feat: odek v2 merge-blocker gaps (cache usage, idle timeout, reasoning replay) - #4
Merged
Conversation
…g replay) Normalize provider cache tokens to exclusive PromptTokens so odek can budget without double-counting, and close the remaining v2 wire gaps: idle-watchdog setter, reasoning_content replay, GLM thinking map, user-message cache markers, Retry-After cap, and CF 520-524. Co-authored-by: Cursor <cursoragent@cursor.com>
Concatenating system blocks collapsed prompt-tiering (stable base + volatile memory) and busted prefix cache on every memory refresh. Co-authored-by: Cursor <cursoragent@cursor.com>
5 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
CacheReadTokens,CacheCreationTokens,CachedTokens,CacheReported) with odekapplyUsagenormalization so OpenAI/DeepSeek inclusive volumes are subtracted fromPromptTokensand Anthropic exclusive volumes are left alone.SetStreamIdleTimeout/StreamIdleTimeout, replay OpenAI-formatreasoning_contenton assistant turns, map GLM thinkingmedium→highandmax→max, and emit Anthropic user-messagecache_controlwhenMessage.Cacheis set.Retry-Afterat 120s, treat Cloudflare 520–524 as retryable, recognize the OpenAI “exceeded your current quota” billing marker, and honorHTTP_PROXYon the pooled transport.Test plan
go test -count=1 -timeout 120s .(green)CheckUsageWithCachefromUsagecache fields without double-countingMade with Cursor