> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Weave SDK releases

> View release notes for the Weave Python SDK (`weave` package), including new features, bug fixes, and performance improvements by version.

This page includes release notes for the [W\&B Weave Python SDK](https://pypi.org/project/weave/) (`weave` package). For the Weights & Biases Python SDK (`wandb` package), see [Weights & Biases SDK releases](https://docs.coreweave.com/release-notes/sdk-releases.md). Release packages and per-commit history are on [GitHub Releases for `wandb/weave`](https://github.com/wandb/weave/releases).

> [!NOTE]
>
> These entries summarize user-facing SDK and trace server changes, and omit details about internal-only test, CI, and refactor work. For every merged change, see the GitHub release entry for that tag. If a tag has no GitHub release entry, compare it with the previous tag, for example [`v0.53.10...v0.53.11`](https://github.com/wandb/weave/compare/v0.53.10...v0.53.11).

**0.53.12**

October 9, 2026

## Changed

* `import weave` no longer loads `weave.trace_server`. Code that accesses `weave.trace_server` as an attribute after only `import weave` raises `AttributeError`. Import the module explicitly instead. Existing `weave.trace_server` import paths continue to work.
* `weave` supports `opentelemetry-exporter-otlp-proto-http` 1.45 and later again. The 0.53.11 version cap has been removed.
* Project retention applies to new agent spans and to the chat messages copied from them. Spans and messages that were stored earlier keep their existing expiry.
* Project stats report agent span storage separately, as `spans_storage_size_bytes`. `trace_storage_size_bytes` continues to count calls only. Spans stored before span stats were introduced in 0.53.0 aren't counted.
* Agent span storage no longer expands the JSON payload of a known semantic convention attribute, such as `gen_ai.tool.call.arguments`, into one custom attribute per field. Spans that were already stored keep their custom attributes, and filters on payload-derived attributes no longer match new spans.
* Searching call payloads with filters reads less data, because the filtered page is evaluated once instead of three times.
* Agent span lookups by span ID consider only the matching trace, instead of every trace in the project.
* Vertex AI is no longer available as a model provider in the Playground.
* Updated model cost data.

## Fixed

* Fixed incomplete usage and cost totals from `/calls/usage` when the requested traces contained more calls than the request's `limit` field (default 10,000). Each trace is now aggregated in full, and a single trace that exceeds the limit raises `RequestTooLarge`.

**0.53.11**

September 25, 2026

## Changed

* Conversation SDK spans identify the SDK through the `wandb.sdk.name`, `wandb.sdk.version`, and `wandb.sdk.language` OpenTelemetry resource attributes.

## Fixed

* Fixed `weave.init()` failing with `AttributeError: 'OTLPSpanExporter' object has no attribute '_session'` after the release of `opentelemetry-exporter-otlp-proto-http` 1.45.0. `weave` now requires a version earlier than 1.45.
* Sibling agent spans that share a start time are ordered by the earliest end time.

**0.53.10**

September 24, 2026

## Added

* Agent span queries and stats accept `insight_filters` for filtering by intent category, failure category, failure severity, intent and failure clusters, and intent sentiment.
* Trace server support for routing Playground chat completions to a Dedicated Inference connection.

## Changed

* The SDK uses the generated trace server client by default. To use the previous client, set `WEAVE_USE_STAINLESS_SERVER=false`.
* Token totals that the provider reports, including totals of zero, are preserved.

## Fixed

* Fixed Google GenAI calls receiving traced Weave values instead of the underlying values.
* Gemini content parts keep their original order.
* Agent chat messages include the span's `error_type` and `status_message`.
* Illegal query arguments return `400` instead of `403`.

**0.53.9**

September 10, 2026

## Changed

* The opt-in generated trace server client (`WEAVE_USE_STAINLESS_SERVER=true`) covers the remaining trace server routes and the `calls_complete` write path.
* Updated model provider and cost data.

## Fixed

* When the startup server info request fails, `weave.init()` reports the underlying cause, such as a TLS certificate error, instead of a generic message.
* With the generated trace server client, `WEAVE_INSECURE_DISABLE_SSL` and the SDK request timeout take effect, and parallel chunked table uploads turn on.
* With the generated trace server client, permanent `4xx` errors fail on the first response and name the lost calls instead of being retried.

**0.53.8**

September 3, 2026

## Added

* Federated identity support. When `WANDB_IDENTITY_TOKEN_FILE` points to a JWT, the SDK exchanges it for an access token and caches the token in the credentials file (`WANDB_CREDENTIALS_FILE`), as the `wandb` SDK does.

## Changed

* Updated model cost data.

**0.53.7**

August 27, 2026

## Added

* `EvaluationLogger` accepts `trace_scores`. Set `trace_scores=False` to record score values on `Evaluation.predict_and_score` without creating a separate call for each score. The default is `True`.

## Changed

* The trace server requires `clickhouse-connect` 1.6.

## Fixed

* Fixed `ImportError` when importing the trace server after installing `weave[trace_server]`. The extra now declares every package that the trace server imports.
* Fixed unnamed evaluations failing to save when the dataset name reached the 128-character name limit, which gave the evaluation the same object ID as its dataset.
* Evaluation summaries keep rows that produced no score.
* ClickHouse stream failures return `502`, and the trace server reads structured ClickHouse error codes.

**0.53.6**

August 13, 2026

## Added

* A `@weave.op` call links to the agent spans it produces, and a call records the agent span that invoked it.
* `record_error()` on Conversation SDK `Tool`, `LLM`, `SubAgent`, and `Turn` spans records an exception without ending the span.
* The Claude Agent SDK integration traces subagents.

## Fixed

* Fixed streaming chat completions for Playground and Inference closing before the stream is consumed.
* Fixed Claude Agent SDK async-iterable queries not being traced per turn, and fixed turns being attributed to the wrong async query.
* Fixed an `UnboundLocalError` in the MCP `read_resource` wrapper.
* Fixed duplicate OpenAI Agents SDK telemetry.
* Fixed the mapping of OpenAI cache write tokens.
* Traces show the details of OpenTelemetry exception events.
* Latency stats ignore unfinished calls, and root usage stats include OpenTelemetry spans.
* Cost timestamps are generated in UTC.
* Fixed new model costs not being added when the database schema was already current.

**0.53.4**

July 31, 2026

## Added

* `WeaveClient.register_custom_runtime()` registers or replaces a custom runtime, which is an OpenAI-compatible endpoint with a list of runtime IDs. `weave.CustomRuntimeID` sets a token limit for an individual ID.
* Conversation SDK turns record output messages through `Turn.output_messages` and the `output_messages` argument of `Turn.record()`.
* The Claude Agent SDK integration traces image prompts.
* Trace file storage on Azure supports workload identity through `DefaultAzureCredential` when no connection string or account key is configured.
* Cost data for Claude Opus 5.

## Changed

* The Claude Agent SDK OpenTelemetry integration is built on the Conversation SDK.
* The trace server logs and ignores unknown request fields instead of rejecting the request.

## Fixed

* Cost queries are scoped to the requested project.
* The trace server validates field qualifiers in queries.
* Custom provider names are preserved in model selectors.

**0.53.3**

July 31, 2026

## Added

* `WeaveClient.add_cost()` accepts cache read and cache creation token prices, and `query_costs()` returns them.
* The completions API accepts `reasoning_effort`.
* `AgentDashboard` object type for saving, loading, and forking agent dashboard configurations.
* Feedback queries return `total_count`.
* Agent spans stamped with evaluation metadata link to evaluation results.

## Fixed

* Fixed calls queries failing with `400` because of a collision between boolean and integer parameters.
* OpenAI `cached_tokens` values in OpenTelemetry spans count as cache read tokens.
* Traces of Serverless Inference calls made through the OpenAI SDK show the requested model.
* Normalized cached input tokens from the Claude Agent SDK integration.

**0.53.2**

July 16, 2026

## Added

* `WeaveClient.get_agent_span_feedback()`, `get_agent_turn_feedback()`, and `get_agent_conversation_feedback()` return feedback queries for agent spans, turns, and conversations. Reactions added through them appear as thumbs in the agent view.
* `SubAgent.start_subagent()` nests a sub-agent under another sub-agent.
* Server-side sampling for agent spans. The existing call sampling settings, such as `WEAVE_INGEST_SAMPLE_RATE`, also apply to spans, and traces with `weave.eval.*` attributes are always kept.
* The trace server stores base64 and data URL content from agent OpenTelemetry exports as content objects, as it does for SDK traces.
* Object delete responses report the deleted versions.
* Cost and provider data for new models, including GPT-5.6.

## Changed

* `Turn` and `SubAgent` factory methods are renamed to `start_llm()`, `start_tool()`, and `start_subagent()`. The old `llm()`, `tool()`, and `subagent()` methods still work but emit a `DeprecationWarning`.
* Improved read and write performance for `calls_complete` storage.

## Fixed

* Direct `openai` calls are traced again when `use_otel_v2` is on, which is the default. From 0.52.43 through 0.53.1, direct calls weren't traced unless you called `weave.integrations.patch_openai()`.
* Fixed child spans detaching from their parent when they start after the parent's `with` block exits, including from another thread.
* Fixed missing Bedrock cache tokens in streaming Converse responses.
* Fixed missing costs for Serverless Inference model calls.
* Summary `input_tokens` include Anthropic prompt cache tokens.
* Client-side digests are stable for dictionaries with non-string keys.
* Support for `google-adk` 2.3.0 and later.
* Fixed recursion errors when converting refs in deeply nested payloads.
* Request validation failures return `400` instead of `500`.
* ClickHouse migrations are idempotent and recover automatically from partial runs.

**0.53.1**

July 2, 2026

## Added

* `Conversation` accepts `agent_id`, `agent_description`, and `agent_version` defaults, which each turn inherits. `start_turn()` accepts the same arguments.
* Evaluation result summaries include a predict-only cost total.
* The `weave-instrument` agent skill in the `wandb/weave` repository helps a coding agent add Weave tracing to a Python or TypeScript codebase.
* Cost and provider data for new models, including Claude Sonnet 5.

## Changed

* `add_event()` on Conversation SDK spans is deprecated. Use `set_attributes()` instead.
* The `trace_server` extra no longer installs `ddtrace`.
* Attachment uploads run in parallel on all writes.

## Fixed

* Agent traces go to the active project when you call `weave.init()` again.
* Completion error payloads keep the provider's HTTP status code.
* Negative JSON path array indices return `422` instead of `502`.

**0.53.0**

July 2, 2026

## Added

* `WeaveClient` methods for reading agent data, including `get_agents()`, `get_agent_versions()`, `get_agent_spans()`, `get_agent_turn()`, `get_agent_turns()`, and `get_agent_span_stats()`.
* `Turn.record()` and `SubAgent.record()` set many fields in one call, and `log_turn()` accepts `agent_id`, `agent_description`, and `agent_version`.
* `start_conversation()`, `log_turn()`, and `log_conversation()` accept custom `attributes`, which are stamped on every span of the conversation.
* Turn and sub-agent spans record system instructions.
* OpenTelemetry-native exporter for the OpenAI Realtime integration, selected by default.
* Evaluation results support match-any and match-all filtering across evaluations, and filtering on inputs.
* Evaluation result summaries include a predict-only token total.
* Agent span and stats APIs include query-time costs.

## Changed

* The Session SDK is renamed the Conversation SDK. Use `Conversation`, `weave.start_conversation()`, `weave.end_conversation()`, `weave.get_current_conversation()`, and `weave.log_conversation()`, or the `weave.conversation` module. The session names still work but emit a `DeprecationWarning`, and `session_id` and `session_name` arguments map to `conversation_id` and `conversation_name`.
* Calls from declarative evaluations carry evaluation metadata, matching `EvaluationLogger`.
* Improved query performance for evaluation results and call stats.

## Fixed

* Fixed the DSPy, GEPA, and LangChain integrations publishing a new object version on every run because `repr()` output included memory addresses.
* `weave` installs alongside `google-adk`.
* Fixed `dictify` getting stuck in a reference cycle.
* `LLMAsAJudgeScorer` no longer includes op methods in its published payload.
* Fixed model ID detection for Bedrock inference profile ARNs with the invoke API.
* Clearer error when you don't have permission to access a project.
* The trace server returns `400` instead of `500` for bad query parameters and malformed annotation specs, and invalid-field errors list the allowed fields.

**0.52.43**

June 15, 2026

## Added

* `set_attributes()` and `add_event()` on Session SDK `Turn`, `LLM`, `Tool`, and `SubAgent` spans.
* Integrations record integration metadata on the calls and spans they create.
* `allow_unsafe_custom_obj_decode` setting, `True` by default. Server-side evaluation workers turn it off, so they decode data-only types such as images and audio but refuse ops and other code-bearing objects.
* Cost and provider data for new models, including Claude Fable 5.

## Changed

* OpenTelemetry-based integrations are on by default (`use_otel_v2`, `WEAVE_USE_OTEL_V2`). In this mode, direct `openai` calls aren't traced automatically. To trace them, call `weave.integrations.patch_openai()` or set `WEAVE_USE_OTEL_V2=false`.
* Publishing an object under a name that an object of a different type already uses fails with a `400` error.
* `import weave` is faster because `jsonschema` is imported only when needed.
* Removed the SQLite trace server.

## Fixed

* Fixed creating monitors by op name, which the documentation examples use.
* `WEAVE_INSECURE_DISABLE_SSL` takes effect when you set it after `import weave`.
* Fixed `flush()` stalling on unpaired eager calls when `calls_complete` is on.
* Fixed `PaginatedIterator` instances sharing one page cache.
* Streaming calls keep caller-set `started_at` and `ended_at` values.
* Fixed Bedrock streaming of tool-use and reasoning deltas.
* Fixed WAV detection for in-memory audio when `libmagic` returns `application/octet-stream`.
* Fixed scorer `auto_summarize` for mixed `BaseModel` and `WeaveDict` results.
* OpenTelemetry spans with an all-zero `parent_span_id` are treated as root spans.
* The trace server returns `4xx` errors instead of `500` for unsupported or unselectable fields.

**0.52.42**

June 2, 2026

## Added

* `WeaveClient` methods for managing annotation queues, including `create_annotation_queue()`, `add_calls_to_annotation_queue()`, and `get_annotation_queue()`.
* Preliminary Google ADK integration that traces agent spans automatically through OpenTelemetry.
* OpenTelemetry-based integrations for the OpenAI Agents SDK and the Claude Agent SDK.
* Agent span usage includes cache creation and cache read input tokens, and reasoning output tokens.
* Trace server `rescore` endpoint that reruns scorers against an existing evaluation run and creates a new evaluation run.
* Cost and provider data for new models, including Claude Opus 4.8.

## Changed

* The `use_calls_complete` setting defaults to `True`. The SDK pairs each call's start and end and writes the call as one record.
* The Session SDK respects `WEAVE_DISABLED`, `WEAVE_REDACT_PII`, `WEAVE_CAPTURE_CLIENT_INFO`, and `WEAVE_CAPTURE_SYSTEM_INFO`.

## Fixed

* `str(ref)` returns the Weave URI, so leaderboard columns built with `str(ref)` match evaluation results.
* Fixed `LLM.reasoning` appearing in output messages when `include_content=False`.
* Project trace storage size includes OpenTelemetry span data.
* Feedback `created_at` timestamps are read as UTC.
* The trace server validates image URLs before fetching them for image completions.
* Azure file storage no longer overwrites existing blobs.

**0.52.41**

May 28, 2026

## Added

* Spans that GenAI integrations emit inside an evaluation's `predict_and_score` call link to that evaluation automatically.
* Type-cast inference for dynamic JSON filters also applies to feedback queries.

## Changed

* Every object publish writes an explicit `latest` alias. Republishing existing content makes it the `latest` version, and when you delete the `latest` version, `latest` falls back to the next surviving version.
* The MCP integration is renamed FastMCP. `weave.integrations.patch_mcp()` is now `patch_fastmcp()`, the `weave.integrations.mcp` module is now `weave.integrations.fastmcp`, and the `mcp` extra is now `fastmcp`.
* The OTLP exporter respects `WEAVE_INSECURE_DISABLE_SSL`.

## Fixed

* Fixed `import weave` failing with a protobuf `TypeError` when `wandb` was installed before `weave`. `weave` now requires the `opentelemetry` packages at version 1.28.0 or later.
* Saved views persist `expand_columns`.
* Failed file uploads are no longer cached, so a later upload of the same file is retried.

**0.52.40**

May 14, 2026

> [!WARNING]
>
> This release is yanked on PyPI because of a protobuf-related issue. Use 0.52.41 or later, which fixes `import weave` failing when `wandb` is installed first.

## Added

* Call filters infer type casts for dynamic JSON fields under `inputs`, `output`, `attributes`, and `summary` from the comparison value, so many numeric and boolean comparisons no longer need `$convert`.
* Trace server support for feedback on agent spans, turns, and conversations.

## Changed

* Reduced per-op overhead when tracing async functions.
* The ClickHouse trace server uses asynchronous inserts by default.

## Fixed

* Fixed `$not` filters around `$contains`, `$eq`, or `$in` on large fields returning too few calls.
* Fixed a potential memory leak in the streaming accumulator.

**0.52.39**

May 11, 2026

> [!WARNING]
>
> This release is yanked on PyPI because of a protobuf-related issue. Use 0.52.41 or later, which fixes `import weave` failing when `wandb` is installed first.

## Added

* The Session SDK emits spans that follow the OpenTelemetry GenAI semantic conventions, and adds `weave.start_tool()`, `weave.start_subagent()`, and `MediaAttachment`.
* Trace server storage and queries for GenAI agent spans.
* Cost and provider data for new models, including Grok 4.3.

## Changed

* `weave` depends on `opentelemetry-api`, `opentelemetry-sdk`, and `opentelemetry-exporter-otlp-proto-http`.
* `weave.init()` is faster because it requests server info only once.
* Setting `WANDB_ERROR_REPORTING=false` turns off the Weave SDK's Sentry error reporting.

## Fixed

* `EvaluationLogger` sends its root call's start immediately, so the evaluation appears in the UI before `log_summary()` runs.
* Fixed flushing returning before chained background work finished.
* Fixed handling of newer OpenAI Agents SDK span types.
* Fixed handling of invalid UTF-8 surrogates in trace data.

**0.52.38**

May 5, 2026

## Added

* `weave.link_prompt_to_registry()` and the matching `WeaveClient` method link a published prompt or object version to a registry.
* Session SDK API surface for manually instrumenting agents: `Session`, `Turn`, `LLM`, `Tool`, and `SubAgent`, plus functions such as `weave.start_session()` and `weave.start_turn()`. In this release the API is a stub that doesn't emit spans.
* Preliminary GEPA integration that logs traces to Weave automatically, installed with the `gepa` extra.
* The `/eval_results` API supports server-side sorting, filtering, and pagination, and resolves dataset-backed evaluation inputs.
* Cost and provider data for new models, including GPT-5.5.

## Changed

* `wandb` is an optional dependency again.
* ClickHouse migrations on replicated clusters use `Atomic` databases with `ReplicatedMergeTree` tables and `ON CLUSTER` statements instead of the `Replicated` database engine.

## Fixed

* The SDK retries object reads that fail with `404` because of replica lag.
* Fixed OpenAI Agents SDK `responses.create` calls not linking to agent traces.
* Fixed error handling when unwrapping raw OpenAI responses.

**0.52.37**

April 17, 2026

## Added

* OpenTelemetry integrations follow the latest semantic conventions.
* Cost calculations and provider integrations include cache token usage.

## Changed

* Improved performance for some call queries by optionally skipping a nested subquery.
* `ClassifierMonitor` is exported from the top-level `weave` package.
* The calls API accepts an optional `query` parameter for richer filtering.

## Fixed

* Fixed the evaluation results API SQL for some filter combinations.
* Fixed a bug where the TypeScript SDK could drop the URL scheme from `WANDB_BASE_URL`.
* Fixed a bug where calls with multiple feedback rows could appear multiple times in list results.
* Fixed ISO-8601 timestamp handling for ClickHouse-backed queries.
* Fixed distributed ClickHouse mutations that incorrectly appended a `_local` suffix to table names.
* Fixed missing spans when tracing OpenAI Agents SDK flows.
* Fixed Google GenAI tracing when responses include non-text parts.
* Fixed path sanitization for in-memory trace file artifacts and provider hostname handling in HTTP clients.

**0.52.36**

April 1, 2026

## Added

* Call queries can resolve human-readable usernames.
* `ref.get()` works without explicitly initializing the client in some flows.
* APIs and storage paths for text-based evaluation results, including improved handling of large evaluation sets.

## Changed

* LiteLLM is pinned for compatibility with bundled integrations.
* Moonshot is available as a model provider.
* Underlying write-ahead logging infrastructure improves durability of trace writes.

## Fixed

* Fixed a bug where abandoning a streaming generator could surface `GeneratorExit` incorrectly.
* Fixed deserialization when stored objects include extra metadata fields.
* Fixed feedback filters when a call has multiple feedback rows.
* Fixed SQLite-backed call cost tracking and invalid `trace_id` handling in batch upserts.
* Improved ClickHouse migration behavior, including retries on transient errors and clearer migrator exit status.
* Fixed a bug where evaluation runs with more than 1000 calls could fail to load for prediction and scoring.

**0.52.35**

March 19, 2026

## Added

* Write-ahead log support for trace ingestion.
* Feedback statistics queries for analytics over feedback data.

## Changed

* `Ref.uri` can be read as a property (`ref.uri`) without calling `ref.uri()`.
* You can configure the maximum size of debounced scoring history via environment variables.

## Fixed

* Fixed ClickHouse casting for negative numeric filter values.
* Fixed replicated database engine errors during on-cluster migrations.
* Fixed `DelegatingTraceServerMixin` not forwarding some `ServiceInterface` methods.
* Fixed retries when calling the W\&B API during `weave.init()`.
* Fixed a bug where `EvaluationLogger` could crash when `WEAVE_DISABLED` is set.
* Fixed `RefJSONEncoder` edge cases and classmethod instantiation for subclasses.

**0.52.33**

March 12, 2026

## Added

* Python SDK methods and HTTP models for object tags and aliases.
* Instrumentation for the OpenAI Realtime API, including tool calls plus optional audio, text, and voice capture (see the TypeScript examples in the upstream release notes).

## Fixed

* Fixed accumulation of Anthropic streaming completions in traces.
* Fixed authenticated `PUT` requests in `RemoteHTTPTraceServer`.
* Fixed cost query handling for `calls_complete` projections.

**0.52.31**

March 10, 2026

## Added

* Trace server support for tags and aliases on stored objects.
* Claude Agents tracing integration.
* Timestamps and time-to-first-token metrics for Realtime sessions.
* Monitors can use merged scorers.

## Changed

* Improved OpenTelemetry performance with a cross-request operation reference cache.

## Fixed

* Fixed multiple issues in cost query construction, including escaping of internal fields and distributed ClickHouse setups.
* Fixed LangChain integration handling for Pydantic v2 `Run` objects.
* Fixed edge cases in prediction and scorer resolvers when inputs or metadata are missing.
* Fixed Vertex AI text accumulation and thread visibility in `calls_complete` queries.

**0.52.30**

March 10, 2026

## Added

* Score backfill API for recomputing stored scores.
* Gemini request tracking in the TypeScript SDK.

## Changed

* Sharded distributed calls tables by `trace_id` or `project_id` for better query performance.
* Simplified `calls_complete` query plans for lower latency.

## Fixed

* Fixed a bug where Gemini media could fail to render in the Weave UI.
* OpenTelemetry batch inserts now use async ClickHouse inserts.
* Fixed `NO_PROXY` handling in HTTP clients.
* Fixed entity versus team naming in some error messages.

**0.52.29**

February 27, 2026

## Added

* Usage APIs expose metadata for unfinished calls.
* Optional `python-magic` integration for richer MIME detection.
* Realtime threads participate in usage summaries.
* Schema support for tags and aliases on Weave objects.
* Structured `eval_results` query API for evaluation tables.

## Changed

* Improved indexing by storing timestamps as strings in ClickHouse.
* Reduced duplicate work during batched file creation on call upsert.

## Fixed

* Fixed a bug where generators did not respect configured sampling rates.
* Fixed buffering so streams flush immediately when a call ends.
* Fixed sort-query index errors and deterministic JSON serialization for digest computation.
* Fixed OpenTelemetry display names, `make_safe_name` handling, and LangChain serialization for Pydantic models.

**0.52.28**

February 14, 2026

## Added

* OpenAI Realtime tracing is generally available.

## Fixed

* Fixed the SDK requiring an OpenTelemetry package that it doesn't need.

**0.52.27**

February 13, 2026

## Added

* OpenTelemetry export requests accept a run ID for each set of resource spans, which links the spans to a run.
* You can now use the ORM’s query expressions to filter values with less-than and less-than-or-equal comparisons. This makes it easier to write date and range queries more directly, without needing to combine `$gt` with `$not`.
* New OpenTelemetry projects write directly into the `calls_complete` table.
* Calls returned by `get_calls()` include their run and storage fields, such as `wb_run_id`, `wb_run_step`, and `storage_size_bytes`.
* Vertex AI is available as a model provider in the Playground.

## Changed

* Improved performance for table scans and call statistics queries.
* Updated model cost data, including Claude Opus 4.6.

## Fixed

* Fixed filtering calls by thread ID, including cases where filters were incorrectly optimized away.
* Annotation queue state updates are idempotent.
* Fixed a bug where `weave.finish()` didn't always flush pending client data.
* Fixed type hints being lost on methods decorated with `@weave.op`.
* Fixed `PaginatedIterator` not implementing the iterator protocol.
* `Dataset.select()` preserves the dataset name and description.
* Fixed large trace size queries running out of memory.

**0.52.26**

February 3, 2026

## Added

* Usage statistics APIs plus `/trace/usage` and `/calls/usage` endpoints for aggregated usage.
* Optional performance mode flag for high-throughput deployments.
* Anthropic structured-parse patching.
* Saved views support a `column_order` field.

## Changed

* Improved `PREWHERE` optimization for distributed cluster queries.

## Fixed

* Fixed a bug where failed ClickHouse inserts could leak buffered rows.
* Fixed a bug where importing IPython at import time could slow cold starts.
* Fixed synchronous mutation migrations, summary filtering on `calls_complete`, and Google GenAI token overcounting.
* Fixed OpenTelemetry spans with monitors and duplicate upload handling for Google Cloud Storage.

**0.52.25**

January 20, 2026

## Fixed

* Removed redundant HTTP response capture in some integrations.
* Google GenAI tracing now records system instructions.
* Google GenAI tracing now records thinking tokens separately from completion tokens.

**0.52.24**

January 15, 2026

## Added

* TypeScript helper APIs for working with prompts in the Node SDK.
* Trace server safely autoconverts Base64 payloads where appropriate.
* Leaderboard schema updates for upcoming comparison features.
* `redact_pii_exclude_fields` setting to fine-tune PII redaction.
* Audio inputs in `LLMAsAJudgeScorer` and richer op metadata (kinds and colors) for integrations.

## Fixed

* Fixed invalid characters blocking op creation in edge cases.
* Fixed HTTP and HTTPS proxy handling for the HTTPX client.
* Fixed nested tracing when wrapping generators.

**0.52.23**

January 8, 2026

## Added

* Parsing helpers for Logfire Pydantic AI instrumentation inputs and outputs.

## Fixed

* Fixed non-deterministic ordering for large-table evaluations.
* Fixed cost queries that omitted input and output tokens.
* Fixed distributed replicated ClickHouse tables and guarded Kafka flush behavior behind configuration.

**0.52.22**

January 8, 2026

## Added

* Prompts and template variables on `LLMStructuredCompletionModels` persist through completion calls.

## Fixed

* Fixed ClickHouse import compatibility issues in some environments.

**0.52.20**

November 26, 2025

## Added

* Completions streaming APIs accept prompts and template variables.
* `ObjectRef.from_uri` reconstructs objects from Weave URIs.
* OpenAI Responses API tracing records `x-request-id` headers.
* Bedrock Agents integration coverage.
* TypeScript SDK `withAttributes` helper for span metadata.

## Fixed

* Fixed a memory leak in the OpenAI Agents tracing processor.
* Fixed a bug where refs could still publish when Weave was disabled.
* Fixed iterator behavior when migrating HTTP client code from `requests` to `httpx`.

> [!TIP]
>
> For releases older than 0.52.20, see [GitHub Releases for `wandb/weave`](https://github.com/wandb/weave/releases). Those entries use the default GitHub compare format (pull request links and commit prefixes). This docs page is updated for newer versions with customer-facing wording.
