revenium-python-sdk 0.6.0__tar.gz → 0.8.0__tar.gz

{revenium_python_sdk-0.6.0 → revenium_python_sdk-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: revenium-python-sdk
-Version: 0.6.0
+Version: 0.8.0
 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
@@ -264,7 +264,63 @@ when the provider's SDK is installed.
 
 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`.
+> **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_WRITE_API_KEY` > `REVENIUM_OUTCOME_API_KEY` (deprecated fallback) > `REVENIUM_METERING_API_KEY`.
+
+### Job-Type Economics and Outcome Facts
+
+Keep a metering key for AI telemetry and a separate write key for outcomes and
+job-type configuration. A registered `valuePerUnit` rule takes precedence over
+an outcome's `outcome_value`; the backend never sums the two value sources.
+
+```python
+from revenium_middleware import (
+    Baseline, JobTypeEconomics, PeriodFactEntry, create_baseline,
+    report_period_facts, upsert_job_type_economics,
+)
+
+upsert_job_type_economics("claim", JobTypeEconomics(
+    unit_metric_key="completed_claims", unit_label="claim",
+    metrics=[{
+        "key": "completed_claims", "type": "COUNT",
+        "direction": "HIGHER_IS_BETTER", "aggregation": "SUM",
+        "resolution": "PER_JOB",
+    }],
+    dimensions=[{"key": "region", "allowedValues": ["us", "ca"]}],
+    monetization={
+        "metricKey": "completed_claims", "valuePerUnit": 4.25,
+        "currency": "USD", "category": "COST_AVOIDED", "basis": "REALIZED",
+    },
+))
+create_baseline("claim", Baseline(
+    effective_from="2026-08-01T00:00:00Z", cost_per_unit=4.25, currency="USD",
+))
+report_period_facts("claim", [PeriodFactEntry(
+    period_start="2026-08-01T00:00:00Z", period_end="2026-09-01T00:00:00Z",
+    dimension_key="region", dimension_value="us",
+    key="completed_claims", value=1280,
+)])
+```
+
+`effective_from` is the only required field on a baseline; every other field
+is optional, and a baseline without it is rejected. A job type must be
+declared with `upsert_job_type_economics` before it accepts baselines or
+facts, and `report_period_facts` accepts only metrics declared with
+`"resolution": "PERIOD"`.
+
+Job economics currency values must be USD. Baselines and period facts use
+server-supplied attribution when their provenance,
+reporter, and source fields are omitted. Set those fields only when you need an
+explicit override. Economics metric directions are
+`HIGHER_IS_BETTER` or `LOWER_IS_BETTER`; monetization categories are
+`REVENUE`, `COST_AVOIDED`, `TIME_SAVED`, and `LEADING_VALUE`, with a
+`REALIZED` or `EXPECTED` basis.
+
+Use `CUSTOMER_DECLARED` or `MEASURED` for a baseline override. Use `MEASURED`,
+`SELF_REPORTED`, or `DERIVED` for a period fact override.
+
+Facts are append-only and keyed on the period, dimension and metric key
+together. Re-appending that tuple supersedes the active fact, and the server
+requires `reason=` on the entry when it does.
 
 ### JobContext
 
@@ -311,7 +367,70 @@ 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.
+`amend_outcome()` takes `reason` — the amendment's audit justification, still the first positional argument — plus the same optional fields as `report_outcome()` (`execution_status`, `outcome_type`, `outcome_value`, `outcome_currency`, `metadata`, `reported_by`, `outcome_reason`, `metrics`), and returns the updated job as a dict.
+
+- **Detecting a lost update:** `report_outcome()` and `amend_outcome()` record the job's `entityVersion` from the response on the handle (readable as `job.entity_version`). The next `amend_outcome()` on that same handle sends it as `expectedEntityVersion`, so an amendment that would overwrite a change made by another writer in the meantime raises `OutcomeAmendConflictError` instead of silently winning. Pass `expected_entity_version=` to lock against a version you fetched yourself; use a fresh `JobContext.attach()` handle — which has recorded nothing — for the old last-write-wins behavior.
+
+```python
+from revenium_middleware import OutcomeAmendConflictError, get_outcome_history
+
+try:
+    job.amend_outcome(reason="Chargeback", outcome_value=0.0)
+except OutcomeAmendConflictError as conflict:
+    # The conflict reports the version the platform actually holds.
+    print(conflict.current_entity_version)          # e.g. 9
+
+    # Look at what the other writer changed, and only re-issue the amendment
+    # if it still applies to what is recorded now.
+    history = get_outcome_history("sales-lead-8842")
+    if still_applies(history[-1]):
+        job.amend_outcome(reason="Chargeback, re-checked", outcome_value=0.0,
+                          expected_entity_version=conflict.current_entity_version)
+```
+
+The handle also records that version, so the retry above works with or without passing `expected_entity_version=` explicitly. `current_entity_version` is `None` when the conflict body carries no version; the version then has to come from a job read (`GET /v2/api/jobs/{agenticJobId}`), which this SDK does not wrap yet, and a retry without it is unlocked (last-write-wins). `get_outcome_history()` rows carry an `amendment_sequence`, not an entity version — history tells you *what* changed, never which version to retry with.
+
+Every outcome call replaces the recorded version with the one its response reports, including clearing it when a response carries none, so a completed call never leaves a token behind that the platform has already moved past.
+
+- **Omitting `reason`:** an API-key caller may leave `reason` out and the platform records an automated correction reason derived from the source. A session caller must supply one; a blank string is rejected client-side either way.
+- **`reason` vs `outcome_reason`:** `reason` is the amendment's own audit justification (why the record changed); `outcome_reason` is the business explanation of why the job failed or was cancelled. Use `outcome_reason` for failure explanations rather than burying them in `metadata` — it is a first-class field on the outcome and is returned on every `get_outcome_history()` row.
+- **Clearing `outcome_reason`:** omit the argument to leave the stored value untouched; pass an empty string (`outcome_reason=""`) to clear it.
+- **`metrics`:** both `report_outcome()` and `amend_outcome()` accept a `metrics` argument for recording the measurable facts behind an outcome.
+
+### Recording Metric Facts
+
+Beyond the single `outcome_value`, a job can carry the measurable facts its job type declares — `quality_rate` and its siblings — either with the outcome or later, once they are measurable.
+
+```python
+from revenium_middleware import JobContext
+
+with JobContext("claim-8842", type="claims_triage") as job:
+    ...
+    job.report_outcome(
+        execution_status="SUCCESS",
+        outcome_type="CONVERTED",
+        metrics=[
+            {"key": "quality_rate", "value": 0.93, "provenance": "MEASURED"},
+            {"key": "cases_closed", "value": 12},
+        ],
+    )
+
+# Two days later a human grades a sample of that same job's output.
+handle = JobContext.attach("claim-8842")
+handle.append_outcome_metrics([
+    {"key": "quality_rate", "value": 0.87, "provenance": "ATTESTED",
+     "reason": "graded sample of 200 cases"},
+])
+handle.close()
+```
+
+- **Declare the metric first:** a fact only lands if the job type's economics contract declares that key as a `PER_JOB` metric; an undeclared key is rejected with a 400. `quality_rate` is a rate and the platform range-checks it to 0..1.
+- **Entry shape:** `key` and `value` are required; `provenance` (`MEASURED` | `SELF_REPORTED` | `DERIVED` | `ATTESTED`), `recordedBy`, `source`, `reason` and `recordedAt` are optional. Entries are sent exactly as you write them, so the fields you omit take the platform's defaults (`SELF_REPORTED`, the calling principal, `api`) instead of being guessed by the SDK. A missing `key` or `value` — or no entries at all on `append_outcome_metrics()` — raises `ValueError` before any HTTP request, on `JobContext` and `AgenticOutcomeClient` alike.
+- **Append-only:** facts accumulate; the SDK never dedupes or replaces one, because the platform owns fact identity. `metrics=` on `amend_outcome()` appends as part of the amendment.
+- **Not part of outcome history:** `get_outcome_history()` returns the outcome revisions only — appended facts do not appear in those rows.
+- **Retries:** an append is retried only on `429`, which proves the platform rejected the request before recording anything. A `502`/`503`/`504` is raised instead of retried: the facts may already be recorded, and a second append is a second fact, so the decision to resend is yours (check the recorded facts first).
+- **Locking is unaffected:** appending facts does not change the job's `entityVersion`, so the handle keeps the version it recorded and a following `amend_outcome()` still locks against it. (`report_outcome()` and `amend_outcome()` clear the recorded version when their response carries none, because those calls advance it; an append does not.)
+- **Why it matters:** AI Alerts evaluate `QUALITY_RATE` from these facts, so a job whose integration emits none is invisible to those rules.
 
 ### Outcome Exceptions
 
@@ -322,7 +441,7 @@ All outcome exceptions are importable from `revenium_middleware` and share the `
 | `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 |
+| `OutcomeAmendConflictError` | A concurrent amendment changed the outcome (backend 409, optimistic lock) | Re-check the outcome against `get_outcome_history()`, then retry with `expected_entity_version=conflict.current_entity_version` — the SDK does not auto-retry |
 
 ### Low-Level Client
 
@@ -337,10 +456,11 @@ client = AgenticOutcomeClient(settings)
 client.emit_completion(...)                # one per LLM call
 client.emit_tool_event(...)                # one per tool / step
 client.report_outcome(job_id, {...})       # close the job with a terminal outcome
+client.append_outcome_metrics(job_id, [...])  # append declared per-job facts later
 client.close()
 ```
 
-The job is created implicitly by the first metric ingested for `agenticJobId`. Call `client.create_job(job_id)` explicitly if you need to record an agent run before emitting any metrics.
+The job is created implicitly by the first metric ingested for `agenticJobId`. Call `client.create_job(job_id)` explicitly if you need to record an agent run before emitting any metrics; it returns the created job resource merged over the fields you supplied, including the `entityVersion` an outcome amendment sends back as `expectedEntityVersion`.
 
 See [`examples/agentic_outcomes/`](examples/agentic_outcomes/) for runnable demos (sales / coding / support) with configurable failure rates and outcome distributions.
 
@@ -779,6 +899,7 @@ litellm_settings:
 ```
 
 When using the LiteLLM proxy, pass metadata via HTTP headers (`x-revenium-*`).
+Reasoning effort travels as `x-revenium-effort` on the proxied request.
 
 #### LiteLLM Decorators
 
@@ -1071,6 +1192,7 @@ Add business context to any API call by passing a `usage_metadata` dictionary. A
 | `productName` | Your product or feature name | Attribute AI costs to specific features (e.g., `"customer-chatbot"`, `"email-assistant"`). Auto-creates if not found |
 | `agent` | AI agent or bot identifier | Distinguish between multiple AI agents or automation workflows |
 | `response_quality_score` | Custom quality rating (0.0-1.0) | Track user satisfaction or automated quality metrics for model performance analysis |
+| `effort` | Reasoning effort level requested of the model (free-form string, max 16 chars, `^[A-Za-z0-9_-]+$`) | Report what share of AI spend is high-effort reasoning, and compare cost per effort level |
 
 **Example:**
 
@@ -1093,11 +1215,27 @@ response = client.chat.completions.create(
         "subscription_id": "pro-plan-Q1",
         "productName": "customer-support-chatbot",
         "agent": "support-agent",
-        "response_quality_score": 0.92
+        "response_quality_score": 0.92,
+        "effort": "high"
     }
 )
 ```
 
+**Reasoning effort:** `effort` records how hard the model was asked to think, so
+high-effort reasoning spend can be separated from the rest. It is a free-form
+string, not an enum -- vendor vocabularies differ and drift, so `low`, `medium`,
+`high`, `xhigh` and `ultra` are all real values, and a level this SDK release has
+never heard of is passed through untouched rather than rejected or rewritten. The
+Revenium backend owns validation (at most 16 characters, matching
+`^[A-Za-z0-9_-]+$`); a value it rejects fails the metering call visibly instead
+of being silently dropped, so it surfaces in the log and in
+`get_metering_status()`. It is distinct from the reported reasoning token count,
+which measures the tokens actually spent rather than the level requested.
+
+Set it per call in `usage_metadata` on any provider integration. In LiteLLM proxy
+mode, where per-call attribution travels as request headers rather than
+`usage_metadata`, send `x-revenium-effort` instead.
+
 **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)
@@ -1121,6 +1259,7 @@ Enhanced observability fields for tracking AI operations across environments, re
 | `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 |
+| `agent_version` | _(none — per call only)_ | Version of the AI agent that produced the call (max 64 chars) | Compare cost across agent releases; not `agentic_job_version`, which versions the job definition |
 | `skill_name` | `REVENIUM_SKILL_NAME` | Name of the agent skill that produced the call (max 256 chars) | Attribute AI costs to the skill that generated them |
 | `skill_source` | `REVENIUM_SKILL_SOURCE` | Where the skill was loaded from — accepted values: `bundled`, `projectSettings`, `userSettings`, `plugin` (case-sensitive) | Classify skill origin in the shared skill catalog |
 | `skill_kind` | `REVENIUM_SKILL_KIND` | Kind of skill invoked — accepted value: `workflow` (omit otherwise) | Distinguish workflow skills in reporting |
@@ -1155,7 +1294,8 @@ response = client.chat.completions.create(
         "trace_name": "Support Chat Session",
         "transaction_name": "Generate Response",
         "parent_transaction_id": "parent-txn-123",
-        "ticket_id": "JIRA-123"
+        "ticket_id": "JIRA-123",
+        "agent_version": "1.4.2"
     }
 )
 ```
@@ -1572,7 +1712,8 @@ print(get_buffer_stats())
 | `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_WRITE_API_KEY` | - | Primary write-scope key (`rev_sk_`) for the agentic outcomes API (report/amend/history); falls back to `REVENIUM_OUTCOME_API_KEY` (deprecated), then `REVENIUM_METERING_API_KEY` |
+| `REVENIUM_OUTCOME_API_KEY` | - | Deprecated fallback name for the write-scope key; used only when `REVENIUM_WRITE_API_KEY` is unset |
 | `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_python_sdk-0.6.0 → revenium_python_sdk-0.8.0}/README.md

@@ -167,7 +167,63 @@ when the provider's SDK is installed.
 
 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`.
+> **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_WRITE_API_KEY` > `REVENIUM_OUTCOME_API_KEY` (deprecated fallback) > `REVENIUM_METERING_API_KEY`.
+
+### Job-Type Economics and Outcome Facts
+
+Keep a metering key for AI telemetry and a separate write key for outcomes and
+job-type configuration. A registered `valuePerUnit` rule takes precedence over
+an outcome's `outcome_value`; the backend never sums the two value sources.
+
+```python
+from revenium_middleware import (
+    Baseline, JobTypeEconomics, PeriodFactEntry, create_baseline,
+    report_period_facts, upsert_job_type_economics,
+)
+
+upsert_job_type_economics("claim", JobTypeEconomics(
+    unit_metric_key="completed_claims", unit_label="claim",
+    metrics=[{
+        "key": "completed_claims", "type": "COUNT",
+        "direction": "HIGHER_IS_BETTER", "aggregation": "SUM",
+        "resolution": "PER_JOB",
+    }],
+    dimensions=[{"key": "region", "allowedValues": ["us", "ca"]}],
+    monetization={
+        "metricKey": "completed_claims", "valuePerUnit": 4.25,
+        "currency": "USD", "category": "COST_AVOIDED", "basis": "REALIZED",
+    },
+))
+create_baseline("claim", Baseline(
+    effective_from="2026-08-01T00:00:00Z", cost_per_unit=4.25, currency="USD",
+))
+report_period_facts("claim", [PeriodFactEntry(
+    period_start="2026-08-01T00:00:00Z", period_end="2026-09-01T00:00:00Z",
+    dimension_key="region", dimension_value="us",
+    key="completed_claims", value=1280,
+)])
+```
+
+`effective_from` is the only required field on a baseline; every other field
+is optional, and a baseline without it is rejected. A job type must be
+declared with `upsert_job_type_economics` before it accepts baselines or
+facts, and `report_period_facts` accepts only metrics declared with
+`"resolution": "PERIOD"`.
+
+Job economics currency values must be USD. Baselines and period facts use
+server-supplied attribution when their provenance,
+reporter, and source fields are omitted. Set those fields only when you need an
+explicit override. Economics metric directions are
+`HIGHER_IS_BETTER` or `LOWER_IS_BETTER`; monetization categories are
+`REVENUE`, `COST_AVOIDED`, `TIME_SAVED`, and `LEADING_VALUE`, with a
+`REALIZED` or `EXPECTED` basis.
+
+Use `CUSTOMER_DECLARED` or `MEASURED` for a baseline override. Use `MEASURED`,
+`SELF_REPORTED`, or `DERIVED` for a period fact override.
+
+Facts are append-only and keyed on the period, dimension and metric key
+together. Re-appending that tuple supersedes the active fact, and the server
+requires `reason=` on the entry when it does.
 
 ### JobContext
 
@@ -214,7 +270,70 @@ 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.
+`amend_outcome()` takes `reason` — the amendment's audit justification, still the first positional argument — plus the same optional fields as `report_outcome()` (`execution_status`, `outcome_type`, `outcome_value`, `outcome_currency`, `metadata`, `reported_by`, `outcome_reason`, `metrics`), and returns the updated job as a dict.
+
+- **Detecting a lost update:** `report_outcome()` and `amend_outcome()` record the job's `entityVersion` from the response on the handle (readable as `job.entity_version`). The next `amend_outcome()` on that same handle sends it as `expectedEntityVersion`, so an amendment that would overwrite a change made by another writer in the meantime raises `OutcomeAmendConflictError` instead of silently winning. Pass `expected_entity_version=` to lock against a version you fetched yourself; use a fresh `JobContext.attach()` handle — which has recorded nothing — for the old last-write-wins behavior.
+
+```python
+from revenium_middleware import OutcomeAmendConflictError, get_outcome_history
+
+try:
+    job.amend_outcome(reason="Chargeback", outcome_value=0.0)
+except OutcomeAmendConflictError as conflict:
+    # The conflict reports the version the platform actually holds.
+    print(conflict.current_entity_version)          # e.g. 9
+
+    # Look at what the other writer changed, and only re-issue the amendment
+    # if it still applies to what is recorded now.
+    history = get_outcome_history("sales-lead-8842")
+    if still_applies(history[-1]):
+        job.amend_outcome(reason="Chargeback, re-checked", outcome_value=0.0,
+                          expected_entity_version=conflict.current_entity_version)
+```
+
+The handle also records that version, so the retry above works with or without passing `expected_entity_version=` explicitly. `current_entity_version` is `None` when the conflict body carries no version; the version then has to come from a job read (`GET /v2/api/jobs/{agenticJobId}`), which this SDK does not wrap yet, and a retry without it is unlocked (last-write-wins). `get_outcome_history()` rows carry an `amendment_sequence`, not an entity version — history tells you *what* changed, never which version to retry with.
+
+Every outcome call replaces the recorded version with the one its response reports, including clearing it when a response carries none, so a completed call never leaves a token behind that the platform has already moved past.
+
+- **Omitting `reason`:** an API-key caller may leave `reason` out and the platform records an automated correction reason derived from the source. A session caller must supply one; a blank string is rejected client-side either way.
+- **`reason` vs `outcome_reason`:** `reason` is the amendment's own audit justification (why the record changed); `outcome_reason` is the business explanation of why the job failed or was cancelled. Use `outcome_reason` for failure explanations rather than burying them in `metadata` — it is a first-class field on the outcome and is returned on every `get_outcome_history()` row.
+- **Clearing `outcome_reason`:** omit the argument to leave the stored value untouched; pass an empty string (`outcome_reason=""`) to clear it.
+- **`metrics`:** both `report_outcome()` and `amend_outcome()` accept a `metrics` argument for recording the measurable facts behind an outcome.
+
+### Recording Metric Facts
+
+Beyond the single `outcome_value`, a job can carry the measurable facts its job type declares — `quality_rate` and its siblings — either with the outcome or later, once they are measurable.
+
+```python
+from revenium_middleware import JobContext
+
+with JobContext("claim-8842", type="claims_triage") as job:
+    ...
+    job.report_outcome(
+        execution_status="SUCCESS",
+        outcome_type="CONVERTED",
+        metrics=[
+            {"key": "quality_rate", "value": 0.93, "provenance": "MEASURED"},
+            {"key": "cases_closed", "value": 12},
+        ],
+    )
+
+# Two days later a human grades a sample of that same job's output.
+handle = JobContext.attach("claim-8842")
+handle.append_outcome_metrics([
+    {"key": "quality_rate", "value": 0.87, "provenance": "ATTESTED",
+     "reason": "graded sample of 200 cases"},
+])
+handle.close()
+```
+
+- **Declare the metric first:** a fact only lands if the job type's economics contract declares that key as a `PER_JOB` metric; an undeclared key is rejected with a 400. `quality_rate` is a rate and the platform range-checks it to 0..1.
+- **Entry shape:** `key` and `value` are required; `provenance` (`MEASURED` | `SELF_REPORTED` | `DERIVED` | `ATTESTED`), `recordedBy`, `source`, `reason` and `recordedAt` are optional. Entries are sent exactly as you write them, so the fields you omit take the platform's defaults (`SELF_REPORTED`, the calling principal, `api`) instead of being guessed by the SDK. A missing `key` or `value` — or no entries at all on `append_outcome_metrics()` — raises `ValueError` before any HTTP request, on `JobContext` and `AgenticOutcomeClient` alike.
+- **Append-only:** facts accumulate; the SDK never dedupes or replaces one, because the platform owns fact identity. `metrics=` on `amend_outcome()` appends as part of the amendment.
+- **Not part of outcome history:** `get_outcome_history()` returns the outcome revisions only — appended facts do not appear in those rows.
+- **Retries:** an append is retried only on `429`, which proves the platform rejected the request before recording anything. A `502`/`503`/`504` is raised instead of retried: the facts may already be recorded, and a second append is a second fact, so the decision to resend is yours (check the recorded facts first).
+- **Locking is unaffected:** appending facts does not change the job's `entityVersion`, so the handle keeps the version it recorded and a following `amend_outcome()` still locks against it. (`report_outcome()` and `amend_outcome()` clear the recorded version when their response carries none, because those calls advance it; an append does not.)
+- **Why it matters:** AI Alerts evaluate `QUALITY_RATE` from these facts, so a job whose integration emits none is invisible to those rules.
 
 ### Outcome Exceptions
 
@@ -225,7 +344,7 @@ All outcome exceptions are importable from `revenium_middleware` and share the `
 | `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 |
+| `OutcomeAmendConflictError` | A concurrent amendment changed the outcome (backend 409, optimistic lock) | Re-check the outcome against `get_outcome_history()`, then retry with `expected_entity_version=conflict.current_entity_version` — the SDK does not auto-retry |
 
 ### Low-Level Client
 
@@ -240,10 +359,11 @@ client = AgenticOutcomeClient(settings)
 client.emit_completion(...)                # one per LLM call
 client.emit_tool_event(...)                # one per tool / step
 client.report_outcome(job_id, {...})       # close the job with a terminal outcome
+client.append_outcome_metrics(job_id, [...])  # append declared per-job facts later
 client.close()
 ```
 
-The job is created implicitly by the first metric ingested for `agenticJobId`. Call `client.create_job(job_id)` explicitly if you need to record an agent run before emitting any metrics.
+The job is created implicitly by the first metric ingested for `agenticJobId`. Call `client.create_job(job_id)` explicitly if you need to record an agent run before emitting any metrics; it returns the created job resource merged over the fields you supplied, including the `entityVersion` an outcome amendment sends back as `expectedEntityVersion`.
 
 See [`examples/agentic_outcomes/`](examples/agentic_outcomes/) for runnable demos (sales / coding / support) with configurable failure rates and outcome distributions.
 
@@ -682,6 +802,7 @@ litellm_settings:
 ```
 
 When using the LiteLLM proxy, pass metadata via HTTP headers (`x-revenium-*`).
+Reasoning effort travels as `x-revenium-effort` on the proxied request.
 
 #### LiteLLM Decorators
 
@@ -974,6 +1095,7 @@ Add business context to any API call by passing a `usage_metadata` dictionary. A
 | `productName` | Your product or feature name | Attribute AI costs to specific features (e.g., `"customer-chatbot"`, `"email-assistant"`). Auto-creates if not found |
 | `agent` | AI agent or bot identifier | Distinguish between multiple AI agents or automation workflows |
 | `response_quality_score` | Custom quality rating (0.0-1.0) | Track user satisfaction or automated quality metrics for model performance analysis |
+| `effort` | Reasoning effort level requested of the model (free-form string, max 16 chars, `^[A-Za-z0-9_-]+$`) | Report what share of AI spend is high-effort reasoning, and compare cost per effort level |
 
 **Example:**
 
@@ -996,11 +1118,27 @@ response = client.chat.completions.create(
         "subscription_id": "pro-plan-Q1",
         "productName": "customer-support-chatbot",
         "agent": "support-agent",
-        "response_quality_score": 0.92
+        "response_quality_score": 0.92,
+        "effort": "high"
     }
 )
 ```
 
+**Reasoning effort:** `effort` records how hard the model was asked to think, so
+high-effort reasoning spend can be separated from the rest. It is a free-form
+string, not an enum -- vendor vocabularies differ and drift, so `low`, `medium`,
+`high`, `xhigh` and `ultra` are all real values, and a level this SDK release has
+never heard of is passed through untouched rather than rejected or rewritten. The
+Revenium backend owns validation (at most 16 characters, matching
+`^[A-Za-z0-9_-]+$`); a value it rejects fails the metering call visibly instead
+of being silently dropped, so it surfaces in the log and in
+`get_metering_status()`. It is distinct from the reported reasoning token count,
+which measures the tokens actually spent rather than the level requested.
+
+Set it per call in `usage_metadata` on any provider integration. In LiteLLM proxy
+mode, where per-call attribution travels as request headers rather than
+`usage_metadata`, send `x-revenium-effort` instead.
+
 **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)
@@ -1024,6 +1162,7 @@ Enhanced observability fields for tracking AI operations across environments, re
 | `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 |
+| `agent_version` | _(none — per call only)_ | Version of the AI agent that produced the call (max 64 chars) | Compare cost across agent releases; not `agentic_job_version`, which versions the job definition |
 | `skill_name` | `REVENIUM_SKILL_NAME` | Name of the agent skill that produced the call (max 256 chars) | Attribute AI costs to the skill that generated them |
 | `skill_source` | `REVENIUM_SKILL_SOURCE` | Where the skill was loaded from — accepted values: `bundled`, `projectSettings`, `userSettings`, `plugin` (case-sensitive) | Classify skill origin in the shared skill catalog |
 | `skill_kind` | `REVENIUM_SKILL_KIND` | Kind of skill invoked — accepted value: `workflow` (omit otherwise) | Distinguish workflow skills in reporting |
@@ -1058,7 +1197,8 @@ response = client.chat.completions.create(
         "trace_name": "Support Chat Session",
         "transaction_name": "Generate Response",
         "parent_transaction_id": "parent-txn-123",
-        "ticket_id": "JIRA-123"
+        "ticket_id": "JIRA-123",
+        "agent_version": "1.4.2"
     }
 )
 ```
@@ -1475,7 +1615,8 @@ print(get_buffer_stats())
 | `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_WRITE_API_KEY` | - | Primary write-scope key (`rev_sk_`) for the agentic outcomes API (report/amend/history); falls back to `REVENIUM_OUTCOME_API_KEY` (deprecated), then `REVENIUM_METERING_API_KEY` |
+| `REVENIUM_OUTCOME_API_KEY` | - | Deprecated fallback name for the write-scope key; used only when `REVENIUM_WRITE_API_KEY` is unset |
 | `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_python_sdk-0.6.0 → revenium_python_sdk-0.8.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "revenium-python-sdk"
-version = "0.6.0"
+version = "0.8.0"
 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"

{revenium_python_sdk-0.6.0 → revenium_python_sdk-0.8.0}/revenium_middleware/__init__.py

@@ -179,6 +179,13 @@ from .agentic_outcomes import AgenticOutcomeClient, AgenticOutcomeSettings  # no
 # Public job-context surface (BACK-777)
 from .job_context import JobContext  # noqa: E402
 from .job_history import JobOutcomeAmendment, get_outcome_history  # noqa: E402
+from .job_type_economics import (  # noqa: E402
+    Baseline, BaselineProvenance, JobTypeEconomics, JobTypeMetricDirection,
+    JobTypeMonetizationBasis, JobTypeMonetizationCategory,
+    OutcomeMetricProvenance, PeriodFactEntry,
+    create_baseline, get_job_type_economics, list_baselines,
+    report_period_facts, upsert_job_type_economics,
+)
 from ._core.exceptions import (  # noqa: E402
     OutcomeAlreadyReportedError,
     OutcomeAmendConflictError,
@@ -235,4 +242,17 @@ __all__ = [
     "JobOutcomeAmendment",
     "OutcomeNotReportedError",
     "OutcomeAmendConflictError",
+    "PeriodFactEntry",
+    "Baseline",
+    "BaselineProvenance",
+    "JobTypeEconomics",
+    "JobTypeMetricDirection",
+    "JobTypeMonetizationBasis",
+    "JobTypeMonetizationCategory",
+    "OutcomeMetricProvenance",
+    "report_period_facts",
+    "get_job_type_economics",
+    "upsert_job_type_economics",
+    "create_baseline",
+    "list_baselines",
 ]

revenium_python_sdk-0.8.0/revenium_middleware/_core/cache_tokens.py

@@ -0,0 +1,109 @@
+"""Tolerant field access for provider usage objects (dict or attribute-style).
+
+Cache token fields differ by provider surface:
+
+- Anthropic-style: top-level ``cache_read_input_tokens`` / ``cache_creation_input_tokens``,
+  plus the nested per-TTL breakdown under ``cache_creation``.
+- OpenAI-style: nested ``prompt_tokens_details.cached_tokens``; no separate
+  cache-creation count.
+
+See BACK-2391 for the history of this bug class (hardcoded/zeroed cache-token
+fields recurring across multiple emitters) and BACK-1925 for the LiteLLM
+client's cache-token contract, which this module's defaults must not break.
+"""
+from numbers import Number
+from typing import Any, Dict, NamedTuple, Optional
+
+
+class CacheTokens(NamedTuple):
+    cache_read_tokens: int
+    cache_creation_tokens: int
+
+
+def _get(source: Any, name: str) -> Any:
+    """Read `name` from a dict or an attribute-style object; None if absent."""
+    if source is None:
+        return None
+    if isinstance(source, dict):
+        return source.get(name)
+    return getattr(source, name, None)
+
+
+def get_usage_field(usage: Any, name: str, default: int = 0) -> Any:
+    """Read a single usage field through the same tolerant accessor as
+    `extract_cache_tokens`, so cache fields and base token fields (prompt/
+    completion/total) are read consistently from the same dict-or-object
+    usage value. Missing or None fields return `default`.
+
+    Normalizing a usage object to a plain dict *before* reading it (e.g. to
+    simplify a `.get(...)` call) silently drops every field for
+    attribute-style usage objects that fall through that normalization --
+    exactly the inconsistency this function exists to prevent. Callers with
+    multiple fields to read from the same `usage` value should read all of
+    them through this function (or `extract_cache_tokens`) rather than
+    normalizing `usage` itself first.
+    """
+    value = _get(usage, name)
+    return default if value is None else value
+
+
+def extract_cache_tokens(usage: Any) -> CacheTokens:
+    """Extract (cache_read_tokens, cache_creation_tokens) from a usage object.
+
+    Tolerates dicts and attribute-style objects (SimpleNamespace, SDK response
+    models) and treats missing or None fields as 0. Checked in order:
+
+    1. OpenAI-style nested cache reads: ``usage.prompt_tokens_details.cached_tokens``
+    2. Anthropic-style top-level cache reads: ``usage.cache_read_input_tokens``
+    3. Anthropic-style top-level cache creation: ``usage.cache_creation_input_tokens``
+    """
+    prompt_details = _get(usage, "prompt_tokens_details")
+    cache_read_tokens = get_usage_field(prompt_details, "cached_tokens", 0)
+    if not cache_read_tokens:
+        cache_read_tokens = get_usage_field(usage, "cache_read_input_tokens", 0)
+    cache_creation_tokens = get_usage_field(usage, "cache_creation_input_tokens", 0)
+
+    return CacheTokens(cache_read_tokens=cache_read_tokens, cache_creation_tokens=cache_creation_tokens)
+
+
+def _optional_token_count(source: Any, name: str) -> Optional[int]:
+    """Read an integral token count, or None when it is absent or unusable.
+
+    Unlike `get_usage_field`, a missing field is reported as None rather than
+    coerced to 0, so callers can tell "the provider reported zero" apart from
+    "the provider reported nothing". Non-numeric values (including the
+    attributes that attribute-style test doubles auto-create on access) count
+    as nothing rather than being forwarded into a metering payload.
+    """
+    value = _get(source, name)
+    if isinstance(value, bool) or not isinstance(value, Number):
+        return None
+    return int(value)
+
+
+def extract_cache_creation_ttl_counts(usage: Any) -> Dict[str, int]:
+    """Extract the per-TTL cache-creation breakdown as metering parameters.
+
+    Anthropic reports the split under a nested ``usage.cache_creation`` object
+    (``ephemeral_5m_input_tokens`` / ``ephemeral_1h_input_tokens``). That
+    object is absent on older responses and whenever the extended cache-TTL
+    beta is not in play, so it is read defensively.
+
+    Returns metering parameter names mapped to the counts the provider
+    actually reported, ready to be merged into a metering payload. A bucket the
+    provider did not report is left out entirely instead of being sent as a
+    zero: the aggregate ``cache_creation_token_count`` stays authoritative and
+    the backend prices the flat fallback from it when no split is present,
+    whereas an explicit zero would assert a split that never happened. A
+    bucket the provider does report as 0 is forwarded as 0.
+    """
+    cache_creation = _get(usage, "cache_creation")
+
+    counts: Dict[str, int] = {}
+    ephemeral_5m = _optional_token_count(cache_creation, "ephemeral_5m_input_tokens")
+    if ephemeral_5m is not None:
+        counts["cache_creation5m_token_count"] = ephemeral_5m
+    ephemeral_1h = _optional_token_count(cache_creation, "ephemeral_1h_input_tokens")
+    if ephemeral_1h is not None:
+        counts["cache_creation1h_token_count"] = ephemeral_1h
+    return counts