Python: surface Bedrock cache token counts in usage details

[he-yufeng]

Motivation & Context

The Bedrock chat client only surfaces input, output, and total token counts in usage_details. When prompt caching is active, the Bedrock Converse API also reports cacheReadInputTokens (input tokens served from a cache) and cacheWriteInputTokens (input tokens written to a cache), and _parse_usage drops both. So cache usage silently reads as zero for cached prompts, which throws off cost and token accounting.

UsageDetails already defines canonical fields for these (cache_read_input_token_count, cache_creation_input_token_count), and the OpenAI and Anthropic connectors already populate them, so Bedrock was the odd one out.

Description & Review Guide

• What are the major changes? BedrockChatClient._parse_usage now maps cacheReadInputTokens to cache_read_input_token_count and cacheWriteInputTokens to cache_creation_input_token_count, following the same is not None guard pattern as the existing three fields.
• What is the impact of these changes? Cache-read and cache-write token counts are now reported for Bedrock, consistent with the OpenAI and Anthropic connectors. Responses without prompt caching are unchanged (the fields stay unset).
• What do you want reviewers to focus on? That the Converse field names (cacheReadInputTokens / cacheWriteInputTokens) are mapped to the right UsageDetails keys.

Added test_parse_usage_surfaces_cache_tokens and ran the Bedrock test suite locally (8 passed). This mirrors #6638, which did the same for the Gemini connector.

Related Issue

Fixes #6639

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue.
• This is not a breaking change.

[Copilot]

Pull request overview

Surfaces Bedrock Converse prompt-cache token counts in the framework’s canonical usage_details so cached prompts don’t report zero cache usage, aligning Bedrock behavior with other connectors that already populate these fields.

Changes:

• Map Bedrock Converse cacheReadInputTokens → cache_read_input_token_count and cacheWriteInputTokens → cache_creation_input_token_count in BedrockChatClient._parse_usage.
• Add a Bedrock unit test asserting the cache token counts are surfaced.
• Also includes Gemini usage parsing + tests for cached/thinking token counts (note: this expands scope beyond the PR title/description).

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
python/packages/bedrock/agent_framework_bedrock/_chat_client.py	Map Bedrock Converse cache token fields into canonical UsageDetails keys.
python/packages/bedrock/tests/test_bedrock_client.py	Add unit test covering Bedrock cache token parsing.
python/packages/gemini/agent_framework_gemini/_chat_client.py	Add parsing of Gemini cached/thinking token counts into canonical usage fields.
python/packages/gemini/tests/test_gemini_client.py	Extend test helpers and add a test for Gemini cached/reasoning usage fields.

[eavanvalkenburg]

Please fix the comment from copilot

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/bedrock/agent_framework_bedrock
_chat_client.py	449	98	78%	304–305, 321–330, 336, 404, 413, 424, 426, 428, 433, 452–453, 477, 490, 502, 505, 513–514, 517–518, 520–521, 526–528, 530, 540–541, 563, 570, 579–580, 582–583, 585–587, 589, 591–592, 598–600, 603–604, 610–613, 619–629, 632, 651, 656, 706–707, 720, 746, 758, 763, 791, 795–796, 799, 817, 841, 853, 857, 871, 879–880, 884, 886–893
packages/gemini/agent_framework_gemini
_chat_client.py	380	3	99%	398, 821, 832
TOTAL	40636	4626	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
8098	34 💤	0 ❌	0 🔥	1m 59s ⏱️