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

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).

docs/architecture.md

@@ -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)
 

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

@@ -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
 

packages/core/agent-loop/README.md

@@ -33,7 +33,7 @@ interface Config {
 }
 ```
 
-Agents listed in config are auto-created at startup. The plugin also registers the per-agent prompt pieces on `ctx.systemPrompt`: the `agent:persona` section (order 0 — `AgentOptions.systemPrompt` renders before all tool guidance) and the built-in `model`/`cwd` prompt variables, each resolved per step from the `assemble({ agent })` context.
+Agents listed in config are auto-created at startup. The plugin also registers the harness-owned prompt pieces on `ctx.systemPrompt`: the `harness:identity` section (order −100 — every agent's prompt opens by stating it is powered by the DeepSeek Harness SDK), the `agent:persona` section (order 0 — `AgentOptions.systemPrompt` renders after it, before all tool guidance), and the built-in `model`/`cwd` prompt variables, resolved per step from the `assemble({ agent })` context.
 
 ### Classes
 

packages/core/agent-loop/src/index.ts

@@ -82,13 +82,20 @@ export class AgentLoop extends Service implements AgentFactory {
     // Provide the agent-creation factory to the registry (effect-scoped: the
     // slot is cleared on dispose).
     ctx.effect(() => this.ctx.agents.setFactory(this), 'agentLoop.setFactory()')
-    // The per-agent prompt pieces, registered once and resolved per assembly
-    // from the AssembleContext the loop passes (loop.ts assembles with
-    // `{ agent }` each step). The persona is the order-0 section — identity
-    // renders before all tool guidance; `{{model}}`/`{{cwd}}` are the built-in
-    // prompt variables projecting the agent's configured model and its
-    // session workspace. A provider returns undefined when the fact is absent
-    // (renderPrompt then rejects a persona that claims it — fail loud).
+    // The prompt pieces the harness itself owns, registered once. The
+    // harness-identity section states what every agent on this loop IS,
+    // ahead of everything (order −100 — before the deployment's persona);
+    // the persona is the order-0 section resolved per assembly from the
+    // AssembleContext the loop passes (loop.ts assembles with `{ agent }`
+    // each step); `{{model}}`/`{{cwd}}` are the built-in prompt variables
+    // projecting the agent's configured model and its session workspace. A
+    // provider returns undefined when the fact is absent (renderPrompt then
+    // rejects a persona that claims it — fail loud).
+    ctx.systemPrompt.section({
+      name: 'harness:identity',
+      order: -100,
+      text: 'You are an AI agent powered by the DeepSeek Harness SDK.',
+    })
     ctx.systemPrompt.section({
       name: 'agent:persona',
       order: 0,

packages/core/agent-loop/tests/loop.spec.ts

@@ -141,7 +141,7 @@ describe('agent loop', () => {
       .toEqual({ diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] })
   })
 
-  it('renders the persona as the order-0 section — before tool guidance — with {{variables}} resolved', async () => {
+  it('renders harness identity, then the persona, then tool guidance — with {{variables}} resolved', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
     ctx.systemPrompt.section({ name: 'tool:noop', order: 100, text: 'Use the noop tool wisely.' })
@@ -161,7 +161,7 @@ describe('agent loop', () => {
     await waitForIdle(ctx, agent)
 
     const request = adapter.requests[0]
-    expect(request!.system).toBe('You are a test agent on mock.\n\nUse the noop tool wisely.')
+    expect(request!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a test agent on mock.\n\nUse the noop tool wisely.')
     expect(request!.tools?.map(t => t.name)).toEqual(['noop'])
   })
 
@@ -179,7 +179,7 @@ describe('agent loop', () => {
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
 
-    expect(adapter.requests[0]!.system).toBe('Working in /work/space.')
+    expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nWorking in /work/space.')
   })
 
   it('contains a strict-variable render failure: the turn errors, the loop keeps serving turns', async () => {
@@ -212,7 +212,7 @@ describe('agent loop', () => {
     await waitForIdle(ctx, agent)
 
     expect(adapter.requests).toHaveLength(1)
-    expect(adapter.requests[0]!.system).toBe('In /rescued.')
+    expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nIn /rescued.')
     const turnEnds = agent.session.events.filter(e => e.type === 'turn/end')
     expect(turnEnds).toHaveLength(2)
     expect(turnEnds[1]?.type === 'turn/end' && turnEnds[1].data.reason.kind).toBe('completed')
@@ -426,10 +426,12 @@ describe('agent loop', () => {
     send(agent, 'go')
     await waitForIdle(ctx, agent)
 
-    // One fire per step, in order, each with the assembled system prompt.
+    // One fire per step, in order, each with the assembled system prompt
+    // (here just the loop's own harness-identity section — no persona set).
+    const HARNESS = 'You are an AI agent powered by the DeepSeek Harness SDK.'
     expect(fires).toEqual([
-      { turn: 1, step: 1, fullSystemPrompt: '' },
-      { turn: 1, step: 2, fullSystemPrompt: '' },
+      { turn: 1, step: 1, fullSystemPrompt: HARNESS },
+      { turn: 1, step: 2, fullSystemPrompt: HARNESS },
     ])
   })
 

packages/core/system-prompt/README.md

@@ -21,7 +21,7 @@ System prompt assembly registry. Plugins contribute ordered text sections, tool-
 ### Key types
 
 - `AssembleContext` — what one `assemble()` call is FOR. Declared empty here and merge-extensible; `dsh-agent` declares `agent?: Agent`, so providers project per-agent facts. Providers must tolerate absent fields (a bare `assemble()` carries an empty context).
-- `PromptSection` — `{ name, order, text: string | ((context) => string) }`. Sections are concatenated in ascending `order`. Order bands: `0` is the per-agent persona (registered by the agent loop), tool guidance uses `100–199`; negative orders render before the persona.
+- `PromptSection` — `{ name, order, text: string | ((context) => string) }`. Sections are concatenated in ascending `order`. Order bands: `-100` is the harness identity, `0` the per-agent persona (both registered by the agent loop), tool guidance uses `100–199`; other negative orders also render before the persona.
 - `PromptAssembly` — `{ sections: AssembledSection[], tools: ToolSchema[], variables: Record<string, string | undefined> }`. Section texts arrive resolved but not yet interpolated; `variables` holds every registered variable resolved against the context. Tool schemas are part of the assembly by design: "what the model is told it can do" is one coherent thing, even though adapters transmit schemas as a separate wire field.
 - `renderPrompt(assembly)` — interpolates `{{variable}}` references in each section, drops empty sections, joins with blank lines. STRICT: an unknown reference (`Object.hasOwn` lookup — prototype names like `{{constructor}}` are unknown), a registered-but-valueless reference, a malformed complete `{{…}}` group, or a `{{` that opens no complete group while a `}}` still follows (`{{{model}}}`) throws — fail loud beats shipping a malformed prompt. A lone `{{` with no `}}` anywhere after it passes through verbatim; substituted values are never re-scanned.
 
@@ -29,7 +29,7 @@ Merge-extensible: plugins can declare extra fields on `PromptAssembly` and `Asse
 
 ### Extension points
 
-- Section providers: tool packages own their cross-call guidance (`tool:bash`, `tool:read`, …); the agent loop owns `agent:persona`.
+- Section providers: tool packages own their cross-call guidance (`tool:bash`, `tool:read`, …); the agent loop owns `harness:identity` and `agent:persona`.
 - Variable providers: the agent loop registers `model` and `cwd`; any plugin can register the facts it owns (a future `date`, git state, …).
 - Tool schema providers: `ToolRegistry` registers itself as a tool provider automatically.
 - The `system-prompt/assemble` waterfall: mutate or replace the assembly per caller (dynamic tool filtering, extra variables).

packages/core/system-prompt/src/index.ts

@@ -54,9 +54,9 @@ export interface PromptSection {
   /** Unique name — a duplicate registration throws (see {@link SystemPrompt.section}). */
   name: string
   /**
-   * Sections are concatenated in ascending order. Convention: `0` is the
-   * per-agent persona, tool guidance uses 100–199; negative orders render
-   * before the persona.
+   * Sections are concatenated in ascending order. Convention: `-100` is the
+   * harness identity, `0` the per-agent persona, tool guidance uses 100–199;
+   * other negative orders also render before the persona.
    */
   order: number
   /**