diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 4fc13f8bed..c5553703cb 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -26,6 +26,7 @@ const AGENT = { // replay swap resolves each one's sibling `*cordis.snapshot.yml`). const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url)) const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url)) +const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cordis.yml', import.meta.url)) function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] { switch (value) { @@ -67,6 +68,19 @@ const SCENARIOS: Scenario[] = [ // the fixture scripts five identical todo_write calls and pins BOTH reminder // tiers (gentle at 3, detailed at 5) as context/message in transcript and log. { name: 'repeat-tool-guard', hasModelTurn: true, recorded: false }, + // Authored replay: a root AGENTS.md pins the session prefix, then a read in + // nested/ discovers its narrower AGENTS.md as a raw, metadata-bearing + // context/message. The scenario-specific config keeps home/root discovery + // hermetic, and the resulting prefix needs its own pinned header class. + { + name: 'workspace-context', + hasModelTurn: true, + recorded: false, + overridden: true, + pinsHeader: true, + headerClass: 'workspace-context', + configPath: WORKSPACE_CONTEXT_CONFIG, + }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, { name: 'subagent-spawn', hasModelTurn: true, recorded: true, childSessions: 1 }, { name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 }, diff --git a/examples/acp-agent/tests/snapshots/workspace-context/input.json b/examples/acp-agent/tests/snapshots/workspace-context/input.json new file mode 100644 index 0000000000..94fd9dae92 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Read nested/task.txt with the read tool, then reply DONE." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/replay.override.json b/examples/acp-agent/tests/snapshots/workspace-context/replay.override.json new file mode 100644 index 0000000000..ef70491338 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/replay.override.json @@ -0,0 +1,22 @@ +[ + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 0, "id": "call_workspace_read", "name": "read", "argumentsDelta": "{\"file_path\":\"nested/task.txt\"}" }, + { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_workspace_read", "name": "read", "arguments": "{\"file_path\":\"nested/task.txt\"}" } }, + { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } }, + { "type": "finish", "reason": { "kind": "tool-calls" } } + ] + }, + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "text" }, + { "type": "text-delta", "index": 0, "text": "DONE" }, + { "type": "block-end", "index": 0, "block": { "type": "text", "text": "DONE" } }, + { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 2 } }, + { "type": "finish", "reason": { "kind": "stop" } } + ] + } +] diff --git a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl new file mode 100644 index 0000000000..f7813f414a --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl @@ -0,0 +1,24 @@ +{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"} +{"type":"turn/start","seq":0,"time":1783778297065,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783778297066,"data":{"content":[{"type":"text","text":"Read nested/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783778297069,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783778297070,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse 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.","tools":[{"name":"bash","description":"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`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"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.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n"}]}]},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_read","name":"read","argumentsDelta":"{\"file_path\":\"nested/task.txt\"}"}}} +{"type":"assistant/chunk","seq":6,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} +{"type":"assistant/chunk","seq":8,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":9,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"tool/call","seq":10,"time":1783778297070,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}} +{"type":"tool/result","seq":11,"time":1783778297072,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"{{cwd}}/nested/task.txt\nfile\n\n1: snapshot task\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} +{"type":"context/message","seq":12,"time":1783778297072,"data":{"content":[{"type":"text","text":"\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n"}],"source":{"kind":"plugin","plugin":"workspace-context"},"envelope":"raw","meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested","path":"nested/AGENTS.md","digest":"ba0e42954526e3c7ae2b225c95f77ff00fdfaf71a7c982d0339fd3c5d8889d71"}]}},"surfaceOp":"append"} +{"type":"step/end","seq":13,"time":1783778297072,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":14,"time":1783778297072,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":15,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":16,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}} +{"type":"assistant/chunk","seq":17,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":18,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}} +{"type":"assistant/chunk","seq":19,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":20,"time":1783778297073,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"} +{"type":"step/end","seq":21,"time":1783778297073,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":22,"time":1783778297073,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/stdout.golden.jsonl new file mode 100644 index 0000000000..d9d9ff7f40 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/stdout.golden.jsonl @@ -0,0 +1,6 @@ +{"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":"tool_call","toolCallId":"call_workspace_read","title":"Read nested/task.txt","kind":"read","status":"in_progress","locations":[{"path":"nested/task.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_workspace_read","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/nested/task.txt\nfile\n\n1: snapshot task\n\n(End of file - total 1 lines)\n"}}]}}} +{"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"}} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/workspace/.dsh-project b/examples/acp-agent/tests/snapshots/workspace-context/workspace/.dsh-project new file mode 100644 index 0000000000..8ce6fed8d7 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/workspace/.dsh-project @@ -0,0 +1 @@ +snapshot root marker diff --git a/examples/acp-agent/tests/snapshots/workspace-context/workspace/AGENTS.md b/examples/acp-agent/tests/snapshots/workspace-context/workspace/AGENTS.md new file mode 100644 index 0000000000..a66cf16a13 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/workspace/AGENTS.md @@ -0,0 +1 @@ +Root snapshot instruction. diff --git a/examples/acp-agent/tests/snapshots/workspace-context/workspace/nested/AGENTS.md b/examples/acp-agent/tests/snapshots/workspace-context/workspace/nested/AGENTS.md new file mode 100644 index 0000000000..862c12a235 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/workspace/nested/AGENTS.md @@ -0,0 +1 @@ +Nested snapshot instruction. diff --git a/examples/acp-agent/tests/snapshots/workspace-context/workspace/nested/task.txt b/examples/acp-agent/tests/snapshots/workspace-context/workspace/nested/task.txt new file mode 100644 index 0000000000..39e2106a6f --- /dev/null +++ b/examples/acp-agent/tests/snapshots/workspace-context/workspace/nested/task.txt @@ -0,0 +1 @@ +snapshot task diff --git a/examples/acp-agent/workspace-context.cordis.snapshot.yml b/examples/acp-agent/workspace-context.cordis.snapshot.yml new file mode 100644 index 0000000000..da175da8e8 --- /dev/null +++ b/examples/acp-agent/workspace-context.cordis.snapshot.yml @@ -0,0 +1,29 @@ +# Keyless replay counterpart of workspace-context.cordis.yml. Patches do not +# compose across includes, so this applies the scenario config and model swap +# directly to the live tree. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: acp-agent + name: '@deepseek-ai/dsh-acp-agent' + config: + model: deepseek-v4-flash + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + workspaceContext: + dshHome: !!js process.cwd() + '/.dsh' + projectRootMarkers: + - .dsh-project + persona: | + You are a coding assistant powered by the {{model}} model. Your working + directory is {{cwd}}. + + Verify your work by running the code or tests. Keep answers brief and + factual. + - insert: + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/acp-agent/workspace-context.cordis.yml b/examples/acp-agent/workspace-context.cordis.yml new file mode 100644 index 0000000000..9db52c86ec --- /dev/null +++ b/examples/acp-agent/workspace-context.cordis.yml @@ -0,0 +1,23 @@ +# Workspace-context snapshot overlay: keep project-root and user-global +# discovery inside the scenario's temporary cwd. The app config patch replaces +# the whole base config, so the base fields are restated verbatim. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: acp-agent + name: '@deepseek-ai/dsh-acp-agent' + config: + model: deepseek-v4-flash + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + workspaceContext: + dshHome: !!js process.cwd() + '/.dsh' + projectRootMarkers: + - .dsh-project + persona: | + You are a coding assistant powered by the {{model}} model. Your working + directory is {{cwd}}. + + Verify your work by running the code or tests. Keep answers brief and + factual.