@letta-ai/letta-code 0.25.1 → 0.25.2

package/letta.js

@@ -3143,7 +3143,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "@letta-ai/letta-code",
-    version: "0.25.1",
+    version: "0.25.2",
     description: "Letta Code is a CLI tool for interacting with stateful Letta agents from the terminal.",
     type: "module",
     bin: {
@@ -5397,6 +5397,11 @@ var init_manager = __esm(() => {
   init_settings_manager();
   ENABLED_TOGGLE_VALUES = new Set(["1", "true", "yes"]);
   EXPERIMENT_DEFINITIONS = [
+    {
+      id: "conversation_titles",
+      label: "conversation titles",
+      description: "Generate conversation titles from the transcript with letta/auto (uses your credits)."
+    },
     {
       id: "node",
       label: "node",
@@ -5772,6 +5777,7 @@ __export(exports_memoryGit, {
   normalizeCredentialBaseUrl: () => normalizeCredentialBaseUrl,
   maybeUpdateMemoryRemoteOrigin: () => maybeUpdateMemoryRemoteOrigin,
   isRetryableGitTransientError: () => isRetryableGitTransientError,
+  isRepairableMemfsRemoteUrl: () => isRepairableMemfsRemoteUrl,
   isMissingCwdGitError: () => isMissingCwdGitError,
   isMemfsRemoteUrlForAgent: () => isMemfsRemoteUrlForAgent,
   isMemfsGitNetworkCommand: () => isMemfsGitNetworkCommand,
@@ -5844,6 +5850,17 @@ function isMemfsRemoteUrlForAgent(remoteUrl, agentId) {
   const escapedAgentId = escapeRegex(agentId);
   return new RegExp(`^https?://[^\\s]+/v1/git/${escapedAgentId}/state\\.git$`, "i").test(normalized);
 }
+function isRepairableMemfsRemoteUrl(remoteUrl, agentId) {
+  const normalized = normalizeRemoteUrl(remoteUrl);
+  const escapedAgentId = escapeRegex(agentId);
+  if (isMemfsRemoteUrlForAgent(normalized, agentId)) {
+    return true;
+  }
+  if (new RegExp(`^https?://[^\\s]+/v1/git/${escapedAgentId}$`, "i").test(normalized)) {
+    return true;
+  }
+  return /^https?:\/\/[^\s]+\/v1\/git$/i.test(normalized);
+}
 function getGitRemoteUrl(agentId, baseUrl) {
   const resolvedBaseUrl = (baseUrl ?? getMemfsServerUrl()).trim().replace(/\/+$/, "");
   return `${resolvedBaseUrl}/v1/git/${agentId}/state.git`;
@@ -5859,7 +5876,7 @@ async function maybeUpdateMemoryRemoteOrigin(repoDir, agentId) {
   if (!currentOrigin) {
     return;
   }
-  if (!isMemfsRemoteUrlForAgent(currentOrigin, agentId)) {
+  if (!isRepairableMemfsRemoteUrl(currentOrigin, agentId)) {
     return;
   }
   const expectedOrigin = normalizeRemoteUrl(getGitRemoteUrl(agentId));
@@ -6228,6 +6245,10 @@ function isNonFastForwardPushError(error) {
   const message = error instanceof Error ? error.message : String(error);
   return NON_FAST_FORWARD_PUSH_ERROR_RE.test(message);
 }
+function isRecoverableMemoryPullHistoryError(error) {
+  const message = error instanceof Error ? error.message : String(error);
+  return UNRELATED_HISTORY_PULL_ERROR_RE.test(message) || NO_UPSTREAM_PULL_ERROR_RE.test(message);
+}
 async function prepareMemoryRepoForGitOps(memoryDir, agentId, token) {
   await maybeUpdateMemoryRemoteOrigin(memoryDir, agentId);
   await configureLocalCredentialHelper(memoryDir, token);
@@ -6235,6 +6256,55 @@ async function prepareMemoryRepoForGitOps(memoryDir, agentId, token) {
   installPostCommitHook(memoryDir);
   await ensureLocalMemfsGitConfig(memoryDir, agentId);
 }
+async function recoverMemoryPullByResettingToRemote(memoryDir, token) {
+  const { stdout: status } = await runGit(memoryDir, ["status", "--porcelain"]);
+  if (status.trim()) {
+    throw new Error("Local memory repo has uncommitted changes; refusing to auto-reset unrelated history.");
+  }
+  await runGitWithRetry(memoryDir, ["fetch", "origin", "main"], token, {
+    operation: "fetch memory repo for reset"
+  });
+  const { stdout: remoteShaOut } = await runGit(memoryDir, [
+    "rev-parse",
+    "--verify",
+    "refs/remotes/origin/main"
+  ]);
+  const remoteSha = remoteShaOut.trim();
+  if (!remoteSha) {
+    throw new Error("Remote memory repo did not advertise origin/main.");
+  }
+  let backupRef = null;
+  try {
+    const { stdout: localShaOut } = await runGit(memoryDir, [
+      "rev-parse",
+      "--verify",
+      "HEAD"
+    ]);
+    const localSha = localShaOut.trim();
+    if (localSha && localSha !== remoteSha) {
+      backupRef = `refs/letta-backup/pre-sync-${Date.now()}`;
+      await runGit(memoryDir, ["update-ref", backupRef, localSha]);
+    }
+  } catch {}
+  await runGit(memoryDir, ["reset", "--hard", "refs/remotes/origin/main"]);
+  try {
+    await runGit(memoryDir, [
+      "branch",
+      "--set-upstream-to",
+      "origin/main",
+      "main"
+    ]);
+  } catch {}
+  return backupRef ? `Recovered memory repo by resetting to origin/main (${remoteSha.slice(0, 7)}). Previous local HEAD was preserved at ${backupRef}.` : `Recovered memory repo by resetting to origin/main (${remoteSha.slice(0, 7)}).`;
+}
+async function hasMergeBaseWithUpstream(memoryDir) {
+  try {
+    await runGit(memoryDir, ["merge-base", "HEAD", "@{u}"]);
+    return true;
+  } catch {
+    return false;
+  }
+}
 async function prepareLocalOnlyMemoryRepoForGitOps(memoryDir, author) {
   installPreCommitHook(memoryDir);
   installPostCommitHook(memoryDir);
@@ -6567,11 +6637,33 @@ async function pullMemory(agentId) {
       summary: updated ? output.trim() : "Already up to date"
     };
   } catch {
+    if (!await hasMergeBaseWithUpstream(dir)) {
+      try {
+        return {
+          updated: true,
+          summary: await recoverMemoryPullByResettingToRemote(dir, token)
+        };
+      } catch (recoverErr) {
+        const recoverMsg = recoverErr instanceof Error ? recoverErr.message : String(recoverErr);
+        debugWarn("memfs-git", `Automatic memory repo reset failed: ${recoverMsg}`);
+      }
+    }
     debugWarn("memfs-git", "Fast-forward pull failed, trying rebase");
     try {
       const { stdout, stderr } = await runGitWithRetry(dir, ["pull", "--rebase"], token, { operation: "pull --rebase" });
       return { updated: true, summary: (stdout + stderr).trim() };
     } catch (rebaseErr) {
+      if (isRecoverableMemoryPullHistoryError(rebaseErr)) {
+        try {
+          return {
+            updated: true,
+            summary: await recoverMemoryPullByResettingToRemote(dir, token)
+          };
+        } catch (recoverErr) {
+          const recoverMsg = recoverErr instanceof Error ? recoverErr.message : String(recoverErr);
+          debugWarn("memfs-git", `Automatic memory repo reset failed: ${recoverMsg}`);
+        }
+      }
       const msg = rebaseErr instanceof Error ? rebaseErr.message : String(rebaseErr);
       debugWarn("memfs-git", `Pull failed: ${msg}`);
       return {
@@ -6649,7 +6741,7 @@ async function removeGitMemoryTag(agentId) {
     debugWarn("memfs-git", `Failed to remove git-memory tag: ${err instanceof Error ? err.message : String(err)}`);
   }
 }
-var execFile, GIT_MEMORY_ENABLED_TAG = "git-memory-enabled", RETRYABLE_GIT_HTTP_ERROR_RE, RETRYABLE_GIT_NETWORK_ERROR_RE, MISSING_CWD_GIT_ERROR_RE, NON_FAST_FORWARD_PUSH_ERROR_RE, AGENT_DISPLAY_NAME_TIMEOUT_MS = 3000, PRE_COMMIT_HOOK_SCRIPT = `#!/usr/bin/env bash
+var execFile, GIT_MEMORY_ENABLED_TAG = "git-memory-enabled", RETRYABLE_GIT_HTTP_ERROR_RE, RETRYABLE_GIT_NETWORK_ERROR_RE, MISSING_CWD_GIT_ERROR_RE, NON_FAST_FORWARD_PUSH_ERROR_RE, UNRELATED_HISTORY_PULL_ERROR_RE, NO_UPSTREAM_PULL_ERROR_RE, AGENT_DISPLAY_NAME_TIMEOUT_MS = 3000, PRE_COMMIT_HOOK_SCRIPT = `#!/usr/bin/env bash
 # Validate frontmatter in staged memory .md files
 # Installed by Letta Code CLI
 
@@ -6814,6 +6906,8 @@ var init_memoryGit = __esm(() => {
   RETRYABLE_GIT_NETWORK_ERROR_RE = /(remote end hung up unexpectedly|connection reset by peer|operation timed out|timed out)/i;
   MISSING_CWD_GIT_ERROR_RE = /(Unable to read current working directory: No such file or directory|\buv_cwd\b|\bcwd\b.*\bENOENT\b)/i;
   NON_FAST_FORWARD_PUSH_ERROR_RE = /(non-fast-forward|fetch first|failed to push some refs|updates were rejected|remote contains work that you do not have locally|tip of your current branch is behind)/i;
+  UNRELATED_HISTORY_PULL_ERROR_RE = /(no common commits|refusing to merge unrelated histories)/i;
+  NO_UPSTREAM_PULL_ERROR_RE = /(there is no tracking information for the current branch|no upstream configured|no tracking branch)/i;
 });
 
 // node_modules/@ai-sdk/provider/dist/index.mjs
@@ -55335,7 +55429,7 @@ assistant: Clients are marked as failed in the \`connectToServer\` function in s
 var init_source_claude = () => {};
 
 // src/agent/prompts/source_codex.md
-var source_codex_default = `You are Codex, a coding agent based on GPT-5. You and the user share the same workspace and collaborate to achieve the user's goals.
+var source_codex_default = `You are Codex, a coding agent based on GPT-5. You and the user share one workspace, and your job is to collaborate with them until their goal is genuinely handled.
 
 # Personality
 
@@ -55348,107 +55442,148 @@ You are guided by these core values:
 - Rigor: You expect technical arguments to be coherent and defensible, and you surface gaps or weak assumptions politely with emphasis on creating clarity and moving the task forward.
 
 ## Interaction Style
-You communicate concisely and respectfully, focusing on the task at hand. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
+You communicate respectfully, focusing on the task at hand. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps.
 
-You avoid cheerleading, motivational language, or artificial reassurance, or any kind of fluff. You don't comment on user requests, positively or negatively, unless there is reason for escalation. You don't feel like you need to fill the space with words, you stay concise and communicate what is necessary for user collaboration - not more, not less.
+You avoid cheerleading, motivational language, artificial reassurance, and general fluffiness. You don't comment on user requests, positively or negatively, unless there is reason for escalation.
 
 ## Escalation
 You may challenge the user to raise their technical bar, but you never patronize or dismiss their concerns. When presenting an alternative approach or solution to the user, you explain the reasoning behind the approach, so your thoughts are demonstrably correct. You maintain a pragmatic mindset when discussing these tradeoffs, and so are willing to work with the user after concerns have been noted.
 
-# General
 
-- When searching for text or files, prefer using \`rg\` or \`rg --files\` respectively because \`rg\` is much faster than alternatives like \`grep\`. (If the \`rg\` command is not found, then use alternatives.)
-- Parallelize tool calls whenever possible - especially file reads, such as \`cat\`, \`rg\`, \`sed\`, \`ls\`, \`git show\`, \`nl\`, \`wc\`. Use \`multi_tool_use.parallel\` to parallelize tool calls and only this.
+# General
+You bring a senior engineer’s judgment to the work, but you let it arrive through attention rather than premature certainty. You read the codebase first, resist easy assumptions, and let the shape of the existing system teach you how to move.
+
+- When you search for text or files, you reach first for \`rg\` or \`rg --files\`; they are much faster than alternatives like \`grep\`. If \`rg\` is unavailable, you use the next best tool without fuss.
+- You parallelize tool calls whenever you can, especially file reads such as \`cat\`, \`rg\`, \`sed\`, \`ls\`, \`git show\`, \`nl\`, and \`wc\`. You use \`multi_tool_use.parallel\` for that parallelism, and only that. Do not chain shell commands with separators like \`echo "====";\`; the output becomes noisy in a way that makes the user’s side of the conversation worse.
+
+## Engineering judgment
+
+When the user leaves implementation details open, you choose conservatively and in sympathy with the codebase already in front of you:
+
+- You prefer the repo’s existing patterns, frameworks, and local helper APIs over inventing a new style of abstraction.
+- For structured data, you use structured APIs or parsers instead of ad hoc string manipulation whenever the codebase or standard toolchain gives you a reasonable option.
+- You keep edits closely scoped to the modules, ownership boundaries, and behavioral surface implied by the request and surrounding code. You leave unrelated refactors and metadata churn alone unless they are truly needed to finish safely.
+- You add an abstraction only when it removes real complexity, reduces meaningful duplication, or clearly matches an established local pattern.
+- You let test coverage scale with risk and blast radius: you keep it focused for narrow changes, and you broaden it when the implementation touches shared behavior, cross-module contracts, or user-facing workflows.
+
+## Frontend guidance
+
+You follow these instructions when building applications with a frontend experience:
+
+### Build with empathy
+- If working with an existing design or given a design framework in context, you pay careful attention to existing conventions and ensure that what you build is consistent with the frameworks used and design of the existing application.
+- You think deeply about the audience of what you are building and use that to decide what features to build and when designing layout, components, visual style, on-screen text, and interaction patterns. Using your application should feel rich and sophisticated.
+- You make sure that the frontend design is tailored for the domain and subject matter of the application. For example, SaaS, CRM, and other operational tools should feel quiet, utilitarian, and work-focused rather than illustrative or editorial: avoid oversized hero sections, decorative card-heavy layouts, and marketing-style composition, and instead prioritize dense but organized information, restrained visual styling, predictable navigation, and interfaces built for scanning, comparison, and repeated action. A game can be more illustrative, expressive, animated, and playful.
+- You make sure that common workflows within the app are ergonomic and efficient, yet comprehensive -- the user of your application should be able to seamlessly navigate in and out of different views and pages in the application.
+
+### Design instructions
+- You make sure to use icons in buttons for tools, swatches for color, segmented controls for modes, toggles/checkboxes for binary settings, sliders/steppers/inputs for numeric values, menus for option sets, tabs for views, and text or icon+text buttons only for clear commands (unless otherwise specified). Cards are kept at 8px border radius or less unless the existing design system requires otherwise.
+- You do not use rounded rectangular UI elements with text inside if you could use a familiar symbol or icon instead (examples include arrow icons for undo/redo, B/I icons for bold/italics, save/download/zoom icons). You build tooltips which name/describe unfamiliar icons when the user hovers over it.
+- You use lucide icons inside buttons whenever one exists instead of manually-drawn SVG icons. If there is a library enabled in an existing application, you use icons from that library.
+- You build feature-complete controls, states, and views that a target user would naturally expect from the application.
+- You do not use visible, in-app text to describe the application's features, functionality, keyboard shortcuts, styling, visual elements, or how to use the application.
+- You should not make a landing page unless absolutely required; when asked for a site, app, game, or tool, build the actual usable experience as the first screen, not marketing or explanatory content.
+- When making a hero page, you use a relevant image, generated bitmap image, or immersive full-bleed interactive scene as the background with text over it that is not in a card; never use a split text/media layout where a card is one side and text is on another side, never put hero text or the primary experience in a card, never use a gradient/SVG hero page, and do not create an SVG hero illustration when a real or generated image can carry the subject.
+- On branded, product, venue, portfolio, or object-focused pages, the brand/product/place/object must be a first-viewport signal, not only tiny nav text or an eyebrow. Hero content must leave a hint of the next section's content visible on every mobile and desktop viewport, including wide desktop.
+- For landing-page heroes, make the H1 the brand/product/place/person name or a literal offer/category; put descriptive value props in supporting copy, not the headline.
+- Websites and games must use visual assets. You can use image search, known relevant images, or generated bitmap images instead of SVGs, unless making a game. Primary images and media should reveal the actual product, place, object, state, gameplay, or person; you refrain from dark, blurred, cropped, stock-like, or purely atmospheric media when the user needs to inspect the real thing. For highly specific game assets you use custom SVG/Three.js/etc.
+- For games or interactive tools with well-established rules, physics, parsing, or AI engines, you use a proven existing library for the core domain logic instead of hand-rolling it, unless the user explicitly asks for a from-scratch implementation.
+- You use Three.js for 3D elements, and make the primary 3D scene full-bleed or unframed and not inside a decorative card/preview container. Before finishing, you verify with Playwright screenshots and canvas-pixel checks across desktop/mobile viewports that it is nonblank, correctly framed, interactive/moving, and that referenced assets render as intended without overlapping.
+- You do not put UI cards inside other cards. Do not style page sections as floating cards. Only use cards for individual repeated items, modals, and genuinely framed tools. Page sections must be full-width bands or unframed layouts with constrained inner content.
+- You do not add discrete orbs, gradient orbs, or bokeh blobs as decoration or backgrounds.
+- You make sure that text fits within its parent UI element on all mobile and desktop viewports. Move it to a new line if needed, and if it still does not fit inside the UI element, use dynamic sizing so the longest word fits. Text must also not occlude preceding or subsequent content. Despite this, you check that text inside a UI button/card looks professionally designed and polished.
+- Match display text to its container: reserve hero-scale type for true heroes, and use smaller, tighter headings inside compact panels, cards, sidebars, dashboards, and tool surfaces.
+- You define stable dimensions with responsive constraints (such as  aspect-ratio, grid tracks, min/max, or container-relative sizing) for fixed-format UI elements like boards, grids, toolbars, icon buttons, counters, or tiles, so hover states, labels, icons, pieces, loading text, or dynamic content cannot resize or shift the layout.
+- You do not scale font size with viewport width. Letter spacing must be 0, not negative.
+- You do not make one-note palettes: avoid UIs dominated by variations of a single hue family, and limit dominant purple/purple-blue gradients, beige/cream/sand/tan, dark blue/slate, and brown/orange/espresso palettes; scan CSS colors before finalizing and revise if the page reads as one of these themes.
+- You make sure that UI elements and on-screen text do not overlap with each other in an incoherent manner. This is extremely important as it leads to a jarring user experience.
+
+When building a site or app that needs a dev server to run properly, you start the local dev server after implementation and give the user the URL so they can try it. If there's already a server on that port, you use another one. For a website where just opening the HTML will work, you don't start a dev server, and instead give the user a link to the HTML file that can open in their browser.
 
 ## Editing constraints
 
-- Default to ASCII when editing or creating files. Only introduce non-ASCII or other Unicode characters when there is a clear justification and the file already uses them.
-- Add succinct code comments that explain what is going on if code is not self-explanatory. You should not add comments like "Assigns the value to the variable", but a brief comment might be useful ahead of a complex code block that the user would otherwise have to spend time parsing out. Usage of these comments should be rare.
-- Try to use apply_patch for single file edits, but it is fine to explore other options to make the edit if it does not work well. Do not use apply_patch for changes that are auto-generated (i.e. generating package.json or running a lint or format command like gofmt) or when scripting is more efficient (such as search and replacing a string across a codebase).
-- Do not use Python to read/write files when a simple shell command or apply_patch would suffice.
+- You default to ASCII when editing or creating files. You introduce non-ASCII or other Unicode characters only when there is a clear reason and the file already lives in that character set.
+- You add succinct code comments only where the code is not self-explanatory. You avoid empty narration like "Assigns the value to the variable", but you do leave a short orienting comment before a complex block if it would save the user from tedious parsing. You use that tool sparingly.
+- Use \`apply_patch\` for manual code edits. Do not create or edit files with \`cat\` or other shell write tricks. Formatting commands and bulk mechanical rewrites do not need \`apply_patch\`.
+- Do not use Python to read or write files when a simple shell command or \`apply_patch\` is enough.
 - You may be in a dirty git worktree.
-    * NEVER revert existing changes you did not make unless explicitly requested, since these changes were made by the user.
-    * If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, don't revert those changes.
-    * If the changes are in files you've touched recently, you should read carefully and understand how you can work with the changes rather than reverting them.
-    * If the changes are in unrelated files, just ignore them and don't revert them.
-- Do not amend a commit unless explicitly requested to do so.
-- While you are working, you might notice unexpected changes that you didn't make. If this happens, STOP IMMEDIATELY and ask the user how they would like to proceed.
-- **NEVER** use destructive commands like \`git reset --hard\` or \`git checkout --\` unless specifically requested or approved by the user.
-- You struggle using the git interactive console. **ALWAYS** prefer using non-interactive git commands.
+  * NEVER revert existing changes you did not make unless explicitly requested, since these changes were made by the user.
+  * If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, you don't revert those changes.
+  * If the changes are in files you've touched recently, you read carefully and understand how you can work with the changes rather than reverting them.
+  * If the changes are in unrelated files, you just ignore them and don't revert them.
+- While working, you may encounter changes you did not make. You assume they came from the user or from generated output, and you do NOT revert them. If they are unrelated to your task, you ignore them. If they affect your task, you work **with** them instead of undoing them. Only ask the user how to proceed if those changes make the task impossible to complete.
+- Never use destructive commands like \`git reset --hard\` or \`git checkout --\` unless the user has clearly asked for that operation. If the request is ambiguous, ask for approval first.
+- You are clumsy in the git interactive console. Prefer non-interactive git commands whenever you can.
 
 ## Special user requests
 
-- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such as \`date\`), you should do so.
-- If the user asks for a "review", default to a code review mindset: prioritise identifying bugs, risks, behavioural regressions, and missing tests. Findings must be the primary focus of the response - keep summaries or overviews brief and only after enumerating the issues. Present findings first (ordered by severity with file/line references), follow with open questions or assumptions, and offer a change-summary only as a secondary detail. If no findings are discovered, state that explicitly and mention any residual risks or testing gaps.
+- If the user makes a simple request that can be answered directly by a terminal command, such as asking for the time via \`date\`, you go ahead and do that.
+- If the user asks for a "review", you default to a code-review stance: you prioritize bugs, risks, behavioral regressions, and missing tests. Findings should lead the response, with summaries kept brief and placed only after the issues are listed. Present findings first, ordered by severity and grounded in file/line references; then add open questions or assumptions; then include a change summary as secondary context. If you find no issues, you say that clearly and mention any remaining test gaps or residual risk.
 
-## Frontend tasks
-
-When doing frontend design tasks, avoid collapsing into "AI slop" or safe, average-looking layouts.
-Aim for interfaces that feel intentional, bold, and a bit surprising.
-- Typography: Use expressive, purposeful fonts and avoid default stacks (Inter, Roboto, Arial, system).
-- Color & Look: Choose a clear visual direction; define CSS variables; avoid purple-on-white defaults. No purple bias or dark mode bias.
-- Motion: Use a few meaningful animations (page-load, staggered reveals) instead of generic micro-motions.
-- Background: Don't rely on flat, single-color backgrounds; use gradients, shapes, or subtle patterns to build atmosphere.
-- Overall: Avoid boilerplate layouts and interchangeable UI patterns. Vary themes, type families, and visual languages across outputs.
-- Ensure the page loads properly on both desktop and mobile
+## Autonomy and persistence
+You stay with the work until the task is handled end to end within the current turn whenever that is feasible. Do not stop at analysis or half-finished fixes. Do not end your turn while \`exec_command\` sessions needed for the user’s request are still running. You carry the work through implementation, verification, and a clear account of the outcome unless the user explicitly pauses or redirects you.
 
-Exception: If working within an existing website or design system, preserve the established patterns, structure, and visual language.
+Unless the user explicitly asks for a plan, asks a question about the code, is brainstorming possible approaches, or otherwise makes clear that they do not want code changes yet, you assume they want you to make the change or run the tools needed to solve the problem. In those cases, do not stop at a proposal; implement the fix. If you hit a blocker, you try to work through it yourself before handing the problem back.
 
 # Working with the user
 
-You interact with the user through a terminal. You have 2 ways of communicating with the users:
-- Share intermediary updates in \`commentary\` channel. 
-- After you have completed all your work, send a message to the \`final\` channel.
-You are producing plain text that will later be styled by the program you run in. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value. Follow the formatting rules exactly.
+You have two channels for staying in conversation with the user:
+- You share updates in \`commentary\` channel.
+- After you have completed all of your work, you send a message to the \`final\` channel.
 
-## Autonomy and persistence
-Persist until the task is fully handled end-to-end within the current turn whenever feasible: do not stop at analysis or partial fixes; carry changes through implementation, verification, and a clear explanation of outcomes unless the user explicitly pauses or redirects you.
+The user may send messages while you are working. If those messages conflict, you let the newest one steer the current turn. If they do not conflict, you make sure your work and final answer honor every user request since your last turn. This matters especially after long-running resumes or context compaction. If the newest message asks for status, you give that update and then keep moving unless the user explicitly asks you to pause, stop, or only report status.
 
-Unless the user explicitly asks for a plan, asks a question about the code, is brainstorming potential solutions, or some other intent that makes it clear that code should not be written, assume the user wants you to make code changes or run tools to solve the user's problem. In these cases, it's bad to output your proposed solution in a message, you should go ahead and actually implement the change. If you encounter challenges or blockers, you should attempt to resolve them yourself.
+Before sending a final response after a resume, interruption, or context transition, you do a quick sanity check: you make sure your final answer and tool actions are answering the newest request, not an older ghost still lingering in the thread.
+
+When you run out of context, the tool automatically compacts the conversation. That means time never runs out, though sometimes you may see a summary instead of the full thread. When that happens, you assume compaction occurred while you were working. Do not restart from scratch; you continue naturally and make reasonable assumptions about anything missing from the summary.
 
 ## Formatting rules
 
+You are writing plain text that will later be styled by the program you run in. Let formatting make the answer easy to scan without turning it into something stiff or mechanical. Use judgment about how much structure actually helps, and follow these rules exactly.
+
 - You may format with GitHub-flavored Markdown.
-- Structure your answer if necessary, the complexity of the answer should match the task. If the task is simple, your answer should be a one-liner. Order sections from general to specific to supporting.
-- Never use nested bullets. Keep lists flat (single level). If you need hierarchy, split into separate lists or sections or if you use : just include the line you might usually render using a nested bullet immediately after it. For numbered lists, only use the \`1. 2. 3.\` style markers (with a period), never \`1)\`.
-- Headers are optional, only use them when you think they are necessary. If you do use them, use short Title Case (1-3 words) wrapped in **…**. Don't add a blank line.
-- Use monospace commands/paths/env vars/code ids, inline examples, and literal keyword bullets by wrapping them in backticks.
+- You add structure only when the task calls for it. You let the shape of the answer match the shape of the problem; if the task is tiny, a one-liner may be enough. Otherwise, you prefer short paragraphs by default; they leave a little air in the page. You order sections from general to specific to supporting detail.
+- Avoid nested bullets unless the user explicitly asks for them. Keep lists flat. If you need hierarchy, split content into separate lists or sections, or place the detail on the next line after a colon instead of nesting it. For numbered lists, use only the \`1. 2. 3.\` style, never \`1)\`. This does not apply to generated artifacts such as PR descriptions, release notes, changelogs, or user-requested docs; preserve those native formats when needed.
+- Headers are optional; you use them only when they genuinely help. If you do use one, make it short Title Case (1-3 words), wrap it in **…**, and do not add a blank line.
+- You use monospace commands/paths/env vars/code ids, inline examples, and literal keyword bullets by wrapping them in backticks.
 - Code samples or multi-line snippets should be wrapped in fenced code blocks. Include an info string as often as possible.
-- File References: When referencing files in your response follow the below rules:
-  * Use markdown links (not inline code) for clickable file paths.
-  * Each reference should have a stand alone path. Even if it's the same file.
-  * For clickable/openable file references, the path target must be an absolute filesystem path. Labels may be short (for example, \`[app.ts](/abs/path/app.ts)\`).
-  * Optionally include line/column (1-based): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
-  * Do not use URIs like file://, vscode://, or https://.
-  * Do not provide range of lines
-  * Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\\repo\\project\\main.rs:12:5
-- Don't use emojis or em dashes unless explicitly instructed.
+- When referencing a real local file, prefer a clickable markdown link.
+  * Clickable file links should look like [app.py](/abs/path/app.py:12): plain label, absolute target, with optional line number inside the target.
+  * If a file path has spaces, wrap the target in angle brackets: [My Report.md](</abs/path/My Project/My Report.md:3>).
+  * Do not wrap markdown links in backticks, or put backticks inside the label or target. This confuses the markdown renderer.
+  * Do not use URIs like file://, vscode://, or https:// for file links.
+  * Do not provide ranges of lines.
+  * Avoid repeating the same filename multiple times when one grouping is clearer.
+- Don’t use emojis or em dashes unless explicitly instructed.
 
 ## Final answer instructions
-- Balance conciseness to not overwhelm the user with appropriate detail for the request. Do not narrate abstractly; explain what you are doing and why.
-- Do not begin responses with conversational interjections or meta commentary. Avoid openers such as acknowledgements ("Done —", "Got it", "Great question, ") or framing phrases.
+
+In your final answer, you keep the light on the things that matter most. Avoid long-winded explanation. In casual conversation, you just talk like a person. For simple or single-file tasks, you prefer one or two short paragraphs plus an optional verification line. Do not default to bullets. When there are only one or two concrete changes, a clean prose close-out is usually the most humane shape.
+
+- You suggest follow ups if useful and they build on the users request, but never end your answer with an "If you want" sentence.
+- When you talk about your work, you use plain, idiomatic engineering prose with some life in it. You avoid coined metaphors, internal jargon, slash-heavy noun stacks, and over-hyphenated compounds unless you are quoting source text. In particular, do not lean on words like "seam", "cut", or "safe-cut" as generic explanatory filler.
 - The user does not see command execution outputs. When asked to show the output of a command (e.g. \`git show\`), relay the important details in your answer or summarize the key lines so the user understands the result.
 - Never tell the user to "save/copy this file", the user is on the same machine and has access to the same files as you have.
-- If the user asks for a code explanation, structure your answer with code references.
-- When given a simple task, just provide the outcome in a short answer without strong formatting.
-- When you make big or complex changes, state the solution first, then walk the user through what you did and why.
-- For casual chit-chat, just chat.
-- If you weren't able to do something, for example run tests, tell the user.
-- If there are natural next steps the user may want to take, suggest them at the end of your response. Do not make suggestions if there are no natural next steps. When suggesting multiple options, use numeric lists for the suggestions so the user can quickly respond with a single number.
+- If the user asks for a code explanation, you include code references as appropriate.
+- If you weren't able to do something, for example run tests, you tell the user.
+- Never overwhelm the user with answers that are over 50-70 lines long; provide the highest-signal context instead of describing everything exhaustively.
+- Tone of your final answer must match your personality.
+- Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query.
 
-## Intermediary updates 
+## Intermediary updates
 
 - Intermediary updates go to the \`commentary\` channel.
 - User updates are short updates while you are working, they are NOT final answers.
-- You use 1-2 sentence user updates to communicated progress and new information to the user as you are doing work. 
-- Do not begin responses with conversational interjections or meta commentary. Avoid openers such as acknowledgements ("Done —", "Got it", "Great question, ") or framing phrases.
-- You provide user updates frequently, every 20s.
-- Before exploring or doing substantial work, you start with a user update acknowledging the request and explaining your first step. You should include your understanding of the user request and explain what you will do. Avoid commenting on the request or using starters such at "Got it -" or "Understood -" etc.
-- When exploring, e.g. searching, reading files you provide user updates as you go, every 20s, explaining what context you are gathering and what you've learned. Vary your sentence structure when providing these updates to avoid sounding repetitive - in particular, don't start each sentence the same way.
-- After you have sufficient context, and the work is substantial you provide a longer plan (this is the only user update that may be longer than 2 sentences and can contain formatting).
+- You treat messages to the user while you are working as a place to think out loud in a calm, companionable way. You casually explain what you are doing and why in one or two sentences.
+- Never praise your plan by contrasting it with an implied worse alternative. For example, never use platitudes like "I will do <this good thing> rather than <this obviously bad thing>", "I will do <X>, not <Y>".
+- Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query.
+- You provide user updates frequently, every 30s.
+- When exploring, such as searching or reading files, you provide user updates as you go. You explain what context you are gathering and what you are learning. You vary your sentence structure so the updates do not fall into a drumbeat, and in particular you do not start each one the same way.
+- When working for a while, you keep updates informative and varied, but you stay concise.
+- Once you have enough context, and if the work is substantial, you offer a longer plan. This is the only user update that may run past two sentences and include formatting.
+- If you create a checklist or task list, you update item statuses incrementally as each item is completed rather than marking every item done only at the end.
 - Before performing file edits of any kind, you provide updates explaining what edits you are making.
-- As you are thinking, you very frequently provide updates even if not taking any actions, informing the user of your progress. You interrupt your thinking and send multiple updates in a row if thinking for more than 100 words.
-- Tone of your updates MUST match your personality.
+- Tone of your updates must match your personality.
 `;
 var init_source_codex = () => {};
 
@@ -57712,7 +57847,9 @@ async function updateAgentLLMConfig(agentId, modelHandle, updateArgs, options) {
       max_tokens: updateArgs.max_output_tokens
     }
   });
-  const finalAgent = await backend.retrieveAgent(agentId);
+  const finalAgent = await backend.retrieveAgent(agentId, {
+    include: ["agent.secrets", "agent.tools", "agent.tags"]
+  });
   return finalAgent;
 }
 async function updateConversationLLMConfig(conversationId, modelHandle, updateArgs, options) {
@@ -57785,7 +57922,9 @@ async function updateAgentSystemPrompt(agentId, systemPromptId) {
         settingsManager2.clearSystemPromptPreset(agentId);
       }
     }
-    const agent = await backend.retrieveAgent(agentId);
+    const agent = await backend.retrieveAgent(agentId, {
+      include: ["agent.secrets", "agent.tools", "agent.tags"]
+    });
     return {
       success: true,
       message: "System prompt applied successfully",
@@ -133158,9 +133297,20 @@ function isCloudflareEdge52xHtmlError2(text2) {
   return hasCloudflare && hasHtml && has52xCode;
 }
 function isCloudflareEdge52xErrorText(text2) {
-  return CLOUDFLARE_EDGE_5XX_FORMATTED_PATTERN.test(text2) || isCloudflareEdge52xHtmlError2(text2);
+  return CLOUDFLARE_EDGE_5XX_FORMATTED_PATTERN.test(text2) || CLOUDFLARE_JSON_5XX_PATTERN2.test(text2) || isCloudflareEdge52xHtmlError2(text2);
 }
 function parseCloudflareEdgeError2(text2) {
+  if (CLOUDFLARE_JSON_5XX_PATTERN2.test(text2)) {
+    try {
+      const obj = JSON.parse(text2);
+      return {
+        code: String(obj.status),
+        statusText: obj.error_name || obj.title || undefined,
+        host: obj.zone || undefined,
+        rayId: obj.ray_id || undefined
+      };
+    } catch {}
+  }
   if (!isCloudflareEdge52xHtmlError2(text2))
     return;
   const code = text2.match(/^\s*(502|52[0-6])\s*<!doctype html/i)?.[1] ?? text2.match(/error code\s*(502|52[0-6])/i)?.[1] ?? text2.match(/\|\s*(502|52[0-6])\s*:/i)?.[1];
@@ -133579,7 +133729,7 @@ function getRetryStatusMessage(errorDetail) {
   if (!errorDetail)
     return DEFAULT_RETRY_MESSAGE;
   if (isCloudflareEdge52xErrorText(errorDetail))
-    return null;
+    return "Cloudflare transient error, retrying...";
   if (checkZaiError(errorDetail))
     return "Z.ai API error, retrying...";
   if (errorDetail.includes("Anthropic API is overloaded"))
@@ -133605,7 +133755,7 @@ function createAgentLink2(runId, agentId, conversationId) {
   const url2 = buildChatUrl(agentId, { conversationId });
   return `View agent: \x1B]8;;${url2}\x1B\\${agentId}\x1B]8;;\x1B\\ (run: ${runId})`;
 }
-var LETTA_USAGE_URL2, LETTA_AGENTS_URL2, CLOUDFLARE_EDGE_5XX_MARKER_PATTERN2, CLOUDFLARE_EDGE_5XX_TITLE_PATTERN2, CLOUDFLARE_EDGE_5XX_FORMATTED_PATTERN, CHATGPT_USAGE_LIMIT_HINT2 = "Switch models with /model, or connect your own provider keys with /connect.", ENCRYPTED_CONTENT_HINT2, DEFAULT_RETRY_MESSAGE = "Unexpected downstream LLM API error, retrying...", ENDPOINT_TYPE_DISPLAY_NAMES;
+var LETTA_USAGE_URL2, LETTA_AGENTS_URL2, CLOUDFLARE_EDGE_5XX_MARKER_PATTERN2, CLOUDFLARE_EDGE_5XX_TITLE_PATTERN2, CLOUDFLARE_EDGE_5XX_FORMATTED_PATTERN, CLOUDFLARE_JSON_5XX_PATTERN2, CHATGPT_USAGE_LIMIT_HINT2 = "Switch models with /model, or connect your own provider keys with /connect.", ENCRYPTED_CONTENT_HINT2, DEFAULT_RETRY_MESSAGE = "Unexpected downstream LLM API error, retrying...", ENDPOINT_TYPE_DISPLAY_NAMES;
 var init_errorFormatter = __esm(() => {
   init_error();
   init_errorContext();
@@ -133615,6 +133765,7 @@ var init_errorFormatter = __esm(() => {
   CLOUDFLARE_EDGE_5XX_MARKER_PATTERN2 = /(^|\s)(502|52[0-6])\s*<!doctype html|error code\s*(502|52[0-6])/i;
   CLOUDFLARE_EDGE_5XX_TITLE_PATTERN2 = /\|\s*(502|52[0-6])\s*:/i;
   CLOUDFLARE_EDGE_5XX_FORMATTED_PATTERN = /\bCloudflare\s+(502|52[0-6])\b/i;
+  CLOUDFLARE_JSON_5XX_PATTERN2 = /"cloudflare_error"\s*:\s*true/s;
   ENCRYPTED_CONTENT_HINT2 = [
     "",
     "This occurs when the conversation contains messages with encrypted",
@@ -138101,7 +138252,7 @@ function extractTelemetryInputText(content) {
 }
 
 // src/websocket/listener/constants.ts
-var MAX_RETRY_DURATION_MS, INITIAL_RETRY_DELAY_MS = 1000, MAX_RETRY_DELAY_MS = 30000, SYSTEM_REMINDER_RE, LLM_API_ERROR_MAX_RETRIES = 3, EMPTY_RESPONSE_MAX_RETRIES = 2, MAX_PRE_STREAM_RECOVERY = 2, MAX_POST_STOP_APPROVAL_RECOVERY = 2, NO_AWAITING_APPROVAL_DETAIL_FRAGMENT = "no tool call is currently awaiting approval";
+var MAX_RETRY_DURATION_MS, INITIAL_RETRY_DELAY_MS = 1000, MAX_RETRY_DELAY_MS = 30000, SYSTEM_REMINDER_RE, LLM_API_ERROR_MAX_RETRIES = 3, EMPTY_RESPONSE_MAX_RETRIES = 2, MAX_PRE_STREAM_RECOVERY = 2, MAX_POST_STOP_APPROVAL_RECOVERY = 2;
 var init_constants2 = __esm(() => {
   MAX_RETRY_DURATION_MS = 5 * 60 * 1000;
   SYSTEM_REMINDER_RE = /<system-reminder>[\s\S]*?<\/system-reminder>/g;
@@ -139805,16 +139956,23 @@ var init_secrets_sync = __esm(() => {
 
 // src/websocket/listener/recovery.ts
 function isApprovalToolCallDesyncError(detail) {
-  if (isInvalidToolCallIdsError(detail) || isApprovalPendingError(detail)) {
-    return true;
+  return isInvalidToolCallIdsError(detail) || isApprovalPendingError(detail);
+}
+function getApprovalToolCallDesyncErrorText(errorInfo) {
+  const detail = errorInfo.detail;
+  if (typeof detail === "string" && isApprovalToolCallDesyncError(detail)) {
+    return detail;
   }
-  return typeof detail === "string" && detail.toLowerCase().includes(NO_AWAITING_APPROVAL_DETAIL_FRAGMENT);
+  const message = errorInfo.message;
+  if (typeof message === "string" && isApprovalToolCallDesyncError(message)) {
+    return message;
+  }
+  return null;
 }
 function shouldAttemptPostStopApprovalRecovery(params) {
-  const approvalDesyncDetected = isApprovalToolCallDesyncError(params.runErrorDetail) || isApprovalToolCallDesyncError(params.latestErrorText);
-  const genericNoRunError = params.stopReason === "error" && params.runIdsSeen === 0;
+  const approvalDesyncDetected = isApprovalToolCallDesyncError(params.runErrorDetail) || isApprovalToolCallDesyncError(params.latestErrorText) || isApprovalToolCallDesyncError(params.fallbackError);
   return shouldAttemptApprovalRecovery({
-    approvalPendingDetected: approvalDesyncDetected || genericNoRunError,
+    approvalPendingDetected: approvalDesyncDetected,
     retries: params.retries,
     maxRetries: MAX_POST_STOP_APPROVAL_RECOVERY
   });
@@ -143605,18 +143763,23 @@ async function handleIncomingMessage(msg, socket, runtime, onStatusChange, conne
           }
         }
         if (errorInfo) {
-          latestErrorText = errorInfo.message || latestErrorText;
-          emitLoopErrorNotice(socket, runtime, {
-            message: errorInfo.message || "Stream error",
-            stopReason: errorInfo.error_type || "error",
-            isTerminal: false,
-            runId: runId || errorInfo.run_id,
-            agentId,
-            conversationId,
-            errorInfo,
-            cancelRequested: runtime.cancelRequested,
-            abortSignal: turnAbortSignal
-          });
+          const recoverableApprovalErrorText = getApprovalToolCallDesyncErrorText(errorInfo);
+          latestErrorText = recoverableApprovalErrorText || errorInfo.detail || errorInfo.message || latestErrorText;
+          if (!recoverableApprovalErrorText) {
+            emitLoopErrorNotice(socket, runtime, {
+              message: errorInfo.message || "Stream error",
+              stopReason: errorInfo.error_type || "error",
+              isTerminal: false,
+              runId: runId || errorInfo.run_id,
+              agentId,
+              conversationId,
+              errorInfo,
+              cancelRequested: runtime.cancelRequested,
+              abortSignal: turnAbortSignal
+            });
+          } else {
+            debugLog("recovery", "Suppressing streamed approval conflict while post-stop recovery runs: %s", recoverableApprovalErrorText);
+          }
         }
         if (shouldOutput) {
           const normalizedChunk = normalizeToolReturnWireMessage(chunk);
@@ -143634,6 +143797,7 @@ async function handleIncomingMessage(msg, socket, runtime, onStatusChange, conne
       }, runtime.contextTracker);
       const stopReason = result.stopReason;
       const approvals = result.approvals || [];
+      const fallbackError = result.fallbackError ?? null;
       lastApprovalContinuationAccepted = false;
       if (stopReason === "end_turn" && runtime.cancelRequested) {
         finalizeInterruptedTurn(socket, runtime, {
@@ -143676,13 +143840,14 @@ async function handleIncomingMessage(msg, socket, runtime, onStatusChange, conne
       if (stopReason !== "requires_approval") {
         const lastRunId = runId || msgRunIds[msgRunIds.length - 1] || null;
         const runErrorInfo = lastRunId ? await fetchRunErrorInfo(lastRunId) : null;
-        const errorDetail = latestErrorText || runErrorInfo?.detail || runErrorInfo?.message || null;
+        const errorDetail = latestErrorText || runErrorInfo?.detail || runErrorInfo?.message || fallbackError || null;
         if (shouldAttemptPostStopApprovalRecovery({
           stopReason,
           runIdsSeen: msgRunIds.length,
           retries: postStopApprovalRecoveryRetries,
           runErrorDetail: errorDetail,
-          latestErrorText
+          latestErrorText,
+          fallbackError
         })) {
           postStopApprovalRecoveryRetries += 1;
           emitRecoverableStatusNotice(socket, runtime, {
@@ -151104,6 +151269,7 @@ var init_client4 = __esm(async () => {
     getInterruptApprovalsForEmission,
     normalizeToolReturnWireMessage,
     normalizeExecutionResultsForInterruptParity,
+    getApprovalToolCallDesyncErrorText,
     shouldAttemptPostStopApprovalRecovery,
     getApprovalContinuationRecoveryDisposition,
     markAwaitingAcceptedApprovalContinuationRunId,
@@ -154078,7 +154244,9 @@ In headless mode, use:
     try {
       debugLog("conversations", `retrieve(${specifiedConversationId}) [headless conv→agent lookup]`);
       const conversation = await backend4.retrieveConversation(specifiedConversationId);
-      agent = await backend4.retrieveAgent(conversation.agent_id);
+      agent = await backend4.retrieveAgent(conversation.agent_id, {
+        include: ["agent.secrets", "agent.tools", "agent.tags"]
+      });
     } catch (error51) {
       trackHeadlessBoundaryError("headless_conversation_lookup_failed", error51, "headless_startup_conversation_lookup");
       console.error(`Conversation ${specifiedConversationId} not found`);
@@ -154216,12 +154384,12 @@ In headless mode, use:
   let conversationId;
   let effectiveReflectionSettings;
   const isSubagent = process.env.LETTA_CODE_AGENT_ROLE === "subagent";
-  const startupMemfsFlag = autoEnableMemfsForFreshAgent ? true : memfsFlag;
+  let startupMemfsFlag = autoEnableMemfsForFreshAgent ? true : memfsFlag;
   if (backend4.capabilities.remoteMemfs && !autoEnableMemfsForFreshAgent) {
-    const { hydrateMemfsSettingFromAgent: hydrateMemfsSettingFromAgent2 } = await Promise.resolve().then(() => (init_memoryFilesystem(), exports_memoryFilesystem));
+    const { hydrateMemfsSettingFromAgent: hydrateMemfsSettingFromAgent2, isLettaCloud: isLettaCloud2 } = await Promise.resolve().then(() => (init_memoryFilesystem(), exports_memoryFilesystem));
     const memfsEnabled = await hydrateMemfsSettingFromAgent2(agent);
-    if (!memfsEnabled) {
-      console.warn("Warning: this agent does not have git-backed memory enabled. Run `/memfs enable` to enable MemFS.");
+    if (!memfsEnabled && !noMemfsFlag && await isLettaCloud2()) {
+      startupMemfsFlag = true;
     }
   }
   let memfsBgPromise;
@@ -154309,7 +154477,9 @@ In headless mode, use:
         const expected = rebuildPrompt(storedPreset, memoryMode);
         if (agent.system !== expected) {
           await backend4.updateAgent(agent.id, { system: expected });
-          agent = await backend4.retrieveAgent(agent.id);
+          agent = await backend4.retrieveAgent(agent.id, {
+            include: ["agent.secrets", "agent.tools", "agent.tags"]
+          });
         }
       } else {
         settingsManager.clearSystemPromptPreset(agent.id);
@@ -180148,7 +180318,7 @@ var init_registry2 = __esm(() => {
       }
     },
     "/rename": {
-      desc: "Rename agent or conversation (/rename agent|convo <name>)",
+      desc: "Rename agent or conversation (/rename agent [name]|convo [name])",
       order: 24,
       handler: () => {
         return "Renaming...";
@@ -198307,6 +198477,91 @@ var init_contextChart = __esm(() => {
   ].map(hexToFgAnsi);
 });
 
+// src/cli/helpers/conversationTitle.ts
+function normalizeConversationTitle(value) {
+  let normalized = value.replace(/\s+/g, " ").trim();
+  if (normalized.startsWith('"') && normalized.endsWith('"') || normalized.startsWith("'") && normalized.endsWith("'")) {
+    normalized = normalized.slice(1, -1).trim();
+  }
+  if (!normalized || normalized.startsWith("/")) {
+    return null;
+  }
+  return normalized.slice(0, CONVERSATION_TITLE_MAX_LENGTH);
+}
+function extractAssistantText(content) {
+  if (typeof content === "string") {
+    return content;
+  }
+  if (Array.isArray(content)) {
+    let collected = "";
+    for (const part of content) {
+      if (part && typeof part === "object" && "text" in part && typeof part.text === "string") {
+        collected += part.text;
+      }
+    }
+    return collected;
+  }
+  return "";
+}
+async function generateConversationTitleFromFork(client, conversationId) {
+  let forkId = null;
+  const abortController = new AbortController;
+  const timeoutId = setTimeout(() => abortController.abort(), CONVERSATION_TITLE_TIMEOUT_MS);
+  try {
+    const fork = await forkConversation(conversationId, { hidden: true });
+    forkId = fork.id;
+    const stream2 = await client.conversations.messages.create(forkId, {
+      messages: [
+        {
+          role: "user",
+          content: CONVERSATION_TITLE_USER_PROMPT
+        }
+      ],
+      override_model: DEFAULT_SUMMARIZATION_MODEL,
+      override_system: CONVERSATION_TITLE_SYSTEM_PROMPT,
+      max_steps: 1,
+      streaming: true,
+      stream_tokens: false,
+      include_pings: false
+    }, { signal: abortController.signal });
+    let titleText = "";
+    for await (const chunk of stream2) {
+      if (chunk && typeof chunk === "object" && "message_type" in chunk && chunk.message_type === "assistant_message") {
+        titleText += extractAssistantText(chunk.content);
+      }
+    }
+    return normalizeConversationTitle(titleText);
+  } catch (err) {
+    if (isDebugEnabled()) {
+      console.error("[DEBUG] generateConversationTitleFromFork failed:", err);
+    }
+    return null;
+  } finally {
+    clearTimeout(timeoutId);
+    if (forkId) {
+      client.conversations.delete(forkId).catch((err) => {
+        if (isDebugEnabled()) {
+          console.error("[DEBUG] failed to delete title-fork conversation:", err);
+        }
+      });
+    }
+  }
+}
+var CONVERSATION_TITLE_MAX_LENGTH = 100, CONVERSATION_TITLE_TIMEOUT_MS = 30000, CONVERSATION_TITLE_SYSTEM_PROMPT = `You are a conversation title generator.
+
+Output ONLY a short, descriptive title for the conversation above.
+Rules:
+- 2 to 7 words
+- describe the actual topic, not the mood
+- no quotes, markdown, prefixes, or trailing punctuation
+- never call any tools — reply with plain text only
+- avoid generic titles like "New conversation" or "Help request"`, CONVERSATION_TITLE_USER_PROMPT = "Based on the conversation above, output a short title (2-7 words) describing the topic. Reply with ONLY the title text — no quotes, no tools, no preamble.";
+var init_conversationTitle = __esm(() => {
+  init_conversations2();
+  init_constants();
+  init_debug();
+});
+
 // src/cli/helpers/logoutMessage.ts
 function buildLogoutSuccessMessage(hasEnvApiKey) {
   if (!hasEnvApiKey) {
@@ -200873,8 +201128,53 @@ function App2({
   const sharedReminderStateRef = import_react105.useRef(createSharedReminderState());
   const systemPromptRecompileByConversationRef = import_react105.useRef(new Map);
   const queuedSystemPromptRecompileByConversationRef = import_react105.useRef(new Set);
-  const hasSetConversationSummaryRef = import_react105.useRef(resumedExistingConversation);
+  const shouldAutoGenerateConversationTitleRef = import_react105.useRef(!resumedExistingConversation);
+  const isAutoConversationTitleInFlightRef = import_react105.useRef(false);
   const firstUserQueryRef = import_react105.useRef(null);
+  const setConversationAutoTitleEligibility = import_react105.useCallback((enabled) => {
+    shouldAutoGenerateConversationTitleRef.current = enabled;
+    isAutoConversationTitleInFlightRef.current = false;
+    firstUserQueryRef.current = null;
+  }, []);
+  const deriveAutoConversationTitle = import_react105.useCallback(() => {
+    if (firstUserQueryRef.current) {
+      return firstUserQueryRef.current;
+    }
+    for (const lineId of buffersRef.current.order) {
+      const line = buffersRef.current.byId.get(lineId);
+      if (!line || line.kind !== "user") {
+        continue;
+      }
+      const title = normalizeConversationTitle(line.text);
+      if (title) {
+        return title;
+      }
+    }
+    return null;
+  }, []);
+  const generateConversationTitle = import_react105.useCallback(async () => {
+    const fallback = deriveAutoConversationTitle();
+    if (!experimentManager.isEnabled("conversation_titles")) {
+      return fallback;
+    }
+    if (getBackend().capabilities.localModelCatalog) {
+      return fallback;
+    }
+    const conversationId2 = conversationIdRef.current;
+    if (!conversationId2 || conversationId2 === "default") {
+      return fallback;
+    }
+    try {
+      const client = await getClient();
+      const aiTitle = await generateConversationTitleFromFork(client, conversationId2);
+      return aiTitle ?? fallback;
+    } catch (err) {
+      if (isDebugEnabled()) {
+        console.error("[DEBUG] generateConversationTitle failed:", err);
+      }
+      return fallback;
+    }
+  }, [deriveAutoConversationTitle]);
   const resetBootstrapReminderState = import_react105.useCallback(() => {
     resetSharedReminderState(sharedReminderStateRef.current);
   }, []);
@@ -202724,16 +203024,25 @@ ${feedback}
           if (needsEagerApprovalCheck) {
             setNeedsEagerApprovalCheck(false);
           }
-          if (!hasSetConversationSummaryRef.current && firstUserQueryRef.current && conversationIdRef.current !== "default") {
-            hasSetConversationSummaryRef.current = true;
-            const client = await getClient();
-            client.conversations.update(conversationIdRef.current, {
-              summary: firstUserQueryRef.current
-            }).catch((err) => {
-              if (isDebugEnabled()) {
-                console.error("[DEBUG] Failed to set conversation summary:", err);
-              }
-            });
+          if (shouldAutoGenerateConversationTitleRef.current && !isAutoConversationTitleInFlightRef.current && conversationIdRef.current !== "default") {
+            isAutoConversationTitleInFlightRef.current = true;
+            const conversationTitle = await generateConversationTitle();
+            if (!conversationTitle) {
+              isAutoConversationTitleInFlightRef.current = false;
+            } else {
+              const client = await getClient();
+              client.conversations.update(conversationIdRef.current, {
+                summary: conversationTitle
+              }).then(() => {
+                shouldAutoGenerateConversationTitleRef.current = false;
+              }).catch((err) => {
+                if (isDebugEnabled()) {
+                  console.error("[DEBUG] Failed to update conversation title:", err);
+                }
+              }).finally(() => {
+                isAutoConversationTitleInFlightRef.current = false;
+              });
+            }
           }
           const trajectorySnapshot = sessionStatsRef.current.endTrajectory();
           setTrajectoryTokenBase(0);
@@ -203884,6 +204193,7 @@ ${feedback}
       const resumeData = await getResumeData(client, agentState, conversationId2);
       await maybeCarryOverActiveConversationModel(conversationId2);
       setConversationIdAndRef(conversationId2);
+      setConversationAutoTitleEligibility(false);
       pendingConversationSwitchRef.current = {
         origin: "fork",
         conversationId: conversationId2,
@@ -203948,6 +204258,7 @@ ${feedback}
     runEndHooks,
     maybeCarryOverActiveConversationModel,
     resetBootstrapReminderState,
+    setConversationAutoTitleEligibility,
     setConversationIdAndRef,
     setCommandRunning,
     setStreaming,
@@ -204002,6 +204313,7 @@ ${feedback}
       const agentModelHandle = getPreferredAgentModelHandle2(agent);
       setCurrentModelHandle(agentModelHandle);
       setConversationIdAndRef(targetConversationId);
+      setConversationAutoTitleEligibility(false);
       resetBootstrapReminderState();
       {
         const { getModelDisplayName: getModelDisplayName3 } = await Promise.resolve().then(() => (init_model(), exports_model));
@@ -204055,6 +204367,7 @@ ${feedback}
     resetTrajectoryBases,
     resetBootstrapReminderState,
     resetPendingReasoningCycle,
+    setConversationAutoTitleEligibility,
     setConversationIdAndRef
   ]);
   const handleCreateNewAgent = import_react105.useCallback(async (name21) => {
@@ -204125,6 +204438,7 @@ ${feedback}
       const agentModelHandle = getPreferredAgentModelHandle2(agent);
       setCurrentModelHandle(agentModelHandle);
       setConversationIdAndRef(targetConversationId);
+      setConversationAutoTitleEligibility(false);
       pendingConversationSwitchRef.current = {
         origin: "agent-switch",
         conversationId: targetConversationId,
@@ -204159,6 +204473,7 @@ ${feedback}
     resetDeferredToolCallCommits,
     resetTrajectoryBases,
     resetBootstrapReminderState,
+    setConversationAutoTitleEligibility,
     setConversationIdAndRef
   ]);
   const handleBashSubmit = import_react105.useCallback(async (command) => {
@@ -204364,8 +204679,8 @@ ${SYSTEM_REMINDER_CLOSE}` : "";
     if (!isSystemOnly && userTextForInput.length > 0) {
       telemetry.trackUserInput(userTextForInput, "user", currentModelId || "unknown");
     }
-    if (!hasSetConversationSummaryRef.current && firstUserQueryRef.current === null && !isSystemOnly && userTextForInput.length > 0 && !userTextForInput.startsWith("/")) {
-      firstUserQueryRef.current = userTextForInput.slice(0, 100);
+    if (shouldAutoGenerateConversationTitleRef.current && firstUserQueryRef.current === null && !isSystemOnly && userTextForInput.length > 0 && !userTextForInput.startsWith("/")) {
+      firstUserQueryRef.current = userTextForInput.replace(/\s+/g, " ").trim().slice(0, 100);
     }
     if (pendingApprovals.length > 0) {
       return { submitted: false };
@@ -205054,9 +205369,7 @@ Type your task to begin the loop.`, true);
             isolated_block_labels: [...ISOLATED_BLOCK_LABELS],
             ...conversationName && { summary: conversationName }
           });
-          if (conversationName) {
-            hasSetConversationSummaryRef.current = true;
-          }
+          setConversationAutoTitleEligibility(!conversationName);
           await maybeCarryOverActiveConversationModel(conversation.id);
           setConversationIdAndRef(conversation.id);
           pendingConversationSwitchRef.current = {
@@ -205100,8 +205413,8 @@ Type your task to begin the loop.`, true);
             await client.conversations.update(forked.id, {
               summary: conversationSummary
             });
-            hasSetConversationSummaryRef.current = true;
           }
+          setConversationAutoTitleEligibility(false);
           await maybeCarryOverActiveConversationModel(forked.id);
           setConversationIdAndRef(forked.id);
           pendingConversationSwitchRef.current = {
@@ -205156,6 +205469,7 @@ Type your task to begin the loop.`, true);
             agent_id: agentId,
             isolated_block_labels: [...ISOLATED_BLOCK_LABELS]
           });
+          setConversationAutoTitleEligibility(true);
           await maybeCarryOverActiveConversationModel(conversation.id);
           setConversationIdAndRef(conversation.id);
           pendingConversationSwitchRef.current = {
@@ -205273,8 +205587,8 @@ Type your task to begin the loop.`, true);
             "Rename the current agent or conversation.",
             "",
             "USAGE",
-            "  /rename agent <name>      — rename the agent",
-            "  /rename convo <summary>   — rename the conversation",
+            "  /rename agent [name]      — rename the agent",
+            "  /rename convo [name]      — rename the convo, or auto-generate when omitted",
             "  /rename help              — show this help"
           ].join(`
 `);
@@ -205282,26 +205596,41 @@ Type your task to begin the loop.`, true);
           return { submitted: true };
         }
         if (!subcommand || subcommand !== "agent" && subcommand !== "convo") {
-          cmd.fail("Usage: /rename agent <name> or /rename convo <summary>");
+          cmd.fail("Usage: /rename agent [name] or /rename convo [name]");
           return { submitted: true };
         }
         const newValue = parts.slice(2).join(" ");
-        if (!newValue) {
-          cmd.fail(subcommand === "convo" ? "Please provide a summary: /rename convo <summary>" : "Please provide a name: /rename agent <name>");
+        if (subcommand === "agent" && !newValue) {
+          cmd.fail("Please provide a name: /rename agent <name>");
           return { submitted: true };
         }
         if (subcommand === "convo") {
+          const shouldAutoGenerate = newValue.trim().length === 0;
           cmd.update({
-            output: `Renaming conversation to "${newValue}"...`,
+            output: shouldAutoGenerate ? "Generating conversation title..." : `Renaming conversation to "${newValue}"...`,
             phase: "running"
           });
           setCommandRunning(true);
           try {
             const client = await getClient();
-            await client.conversations.update(conversationId, {
-              summary: newValue
-            });
-            cmd.finish(`Conversation renamed to "${newValue}"`, true);
+            if (shouldAutoGenerate) {
+              const conversationTitle = await generateConversationTitle();
+              if (!conversationTitle) {
+                cmd.fail("No conversation content available to generate a title");
+                return { submitted: true };
+              }
+              await client.conversations.update(conversationId, {
+                summary: conversationTitle
+              });
+              setConversationAutoTitleEligibility(false);
+              cmd.finish(`Conversation title set to "${conversationTitle}"`, true);
+            } else {
+              await client.conversations.update(conversationId, {
+                summary: newValue
+              });
+              setConversationAutoTitleEligibility(false);
+              cmd.finish(`Conversation renamed to "${newValue}"`, true);
+            }
           } catch (error51) {
             const errorDetails = formatErrorDetails2(error51, agentId);
             cmd.fail(`Failed: ${errorDetails}`);
@@ -205408,6 +205737,7 @@ Type your task to begin the loop.`, true);
               const client = await getClient();
               const resumeData = await getResumeData(client, agentState, targetConvId);
               setConversationIdAndRef(targetConvId);
+              setConversationAutoTitleEligibility(false);
               pendingConversationSwitchRef.current = {
                 origin: "resume-direct",
                 conversationId: targetConvId,
@@ -206532,6 +206862,7 @@ ${SYSTEM_REMINDER_CLOSE}
     systemInfoReminderEnabled,
     appendTaskNotificationEvents,
     maybeCarryOverActiveConversationModel,
+    setConversationAutoTitleEligibility,
     setConversationIdAndRef
   ]);
   const onSubmitRef = import_react105.useRef(onSubmit);
@@ -207578,6 +207909,7 @@ ${guidance}`);
               if (agentState) {
                 const resumeData = await getResumeData(client, agentState, action.conversationId);
                 setConversationIdAndRef(action.conversationId);
+                setConversationAutoTitleEligibility(false);
                 pendingConversationSwitchRef.current = {
                   origin: "resume-selector",
                   conversationId: action.conversationId,
@@ -207637,6 +207969,7 @@ ${guidance}`);
     commandRunner.start,
     recoverRestoredPendingApprovals,
     resetBootstrapReminderState,
+    setConversationAutoTitleEligibility,
     setConversationIdAndRef
   ]);
   const handleFeedbackSubmit = import_react105.useCallback(async (message) => {
@@ -208888,6 +209221,7 @@ If using apply_patch, use this exact relative patch path: ${applyPatchRelativePa
                       const client = await getClient();
                       const resumeData = await getResumeData(client, agentState, convId);
                       setConversationIdAndRef(convId);
+                      setConversationAutoTitleEligibility(false);
                       pendingConversationSwitchRef.current = {
                         origin: "resume-selector",
                         conversationId: convId,
@@ -208896,9 +209230,6 @@ If using apply_patch, use this exact relative patch path: ${applyPatchRelativePa
                         summary: selectorContext?.summary,
                         messageHistory: resumeData.messageHistory
                       };
-                      if (selectorContext?.summary) {
-                        hasSetConversationSummaryRef.current = true;
-                      }
                       settingsManager.persistSession(agentId, convId);
                       const currentAgentName = agentState.name || "Unnamed Agent";
                       const successLines = resumeData.messageHistory.length > 0 ? [
@@ -209000,6 +209331,7 @@ If using apply_patch, use this exact relative patch path: ${applyPatchRelativePa
                     });
                     await maybeCarryOverActiveConversationModel(conversation.id);
                     setConversationIdAndRef(conversation.id);
+                    setConversationAutoTitleEligibility(true);
                     settingsManager.persistSession(agentId, conversation.id);
                     const currentAgentName = agentState?.name || "Unnamed Agent";
                     const shortConvId = conversation.id.slice(0, 20);
@@ -209084,6 +209416,7 @@ If using apply_patch, use this exact relative patch path: ${applyPatchRelativePa
                       const client = await getClient();
                       const resumeData = await getResumeData(client, agentState, actualTargetConv);
                       setConversationIdAndRef(actualTargetConv);
+                      setConversationAutoTitleEligibility(false);
                       pendingConversationSwitchRef.current = {
                         origin: "search",
                         conversationId: actualTargetConv,
@@ -209315,6 +209648,7 @@ var init_App2 = __esm(async () => {
   init_backfill();
   init_chunkLog();
   init_contextChart();
+  init_conversationTitle();
   init_diff2();
   init_errorContext();
   init_errorFormatter();
@@ -211700,7 +212034,9 @@ async function updateAgentLLMConfig2(agentId, modelHandle, updateArgs, options)
       max_tokens: updateArgs.max_output_tokens
     }
   });
-  const finalAgent = await backend3.retrieveAgent(agentId);
+  const finalAgent = await backend3.retrieveAgent(agentId, {
+    include: ["agent.secrets", "agent.tools", "agent.tags"]
+  });
   return finalAgent;
 }
 async function updateAgentSystemPromptRaw2(agentId, systemPromptContent) {
@@ -211742,7 +212078,9 @@ async function updateAgentSystemPrompt2(agentId, systemPromptId) {
         settingsManager2.clearSystemPromptPreset(agentId);
       }
     }
-    const agent = await backend3.retrieveAgent(agentId);
+    const agent = await backend3.retrieveAgent(agentId, {
+      include: ["agent.secrets", "agent.tools", "agent.tags"]
+    });
     return {
       success: true,
       message: "System prompt applied successfully",
@@ -212930,6 +213268,7 @@ function extractReasonList(value) {
 }
 var CLOUDFLARE_EDGE_5XX_MARKER_PATTERN = /(^|\s)(502|52[0-6])\s*<!doctype html|error code\s*(502|52[0-6])/i;
 var CLOUDFLARE_EDGE_5XX_TITLE_PATTERN = /\|\s*(502|52[0-6])\s*:/i;
+var CLOUDFLARE_JSON_5XX_PATTERN = /"cloudflare_error"\s*:\s*true/s;
 function isCloudflareEdge52xHtmlError(text2) {
   const normalized = text2.toLowerCase();
   const hasCloudflare = normalized.includes("cloudflare");
@@ -212938,6 +213277,17 @@ function isCloudflareEdge52xHtmlError(text2) {
   return hasCloudflare && hasHtml && has52xCode;
 }
 function parseCloudflareEdgeError(text2) {
+  if (CLOUDFLARE_JSON_5XX_PATTERN.test(text2)) {
+    try {
+      const obj = JSON.parse(text2);
+      return {
+        code: String(obj.status),
+        statusText: obj.error_name || obj.title || undefined,
+        host: obj.zone || undefined,
+        rayId: obj.ray_id || undefined
+      };
+    } catch {}
+  }
   if (!isCloudflareEdge52xHtmlError(text2))
     return;
   const code = text2.match(/^\s*(502|52[0-6])\s*<!doctype html/i)?.[1] ?? text2.match(/error code\s*(502|52[0-6])/i)?.[1] ?? text2.match(/\|\s*(502|52[0-6])\s*:/i)?.[1];
@@ -220554,4 +220904,4 @@ Error during initialization: ${message}`);
 }
 main();
 
-//# debugId=DF17D4182CD359FB64756E2164756E21
+//# debugId=F09C9549AC025A7964756E2164756E21

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@letta-ai/letta-code",
-  "version": "0.25.1",
+  "version": "0.25.2",
   "description": "Letta Code is a CLI tool for interacting with stateful Letta agents from the terminal.",
   "type": "module",
   "bin": {