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

feat(agent-loop): open every prompt with the harness identity section

Browse Source 
A static harness:identity section at order -100 — the first occupant of
the documented negative band — states that the agent is powered by the
DeepSeek Harness SDK before the deployment's persona renders. Harness
attribution is a harness fact: it lives on the loop plugin, not in each
deployment's persona, so every agent (subagents included) carries it and
no YAML can forget it. A deployment that must drop it can remove the
section in the system-prompt/assemble waterfall.

Order-band docs updated in all five homes (PromptSection JSDoc, the
system-prompt and agent-loop READMEs, architecture.md, the RFC).
This commit is contained in:
Tianyi Cui
2026-07-05 11:37:32 +08:00
parent 2f191cc72b
commit 00cf8b693a
7 changed files with 31 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/architecture.md
View File

@@ -69,7 +69,7 @@ A `Session` is an append-only log of typed `SessionEvent`s — the single source
## Prompt assembly (dsh-system-prompt)
Plugins contribute `PromptSection`s (named, ordered, static or computed from the per-call `AssembleContext`), tool-schema providers, and named **prompt variables** interpolated as `{{name}}` at render (strict: an unknown or valueless reference throws). `renderPrompt(assemble({ agent }))` IS the full prompt: the loop's `agent:persona` section (order 0) and its `model`/`cwd` variables carry the per-agent facts — no second composition path. Tool schemas are deliberately part of the assembly ([RFC](rfc/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md)); prompt-fact ownership (persona vs description vs section vs variable) is pinned by [the prompt-variables RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
Plugins contribute `PromptSection`s (named, ordered, static or computed from the per-call `AssembleContext`), tool-schema providers, and named **prompt variables** interpolated as `{{name}}` at render (strict: an unknown or valueless reference throws). `renderPrompt(assemble({ agent }))` IS the full prompt: the loop's `harness:identity` (−100) and `agent:persona` (0) sections plus its `model`/`cwd` variables carry the harness and per-agent facts — no second composition path. Tool schemas are deliberately part of the assembly ([RFC](rfc/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md)); prompt-fact ownership (persona vs description vs section vs variable) is pinned by [the prompt-variables RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
## Tool pipeline (dsh-tools)

2
docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
View File

@@ -30,7 +30,7 @@ Plugins contribute named values via `ctx.systemPrompt.variable(name, provider)`;
### Persona as the order-0 section
The loop plugin registers ONE section, `agent:persona` at order 0, whose text is `context.agent?.options.systemPrompt ?? ''`. The loop's special-case join is deleted: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. Order bands are now convention: persona `0`, tool guidance `100–199`, negative orders render before the persona. `AgentOptions.systemPrompt` keeps its familiar key but is documented as what it is — the persona template fragment, one section of the full prompt, never the whole (see `CONTEXT.md`).
The loop plugin registers ONE section, `agent:persona` at order 0, whose text is `context.agent?.options.systemPrompt ?? ''`. The loop's special-case join is deleted: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. Order bands are now convention: harness identity `-100` (the loop's static `harness:identity` section — every agent's prompt opens by stating it is powered by the DeepSeek Harness SDK), persona `0`, tool guidance `100–199`; other negative orders also render before the persona. `AgentOptions.systemPrompt` keeps its familiar key but is documented as what it is — the persona template fragment, one section of the full prompt, never the whole (see `CONTEXT.md`).
### Tool guidance ownership