@spinalfluid/ultrac 0.1.11 → 0.1.18

package/README.md

@@ -142,11 +142,24 @@ 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 the current model, elapsed task time, reported token usage,
-  and estimated context usage. Unreported token counts appear as unknown.
+  run above it. The footer shows only the current model. `/usage` and `/context` show token and context details.
+  Working and tool activity lines show their own live elapsed timers and retain the measured
+  duration when finished. Sub-second durations are hidden. Tool calls stay in a collapsed group directly below the live working timer;
+  click it or press Ctrl+O to expand, then click an action for command and output details. When the
+  task ends, the group moves below its result in the transcript. Working time accumulates across
+  model calls and continuation rounds. Long-running tasks emit brief progress updates based on
+  completed calls and the active tool or model wait. 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
@@ -157,7 +170,8 @@ Inside a 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
+  allows up to five rounds when a task reaches its step ceiling (enabled by default; `/autonomous off`
+  disables continuation). 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
@@ -447,15 +461,11 @@ 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
@@ -744,3 +754,13 @@ ultrac skills create project-check --description "Run project checks" --command
 Edit the generated `SKILL.md` instructions, approve the project workspace, and invoke
 `/project-check` in the terminal. The agent can also write a new `SKILL.md` with its file tools and load it with
 `skill`; normal write and tool permissions still apply.
+
+
+Tool approval presets can be chosen at startup: `ultrac --permissions full` grants file writes,
+shell execution, and network tools without tool approval prompts for that session. Use
+`/permissions full` to enable it inside an existing session. `workspace` grants writes and
+denies shell and network access; `readonly` denies all three permissions. The default mode asks
+when a tool needs an ungranted permission.
+These presets do not bypass operating-system permissions or the restrictions of a read-only
+agent mode. Approval dialogs offer separate choices for one call, the session, denial, or
+session-long refusal, with keyboard selection in interactive terminals.