GoodMemGoodMem
ReferenceOpenTelemetry

Spans, attributes, and outcomes

Trace structure, diagnostic fields, outcome rules, and the generated attribute inventory.

Spans, attributes, and outcomes

A span describes one operation, with attributes for its scope, outcome, and measured counts. Some fields explicitly identify the enclosing request or job; count units depend on the span kind.

Span structure

REST and hosted HTTP MCP use an HTTP entry span, while direct network gRPC calls use a gRPC server span. The internal REST/MCP-to-gRPC bridge preserves parentage without extra transport spans.

A retrieval trace can show a structure like this:

Request
  Retrieval
    Query preparation and embedding
      Provider call
        Attempts and retry waits
    Search and result preparation
    Postprocessing
      Rerank or generation call

The request determines which operations appear. Parallel stages can overlap, so their duration sum can exceed the request duration. Provider observations also cover ingestion and provider checks outside retrieval. Use the generated span inventory for the current span names.

The inference proxy supplies transport traces only, without semantic generation spans or token counts. SQL spans require separate instrumentation.

REST and gRPC Decide calls add a gen_ai.decide child span with operation decide and observation kind decision. It records the decision-model UUID, provider, requested/returned model, duration and typed outcome. State, question names, rubrics, media and answers are excluded. The Langfuse profile labels it as a generation; LangSmith labels it as an LLM run. These labels do not change the typed decision API. Live decision ingestion and automatic pricing are unverified.

Request and resource filters

AttributeTypeMeaning
goodmem.trace.nameTextEnclosing GoodMem request or job name; not the remote caller's trace name
goodmem.trace.ownedBooleanGoodMem started the trace rather than joining the caller's trace
goodmem.request.idTextServer request ID; separate from the trace ID
goodmem.operationTextOperation on this span
goodmem.request.operationTextEnclosing request operation on a child span
goodmem.principal.idUUID textAuthenticated principal
goodmem.api_key.idUUID textExact API-key identifier; never the key secret
goodmem.resource.kindTextResource kind for the operation
goodmem.resource.idUUID textValidated resource identifier
goodmem.retrieval.space_idsText arrayAuthorized search spaces; a bounded number of IDs
goodmem.retrieval.accessible_space_countIntegerFull authorized space count
goodmem.retrieval.space_ids_truncatedBooleanWhether the retained space list omits IDs
goodmem.space.idUUID textSingle authorized retrieval space, or the applicable resource/job space

Retrieval space fields describe the authorized search scope. A truncated list can omit a space that the request searches. If goodmem.retrieval.space_ids_truncated is true, a negative match cannot exclude an omitted space. The generated inventory lists the vendor aliases for these fields. Principal IDs remain resource metadata rather than backend application-user or session IDs.

Outcomes and errors

goodmem.outcome has four values:

ValueMeaning
successOperation completed without a known failure
failedOperation failed, or no attempted logical item succeeded
partialSome work failed, or usable output required a fallback
cancelledOperation stopped before normal completion through cancellation
Failure fieldMeaning
goodmem.failure.categoryWhat failed
goodmem.failure.originSource of the failure, such as caller or provider
goodmem.failure.expectedPositive identification of an expected rejection or intentional stop
goodmem.status_codeGoodMem status where available
goodmem.rpc.status_codeCanonical RPC result, such as DEADLINE_EXCEEDED
rpc.grpc.status_codeNumeric gRPC transport status
http.response.status_codeNumeric HTTP response status
exception.typeException class where available; no raw message or stack trace

Common categories include authentication, permission, timeout, and provider_failure. Other values can appear in later versions.

For cross-provider failure filters, use goodmem.failure.category; transport spans retain their native error.type conventions.

Result counts

A result count describes the output of the span that carries it, rather than one universal unit for the request. For example, retrieval counts describe emitted results, while vector-search counts describe candidate hits. Do not sum result counts across spans.

A stage reports a count only when the operation supplies one. See the generated mappings for the fields that use the destination alias result_count.

Provider usage and retries

gen_ai.usage.input_tokens and gen_ai.usage.output_tokens contain the nonnegative token counts that the provider reports. An absent counter means unknown usage; an explicit zero means reported zero. Coverage follows the transport actually used by the configured provider:

Embedding provider / routeSource of input tokens
OpenAI / vLLMusage.prompt_tokens
Voyageusage.total_tokens
Jinausage.input_tokens when the field is present; otherwise usage.total_tokens
Coheremeta.tokens.input_tokens, falling back to meta.billed_units.input_tokens
TEI dense and sparsex-compute-tokens HTTP response header
DashScope native textusage.total_tokens
DashScope OpenAI-compatible fallbackusage.prompt_tokens
DashScope multimodal endpoint (text inputs)usage.input_tokens; explicit usage.output_tokens is recorded separately
Gemini Developer API (API key or ADC) / Google CloudusageMetadata.promptTokenCount

This table is the authoritative source of provider field precedence. For Jina, a present but null or invalid input_tokens field leaves input usage unknown; GoodMem does not substitute the total in that case. Raw JSON is inspected before SDK numeric coercion.

These cover every provider supported by the embedding factory. The Gemini routes use the currently supported Gemini embedding model's batchEmbedContents / embedContent operations. GoodMem reads native metadata before the pinned SDK discards it or rounds Cloud counts through floating point. It does not derive tokens from Google's billable character counts. Cohere's billed input tokens are token units; search units and image counts are not. DashScope's multimodal total can include output tokens, so it is not used as the input count. See Cohere embedding usage, Gemini embedding usage, and DashScope multimodal usage.

Reranker providerSource of input tokens
Voyageusage.total_tokens
Jinausage.total_tokens
vLLM / llama.cppShared Jina-compatible adapter: usage.total_tokens, when returned
DashScope (native and compatible)usage.total_tokens
TEIx-compute-tokens HTTP response header
Coheremeta.tokens.input_tokens, if supplied; responses containing only meta.billed_units.search_units leave tokens unknown

TEI's count covers the tokenized query/document pairs for the request. Local hosting does not imply zero usage or a known monetary price. Cohere's meta.billed_units.search_units is exported separately as the numeric attribute goodmem.rerank.cohere.search_units, with cohere_search_units metadata in both Langfuse and LangSmith profiles. It preserves fractional quantities and explicit zero; absent, negative, non-numeric, or non-finite values remain unknown. Search units are summed independently of token counts on the logical rerank span. They are billing quantities, not token counts or currency, and can support custom dashboards or cost calculations using the applicable provider rate. See the provider contracts for vLLM, TEI, DashScope, and Cohere. The shared InferenceUsage accumulator publishes these counts; the generated inventory links one representative source per attribute. These operations do not invent output-token counts or prices.

Each embedding/rerank response submits one immutable usage observation. Every observation accounts for input, output, total, model identity, and billing units; an omitted field is explicitly unknown. The shared raw-response inspector treats missing usage and inspection failures consistently and leaves SDK response consumption and transport configuration intact.

Counts are summed across decoded successful provider responses on the logical inference span, including batches. HTTP and retry child spans do not repeat token counts. Failed HTTP attempts do not supply counts; reported usage survives a later result-validation failure or cancellation when no batch work is abandoned. When concurrent execution abandons outstanding batches, provider usage and measurement exports for that invocation are suppressed: cancelled workers may still finish and report later. If any decoded response omits a valid count, that counter’s aggregate stays absent rather than reporting a partial total. Input and output completeness are independent. A call that makes no provider requests also leaves usage absent. See the generated inventory for usage fields, retry counters, and vendor aliases.

Jev, Laya and Clef decision calls publish valid usage.input_tokens and usage.output_tokens on gen_ai.decide, with the same unknown-versus-zero rules. GoodMem does not derive a total. Usage from a decoded successful HTTP response survives later answer-validation failure; failed HTTP attempts and undecodable responses supply no counts.

Local providers and recognized destination attributes

For vLLM, Ollama, and llama.cpp chat streams, the provider request policy selected at client construction requests stream_options.include_usage=true when the caller has not specified it. Explicit false and other stream options are preserved. This policy is independent of tracing; the tracer observes usage without changing the request. A terminal usage-only chunk supplies the totals; interrupted streams can still have unknown usage. The OpenAI-compatible embedding transport also records gen_ai.response.model when every decoded batch response supplies the same valid model. This preserves the actual served model alongside the requested alias. The shared Jina-compatible rerank adapter likewise preserves a returned model, including vLLM's model field. Both transports also record explicit usage.total_tokens as gen_ai.usage.total_tokens, independently of the input/output split. Ollama currently has a chat provider in GoodMem, but no dedicated embedding or rerank provider; an OpenAI-compatible embedding endpoint uses the OpenAI transport.

LLM spans emit the validated provider total as gen_ai.usage.total_tokens in every profile. Client-observed streaming latency uses goodmem.llm.time_to_first_output_ms. GoodMem does not emit or translate obsolete total-token or first-token aliases.

The compatibility profiles add these recognized attributes only when the source fact exists:

Canonical factLangfuse exportLangSmith export
goodmem.llm.cached_input_tokensgen_ai.usage.cache_read.input_tokensgen_ai.usage.cache_read_input_tokens, plus metadata
goodmem.llm.reasoning_tokensgen_ai.usage.reasoning.output_tokensgen_ai.usage.details.reasoning_tokens
gen_ai.response.modelAlso langfuse.observation.model.name, selecting the returned modelAlso ls_model_name in JSON metadata, with request model fallback
gen_ai.provider.nameCanonical attribute retainedAlso gen_ai.system, mapped to provider metadata

Langfuse ingestion treats cache reads and reasoning tokens as subsets of input/output, avoiding double counting. LangSmith documents its reasoning, model, and provider mappings; GoodMem uses the underscore cache-read alias verified against LangSmith ingestion, retaining the canonical cached count in metadata as well. Cache reads remain a subset of total input tokens; neither profile subtracts them from the canonical input count. LangSmith's pricing metadata explicitly selects the response model, falling back to the request model; its invocation model alone is insufficient for price matching. Embedding and rerank counts can appear in outputs.usage_metadata while top-level token totals remain zero; those zeros do not mean zero consumption. Controlled backend pricing checks with synthetic gpt-4o-mini usage verified discounted cache-read pricing in both destinations; this does not establish other model catalogs, provider invoices, or embedding/rerank automatic pricing. The neutral profile preserves canonical facts without destination aliases.

These counters depend on what the installed server returns. vLLM can return cached-token details when prompt-token details are enabled and reasoning-token details when a reasoning parser is configured. Ollama's OpenAI adapter can return prompt, completion, total, and cached prompt counts; GoodMem does not infer missing reasoning counts from output text.

TEI's usage source is x-compute-tokens for dense/sparse embeddings and reranking. Its response measurements are captured separately below. GoodMem also accepts optional provider generation measurements through the existing OpenAI-compatible SDK, without probing or upgrading runtimes:

Provider extensionCanonical attributesAvailability
llama.cpp root timingsgoodmem.llama_cpp.timings. plus prompt_ms, predicted_ms, prompt_per_token_ms, predicted_per_token_ms, prompt_per_second, predicted_per_secondCompletion and streaming SDK fixtures, including chunks without usage; live runtime/backend ingestion remains unverified
Ollama root timingsgoodmem.ollama.timings. plus prompt_ms, predicted_ms, prompt_per_token_ms, predicted_per_token_ms, prompt_per_second, predicted_per_secondObserved on Ollama 0.40.2 terminal streaming usage chunks; absent from tested non-streaming responses
vLLM root metricsgoodmem.vllm.timings. plus time_to_first_token_ms, generation_time_ms, queue_time_ms, mean_itl_ms, tokens_per_secondOptional on completion and final streaming usage responses; requires server support/configuration

All measurements are finite nonnegative float64 values; fractions and explicit zero survive, while missing or malformed values remain absent. Repeated stream snapshots replace present fields without summing; a missing later field does not erase a previously reported measurement. Early closure does not consume a terminal chunk to obtain metrics. Explicit usage opt-out remains honored. Both compatibility profiles expose these as diagnostic metadata named llama_cpp_, ollama_, or vllm_ plus the field name. They have no claimed native latency or pricing mapping.

Provider timings do not replace span duration, client time to first visible output, or Langfuse's completion-start timestamp. In vLLM v0.31.0, server TTFT starts at scheduling, excluding queue time; generation time covers first-to-last output; throughput includes the inference interval. Metrics require --enable-per-request-metrics, with statistics logging where required; multiple choices suppress metrics in that version. The decoder is SDK-fixture validated for this format, not E2E validated against a newer runtime. The audited vLLM 0.11.0 runtime supplied no per-request metrics. Aggregate /metrics histograms are never attributed to individual calls. Ollama native load_duration and total_duration are still unavailable through the tested compatible responses; no native adapter or runtime upgrade is implied. Compatibility with older Ollama builds that might reject stream_options remains unverified; GoodMem does not negotiate runtime capabilities or send extra inference probes.

Explicit usage field coverage

The following matrix supplements the input precedence tables above. Counts are int64; every field has independent completeness across successful responses. A missing, invalid, or overflowing count suppresses only its aggregate. An explicit zero is preserved. These are provider-reported facts, not sums inferred from other counters.

Response field and extraction pathCanonical fieldBackend interpretation
Voyage embedding/rerank and native DashScope text/rerank usage.total_tokensBoth gen_ai.usage.input_tokens and gen_ai.usage.total_tokens for these input-only operationsStandard usage; destination-computed totals are not evidence of an emitted provider total
Jina embedding raw usage.input_tokens (fallback to total only when absent), output_tokens, total_tokensIndependent input, output, total token fieldsRaw inspection precedes SDK coercion; output and total remain valid even if input is malformed
OpenAI-compatible embedding SDK usage prompt_tokens, optional extension completion_tokens, total_tokensIndependent input, output, total token fieldsvLLM output zero is preserved; absent output remains unknown
DashScope compatible text JSON usage.prompt_tokens, completion_tokens, total_tokensIndependent input, output, total token fieldsSame presence rules as other compatible embeddings
DashScope multimodal JSON usage.input_tokens, output_tokens, total_tokensIndependent input, output, total token fieldsA total never supplies a missing multimodal input count
TEI x-compute-tokensInput onlyNo explicit total or output count is inferred

TEI response measurements

TeiResponseMetadata decodes headers for dense, sparse and rerank. ProviderResponseMetrics validates immutable observations; the invocation collector owns completeness and aggregation. All numeric headers require one unambiguous, nonnegative decimal integer in signed 64-bit range. Missing, duplicate, negative, fractional, and overflowing values are unknown; reported zero remains zero.

The logical span retains at most eight goodmem.provider.response events, in response completion order, with receipt timestamps and no token counters or content. Each event carries goodmem.provider.response.sequence and the valid raw measurements below. The summary accounts for every decoded successful response, even when the bounded event buffer is full.

Provider headerEvent attribute under goodmem.provider.response.Logical-span summary under the same prefixType / units
x-compute-characterscompute_characterscompute_characters_total (complete sum)int64 characters
x-compute-timecompute_time_mscompute_time_max_msint64 milliseconds
x-total-timetotal_time_mstotal_time_max_msint64 milliseconds
x-tokenization-timetokenization_time_mstokenization_time_max_msint64 milliseconds
x-queue-timequeue_time_msqueue_time_max_msint64 milliseconds
x-inference-timeinference_time_msinference_time_max_msint64 milliseconds
x-compute-typecompute_typecompute_type (only if every response agrees)bounded provider label

Each numeric summary is absent if any successful response lacks that valid field. Characters also become unknown on sum overflow. count records successful responses; events_dropped counts samples omitted by the eight-event buffer (SDK event limits can independently drop more). Failed HTTP attempts supply neither counts nor measurements. Already observed responses survive later result-validation failure or cancellation when no batch work is abandoned. Outstanding batches abandoned by concurrent execution suppress these summaries and samples rather than exporting an incomplete snapshot. These summaries do not claim completeness for unreported failed attempts.

TEI v1.9 reports component timings as per-item averages and total time as request elapsed time. Maxima above are maxima of those reported values, not operation duration, summed work, or an average across all batches. Components need not add to total. x-compute-type is a provider label; v1.9 can report gpu+optimized even on CPU. See the versioned header source and batch calculation.

Neutral export retains canonical events and summaries. Both compatibility profiles expose summaries as metadata: provider_response_ plus the summary suffix, except compute_type uses provider_compute_type. LangSmith receives numeric JSON metadata; Langfuse uses its existing string metadata convention. These are diagnostic metadata, with no claimed native latency or cost mapping. LangSmith additionally receives provider_response_samples, a structured metadata array containing only the approved event measurements, sequence, and received_at_unix_ns as a decimal string to preserve nanosecond precision. This retains at most eight samples and 2,048 UTF-8 bytes, as a prefix in completion order. provider_response_samples_dropped, when present, counts export-projection omissions separately from recorder provider_response_events_dropped and native SDK event drops. This metadata is diagnostic detail, not a native LangSmith event timeline. Neutral and Langfuse exports retain the original event representation without this projection. They do not replace span duration or client-observed time to first output, which Langfuse receives through langfuse.observation.completion_start_time.

Background jobs

Each execution attempt starts a new trace, separate from the original enqueue request. Use goodmem.job.id to correlate attempts, or goodmem.job.attempt.id and goodmem.job.attempt.number to select one attempt. Attempt duration covers execution only, without queue delay or time between durable retries.

Attribute limits

GoodMem bounds the number of attributes, text length, and array size per span. The counters goodmem.telemetry.dropped_field_count and goodmem.attributes.dropped_count report omissions from these controls.

Generated span inventory

This table lists named spans from GoodMem source. HTTP route names and spans from dependency instrumentation vary with the request.

SpanSource
gen_ai.chatInferenceTracing
gen_ai.decideInferenceTracing
gen_ai.embeddingsInferenceTracing
gen_ai.rerankInferenceTracing
goodmem.embedding.provider_attemptEmbeddingAttemptTracing
goodmem.embedding.retry_backoffEmbeddingAttemptTracing
goodmem.job.attemptBgJobTracing
goodmem.job.enqueueMemoryServiceImpl
goodmem.job.memoryBgJobTracing
goodmem.openai.http_attemptOpenAIHttpTracing
goodmem.openai.retry_backoffOpenAIHttpTracing
goodmem.retrievalRetrievalTracing
goodmem.retrieval.fusionRetrievalTracing
goodmem.retrieval.hydrationRetrievalTracing
goodmem.retrieval.planMemoryServiceImpl
goodmem.retrieval.postprocessMemoryServiceImpl
goodmem.retrieval.query_embeddingRetrievalTracing
goodmem.retrieval.vector_searchRetrievalTracing

Generated attribute inventory

This inventory covers goodmem.* and gen_ai.* declarations in GoodMem source, without attributes from dependency instrumentation. In goodmem.result.status_count.<code>, <code> is a lowercase gRPC status name. Each span contains only the fields that its operation supplies.

The type column describes canonical OTLP values: int64 is an integer, and float64 is a floating-point number. Langfuse scalar metadata aliases use strings. LangSmith metadata preserves canonical types.

The metadata columns list destination aliases; a dash marks fields without an alias, whose canonical attributes remain available. Standard GenAI fields also use native backend mappings.

Langfuse prefixes aliases with langfuse.observation.metadata., while LangSmith stores them in its JSON metadata attribute.

AttributeTypeSourceLangfuse metadataLangSmith metadata
gen_ai.operation.namestringTelemetryAttributes——
gen_ai.provider.namestringTelemetryAttributes——
gen_ai.request.choice.countint64TelemetryAttributes——
gen_ai.request.frequency_penaltyfloat64TelemetryAttributes——
gen_ai.request.max_tokensint64TelemetryAttributes——
gen_ai.request.modelstringTelemetryAttributes—ls_model_name
gen_ai.request.presence_penaltyfloat64TelemetryAttributes——
gen_ai.request.seedint64TelemetryAttributes——
gen_ai.request.temperaturefloat64TelemetryAttributes——
gen_ai.request.top_pfloat64TelemetryAttributes——
gen_ai.response.finish_reasonsstring[]TelemetryAttributes——
gen_ai.response.modelstringTelemetryAttributes—ls_model_name
gen_ai.usage.input_tokensint64TelemetryAttributes——
gen_ai.usage.output_tokensint64TelemetryAttributes——
gen_ai.usage.total_tokensint64TelemetryAttributes——
goodmem.api_key.authority_modestringApiObservation——
goodmem.api_key.ceiling_omittedbooleanApiObservation——
goodmem.api_key.ceiling_rule_countint64ApiObservation——
goodmem.api_key.expiration_presentbooleanApiObservation——
goodmem.api_key.idstringApiObservationapi_key_idapi_key_id
goodmem.api_key.lifecyclestringApiObservation——
goodmem.api_key.statusstringApiObservation——
goodmem.attributes.dropped_countint64ApiObservation——
goodmem.audit_actor.idstringTelemetryAttributes——
goodmem.authentication.mechanismstringTelemetryAttributes——
goodmem.authentication.outcomestringTelemetryAttributes——
goodmem.authorization.allowed_countint64ApiObservation——
goodmem.authorization.audiencestringApiObservation——
goodmem.authorization.not_allowed_countint64ApiObservation——
goodmem.authorization.operationstringApiObservation——
goodmem.authorization.outcomestringTelemetryAttributes——
goodmem.authorization.rolestringApiObservation——
goodmem.authorization.selectorstringApiObservation——
goodmem.authorization.target_idstringApiObservation——
goodmem.authorization.target_kindstringApiObservation——
goodmem.bootstrap.already_initializedbooleanApiObservation——
goodmem.credential.authority_modestringTelemetryAttributes——
goodmem.decision_model.idstringTelemetryAttributesdecision_model_iddecision_model_id
goodmem.drain.quiescedbooleanApiObservation——
goodmem.effective.interval_msint64ApiObservation——
goodmem.effective.limitint64TelemetryAttributeseffective_limiteffective_limit
goodmem.effective.max_in_flightint64ApiObservation——
goodmem.effective.probe_countint64ApiObservation——
goodmem.effective.timeout_msint64ApiObservation——
goodmem.effective.timeout_secondsint64ApiObservation——
goodmem.embedder.idstringTelemetryAttributesembedder_idembedder_id
goodmem.embedding.adaptive_attempt_countint64TelemetryAttributes—embedding_adaptive_attempt_count
goodmem.embedding.attempt_numberint64TelemetryAttributes——
goodmem.embedding.batch_countint64TelemetryAttributes—embedding_batch_count
goodmem.embedding.configured_dimensionint64TelemetryAttributes—embedding_configured_dimension
goodmem.embedding.contextstringTelemetryAttributesembedding_contextembedding_context
goodmem.embedding.dimensionsint64ApiObservation——
goodmem.embedding.distribution_typestringApiObservation——
goodmem.embedding.input_char_countint64TelemetryAttributes——
goodmem.embedding.output_dimensionint64TelemetryAttributes—embedding_output_dimension
goodmem.embedding.provider_attempt_countint64TelemetryAttributes—embedding_provider_attempt_count
goodmem.embedding.retry_backoff_countint64TelemetryAttributes—embedding_retry_backoff_count
goodmem.embedding.retry_countint64TelemetryAttributes—embedding_retry_count
goodmem.embedding.retry_elapsed_delay_msfloat64TelemetryAttributes—embedding_retry_elapsed_delay_ms
goodmem.embedding.retry_requested_delay_msint64TelemetryAttributes—embedding_retry_requested_delay_ms
goodmem.embedding.split_countint64TelemetryAttributes—embedding_split_count
goodmem.embedding.title_countint64TelemetryAttributes——
goodmem.embedding.vector_typestringTelemetryAttributes——
goodmem.enrollment.already_completedbooleanApiObservation——
goodmem.enrollment.bootstrap_eligiblebooleanApiObservation——
goodmem.enrollment.statusstringApiObservation——
goodmem.entry_surfacestringTelemetryAttributesentry_surfaceentry_surface
goodmem.event_countint64TelemetryAttributes——
goodmem.extension.statusstringApiObservation——
goodmem.extension.typestringApiObservation——
goodmem.failure.categorystringApiObservationfailure_categoryfailure_category
goodmem.failure.expectedbooleanApiObservationfailure_expectedfailure_expected
goodmem.failure.originstringApiObservationfailure_originfailure_origin
goodmem.fusion.score_directionstringTelemetryAttributes—fusion_score_direction
goodmem.hnsw.defaults_usedbooleanTelemetryAttributes—hnsw_defaults_used
goodmem.hnsw.ef_searchint64TelemetryAttributes—hnsw_ef_search
goodmem.hnsw.iterative_scanstringTelemetryAttributes—hnsw_iterative_scan
goodmem.hnsw.max_scan_tuplesint64TelemetryAttributes—hnsw_max_scan_tuples
goodmem.hnsw.scan_mem_multiplierfloat64TelemetryAttributes—hnsw_scan_mem_multiplier
goodmem.inference.completion_start_timestringTracedLLMInference——
goodmem.inference.purposestringTelemetryAttributes——
goodmem.input_countint64TelemetryAttributes——
goodmem.internal_rpc.cancelled_countint64TelemetryAttributes——
goodmem.internal_rpc.countint64TelemetryAttributes——
goodmem.internal_rpc.error_countint64TelemetryAttributes——
goodmem.internal_rpc.partial_countint64TelemetryAttributes——
goodmem.internal_rpc.success_countint64TelemetryAttributes——
goodmem.job.attempt.idint64TelemetryAttributesjob_attempt_idjob_attempt_id
goodmem.job.attempt.numberint64TelemetryAttributesjob_attempt_numberjob_attempt_number
goodmem.job.completion.decisionstringBgJobTracing——
goodmem.job.completion.status_codestringBgJobTracing——
goodmem.job.countint64TelemetryAttributes——
goodmem.job.idint64TelemetryAttributesjob_idjob_id
goodmem.job.memory.resultstringBgJobTracing——
goodmem.job.memory.status_codestringBgJobTracing——
goodmem.job.resultstringBgJobTracing——
goodmem.job.typestringTelemetryAttributesjob_typejob_type
goodmem.license.active_presentbooleanApiObservation——
goodmem.license.reload_statusstringApiObservation——
goodmem.lifecycle.statestringApiObservation——
goodmem.llama_cpp.timings.predicted_msfloat64TelemetryAttributesllama_cpp_predicted_msllama_cpp_predicted_ms
goodmem.llama_cpp.timings.predicted_per_secondfloat64TelemetryAttributesllama_cpp_predicted_per_secondllama_cpp_predicted_per_second
goodmem.llama_cpp.timings.predicted_per_token_msfloat64TelemetryAttributesllama_cpp_predicted_per_token_msllama_cpp_predicted_per_token_ms
goodmem.llama_cpp.timings.prompt_msfloat64TelemetryAttributesllama_cpp_prompt_msllama_cpp_prompt_ms
goodmem.llama_cpp.timings.prompt_per_secondfloat64TelemetryAttributesllama_cpp_prompt_per_secondllama_cpp_prompt_per_second
goodmem.llama_cpp.timings.prompt_per_token_msfloat64TelemetryAttributesllama_cpp_prompt_per_token_msllama_cpp_prompt_per_token_ms
goodmem.llm.budget_sourcestringTelemetryAttributes—llm_budget_source
goodmem.llm.cached_input_tokensint64TelemetryAttributes—llm_cached_input_tokens
goodmem.llm.choice_countint64TelemetryAttributes——
goodmem.llm.chunk_countint64TracedLLMInference——
goodmem.llm.configured_modelstringTelemetryAttributes—llm_configured_model
goodmem.llm.context_limitint64ApiObservation——
goodmem.llm.counts_truncatedbooleanTelemetryAttributes——
goodmem.llm.has_contentbooleanTelemetryAttributes——
goodmem.llm.has_refusalbooleanTelemetryAttributes——
goodmem.llm.idstringTelemetryAttributesllm_idllm_id
goodmem.llm.reasoning_tokensint64TelemetryAttributes—llm_reasoning_tokens
goodmem.llm.sampling_params_appliedbooleanInferenceTracingsampling_params_appliedsampling_params_applied
goodmem.llm.system_message_modestringInferenceTracingsystem_message_modesystem_message_mode
goodmem.llm.time_to_first_output_msfloat64TelemetryAttributes——
goodmem.llm.tool_call_countint64TelemetryAttributes——
goodmem.log_policy.activebooleanApiObservation——
goodmem.log_policy.active_from_presentbooleanApiObservation——
goodmem.log_policy.active_until_presentbooleanApiObservation——
goodmem.log_policy.clause_countint64ApiObservation——
goodmem.log_policy.match_allbooleanApiObservation——
goodmem.mcp.is_errorbooleanTelemetryAttributes——
goodmem.mcp.methodstringTelemetryAttributes——
goodmem.mcp.toolstringTelemetryAttributesmcp_toolmcp_tool
goodmem.memory.idstringTelemetryAttributesmemory_idmemory_id
goodmem.memory.page_image_countint64ApiObservation——
goodmem.memory.page_image_statusstringApiObservation——
goodmem.memory.processing_statusstringApiObservation——
goodmem.mutation.outcomestringApiObservation——
goodmem.observation.kindstringMemoryServiceImpl——
goodmem.ocr.detected_formatstringApiObservation——
goodmem.ocr.processing_msint64ApiObservation——
goodmem.ocr.queue_wait_msint64ApiObservation——
goodmem.ocr.render_msint64ApiObservation——
goodmem.ocr.wall_time_msint64ApiObservation——
goodmem.ollama.timings.predicted_msfloat64TelemetryAttributesollama_predicted_msollama_predicted_ms
goodmem.ollama.timings.predicted_per_secondfloat64TelemetryAttributesollama_predicted_per_secondollama_predicted_per_second
goodmem.ollama.timings.predicted_per_token_msfloat64TelemetryAttributesollama_predicted_per_token_msollama_predicted_per_token_ms
goodmem.ollama.timings.prompt_msfloat64TelemetryAttributesollama_prompt_msollama_prompt_ms
goodmem.ollama.timings.prompt_per_secondfloat64TelemetryAttributesollama_prompt_per_secondollama_prompt_per_second
goodmem.ollama.timings.prompt_per_token_msfloat64TelemetryAttributesollama_prompt_per_token_msollama_prompt_per_token_ms
goodmem.openai.body_completionstringTelemetryAttributes——
goodmem.openai.connect_timeout_msint64TelemetryAttributes——
goodmem.openai.connection_attempt_countint64TelemetryAttributes——
goodmem.openai.connection_duration_msint64TelemetryAttributes——
goodmem.openai.connection_failure_countint64TelemetryAttributes——
goodmem.openai.failure_categorystringTelemetryAttributes——
goodmem.openai.http_attempt_countint64TelemetryAttributes—openai_http_attempt_count
goodmem.openai.http_exchange_countint64TelemetryAttributes——
goodmem.openai.read_timeout_msint64TelemetryAttributes——
goodmem.openai.request_timeout_msint64TelemetryAttributes——
goodmem.openai.retry_backoff_countint64TelemetryAttributes—openai_retry_backoff_count
goodmem.openai.retry_elapsed_delay_msint64TelemetryAttributes—openai_retry_elapsed_delay_ms
goodmem.openai.retry_requested_delay_msint64TelemetryAttributes—openai_retry_requested_delay_ms
goodmem.openai.write_timeout_msint64TelemetryAttributes——
goodmem.operationstringTelemetryAttributesoperationoperation
goodmem.operation.cancelledbooleanFailureTracing——
goodmem.operation.categorystringTelemetryAttributesoperation_categoryoperation_category
goodmem.outcomestringTelemetryAttributesoutcomeoutcome
goodmem.owner.idstringTelemetryAttributes——
goodmem.ping.bytes_receivedint64ApiObservation——
goodmem.ping.bytes_sentint64ApiObservation——
goodmem.ping.error_countint64ApiObservation——
goodmem.ping.http_statusint64ApiObservation——
goodmem.ping.last_probe_okbooleanApiObservation——
goodmem.ping.request_countint64ApiObservation——
goodmem.ping.rtt_msfloat64ApiObservation——
goodmem.ping.target_kindstringApiObservation——
goodmem.ping.timeout_countint64ApiObservation——
goodmem.postprocessbooleanTelemetryAttributes——
goodmem.postprocess.chronological_resortbooleanTelemetryAttributes—chronological_resort
goodmem.postprocess.fallbackbooleanTelemetryAttributes—postprocess_fallback
goodmem.postprocess.filter_appliedbooleanTelemetryAttributes—postprocess_filter_applied
goodmem.postprocess.kindstringTelemetryAttributespostprocess_kindpostprocess_kind
goodmem.postprocess.max_resultsint64TelemetryAttributes—postprocess_max_results
goodmem.postprocess.record_projectionstringTelemetryAttributes——
goodmem.postprocess.relevance_thresholdfloat64TelemetryAttributes—relevance_threshold
goodmem.postprocess.rerank_attemptedbooleanTelemetryAttributes—rerank_attempted
goodmem.postprocess.rerank_succeededbooleanTelemetryAttributes—rerank_succeeded
goodmem.postprocess.synthesis_attemptedbooleanTelemetryAttributes—synthesis_attempted
goodmem.postprocess.synthesis_succeededbooleanTelemetryAttributes—synthesis_succeeded
goodmem.principal.idstringTelemetryAttributesprincipal_idprincipal_id
goodmem.principal.typestringTelemetryAttributes——
goodmem.provider.api_dialectstringApiObservation——
goodmem.provider.backendstringApiObservation——
goodmem.provider.modalitiesstring[]ApiObservation——
goodmem.provider.response.compute_charactersint64TelemetryAttributes——
goodmem.provider.response.compute_characters_totalint64TelemetryAttributesprovider_response_compute_characters_totalprovider_response_compute_characters_total
goodmem.provider.response.compute_time_max_msint64TelemetryAttributesprovider_response_compute_time_max_msprovider_response_compute_time_max_ms
goodmem.provider.response.compute_time_msint64TelemetryAttributes——
goodmem.provider.response.compute_typestringTelemetryAttributesprovider_compute_typeprovider_compute_type
goodmem.provider.response.countint64TelemetryAttributesprovider_response_countprovider_response_count
goodmem.provider.response.events_droppedint64TelemetryAttributesprovider_response_events_droppedprovider_response_events_dropped
goodmem.provider.response.inference_time_max_msint64TelemetryAttributesprovider_response_inference_time_max_msprovider_response_inference_time_max_ms
goodmem.provider.response.inference_time_msint64TelemetryAttributes——
goodmem.provider.response.queue_time_max_msint64TelemetryAttributesprovider_response_queue_time_max_msprovider_response_queue_time_max_ms
goodmem.provider.response.queue_time_msint64TelemetryAttributes——
goodmem.provider.response.sequenceint64TelemetryAttributes——
goodmem.provider.response.tokenization_time_max_msint64TelemetryAttributesprovider_response_tokenization_time_max_msprovider_response_tokenization_time_max_ms
goodmem.provider.response.tokenization_time_msint64TelemetryAttributes——
goodmem.provider.response.total_time_max_msint64TelemetryAttributesprovider_response_total_time_max_msprovider_response_total_time_max_ms
goodmem.provider.response.total_time_msint64TelemetryAttributes——
goodmem.provider.typestringTelemetryAttributesprovider_typeprovider_type
goodmem.proxy.upstream.status_codeint64TelemetryAttributes——
goodmem.purge.attempt_countint64ApiObservation——
goodmem.purge.dry_runbooleanApiObservation——
goodmem.purge.job_countint64ApiObservation——
goodmem.purge.reference_countint64ApiObservation——
goodmem.request.activation_presentbooleanApiObservation——
goodmem.request.api_dialectstringApiObservation——
goodmem.request.authority_modestringApiObservation——
goodmem.request.ceiling_rule_countint64ApiObservation——
goodmem.request.chunk_length_measurementstringApiObservation——
goodmem.request.chunk_overlapint64ApiObservation——
goodmem.request.chunk_sizeint64ApiObservation——
goodmem.request.chunking_strategystringApiObservation——
goodmem.request.client_provided_idbooleanApiObservation——
goodmem.request.content_bytesint64ApiObservation——
goodmem.request.context_countint64ApiObservation——
goodmem.request.context_limitint64ApiObservation——
goodmem.request.continuation_presentbooleanApiObservation——
goodmem.request.control_actionstringApiObservation——
goodmem.request.credential_generation_modestringApiObservation——
goodmem.request.cutoff_presentbooleanApiObservation——
goodmem.request.dimensionsint64ApiObservation——
goodmem.request.distribution_typestringApiObservation——
goodmem.request.dpiint64ApiObservation——
goodmem.request.dry_runbooleanApiObservation——
goodmem.request.embedder_countint64ApiObservation——
goodmem.request.end_pageint64ApiObservation——
goodmem.request.expiration_presentbooleanApiObservation——
goodmem.request.extension_typestringApiObservation——
goodmem.request.extract_page_imagesbooleanApiObservation——
goodmem.request.fetch_memorybooleanApiObservation——
goodmem.request.fetch_memory_contentbooleanApiObservation——
goodmem.request.field_countint64ApiObservation——
goodmem.request.fieldsstring[]ApiObservation——
goodmem.request.filter_presentbooleanApiObservation——
goodmem.request.formatstringApiObservation——
goodmem.request.idstringTelemetryAttributesrequest_idrequest_id
goodmem.request.include_contentbooleanApiObservation——
goodmem.request.include_credentialsbooleanApiObservation——
goodmem.request.include_deletedbooleanApiObservation——
goodmem.request.include_enrollment_summarybooleanApiObservation——
goodmem.request.include_markdownbooleanApiObservation——
goodmem.request.include_processing_historybooleanApiObservation——
goodmem.request.include_raw_jsonbooleanApiObservation——
goodmem.request.include_revokedbooleanApiObservation——
goodmem.request.interval_msint64ApiObservation——
goodmem.request.item_countint64ApiObservation——
goodmem.request.job_statusesstring[]ApiObservation——
goodmem.request.key_lifecyclestringApiObservation——
goodmem.request.key_statusstringApiObservation——
goodmem.request.key_viewstringApiObservation——
goodmem.request.label_countint64ApiObservation——
goodmem.request.label_selector_countint64ApiObservation——
goodmem.request.label_update_strategystringApiObservation——
goodmem.request.limitint64TelemetryAttributesrequested_limitrequested_limit
goodmem.request.max_in_flightint64ApiObservation——
goodmem.request.media_typestringApiObservation——
goodmem.request.message_countint64ApiObservation——
goodmem.request.min_chunk_sizeint64ApiObservation——
goodmem.request.modalitiesstring[]ApiObservation——
goodmem.request.name_filter_presentbooleanApiObservation——
goodmem.request.new_owner_idstringApiObservation——
goodmem.request.operationstringTelemetryAttributesrequest_operationrequest_operation
goodmem.request.operation.categorystringTelemetryAttributesrequest_operation_categoryrequest_operation_category
goodmem.request.owner_idstringApiObservation——
goodmem.request.page_indexint64ApiObservation——
goodmem.request.payload_size_bytesint64ApiObservation——
goodmem.request.payload_typestringApiObservation——
goodmem.request.payload_variantstringApiObservation——
goodmem.request.postprocessbooleanApiObservation——
goodmem.request.probe_countint64ApiObservation——
goodmem.request.processing_statusstringApiObservation——
goodmem.request.provider_backendstringApiObservation——
goodmem.request.provider_typestringApiObservation——
goodmem.request.resource_idstringApiObservation——
goodmem.request.rotate_existingbooleanApiObservation——
goodmem.request.selector_kindstringApiObservation——
goodmem.request.sequence_limitint64ApiObservation——
goodmem.request.space_countint64ApiObservation——
goodmem.request.start_pageint64ApiObservation——
goodmem.request.subject_principal_idstringApiObservation——
goodmem.request.target_kindstringApiObservation——
goodmem.request.timeout_msint64ApiObservation——
goodmem.request.timeout_secondsint64ApiObservation——
goodmem.request.wait_for_quiescebooleanApiObservation——
goodmem.requested_sizeint64TelemetryAttributes—requested_size
goodmem.rerank.cohere.search_unitsfloat64TelemetryAttributescohere_search_unitscohere_search_units
goodmem.reranker.idstringTelemetryAttributesreranker_idreranker_id
goodmem.resource.deletedbooleanApiObservation——
goodmem.resource.idstringTelemetryAttributesresource_idresource_id
goodmem.resource.kindstringTelemetryAttributesresource_kindresource_kind
goodmem.resource.revokedbooleanApiObservation——
goodmem.response.message_countint64ApiObservation——
goodmem.result.capability_countint64ApiObservation——
goodmem.result.content_bytesint64ApiObservation——
goodmem.result.countint64TelemetryAttributesresult_countresult_count
goodmem.result.deleted_countint64ApiObservation——
goodmem.result.dpiint64ApiObservation——
goodmem.result.embedder_countint64ApiObservation——
goodmem.result.failure_countint64TelemetryAttributesfailure_countfailure_count
goodmem.result.informational_status_countint64ApiObservation——
goodmem.result.media_typestringApiObservation——
goodmem.result.next_page_presentbooleanApiObservation——
goodmem.result.page_indexint64ApiObservation——
goodmem.result.status_count.<code>int64ApiObservation——
goodmem.result.success_countint64TelemetryAttributessuccess_countsuccess_count
goodmem.result_countint64TelemetryAttributesresult_countresult_count
goodmem.retrieval.abstract_reply_countint64TelemetryAttributes——
goodmem.retrieval.accessible_space_countint64TelemetryAttributesspace_countspace_count
goodmem.retrieval.boundary_countint64TelemetryAttributes——
goodmem.retrieval.context_countint64TelemetryAttributes——
goodmem.retrieval.effective_top_kint64TelemetryAttributeseffective_top_keffective_top_k
goodmem.retrieval.fetch_contentbooleanTelemetryAttributes——
goodmem.retrieval.fetch_memorybooleanTelemetryAttributes——
goodmem.retrieval.filter_countint64TelemetryAttributes——
goodmem.retrieval.memory_definition_countint64TelemetryAttributes——
goodmem.retrieval.required_embedder_countint64TelemetryAttributes——
goodmem.retrieval.result_item_countint64TelemetryAttributesresult_countresult_count
goodmem.retrieval.space_idsstring[]TelemetryAttributesspace_idsspace_ids
goodmem.retrieval.space_ids_truncatedbooleanTelemetryAttributesspace_ids_truncatedspace_ids_truncated
goodmem.retrieval.status_codesstring[]TelemetryAttributes——
goodmem.retrieval.status_countint64TelemetryAttributes——
goodmem.rpc.status_codestringApiObservationrpc_status_namerpc_status_name
goodmem.server.lifecycle_statestringTelemetryAttributes——
goodmem.space.idstringTelemetryAttributesspace_idspace_id
goodmem.space_countint64TelemetryAttributes——
goodmem.status_codestringFailureTracing——
goodmem.streamingbooleanTracedLLMInference—streaming
goodmem.target.principal_idstringApiObservation——
goodmem.target.user_idstringApiObservation——
goodmem.telemetry.dropped_field_countint64TelemetryAttributes——
goodmem.trace.namestringTraceAttribution——
goodmem.trace.ownedbooleanTelemetryAttributes——
goodmem.vector.dimensionint64TelemetryAttributes—vector_dimension
goodmem.vector.metricstringTelemetryAttributes—vector_metric
goodmem.vllm.timings.generation_time_msfloat64TelemetryAttributesvllm_generation_time_msvllm_generation_time_ms
goodmem.vllm.timings.mean_itl_msfloat64TelemetryAttributesvllm_mean_itl_msvllm_mean_itl_ms
goodmem.vllm.timings.queue_time_msfloat64TelemetryAttributesvllm_queue_time_msvllm_queue_time_ms
goodmem.vllm.timings.time_to_first_token_msfloat64TelemetryAttributesvllm_time_to_first_token_msvllm_time_to_first_token_ms
goodmem.vllm.timings.tokens_per_secondfloat64TelemetryAttributesvllm_tokens_per_secondvllm_tokens_per_second

On this page