@spinalfluid/ultrac 0.1.9 → 0.1.14

package/README.md

@@ -141,12 +141,38 @@ ultrac "Find the main entry points and summarize the architecture"
 Inside a session:
 
 - Type to talk to Ultrac; it inspects the repository with tools as needed.
+- On supported terminals, the full-width input box stays at the bottom while tools and replies
+  run above it. The footer shows only the current model. `/usage` and `/context` show token and context details.
+  Thinking and tool activity lines show their own live elapsed timers and retain the measured
+  duration when finished. Sub-second durations are hidden. Tool actions stay in a collapsed activity group;
+  click it or press Ctrl+O to expand, then click an action for command and output details. Green and red
+  dots show success and failure. Use `/output` for full saved results. Slash suggestions use aligned
+  command and description columns on the terminal background.
+- Type `/` to browse built-in commands and available skills. Type to filter, use arrow keys
+  to select, and press Tab or Enter to fill the command. Press Enter again to run it;
+  Esc dismisses the menu. `/skill <name> [args]` runs a skill without a custom command.
+- Drop a PNG, JPEG or WebP screenshot into the composer: it displays as `[Image 1]`,
+  and Cosmic receives the pixels. Images are resized to fit 1024 × 1024, with one active image
+  at a time; follow-up questions retain it until another image replaces it. Normalized images
+  are included in the private saved-session checkpoint so resumed tasks can inspect them.
+- When a newer public npm release exists, choose Update now, Skip, or Skip until next version.
+  Installing requires an explicit choice and verifies the selected installed CLI version.
+- Multiple-choice questions accept arrow keys and Enter, or a mouse click where the terminal
+  supports mouse reporting. You can also type a number or your own answer.
 - You can type another message while Ultrac is working. It is queued and inserted after the current
   tool call finishes, before the next model request. Remaining tools in that batch are skipped.
   Slash commands wait for the main prompt instead of entering model context.
 - Esc stops the current turn at a safe boundary and returns to the prompt. Ctrl-C exits and saves
   the session.
 - Gated tools (file writes, shell, network) prompt for approval: `once` / `always` / `no`.
+- `/mcp` shows the connected servers in this session; `/doctor` checks local setup.
+- `/continue [focus]` continues an unfinished task using its current transcript. `/autonomous on`
+  enables up to five rounds when a task reaches its step ceiling. Checkpoints, a six-hour elapsed
+  limit, stall detection, and Esc cancellation remain active. `/autonomous off` restores one round.
+  Failed rounds are not automatically replayed; provider retry/failover handles request failures.
+- The agent can use `create_skill` in default/coding modes (or with `--tools all`) to create a
+  project playbook with full instructions and an optional slash command. It requires write
+  permission, refuses overwrites, and retains the workspace trust requirement for loading.
 - Coding commands: `/plan [task]`, `/coding`, `/review [focus]`, `/diff [--staged]`,
   `/test [instructions]`, `/init`, `/max-steps [number]`.
 - Quiet output: `/ghost [on|off|status]` hides activity headers and progress for the current
@@ -431,15 +457,11 @@ and tool-step restore; later direct messages and `ask_user` answers cannot be re
 files.
 
 The window defaults to 262,144 tokens and is set with `--context-tokens`, `ULTRAC_MODEL_CONTEXT_TOKENS`,
-or `"contextTokens"` in the config, in that order of precedence. The session banner prints the
-budget it started with:
-
-```
-tools 16 (mode default) ≈ 9,152 chars · window 262,144 tokens · tool results capped at 6,000 chars
-```
+or `"contextTokens"` in the config, in that order of precedence. Use `/context` to inspect the
+current budget. The startup header shows the model, authenticated plan and workspace.
 
 Every `ask`, `run`, and interactive process creates a private `0600` JSONL lifecycle log under
-`.ultrac/logs` and prints its path. It records correlated provider attempts, request heartbeats,
+`.ultrac/logs`. Use `/logs` to see its path in an interactive session. It records correlated provider attempts, request heartbeats,
 first chunks, retries, cancellation, compaction, tools, subagents, and checkpoints. Prompt text,
 tool arguments/results, request bodies, headers, and credentials are replaced by lengths and
 SHA-256 fingerprints; they are never written raw. The directory is ignored by workspace discovery