Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: retire completed tagged-envelope review TODO

Browse Source
This commit is contained in:
Tianyi Cui
2026-06-19 09:28:23 +08:00
parent 350e66982e
commit 4a1c64663b
3 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/rfc/implemented/2026-06-11-content-block-vocabulary.md
View File

@@ -12,10 +12,10 @@ The harness needs one internal language for messages that the loop, session log,
Own it: messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`, `image`), with the union derived from the merge-extensible `ContentBlockMap` so plugins add block types via declaration merging. The same merge-extensible-map pattern types every "stringly" field (`MessageSource`, `FinishReason`, `TurnTrigger`, `TurnEndReason`). Streaming is a raw chunk protocol; `BlockAssembler` is the single shared assembly implementation. Adapters translate to provider wire formats — mapping cost lives in adapters, where it belongs.
In-session context injection (`context/message`, `steering/message`) renders as tagged user-role envelopes (the system-reminder pattern) rather than a new role, so adapters carry zero burden. TODO(review): verify the tagged-envelope rendering against live model behavior; the real adapters that were the original precondition now exist (see the twin-adapter RFC).
In-session context injection (`context/message`, `steering/message`) renders as tagged user-role envelopes (the system-reminder pattern) rather than a new role, so adapters carry zero burden. Live-adapter review has since validated the tagged-envelope rendering against current DeepSeek behavior; a future provider-specific mismatch should be handled in that adapter rather than by adding a new role to the canonical content vocabulary.
## Consequences
- Reasoning, prefill, cache hints, and multimodal content all have a home without provider contortions.
- Every adapter pays a translation cost; the streaming protocol carries a TODO(review) marker until the first real adapter validates it.
- Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests.
- IDs that cross package boundaries are branded (`CallId`, `SessionId`, `AgentId`) — nominal typing at zero runtime cost.