Anandan 739a47e3ea perf(agent): preserve prompt cache prefixes (#760) ...

* perf(agent): preserve prompt cache prefixes

Build the system prompt once per run, fingerprint the exact emitted prompt and ordered tool definitions, and expose the full system-prompt hash in traces.

Add normalized and serialized two-turn regressions covering append-only messages, stable tools, and a stable session cache key.

* fix(tools): stabilize registry iteration order

Return registered tools in name order so provider-visible tool lists and prompt-prefix fingerprints cannot drift with Go map iteration. Add a regression covering the registry ordering contract.

2026-07-19 20:29:58 +05:30

..

anthropic

feat: agent quality, caching, retry, and tooling upgrades (#506)

2026-07-05 17:25:26 +08:00

gemini

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

openai

perf(agent): preserve prompt cache prefixes (#760)

2026-07-19 20:29:58 +05:30

providerio

Add per-turn tracing and a turn-benchmark harness (Phase 0 baseline) (#700)

2026-07-16 21:58:20 +08:00

factory_test.go

feat(providers): add AI/ML API preset (rebased onto main) (#621)

2026-07-16 22:57:35 +08:00

factory_turn_session_test.go

perf(providers): provider capabilities and default turn-session adapter (PR7) (#720)

2026-07-18 09:33:07 +05:30

factory.go

perf(providers): provider capabilities and default turn-session adapter (PR7) (#720)

2026-07-18 09:33:07 +05:30

turn_session_gate_test.go

perf(openai): optimized turn session — background prewarm and prefix telemetry (PR8) (#723)

2026-07-18 14:24:50 +05:30

turn_session.go

perf(openai): optimized turn session — background prewarm and prefix telemetry (PR8) (#723)

2026-07-18 14:24:50 +05:30