[bot] Anthropic MCP connector tool calls (mcp_tool_use/mcp_tool_result) produce broken, input-less child spans
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 2/5
- Tempo stimato
- 1-3 ore
- Idoneità per principianti
- 82/100
- Tipo di issue
- Bug
- Chiarezza
- Specificata chiaramente
- Stato di attività
- Attiva
- Stack tecnologico
- java
- Ambito
- observability
Direzione di ricerca
Inizia in InstrumentationSemConv.addAnthropicServerSideChildSpans in braintrust-sdk/src/main/java/dev/braintrust/instrumentation/InstrumentationSemConv.java, dove i blocchi vengono dispatchati tramite type; leggi anche ANTHROPIC_SERVER_TOOL_USE_TYPE, isAnthropicToolResultType e i fallback call == null. Registra mcp_tool_use come tipo di chiamata in modo che la corrispondenza dei risultati basata sul suffisso esistente lo abbini a mcp_tool_result. Rispecchia la copertura esistente di server_tool_use in BraintrustAnthropicServerSideSpansTest.java ed esegui quella classe di test; fatto significa che lo span figlio MCP porta il nome reale dello strumento e input_json.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Summary
InstrumentationSemConv.addAnthropicServerSideChildSpans dispatches Anthropic Messages response content blocks by checking each block's "type" against the literal string "server_tool_use" (see ANTHROPIC_SERVER_TOOL_USE_TYPE and the dispatch check). Anthropic's MCP connector feature emits a different, distinct pair of block types for server-executed MCP tool calls: "mcp_tool_use" (the call) and "mcp_tool_result" (the result). "mcp_tool_use" does not match the "server_tool_use" check, so it is never registered in the call-tracking map used to pair calls with results.
Meanwhile "mcp_tool_result" does match the result-type check, which is a suffix check (type.endsWith("_tool_result") && !type.equals("tool_result")). So the result proceeds through the pairing logic, never finds its matching call, and is emitted alone with call == null.
Consequence for every MCP connector tool invocation:
- The child span is named generically
"mcp_tool"(derived by stripping"_tool_result"off the result's type) instead of the real tool name, because the fallback naming path only runs whencall == null. input_jsonis never set on the span, because the input-extraction path also returnsnullwhencall == null. The tool'sname,server_name, andinputarguments — which live only in the droppedmcp_tool_useblock — are permanently lost from the structured child span.
The raw response body is still present in the parent LLM span's full JSON passthrough, so the data isn't gone from Braintrust entirely, but the per-tool-call child span that Braintrust's UI specifically surfaces for tool calls is broken for every MCP connector invocation — call name and input are unrecoverable from that span.
Braintrust docs status: supported
Braintrust's docs at https://www.braintrust.dev/docs/integrations/ai-providers/anthropic describe this capability for the Python SDK: tool calls (including MCP connector tool calls) are captured "with its input and result ... named after the tool" as dedicated spans. This confirms the capability is documented/expected, just not delivered correctly by the Java SDK.
Why this isn't speculative
The identical bug (same mechanism: literal match on "server_tool_use", suffix-based result matching that doesn't require a paired call) was already found and fixed in Braintrust's Python SDK — see braintrustdata/braintrust-sdk-python#797 (fixed in py-sdk-v0.44.1) — and is tracked as still-open for the Go SDK in braintrustdata/braintrust-sdk-go#107. The fix was never ported to the Java SDK.
Upstream sources
- https://docs.anthropic.com/en/docs/agents-and-tools/mcp-connector — documents the
mcp_tool_use/mcp_tool_resultcontent block shapes (e.g.{"type":"mcp_tool_use","id":"mcptoolu_...","name":"<tool>","server_name":"<server>","input":{...}}), distinct fromserver_tool_use. - https://github.com/anthropics/anthropic-sdk-java/blob/v2.2.0/anthropic-java-core/src/main/kotlin/com/anthropic/models/beta/messages/BetaContentBlock.kt — confirms these block types were already modeled in the Anthropic Java SDK at the version this repo pins (2.2.0). This instrumentation parses raw JSON directly rather than typed SDK objects, so the gap is a pure string-literal dispatch miss, not an SDK-version-currency issue.
- https://github.com/braintrustdata/braintrust-sdk-python/issues/797 — identical bug, already fixed in the Python SDK.
- https://github.com/braintrustdata/braintrust-sdk-go/issues/107 — same class of bug, open in the Go SDK.
Local repo files inspected
braintrust-sdk/src/main/java/dev/braintrust/instrumentation/InstrumentationSemConv.java—ANTHROPIC_SERVER_TOOL_USE_TYPEconstant and dispatch check;addAnthropicServerSideChildSpans(call registration loop);isAnthropicToolResultType(suffix-based result matching);emitAnthropicServerToolSpan,anthropicToolSpanName,anthropicToolSpanInput(fallback behavior whencall == null).braintrust-sdk/instrumentation/anthropic_2_2_0/src/test/java/dev/braintrust/instrumentation/anthropic/v2_2_0/BraintrustAnthropicServerSideSpansTest.java— only exercisesweb_search/server_tool_use; nomcp_tool_use/mcp_tool_resulttest coverage exists.- Repo-wide search for
mcp_tool_use/mcp_tool_result/ "MCP connector" — zero matches outside this finding.
Suggested fix
Recognize "mcp_tool_use" as an additional call-type alongside "server_tool_use" when populating the call-tracking map (the existing suffix-based result matching already handles "mcp_tool_result" correctly once a matching call is registered), and add a test mirroring the existing server_tool_use test for the MCP connector block pair.
- Lingua principale
- Java
- Stelle
- 21
- Fork
- 5
- Merge medio
- 1g 1h
- PR unite (30g)
- 5
Preparare l'ambiente
- Nessun Dockerfile né file Docker Compose
- Nessun modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di braintrustdata/braintrust-sdk-java
-
java
Difficoltà 2/5 1-3 ore Idoneità per principianti 80/100
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
-
java
Difficoltà 4/5 3-5 giorni Idoneità per principianti 45/100
-
Difficoltà 5/5 Più di una settimana Idoneità per principianti 35/100
Tutte le issue di braintrustdata/braintrust-sdk-java
Issue simili
-
Update samples to Citrus 5.1.0Forse già presa @asuruceanu l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
snowflakedb/snowflake-kafka-connector#1610 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
swagger-api/swagger-petstore#245 ·
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
liquid-java/liquidjava#443 ·
I maintainer di solito rispondono entro 2 giorni