Documentation
Task workspace
Conversations, the live work log, file changes, the context meter, and what each CLI actually reports about your plan usage.
Every task is a conversation
Tasks are multi-turn, not one-shot. The initial prompt seeds a user turn and each run appends an assistant turn. The output panel renders the thread with a composer at the bottom — press Enter to send a follow-up.
| Agent | How a follow-up continues |
|---|---|
| Claude Code |
Resumes the real CLI session with --resume <sessionId>. Only your new message is sent;
the CLI keeps the history.
|
| Every other agent | Replays the conversation transcript as context, then the new message. |
When a task is stopped, a Next provider selector appears. Switching clears any provider-private resume session, and the next turn receives the full attributed transcript — including cancelled and partial turns. Without an explicit change, later turns stay pinned to the agent you last selected.
The live work log
Frontier parses each CLI's stream into three things: assistant text, the model actually in use, and activity — tool calls and thinking. The result is a running "how it's working" feed rather than a spinner.
-
Claude is fully parsed: the model badge comes from the
system/initevent, text streams token by token, tool calls and thinking arrive as they happen. - Codex is best-effort: command executions, file changes, MCP tool calls, and reasoning become activity; agent messages become text.
- Copilot and Ollama stream plain text, so the model badge falls back to the provider's configured model.
Files changed
Write, Edit, MultiEdit, and NotebookEdit activity is turned into a de-duplicated list of created and edited paths, shown in its own panel.
The task workspace
Open details — or double-click a task — opens a dedicated view with a large conversation pane, the provider route and work log, a task context meter, and a Files & changes tab with syntax-highlighted source and Git working-tree diffs.
The file tree comes from git ls-files --cached --others --exclude-standard when the directory is a
repository, so it respects your project's own .gitignore. Folders start collapsed except the branches
holding this task's changed files. File reads are restricted to paths that task actually touched, enforce workspace
containment, cap text at 1 MB, and identify binaries rather than dumping them.
Context window
Context occupancy is task-scoped and never inferred from cumulative billing usage.
- Claude reports enough per-request data for a live gauge — current conversation occupancy paired with the active model's real context window.
- Codex exposes no dedicated context field, so its per-turn input and output tokens are used as occupancy and paired with the configured or known window. The UI labels this an estimate.
- Agents that report neither show Not reported rather than a fabricated number.
Usage and plan windows
The Usage view shows session and plan usage, reset countdowns, tracked tokens, and automatic-fallback state for every provider. What it can show depends entirely on what each CLI reports:
| Agent | What it reports |
|---|---|
| Claude |
Names the window (for example five_hour → 5-hour), its status, and its reset time — and
no utilisation percentage at all. Frontier therefore shows the window and countdown with a
muted bar tracking elapsed time, explicitly labelled as such. It never invents a usage percentage.
|
| Codex | Carries real percentages, window lengths, and reset times on its token-count events. |
| Copilot / Ollama | Stream no JSON, so they legitimately report nothing. |
Frontier memory
A shared memory block, edited in Settings, is prepended as context to every new task's first turn and to the planner prompt — so project knowledge carries across tasks instead of being retyped. Continuations inherit it through the resumed session.
Working comfortably
- A keyboard-first command palette for navigation, common actions, and task lookup (
⌘K/Ctrl+K). - Image attachments by picker, paste, or drag-and-drop.
@references resolved against the task's selected working directory.- A draggable divider between the work queue and the live output, remembered between sessions.
For what each agent is permitted to do inside your project, see security & data.