[email protected]andClaude Opus 4.6 5fcb4d3c03 feat: add tool execution idempotency cache ...

When the LLM re-requests the same idempotent tool with identical args
(common during self-repair recovery, stuck job retries, or chat-mode
retry loops), the cache returns the previous result instantly without
re-executing.

Design improvements over the closed PR #204:
- Single global LRU cache (lru crate) instead of per-job HashMap with
  O(N) manual eviction
- Global cap of 2000 entries prevents memory leaks from chat-path
  ephemeral job IDs that never get invalidated
- TTL expiry (30min) checked on read; LRU eviction handles the rest
- Job invalidation still runs on worker completion for prompt cleanup

Idempotent tools: echo, time, json, memory_read/search/tree,
read_file, list_dir, list_jobs, job_status.

Closes #204

Co-Authored-By: Claude Opus 4.6 <[email protected]>

2026-03-10 02:01:58 -07:00

..

assertions.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

cleanup.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

instrumented_llm.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

metrics.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

mod.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

test_channel.rs

feat: WASM channel attachments with LLM pipeline integration (#596)

2026-03-07 18:01:40 +00:00

test_rig.rs

feat: add tool execution idempotency cache

2026-03-10 02:01:58 -07:00

trace_llm.rs

fix(config): init_secrets no longer overwrites entire config (#726)

2026-03-08 13:32:42 -07:00