- Reuse successful wire beta snapshots across thread turns and executor reloads.
- Keep continuations on their original credential and honor explicit payload/header policies.
- Recover snapshots through KV and publish state before streaming completion, with regression coverage.
Closes: #7470
Co-authored-by: Dylan <1990016@gmail.com>
Co-authored-by: lzt404 <2596933790@qq.com>
- Replace tidwall/gjson and tidwall/sjson with github.com/MoeForge/moego/ojson
and encoding/base64 with github.com/MoeForge/moego/base64 across the main
module and examples
- Introduce cross-method *ojson.Doc request rewriting pipelines across
thinking, signature, client/codex, runtime/executor/helps, pluginhost, and
all provider executors with FinalizePayloadDoc as the final semantic barrier
- Convert all consecutive JSON mutations (>= 2 Set/SetRaw/Delete operations)
to batch edits on ojson.Doc
- Upgrade read-only byte paths to ojson.GetBytesNoCopy,
ojson.GetManyBytesNoCopy, and util.ParseGJSONBytesNoCopy with explicit
strings.Clone ownership protection across streaming and persistent state
- Use base64.StdEncoding.ValidateString for zero-allocation signature checks
and base64.EncodeDataURL for single-allocation data URL construction
- Introduce `sessionObject` to index top-level JSON fields once for session key lookups
- Prevent repeated rescans of large message payloads when probing missing candidate keys
- Support duplicate top-level keys when resolving nested paths
Closes: #6114
- Share request payload reference during session identity enrichment when original request is unset
- Avoid cloning request payload when interceptors do not mutate the body
- Pass request body directly to handler and conductor interceptors
Closes: #6101
- Define context compaction, node kind, and LCP metadata keys in executor types
- Parse and populate `NodeKind`, `IsFork`, and `IsCompaction` on client request metadata during conductor execution
- Reset compaction, fork, and node kind state when canonical session ID is empty
Closes: #5980
- Decode and validate host affinity lookup requests for provider, model, and session ID.
- Query the active auth manager for session affinity bindings and status.
- Return lookup responses containing the auth index, observation timestamp, and credential availability state.
Closes: #5604
- Reject bare/empty session prefixes after unwrapping rather than projecting an empty string into a shared ghost UUIDv8.
- Include ctx:v1: and ctx: in knownSessionPrefixes to ensure identical canonical UUIDv8 projection for context root hashes.
- Strip known prefixes iteratively to support layered prefixes such as derived:ctx:v1:.
- Document knownSessionPrefixes as a transitional compatibility table slated for deprecation when session extractors emit canonical UUIDv8 directly.
- Add regression unit test coverage for empty prefixes, context root prefix parity, chained prefix unwrapping, and golden UUIDv8 assertion.
- Reuse coresession.ExtractSessionInfo across HTTP headers and request payloads to unify canonical session prefix namespaces with the scheduler.
- Extract hierarchical session identities in two phases: initial extraction from request headers on entry, and authoritative deep extraction once request payloads and metadata are available.
- Support Claude Code multi-level subagents (X-Claude-Code-Agent-Id, metadata.agent_id) and Codex thread fork lineages.
- Propagate SessionID and ParentSessionID across ClientRequestMetadata, UsageReporter, and coreusage.Record without root_session_id.
- Include session_id and parent_session_id in queuedUsageDetail for Home LPushUsage forwarding and Redis consumption with self-loop guards.
- Add comprehensive test coverage for canonical headers, body extraction, ghost parent elimination, and self-referential loop guards.
- root derived session ID in rolling prefix key to disambiguate conversations with different system prompts
- sanitize matcher config to guarantee MaxPrefixes >= MaxTurns
- tie-break tool parts sorting with digest for determinism
- Extract subagent IDs, user IDs, and prompt cache keys from nested `request` objects across session identity, session info, and auth selection.
- Normalize and fall back appropriately when top-level prompt cache key fields are empty strings.
- Inspect nested request fields when validating explicit session identities.
- Attach candidate upstream errors as causes to scheduler availability and cooldown errors.
- Introduce `errorWithCause` wrapper to extract and display upstream error summaries.
- Enrich auth selection error messages with upstream details and preserve model cooldown errors.
- Forward `Retry-After` response headers for model cooldown errors in Claude Code handler.
Closes: #5365
- Implement Merkle Longest Common Prefix (LCP) session affinity engine across OpenAI, Claude, Gemini, Interactions, and Responses protocols in sdk/cliproxy/session/lcp.go
- Implement in-memory hierarchical session tree store with dynamic lineage recalculation, reparenting, cycle prevention, and parentIndex descendant cascading in sdk/cliproxy/session/tree.go
- Integrate Merkle prefix matching and hierarchical session tree into SessionAffinitySelector
- Bound SessionCache capacity to 65,536 entries with deterministic eviction
- Support Claude nested metadata parent extraction and Header+Body parent merging
- Enforce TTL expiration checks in touchLocked and bindLocked
- Propagate ParentSessionID in authDispatchRequest and RPopAuthWithSessionHierarchy for distributed Home dispatch
- Add isHierarchyParent in home_session_alias.go covering Claude, Codex, Pi slot, Antigravity, and Gemini caching
- Add comprehensive test suites in lcp_test.go, tree_test.go, selector_lcp_test.go, client_test.go, and home_session_alias_test.go
gjson.GetBytes copies the matched subtree before returning it, so every read of
request.contents on a multi-megabyte request allocated another copy of it. The
reasoning replay, executor, signature validation and session identity paths all
read whole arrays this way, and hasExplicitSession parsed the entire body with
gjson.ParseBytes on every request.
Use the no-copy helpers for these reads. Each call site only reads from the
result and writes through sjson, which allocates a new buffer, so the payload
stays immutable while the results are alive.