Repository navigation
Custom baseURL providers report zero prompt cache tokens for subagent sessions #30663
Description
Description
When using a custom OpenAI-compatible baseURL, prompt cache accounting stays at zero for subagent sessions.
I tested both provider configurations:
npm: "@ai-sdk/openai"with a custombaseURLnpm: "@ai-sdk/openai-compatible"with a custombaseURL
In both cases, after running a subagent task and exporting the subagent session with opencode export <sessionID>, the exported subagent session reports:
"tokens": {
"cache": {
"read": 0,
"write": 0
}
}Each assistant message in the exported subagent session also reports tokens.cache.read = 0 and tokens.cache.write = 0.
The same custom endpoint does report prompt cache normally in the main conversation. The zero cache accounting appears specific to subagent sessions.
This looks related to, but not identical to:
- setCacheKey sends promptCacheKey (wrong) instead of cache_control on content blocks for openai-compatible Bedrock proxies (Bifrost, LiteLLM) #25984, which covers
@ai-sdk/openai-compatiblesending the wrong caching shape for some custom/proxy backends. - Prompt Caching Not Working for Xiaomi/MiMo Models #26460, which reports zero cache hits for a direct custom API using
@ai-sdk/openai-compatible.
The difference here is that the issue reproduces with both @ai-sdk/openai and @ai-sdk/openai-compatible, while the main conversation cache works normally. The observed symptom is specifically exported subagent sessions reporting zero cache read/write tokens.
Plugins
None
OpenCode version
1.15.13
Steps to reproduce
- Configure a custom provider with a custom OpenAI-compatible
baseURLusing@ai-sdk/openai. - Run a normal main conversation and confirm prompt cache accounting is non-zero.
- Run a simple subagent task, for example an
exploresubagent that reads a few repository files. - Export the subagent session:
opencode export <subagent-session-id>- Observe that the exported subagent session has
tokens.cache.read = 0andtokens.cache.write = 0. - Repeat with the same custom
baseURLconfigured through@ai-sdk/openai-compatible. - Observe the same zero cache accounting in the exported subagent session.
Expected behavior: if prompt caching is enabled and reported for the custom endpoint in the main conversation, subagent sessions should report cache read/write token counts consistently as well.
Actual behavior: both provider paths report zero cache read/write tokens for exported subagent sessions, while the main conversation cache works normally.
Operating System
Windows / win32
Terminal
PowerShell / Windows terminal environment
Activity
ulises-jeremias commentedon Jun 4, 2026
I investigated this path and prepared a fix.
Root cause: cache token extraction in
Session.getUsage()was mostly usage-field driven (usage.cacheReadInputTokens/usage.cacheWriteInputTokens) with provider-specific metadata fallback for Anthropic/Vertex/Bedrock/Venice only.For custom OpenAI-compatible endpoints, cache counts can arrive in provider metadata under an OpenAI-style payload (
usage.prompt_tokens_details.cached_tokens) instead of normalized usage fields. In that case, session token accounting records cache read/write as zero, which matches the symptom reported for exported subagent sessions.Fix approach:
Session.getUsage()for OpenAI-style metadata usage payloads.prompt_tokens_details.cached_tokensas cache read fallback.cache_creation_input_tokens/cacheWriteInputTokens).I’m opening a PR with this now.
ThreeIce commentedon Jun 4, 2026
I'll test it after the pr is merged. But I suspect the issue might be a cache failure, rather than just a stats error. I'm charged as if there is no cache.
Image 1 shows the scenario where the requests failed to be cached. Image 2 shows the expected scenario.
Necmttn commentedon Jun 22, 2026
I would make the regression compare main and subagent usage provenance directly.
For each exported session, keep parent session id, child session id, provider raw usage path, normalized usage fields, metadata fallback path used, cache read/write tokens, and
cache_status(reported_zero,not_reported,parsed_from_metadata,provider_absent). That separates an actual cache miss from a subagent export/parser path that dropped the cache fields.Generated with ax - https://github.com/Necmttn/ax
ulises-jeremias commentedon Jul 14, 2026
Reopened the fix PR after automated cleanup closure: #36861
@nexxeln could you please take a look when you get a chance? Thanks!
github-actions commentedon Sep 14, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.