- Add Claude replay enablement and scope derivation for API-key compatible Claude requests with isolated model/session keys.
- Restore cached signed reasoning blocks into outbound requests and persist completed assistant turns after execution, including stream handling.
- Introduce a dedicated Claude thinking-replay cache with local + home-KV paths, CAS-based snapshot replace/clear, TTL/size limits, and bounded eviction/expiration management.
Closes: #4856
Classify malformed caller metadata and Fast failures as request-scoped, reuse the strict Anthropic origin gate, bound diagnostics and proxy caches, and remove the unrelated translator test change.
- Added logic for caching and restoring Kimi "Thinking Replay" states to improve continuity across requests.
- Implemented `kimiThinkingReplayScope`, content replay preparation, and conditional cache storage based on replay validity.
- Introduced helper methods for replay content restoration, caching, and cleanup on errors.
- Enhanced executor workflows to utilize the "Thinking Replay" cache for both immediate and streaming response handling.
- Integrated periodic cleanup of expired and oversized replay cache entries.
Closes: #4695
Client.KVCompareAndSwap sent Redis EVAL with a Lua script, but the Home RESP
subset does not implement EVAL, so Home replied "ERR unknown command 'eval'".
That broke the Antigravity and Codex reasoning replay caches in Home mode.
Switch the transport to Home's dedicated CAS command:
CAS <key> <expected-exists 0|1> <expected-value> <new-value> [PX <ttl-ms>]
The semantics match the old script argument for argument, so KVCompareAndSwap's
signature and all its callers are unchanged. Omitting PX when ttl <= 0 mirrors
the script's SET-without-PX branch, which clears the TTL.
Deployments that predate CAS reject the command. Detect that by matching the
unsupported-command error, latch ErrCompareAndSwapUnsupported for the client
lifetime so later calls skip the round trip, and warn exactly once. The latch is
deliberately not carried across NewLifetime, so a Home upgrade takes effect on
the next reconnect rather than requiring a CPA restart.
Also stop replay-state failures from failing the request. A bare replay error has
no HTTP status, so resultErrorFromError does not classify it as request-scoped and
MarkResult marks the credential unavailable for that model, walking every
candidate credential until alias resolution has nothing left and returns 503. A
ledger miss is already a tolerated outcome, so degrade to "no replay this turn"
instead. The pairing failure still returns its 400.
Verified end to end against a real Home over RESP/mTLS on PostgreSQL with
Antigravity OAuth credentials: patched Home recreates the replay row through CAS
with its TTL, while a pre-CAS Home latches once, keeps returning 200 instead of
503, and records no credential error attributable to the replay path.
Refs router-for-me/CLIProxyAPIHome#79
- Introduced agent-specific cache key isolation to ensure distinct prompt caching across agents.
- Improved reasoning replay handling for Claude models, including cumulative tool turn restoration and validation.
- Enhanced HTTP and WebSocket session consistency during execution scope and cache replay synchronization.
- Added new unit tests and extended coverage for prompt caching, agent isolation, and replay cache functionality.
Closes: #4352
Preserve include=reasoning.encrypted_content, cache reasoning+assistant message
for store:false multi-turn, and accept Grok thinking signatures on Claude→Codex
for grok targets.
Harden replay cache: blob-level reasoning filter, never double-inject assistant
when history has a last message, isolate session keys by downstream API key,
clear cache on non-replayable completed turns, and normalize refusal parts.
Add Grok-native reasoning replay for Claude-sourced xAI Responses requests. Replay state is scoped by model and session, normalized to reasoning/function_call/custom_tool_call items, and injected with the same tool-call alignment semantics used by Codex.
Include the minimal Grok encrypted_content validator needed on upstream/dev so replay cache entries cannot accept Codex/GPT, Gemini, or Claude signature shapes. Cache completed output items from HTTP, streaming, and WebSocket xAI responses.
Cover two-turn Claude replay, tool_result continuity, valid Grok cache storage, and rejection of Codex-shaped encrypted_content.
Add executor-scoped replay cache aligned with Codex HOME replay:
Scope, observe SSE/non-stream responses, store normalized thought_signature
and function_call_part items, apply on the next streamGenerateContent
request, and invalidate on invalid signature responses.
Gemini/flash/agent models use HOME replay; native per-part signature
replay is not wired on upstream/dev. Wire non-stream and stream paths
in antigravity_executor and purge expired entries from signature_cache.
Includes unit tests and HOME-provider-replay documentation.
Add executor-scoped replay cache aligned with Codex HOME replay:
Scope, observe SSE/non-stream responses, store normalized thought_signature
and function_call_part items, apply on the next streamGenerateContent
request, and invalidate on invalid signature responses.
Gemini/flash/agent models use HOME replay; native per-part signature
replay is not wired on upstream/dev. Wire non-stream and stream paths
in antigravity_executor and purge expired entries from signature_cache.
Includes unit tests and HOME-provider-replay documentation.
- Updated Antigravity Credits fallback to handle KV store unavailability as a service error.
- Enhanced signature caching mechanisms with request-time KV access and sliding expiration.
- Added and improved tests for KV client interactions, including error handling and expiration behaviors.
- Introduced `CacheSignatureBestEffort` for non-critical signature caching and clarified function flows with required context.
- Ensured consistent error reporting for missing or unavailable KV stores in various scenarios.
- Replaced direct `homekv` calls with injectable KV client interfaces for `antigravity` and `codex_reasoning_replay` modules.
- Improved error reporting and handling for KV operations, including `KVGet`, `KVSet`, `KVDel`, and `KVExpire`.
- Introduced dedicated fake KV clients for expanded and granular test coverage.
- Added new unit tests to validate KV client behaviors and error scenarios, ensuring robustness and sliding expiration functionality.
Improve the cache eviction routine to sort entries by timestamp using the standard library sort routine (stable, clearer and faster than the prior manual selection/bubble logic), and remove a redundant request-derived session ID helper in favor of the centralized session ID function. Also drop now-unused crypto/encoding imports.
This yields clearer, more maintainable eviction logic and removes duplicated/unused code and imports to reduce surface area and potential inconsistencies.
