Yichen Jiang
ea4c10d753
Review discussion converged on the industry shape (Claude Code caches user context per conversation; Codex separates initial context from diffs; Kimi appends at continuation boundaries to protect prompt caching): stable openers belong in a compose-once prefix, mid-session changes belong in append-only history — not in a per-request slot. agent/session-prefix fires ONCE per loop instance, lazily on its first request-building step: the composed Message[] is deep-frozen, cached on the transmission bookkeeping, recorded as EpochHeader.messagePrefix on the anchoring 'initial'/'resume' snapshot, and reused verbatim for every request the instance sends — prefix stability is structural, not a producer discipline, and a resume recomposes with attributable drift. The request is messagePrefix + boundary snapshot. The per-step RequestAdvice/RequestAdviceContext surface and the messageSuffix header field are dropped: the tail slot had no consumer, and every current update pattern (new AGENTS.md discovered, memory update, skills change) routes through the existing append-only history channels — inject(), tools/post-execute additionalContext, prompt-submit additionalContext — each paid once and prefix-cached thereafter. The messagePrefix delta arm stays for codec totality; the loop never produces one in practice.
llm/ — LLM capability family
The LLM seam and its provider adapters. The interface package (llm) owns the abstract service, the content-block vocabulary, and the stream-chunk assembler; the adapters are concrete implementations that register on ctx.llm. All product packages.
| Package | Role | ctx key |
|---|---|---|
llm/ |
Abstract LLM service + content-block vocabulary + chunk assembler | ctx.llm |
llm-deepseek/ |
DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on ctx.llm) |
llm-pi-ai/ |
DeepSeek adapter via @earendil-works/pi-ai (design twin) |
(registers on ctx.llm) |
The interface lives at llm/llm/; adapters are flat siblings under the group. A new provider adapter joins here and registers on ctx.llm without touching the interface. See twin LLM adapters for why two adapters exist.