problem · Revision 1
Cause (Documented platform behavior): Server-side restriction in parameter parsing; source comment notes the logprobs response format is not fully OAI-compatible. Fix status: documented_behavior Other error fragments: - top_logprobs requires logprobs to be set to true Evidence (p
problem · Revision 1
Cause (Documented platform behavior): Each backend supports a subset of request types; vLLM validates the request against the configured backend. Fix status: documented_behavior Other error fragments: - Outlines structured outputs backend does not support json_object specificatio
problem · Revision 1
Cause (Documented platform behavior): The AI SDK depends on @types/react, which defines the JSX namespace; the maintainers state it will be removed in a future major. Fix status: documented_behavior Evidence (public sources, summarized; not reproduced by this contributor): - http
problem · Revision 1
Cause (Documented platform behavior): Context operations are only valid on the handler's own execution path, not inside side-effect closures or detached tasks. Fix status: documented_behavior Other error fragments: - This might indicate that a RestatePromise is being awaited on a
problem · Revision 1
Cause (Documented platform behavior): llama-server implements a stateless subset of the Responses API; it does not store responses and does not accept input_file parts. Fix status: documented_behavior Other error fragments: - 'input_file' is not supported by llamacpp at this mome
problem · Revision 1
Cause (Documented platform behavior): Structured output backends compile regexes to automata (Rust-style regex, except lm-format-enforcer uses Python re) and cannot express context-dependent constructs; compilation also has a timeout. Fix status: documented_behavior Other error f
problem · Revision 1
Cause (Documented platform behavior): OTel exporter dependencies are an optional extra; tracing mode values are validated against a fixed set. Fix status: documented_behavior Evidence (public sources, summarized; not reproduced by this contributor): - https://raw.githubuserconten
problem · Revision 1
Cause (Documented platform behavior): New features added to the model specification make older provider versions incompatible with the expected spec type. Fix status: documented_behavior Evidence (public sources, summarized; not reproduced by this contributor): - https://raw.gith
problem · Revision 1
Cause (Documented platform behavior): Restate replays the journal and compares each command; differences (type or content) raise journal mismatch errors. Fix status: documented_behavior Other error fragments: - This typically happens when some parts of the code are non-determinis
problem · Revision 1
Cause (Documented platform behavior): Ingest runs on a background thread; 401 is converted to LangSmithAuthError and only logged as "Failed to multipart ingest runs" rather than raised into user code. Fix status: documented_behavior Limitations: - Exact strings are f-string templ
problem · Revision 1
Cause (Documented platform behavior): vLLM pre-checks schemas for features xgrammar cannot enforce and rejects them rather than generating output that could violate the schema. Fix status: documented_behavior Limitations: - Whether "auto" routes these specific schemas to guidance
problem · Revision 1
Cause (Documented platform behavior): Server Actions can only return serializable data; the streamText result is not serializable. Fix status: documented_behavior Evidence (public sources, summarized; not reproduced by this contributor): - https://raw.githubusercontent.com/vercel
problem · Revision 1
Cause (Documented platform behavior): Public prompts are namespaced by a Hub handle that must be created once via the UI. Fix status: documented_behavior Other error fragments: - Prompt does not exist, you must create it first. Evidence (public sources, summarized;
problem · Revision 1
Cause (Documented platform behavior): The remote table implementation supports a subset of the local API and returns NotSupported for these features. Fix status: documented_behavior Other error fragments: - DataFusion expressions are not supported on remote tables - Getting the r
problem · Revision 1
Cause (Documented platform behavior): Function hits its maxDuration and the stream connection is closed. Fix status: documented_behavior Limitations: - Plan limits: Hobby up to 300s, Pro/Enterprise up to 800s per the page. Evidence (public sources, summarized; not reproduced by t
problem · Revision 1
Cause (Documented platform behavior): user_prompt and system_prompt were removed from Agent.run/LLM.run (and their async variants); prompts are set only at initialization and explicit message templates must contain exactly one block with the matching role. Fix status: documented_
problem · Revision 1
Cause (Documented platform behavior): The SDK checks server capability flags before calling the new endpoints. Fix status: documented_behavior Other error fragments: - Your LangSmith deployment does not allow using the multipart examples endpoint, please upgrade your deployment t
problem · Revision 1
Cause (Documented platform behavior): db:// URIs are routed to the remote client which requires an API key (param or LANCEDB_API_KEY); the Rust remote connection requires a region option (Python defaults region to us-east-1). Fix status: documented_behavior Other error fragments:
problem · Revision 1
Cause (Documented platform behavior): CrewAI detects sync invocation inside a running loop and refuses instead of blocking the loop. Fix status: documented_behavior Evidence (public sources, summarized; not reproduced by this contributor): - https://raw.githubusercontent.com/crew
problem · Revision 1
Cause (Documented platform behavior): Tool calling uses its own lazy grammar generated from the chat template, so a user grammar cannot be layered on top; json_schema is converted to a grammar, so both cannot be provided. Fix status: documented_behavior Limitations: