Merge remote-tracking branch 'origin/master' into codex/system-prompt-snapshots

# Conflicts:
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/support/acp-snapshot/src/suite.ts

examples/acp-agent/README.md

@@ -37,4 +37,4 @@ This example is the home of the harness's **snapshot tests** — they boot this
 
 ## MVP limitations
 
-The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, `additionalDirectories` and `mcpServers` are rejected, and the tool-permission gate is deferred (`TODO(rfc010-permission-gate)` — tools run with the executor's full authority). See `packages/ui/acp/README.md` for the full contract.
+The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, and `additionalDirectories` and `mcpServers` are rejected. Permission prompts (`session/request_permission`) are wired through the approval seam, but this example composes no ask-producing policy, so tools run with the executor's full authority. See `packages/ui/acp/README.md` for the full contract.

examples/acp-agent/tests/acp.e2e.ts

@@ -63,7 +63,16 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
   const child = spawn(
     process.execPath,
     ['--import', tsxLoader, binScript, configPath],
-    { cwd, env: { ...env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] },
+    {
+      cwd,
+      env: {
+        ...env,
+        TSX_TSCONFIG_PATH: repoTsconfig,
+        DSH_HOME: join(cwd, '.dsh'),
+        DSH_AGENTS_HOME: join(cwd, '.agents'),
+      },
+      stdio: ['pipe', 'pipe', 'pipe'],
+    },
   )
   const stderr: string[] = []
   child.stderr.setEncoding('utf8')
@@ -80,8 +89,9 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
       return Promise.resolve()
     },
     requestPermission(_params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
-      // Permission gate is deferred (TODO(rfc010-permission-gate)); the bridge
-      // never requests permission yet, so just allow if it ever does.
+      // This example composes no ask-producing policy (no hooks), so the
+      // bridge never prompts here; answer cancelled (fail closed) if it ever
+      // does — an unexpected prompt must not grant anything.
       return Promise.resolve({ outcome: { outcome: 'cancelled' } })
     },
   })
@@ -150,7 +160,13 @@ describe('acp-agent over real stdio (no key required)', () => {
     // which this purity test never triggers). So this runs WITHOUT real creds.
     const child = spawn(process.execPath, ['--import', tsxLoader, binScript, configPath], {
       cwd: workdir,
-      env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig },
+      env: {
+        ...process.env,
+        DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot',
+        TSX_TSCONFIG_PATH: repoTsconfig,
+        DSH_HOME: join(workdir, '.dsh'),
+        DSH_AGENTS_HOME: join(workdir, '.agents'),
+      },
       stdio: ['pipe', 'pipe', 'pipe'],
     })
     const out: string[] = []

examples/acp-agent/tests/acp.snapshot.ts

@@ -51,6 +51,7 @@ const SCENARIOS: Scenario[] = [
   { name: 'tool-call-turn', hasModelTurn: true, recorded: true },
   { name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
   { name: 'todo-plan', hasModelTurn: true, recorded: true },
+  { name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
   { name: 'workspace-edit', hasModelTurn: true, recorded: true },
   { name: 'fs-read', hasModelTurn: true, recorded: true },
   { name: 'fs-write', hasModelTurn: true, recorded: true },

examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md

@@ -28,7 +28,7 @@ The available tools:
 
 ```ts
 declare const tools: {
-  /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
+  /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
   bash(args: {
     /** The bash command to execute. */
     command: string;
@@ -71,6 +71,11 @@ declare const tools: {
     /** Maximum number of lines to return. Defaults to 2000. */
     limit?: number;
   }): Promise<string>;
+  /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
+  skill(args: {
+    /** The exact skill name from the available skills list. */
+    name: string;
+  }): Promise<string>;
   /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */
   subagent(args: {
     /** A short (3-5 word) description of the delegated task, for display. */

examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md

@@ -28,7 +28,7 @@ The available tools:
 
 ```ts
 declare const tools: {
-  /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
+  /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
   bash(args: {
     /** The bash command to execute. */
     command: string;
@@ -71,6 +71,11 @@ declare const tools: {
     /** Maximum number of lines to return. Defaults to 2000. */
     limit?: number;
   }): Promise<string>;
+  /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
+  skill(args: {
+    /** The exact skill name from the available skills list. */
+    name: string;
+  }): Promise<string>;
   /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */
   subagent(args: {
     /** A short (3-5 word) description of the delegated task, for display. */

examples/acp-agent/tests/snapshots/skill-load/input.json

@@ -0,0 +1,7 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "Load the snapshot-skill skill with the skill tool, then reply DONE." }
+  ]
+}

examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl

@@ -0,0 +1,8 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The skill is loaded."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}

examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md

@@ -0,0 +1,16 @@
+You are an AI agent powered by the DeepSeek Harness SDK.
+
+You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
+
+Verify your work by running the code or tests. Keep answers brief and factual.
+
+
+Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
+
+Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
+
+Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
+
+Check the [exit code: N] marker on every bash result; investigate failures before moving on.
+
+Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.

examples/acp-agent/tests/snapshots/skill-load/workspace/.dsh/skills/snapshot-skill/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: snapshot-skill
+description: Exercise project skill discovery and loading in snapshot tests.
+---
+
+Follow these snapshot-only instructions.
+Resolve referenced resources relative to this skill directory.