Skip to content

Caudra 0.2 Preview 11

View Markdown~3,265 tokens

v0.2.0-preview.11 on GitHub

  • Sign in to one provider with several subscriptions and API keys, and let Caudra switch between them without breaking the prompt cache.
  • Config edits keep your comments.
  • Opt-in cache warming keeps the Anthropic prompt cache alive through long tool runs.
  • Editors and desktop apps get more of Caudra over ACP: several sessions, session management, sign-in, steering, and background subagents.
  • Image generation, the host description, workflows, and automations move into the code tool as modules with on-demand help, and tool_search is gone.
  • Snippets can sleep and read the clock, and timeoutSec bounds a run.

Important

Close every other Caudra session before you start Preview 11. On its first start, Preview 11 upgrades the session database in your state directory, and the upgrade needs exclusive access. This includes other terminals, editor sessions over ACP, and caudra storage commands. While any of them has the database open, Preview 11 does not start. It lists the sessions to close, and nothing is changed.

The upgrade keeps your sessions, saves the old database as caudra.db.v30.bak next to caudra.db, and moves each saved provider login to auth/accounts/<provider>/default.json. Preview 10 and earlier cannot open the upgraded database or read the moved logins, and caudra rollback restores only the previous binary.

Warning

Before you start Preview 11, remove the settings that deferred tools. image_generate, execution_environment, workflow, and automation are now modules of the code tool, and tool_search is gone. A config or profile that still uses any of the following fails to load, with an error that names the fix:

  1. Delete defer_builtin_tools from [agent] in caudra.toml.
  2. Delete tool_search from [decisions.features].
  3. Replace lazy in a system prompt profile's tools block with eager or disabled. An MCP tool that was lazy stays callable as eager.
  4. Remove code from agent.disabled_tools and from profile overrides that disable it. code now hosts the modules and cannot be turned off, so turn off a module's tool group instead: images for image, execution for host, and delegation for workflow and automation.

Permission rules, agent.disabled_tools entries, and profile groups that name the four tools keep working. In snippets, decide(), rerank(), search(), servers(), resources(), and read_resource() are now decisions.decide(), decisions.rerank(), mcp.search(), mcp.servers(), mcp.resources(), and mcp.read_resource(), and the old names raise NameError naming the new call.

  • Modules with on-demand help: A code snippet now reaches everything beyond the interpreter through modules: history, mcp, decisions, image, host, workflow, and automation. help() lists them, and help("image") or help("workflow.start") shows the full reference with examples. The first history.search, history.read, image.generate, or workflow.start in a conversation returns its reference instead of running, unless help already showed it. The code description no longer changes with what the session connects, so the prompt cache holds. See Modules.
  • Tools as module calls: await image.generate(prompt, out), await host.environment(), await workflow.start(...), and await automation.list() run the tools they replace, with the same permission rules, plan mode checks, and cards, and return dicts to the snippet. Each call's row on the code card opens to the tool's own card. See Tools reached from code.
  • Sleep, clocks, and timeoutSec: time.sleep() and await asyncio.sleep() now wait for real, and time.time(), time.monotonic(), and datetime.now() read the host clock in UTC. Waiting does not count toward the 30 seconds of computation, and Esc stops it. timeoutSec is back as a wall-clock deadline for the whole run, 120 seconds by default and up to 3600, so a snippet can poll a workflow. See The Python subset and Run time.
  • More Python: Monty 1.2 adds CSV and TOML parsing, hashing, bisection, os.path, match statements, and dataclass field defaults.
  • JavaScript habits repaired: A snippet that starts an assignment with const, let, or var, or passes a host call one JavaScript object, now runs as the Python it meant. See Results and errors.
  • What a subagent did, on its task card: A running task card now lists every step of the subagent, newest last, instead of only the current one. A code row reads like code 3 calls and lists the newest calls with their status. See In the transcript.
  • Several accounts per provider: Each caudra auth login adds an account, such as a second Claude subscription or an API key, and --name names it. caudra auth status lists every account with the quota it has left, caudra auth use <provider> <name|auto> chooses one, and caudra auth rename and caudra auth logout <provider> [name] [--all] manage them. --account <provider>:<name|auto> and CAUDRA_ACCOUNT choose an account for one run. Several comma-separated keys in a provider's key variable become the accounts env-1, env-2, and so on. See Accounts.
  • Automatic switching: With two or more accounts, Auto keeps each conversation on its account and moves it to another before the account runs out. It moves only where the prompt cache is cold anyway, unless the account is nearly spent or refused, and a rate limit shorter than 30 seconds waits on the same account. ordered tries the accounts in priority order, and paced uses the quota that resets soonest. [<provider>.switching] and [[<provider>.accounts]] in providers.toml set the thresholds, the order, and which API keys may take over from spent subscriptions. See How Auto switches.
  • Across providers: With [switching] providers = ["anthropic", "openai"] in providers.toml, Auto moves a conversation to another provider's subscription once every subscription of its own runs out, and back once the first provider has quota again. See Across providers.
  • Accounts in the TUI: /accounts or Ctrl+X i lists, pins, adds, renames, orders, and removes the accounts of every provider, with fresh quota readings. The status bar shows the account a conversation uses, each switch adds a transcript row with its cause and cache cost, and /usage splits spend by account. /login also offers the xAI subscription sign-in.
  • Sign-in details: A key saved by caudra auth login is now tried before the provider's key variable, and the prompt hides the key as you type it. caudra auth logout deletes only the credential and keeps the account entry in providers.toml.
  • Opt-in cache warming: cache_warming = "running" under [agent] in the global caudra.toml sends the last request again with max_tokens: 0 shortly before its Anthropic prompt cache expires, while a run waits on a long tool, subagent, question, or permission prompt. "idle" also warms for up to 30 minutes after a run ends. It is off by default, covers the Anthropic API only, and warms only when that costs less than the cache write it avoids. /usage shows what warming cost and saved, or what it would have saved while it is off. See Cache warming.
  • Several sessions: One caudra acp process now keeps every session an editor opens, each with its own tools, so sessions in different projects run side by side. Editors can list, resume, close, delete, and fork Caudra sessions, and the list shows each session's title and its first and last prompt. See ACP and Sessions.
  • Sign-in: Editors get a caudra-login auth method that runs caudra auth login, and caudra acp starts with no signed-in provider so the editor can offer it. See Authentication.
  • Pickers and model catalog: Editors get pickers for reasoning effort, mode, and permission mode beside the model, and a fast mode toggle where supported. The choices are saved with the session, and editors can list models before opening one. See Config options.
  • Slash commands and compaction: Editors list /compact, your skills, and MCP prompts as slash commands, and show compaction progress and retried provider requests. See Slash commands.
  • Cancellation and steering: Cancelling a prompt withdraws open permission prompts and questions and answers cancelled exactly once. A prompt sent right after a cancel runs once the cancelled turn ends, so editors such as Orca that steer by cancelling and prompting again work, and a prompt sent with _meta.caudra.delivery: "steer" joins the running turn. See Prompts, cancellation, and steering.
  • Turn details: Answers carry the turn's duration and usage, tool calls name their tool, shell calls report stdout, stderr, and exit code, and failures carry their text instead of a bare "Internal error". See Turn updates.
  • Subagents and background tasks: Subagents and shell commands can run in the background over ACP, as in the TUI. Editors that support ACP subagent sessions get one per subagent, editors that opt in with _meta["caudra/childWork"] can follow and stop this work, and other editors see each subagent's tool calls in the parent session. See Subagents and background tasks.
  • Questions as permission requests: An editor without form elicitation that sets _meta["caudra/questionsViaPermission"] gets the question tool's questions as permission requests. See Permissions and questions.
  • Answers every request: A second prompt to a busy session is refused instead of left unanswered, and a stdin line that is not JSON or is over 64 MiB is skipped instead of breaking the connection.
  • Image viewing: The image viewer and workbench image tabs now zoom and pan. Pictures are sized to the terminal's cells and redrawn when the window or font changes, and a click outside the picture closes the viewer.
  • Orca resumes Caudra: In an Orca terminal, Caudra now reports its session id, so Orca can reopen it with caudra --resume <id>, and lists running subagents as child rows. Off Windows, clicking a row switches to that subagent's chat when Orca supports it. See Orca.
  • Docs from any modal: A ? on the top border of a modal such as /accounts or /usage, or F1, opens the manual section about it above the modal, so Esc returns to it. The key hints on the top border of /usage and /tools also answer a click. See Docs.
  • Tool cards fold like a file read: source_code_context, source_code_refs, and memory reads now rest as one row that a click opens whole. A Home Assistant or Executor call inside a code or batch card shows its whole card, a memory write shows the whole note, and a click on a write's title folds it in the expanded /view too. If you set your own ui.always_collapsed list, add "source_code_context", "source_code_refs", and "memory_read" to it.
  • One proxy for every request: All of Caudra's own requests, decision endpoints and Lua's caudra.net included, now use HTTPS_PROXY, HTTP_PROXY, ALL_PROXY, and NO_PROXY. A proxy set only in a project .caudra/.env no longer applies, so set it in your shell or the global .env. See Network proxies.
  • Cancelling stops the running command: Cancelling a turn while a shell command runs, with Esc or from an ACP editor, now stops the command and every process it started.
  • Config edits keep your comments: Saving a provider or decision endpoint, toggling an MCP server, or saving sandbox records now changes only the keys that changed, and keeps your comments, quoting, and table order.
  • Refusals end the turn: A provider refusal or content filter now ends the turn as refused instead of prompting a retry.
  • Resources read as their type: An MCP resource that is not markdown now shows its text as the server wrote it.
  • Purposes sorted by spend: The session's Per purpose table in /usage now lists the purpose that cost the most first.

Website privacy and analytics