza
Project-URL: Documentation, https://github.com/kironovlaziz-del/provenza/tree/main/sdk/python
Keywords: ai-governance,agents,audit,mcp,mcp-server,mcp-gateway,a2a,security
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Security
Classifier: Typing :: Typed
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
License-File: NOTICE
Requires-Dist: cryptography>=42
Requires-Dist: httpx>=0.27
Provides-Extra: keychain
Requires-Dist: keyring>=24; extra == "keychain"
Provides-Extra: pq
Requires-Dist: cryptography>=48; extra == "pq"
Provides-Extra: openai
Requires-Dist: openai>=1.40; extra == "openai"
Provides-Extra: langchain
Requires-Dist: langchain-core>=0.3; extra == "langchain"
Provides-Extra: autogen
Requires-Dist: autogen-core>=0.4; extra == "autogen"
Provides-Extra: crewai
Requires-Dist: crewai>=1.0; extra == "crewai"
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
Dynamic: license-file

# Provenza Python SDK

Governed, signed and auditable actions for AI agents.

<!-- mcp-name: io.github.kironovlaziz-del/provenza -->

```bash
pip install provenza
```

```python
from provenza import Agent

agent = Agent("support-bot")   # reads PROVENZA_URL and PROVENZA_TOKEN

@agent.tool(name="zendesk.read")
def open_tickets(status: str = "open") -> list:
    return zendesk.tickets.list(status=status)

open_tickets()   # checked by Provenza, run, recorded and signed
```

## What happens on a call

In **connected** mode (when `PROVENZA_URL` is set):

1. The SDK asks the server whether this call may run. The server checks
   the agent's rights, your organization's policies, the Tool Registry,
   behaviour, and the circuit breaker.
2. The tool runs only if the call is allowed. Otherwise:
   - a denied call raises `ProvenzaDenied` (a `PermissionError`);
   - a call that needs a human decision raises `ProvenzaApprovalRequired`.

   In both cases the attempt is recorded. Once a person approves the held
   call, make exactly the same call again: it runs once, within an hour.

   ```python
   try:
       send_report(to="cfo@example.com")
   except ProvenzaApprovalRequired as held:
       if agent.wait_for_approval(held.action_id)["decision"] == "approved":
           send_report(to="cfo@example.com")      # the same call: runs once
   ```
3. The result is recorded and signed with the agent's own key. Provenza
   seals it into its signed audit log, so you can download a receipt for
   it that is verifiable offline.

The SDK **fails closed**: if the server cannot be reached, the tool does not
run and the SDK raises `ProvenzaUnavailable`. Pass `fail_open=True` to run
anyway and log the call locally as unchecked.

In **standalone** mode (no server), calls run and are written to a local,
signed, hash-chained audit log. You can restrict them with
`allowed_tools=[...]`.

Only hashes of arguments and results are written to the local audit log,
never the content.

## Getting an identity

An admin issues a one-time enrollment token in Provenza (**Agents → New
agent**). The agent's keys are generated on its own machine, and only the
public key goes to the server:

```bash
export PROVENZA_URL=https://provenza.example.com
export PROVENZA_TOKEN=pvz_enr_...      # used once; afterwards the identity file is enough
```

The identity is stored in `~/.config/provenza/agents/<name>.json` (mode
600). The SDK refuses to load it if other users can read it. It is the same
file `tools/provenza_sign.py enroll` writes, so you can enroll with the CLI
and run with the SDK.

To keep the private keys in the OS keychain instead:

```bash
pip install 'provenza[keychain]'
```

```python
Agent("bot", key_store="keychain")
```

For post-quantum hybrid keys (Ed25519 + ML-DSA-65):

```bash
pip install 'provenza[pq]'
```

```python
Agent("bot", hybrid=True)
```

`agent.fingerprint` is the value to give whoever verifies the agent's
signatures.

## More

```python
with agent.chain(chain_id):            # act inside a delegation chain
    open_tickets()

agent.delegate(other_agent_id, "summarize Q3", ["read"], tools=["db.read"], expires_in=600)

chk = agent.check("files.delete", {"path": p})   # ask for something that is not a decorated tool
if chk.allowed:
    delete(p)
    agent.record(chk, {"deleted": True})
```

Async tools work the same way (`async def`). If a call ran but could not be
recorded on the server (the server went down mid-call), the SDK does not
hide the result. It writes a signed **gap** entry to the local audit log and
emits a `ProvenzaWarning`.

## Latency

A governed call costs the SDK's own work plus round-trips to the server.
The SDK's own work was measured against an in-process server (no network)
on 2026-10-11:

| `record_mode` | round-trips before the tool returns | median | p95 |
|---|---|---|---|
| `"sync"` (default) | 2 (check, record) | 0.42 ms | 0.59 ms |
| `"background"` | 1 (check) | 0.15 ms | 0.33 ms |

Add your network round-trip (×2 or ×1) and the server's checks.

With `"sync"`, the record is on the server when the tool returns.

With `"background"`, records are sent from a queue, in order. A failure
becomes a signed gap in the local audit log, the same as in sync mode.
`flush()` / `aflush()` wait for the queue, and `close()` and interpreter
exit drain it. A process that is **killed** loses whatever is still
queued; that is the price of not waiting.

Refusals are always recorded before the exception is raised, so
`ProvenzaDenied.action_id` is known at once.

## Auto-instrumentation

```python
import provenza.auto
provenza.auto.instrument(agent)        # httpx (sync and async) and requests
```

Every **direct** call from this process to an AI provider becomes a
governed action. That covers the OpenAI, Anthropic, Mistral, Cohere and
Gemini SDKs, LangChain's provider clients, or plain HTTP. The provider
hosts come from your organization's AI domain catalog (Shadow AI), and the
**server** decides each call:

| catalog status | result |
|---|---|
| `blocked` | refused; incident `ai_domain_blocked` |
| `allowed` | sent, unless a policy refuses it |
| not classified | sent, unless a policy refuses it; recorded for an admin to classify |

Only the host, method, path (without the query string), and the hash and
size of the body are recorded. The prompt is never recorded.

A refusal comes back as an HTTP answer: 403 with an OpenAI-style error
body and `x-should-retry: false`. Provider SDKs therefore raise their usual
permission error with Provenza's reason and do not retry. With the server
unreachable, nothing is sent (503). Other hosts, and calls to Provenza
itself, are untouched. `provenza.auto.uninstrument()` puts everything back.

## Egress proxy

Behind a Provenza egress proxy (`proxy/` in the repository) the agent has
two options. It can send its key and let the proxy check every request, or
it can check a request itself and send the check id:

```python
body = json.dumps({"amount": 1000}).encode()
chk = agent.proxy_check("stripe", "POST", "/v1/charges", body=body)
if chk.allowed:
    httpx.post("http://127.0.0.1:8443/stripe/v1/charges", content=body, headers=chk.proxy_headers)
```

`path`, `query` and `body` must be exactly what goes on the wire. The proxy
refuses any other request under that check. The proxy records the request,
so it is not passed to `record()`.

`agent.proxy_request_headers(...)` (same arguments) returns the headers to
send: the check's, or, while Provenza is unreachable, only the agent's
signed request. A proxy that enforces the signed policy then judges it by
the signed release alone until its local kill switch stops it, and Provenza
records the request when it is back (docs/pvp/edge.md, section 6).

## HTTP tools through Provenza

An API registered in Provenza (**Gateways → HTTP tools**) is called through
Provenza, and the agent never holds its key. The call is checked, made and
recorded in one step. A tool that takes a credential is called through the
egress proxy, which holds it - Provenza itself holds no credential:

```python
agent = Agent("billing-bot", egress_proxy="http://127.0.0.1:8443")   # or PROVENZA_EGRESS_PROXY
out = agent.invoke("crm.set_tier", {"id": "42", "tier": "gold"})
out["status"], out["body"]          # a refusal raises ProvenzaDenied
agent.http_tools()                  # names, descriptions and input schemas, for the model
```

Through a proxy the HTTP request itself is signed too (`X-Provenza-Request`),
which a proxy in enforce mode requires on every path. For clients that cannot
sign (a stock OpenAI or MCP client) run the proxy's agent mode next to the
agent with this identity file (`provenza-proxy -agent-identity …`,
`proxy/README.md`).

## Egress self-check

Is this host confined to the Provenza egress proxy, its only way out? Run
the check at start-up and then periodically. With **Require confined egress**
on, an agent acts only while its latest check is `confined`. See
`docs/egress-lockdown.md`.

```python
agent.egress_selfcheck()     # {"verdict": "confined" | "open", ...}
```

## Permits for tools

An allowed check carries a permit signed by the organization. The agent
sends it with the call:

```python
chk = agent.check("crm.update", payload)
if chk.allowed:
    httpx.post("https://crm-tool.internal/update", json=payload, headers=chk.permit_headers)
    agent.record(chk, output)
```

The tool runs nothing without a valid permit for exactly this call:

```python
from provenza.permit import PermitMiddleware, PermitVerifier, require_permit

verifier = PermitVerifier("https://provenza.example.com", org="acme")
app = PermitMiddleware(app, verifier, tool="crm.update")   # any ASGI app: FastAPI, Starlette, ...

@require_permit(verifier, "db.read")                         # or a plain function
def read(query: str): ...
```

The verifier checks the signature against the organization's JWKS, the
tool, the hash of the JSON body (it must be the checked input) and the
expiry. It then redeems the permit with Provenza, so it is used once across
every replica of the tool. If Provenza cannot be reached, it refuses.

## Integrations

Each framework is an optional extra. The SDK never requires one: `crewai`
and `autogen-core` even need conflicting `protobuf` versions.

**Through Provenza's gateways.** The call goes through the server, which
holds the provider credentials, so it is enforced whatever the agent's
code does.

```python
# pip install 'provenza[openai]'
from provenza.integrations.openai import gateway_client, wrap
client = gateway_client(agent)              # an openai.OpenAI pointed at the LLM gateway, with the agent's key
client = wrap(existing_client, agent)       # or a copy of one you already configured

# MCP: no extra needed. Point any MCP client at Provenza instead of at the servers.
from provenza.integrations.mcp import connection, client_config
conn = connection(agent)                    # {"url": ".../api/v1/mcp", "headers": {...}}
```

**MCP clients that start a local command** (Claude Desktop, Claude Code,
Cursor, Windsurf, Gemini CLI, VS Code): `provenza-mcp` is the same gateway
over stdio. Issue an enrollment token in Provenza (**Agents → New agent**)
and add:

```json
{"mcpServers": {"provenza": {
  "command": "uvx", "args": ["provenza-mcp"],
  "env": {"PROVENZA_URL": "https://provenza.example.com", "PROVENZA_TOKEN": "pvz_enr_..."}}}}
```

On the first start the agent enrolls: its keys are made on that machine,
and the token can then be removed. The client sees only the tools an
administrator approved, and every call is checked against the
organization's policies and recorded. Set `PROVENZA_AGENT_NAME` to run more
than one agent on a machine.

Through the LLM gateway, the server checks allowed models and providers,
policies and limits; it stores no prompt or answer. Every model the organization has
routed (OpenAI, Anthropic, Azure, …) is reached through this one
OpenAI-compatible endpoint. Streaming is not supported yet.

**Tool wrappers.** These keep the tool's name, description and argument
schema, so the model sees no difference:

```python
# pip install 'provenza[langchain]'
from provenza.integrations.langchain import govern_tools
tools = govern_tools(agent, [search, read_file])        # a refusal reaches the model as the tool's answer

# pip install 'provenza[autogen]'
from provenza.integrations.autogen import govern_tools
tools = govern_tools(agent, [FunctionTool(lookup, description="...")])

# pip install 'provenza[crewai]'
from provenza.integrations.crewai import govern_tools
researcher = crewai.Agent(role="...", goal="...", tools=govern_tools(agent, [search_tool]))
```

`prefix=` namespaces the names policies see, so `prefix="kb."` turns
`search` into `kb.search`. For anything else, govern a single call with
`agent.call(name, arguments, lambda: ...)` or `await agent.acall(...)`.

## What this is, and what it is not

The SDK runs inside your agent's process. It is the agent's honest record
and cooperative enforcement: code in the same process could call a tool
around it, and could read the agent's keys. Enforcement that does not
depend on the agent's code comes from Provenza's gateways (LLM, MCP, A2A),
which hold the credentials so the agent never has them.

Verify a local audit log with `provenza.audit_log.verify(path, public_key)`.
Verify a server receipt with `tools/provenza_audit.py receipt`.
