revenium-python-sdk 0.1.5__tar.gz → 0.1.7__tar.gz

{revenium_python_sdk-0.1.5/revenium_python_sdk.egg-info → revenium_python_sdk-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: revenium-python-sdk
-Version: 0.1.5
+Version: 0.1.7
 Summary: The official Revenium Python SDK — unified AI metering middleware for OpenAI, Anthropic, Google, Ollama, LiteLLM, Perplexity, and fal.ai.
 Author-email: Revenium <support@revenium.io>
 License: MIT
@@ -194,7 +194,7 @@ import revenium_middleware_openai  # Auto-initializes on import
 
 client = openai.OpenAI()
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}]
 )
 print(response.choices[0].message.content)
@@ -227,6 +227,98 @@ See [`examples/agentic_outcomes/`](examples/agentic_outcomes/) for runnable demo
 
 ---
 
+## Idempotency
+
+Every metering POST from the provider middleware automatically includes an `Idempotency-Key` header. If the Revenium API receives the same key with the same body within 24 hours, it returns the cached response instead of double-billing — making metering submissions safe to retry.
+
+### Default
+
+A fresh UUID v4 is generated automatically for every metering call. No action required.
+
+### Override
+
+Use the `idempotency_key` context manager to tie metering to a business-level identifier so the same logical operation never double-meters across retries:
+
+```python
+from revenium_middleware import idempotency_key
+
+with idempotency_key(f"order-{order_id}"):
+    response = openai.chat.completions.create(...)
+```
+
+The context manager is backed by `contextvars`, so it scopes correctly across threads and asyncio tasks.
+
+### Backend behavior
+
+| Scenario | Backend response |
+| -- | -- |
+| First call with key K and body B | Executes, caches for 24h |
+| Retry with same K and same B | Returns cached response (no double-bill) |
+| Same K with different B | `409 idempotency_key_mismatch` |
+| Concurrent in-flight with same K | `409 idempotency_key_in_progress` + `Retry-After: 1` |
+| Malformed key | `400 invalid_idempotency_key` |
+
+See [docs.revenium.io/integrations/idempotency](https://docs.revenium.io/integrations/idempotency) for full backend semantics.
+
+### Key format
+
+`Idempotency-Key` must be 1–255 printable ASCII characters. UUID v4 is the recommended format and what the SDK generates by default.
+
+---
+
+## Webhook Signature Verification
+
+Revenium signs every outbound webhook with HMAC-SHA256 when a signing secret is configured. The SDK ships a verification helper so your handler can validate signatures without writing crypto.
+
+Two headers arrive on every signed delivery:
+
+| Header | Value |
+| -- | -- |
+| `X-Revenium-Signature-256` | `sha256=<hex>`. During a 24h rotation overlap: `sha256=A, sha256=B`. |
+| `X-Revenium-Webhook-Timestamp` | Unix seconds at signing time. |
+
+### FastAPI example
+
+```python
+import os
+
+from fastapi import FastAPI, Header, HTTPException, Request
+
+from revenium_middleware.webhooks import verify_signature
+
+app = FastAPI()
+SIGNING_SECRETS = [os.environ["REVENIUM_WEBHOOK_SECRET"]]
+
+
+@app.post("/webhooks/revenium")
+async def receive(
+    request: Request,
+    x_revenium_signature_256: str = Header(...),
+    x_revenium_webhook_timestamp: str = Header(...),
+):
+    body = await request.body()
+    if not verify_signature(
+        payload=body,
+        signature_header=x_revenium_signature_256,
+        timestamp_header=x_revenium_webhook_timestamp,
+        secrets=SIGNING_SECRETS,
+    ):
+        raise HTTPException(status_code=401, detail="Invalid signature")
+
+    # ... process the event
+    return {"ok": True}
+```
+
+### Secret rotation
+
+When you rotate a signing secret in the Revenium dashboard with the default 24-hour overlap, both the old and new secrets are active simultaneously and every webhook is signed with both. Supply both values in `SIGNING_SECRETS` during the overlap window; remove the old one once it expires.
+
+### Webhooks without a signing secret
+
+Webhook deliveries without a configured signing secret arrive without HMAC headers. If your endpoint receives both signed and unsigned traffic, branch on header presence: treat missing headers as legacy unsigned mode and missing-signature-on-signed-only endpoints as an authentication failure.
+
+---
+
 ## Provider Usage Guides
 
 ### OpenAI
@@ -244,7 +336,7 @@ client = openai.OpenAI()
 
 # Basic chat completion
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "organizationName": "AcmeCorp",
@@ -256,7 +348,7 @@ response = client.chat.completions.create(
 
 # Streaming
 stream = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Tell me a story"}],
     stream=True
 )
@@ -547,7 +639,7 @@ litellm.api_base = os.getenv("LITELLM_PROXY_URL")
 litellm.api_key = os.getenv("LITELLM_API_KEY")
 
 response = litellm.completion(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "organizationName": "AcmeCorp",
@@ -705,7 +797,7 @@ handler = ReveniumCallbackHandler(
     agent_name="support_agent"
 )
 
-llm = ChatOpenAI(model="gpt-5.5", callbacks=[handler])
+llm = ChatOpenAI(model="gpt-4o-mini", callbacks=[handler])
 response = llm.invoke("Hello!")
 ```
 
@@ -744,7 +836,7 @@ result = agent.invoke(
 from revenium_middleware_langchain import AsyncReveniumCallbackHandler
 
 handler = AsyncReveniumCallbackHandler(trace_id="async-session")
-llm = ChatOpenAI(model="gpt-5.5", callbacks=[handler])
+llm = ChatOpenAI(model="gpt-4o-mini", callbacks=[handler])
 response = await llm.ainvoke("Hello!")
 ```
 
@@ -790,7 +882,7 @@ Add business context to any API call by passing a `usage_metadata` dictionary. A
 
 ```python
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "trace_id": "conv-28a7e9d4",
@@ -812,7 +904,7 @@ response = client.chat.completions.create(
 )
 ```
 
-**Deprecation notice:** The old field names `organizationId`, `organization_id`, `productId`, and `product_id` are still supported for backward compatibility but are deprecated. Use `organizationName` and `productName` for new implementations.
+**Deprecation notice:** The legacy field aliases `organizationId`, `organization_id`, `productId`, and `product_id` are accepted by this SDK only as an input-layer convenience and emit a `DeprecationWarning`. The Revenium backend no longer accepts them — they are translated to `organizationName` / `productName` before the wire call. Migrate to `organization_name` / `organizationName` and `product_name` / `productName` now; the input-layer aliases will be removed in the next major release.
 
 **API Reference:** [Complete metadata field documentation](https://revenium.readme.io/reference/meter_ai_completion)
 
@@ -853,7 +945,7 @@ REVENIUM_TRACE_TYPE=customer-support
 
 ```python
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "environment": "production",
@@ -877,7 +969,7 @@ workflow_id = str(uuid.uuid4())
 
 # Step 1: Parent operation
 parent_response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Analyze this document"}],
     usage_metadata={
         "trace_id": "analysis-session-456",
@@ -888,7 +980,7 @@ parent_response = client.chat.completions.create(
 
 # Step 2: Child operation linked to parent
 child_response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Summarize findings"}],
     usage_metadata={
         "trace_id": "analysis-session-456",
@@ -919,7 +1011,7 @@ from revenium_middleware import revenium_metadata
 def handle_customer_query(question: str) -> str:
     # All API calls automatically include the decorator metadata
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": question}]
     )
     return response.choices[0].message.content
@@ -958,13 +1050,13 @@ def outer_function():
 def mixed_metadata():
     # Uses decorator metadata
     response1 = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": "Hello"}]
     )
 
     # API-level metadata overrides decorator's task_type
     response2 = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": "Hello"}],
         usage_metadata={
             "task_type": "special-override",  # Overrides decorator
@@ -993,7 +1085,7 @@ from revenium_middleware import revenium_meter, revenium_metadata
 def premium_feature(prompt: str) -> str:
     # This WILL be metered (decorated with @revenium_meter)
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": prompt}]
     )
     return response.choices[0].message.content
@@ -1001,7 +1093,7 @@ def premium_feature(prompt: str) -> str:
 def free_feature(prompt: str) -> str:
     # This will NOT be metered (no @revenium_meter decorator)
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": prompt}]
     )
     return response.choices[0].message.content
@@ -1087,7 +1179,7 @@ from openai import OpenAI
 
 client = OpenAI()
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[
         {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": "What is the capital of France?"}
@@ -1109,62 +1201,6 @@ Prompt capture works with both streaming and non-streaming requests, and with mu
 
 ---
 
-## Terminal Summary Output
-
-Display a cost and usage summary in your terminal after each API request. Useful for development, debugging, and monitoring AI costs in real-time.
-
-### Configuration
-
-| Environment Variable | Values | Description |
-|---------------------|--------|-------------|
-| `REVENIUM_PRINT_SUMMARY` | `false` (default), `true` or `human`, `json` | Controls output format |
-| `REVENIUM_TEAM_ID` | Your team ID | Required to fetch and display cost information |
-
-```bash
-# Enable human-readable output
-export REVENIUM_PRINT_SUMMARY=human
-
-# Required for cost display (find in Revenium web app)
-export REVENIUM_TEAM_ID=your-team-id-here
-```
-
-### Human-Readable Format
-
-```
-============================================================
-REVENIUM USAGE SUMMARY
-============================================================
-Model: gpt-5.5
-Provider: OPENAI
-Duration: 1.23s
-
-Token Usage:
-  Input Tokens:  150
-  Output Tokens: 250
-  Total Tokens:  400
-
-Cost: $0.000045
-
-Trace ID: abc-123
-============================================================
-```
-
-### JSON Format
-
-```json
-{"model":"gpt-5.5","provider":"OPENAI","durationSeconds":1.23,"inputTokenCount":150,"outputTokenCount":250,"totalTokenCount":400,"cost":0.000045,"costStatus":"available","traceId":"abc-123"}
-```
-
-### Cost Status
-
-| Scenario | Display |
-|----------|---------|
-| Cost available | `$0.000045` |
-| `REVENIUM_TEAM_ID` set, cost pending | `Pending (aggregating... check Revenium dashboard)` |
-| `REVENIUM_TEAM_ID` not set | `Add REVENIUM_TEAM_ID to see pricing` |
-
----
-
 ## Cost Controls / Enforcement
 
 Block outbound provider requests client-side when a Revenium cost control trips. When the circuit breaker is enabled, the middleware polls compiled enforcement rules from the Revenium API in a background daemon thread and raises `BudgetExceededError` **before** the upstream call, preventing spend beyond the configured limit.
@@ -1243,7 +1279,7 @@ client = openai.OpenAI()
 
 try:
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": "Summarize the meeting notes"}],
     )
 except BudgetExceededError as exc:
@@ -1282,9 +1318,8 @@ See [`examples/openai/openai_blocking_demo.py`](examples/openai/openai_blocking_
 | `REVENIUM_METERING_BASE_URL` | `https://api.revenium.ai` | Revenium API endpoint |
 | `REVENIUM_LOG_LEVEL` | `INFO` | Log level: `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` |
 | `REVENIUM_CAPTURE_PROMPTS` | `false` | Enable prompt capture |
-| `REVENIUM_PRINT_SUMMARY` | `false` | Terminal output: `false`, `true`/`human`, `json` |
 | `REVENIUM_SELECTIVE_METERING` | `false` | Only meter `@revenium_meter` decorated functions |
-| `REVENIUM_TEAM_ID` | - | Team ID for cost display in terminal summary |
+| `REVENIUM_TEAM_ID` | - | Team ID for cost lookups |
 | `REVENIUM_ENVIRONMENT` | - | Deployment environment (auto-detects from `ENVIRONMENT`, `DEPLOYMENT_ENV`) |
 | `REVENIUM_REGION` | - | Cloud region (auto-detects from `AWS_REGION`, `AZURE_REGION`, `GCP_REGION`) |
 | `REVENIUM_CREDENTIAL_ALIAS` | - | Human-readable API key name |

{revenium_python_sdk-0.1.5 → revenium_python_sdk-0.1.7}/README.md

@@ -106,7 +106,7 @@ import revenium_middleware_openai  # Auto-initializes on import
 
 client = openai.OpenAI()
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}]
 )
 print(response.choices[0].message.content)
@@ -139,6 +139,98 @@ See [`examples/agentic_outcomes/`](examples/agentic_outcomes/) for runnable demo
 
 ---
 
+## Idempotency
+
+Every metering POST from the provider middleware automatically includes an `Idempotency-Key` header. If the Revenium API receives the same key with the same body within 24 hours, it returns the cached response instead of double-billing — making metering submissions safe to retry.
+
+### Default
+
+A fresh UUID v4 is generated automatically for every metering call. No action required.
+
+### Override
+
+Use the `idempotency_key` context manager to tie metering to a business-level identifier so the same logical operation never double-meters across retries:
+
+```python
+from revenium_middleware import idempotency_key
+
+with idempotency_key(f"order-{order_id}"):
+    response = openai.chat.completions.create(...)
+```
+
+The context manager is backed by `contextvars`, so it scopes correctly across threads and asyncio tasks.
+
+### Backend behavior
+
+| Scenario | Backend response |
+| -- | -- |
+| First call with key K and body B | Executes, caches for 24h |
+| Retry with same K and same B | Returns cached response (no double-bill) |
+| Same K with different B | `409 idempotency_key_mismatch` |
+| Concurrent in-flight with same K | `409 idempotency_key_in_progress` + `Retry-After: 1` |
+| Malformed key | `400 invalid_idempotency_key` |
+
+See [docs.revenium.io/integrations/idempotency](https://docs.revenium.io/integrations/idempotency) for full backend semantics.
+
+### Key format
+
+`Idempotency-Key` must be 1–255 printable ASCII characters. UUID v4 is the recommended format and what the SDK generates by default.
+
+---
+
+## Webhook Signature Verification
+
+Revenium signs every outbound webhook with HMAC-SHA256 when a signing secret is configured. The SDK ships a verification helper so your handler can validate signatures without writing crypto.
+
+Two headers arrive on every signed delivery:
+
+| Header | Value |
+| -- | -- |
+| `X-Revenium-Signature-256` | `sha256=<hex>`. During a 24h rotation overlap: `sha256=A, sha256=B`. |
+| `X-Revenium-Webhook-Timestamp` | Unix seconds at signing time. |
+
+### FastAPI example
+
+```python
+import os
+
+from fastapi import FastAPI, Header, HTTPException, Request
+
+from revenium_middleware.webhooks import verify_signature
+
+app = FastAPI()
+SIGNING_SECRETS = [os.environ["REVENIUM_WEBHOOK_SECRET"]]
+
+
+@app.post("/webhooks/revenium")
+async def receive(
+    request: Request,
+    x_revenium_signature_256: str = Header(...),
+    x_revenium_webhook_timestamp: str = Header(...),
+):
+    body = await request.body()
+    if not verify_signature(
+        payload=body,
+        signature_header=x_revenium_signature_256,
+        timestamp_header=x_revenium_webhook_timestamp,
+        secrets=SIGNING_SECRETS,
+    ):
+        raise HTTPException(status_code=401, detail="Invalid signature")
+
+    # ... process the event
+    return {"ok": True}
+```
+
+### Secret rotation
+
+When you rotate a signing secret in the Revenium dashboard with the default 24-hour overlap, both the old and new secrets are active simultaneously and every webhook is signed with both. Supply both values in `SIGNING_SECRETS` during the overlap window; remove the old one once it expires.
+
+### Webhooks without a signing secret
+
+Webhook deliveries without a configured signing secret arrive without HMAC headers. If your endpoint receives both signed and unsigned traffic, branch on header presence: treat missing headers as legacy unsigned mode and missing-signature-on-signed-only endpoints as an authentication failure.
+
+---
+
 ## Provider Usage Guides
 
 ### OpenAI
@@ -156,7 +248,7 @@ client = openai.OpenAI()
 
 # Basic chat completion
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "organizationName": "AcmeCorp",
@@ -168,7 +260,7 @@ response = client.chat.completions.create(
 
 # Streaming
 stream = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Tell me a story"}],
     stream=True
 )
@@ -459,7 +551,7 @@ litellm.api_base = os.getenv("LITELLM_PROXY_URL")
 litellm.api_key = os.getenv("LITELLM_API_KEY")
 
 response = litellm.completion(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "organizationName": "AcmeCorp",
@@ -617,7 +709,7 @@ handler = ReveniumCallbackHandler(
     agent_name="support_agent"
 )
 
-llm = ChatOpenAI(model="gpt-5.5", callbacks=[handler])
+llm = ChatOpenAI(model="gpt-4o-mini", callbacks=[handler])
 response = llm.invoke("Hello!")
 ```
 
@@ -656,7 +748,7 @@ result = agent.invoke(
 from revenium_middleware_langchain import AsyncReveniumCallbackHandler
 
 handler = AsyncReveniumCallbackHandler(trace_id="async-session")
-llm = ChatOpenAI(model="gpt-5.5", callbacks=[handler])
+llm = ChatOpenAI(model="gpt-4o-mini", callbacks=[handler])
 response = await llm.ainvoke("Hello!")
 ```
 
@@ -702,7 +794,7 @@ Add business context to any API call by passing a `usage_metadata` dictionary. A
 
 ```python
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "trace_id": "conv-28a7e9d4",
@@ -724,7 +816,7 @@ response = client.chat.completions.create(
 )
 ```
 
-**Deprecation notice:** The old field names `organizationId`, `organization_id`, `productId`, and `product_id` are still supported for backward compatibility but are deprecated. Use `organizationName` and `productName` for new implementations.
+**Deprecation notice:** The legacy field aliases `organizationId`, `organization_id`, `productId`, and `product_id` are accepted by this SDK only as an input-layer convenience and emit a `DeprecationWarning`. The Revenium backend no longer accepts them — they are translated to `organizationName` / `productName` before the wire call. Migrate to `organization_name` / `organizationName` and `product_name` / `productName` now; the input-layer aliases will be removed in the next major release.
 
 **API Reference:** [Complete metadata field documentation](https://revenium.readme.io/reference/meter_ai_completion)
 
@@ -765,7 +857,7 @@ REVENIUM_TRACE_TYPE=customer-support
 
 ```python
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Hello!"}],
     usage_metadata={
         "environment": "production",
@@ -789,7 +881,7 @@ workflow_id = str(uuid.uuid4())
 
 # Step 1: Parent operation
 parent_response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Analyze this document"}],
     usage_metadata={
         "trace_id": "analysis-session-456",
@@ -800,7 +892,7 @@ parent_response = client.chat.completions.create(
 
 # Step 2: Child operation linked to parent
 child_response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Summarize findings"}],
     usage_metadata={
         "trace_id": "analysis-session-456",
@@ -831,7 +923,7 @@ from revenium_middleware import revenium_metadata
 def handle_customer_query(question: str) -> str:
     # All API calls automatically include the decorator metadata
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": question}]
     )
     return response.choices[0].message.content
@@ -870,13 +962,13 @@ def outer_function():
 def mixed_metadata():
     # Uses decorator metadata
     response1 = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": "Hello"}]
     )
 
     # API-level metadata overrides decorator's task_type
     response2 = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": "Hello"}],
         usage_metadata={
             "task_type": "special-override",  # Overrides decorator
@@ -905,7 +997,7 @@ from revenium_middleware import revenium_meter, revenium_metadata
 def premium_feature(prompt: str) -> str:
     # This WILL be metered (decorated with @revenium_meter)
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": prompt}]
     )
     return response.choices[0].message.content
@@ -913,7 +1005,7 @@ def premium_feature(prompt: str) -> str:
 def free_feature(prompt: str) -> str:
     # This will NOT be metered (no @revenium_meter decorator)
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": prompt}]
     )
     return response.choices[0].message.content
@@ -999,7 +1091,7 @@ from openai import OpenAI
 
 client = OpenAI()
 response = client.chat.completions.create(
-    model="gpt-5.5",
+    model="gpt-4o-mini",
     messages=[
         {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": "What is the capital of France?"}
@@ -1021,62 +1113,6 @@ Prompt capture works with both streaming and non-streaming requests, and with mu
 
 ---
 
-## Terminal Summary Output
-
-Display a cost and usage summary in your terminal after each API request. Useful for development, debugging, and monitoring AI costs in real-time.
-
-### Configuration
-
-| Environment Variable | Values | Description |
-|---------------------|--------|-------------|
-| `REVENIUM_PRINT_SUMMARY` | `false` (default), `true` or `human`, `json` | Controls output format |
-| `REVENIUM_TEAM_ID` | Your team ID | Required to fetch and display cost information |
-
-```bash
-# Enable human-readable output
-export REVENIUM_PRINT_SUMMARY=human
-
-# Required for cost display (find in Revenium web app)
-export REVENIUM_TEAM_ID=your-team-id-here
-```
-
-### Human-Readable Format
-
-```
-============================================================
-REVENIUM USAGE SUMMARY
-============================================================
-Model: gpt-5.5
-Provider: OPENAI
-Duration: 1.23s
-
-Token Usage:
-  Input Tokens:  150
-  Output Tokens: 250
-  Total Tokens:  400
-
-Cost: $0.000045
-
-Trace ID: abc-123
-============================================================
-```
-
-### JSON Format
-
-```json
-{"model":"gpt-5.5","provider":"OPENAI","durationSeconds":1.23,"inputTokenCount":150,"outputTokenCount":250,"totalTokenCount":400,"cost":0.000045,"costStatus":"available","traceId":"abc-123"}
-```
-
-### Cost Status
-
-| Scenario | Display |
-|----------|---------|
-| Cost available | `$0.000045` |
-| `REVENIUM_TEAM_ID` set, cost pending | `Pending (aggregating... check Revenium dashboard)` |
-| `REVENIUM_TEAM_ID` not set | `Add REVENIUM_TEAM_ID to see pricing` |
-
----
-
 ## Cost Controls / Enforcement
 
 Block outbound provider requests client-side when a Revenium cost control trips. When the circuit breaker is enabled, the middleware polls compiled enforcement rules from the Revenium API in a background daemon thread and raises `BudgetExceededError` **before** the upstream call, preventing spend beyond the configured limit.
@@ -1155,7 +1191,7 @@ client = openai.OpenAI()
 
 try:
     response = client.chat.completions.create(
-        model="gpt-5.5",
+        model="gpt-4o-mini",
         messages=[{"role": "user", "content": "Summarize the meeting notes"}],
     )
 except BudgetExceededError as exc:
@@ -1194,9 +1230,8 @@ See [`examples/openai/openai_blocking_demo.py`](examples/openai/openai_blocking_
 | `REVENIUM_METERING_BASE_URL` | `https://api.revenium.ai` | Revenium API endpoint |
 | `REVENIUM_LOG_LEVEL` | `INFO` | Log level: `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` |
 | `REVENIUM_CAPTURE_PROMPTS` | `false` | Enable prompt capture |
-| `REVENIUM_PRINT_SUMMARY` | `false` | Terminal output: `false`, `true`/`human`, `json` |
 | `REVENIUM_SELECTIVE_METERING` | `false` | Only meter `@revenium_meter` decorated functions |
-| `REVENIUM_TEAM_ID` | - | Team ID for cost display in terminal summary |
+| `REVENIUM_TEAM_ID` | - | Team ID for cost lookups |
 | `REVENIUM_ENVIRONMENT` | - | Deployment environment (auto-detects from `ENVIRONMENT`, `DEPLOYMENT_ENV`) |
 | `REVENIUM_REGION` | - | Cloud region (auto-detects from `AWS_REGION`, `AZURE_REGION`, `GCP_REGION`) |
 | `REVENIUM_CREDENTIAL_ALIAS` | - | Human-readable API key name |

{revenium_python_sdk-0.1.5 → revenium_python_sdk-0.1.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "revenium-python-sdk"
-version = "0.1.5"
+version = "0.1.7"
 description = "The official Revenium Python SDK — unified AI metering middleware for OpenAI, Anthropic, Google, Ollama, LiteLLM, Perplexity, and fal.ai."
 readme = "README.md"
 requires-python = ">=3.8"