raindrop-azure-openai

Raindrop observability integration for Azure OpenAI (Python). Automatically captures chat.completions.create() calls by wrapping AzureOpenAI and AsyncAzureOpenAI clients.

Installation

pip install raindrop-azure-openai openai

Quick Start

from raindrop_azure_openai import RaindropAzureOpenAI
from openai import AzureOpenAI

raindrop = RaindropAzureOpenAI(
    api_key="rk_...",
    user_id="user-123",
    debug=False,  # set True for verbose logging
)

client = AzureOpenAI(
    azure_endpoint="https://your-resource.openai.azure.com",
    api_key="...",
    api_version="2024-10-21",
)
wrapped = raindrop.wrap(client)

response = wrapped.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

raindrop.shutdown()

Projects

Route events to a specific project by passing its slug as project_id:

raindrop = RaindropAzureOpenAI(
    api_key="rk_...",
    project_id="support-prod",
)

project_id sets the X-Raindrop-Project-Id header on every event. Omit it (or pass "default") to use your org's default Production project, which is the existing behavior. The same option is accepted by the create_raindrop_azure_openai(...) factory. Invalid slugs are ignored with a warning and no header is sent.

Debug Mode

raindrop = RaindropAzureOpenAI(api_key="rk_...", debug=True)

When debug=True, verbose logs are emitted to the raindrop_azure_openai logger at DEBUG level.

Async Support

from raindrop_azure_openai import RaindropAzureOpenAI
from openai import AsyncAzureOpenAI

raindrop = RaindropAzureOpenAI(api_key="rk_...", user_id="user-123")

client = AsyncAzureOpenAI(
    azure_endpoint="https://your-resource.openai.azure.com",
    api_key="...",
    api_version="2024-10-21",
)
wrapped = raindrop.wrap(client)

response = await wrapped.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

raindrop.shutdown()

Per-call properties and identity

chat.completions.create has no channel for your own event data, so wrap the call in event_context. Its properties merge into every event captured inside the block, and user_id / convo_id replace the constructor values for those events:

from raindrop_azure_openai import event_context

with event_context(user_id="user-123", convo_id="conv-9", properties={"plan": "pro"}):
    wrapped.chat.completions.create(model="gpt-4o-mini", messages=[{"role": "user", "content": "Hello!"}])

Updating the last event

last_event_id is the event_id of the most recent event this wrapper captured. Use it to attach a signal, or reopen the event with resume_interaction() (defaults to last_event_id) and update it through the core SDK's Interaction:

interaction = raindrop.resume_interaction()
if interaction is not None:
    interaction.set_properties({"reviewed": True})
    interaction.finish()

Key clashes. If one of your properties has the same key as one the wrapper derives itself, your value wins, whichever update carries it (a debug-level log line names the key). The wrapper's own keys are ai.* (for example ai.usage.prompt_tokens), error/error.* and azure_openai.*; avoid them unless you mean to replace the wrapper's value.

Property-only updates need raindrop-ai 0.0.76 or newer; older core versions drop an update that carries no input or output.

last_event_id is per wrapper instance; under concurrent calls it is whichever event was captured last, so pass event_id= when you need to correlate concurrent calls.

User Identification

raindrop.identify("user-123", traits={"plan": "pro", "name": "Alice"})

Tracking Signals

raindrop.track_signal(
    event_id="evt-abc",
    name="thumbs_up",
    signal_type="feedback",
    sentiment="POSITIVE",
    comment="Great response!",
)

Flushing and Shutdown

raindrop.flush()     # flush pending data
raindrop.shutdown()  # flush + release resources

Factory Function (Backwards-Compatible)

from raindrop_azure_openai import create_raindrop_azure_openai

raindrop = create_raindrop_azure_openai(api_key="rk_...", user_id="user-123")
# raindrop is now a RaindropAzureOpenAI instance with .wrap(), .flush(), .shutdown()

What Gets Captured

• Chat completions — input messages, output text, model, token usage
• Finish reason — azure_openai.finish_reason (stop, length, content_filter, tool_calls)
• Extended tokens — ai.usage.cached_tokens (prompt cache hits) and ai.usage.thoughts_tokens (reasoning tokens for o1/o3 models)
• Errors — error type and message captured as properties, then re-raised to the caller
• Async support — both sync (AzureOpenAI) and async (AsyncAzureOpenAI) clients are instrumented

Configuration

Library auto-instrumentation is opt-in

As of 0.0.4, disable_auto_instrument defaults to True: the integration no longer lets Traceloop monkey-patch every LLM client library it recognizes in your process (the OpenAI client itself, Anthropic, botocore, etc.). The wrapper captures input/output, token usage, model name, and finish_reason directly from the wrapped client's responses, so no library patching is needed for full dashboards.

Model spans need no library instrumentation: the wrapper records its own (see Model spans). If you specifically want the instrumentor's spans instead and have verified compatibility in your environment, opt back in with disable_auto_instrument=False; the wrapper then adds no span for calls that instrumentation already records.

Tool catalog capture (ai.prompt.tools)

Every model span records the tools the request carried as ai.prompt.tools: an OTel string array, one JSON document per tool with name, description and the full JSON Schema as inputSchema ({"type": "function", ...}), or {"type": "provider-defined", ...} for provider-owned tools. The capture is exact, per call: the wrapped chat.completions.create(...) sees the request's own tools= (or legacy functions=) and binds that list through the core's prompt_tools_scope mechanism for the duration of the call, sync and async. A request with neither records []. Streaming (stream=True) is covered because the instrumentor starts the model span inside create(), while the list is bound; the response being consumed later does not matter.

With disable_auto_instrument=False, model spans come from the OpenLLMetry OpenAI instrumentor. OpenLLMetry 0.62 writes the same list to gen_ai.tool.definitions, not llm.request.functions.*; raindrop-ai 0.0.70 / 0.0.71 do not rebuild ai.prompt.tools from that attribute and 0.0.72 does, so the wrapper-side scope is what puts the attribute on the span on every core version, and it takes precedence over the rebuilt list when both are present. With the default disable_auto_instrument=True, the wrapper's own model span (see Model spans) carries it.

Override:

rd = RaindropAzureOpenAI(api_key="...", user_id="u1", disable_auto_instrument=False,
                         tools=[{"type": "function", "name": "get_weather", "inputSchema": {...}}])
client = rd.wrap(AzureOpenAI(...))                 # constructor default applies to every call
client = rd.wrap(AzureOpenAI(...), tools=[...])    # per-wrap value replaces the default

tools=[] at either level records an empty catalog. An enclosing raindrop.prompt_tools(...) / begin(..., tools=...) scope is also treated as an override and is never shadowed by the request's list.

Semantics shared with every Raindrop SDK:

• Attribute absent: the wrapper could not see the tool list (or there is no model span, see below).
• []: the model had no tools.
• Override replaces, never merges. A tools= you pass wins over anything inferred; tools=[] records an empty catalog.
• Content gate. Tool definitions are prompt content. With TRACELOOP_TRACE_CONTENT=false nothing is recorded, overrides included.
• Malformed entries are skipped with a debug log; nothing here raises into your application.

Accepted shapes for tools=: canonical {"type": "function", "name", "description", "inputSchema"}, OpenAI {"type": "function", "function": {...}}, Anthropic {"name", "description", "input_schema"}, and {"type": "provider-defined", "name", ...}. The core normalises them; the JSON Schema is kept exactly as given.

Needs raindrop-ai>=0.0.70; on an older core the wrapper logs at debug and records nothing.

Double-Wrap Protection

Calling wrap() on an already-instrumented client is a safe no-op — the client is returned unchanged.

Standard options and flush results

When the wrapper builds its own client, it accepts the core SDK's standard options by the same names and passes them on:

raindrop = RaindropAzureOpenAI(
    api_key="rk_...",
    user_id="user-123",
    redact_pii=True,        # local PII redaction of event input/output
    flush_timeout=5,        # seconds; deadline for flush() and shutdown()
    debug=True,             # also raises the core SDK's log verbosity
    max_queue_size=5_000,   # any other option `Raindrop(...)` declares
)

result = raindrop.flush()   # the core's FlushResult; safe to ignore

• An option the installed raindrop-ai does not support is ignored with a debug log, never an error. flush_timeout and the FlushResult return value need raindrop-ai 0.0.76 or later; on older releases flush() and shutdown() return None.
• With client= (a Raindrop you built), configure these options on that client; the wrapper ignores them (debug log).
• flush() and shutdown() never raise. The result is truthy when everything was delivered, and reports pending, dropped and timed_out.

Full Documentation

See the Raindrop docs for the complete reference.

Application Git metadata

RaindropAzureOpenAI(...) and create_raindrop_azure_openai(...) accept the keyword-only app_git option. It defaults to True: explicit Raindrop Git environment or deployment context is applied immediately, and the base SDK may perform one bounded background local-Git lookup from the process working directory. Event capture, flush, and shutdown never wait for that lookup. Pass False to disable enrichment, or pass an AppGitOptions mapping with commit_sha, commit_dirty, branch, source_directory, detect_branch, and/or auto_detect. Automatic branch discovery remains opt-in through detect_branch=True (or RAINDROP_GIT_DETECT_BRANCH=true).

For an ordinary in-process application, the process working directory is treated as the application-under-test checkout. A remote, coding, workflow, or observer process must not rely on its own checkout: pass app_git=False, provide explicit revision values, or set source_directory to the actual application checkout. Canonical per-operation properties remain authoritative. When supplying client=, configure app_git while constructing that Raindrop client; the supplied client is authoritative and the wrapper's app_git argument does not reconfigure it.

Release order is deliberate: first publish the base SDK feature, then publish the wrapper feature release with its minimum dependency coordinated to that base release. The existing raindrop-ai lower bound remains compatible, but application Git metadata is unavailable on an older core and must not be claimed complete until the base is upgraded. Until coordination assigns a released version, the wrapper checks for an explicit base app_git parameter and omits the option when unsupported. Explicit non-default configuration is debug-logged and omitted. Unsupported app_git is determined by signature inspection before construction, not by retrying initialization after a TypeError; Git configuration adds no initialization attempts and does not change any existing framework-specific initialization fallback.

User id

Every event needs a real user id: set user_id= on the wrapper or per call with event_context(user_id=...). Without one (missing, blank, or a placeholder such as "unknown" or "anonymous"), the event is not sent and the wrapper logs one warning; it never raises. Updating an event you resumed with resume_interaction(event_id=...) needs no user id, since ingest keeps the one it stored.

Model spans

With tracing on (the default), the wrapper records each chat.completions.create call as a span on the Raindrop client's tracing. The span carries:

• the model: gen_ai.provider.name (canonical name, such as openai or amazon-bedrock), gen_ai.request.model and gen_ai.response.model;
• the token usage the provider reports: gen_ai.usage.input_tokens, output_tokens, cache_read_input_tokens, cache_write_input_tokens and reasoning_tokens;
• the event it belongs to: ai.telemetry.metadata.raindrop.eventId and the traceloop.association.properties.* keys.

Token usage also stays on the event as ai.usage.* properties. When an OpenTelemetry instrumentation that sees the call already records it (the provider's own instrumentation, for example with auto_instrument=True on the client), the wrapper adds no span of its own, so a call is never counted twice. An instrumentation for another provider or library does not suppress the wrapper's span.

Testing

cd packages/azure-openai-python
pip install -e ".[dev]"
python -m pytest tests/ -v   # unit tests (no external services)

End-to-end behavior is verified by the cross-SDK conformance harness. This package ships a thin conformance driver at conformance/driver.py that maps the shared scenario corpus onto the wrapper's public API; known gaps are tracked as ticket-linked entries in conformance/failures.txt. The fault lane runs on every PR touching packages/*-python/** (.github/workflows/conformance-wrappers-python.yml) against a local capture server; the prod lane verifies delivery by reading back through the public Query API. The harness is pinned by commit SHA (HARNESS_REF). See the harness docs: HOW-IT-WORKS · AGENTS · README.

License

MIT