docs(cli): conversations

src/content/docs/cli/conversations.mdx

@@ -1,31 +1,76 @@
 ---
-title: "Managing conversations in the {{WARP_CLI}}"
+title: "Managing conversations in the Warp CLI"
 description: >-
-  Start, switch, compact, and resume agent conversations in the {{WARP_CLI}},
+  Start, switch, compact, and resume agent conversations in the Warp CLI,
   including conversation history and the --resume flag.
 ---
 import { VARS } from '@data/vars';
 
-{/* TODO(cli-conversations): draft per drafts/warp-cli-launch-plan.md — "cli/conversations.mdx" section. Feature-doc content type. */}
-
-The {VARS.WARP_CLI} documentation for this page is in progress.
+The {VARS.WARP_CLI} saves every agent conversation as you work, so closing your terminal never loses your progress. You can start fresh conversations, reopen past ones from a searchable history, compact long conversations to free up context, and resume a conversation after exiting the CLI.
 
 ## Conversation persistence
 
-{/* TODO(cli-conversations): conversations persist across sessions and restore with full detail. */}
+The {VARS.WARP_CLI} saves conversations to your Warp account automatically. There is no separate save step. When you reopen a past conversation, the CLI restores the full transcript, including agent responses, tool calls, and file-edit diffs, so you can review earlier work in detail before continuing.
+
+The CLI shows one conversation at a time. Opening a past conversation replaces the current transcript, and your previous conversation remains available in the conversation history. You can't switch conversations while the current conversation is responding or while a command is running; wait for it to finish or stop it with `Ctrl+C` first.
 
 ## Starting a new conversation
 
-{/* TODO(cli-conversations): /new, /agent, /clear. */}
+Use any of these slash commands to clear the transcript and start a fresh conversation:
+
+* **`/new`** - Starts a new conversation.
+* **`/agent`** - Same as `/new`.
+* **`/clear`** - Same as `/new`.
+
+Each command accepts an optional prompt. For example, `/new write tests for the parser` starts a new conversation and immediately sends that prompt to the agent.
+
+Starting a new conversation is useful when you switch tasks. The agent begins with a clean context window, and you avoid carrying over history that is no longer relevant. If you want to keep the history but reduce its size instead, use [`/compact`](#compacting-context).
 
 ## Conversation history
 
-{/* TODO(cli-conversations): /conversations menu and navigation into past conversations. */}
+To browse and reopen past conversations, open the conversation menu in either of two ways:
+
+* **`/conversations`** - Run the slash command from the input.
+* **`←`** - Press the left arrow key when the input is empty and the cursor is at the start. The empty input shows a `← for conversations` hint as a reminder.
+
+The menu lists your Warp Agent conversations, including conversations started in the Warp app and completed cloud agent runs tied to your account. To use the menu:
+
+1. Type to filter conversations by title.
+2. Press `↑` and `↓` to change the selection.
+3. Press `Enter` to open the selected conversation, or `Esc` to close the menu.
+
+Opening a conversation restores its transcript with tool calls and diffs intact, and new prompts you send continue that conversation.
+
+:::caution
+If the CLI can't load conversation data from Warp's servers, the menu shows conversations from your local device only and displays a warning. Conversations from other devices reappear once the connection recovers.
+:::
+
+To continue a cloud agent run from the CLI, or to hand the current conversation off to a cloud agent, see [cloud handoff and orchestration in the {VARS.WARP_CLI}](/cli/cloud-and-orchestration/).
 
 ## Compacting context
 
-{/* TODO(cli-conversations): /compact, when to use it, what the summary block looks like. */}
+Long conversations eventually fill the model's context window, which can degrade response quality. The `/compact` command frees up context by asking the agent to summarize the conversation history so far and carry only the summary forward.
+
+* **`/compact`** - Summarizes the conversation history with default instructions.
+* **`/compact <instructions>`** - Adds custom summarization instructions. For example, `/compact keep the API design decisions` tells the agent what to preserve in the summary.
+
+After compaction, a collapsed **Conversation summary** block appears in the transcript. The summary stays collapsed so it doesn't crowd the transcript; select it to expand the full summary text. The conversation keeps working normally after compaction, with the summary standing in for the compacted history.
 
 ## Resuming conversations
 
-{/* TODO(cli-conversations): exit summary with resume command; `--resume` flag. */}
+When you exit the {VARS.WARP_CLI} with a non-empty conversation, it prints a command for picking that conversation back up:
+
+```bash
+To continue this conversation, run:
+warp --resume YOUR_CONVERSATION_TOKEN
+```
+
+Run the printed command to reopen the conversation in a new CLI session. YOUR_CONVERSATION_TOKEN is a conversation identifier generated by Warp; you don't need to record it yourself as long as you can scroll back to the exit message, and the same conversation also remains available from the [`/conversations` menu](#conversation-history).
+
+The `--resume` flag loads the conversation at startup and restores the full transcript, so you can continue prompting where you left off. For the complete list of command-line flags, see the [{VARS.WARP_CLI} reference](/cli/reference/).
+
+## Related pages
+
+* [Agent conversations in the {VARS.WARP_CLI}](/cli/agent-conversations/) - How transcripts, tool calls, diffs, and agent questions render
+* [Cloud handoff and orchestration in the {VARS.WARP_CLI}](/cli/cloud-and-orchestration/) - Hand off conversations to cloud agents and resume cloud runs
+* [{VARS.WARP_CLI} reference](/cli/reference/) - Command-line flags, slash commands, and keyboard shortcuts