docs: add missing assistant.usage event fields to streaming-events reference (#2074)

* docs: add missing assistant.usage event fields to streaming-events reference

The assistant.usage event table was missing 8 fields that are present
in the AssistantUsageData interface:

- reasoningTokens: reasoning/chain-of-thought token count
- timeToFirstTokenMs: streaming latency (first token)
- interTokenLatencyMs: streaming throughput (avg inter-token)
- contentFilterTriggered: content filter detection
- finishReason: model finish reason (stop/length/content_filter)
- reasoningEffort: reasoning effort level used
- cacheExpiresAt: prompt cache expiration timestamp
- serviceRequestId: server-side request ID for log correlation

Also update the quick-reference table at the end of the file to
include the key new fields.

* docs: correct assistant usage reference

Clarify that serviceRequestId identifies the Copilot service request and keep the event quick reference focused on its established key fields.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: j-zhangyiyuan <j-zhangyiyuan@microsoft.com>
Co-authored-by: Steve Sanderson <1101362+SteveSandersonMS@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: 4 people

docs/features/streaming-events.md

@@ -443,12 +443,20 @@ Ephemeral. Token usage and cost information for an individual API call.
 | `model` | `string` | ✅ | Model identifier (e.g., `"gpt-5.4"`) |
 | `inputTokens` | `number` | | Input tokens consumed |
 | `outputTokens` | `number` | | Output tokens produced |
+| `reasoningTokens` | `number` | | Output tokens used for reasoning/chain-of-thought (subset of `outputTokens`) |
 | `cacheReadTokens` | `number` | | Tokens read from prompt cache |
 | `cacheWriteTokens` | `number` | | Tokens written to prompt cache |
+| `cacheExpiresAt` | `string` | | ISO 8601 timestamp when the prompt cache for this model call expires |
+| `contentFilterTriggered` | `boolean` | | Whether the response was blocked or truncated by content filtering (`finish_reason === 'content_filter'`) |
+| `finishReason` | `string` | | Model finish reason (e.g., `"stop"`, `"length"`, `"tool_calls"`, `"content_filter"`) |
 | `cost` | `number` | | Model multiplier cost for billing |
 | `duration` | `number` | | API call duration in milliseconds |
+| `timeToFirstTokenMs` | `number` | | Time from request dispatch to first token received (streaming latency) |
+| `interTokenLatencyMs` | `number` | | Average latency between consecutive tokens (streaming throughput) |
+| `reasoningEffort` | `string` | | Reasoning effort level used for this call (e.g., `"low"`, `"medium"`, `"high"`) |
 | `initiator` | `string` | | What triggered this call (e.g., `"sub-agent"`); absent for user-initiated |
 | `apiCallId` | `string` | | Completion ID from the provider (e.g., `chatcmpl-abc123`) |
+| `serviceRequestId` | `string` | | Copilot service request ID (`x-copilot-service-request-id`) for CAPI log correlation |
 | `apiEndpoint` | `"/chat/completions" \| "/v1/messages" \| "/responses" \| "ws:/responses"` | | API endpoint used for the model call; useful for observability and cost attribution. `ws:/responses` is the websocket variant of the responses API |
 | `providerCallId` | `string` | | GitHub request tracing ID (`x-github-request-id`) |
 | `parentToolCallId` | `string` | | Deprecated. Use envelope-level `agentId` for sub-agent attribution |