> ## Documentation Index > Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt > Use this file to discover all available pages before exploring further. # List metrics annotated with compatibility for a session > Returns evaluable metrics annotated with whether they can be satisfied by the session's product metadata and test-case availability, plus a `relevance` ranking derived from the session's test case's test (`linked`/`matching`/`none`). A session evaluation scores output that is already stored, so the version needs no conversation target (endpoint, phone, or WebRTC connection) and compatibility never depends on one. Production (monitoring) sessions have no test case, so every metric is `none`, and a metric is incompatible when it needs a test-case param that monitoring cannot supply (expected_output, context, expected_tools, user_persona, goal, scenario, stopping_criterias). A metric needing only `input` stays compatible while some turn of the session yields text of its own; a session whose turns carry only a file, or audio with no transcript, makes `input` unreadable and that metric incompatible. Span-dependent and runtime-only params are out of scope and treated as always satisfied. ## OpenAPI ````yaml https://api.galtea.ai/openapi.json get /sessions/{id}/compatible-metrics openapi: 3.0.0 info: version: 1.0.0 title: Product Management Service API description: API documentation for Product Management Service contact: name: Galtea AI servers: - url: https://api.galtea.ai security: - bearerAuth: [] tags: [] externalDocs: description: Galtea Platform Documentation url: https://docs.galtea.ai paths: /sessions/{id}/compatible-metrics: get: tags: - sessions summary: List metrics annotated with compatibility for a session description: >- Returns evaluable metrics annotated with whether they can be satisfied by the session's product metadata and test-case availability, plus a `relevance` ranking derived from the session's test case's test (`linked`/`matching`/`none`). A session evaluation scores output that is already stored, so the version needs no conversation target (endpoint, phone, or WebRTC connection) and compatibility never depends on one. Production (monitoring) sessions have no test case, so every metric is `none`, and a metric is incompatible when it needs a test-case param that monitoring cannot supply (expected_output, context, expected_tools, user_persona, goal, scenario, stopping_criterias). A metric needing only `input` stays compatible while some turn of the session yields text of its own; a session whose turns carry only a file, or audio with no transcript, makes `input` unreadable and that metric incompatible. Span-dependent and runtime-only params are out of scope and treated as always satisfied. operationId: listCompatibleMetricsBySession parameters: - name: id in: path description: Session ID to evaluate compatibility against required: true schema: type: string - name: limit in: query description: Maximum number of metrics to return (default 100) required: false schema: type: integer - name: inferenceResultId in: query description: >- The turn a run would judge. Input readability is then decided from that turn alone, matching what an evaluation targeting it is sent. Omit to answer for every turn of the session. required: false schema: type: string responses: '200': description: List of metrics with compatibility annotations content: application/json: schema: type: array items: $ref: '#/components/schemas/CompatibleMetric' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Session not found content: application/json: schema: $ref: '#/components/schemas/Error' security: - bearerAuth: [] components: schemas: CompatibleMetric: type: object description: >- Metric annotated with compatibility against the evaluation context: product metadata, test-case availability, and the conversation endpoint connection output mapping when the evaluation has to produce new output. Span-dependent and runtime-only params are out of scope and treated as always satisfied. properties: id: type: string example: metric_123 name: type: string example: Accuracy source: type: string enum: - SELF_HOSTED - FULL_PROMPT - PARTIAL_PROMPT - HUMAN_EVALUATION - GEVAL - DEEPEVAL - DETERMINISTIC nullable: true example: PARTIAL_PROMPT description: >- Evaluation method for the metric. `FULL_PROMPT` is deprecated for creation — `POST /metrics` rejects it with a 400. Use `PARTIAL_PROMPT` for new AI Evaluation metrics. The value remains in the enum because existing FULL_PROMPT metrics are still returned by reads and filters. description: type: string nullable: true example: Measures the accuracy of responses isCompatible: type: boolean description: >- Whether the metric can be satisfied by the resolved evaluation context. Always checked against the product metadata and test-case availability; the conversation endpoint connection output mapping is only checked when the evaluation has to produce new output. For a session, a metric reading `input` is also incompatible when no turn yields text without a file beside it, because the judge is sent the turns and can read neither a document nor an untranscribed audio part. Pass `inferenceResultId` to answer for the one turn a run would judge. A metric reading `conversation_turns` stays compatible: the turns are scored as logged. incompatibilityReason: type: string nullable: true description: >- Human-readable explanation of why the metric is incompatible. Non-null iff `isCompatible === false`. example: 'Missing required parameters: product_capabilities, retrieval_context' relevance: type: string enum: - linked - matching - none description: >- How relevant the metric is to the tests the evaluation runs against. `linked`: linked to a specification of one of those tests. `matching`: linked to a same-product specification whose testType matches one of those tests. `none`: neither, or no test context was provided. example: linked required: - id - name - isCompatible - relevance Error: type: object properties: error: type: string example: Error type message: type: string example: Error message description securitySchemes: bearerAuth: type: http scheme: bearer description: >- API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (`gsk_*`) and legacy (`gsk-`) API keys are accepted, e.g. `Authorization: Bearer gsk_...` or `Authorization: Bearer gsk-...`. ````