revenium-python-sdk 0.3.0__tar.gz → 0.5.0__tar.gz

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: revenium-python-sdk
-Version: 0.3.0
+Version: 0.5.0
 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
@@ -36,6 +36,9 @@ Provides-Extra: langchain
 Requires-Dist: langchain>=0.1.16; extra == "langchain"
 Requires-Dist: langchain-openai>=0.1.0; extra == "langchain"
 Requires-Dist: langchain-core>=0.1.0; extra == "langchain"
+Provides-Extra: griptape
+Requires-Dist: griptape<2.0.0,>=1.0.0; python_version >= "3.10" and extra == "griptape"
+Requires-Dist: requests>=2.25.0; extra == "griptape"
 Provides-Extra: perplexity
 Requires-Dist: wrapt>=1.14.0; extra == "perplexity"
 Requires-Dist: python-dotenv>=0.19.0; extra == "perplexity"
@@ -89,6 +92,7 @@ Requires-Dist: python-dotenv>=0.19.0; extra == "dev"
 Requires-Dist: anthropic>=0.30.0; extra == "dev"
 Requires-Dist: boto3; extra == "dev"
 Requires-Dist: ollama>=0.3.0; extra == "dev"
+Requires-Dist: griptape<2.0.0,>=1.0.0; python_version >= "3.10" and extra == "dev"
 Dynamic: license-file
 
 # Revenium Python SDK
@@ -132,6 +136,7 @@ The official Revenium Python SDK — unified AI metering middleware for deeply a
 | Perplexity (Native SDK) | `perplexity-native` | `pip install revenium-python-sdk[perplexity-native]` |
 | fal.ai | `fal` | `pip install revenium-python-sdk[fal]` |
 | LangChain | `langchain` | `pip install revenium-python-sdk[langchain]` |
+| Griptape | `griptape` | `pip install revenium-python-sdk[griptape]` |
 
 ## Feature Matrix
 
@@ -147,6 +152,7 @@ The official Revenium Python SDK — unified AI metering middleware for deeply a
 | Terminal Summary | Yes | Yes | Yes | Yes | Yes | - | - |
 | Azure / Bedrock | Azure | Bedrock | Vertex AI | - | All | - | - |
 | LangChain Integration | Yes | - | - | - | - | - | - |
+| Griptape Integration | Yes | Yes | - | Yes | Yes | - | - |
 | CrewAI Integration | - | - | - | - | Yes | - | - |
 | Proxy Mode | - | - | - | - | Yes | - | - |
 
@@ -212,6 +218,70 @@ print(response.choices[0].message.content)
 
 Emit per-agent terminal outcomes (`CONVERTED`, `DEFLECTED`, `ESCALATED`) alongside completion and tool-event records, so dashboards show business value next to AI cost.
 
+> **You need a write-scope key (`rev_sk_`) to use the agentic outcomes API.** Metering keys (`rev_mk_`) can only meter completions and tool events — they cannot report, amend, or read job outcomes, and the SDK rejects them client-side before any HTTP request is made. Key resolution: explicit `api_key=` > `REVENIUM_OUTCOME_API_KEY` > `REVENIUM_METERING_API_KEY`.
+
+### JobContext
+
+`JobContext` is the recommended high-level API: every AI call made inside the block is automatically metered against the job (all provider middlewares pick the job fields up from context), and the job's business outcome is reported when the work is done.
+
+```python
+from revenium_middleware import JobContext
+
+with JobContext("loan-app-12345", type="loan_processing", version="2.1") as job:
+    response = client.chat.completions.create(...)  # metered against the job automatically
+    job.report_outcome(
+        execution_status="SUCCESS",  # SUCCESS | FAILED | CANCELLED
+        outcome_type="CONVERTED",
+        outcome_value=500.0,
+        outcome_currency="USD",
+    )
+```
+
+- **Async:** `async with JobContext(...) as job:` works identically.
+- **Auto-FAILED:** if an unhandled exception escapes the block before an outcome was reported, the context automatically reports `execution_status="FAILED"` (error message and class in metadata) and always re-raises the original exception.
+- **Blocking:** outcome calls are synchronous HTTP requests with retries; tune how long they may block with the `retry_attempts`, `retry_initial_seconds`, and `retry_max_seconds` arguments, accepted by the `JobContext` constructor, `JobContext.attach()`, `get_outcome_history()`, and the CrewAI wrapper's `report_job_outcome`/`amend_job_outcome`.
+- **Team resolution:** explicit `team_id=` > `REVENIUM_TEAM_ID` > automatic resolution from the API key; `OutcomeReportingError` is raised if none of these yields a team.
+- **Nesting:** a nested `JobContext` is a different job (replace, not merge); exiting the inner context restores the outer job's fields.
+
+To tag AI calls with job fields without a context manager, use per-call `usage_metadata={"agentic_job_id": ...}`, the `@track_job` decorator (LiteLLM), or the process-wide `REVENIUM_AGENTIC_JOB_*` environment variables — see [Optional Environment Variables](#optional-environment-variables).
+
+### Amending an Outcome
+
+Outcomes are amendable: when the business result changes after the fact, amend the recorded outcome instead of re-reporting it. `JobContext.attach()` returns a lightweight handle to an existing job — it is not entered as a context manager and does not touch AI-call scoping — so amendments work from a different process than the one that ran the job.
+
+```python
+from revenium_middleware import JobContext, get_outcome_history
+
+# Two weeks after the agent converted the lead at $500,
+# the customer expands to the annual plan.
+job = JobContext.attach("sales-lead-8842")
+job.amend_outcome(
+    reason="Customer expanded to the annual plan after the initial conversion",
+    outcome_value=750.0,
+)
+job.close()
+
+history = get_outcome_history("sales-lead-8842")
+# List[JobOutcomeAmendment], ordered by amendment_sequence (1 = the initial report)
+```
+
+`amend_outcome()` takes a mandatory non-blank `reason` plus the same optional fields as `report_outcome()` (`execution_status`, `outcome_type`, `outcome_value`, `outcome_currency`, `metadata`, `reported_by`), and returns the updated job as a dict.
+
+### Outcome Exceptions
+
+All outcome exceptions are importable from `revenium_middleware` and share the `OutcomeReportingError` base, so `except OutcomeReportingError:` catches the whole family:
+
+| Exception | Raised when | What to do |
+|-----------|-------------|------------|
+| `OutcomeReportingError` | Base class — configuration failures (no API key available, unresolvable `team_id`) | Fix the key / team configuration |
+| `OutcomeAlreadyReportedError` | Re-reporting a job that already has an outcome (backend 409) | Amend with `amend_outcome()` instead; the exception carries `reported_at` and `amendment_count` |
+| `OutcomeNotReportedError` | Amending a job that has no outcome yet (backend 422) | Call `report_outcome()` first |
+| `OutcomeAmendConflictError` | A concurrent amendment changed the outcome (backend 409, optimistic lock) | Refetch with `get_outcome_history()` and retry — the SDK does not auto-retry |
+
+### Low-Level Client
+
+For manual control over every metric (one `emit_completion` per LLM call, one `emit_tool_event` per tool/step), use `AgenticOutcomeClient` directly:
+
 ```python
 from revenium_middleware.agentic_outcomes import AgenticOutcomeClient, AgenticOutcomeSettings
 
@@ -678,8 +748,9 @@ LiteLLM provides additional tracking decorators beyond the standard `@revenium_m
 | `@track_product()` | Track product-specific usage |
 | `@track_subscriber()` | Identify end users |
 | `@track_quality()` | Track response quality scores |
+| `@track_job()` | Inject agentic job fields for cost/ROI correlation, e.g. `@track_job(job_id="loan-app-12345", type="loan_processing")` |
 
-All decorators support static values, extraction from function arguments (`name_from_arg`), or extraction from object attributes (`name_from_attr`).
+The tracking decorators above support static values, extraction from function arguments (`name_from_arg`), or extraction from object attributes (`name_from_attr`); `@track_job` supports static values and argument extraction (`job_id_from_arg`, `type_from_arg`) but has no attribute variant.
 
 #### CrewAI Integration
 
@@ -689,6 +760,35 @@ pip install "revenium-python-sdk[litellm]" crewai
 
 Pre-built wrapper for tracking CrewAI agent executions. **Note:** CrewAI requires Python 3.12 or earlier.
 
+**Job outcome tracking:** pass the `agentic_job_*` kwargs to tie every LLM call in the crew to one agentic job, then report (or later amend) the job's business outcome. Requires a write-scope key (`rev_sk_`) — see [Agentic Outcomes](#agentic-outcomes-outcome-based-metering).
+
+```python
+from revenium_middleware.litellm.client.integrations.crewai import ReveniumCrewWrapper
+
+crew = ReveniumCrewWrapper(
+    agents=[support_agent],
+    tasks=[triage_task],
+    organization_id="AcmeCorp",
+    subscription_id="82764738",
+    product_id="Platinum",
+    agentic_job_id="support-ticket-456",
+    agentic_job_name="Support Ticket Triage",
+    agentic_job_type="customer_support",
+    agentic_job_version="2.0",
+)
+result = crew.kickoff()
+
+crew.report_job_outcome(
+    execution_status="SUCCESS",
+    outcome_type="DEFLECTED",
+    outcome_value=25.0,
+)
+
+# Later, if the business result changes:
+# crew.amend_job_outcome(reason="Ticket reopened and escalated to a human agent",
+#                        outcome_type="ESCALATED", outcome_value=0.0)
+```
+
 **LiteLLM environment variables:**
 - `LITELLM_PROXY_URL` - Your LiteLLM proxy URL
 - `LITELLM_API_KEY` - Your LiteLLM proxy API key
@@ -865,6 +965,49 @@ Credentials come from the standard environment variables (`REVENIUM_METERING_API
 
 ---
 
+### Griptape
+
+Metered prompt and embedding drivers for [Griptape](https://github.com/griptape-ai/griptape) applications. Requires Python 3.10+.
+
+```bash
+pip install "revenium-python-sdk[griptape,openai]"     # OpenAI
+pip install "revenium-python-sdk[griptape,anthropic]"  # Anthropic
+pip install "revenium-python-sdk[griptape,ollama]"     # Ollama
+pip install "revenium-python-sdk[griptape,litellm,litellm-proxy]"  # 100+ providers via LiteLLM
+```
+
+`ReveniumDriver` auto-detects the provider from the model name (`gpt-*` → OpenAI, `claude-*` → Anthropic, `llama`/`mistral`/... → Ollama, anything else → LiteLLM) and wraps the matching Griptape prompt driver with Revenium metering:
+
+```python
+import os
+from griptape.structures import Agent
+from revenium_middleware.griptape import ReveniumDriver
+
+os.environ["REVENIUM_METERING_API_KEY"] = "your_revenium_key"
+
+agent = Agent(prompt_driver=ReveniumDriver(
+    model="gpt-4o-mini",
+    usage_metadata={"task_type": "demo"},
+))
+agent.run("Hello!")
+```
+
+Force a provider with `force_provider="litellm"`, or wrap an existing driver with `ReveniumDriver(base_driver=...)`.
+
+**Embeddings:**
+
+```python
+from revenium_middleware.griptape import ReveniumEmbeddingDriver
+
+driver = ReveniumEmbeddingDriver(model="text-embedding-3-large")
+```
+
+**Provider-specific drivers:** for direct control, use `ReveniumOpenAiDriver`, `ReveniumAnthropicDriver`, `ReveniumOllamaDriver`, `ReveniumLiteLLMDriver` or `ReveniumOpenAiEmbeddingDriver` — each subclasses the corresponding Griptape driver and accepts a `usage_metadata` dict (see [Metadata Fields](#metadata-fields)).
+
+**Migrating from `revenium-griptape`:** the standalone package is deprecated — install the `griptape` extra and change `from revenium_griptape import ReveniumDriver` to `from revenium_middleware.griptape import ReveniumDriver`. All driver class names are unchanged. One behaviour difference: the old package called `load_dotenv()` automatically at import time; the SDK never mutates your environment on import, so if you keep credentials in a `.env` file, call `load_dotenv()` yourself before creating a driver.
+
+---
+
 ## Metadata Fields
 
 Add business context to any API call by passing a `usage_metadata` dictionary. All fields are optional.
@@ -931,6 +1074,7 @@ Enhanced observability fields for tracking AI operations across environments, re
 | `parent_transaction_id` | `REVENIUM_PARENT_TRANSACTION_ID` | Parent transaction ID | Link child operations to parents across microservices |
 | `transaction_name` | `REVENIUM_TRANSACTION_NAME` | Human-friendly operation name | Label operations (e.g., `"Generate Response"`, `"Analyze Sentiment"`) |
 | `retry_number` | `REVENIUM_RETRY_NUMBER` | Retry attempt number (0 = first attempt) | Track retry attempts for failed operations |
+| `ticket_id` | `REVENIUM_TICKET_ID` | External ticket or issue ID (e.g., Jira, Linear) (max 256 chars) | Attribute AI costs to individual tickets or issues |
 
 **Note:** `operation_type` (e.g., `CHAT`, `EMBED`, `TOOL_CALL`) and `operation_subtype` (e.g., `function_call`, `streaming`) are automatically detected by the middleware and cannot be overridden.
 
@@ -958,7 +1102,8 @@ response = client.chat.completions.create(
         "trace_type": "customer-support",
         "trace_name": "Support Chat Session",
         "transaction_name": "Generate Response",
-        "parent_transaction_id": "parent-txn-123"
+        "parent_transaction_id": "parent-txn-123",
+        "ticket_id": "JIRA-123"
     }
 )
 ```
@@ -1362,7 +1507,7 @@ print(get_buffer_stats())
 | `REVENIUM_LOG_LEVEL` | `INFO` | Log level: `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` |
 | `REVENIUM_CAPTURE_PROMPTS` | `false` | Enable prompt capture |
 | `REVENIUM_SELECTIVE_METERING` | `false` | Only meter `@revenium_meter` decorated functions |
-| `REVENIUM_TEAM_ID` | - | Team ID for cost lookups |
+| `REVENIUM_TEAM_ID` | - | Team ID for cost lookups and outcome reporting (JobContext team resolution) |
 | `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 |
@@ -1371,10 +1516,18 @@ print(get_buffer_stats())
 | `REVENIUM_PARENT_TRANSACTION_ID` | - | Parent transaction ID for distributed tracing |
 | `REVENIUM_TRANSACTION_NAME` | - | Human-friendly operation name |
 | `REVENIUM_RETRY_NUMBER` | - | Retry attempt number |
+| `REVENIUM_AGENTIC_JOB_ID` | - | Agentic job instance ID attached to all completions in the process (triggers backend job auto-creation) |
+| `REVENIUM_AGENTIC_JOB_NAME` | - | Human-readable agentic job name |
+| `REVENIUM_AGENTIC_JOB_TYPE` | - | Agentic job type category |
+| `REVENIUM_AGENTIC_JOB_VERSION` | - | Agentic job version |
+| `REVENIUM_OUTCOME_API_KEY` | - | Write-scope key (`rev_sk_`) for the agentic outcomes API (report/amend/history); falls back to `REVENIUM_METERING_API_KEY` |
+| `REVENIUM_PROFITSTREAM_BASE_URL` | `https://api.revenium.io` | Agentic outcomes API base URL |
 | `REVENIUM_BEDROCK_DISABLE` | - | Set to `1` to disable Bedrock auto-detection |
 | `REVENIUM_BUFFER_MAX_SIZE` | `1000` | Store-and-forward buffer capacity (oldest events evicted when full) |
 | `REVENIUM_BUFFER_FLUSH_INTERVAL` | `30` | Seconds between automatic replay attempts for buffered events |
 
+Per-call `usage_metadata` values take precedence over the `REVENIUM_AGENTIC_JOB_*` environment variables, and the LiteLLM proxy path sources job fields from `x-revenium-*` headers only — these process-level env fallbacks do not apply to proxied traffic.
+
 ### Provider-Specific Environment Variables
 
 | Variable | Provider | Description |

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/README.md

@@ -39,6 +39,7 @@ The official Revenium Python SDK — unified AI metering middleware for deeply a
 | Perplexity (Native SDK) | `perplexity-native` | `pip install revenium-python-sdk[perplexity-native]` |
 | fal.ai | `fal` | `pip install revenium-python-sdk[fal]` |
 | LangChain | `langchain` | `pip install revenium-python-sdk[langchain]` |
+| Griptape | `griptape` | `pip install revenium-python-sdk[griptape]` |
 
 ## Feature Matrix
 
@@ -54,6 +55,7 @@ The official Revenium Python SDK — unified AI metering middleware for deeply a
 | Terminal Summary | Yes | Yes | Yes | Yes | Yes | - | - |
 | Azure / Bedrock | Azure | Bedrock | Vertex AI | - | All | - | - |
 | LangChain Integration | Yes | - | - | - | - | - | - |
+| Griptape Integration | Yes | Yes | - | Yes | Yes | - | - |
 | CrewAI Integration | - | - | - | - | Yes | - | - |
 | Proxy Mode | - | - | - | - | Yes | - | - |
 
@@ -119,6 +121,70 @@ print(response.choices[0].message.content)
 
 Emit per-agent terminal outcomes (`CONVERTED`, `DEFLECTED`, `ESCALATED`) alongside completion and tool-event records, so dashboards show business value next to AI cost.
 
+> **You need a write-scope key (`rev_sk_`) to use the agentic outcomes API.** Metering keys (`rev_mk_`) can only meter completions and tool events — they cannot report, amend, or read job outcomes, and the SDK rejects them client-side before any HTTP request is made. Key resolution: explicit `api_key=` > `REVENIUM_OUTCOME_API_KEY` > `REVENIUM_METERING_API_KEY`.
+
+### JobContext
+
+`JobContext` is the recommended high-level API: every AI call made inside the block is automatically metered against the job (all provider middlewares pick the job fields up from context), and the job's business outcome is reported when the work is done.
+
+```python
+from revenium_middleware import JobContext
+
+with JobContext("loan-app-12345", type="loan_processing", version="2.1") as job:
+    response = client.chat.completions.create(...)  # metered against the job automatically
+    job.report_outcome(
+        execution_status="SUCCESS",  # SUCCESS | FAILED | CANCELLED
+        outcome_type="CONVERTED",
+        outcome_value=500.0,
+        outcome_currency="USD",
+    )
+```
+
+- **Async:** `async with JobContext(...) as job:` works identically.
+- **Auto-FAILED:** if an unhandled exception escapes the block before an outcome was reported, the context automatically reports `execution_status="FAILED"` (error message and class in metadata) and always re-raises the original exception.
+- **Blocking:** outcome calls are synchronous HTTP requests with retries; tune how long they may block with the `retry_attempts`, `retry_initial_seconds`, and `retry_max_seconds` arguments, accepted by the `JobContext` constructor, `JobContext.attach()`, `get_outcome_history()`, and the CrewAI wrapper's `report_job_outcome`/`amend_job_outcome`.
+- **Team resolution:** explicit `team_id=` > `REVENIUM_TEAM_ID` > automatic resolution from the API key; `OutcomeReportingError` is raised if none of these yields a team.
+- **Nesting:** a nested `JobContext` is a different job (replace, not merge); exiting the inner context restores the outer job's fields.
+
+To tag AI calls with job fields without a context manager, use per-call `usage_metadata={"agentic_job_id": ...}`, the `@track_job` decorator (LiteLLM), or the process-wide `REVENIUM_AGENTIC_JOB_*` environment variables — see [Optional Environment Variables](#optional-environment-variables).
+
+### Amending an Outcome
+
+Outcomes are amendable: when the business result changes after the fact, amend the recorded outcome instead of re-reporting it. `JobContext.attach()` returns a lightweight handle to an existing job — it is not entered as a context manager and does not touch AI-call scoping — so amendments work from a different process than the one that ran the job.
+
+```python
+from revenium_middleware import JobContext, get_outcome_history
+
+# Two weeks after the agent converted the lead at $500,
+# the customer expands to the annual plan.
+job = JobContext.attach("sales-lead-8842")
+job.amend_outcome(
+    reason="Customer expanded to the annual plan after the initial conversion",
+    outcome_value=750.0,
+)
+job.close()
+
+history = get_outcome_history("sales-lead-8842")
+# List[JobOutcomeAmendment], ordered by amendment_sequence (1 = the initial report)
+```
+
+`amend_outcome()` takes a mandatory non-blank `reason` plus the same optional fields as `report_outcome()` (`execution_status`, `outcome_type`, `outcome_value`, `outcome_currency`, `metadata`, `reported_by`), and returns the updated job as a dict.
+
+### Outcome Exceptions
+
+All outcome exceptions are importable from `revenium_middleware` and share the `OutcomeReportingError` base, so `except OutcomeReportingError:` catches the whole family:
+
+| Exception | Raised when | What to do |
+|-----------|-------------|------------|
+| `OutcomeReportingError` | Base class — configuration failures (no API key available, unresolvable `team_id`) | Fix the key / team configuration |
+| `OutcomeAlreadyReportedError` | Re-reporting a job that already has an outcome (backend 409) | Amend with `amend_outcome()` instead; the exception carries `reported_at` and `amendment_count` |
+| `OutcomeNotReportedError` | Amending a job that has no outcome yet (backend 422) | Call `report_outcome()` first |
+| `OutcomeAmendConflictError` | A concurrent amendment changed the outcome (backend 409, optimistic lock) | Refetch with `get_outcome_history()` and retry — the SDK does not auto-retry |
+
+### Low-Level Client
+
+For manual control over every metric (one `emit_completion` per LLM call, one `emit_tool_event` per tool/step), use `AgenticOutcomeClient` directly:
+
 ```python
 from revenium_middleware.agentic_outcomes import AgenticOutcomeClient, AgenticOutcomeSettings
 
@@ -585,8 +651,9 @@ LiteLLM provides additional tracking decorators beyond the standard `@revenium_m
 | `@track_product()` | Track product-specific usage |
 | `@track_subscriber()` | Identify end users |
 | `@track_quality()` | Track response quality scores |
+| `@track_job()` | Inject agentic job fields for cost/ROI correlation, e.g. `@track_job(job_id="loan-app-12345", type="loan_processing")` |
 
-All decorators support static values, extraction from function arguments (`name_from_arg`), or extraction from object attributes (`name_from_attr`).
+The tracking decorators above support static values, extraction from function arguments (`name_from_arg`), or extraction from object attributes (`name_from_attr`); `@track_job` supports static values and argument extraction (`job_id_from_arg`, `type_from_arg`) but has no attribute variant.
 
 #### CrewAI Integration
 
@@ -596,6 +663,35 @@ pip install "revenium-python-sdk[litellm]" crewai
 
 Pre-built wrapper for tracking CrewAI agent executions. **Note:** CrewAI requires Python 3.12 or earlier.
 
+**Job outcome tracking:** pass the `agentic_job_*` kwargs to tie every LLM call in the crew to one agentic job, then report (or later amend) the job's business outcome. Requires a write-scope key (`rev_sk_`) — see [Agentic Outcomes](#agentic-outcomes-outcome-based-metering).
+
+```python
+from revenium_middleware.litellm.client.integrations.crewai import ReveniumCrewWrapper
+
+crew = ReveniumCrewWrapper(
+    agents=[support_agent],
+    tasks=[triage_task],
+    organization_id="AcmeCorp",
+    subscription_id="82764738",
+    product_id="Platinum",
+    agentic_job_id="support-ticket-456",
+    agentic_job_name="Support Ticket Triage",
+    agentic_job_type="customer_support",
+    agentic_job_version="2.0",
+)
+result = crew.kickoff()
+
+crew.report_job_outcome(
+    execution_status="SUCCESS",
+    outcome_type="DEFLECTED",
+    outcome_value=25.0,
+)
+
+# Later, if the business result changes:
+# crew.amend_job_outcome(reason="Ticket reopened and escalated to a human agent",
+#                        outcome_type="ESCALATED", outcome_value=0.0)
+```
+
 **LiteLLM environment variables:**
 - `LITELLM_PROXY_URL` - Your LiteLLM proxy URL
 - `LITELLM_API_KEY` - Your LiteLLM proxy API key
@@ -772,6 +868,49 @@ Credentials come from the standard environment variables (`REVENIUM_METERING_API
 
 ---
 
+### Griptape
+
+Metered prompt and embedding drivers for [Griptape](https://github.com/griptape-ai/griptape) applications. Requires Python 3.10+.
+
+```bash
+pip install "revenium-python-sdk[griptape,openai]"     # OpenAI
+pip install "revenium-python-sdk[griptape,anthropic]"  # Anthropic
+pip install "revenium-python-sdk[griptape,ollama]"     # Ollama
+pip install "revenium-python-sdk[griptape,litellm,litellm-proxy]"  # 100+ providers via LiteLLM
+```
+
+`ReveniumDriver` auto-detects the provider from the model name (`gpt-*` → OpenAI, `claude-*` → Anthropic, `llama`/`mistral`/... → Ollama, anything else → LiteLLM) and wraps the matching Griptape prompt driver with Revenium metering:
+
+```python
+import os
+from griptape.structures import Agent
+from revenium_middleware.griptape import ReveniumDriver
+
+os.environ["REVENIUM_METERING_API_KEY"] = "your_revenium_key"
+
+agent = Agent(prompt_driver=ReveniumDriver(
+    model="gpt-4o-mini",
+    usage_metadata={"task_type": "demo"},
+))
+agent.run("Hello!")
+```
+
+Force a provider with `force_provider="litellm"`, or wrap an existing driver with `ReveniumDriver(base_driver=...)`.
+
+**Embeddings:**
+
+```python
+from revenium_middleware.griptape import ReveniumEmbeddingDriver
+
+driver = ReveniumEmbeddingDriver(model="text-embedding-3-large")
+```
+
+**Provider-specific drivers:** for direct control, use `ReveniumOpenAiDriver`, `ReveniumAnthropicDriver`, `ReveniumOllamaDriver`, `ReveniumLiteLLMDriver` or `ReveniumOpenAiEmbeddingDriver` — each subclasses the corresponding Griptape driver and accepts a `usage_metadata` dict (see [Metadata Fields](#metadata-fields)).
+
+**Migrating from `revenium-griptape`:** the standalone package is deprecated — install the `griptape` extra and change `from revenium_griptape import ReveniumDriver` to `from revenium_middleware.griptape import ReveniumDriver`. All driver class names are unchanged. One behaviour difference: the old package called `load_dotenv()` automatically at import time; the SDK never mutates your environment on import, so if you keep credentials in a `.env` file, call `load_dotenv()` yourself before creating a driver.
+
+---
+
 ## Metadata Fields
 
 Add business context to any API call by passing a `usage_metadata` dictionary. All fields are optional.
@@ -838,6 +977,7 @@ Enhanced observability fields for tracking AI operations across environments, re
 | `parent_transaction_id` | `REVENIUM_PARENT_TRANSACTION_ID` | Parent transaction ID | Link child operations to parents across microservices |
 | `transaction_name` | `REVENIUM_TRANSACTION_NAME` | Human-friendly operation name | Label operations (e.g., `"Generate Response"`, `"Analyze Sentiment"`) |
 | `retry_number` | `REVENIUM_RETRY_NUMBER` | Retry attempt number (0 = first attempt) | Track retry attempts for failed operations |
+| `ticket_id` | `REVENIUM_TICKET_ID` | External ticket or issue ID (e.g., Jira, Linear) (max 256 chars) | Attribute AI costs to individual tickets or issues |
 
 **Note:** `operation_type` (e.g., `CHAT`, `EMBED`, `TOOL_CALL`) and `operation_subtype` (e.g., `function_call`, `streaming`) are automatically detected by the middleware and cannot be overridden.
 
@@ -865,7 +1005,8 @@ response = client.chat.completions.create(
         "trace_type": "customer-support",
         "trace_name": "Support Chat Session",
         "transaction_name": "Generate Response",
-        "parent_transaction_id": "parent-txn-123"
+        "parent_transaction_id": "parent-txn-123",
+        "ticket_id": "JIRA-123"
     }
 )
 ```
@@ -1269,7 +1410,7 @@ print(get_buffer_stats())
 | `REVENIUM_LOG_LEVEL` | `INFO` | Log level: `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` |
 | `REVENIUM_CAPTURE_PROMPTS` | `false` | Enable prompt capture |
 | `REVENIUM_SELECTIVE_METERING` | `false` | Only meter `@revenium_meter` decorated functions |
-| `REVENIUM_TEAM_ID` | - | Team ID for cost lookups |
+| `REVENIUM_TEAM_ID` | - | Team ID for cost lookups and outcome reporting (JobContext team resolution) |
 | `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 |
@@ -1278,10 +1419,18 @@ print(get_buffer_stats())
 | `REVENIUM_PARENT_TRANSACTION_ID` | - | Parent transaction ID for distributed tracing |
 | `REVENIUM_TRANSACTION_NAME` | - | Human-friendly operation name |
 | `REVENIUM_RETRY_NUMBER` | - | Retry attempt number |
+| `REVENIUM_AGENTIC_JOB_ID` | - | Agentic job instance ID attached to all completions in the process (triggers backend job auto-creation) |
+| `REVENIUM_AGENTIC_JOB_NAME` | - | Human-readable agentic job name |
+| `REVENIUM_AGENTIC_JOB_TYPE` | - | Agentic job type category |
+| `REVENIUM_AGENTIC_JOB_VERSION` | - | Agentic job version |
+| `REVENIUM_OUTCOME_API_KEY` | - | Write-scope key (`rev_sk_`) for the agentic outcomes API (report/amend/history); falls back to `REVENIUM_METERING_API_KEY` |
+| `REVENIUM_PROFITSTREAM_BASE_URL` | `https://api.revenium.io` | Agentic outcomes API base URL |
 | `REVENIUM_BEDROCK_DISABLE` | - | Set to `1` to disable Bedrock auto-detection |
 | `REVENIUM_BUFFER_MAX_SIZE` | `1000` | Store-and-forward buffer capacity (oldest events evicted when full) |
 | `REVENIUM_BUFFER_FLUSH_INTERVAL` | `30` | Seconds between automatic replay attempts for buffered events |
 
+Per-call `usage_metadata` values take precedence over the `REVENIUM_AGENTIC_JOB_*` environment variables, and the LiteLLM proxy path sources job fields from `x-revenium-*` headers only — these process-level env fallbacks do not apply to proxied traffic.
+
 ### Provider-Specific Environment Variables
 
 | Variable | Provider | Description |

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "revenium-python-sdk"
-version = "0.3.0"
+version = "0.5.0"
 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"
@@ -51,6 +51,10 @@ langchain = [
     "langchain-openai>=0.1.0",
     "langchain-core>=0.1.0",
 ]
+griptape = [
+    "griptape>=1.0.0,<2.0.0; python_version >= '3.10'",
+    "requests>=2.25.0",
+]
 perplexity = [
     "wrapt>=1.14.0",
     "python-dotenv>=0.19.0",
@@ -116,6 +120,7 @@ dev = [
     "anthropic>=0.30.0",
     "boto3",
     "ollama>=0.3.0",
+    "griptape>=1.0.0,<2.0.0; python_version >= '3.10'",
 ]
 
 [tool.pytest.ini_options]

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/revenium_middleware/__init__.py

@@ -166,6 +166,16 @@ from ._metering import meter_tool, report_tool_call, configure  # noqa: E402
 # Agentic-outcome client (used by examples/agentic_outcomes/ pack)
 from .agentic_outcomes import AgenticOutcomeClient, AgenticOutcomeSettings  # noqa: E402
 
+# Public job-context surface (BACK-777)
+from .job_context import JobContext  # noqa: E402
+from .job_history import JobOutcomeAmendment, get_outcome_history  # noqa: E402
+from ._core.exceptions import (  # noqa: E402
+    OutcomeAlreadyReportedError,
+    OutcomeAmendConflictError,
+    OutcomeNotReportedError,
+    OutcomeReportingError,
+)
+
 __all__ = [
     # Metering exports
     "client",
@@ -199,4 +209,13 @@ __all__ = [
     # Agentic-outcome exports
     "AgenticOutcomeClient",
     "AgenticOutcomeSettings",
+    # Job-context exports (BACK-777)
+    "JobContext",
+    "OutcomeReportingError",
+    "OutcomeAlreadyReportedError",
+    # Outcome amendment / history exports (BACK-777 Phase 3)
+    "get_outcome_history",
+    "JobOutcomeAmendment",
+    "OutcomeNotReportedError",
+    "OutcomeAmendConflictError",
 ]

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/revenium_middleware/_core/config.py

@@ -56,6 +56,15 @@ class Config:
     ENV_REVENIUM_PARENT_TRANSACTION_ID: str = "REVENIUM_PARENT_TRANSACTION_ID"
     ENV_REVENIUM_TRANSACTION_NAME: str = "REVENIUM_TRANSACTION_NAME"
     ENV_REVENIUM_RETRY_NUMBER: str = "REVENIUM_RETRY_NUMBER"
+    ENV_REVENIUM_TICKET_ID: str = "REVENIUM_TICKET_ID"
+
+    # Agentic job field environment variables (BACK-777 fallbacks)
+    ENV_REVENIUM_AGENTIC_JOB_ID: str = "REVENIUM_AGENTIC_JOB_ID"
+    ENV_REVENIUM_AGENTIC_JOB_NAME: str = "REVENIUM_AGENTIC_JOB_NAME"
+    ENV_REVENIUM_AGENTIC_JOB_TYPE: str = "REVENIUM_AGENTIC_JOB_TYPE"
+    ENV_REVENIUM_AGENTIC_JOB_VERSION: str = "REVENIUM_AGENTIC_JOB_VERSION"
+    ENV_REVENIUM_OUTCOME_API_KEY: str = "REVENIUM_OUTCOME_API_KEY"
+    ENV_REVENIUM_PROFITSTREAM_BASE_URL: str = "REVENIUM_PROFITSTREAM_BASE_URL"
 
     # Prompt capture settings
     ENV_REVENIUM_CAPTURE_PROMPTS: str = "REVENIUM_CAPTURE_PROMPTS"

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/revenium_middleware/_core/context.py

@@ -30,6 +30,12 @@ _idempotency_key_context: contextvars.ContextVar[Optional[str]] = contextvars.Co
     'revenium_idempotency_key', default=None
 )
 
+# Context variable holding agentic job fields (wire-name keys) for the current scope.
+# This is the seam the public JobContext (BACK-777 Phase 2) builds on.
+_agentic_job_context: contextvars.ContextVar[Optional[Dict[str, Any]]] = contextvars.ContextVar(
+    'revenium_agentic_job', default=None
+)
+
 
 def is_inside_decorated_function() -> bool:
     """
@@ -172,3 +178,41 @@ def idempotency_key(key: str) -> Iterator[None]:
     finally:
         _idempotency_key_context.reset(token)
 
+
+def get_agentic_job_fields() -> Optional[Dict[str, Any]]:
+    """Return the agentic job fields set on the current context, or None.
+
+    Keys are wire names (``agenticJobId``, ``agenticJobName``, ``agenticJobType``,
+    ``agenticJobVersion``) — the same keys ``extract_agentic_job_fields`` emits,
+    so the fallback merge in ``_core/fields.py`` is key-aligned.
+    """
+    return _agentic_job_context.get()
+
+
+def set_agentic_job_fields(
+    job_id: Optional[str] = None,
+    name: Optional[str] = None,
+    type: Optional[str] = None,
+    version: Optional[str] = None,
+) -> contextvars.Token:
+    """Set agentic job fields on the current context. Returns a Token for reset().
+
+    Maps snake-case arguments to wire-name keys, omitting Nones. Callers own the
+    token and must reset it (``_agentic_job_context.reset(token)``) when the scope
+    ends — the JobContext context manager in Phase 2 does this on exit.
+
+    Raises:
+        ValueError: if no field is provided.
+    """
+    fields: Dict[str, Any] = {}
+    if job_id is not None:
+        fields["agenticJobId"] = job_id
+    if name is not None:
+        fields["agenticJobName"] = name
+    if type is not None:
+        fields["agenticJobType"] = type
+    if version is not None:
+        fields["agenticJobVersion"] = version
+    if not fields:
+        raise ValueError("set_agentic_job_fields requires at least one field")
+    return _agentic_job_context.set(fields)

{revenium_python_sdk-0.3.0 → revenium_python_sdk-0.5.0}/revenium_middleware/_core/exceptions.py

@@ -41,3 +41,45 @@ class BudgetExceededError(Exception):
 # `except ReveniumCostLimitExceeded:` continues to catch the new exception
 # unchanged. Plan to remove in a future major release.
 ReveniumCostLimitExceeded = BudgetExceededError
+
+
+class OutcomeReportingError(Exception):
+    """Raised when an agentic job outcome cannot be reported.
+
+    Base of the outcome exception family (BACK-777). Configuration failures
+    (unresolvable team_id, missing API key) raise this class directly;
+    backend-state conditions raise the subclasses.
+    """
+
+
+class OutcomeAlreadyReportedError(OutcomeReportingError):
+    """The job already has an outcome (backend 409 with amendment guidance).
+
+    Callers can inspect ``reported_at`` / ``amendment_count`` and decide to
+    amend (``amend_outcome``, BACK-777 Phase 3).
+    """
+
+    def __init__(
+        self,
+        message: str,
+        reported_at: Optional[str] = None,
+        amendment_count: Optional[int] = None,
+    ):
+        super().__init__(message)
+        self.reported_at = reported_at
+        self.amendment_count = amendment_count
+
+
+class OutcomeNotReportedError(OutcomeReportingError):
+    """Amendment attempted on a job with no outcome yet (backend 422).
+
+    Report the initial outcome with ``report_outcome`` first.
+    """
+
+
+class OutcomeAmendConflictError(OutcomeReportingError):
+    """Concurrent amendment changed the outcome row (backend 409, optimistic lock).
+
+    Retryable by the caller: refetch the current state (``get_outcome_history``)
+    and re-issue the amendment. The SDK does not auto-retry.
+    """