refactor: move project instructions to prompt group

AGENTS.md

@@ -64,7 +64,10 @@ packages/    Harness packages, grouped by role at packages/<group>/<pkg>/.
     agent-loop/     THE concrete plugin: ReactLoopAgent + the loop driver
     agent-core/     bundle plugin: the providerless/executor-less/UI-less spine
                     (timer+llm+sessions+system-prompt+tools+agents+invariants+
-                    tool-bash+agent-loop) as code; forwards agent-loop's `agents`
+                    tool-bash+project-instructions+agent-loop) as code; forwards
+                    agent-loop's `agents`
+  prompt/        prompt and request-context extensions
+    project-instructions/  AGENTS.md/CLAUDE.md workspace context loader
   llm/            LLM capability family
     llm/            abstract LLM service + content-block vocabulary
     llm-deepseek/   DeepSeek API adapter (hand-rolled fetch/SSE)

docs/architecture.md

@@ -97,6 +97,8 @@ Replay/fork = `ctx.sessions.create(id, { seed: seedEvents })`. Trace/telemetry =
 
 Plugins contribute `PromptSection`s (named, ordered, static or computed) and tool-schema providers. `assemble()` returns a `PromptAssembly { sections, tools }` through the `system-prompt/assemble` waterfall.
 
+Prompt/context extension plugins that shape model inputs without owning a core service live under `packages/prompt/`. `dsh-project-instructions` is the reference case: it is semantically prompt/context assembly, but it uses the per-agent `agent/request` seam instead of a global `ctx.systemPrompt.section()` so concurrent sessions with different cwd values stay isolated.
+
 Tool schemas are deliberately **part of the assembly**: "what the model is told it can do" is one coherent thing managed here, even though adapters transmit schemas as the wire-level `tools` field rather than prompt text.
 
 ## Tool pipeline (dsh-tools)

docs/rfc/implemented/feature/2026-06-24-project-instruction-files.md

@@ -12,7 +12,7 @@ The non-obvious constraint is multi-session cwd. `dsh-system-prompt` sections ar
 
 ## Proposal
 
-Add a new plugin package `packages/core/project-instructions` (`@deepseek-ai/dsh-project-instructions`). It is a single-purpose extension plugin, not an interface/implementation/consumer capability seam: there is no swappable backend, only filesystem discovery plus per-request context injection. It depends on interface packages only (`dsh-agent` and `dsh-llm`) and consumes the existing `agent/request` waterfall.
+Add a new plugin package `packages/prompt/project-instructions` (`@deepseek-ai/dsh-project-instructions`). It is a single-purpose prompt/context extension plugin, not an interface/implementation/consumer capability seam: there is no swappable backend, only filesystem discovery plus per-request context injection. It depends on interface packages only (`dsh-agent` and `dsh-llm`) and consumes the existing `agent/request` waterfall.
 
 The plugin is loaded by `@deepseek-ai/dsh-agent-core` so both product front doors (`dsh-stdio-agent` and `dsh-acp-agent`) get instruction-file behavior by default. The bundle and both app packages expose `projectInstructions` config, so apps may set `projectInstructions: false` or `baselineMaxBytes: 0` when they need a hermetic prompt. The default product behavior matches user expectations for coding agents.
 
@@ -102,7 +102,7 @@ Summarize instruction files before injection. This saves tokens but makes the in
 
 ## Plan
 
-1. Add `packages/core/project-instructions` with config for `dshHome`, `projectRootMarkers` (default `['.git']`), `baselineMaxBytes` (default `65536`), and `enableClaudeFallback` (default `true`). Include pure discovery/rendering helpers so the filesystem rules can be tested without Cordis.
+1. Add `packages/prompt/project-instructions` with config for `dshHome`, `projectRootMarkers` (default `['.git']`), `baselineMaxBytes` (default `65536`), and `enableClaudeFallback` (default `true`). Include pure discovery/rendering helpers so the filesystem rules can be tested without Cordis.
 
 2. Implement baseline `agent/request` injection in `dsh-project-instructions`. The listener computes the instruction block for `agent.session.header.cwd` or the stdio-only `process.cwd()` fallback, prepends one synthetic workspace-context message to the request messages, and returns the request through `next()`. It must never mutate shared global prompt sections or the provider system field.
 

knip.json

@@ -29,7 +29,7 @@
       "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
     },
-    "packages/core/project-instructions": {
+    "packages/prompt/project-instructions": {
       "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
     },

packages/README.md

@@ -9,6 +9,7 @@ Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group dir
 | Group | Role | Release expectation |
 |---|---|---|
 | [`core/`](core/README.md) | Product API spine: session, system-prompt, tools, agent, and the concrete loop | Product — stable surface |
+| [`prompt/`](prompt/README.md) | Prompt and request-context extensions that shape model inputs | Product — stable surface |
 | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface |
 | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface |
 | [`compact/`](compact/README.md) | Compaction capability family: the abstract seam (backend + tool deferred) | Product — stable surface |
@@ -63,9 +64,9 @@ The rule: **extension** plugins depend on interfaces, never on the concrete loop
 | `system-prompt/` | `core` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` |
 | `tools/` | `core` | Tool registry + `tools/execute` waterfall | `ctx.tools` |
 | `agent/` | `core` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` |
-| `project-instructions/` | `core` | `AGENTS.md`/`CLAUDE.md` workspace context loader | (listens on `agent/request`) |
 | `agent-loop/` | `core` | THE concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` |
 | `agent-core/` | `core` | Bundle plugin: the providerless/executor-less/UI-less spine as code (forwards `agent-loop`'s `agents`) | (loads the spine) |
+| `project-instructions/` | `prompt` | `AGENTS.md`/`CLAUDE.md` workspace context loader | (listens on `agent/request`) |
 | `bash/` | `bash` | Abstract bash executor seam (interface + vocabulary) | `ctx.bash` |
 | `bash-local/` | `bash` | Local-subprocess `BashExecutor` implementation | (registers `ctx.bash`) |
 | `tool-bash/` | `bash` | Model-facing `bash`/`bash_output`/`bash_kill` tool schemas | (registers on `ctx.tools`) |

packages/core/README.md

@@ -8,10 +8,9 @@ The packages every harness build is assembled from: the session log, the system-
 | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` |
 | `tools/` | Tool registry + `tools/execute` waterfall | `ctx.tools` |
 | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` |
-| `project-instructions/` | `AGENTS.md`/`CLAUDE.md` workspace context loader | (listens on `agent/request`) |
 | `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` |
 | `agent-core/` | Bundle plugin: the providerless/executor-less/UI-less spine as code | (loads the spine) |
 
 `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; everything else in `core/` is interface/vocabulary. Plugins depend on the `agent` vocabulary, never on `agent-loop` directly, so the loop stays swappable.
 
-`agent-core` is the composition counterpart: one bundle plugin that loads the whole providerless spine (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + `tool-bash` + project-instructions + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds only the swappable backends. It lives in `core/` because it composes exclusively `core/` + interface packages and ships no provider, executor, or UI of its own.
+`agent-core` is the composition counterpart: one bundle plugin that loads the whole providerless spine (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + `tool-bash` + project-instructions + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds only the swappable backends. It lives in `core/` because it is the default spine bundle and ships no provider, executor, or UI of its own; it may include product prompt/tool extensions that are common to every front door.

packages/core/agent-core/tsconfig.json

@@ -30,7 +30,7 @@
       "path": "../../core/agent"
     },
     {
-      "path": "../../core/project-instructions"
+      "path": "../../prompt/project-instructions"
     },
     {
       "path": "../../core/agent-loop"

packages/prompt/README.md

@@ -0,0 +1,9 @@
+# prompt/ — prompt and request-context extensions
+
+Product packages that contribute model-facing prompt or request-context behavior without being core agent/session/tool primitives. These packages usually consume existing seams such as `agent/request` or `system-prompt/assemble`; they do not own the loop and do not provide LLM adapters, execution backends, or UI front doors.
+
+| Package | Role | ctx key |
+|---|---|---|
+| `project-instructions/` | `AGENTS.md`/`CLAUDE.md` workspace context loader | (listens on `agent/request`) |
+
+`project-instructions` lives here because it is semantically a prompt/context extension: it adds workspace guidance to the model request. It deliberately uses the per-agent `agent/request` seam instead of a global `ctx.systemPrompt.section()` so multiple live sessions with different `cwd` values do not leak instruction files into one another.

packages/core/project-instructions/tests/project-instructions.spec.ts → packages/prompt/project-instructions/tests/project-instructions.spec.ts

@@ -1,7 +1,7 @@
 import { chmod, mkdtemp, mkdir, rm, writeFile } from 'node:fs/promises'
 import { join } from 'node:path'
 import { tmpdir } from 'node:os'
-import { describe, expect, it } from 'vitest'
+import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import type { GenerateOptions } from '@deepseek-ai/dsh-llm'
 import { Session, SessionId, SESSION_FORMAT_VERSION } from '@deepseek-ai/dsh-session'
@@ -198,16 +198,18 @@ describe('project instruction discovery', () => {
   it('labels the default DSH home as ~/.dsh when HOME points at the configured default', async () => {
     const root = await tempRepo()
     const home = await tempRepo()
-    const previousHome = process.env.HOME
     try {
-      process.env.HOME = home
       await write(join(home, '.dsh/AGENTS.md'), 'global default rule')
 
-      const files = await discoverBaselineInstructionFiles({ cwd: root })
+      vi.resetModules()
+      vi.doMock('node:os', () => ({ homedir: () => home }))
+      const isolated = await import('@deepseek-ai/dsh-project-instructions')
+      const files = await isolated.discoverBaselineInstructionFiles({ cwd: root })
 
       expect(files.map(file => file.displayPath)).toEqual(['~/.dsh/AGENTS.md'])
     } finally {
-      process.env.HOME = previousHome
+      vi.doUnmock('node:os')
+      vi.resetModules()
       await rm(root, { recursive: true, force: true })
       await rm(home, { recursive: true, force: true })
     }

pnpm-lock.yaml

@@ -164,7 +164,7 @@ importers:
         version: link:../../llm/llm
       '@deepseek-ai/dsh-project-instructions':
         specifier: workspace:^
-        version: link:../project-instructions
+        version: link:../../prompt/project-instructions
       '@deepseek-ai/dsh-session':
         specifier: workspace:^
         version: link:../session
@@ -215,37 +215,6 @@ importers:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
 
-  packages/core/project-instructions:
-    dependencies:
-      schemastery:
-        specifier: ^3.18.0
-        version: 3.18.0
-    devDependencies:
-      '@deepseek-ai/dsh-agent':
-        specifier: workspace:^
-        version: link:../agent
-      '@deepseek-ai/dsh-agent-loop':
-        specifier: workspace:^
-        version: link:../agent-loop
-      '@deepseek-ai/dsh-llm':
-        specifier: workspace:^
-        version: link:../../llm/llm
-      '@deepseek-ai/dsh-llm-deepseek':
-        specifier: workspace:^
-        version: link:../../llm/llm-deepseek
-      '@deepseek-ai/dsh-session':
-        specifier: workspace:^
-        version: link:../session
-      '@deepseek-ai/dsh-system-prompt':
-        specifier: workspace:^
-        version: link:../system-prompt
-      '@deepseek-ai/dsh-tools':
-        specifier: workspace:^
-        version: link:../tools
-      cordis:
-        specifier: ^4.0.0-rc.6
-        version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
-
   packages/core/session:
     devDependencies:
       '@deepseek-ai/dsh-brand':
@@ -323,6 +292,37 @@ importers:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
 
+  packages/prompt/project-instructions:
+    dependencies:
+      schemastery:
+        specifier: ^3.18.0
+        version: 3.18.0
+    devDependencies:
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-agent-loop':
+        specifier: workspace:^
+        version: link:../../core/agent-loop
+      '@deepseek-ai/dsh-llm':
+        specifier: workspace:^
+        version: link:../../llm/llm
+      '@deepseek-ai/dsh-llm-deepseek':
+        specifier: workspace:^
+        version: link:../../llm/llm-deepseek
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      '@deepseek-ai/dsh-system-prompt':
+        specifier: workspace:^
+        version: link:../../core/system-prompt
+      '@deepseek-ai/dsh-tools':
+        specifier: workspace:^
+        version: link:../../core/tools
+      cordis:
+        specifier: ^4.0.0-rc.6
+        version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
+
   packages/session-persistence/session-persistence:
     devDependencies:
       '@deepseek-ai/dsh-session':
@@ -690,7 +690,7 @@ importers:
         version: link:../../core/agent-core
       '@deepseek-ai/dsh-project-instructions':
         specifier: workspace:^
-        version: link:../../core/project-instructions
+        version: link:../../prompt/project-instructions
       '@deepseek-ai/dsh-session-persistence-jsonl':
         specifier: workspace:^
         version: link:../../session-persistence/session-persistence-jsonl
@@ -720,7 +720,7 @@ importers:
         version: link:../../core/agent-core
       '@deepseek-ai/dsh-project-instructions':
         specifier: workspace:^
-        version: link:../../core/project-instructions
+        version: link:../../prompt/project-instructions
       '@deepseek-ai/dsh-session':
         specifier: workspace:^
         version: link:../../core/session

tsconfig.base.json

@@ -41,6 +41,7 @@
       // explicit — TS project references have no wildcard form.
       "@deepseek-ai/dsh-*": [
         "./packages/core/*/src",
+        "./packages/prompt/*/src",
         "./packages/llm/*/src",
         "./packages/bash/*/src",
         "./packages/compact/*/src",

tsconfig.build.json

@@ -19,7 +19,7 @@
     { "path": "./packages/core/system-prompt" },
     { "path": "./packages/core/agent" },
     { "path": "./packages/core/tools" },
-    { "path": "./packages/core/project-instructions" },
+    { "path": "./packages/prompt/project-instructions" },
     { "path": "./packages/core/agent-loop" },
     { "path": "./packages/core/agent-core" },
     { "path": "./packages/bash/bash" },

tsconfig.json

@@ -30,7 +30,7 @@
     { "path": "./packages/core/system-prompt" },
     { "path": "./packages/core/agent" },
     { "path": "./packages/core/tools" },
-    { "path": "./packages/core/project-instructions" },
+    { "path": "./packages/prompt/project-instructions" },
     { "path": "./packages/core/agent-loop" },
     { "path": "./packages/core/agent-core" },
     { "path": "./packages/bash/bash" },