fix: double counting for the usage in stream mode for anthropic models by hustxiayang · Pull Request #2239 · envoyproxy/ai-gateway

hustxiayang · 2026-06-16T16:14:05Z

Description

ExtractTokenUsageFromExplicitCaching is called in both start message and the delta message, as a result. The usage report is not correct.

Fix: remove the accumulation in the message delta; also the previous tests can pass because the test cases did not mock the real cases, update all related tests cases as well.

Signed-off-by: yxia216 <yxia216@bloomberg.net>

**Description** Update the compatibility matrix to specify EG v1.8.1+. Signed-off-by: Aaron Choo <achoo30@bloomberg.net> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…ners (envoyproxy#2194) **Description** Azure is strict about `scheme` header to be same as the TLS transport on which the request is being made. If the listener is an http listener, envoy forwards a request with `scheme: http` instead of `https`. This leads to requests getting dropped. The simple solution is to use `matchUpstream` which is what is being done in MCP backend listeners but missed in regular AI gateway route listeners. **Related Issues/PRs (if applicable)** Fixes envoyproxy#2095 Signed-off-by: Anurag Aggarwal <kanurag94@gmail.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…ackend HTTPRoute (envoyproxy#2134) **Description** When an `MCPRoute` has a `backendRef` with `securityPolicy.apiKey` configured (either via `secretRef` or `inline`), the controller resolves the secret and embeds the **plaintext API key** directly into the generated `HTTPRoute` resource. This happens in two places: 1. **Header injection** — the key is written as a literal value in an `HTTPRouteFilter` of type `RequestHeaderModifier` (e.g., `Authorization: Bearer <plaintext-token>`). 2. **Query parameter injection** — the key is appended to the URL path in a `URLRewrite` filter (e.g., `/mcp?api_key=<plaintext-token>`). fixes envoyproxy#2141 **Possible Solutions** 1. This can be solved for Header injection by using https://gateway.envoyproxy.io/docs/api/extension_types/#httpcredentialinjectionfilter. However, APIKey for `QueryParams` will still continue to be stored in plaintext. **Note: This PR implements this approach.** 2. By contrast, the existing `BackendSecurityPolicy` (used by `AIGatewayRoute` / `AIServiceBackend`) stores the resolved credential inside a Kubernetes **Secret** (the filter config secret consumed by extproc), which benefits from RBAC, encryption at rest, and audit logging. MCPRoute should adopt a similar approach. 3. Explore if we can add support for QueryParams in CredentialInjectionFilter in Envoy Gateway. **Affected code:** - internal/controller/mcp_route.go` **Testing** **Created MCPRoute with credential injection into Authorization header.** Credential got created and HTTPRouteFilter with Credential Injection filter got created. List tools and tool calls work as expected. Credential and filter got deleted on removing backend and deleting MCPRoute. **Created MCPRoute with credential injection into a custom header.** Credential got created and HTTPRouteFilter with Credential Injection filter got created. List tools and tool calls work as expected. Credential and filter got deleted on removing backend and deleting MCPRoute. **Created MCPRoute with inline API Key into Authorization header.** No change in behaviour. **Created MCPRoute with API Key injected into query param** No change in behaviour. --------- Signed-off-by: Aishwarya <aishwarya.raimule@nutanix.com> Signed-off-by: aishwaryaraimule21 <aishwarya.raimule@nutanix.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

**Description** When an MCPRoute/AIGW ROute references a non-existent Gateway in its spec.parentRefs, the controller still marks the route as "Accepted" with the message "Gateway Route reconciled successfully". The controller logs "Gateway not found" but does not propagate this as an error, so the reconciliation appears successful. Root Cause: In internal/controller/mcp_route.go, the syncGateway function was a void function that silently returned on errors — it logged "Gateway not found" but never returned an error to the caller. Since syncGateways (which calls syncGateway for each parentRef) always returned nil, the syncMCPRoute function completed successfully, and Reconcile marked the status as ConditionTypeAccepted. - and same goes for ai gateway route controller Fix: Changed syncGateway to return an error. When the referenced Gateway is not found, it now returns a descriptive error ("gateway <namespace>/<name> not found"). This error propagates through syncGateways → syncRoute → Reconcile, which then calls updateRouteStatus with ConditionTypeNotAccepted and the error message. During Route deletion (via the finalizer path), the error is still logged but does not block cleanup — handleFinalizer already handles onDeletionFn errors non-fatally. --------- Signed-off-by: Hritik003 <hritik.raj@nutanix.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

… in Bedrock translator (envoyproxy#2189) **Description** In the Anthropic-to-AWS-Bedrock translator, Claude Code with mid-conversation-system beta sends system prompts as {"role": "system"} in the messages array. The SDK has no system role constant so these hit the default error case. This promotes them to the top-level system param before conversion. Fixes envoyproxy#2206 Signed-off-by: Linus Schlumberger <linus.schlumberger@siemens.com> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…ror translation (envoyproxy#2161) **Description** Anthropic→OpenAI error translation could fail with an internal 500 when an OpenAI-compatible upstream returned a structured JSON error where `error.code` was numeric (e.g. `400`) instead of string. This change makes the error model tolerant to both representations so upstream 4xx diagnostics can still be translated and surfaced to Anthropic clients. - **Schema decoding hardening (`internal/apischema/openai/openai.go`)** - Added `UnmarshalJSON` for `openai.ErrorType`. - `error.code` now accepts: - JSON string (`"code":"400"`) - JSON number (`"code":400`) - `null` / omitted - Numeric values are normalized to the existing internal `*string` field. - **Translator regression coverage (`internal/translator/anthropic_openai_test.go`)** - Extended `TestAnthropicToOpenAITranslator_ResponseError` with a JSON error fixture containing numeric `code`. - Confirms response still maps to Anthropic error envelope with expected `type` and `message`. ```json { "type": "error", "error": { "type": "invalid_request_error", "message": "Bad request", "param": null, "code": 400 } } ``` **Related Issues/PRs (if applicable)** Fixes envoyproxy#2151 **Special notes for reviewers (if applicable)** N/A --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>

**Description** Fix the vars for the 0.7 and main releases. **Related Issues/PRs (if applicable)** N/A **Special notes for reviewers (if applicable)** N/A Signed-off-by: Ignasi Barrera <nacx@apache.org> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…2199) **Description** Anthropic recently exposed the reasoning tokens via `output_tokens_details`: https://platform.claude.com/docs/en/api/python/messages/create. Thus we should also added this usage information for our users. --------- Signed-off-by: yxia216 <yxia216@bloomberg.net> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…voyproxy#2220) Bumps the go group with 3 updates in the / directory: [go.opentelemetry.io/contrib/exporters/autoexport](https://github.com/open-telemetry/opentelemetry-go-contrib), [go.opentelemetry.io/contrib/propagators/autoprop](https://github.com/open-telemetry/opentelemetry-go-contrib) and [google.golang.org/api](https://github.com/googleapis/google-api-go-client). Updates `go.opentelemetry.io/contrib/exporters/autoexport` from 0.68.0 to 0.69.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go-contrib/releases">go.opentelemetry.io/contrib/exporters/autoexport's releases</a>.</em></p> <blockquote> <h2>v1.44.0/v2.5.1/v0.69.0/v0.37.1/v0.24.0/v0.19.0/v0.16.1/v0.16.0</h2> <h3>Added</h3> <ul> <li>Add <code>error.type</code> attribute to <code>http.client.request.duration</code> for transport failures in <code>otelhttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8801">#8801</a>)</li> <li>Add examples for prometheus compatibility document. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8716">#8716</a>)</li> <li>Add support for <code>cardinality_limits</code> in <code>PeriodicMetricReader</code> in <code>otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8885">#8885</a>)</li> <li>Add <code>Resource</code> method to <code>SDK</code> in <code>go.opentelemetry.io/contrib/otelconf/x</code> to expose the resolved SDK resource from declarative configuration. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8913">#8913</a>)</li> <li>Add <code>go.opentelemetry.io/contrib/detectors/hetzner</code>, a new resource detector for Hetzner Cloud servers, ported from <code>github.com/open-telemetry/opentelemetry-collector-contrib/processor/resourcedetectionprocessor/internal/hetzner</code>. Detects <code>cloud.provider</code>, <code>cloud.platform</code>, <code>cloud.region</code>, <code>cloud.availability_zone</code>, <code>host.id</code>, and <code>host.name</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8979">#8979</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Set error field as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otellogrus</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8776">#8776</a>)</li> <li>Set the "error" field (e.g. created via <code>zap.Error</code>) as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otelzap</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8719">#8719</a>)</li> <li>Set fields implementing <code>error</code> interface from <code>slog</code> records as <code>record.SetErr</code> instead of plain attributes in <code>go.opentelemetry.io/contrib/bridges/otelslog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8774">#8774</a>)</li> <li>Set emitted errors in <code>go.opentelemetry.io/contrib/bridges/otellogr</code> as record errors (<code>Record.SetErr</code>) instead of <code>exception.message</code> attributes. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8775">#8775</a>)</li> </ul> <h3>Fixed</h3> <ul> <li>Fix header attributes lost when using sub-spans in <code>go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8797">#8797</a>)</li> <li>Validate <code>encoding</code> configuration for OTLP HTTP exporters in <code>go.opentelemetry.io/contrib/otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8772">#8772</a>)</li> <li>Remove the custom body wrapper from the request's body after the request is processed to allow body type comparisons with the original type in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> and <code>go.opentelemetry.io/contrib/instrumentation/github.com/gorilla/mux/otelmux</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/6914">#6914</a>)</li> <li>Unknown or empty HTTP methods now report "_OTHER" instead of "GET" across all HTTP instrumentations to align with OpenTelemetry semantic conventions. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8868">#8868</a>)</li> <li>The default span name formatter in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> now conforms to the OpenTelemetry HTTP semantic conventions for server span names. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8871">#8871</a>) <ul> <li>The default span name is now <code>{method} {route}</code> (e.g. <code>GET /foo/{id}</code>) when a route pattern is available, or <code>{method}</code> (e.g. <code>GET</code>) otherwise.</li> </ul> </li> </ul> <h3>Removed</h3> <ul> <li>Remove the deprecated <code>WithSpanOptions</code> option in <code>go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8991">#8991</a>)</li> </ul> <h2>What's Changed</h2> <ul> <li>otelconf: validate encoding configuration for OTLP HTTP exporters by <a href="https://github.com/sonalgaud12"><code>@sonalgaud12</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8772">open-telemetry/opentelemetry-go-contrib#8772</a></li> <li>fix(deps): update module github.com/aws/aws-sdk-go-v2/service/s3 to v1.99.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8780">open-telemetry/opentelemetry-go-contrib#8780</a></li> <li>chore(deps): update prom/prometheus docker tag to v3.11.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8779">open-telemetry/opentelemetry-go-contrib#8779</a></li> <li>otellogrus: Set error field as <code>record.SetErr</code> by <a href="https://github.com/sonalgaud12"><code>@sonalgaud12</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8778">open-telemetry/opentelemetry-go-contrib#8778</a></li> <li>chore(deps): update module golang.org/x/sys to v0.43.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8783">open-telemetry/opentelemetry-go-contrib#8783</a></li> <li>chore(deps): update golang.org/x/telemetry digest to 93c7c8a by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8786">open-telemetry/opentelemetry-go-contrib#8786</a></li> <li>chore(deps): update module github.com/mattn/go-isatty to v0.0.21 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8787">open-telemetry/opentelemetry-go-contrib#8787</a></li> <li>chore(deps): update module github.com/mattn/go-runewidth to v0.0.23 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8788">open-telemetry/opentelemetry-go-contrib#8788</a></li> <li>chore(deps): update golang.org/x by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8791">open-telemetry/opentelemetry-go-contrib#8791</a></li> <li>chore(deps): update actions/github-script action to v9 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8795">open-telemetry/opentelemetry-go-contrib#8795</a></li> <li>fix(deps): update golang.org/x by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8794">open-telemetry/opentelemetry-go-contrib#8794</a></li> <li>otelzap: set error field as record.SetErr by <a href="https://github.com/iblancasa"><code>@iblancasa</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8719">open-telemetry/opentelemetry-go-contrib#8719</a></li> <li>fix(deps): update golang.org/x to 746e56f by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8796">open-telemetry/opentelemetry-go-contrib#8796</a></li> <li>chore(deps): update module golang.org/x/arch to v0.26.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8798">open-telemetry/opentelemetry-go-contrib#8798</a></li> <li>Check if otelgrpc metrics are enabled by <a href="https://github.com/dashpole"><code>@dashpole</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8792">open-telemetry/opentelemetry-go-contrib#8792</a></li> <li>chore(deps): update actions/upload-artifact action to v7.0.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8800">open-telemetry/opentelemetry-go-contrib#8800</a></li> <li>Check instrument enabled in deprecatedruntime by <a href="https://github.com/dashpole"><code>@dashpole</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8793">open-telemetry/opentelemetry-go-contrib#8793</a></li> <li>chore(deps): update module github.com/ashanbrown/forbidigo/v2 to v2.3.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8804">open-telemetry/opentelemetry-go-contrib#8804</a></li> <li>chore(deps): update module github.com/ashanbrown/makezero/v2 to v2.2.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8802">open-telemetry/opentelemetry-go-contrib#8802</a></li> <li>chore(deps): update module github.com/manuelarte/funcorder to v0.6.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8803">open-telemetry/opentelemetry-go-contrib#8803</a></li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go-contrib/blob/main/CHANGELOG.md">go.opentelemetry.io/contrib/exporters/autoexport's changelog</a>.</em></p> <blockquote> <h2>[1.44.0/2.5.1/0.69.0/0.37.1/0.24.0/0.19.0/0.16.1/0.16.0] - 2026-05-28</h2> <h3>Added</h3> <ul> <li>Add <code>error.type</code> attribute to <code>http.client.request.duration</code> for transport failures in <code>otelhttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8801">#8801</a>)</li> <li>Add examples for prometheus compatibility document. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8716">#8716</a>)</li> <li>Add support for <code>cardinality_limits</code> in <code>PeriodicMetricReader</code> in <code>otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8885">#8885</a>)</li> <li>Add <code>Resource</code> method to <code>SDK</code> in <code>go.opentelemetry.io/contrib/otelconf/x</code> to expose the resolved SDK resource from declarative configuration. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8913">#8913</a>)</li> <li>Add <code>go.opentelemetry.io/contrib/detectors/hetzner</code>, a new resource detector for Hetzner Cloud servers, ported from <code>github.com/open-telemetry/opentelemetry-collector-contrib/processor/resourcedetectionprocessor/internal/hetzner</code>. Detects <code>cloud.provider</code>, <code>cloud.platform</code>, <code>cloud.region</code>, <code>cloud.availability_zone</code>, <code>host.id</code>, and <code>host.name</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8979">#8979</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Set error field as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otellogrus</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8776">#8776</a>)</li> <li>Set the "error" field (e.g. created via <code>zap.Error</code>) as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otelzap</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8719">#8719</a>)</li> <li>Set fields implementing <code>error</code> interface from <code>slog</code> records as <code>record.SetErr</code> instead of plain attributes in <code>go.opentelemetry.io/contrib/bridges/otelslog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8774">#8774</a>)</li> <li>Set emitted errors in <code>go.opentelemetry.io/contrib/bridges/otellogr</code> as record errors (<code>Record.SetErr</code>) instead of <code>exception.message</code> attributes. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8775">#8775</a>)</li> </ul> <h3>Fixed</h3> <ul> <li>Fix header attributes lost when using sub-spans in <code>go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8797">#8797</a>)</li> <li>Validate <code>encoding</code> configuration for OTLP HTTP exporters in <code>go.opentelemetry.io/contrib/otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8772">#8772</a>)</li> <li>Remove the custom body wrapper from the request's body after the request is processed to allow body type comparisons with the original type in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> and <code>go.opentelemetry.io/contrib/instrumentation/github.com/gorilla/mux/otelmux</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/6914">#6914</a>)</li> <li>Unknown or empty HTTP methods now report "_OTHER" instead of "GET" across all HTTP instrumentations to align with OpenTelemetry semantic conventions. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8868">#8868</a>)</li> <li>The default span name formatter in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> now conforms to the OpenTelemetry HTTP semantic conventions for server span names. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8871">#8871</a>) <ul> <li>The default span name is now <code>{method} {route}</code> (e.g. <code>GET /foo/{id}</code>) when a route pattern is available, or <code>{method}</code> (e.g. <code>GET</code>) otherwise.</li> </ul> </li> </ul> <h3>Removed</h3> <ul> <li>Remove the deprecated <code>WithSpanOptions</code> option in <code>go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8991">#8991</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/03b2bcdb54b3dde73c9ff91ae216aec262f6c8f5"><code>03b2bcd</code></a> Release v1.44.0/v2.5.1/v0.69.0/v0.37.1/v0.24.0/v0.19.0/v0.16.1/v0.16.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9033">#9033</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/80c46d4037d5991ce324216a52cf7e8d7f2d81fa"><code>80c46d4</code></a> chore(deps): update module github.com/alecthomas/chroma/v2 to v2.26.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9034">#9034</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/51f292197d33b84a21b3c70ae21cb185a2570d5e"><code>51f2921</code></a> fix(deps): update module github.com/hetznercloud/hcloud-go/v2 to v2.41.2 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9026">#9026</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/db82162f1b642bb6dca7fa5be48045315bb466d6"><code>db82162</code></a> fix(deps): update aws-sdk-go-v2 monorepo (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9031">#9031</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/5a3e533d8cd4045128e61a966f6dad58964a78ea"><code>5a3e533</code></a> fix(deps): update module github.com/aws/smithy-go to v1.26.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9032">#9032</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/c67843c753a924faef17bc4aa63c138aa9472477"><code>c67843c</code></a> otelhttp: Remove custom wrapper after handling request (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/6914">#6914</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/c0a41352283151ab6655e88120e4ff4f0a917a2e"><code>c0a4135</code></a> docs(otelhttptrace): add performance guidance for WithoutSubSpans (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8785">#8785</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/a51a86790e1f4df231a70bb5fecc72b95d3c1bf0"><code>a51a867</code></a> otelconf: implement cardinality_limits support in PeriodicMetricReader (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8885">#8885</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/dead6e50fc0b5b3dc4aea288df207953dae5afe7"><code>dead6e5</code></a> chore(deps): update module go.yaml.in/yaml/v2 to v2.4.4 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8994">#8994</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/979ce1857524394d0884fd7c491722c5bcb43d50"><code>979ce18</code></a> chore(deps): update module github.com/jgautheron/goconst to v1.10.2 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9030">#9030</a>)</li> <li>Additional commits viewable in <a href="https://github.com/open-telemetry/opentelemetry-go-contrib/compare/zpages/v0.68.0...zpages/v0.69.0">compare view</a></li> </ul> </details> <br /> Updates `go.opentelemetry.io/contrib/propagators/autoprop` from 0.68.0 to 0.69.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go-contrib/releases">go.opentelemetry.io/contrib/propagators/autoprop's releases</a>.</em></p> <blockquote> <h2>v1.44.0/v2.5.1/v0.69.0/v0.37.1/v0.24.0/v0.19.0/v0.16.1/v0.16.0</h2> <h3>Added</h3> <ul> <li>Add <code>error.type</code> attribute to <code>http.client.request.duration</code> for transport failures in <code>otelhttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8801">#8801</a>)</li> <li>Add examples for prometheus compatibility document. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8716">#8716</a>)</li> <li>Add support for <code>cardinality_limits</code> in <code>PeriodicMetricReader</code> in <code>otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8885">#8885</a>)</li> <li>Add <code>Resource</code> method to <code>SDK</code> in <code>go.opentelemetry.io/contrib/otelconf/x</code> to expose the resolved SDK resource from declarative configuration. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8913">#8913</a>)</li> <li>Add <code>go.opentelemetry.io/contrib/detectors/hetzner</code>, a new resource detector for Hetzner Cloud servers, ported from <code>github.com/open-telemetry/opentelemetry-collector-contrib/processor/resourcedetectionprocessor/internal/hetzner</code>. Detects <code>cloud.provider</code>, <code>cloud.platform</code>, <code>cloud.region</code>, <code>cloud.availability_zone</code>, <code>host.id</code>, and <code>host.name</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8979">#8979</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Set error field as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otellogrus</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8776">#8776</a>)</li> <li>Set the "error" field (e.g. created via <code>zap.Error</code>) as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otelzap</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8719">#8719</a>)</li> <li>Set fields implementing <code>error</code> interface from <code>slog</code> records as <code>record.SetErr</code> instead of plain attributes in <code>go.opentelemetry.io/contrib/bridges/otelslog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8774">#8774</a>)</li> <li>Set emitted errors in <code>go.opentelemetry.io/contrib/bridges/otellogr</code> as record errors (<code>Record.SetErr</code>) instead of <code>exception.message</code> attributes. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8775">#8775</a>)</li> </ul> <h3>Fixed</h3> <ul> <li>Fix header attributes lost when using sub-spans in <code>go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8797">#8797</a>)</li> <li>Validate <code>encoding</code> configuration for OTLP HTTP exporters in <code>go.opentelemetry.io/contrib/otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8772">#8772</a>)</li> <li>Remove the custom body wrapper from the request's body after the request is processed to allow body type comparisons with the original type in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> and <code>go.opentelemetry.io/contrib/instrumentation/github.com/gorilla/mux/otelmux</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/6914">#6914</a>)</li> <li>Unknown or empty HTTP methods now report "_OTHER" instead of "GET" across all HTTP instrumentations to align with OpenTelemetry semantic conventions. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8868">#8868</a>)</li> <li>The default span name formatter in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> now conforms to the OpenTelemetry HTTP semantic conventions for server span names. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8871">#8871</a>) <ul> <li>The default span name is now <code>{method} {route}</code> (e.g. <code>GET /foo/{id}</code>) when a route pattern is available, or <code>{method}</code> (e.g. <code>GET</code>) otherwise.</li> </ul> </li> </ul> <h3>Removed</h3> <ul> <li>Remove the deprecated <code>WithSpanOptions</code> option in <code>go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8991">#8991</a>)</li> </ul> <h2>What's Changed</h2> <ul> <li>otelconf: validate encoding configuration for OTLP HTTP exporters by <a href="https://github.com/sonalgaud12"><code>@sonalgaud12</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8772">open-telemetry/opentelemetry-go-contrib#8772</a></li> <li>fix(deps): update module github.com/aws/aws-sdk-go-v2/service/s3 to v1.99.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8780">open-telemetry/opentelemetry-go-contrib#8780</a></li> <li>chore(deps): update prom/prometheus docker tag to v3.11.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8779">open-telemetry/opentelemetry-go-contrib#8779</a></li> <li>otellogrus: Set error field as <code>record.SetErr</code> by <a href="https://github.com/sonalgaud12"><code>@sonalgaud12</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8778">open-telemetry/opentelemetry-go-contrib#8778</a></li> <li>chore(deps): update module golang.org/x/sys to v0.43.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8783">open-telemetry/opentelemetry-go-contrib#8783</a></li> <li>chore(deps): update golang.org/x/telemetry digest to 93c7c8a by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8786">open-telemetry/opentelemetry-go-contrib#8786</a></li> <li>chore(deps): update module github.com/mattn/go-isatty to v0.0.21 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8787">open-telemetry/opentelemetry-go-contrib#8787</a></li> <li>chore(deps): update module github.com/mattn/go-runewidth to v0.0.23 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8788">open-telemetry/opentelemetry-go-contrib#8788</a></li> <li>chore(deps): update golang.org/x by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8791">open-telemetry/opentelemetry-go-contrib#8791</a></li> <li>chore(deps): update actions/github-script action to v9 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8795">open-telemetry/opentelemetry-go-contrib#8795</a></li> <li>fix(deps): update golang.org/x by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8794">open-telemetry/opentelemetry-go-contrib#8794</a></li> <li>otelzap: set error field as record.SetErr by <a href="https://github.com/iblancasa"><code>@iblancasa</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8719">open-telemetry/opentelemetry-go-contrib#8719</a></li> <li>fix(deps): update golang.org/x to 746e56f by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8796">open-telemetry/opentelemetry-go-contrib#8796</a></li> <li>chore(deps): update module golang.org/x/arch to v0.26.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8798">open-telemetry/opentelemetry-go-contrib#8798</a></li> <li>Check if otelgrpc metrics are enabled by <a href="https://github.com/dashpole"><code>@dashpole</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8792">open-telemetry/opentelemetry-go-contrib#8792</a></li> <li>chore(deps): update actions/upload-artifact action to v7.0.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8800">open-telemetry/opentelemetry-go-contrib#8800</a></li> <li>Check instrument enabled in deprecatedruntime by <a href="https://github.com/dashpole"><code>@dashpole</code></a> in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8793">open-telemetry/opentelemetry-go-contrib#8793</a></li> <li>chore(deps): update module github.com/ashanbrown/forbidigo/v2 to v2.3.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8804">open-telemetry/opentelemetry-go-contrib#8804</a></li> <li>chore(deps): update module github.com/ashanbrown/makezero/v2 to v2.2.1 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8802">open-telemetry/opentelemetry-go-contrib#8802</a></li> <li>chore(deps): update module github.com/manuelarte/funcorder to v0.6.0 by <a href="https://github.com/renovate"><code>@renovate</code></a>[bot] in <a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/pull/8803">open-telemetry/opentelemetry-go-contrib#8803</a></li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go-contrib/blob/main/CHANGELOG.md">go.opentelemetry.io/contrib/propagators/autoprop's changelog</a>.</em></p> <blockquote> <h2>[1.44.0/2.5.1/0.69.0/0.37.1/0.24.0/0.19.0/0.16.1/0.16.0] - 2026-05-28</h2> <h3>Added</h3> <ul> <li>Add <code>error.type</code> attribute to <code>http.client.request.duration</code> for transport failures in <code>otelhttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8801">#8801</a>)</li> <li>Add examples for prometheus compatibility document. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8716">#8716</a>)</li> <li>Add support for <code>cardinality_limits</code> in <code>PeriodicMetricReader</code> in <code>otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8885">#8885</a>)</li> <li>Add <code>Resource</code> method to <code>SDK</code> in <code>go.opentelemetry.io/contrib/otelconf/x</code> to expose the resolved SDK resource from declarative configuration. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8913">#8913</a>)</li> <li>Add <code>go.opentelemetry.io/contrib/detectors/hetzner</code>, a new resource detector for Hetzner Cloud servers, ported from <code>github.com/open-telemetry/opentelemetry-collector-contrib/processor/resourcedetectionprocessor/internal/hetzner</code>. Detects <code>cloud.provider</code>, <code>cloud.platform</code>, <code>cloud.region</code>, <code>cloud.availability_zone</code>, <code>host.id</code>, and <code>host.name</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8979">#8979</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Set error field as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otellogrus</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8776">#8776</a>)</li> <li>Set the "error" field (e.g. created via <code>zap.Error</code>) as <code>record.SetErr</code> instead of a plain attribute in <code>go.opentelemetry.io/contrib/bridges/otelzap</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8719">#8719</a>)</li> <li>Set fields implementing <code>error</code> interface from <code>slog</code> records as <code>record.SetErr</code> instead of plain attributes in <code>go.opentelemetry.io/contrib/bridges/otelslog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8774">#8774</a>)</li> <li>Set emitted errors in <code>go.opentelemetry.io/contrib/bridges/otellogr</code> as record errors (<code>Record.SetErr</code>) instead of <code>exception.message</code> attributes. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8775">#8775</a>)</li> </ul> <h3>Fixed</h3> <ul> <li>Fix header attributes lost when using sub-spans in <code>go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8797">#8797</a>)</li> <li>Validate <code>encoding</code> configuration for OTLP HTTP exporters in <code>go.opentelemetry.io/contrib/otelconf</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8772">#8772</a>)</li> <li>Remove the custom body wrapper from the request's body after the request is processed to allow body type comparisons with the original type in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> and <code>go.opentelemetry.io/contrib/instrumentation/github.com/gorilla/mux/otelmux</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/6914">#6914</a>)</li> <li>Unknown or empty HTTP methods now report "_OTHER" instead of "GET" across all HTTP instrumentations to align with OpenTelemetry semantic conventions. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8868">#8868</a>)</li> <li>The default span name formatter in <code>go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp</code> now conforms to the OpenTelemetry HTTP semantic conventions for server span names. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8871">#8871</a>) <ul> <li>The default span name is now <code>{method} {route}</code> (e.g. <code>GET /foo/{id}</code>) when a route pattern is available, or <code>{method}</code> (e.g. <code>GET</code>) otherwise.</li> </ul> </li> </ul> <h3>Removed</h3> <ul> <li>Remove the deprecated <code>WithSpanOptions</code> option in <code>go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8991">#8991</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/03b2bcdb54b3dde73c9ff91ae216aec262f6c8f5"><code>03b2bcd</code></a> Release v1.44.0/v2.5.1/v0.69.0/v0.37.1/v0.24.0/v0.19.0/v0.16.1/v0.16.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9033">#9033</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/80c46d4037d5991ce324216a52cf7e8d7f2d81fa"><code>80c46d4</code></a> chore(deps): update module github.com/alecthomas/chroma/v2 to v2.26.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9034">#9034</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/51f292197d33b84a21b3c70ae21cb185a2570d5e"><code>51f2921</code></a> fix(deps): update module github.com/hetznercloud/hcloud-go/v2 to v2.41.2 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9026">#9026</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/db82162f1b642bb6dca7fa5be48045315bb466d6"><code>db82162</code></a> fix(deps): update aws-sdk-go-v2 monorepo (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9031">#9031</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/5a3e533d8cd4045128e61a966f6dad58964a78ea"><code>5a3e533</code></a> fix(deps): update module github.com/aws/smithy-go to v1.26.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9032">#9032</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/c67843c753a924faef17bc4aa63c138aa9472477"><code>c67843c</code></a> otelhttp: Remove custom wrapper after handling request (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/6914">#6914</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/c0a41352283151ab6655e88120e4ff4f0a917a2e"><code>c0a4135</code></a> docs(otelhttptrace): add performance guidance for WithoutSubSpans (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8785">#8785</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/a51a86790e1f4df231a70bb5fecc72b95d3c1bf0"><code>a51a867</code></a> otelconf: implement cardinality_limits support in PeriodicMetricReader (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8885">#8885</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/dead6e50fc0b5b3dc4aea288df207953dae5afe7"><code>dead6e5</code></a> chore(deps): update module go.yaml.in/yaml/v2 to v2.4.4 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/8994">#8994</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go-contrib/commit/979ce1857524394d0884fd7c491722c5bcb43d50"><code>979ce18</code></a> chore(deps): update module github.com/jgautheron/goconst to v1.10.2 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go-contrib/issues/9030">#9030</a>)</li> <li>Additional commits viewable in <a href="https://github.com/open-telemetry/opentelemetry-go-contrib/compare/zpages/v0.68.0...zpages/v0.69.0">compare view</a></li> </ul> </details> <br /> Updates `go.opentelemetry.io/otel` from 1.43.0 to 1.44.0 <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go/blob/main/CHANGELOG.md">go.opentelemetry.io/otel's changelog</a>.</em></p> <blockquote> <h2>[1.44.0/0.66.0/0.20.0/0.0.17] 2026-05-27</h2> <h3>Added</h3> <ul> <li>Add <code>ByteSlice</code> and <code>ByteSliceValue</code> functions for new <code>BYTESLICE</code> attribute type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7948">#7948</a>)</li> <li>Apply attribute value limit to the <code>KindBytes</code> attribute type in <code>go.opentelemetry.io/otel/sdk/log</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7990">#7990</a>)</li> <li>Apply attribute value limit to the <code>BYTESLICE</code> attribute type in <code>go.opentelemetry.io/otel/sdk/trace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7990">#7990</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/trace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/zipkin</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Add <code>String</code> method for <code>Value</code> type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8142">#8142</a>)</li> <li>Add <code>Slice</code> and <code>SliceValue</code> functions for new <code>SLICE</code> attribute type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8166">#8166</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/zipkin</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Apply <code>AttributeValueLengthLimit</code> to <code>attribute.SLICE</code> type attribute values in <code>go.opentelemetry.io/otel/sdk/trace</code>, recursively truncating contained string values. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8217">#8217</a>)</li> <li>Add <code>Error</code> field on <code>Record</code> type in <code>go.opentelemetry.io/otel/log/logtest</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8148">#8148</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploggrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>Settable</code> to <code>go.opentelemetry.io/otel/metric/x</code> to allow reusing attribute options. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8178">#8178</a>)</li> <li>Add experimental support for splitting metric data across multiple batches in <code>go.opentelemetry.io/otel/sdk/metric</code>. Set <code>OTEL_GO_X_METRIC_EXPORT_BATCH_SIZE=<max_size></code> to enable for all periodic readers. See <code>go.opentelemetry.io/otel/sdk/metric/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8071">#8071</a>)</li> <li>Add experimental self-observability metrics in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc</code>. Enable with <code>OTEL_GO_X_SELF_OBSERVABILITY=true</code> environment variable. See <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8192">#8192</a>)</li> <li>Add experimental self-observability metrics in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp</code>. Enable with <code>OTEL_GO_X_SELF_OBSERVABILITY=true</code> environment variable. See <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8194">#8194</a>)</li> <li>Add experimental self-observability metrics in <code>go.opentelemetry.io/otel/exporters/stdout/stdoutlog</code>. Enable with <code>OTEL_GO_X_SELF_OBSERVABILITY=true</code> environment variable. See <code>go.opentelemetry.io/otel/stdout/stdoutlog/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8263">#8263</a>)</li> <li>Add <code>WithDefaultAttributes</code> to <code>go.opentelemetry.io/otel/metric/x</code> to support setting default attributes on instruments. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8135">#8135</a>)</li> <li>Add <code>go.opentelemetry.io/otel/semconv/v1.41.0</code> package. The package contains semantic conventions from the <code>v1.41.0</code> version of the OpenTelemetry Semantic Conventions. See the <a href="https://github.com/open-telemetry/opentelemetry-go/blob/main/semconv/v1.41.0/MIGRATION.md">migration documentation</a> for information on how to upgrade from <code>go.opentelemetry.io/otel/semconv/v1.40.0</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8324">#8324</a>)</li> <li>Add Observable variants of instruments to <code>go.opentelemetry.io/otel/semconv/v1.41.0</code> package. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8350">#8350</a>)</li> <li>Generate explicit histogram bucket boundaries from weaver configuration for HTTP and RPC duration instruments in <code>go.opentelemetry.io/otel/semconv/v1.41.0</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8002">#8002</a>)</li> </ul> <h3>Changed</h3> <ul> <li>⚠️ <strong>Breaking Change:</strong> <code>go.opentelemetry.io/otel/sdk/metric</code> now applies a default cardinality limit of 2000 to comply with the Metrics SDK specification recommendation. New attribute sets are dropped when the cardinality limit is reached. The measurement of these sets are aggregated into a special attribute set containing <code>attribute.Bool("otel.metric.overflow", true)</code>.</li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/b62d92831b2dd142f5a0cc89c828270274196877"><code>b62d928</code></a> Release 1.44.0 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8376">#8376</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/94132a0a729e94c5aa6e9e1ce7640c0f802dcfea"><code>94132a0</code></a> chore(deps): update golang.org/x/telemetry digest to 5997936 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8379">#8379</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/6fdcf82adfebc3becfb5d357957546d6d7258469"><code>6fdcf82</code></a> feat: add self-observability metrics to otlpmetricgrpc metric exporters (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8192">#8192</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/761bbfc2f4ae002f4a54f8c57c12b8a58135a741"><code>761bbfc</code></a> fix(deps): update golang.org/x (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8377">#8377</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/3a91dc62d3852313bab40ff151bb3e11fae1745e"><code>3a91dc6</code></a> fix(deps): update googleapis to 3dc84a4 (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8375">#8375</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/f593185679130f56e14bed3c337fa7f8f60756b1"><code>f593185</code></a> exporters/otlp: default max request size to 64 MiB (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8365">#8365</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/f02feacf8652b69c051851cfa2945d2ed5f0d568"><code>f02feac</code></a> Merge commit from fork</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/36c2f1bfd1a6a789dc575f8886399093d7600586"><code>36c2f1b</code></a> semconvkit: add invariant test for histogram-exclusion rule (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8370">#8370</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/d0b6cbdff5346557923fd05bd3f5f34df002aeee"><code>d0b6cbd</code></a> sdk/metric: document unit-sensitivity of DefaultAggregationSelector (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8224">#8224</a>)</li> <li><a href="https://github.com/open-telemetry/opentelemetry-go/commit/9a68034bd45c6f24c481d9f9c87ebbee0a61482f"><code>9a68034</code></a> add self observability for stdout exporter (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8263">#8263</a>)</li> <li>Additional commits viewable in <a href="https://github.com/open-telemetry/opentelemetry-go/compare/v1.43.0...v1.44.0">compare view</a></li> </ul> </details> <br /> Updates `go.opentelemetry.io/otel/exporters/prometheus` from 0.65.0 to 0.66.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go/releases">go.opentelemetry.io/otel/exporters/prometheus's releases</a>.</em></p> <blockquote> <h2>v1.44.0/v0.66.0/v0.20.0/v0.0.17</h2> <h3>Added</h3> <ul> <li>Add <code>ByteSlice</code> and <code>ByteSliceValue</code> functions for new <code>BYTESLICE</code> attribute type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7948">#7948</a>)</li> <li>Apply attribute value limit to the <code>KindBytes</code> attribute type in <code>go.opentelemetry.io/otel/sdk/log</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7990">#7990</a>)</li> <li>Apply attribute value limit to the <code>BYTESLICE</code> attribute type in <code>go.opentelemetry.io/otel/sdk/trace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7990">#7990</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/trace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/zipkin</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Add <code>String</code> method for <code>Value</code> type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8142">#8142</a>)</li> <li>Add <code>Slice</code> and <code>SliceValue</code> functions for new <code>SLICE</code> attribute type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8166">#8166</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/zipkin</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Apply <code>AttributeValueLengthLimit</code> to <code>attribute.SLICE</code> type attribute values in <code>go.opentelemetry.io/otel/sdk/trace</code>, recursively truncating contained string values. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8217">#8217</a>)</li> <li>Add <code>Error</code> field on <code>Record</code> type in <code>go.opentelemetry.io/otel/log/logtest</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8148">#8148</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploggrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>Settable</code> to <code>go.opentelemetry.io/otel/metric/x</code> to allow reusing attribute options. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8178">#8178</a>)</li> <li>Add experimental support for splitting metric data across multiple batches in <code>go.opentelemetry.io/otel/sdk/metric</code>. Set <code>OTEL_GO_X_METRIC_EXPORT_BATCH_SIZE=<max_size></code> to enable for all periodic readers. See <code>go.opentelemetry.io/otel/sdk/metric/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8071">#8071</a>)</li> <li>Add experimental self-observability metrics in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc</code>. Enable with <code>OTEL_GO_X_SELF_OBSERVABILITY=true</code> environment variable. See <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8192">#8192</a>)</li> <li>Add experimental self-observability metrics in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp</code>. Enable with <code>OTEL_GO_X_SELF_OBSERVABILITY=true</code> environment variable. See <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8194">#8194</a>)</li> <li>Add experimental self-observability metrics in <code>go.opentelemetry.io/otel/exporters/stdout/stdoutlog</code>. Enable with <code>OTEL_GO_X_SELF_OBSERVABILITY=true</code> environment variable. See <code>go.opentelemetry.io/otel/stdout/stdoutlog/internal/x</code> for feature documentation. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8263">#8263</a>)</li> <li>Add <code>WithDefaultAttributes</code> to <code>go.opentelemetry.io/otel/metric/x</code> to support setting default attributes on instruments. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8135">#8135</a>)</li> <li>Add <code>go.opentelemetry.io/otel/semconv/v1.41.0</code> package. The package contains semantic conventions from the <code>v1.41.0</code> version of the OpenTelemetry Semantic Conventions. See the <a href="https://github.com/open-telemetry/opentelemetry-go/blob/HEAD/semconv/v1.41.0/MIGRATION.md">migration documentation</a> for information on how to upgrade from <code>go.opentelemetry.io/otel/semconv/v1.40.0</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8324">#8324</a>)</li> <li>Add Observable variants of instruments to <code>go.opentelemetry.io/otel/semconv/v1.41.0</code> package. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8350">#8350</a>)</li> <li>Generate explicit histogram bucket boundaries from weaver configuration for HTTP and RPC duration instruments in <code>go.opentelemetry.io/otel/semconv/v1.41.0</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8002">#8002</a>)</li> </ul> <h3>Changed</h3> <ul> <li>⚠️ <strong>Breaking Change:</strong> <code>go.opentelemetry.io/otel/sdk/metric</code> now applies a default cardinality limit of 2000 to comply with the Metrics SDK specification recommendation. New attribute sets are dropped when the cardinality limit is reached. The measurement of these sets are aggregated into a special attribute set containing <code>attribute.Bool("otel.metric.overflow", true)</code>. This can break users who relied on the previous unlimited default.</li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/open-telemetry/opentelemetry-go/blob/main/CHANGELOG.md">go.opentelemetry.io/otel/exporters/prometheus's changelog</a>.</em></p> <blockquote> <h2>[1.44.0/0.66.0/0.20.0/0.0.17] 2026-05-27</h2> <h3>Added</h3> <ul> <li>Add <code>ByteSlice</code> and <code>ByteSliceValue</code> functions for new <code>BYTESLICE</code> attribute type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7948">#7948</a>)</li> <li>Apply attribute value limit to the <code>KindBytes</code> attribute type in <code>go.opentelemetry.io/otel/sdk/log</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7990">#7990</a>)</li> <li>Apply attribute value limit to the <code>BYTESLICE</code> attribute type in <code>go.opentelemetry.io/otel/sdk/trace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/7990">#7990</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/trace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Support <code>BYTESLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/zipkin</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8153">#8153</a>)</li> <li>Add <code>String</code> method for <code>Value</code> type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8142">#8142</a>)</li> <li>Add <code>Slice</code> and <code>SliceValue</code> functions for new <code>SLICE</code> attribute type in <code>go.opentelemetry.io/otel/attribute</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8166">#8166</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Support <code>SLICE</code> attributes in <code>go.opentelemetry.io/otel/exporters/zipkin</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8216">#8216</a>)</li> <li>Apply <code>AttributeValueLengthLimit</code> to <code>attribute.SLICE</code> type attribute values in <code>go.opentelemetry.io/otel/sdk/trace</code>, recursively truncating contained string values. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8217">#8217</a>)</li> <li>Add <code>Error</code> field on <code>Record</code> type in <code>go.opentelemetry.io/otel/log/logtest</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8148">#8148</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploggrpc</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>WithMaxRequestSize</code> option in <code>go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp</code>. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8157">#8157</a>)</li> <li>Add <code>Settable</code> to <code>go.opentelemetry.io/otel/metric/x</code> to allow reusing attribute options. (<a href="https://redirect.github.com/open-telemetry/opentelemetry-go/issues/8178">#8178</a>)</li> <li>Add experimental support for splitting metric data across multiple batches in <code>go.opentelemetry.io/otel/sdk/metric</code>. Set <code>OTEL_GO_X_METRIC_EXPORT_BATCH_SIZE=<max_size></code> to enable for all periodic readers. See <code>go.opentelemetry.io/otel/s…

**Description** Adds stacklok to adopters page --------- Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…roxy#2225) **Description** The request body we send to GCP Vertex AI (the Gemini generateContent API) had a few field names in the wrong style. Vertex expects camelCase names like `generationConfig` and `systemInstruction`, but three of them were written in snake_case (`generation_config`, `system_instruction`, `tool_config`). The `safetySettings` field was already camelCase, so the struct was inconsistent with itself. This updates those three names to camelCase so they all match the format Vertex documents and the format the `google.golang.org/genai` library uses. Vertex does accept the snake_case versions as well, so this isn't fixing broken behaviour, but it removes the inconsistency and means we're no longer relying on that leniency. I also updated the tests that were asserting the old snake_case output. While I was in there, I replaced some hardcoded content-length values in the unit test with a check that the content-length header matches the actual body length. Those fixed numbers would have needed recalculating every time the body changed by even a byte, and the new check stays correct on its own. Testing: the existing unit tests and the data plane tests pass, including the GCP Vertex AI cases that exercise the request body end to end. Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…m chart (envoyproxy#2226) **Description** The controller and inference-pool `ClusterRole`/`ClusterRoleBinding` names are built with `printf "%s:%s" <base> .Release.Namespace` to keep them unique per-release (introduced in envoyproxy#1511). When `.Release.Namespace` is empty, this renders `name: <base>:` — an unquoted trailing colon that strict YAML parsers reject with `mapping values are not allowed in this context`. The whole render fails and zero resources are produced. This doesn't trigger via `helm install` or `helm template` (the CLI always defaults the namespace), only where a renderer leaves it unset — e.g. the Helm SDK's `engine.Render` without `ReleaseOptions`, or Replicated's image-extraction render. The fix adds two independent layers of defense across the three affected helpers (`_helpers.tpl`) and their six call sites (`serviceaccount.yaml`, `envoy_gateway_cluster_role_for_inference_pool.yaml`): - Wrap the namespace in `default "default"` so the `printf` argument is never empty. No behavior change for real installs, where the namespace is always populated. - Quote the rendered `name` fields so a trailing colon is always unambiguous. Either layer fixes the failure on its own; both are included for robustness. **Special notes for reviewers (if applicable)** Verified with `helm lint` and `helm template` (default and explicit namespaces) — names render correctly as `<base>:<namespace>` with no change to existing behavior. Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…oyproxy#2191) **Description** In the OpenAI-to-AWS-Bedrock message converter, Bedrock Converse rejects assistant messages with empty content arrays. Some clients send empty assistant messages. This skips them when they have no content blocks. Tool-call-only messages are preserved. Fixes envoyproxy#2208 Signed-off-by: Linus Schlumberger <linus.schlumberger@siemens.com> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>

…oyproxy#2170) **Description** **Scope:** this PR fixes the narrow case where the upstream cluster ext_proc filter issued `CONTINUE_AND_REPLACE` even though *nothing in the request pipeline needed to mutate the body* — no translation, no model override, no retry, no backend `HTTPBodyMutation`. In that path, the upstream filter replayed `u.parent.originalRequestBodyRaw` (snapshotted at the router phase), which clobbered any body mutation applied by an earlier ext_proc filter in the listener chain. After this PR, that path emits `CONTINUE` and leaves the body alone. The broader question of "preserve an intermediate filter's body mutation across translation / retries / `HTTPBodyMutation`" is **not** addressed by this PR. When `wantBodyReplace == true`, the replacement body is still derived from the router-phase snapshot, so any intermediate filter's mutation is lost on those branches. That's an architectural property of the snapshot-at-router- phase design — the upstream filter has no view of Envoy's current body, by design, to avoid re-buffering through ext_proc at the upstream phase. Fixing it requires a separate design (either re-buffering at upstream, or propagating a diff via dynamic metadata) and should be its own PR. **Root cause of the narrow bug.** The existing safety net in `applyBodyMutation` looks like it covers the no-config case: if bodyMutator == nil { return bodyMutation } but it does not fire in practice. `bodymutator.NewBodyMutator(nil, ...)` returns a non-nil struct even when its `*filterapi.HTTPBodyMutation` argument is nil. So the early-return is dead code; the function falls through, calls `Mutate(originalRequestBodyRaw)` on a no-config mutator (which returns its input unchanged), wraps that in a `BodyMutation`, and the upstream filter sends `CONTINUE_AND_REPLACE` with the original body — even though nothing asked for a body replacement. **Fix:** * Add `BodyMutator.HasMutations()` predicate. `NewBodyMutator`'s contract is unchanged (it still returns non-nil); callers can ask whether the mutator actually has anything to do. * In `upstreamProcessor.ProcessRequestHeaders`, compute mutatorHasMutations := u.bodyMutator != nil && u.bodyMutator.HasMutations() wantBodyReplace := bodyMutation != nil || forceBodyMutation || mutatorHasMutations before calling `applyBodyMutation`. When false, skip the body-mutation work and emit `CONTINUE` instead of `CONTINUE_AND_REPLACE`, preserving translator header mutations (e.g. path rewrite), header-mutator output, and auth-handler header additions. Skip the content-length dynamic-metadata restamp on the `CONTINUE` branch since the body length did not change. All existing `CONTINUE_AND_REPLACE` callers stay on the existing path (these are the branches where this PR explicitly does not change behavior, including the loss-of-earlier-mutation property documented above): * Translator emits a body (AWS Bedrock/SigV4, OpenAI to Anthropic, OpenAI to Vertex, etc.) — `bodyMutation != nil`. * Backend `HTTPBodyMutation` configured — `HasMutations() == true`. * Retry — `forceBodyMutation == true` via `u.onRetry()`. * Streaming with `IncludeUsage=false` — `forceBodyMutation == true`. * Model override — translator emits `newBody` via `sjson.SetBytesOptions`, so `bodyMutation != nil`. **Tests:** * Added `Test_chatCompletionProcessorUpstreamFilter_ProcessRequestHeaders_BodyReplaceContract` with two subtests: * `no translator body, no mutator, no force -> CONTINUE` exercises the previously untested path. Asserts `Status == CONTINUE`, no `BodyMutation`, preserved translator and auth-handler header mutations, and `DynamicMetadata == nil` (no content-length restamp). * `translator body present -> CONTINUE_AND_REPLACE` pins the existing behavior so a future refactor cannot quietly flip the contract back. The coverage gap that let this ship: every existing `t.Run("ok", ...)` subtest under `Test_chatCompletionProcessorUpstreamFilter_ProcessRequestHeaders` set `retBodyMutation` on the mock translator, so the "translator returns nil body" path was never exercised. **Related Issues/PRs (if applicable)** None. **Special notes for reviewers (if applicable)** * The fix is request-side only. Response-side code is untouched. * `NewBodyMutator`'s contract is intentionally not changed (it still returns non-nil even when given a nil `*filterapi.HTTPBodyMutation`). A predicate is added instead, to keep the blast radius local to `ProcessRequestHeaders`. If reviewers prefer changing the constructor to return nil in the no-config case, that is a larger refactor and a separate PR. * The bug is in the generic `upstreamProcessor[...]`, so the fix applies to every endpoint spec (chat completions, messages, embeddings, completions, GCP, AWS Bedrock, etc.). The new tests exercise one endpoint spec for the same reason the existing `ProcessRequestHeaders` table-test does — locking the generic method's contract. Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>

**Description** **Problem** If a buffer filter (`envoy.filters.http.buffer`) is added to the chain, for example via an EnvoyPatchPolicy to raise the request buffer limit, the AI Gateway extproc could be placed ahead of it. The AI Gateway extproc runs with `RequestBodyMode: BUFFERED`, so when it runs before the buffer filter it buffers the body against Envoy Gateway's default 32 KiB downstream per-connection limit and returns `413 Payload Too Large` for larger bodies before the buffer filter's higher limit applies. The buffer filter raises the stream's buffer limit to `max_request_bytes`, but only for filters that decode after it. This was hit in practice with large request bodies such as Gemini CLI tool definitions. **Solution** When a buffer filter sits at or after the computed ext_proc insertion point, insert the AI Gateway extproc immediately after the last buffer filter. Envoy Gateway already orders the buffer filter before ext_proc, so this honors that order. Behavior is unchanged when no buffer filter is present. This works because EnvoyPatchPolicy patches are applied before the extension hook runs and Envoy Gateway does not re-sort filters afterward, so the buffer filter is visible to this code. The extension server only moves its own filter, not the user's buffer filter, so this fixes the 413 for AI Gateway's extproc specifically and not for other co-resident BUFFERED ext_procs. **Testing** Added table tests for three cases: ext_proc before buffer (inserted after buffer), buffer before ext_proc (inserted after buffer), and no buffer filter (unchanged). Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>

Signed-off-by: yxia216 <yxia216@bloomberg.net>

**Description** This updates the homepage info Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

Signed-off-by: Ignasi Barrera <nacx@apache.org> Signed-off-by: yxia216 <yxia216@bloomberg.net>

**Description** Limit by default the size of MCP request payloads. **Related Issues/PRs (if applicable)** N/A **Special notes for reviewers (if applicable)** N/A Signed-off-by: Ignasi Barrera <nacx@apache.org> Signed-off-by: yxia216 <yxia216@bloomberg.net>

Signed-off-by: yxia216 <yxia216@bloomberg.net>

codecov-commenter · 2026-06-16T16:33:06Z

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 84.70%. Comparing base (2cc2417) to head (d0d9441).

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2239      +/-   ##
==========================================
- Coverage   84.74%   84.70%   -0.05%     
==========================================
  Files         144      144              
  Lines       21210    21204       -6     
==========================================
- Hits        17975    17960      -15     
- Misses       2153     2162       +9     
  Partials     1082     1082

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

hustxiayang · 2026-06-16T16:48:16Z

/retest

Signed-off-by: yxia216 <yxia216@bloomberg.net>

hustxiayang · 2026-06-16T18:03:46Z

/gemini review

gemini-code-assist · 2026-06-16T18:05:23Z

Warning

Gemini encountered an error creating the review. You can try again by commenting /gemini review.

hustxiayang · 2026-06-16T18:06:32Z

/gemini review

gemini-code-assist

Code Review

This pull request refactors the Anthropic stream parser to avoid modifying cache token details during message_delta events, as these are already set in message_start. It also adds comprehensive unit tests for streaming token usage and updates mock SSE responses in integration tests. The review feedback points out that the added comment in anthropic_helper.go is inaccurate: message_delta contains total accumulated output tokens rather than incremental ones, and ignoring cache tokens there is necessary to prevent double-counting when upstreams include full usage details in delta events. A suggestion was provided to clarify this in the code comment.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

Signed-off-by: yxia216 <yxia216@bloomberg.net>

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: hustxiayang <yangxiast@gmail.com>

hustxiayang · 2026-06-16T18:28:51Z

@yuzisun Do you mind to review this? I have update the tests

xiaolin593 · 2026-06-17T09:03:07Z

 		if output, ok := usage.OutputTokens(); ok {
 			p.tokenUsage.AddOutputTokens(output)
 		}
-		// Update input tokens to include any cache tokens from delta


I missed this PR when I was working on #2241.

After discussing offline with @hustxiayang and @yuzisun, we agreed to remove the extra cache token counting from message_start and instead rely on message_delta, which is the provider's final source of truth in streaming mode.

This keeps the logic cleaner and avoids edge cases like the one here: https://github.com/envoyproxy/ai-gateway/pull/2241/changes#diff-aa8ea9f59fc3acd18cfd4a4c571d683817274a213b6a5fad0ab6085cfe0912dfL974-L980.

hustxiayang · 2026-06-17T09:06:54Z

@yuzisun About whether to set input tokens in the start message or the delta message, the anthropic's definition is like

class MessageDeltaUsage(BaseModel):
    cache_creation_input_tokens: Optional[int] = None  # cumulative
    cache_read_input_tokens: Optional[int] = None      # cumulative
    input_tokens: Optional[int] = None                 # cumulative
    output_tokens: int                                 # required, cumulative

and the start message's definition:

class Usage(BaseModel):
    cache_creation_input_tokens: Optional[int] = None
    cache_read_input_tokens: Optional[int] = None
    input_tokens: int        # required
    output_tokens: int       # required

The difference is that input_tokens are required in the start message, but optional in the delta message. Thus it should be safer to use start message as it's guanranted to be set, so it should be safer to get the value from the start message.

hustxiayang · 2026-06-17T09:24:38Z

there is no difference when there is a disconnection or 529 error in the middle of the stream, because it's just to set the value into an intermediate structure (p). It only reports the usage (usage chunk and metrics) until endOfStream=true, which is after both start message and delta message. So there should be no difference.

yuzisun · 2026-06-17T13:00:11Z

@yuzisun About whether to set input tokens in the start message or the delta message, the anthropic's definition is like
class MessageDeltaUsage(BaseModel):
    cache_creation_input_tokens: Optional[int] = None  # cumulative
    cache_read_input_tokens: Optional[int] = None      # cumulative
    input_tokens: Optional[int] = None                 # cumulative
    output_tokens: int                                 # required, cumulative
and the start message's definition:
class Usage(BaseModel):
    cache_creation_input_tokens: Optional[int] = None
    cache_read_input_tokens: Optional[int] = None
    input_tokens: int        # required
    output_tokens: int       # required
The difference is that input_tokens are required in the start message, but optional in the delta message. Thus it should be safer to use start message as it's guanranted to be set, so it should be safer to get the value from the start message.

Then we should get all inputs including cache read/write tokens in the start message since they are set before token streaming.

hustxiayang · 2026-06-17T17:01:44Z

Then we should get all inputs including cache read/write tokens in the start message since they are set before token streaming.

@yuzisun I think the current implementation is set like this. You could check line 971-979, these values are set in the start message.

yuzisun · 2026-06-17T19:28:34Z

-			// Accumulate cache creation tokens
-			p.tokenUsage.AddCacheCreationInputTokens(cacheCreation)
-		}
+		// Cache token details are already set in message_start — don't touch them here


Can you move the comment above, looks odd for comments without code

Thanks, I updated the comment.

Signed-off-by: yxia216 <yxia216@bloomberg.net>

hustxiayang · 2026-06-17T20:24:08Z

@yuzisun could you please help to merge it as well. Thanks!

hustxiayang requested a review from a team as a code owner June 16, 2026 16:14

dosubot Bot added the size:XS This PR changes 0-9 lines, ignoring generated files. label Jun 16, 2026

hustxiayang changed the title ~~update the usage-report~~ fix: fix the twice counting for the usage in stream mode for anthropic models Jun 16, 2026

dosubot Bot added size:S This PR changes 10-29 lines, ignoring generated files. and removed size:XS This PR changes 0-9 lines, ignoring generated files. labels Jun 16, 2026

hustxiayang and others added 23 commits June 16, 2026 12:20

update the usage-report

dddeebd

Signed-off-by: yxia216 <yxia216@bloomberg.net>

docs: update compatibility matrix EG -> V1.8.1 (envoyproxy#2215)

8c758f4

**Description** Update the compatibility matrix to specify EG v1.8.1+. Signed-off-by: Aaron Choo <achoo30@bloomberg.net> Signed-off-by: yxia216 <yxia216@bloomberg.net>

docs(site): adds Stacklok to Adopters Page (envoyproxy#2224)

2857986

**Description** Adds stacklok to adopters page --------- Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

fix: allow strict function definition in anthropic (envoyproxy#2232)

a200229

Signed-off-by: yxia216 <yxia216@bloomberg.net>

docs: update release information to v0.7 (envoyproxy#2233)

8f98b4b

**Description** This updates the homepage info Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> Signed-off-by: yxia216 <yxia216@bloomberg.net>

Merge commit from fork

d34a29d

Signed-off-by: Ignasi Barrera <nacx@apache.org> Signed-off-by: yxia216 <yxia216@bloomberg.net>

cached-tokens

9719b8f

Signed-off-by: yxia216 <yxia216@bloomberg.net>

hustxiayang force-pushed the fix-usage-report branch from 7788e25 to 9719b8f Compare June 16, 2026 16:21

dosubot Bot removed the size:S This PR changes 10-29 lines, ignoring generated files. label Jun 16, 2026

dosubot Bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Jun 16, 2026

hustxiayang changed the title ~~fix: fix the twice counting for the usage in stream mode for anthropic models~~ fix: fix the double counting for the usage in stream mode for anthropic models Jun 16, 2026

yuzisun reviewed Jun 16, 2026

View reviewed changes

Comment thread internal/translator/anthropic_helper.go Outdated

hustxiayang added 2 commits June 16, 2026 13:30

update-tests

7a7e107

Signed-off-by: yxia216 <yxia216@bloomberg.net>

fix-the-tests

a02e6d7

Signed-off-by: yxia216 <yxia216@bloomberg.net>

gemini-code-assist Bot reviewed Jun 16, 2026

View reviewed changes

Comment thread internal/translator/anthropic_helper.go Outdated

update-tests

bbdb144

Signed-off-by: yxia216 <yxia216@bloomberg.net>

hustxiayang force-pushed the fix-usage-report branch from 9535b90 to bbdb144 Compare June 16, 2026 18:11

Update internal/translator/anthropic_helper.go

224ea22

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: hustxiayang <yangxiast@gmail.com>

xiaolin593 reviewed Jun 17, 2026

View reviewed changes

yuzisun reviewed Jun 17, 2026

View reviewed changes

hustxiayang added 2 commits June 17, 2026 15:35

update-comments

da8daf9

Signed-off-by: yxia216 <yxia216@bloomberg.net>

Merge branch 'main' into fix-usage-report

d0d9441

yuzisun changed the title ~~fix: fix the double counting for the usage in stream mode for anthropic models~~ fix: fdouble counting for the usage in stream mode for anthropic models Jun 17, 2026

yuzisun changed the title ~~fix: fdouble counting for the usage in stream mode for anthropic models~~ fix: double counting for the usage in stream mode for anthropic models Jun 17, 2026

yuzisun approved these changes Jun 17, 2026

View reviewed changes

yuzisun merged commit 4ae1ec4 into envoyproxy:main Jun 18, 2026
38 checks passed

xiaolin593 mentioned this pull request Jun 18, 2026

fix: cache token double counting at message_start #2241

Open

pokabookinflab mentioned this pull request Jul 28, 2026

chore: integrate upstream v1.0.0 into fork inflearn/ai-gateway#4

Merged

3 tasks

Uh oh!

Conversation

hustxiayang commented Jun 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

codecov-commenter commented Jun 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

hustxiayang commented Jun 16, 2026

Uh oh!

Uh oh!

hustxiayang commented Jun 16, 2026

Uh oh!

gemini-code-assist Bot commented Jun 16, 2026

Uh oh!

hustxiayang commented Jun 16, 2026

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

hustxiayang commented Jun 16, 2026

Uh oh!

xiaolin593 Jun 17, 2026

Choose a reason for hiding this comment

Uh oh!

hustxiayang commented Jun 17, 2026

Uh oh!

hustxiayang commented Jun 17, 2026

Uh oh!

yuzisun commented Jun 17, 2026

Uh oh!

hustxiayang commented Jun 17, 2026

Uh oh!

yuzisun Jun 17, 2026

Choose a reason for hiding this comment

Uh oh!

hustxiayang Jun 17, 2026

Choose a reason for hiding this comment

Uh oh!

hustxiayang commented Jun 17, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

13 participants

hustxiayang commented Jun 16, 2026 •

edited

Loading

codecov-commenter commented Jun 16, 2026 •

edited

Loading