> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Slash Commands
> Interactive slash commands for PraisonAI CLI
# Slash Commands
PraisonAI CLI provides interactive slash commands for quick actions during your AI coding sessions. Inspired by Gemini CLI, Codex CLI, and Claude Code, these commands give you powerful control without leaving the terminal.
## Overview
Slash commands start with `/` and provide quick access to common operations in interactive mode.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
❯ /help
❯ /tools
❯ /clear
❯ /exit
```
`/cmd` invokes registered commands. For a one-shot **shell command** in the same session, use `!cmd` (or `!!cmd` to attach output as context) — see [Shell Escape](/docs/docs/features/interactive-shell-escape). The `!` prefix bypasses the command registry entirely.
## Available Commands (Interactive Mode)
When using `praisonai chat`, these commands are available. Installed skills and your custom `.praisonai/commands/*.md` files appear in the same `/` menu alongside these built-ins.
| Command | Description |
| ------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- |
| `/help` | Show available commands and features |
| `/exit` | Exit interactive mode |
| `/quit` | Exit interactive mode (alias) |
| `/clear` | Clear the screen **and** the agent's conversation memory (as of PR #4943 — previously screen-only) |
| `/new` | Start a new conversation — resets both the screen and the agent's conversation history |
| `/import ` | Import a conversation from a file and restore it into the agent's state (not just the screen) |
| `/tools` | List available tools |
| `/profile` | Toggle profiling (show timing breakdown) |
| `/model [name]` | Show or change current model |
| `/plan` | Toggle read-only plan mode (`/plan off` to exit; `/plan ` to plan) |
| `/code-review [file] [--staged]` | Review the uncommitted diff for bugs — see [Code Review & Security Review](/docs/docs/features/interactive-code-review) |
| `/security-review [file] [--staged]` | Review the uncommitted diff against a security rubric (injection, authz, secrets, path traversal, SSRF, crypto) |
| `/btw` | Ask a side question in a throwaway context (`--keep` to note it in history) — see [/btw side question](/docs/features/btw-side-question) |
| `/stats` | Show session statistics (tokens, cost) — every REPL surface |
| `/compact` | Compact the model's `chat_history` (reports tokens/messages freed); also runs automatically at the turn boundary |
| `/compact-display` (alias `/dense`) | Toggle compact output display mode (the old `/compact` behaviour) |
| `/git-status` | Show working-tree status (operator command) |
| `/git-diff [--staged]` | Show the uncommitted diff (operator command) |
| `/git-log [n]` | Show the last `n` commits, default 10 (operator command) |
| `/git-commit [message]` | Stage and commit; message auto-generated when omitted (operator command) |
| `/git-undo` | Undo the last commit, keeping changes in the working tree (operator command) |
| `/map [path]` | Show the repository map (operator command) |
| `/undo` | Undo last turn (files + conversation when checkpointing on — on by default in interactive) |
| `/revert [n]` | Revert the last N turns (files + conversation) |
| `/export [file]` | Export the conversation to a file (session-backed or in-memory fallback) |
| `/queue` | Show queued messages |
| `/queue clear` | Clear the message queue |
| `/queue remove N` | Remove message at index N |
| `/tasks` | List background tasks (id, name, status, progress) |
| `/tasks ` | Show detail for one background task (incl. result/error) |
| `/tasks cancel ` | Cancel a running background task |
## Built-in Tools
Interactive mode includes 5 built-in tools that the AI can use:
| Tool | Description | Risk Level |
| ----------------- | ------------------------- | ---------------------------- |
| `read_file` | Read contents of a file | Low |
| `write_file` | Write content to a file | High (requires approval) |
| `list_files` | List files in a directory | Low |
| `execute_command` | Run shell commands | Critical (requires approval) |
| `internet_search` | Search the web | Low |
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
❯ /tools
Available tools: 5
• read_file
• write_file
• list_files
• execute_command
• internet_search
```
## Usage Examples
### Starting Interactive Mode
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Start interactive mode
praisonai chat
# Or use short flag
praisonai -i
```
### Using Help
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
❯ /help
Commands:
/help - Show this help
/exit - Exit interactive mode
/clear - Clear screen
/tools - List available tools
/profile - Toggle profiling (show timing breakdown)
/model [name] - Show or change current model
/code-review [file|--staged] - Review the uncommitted diff for bugs (read-only)
/security-review [file|--staged] - Audit the uncommitted diff for security issues (read-only)
/stats - Show session statistics (tokens, cost)
/compact - Compact chat_history (auto-runs at the turn boundary too)
/compact-display - Toggle compact output display (alias /dense)
/git-status - Show working-tree status
/git-diff - Show the uncommitted diff
/git-log [n] - Show recent commits
/git-commit [m]- Stage and commit (message auto-generated when omitted)
/git-undo - Undo the last commit (keeps changes staged)
/map [path] - Show the repository map
/undo - Undo last turn (files + conversation when checkpointing on)
/revert [n] - Revert the last N turns (files + conversation)
/queue - Show queued messages
/queue clear - Clear message queue
@ Mentions:
@file.txt - Include file content in prompt
@src/ - Include directory listing
Features:
• File operations (read, write, list)
• Shell command execution
• Web search
• Context compression for long sessions
• Queue messages while agent is processing
```
### Listing Tools
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
❯ /tools
Available tools: 5
• read_file
• write_file
• list_files
• execute_command
• internet_search
```
### Using Tools via Natural Language
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# List files
❯ list files in current folder
Here are the files: README.md, main.py, config.yaml
# Read a file
❯ read the contents of README.md
The file contains: # My Project...
# Search the web
❯ search the web for latest AI news
Here are the results from web search...
```
## Python API
You can also use slash commands programmatically:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai.cli.features import SlashCommandHandler
# Create handler
handler = SlashCommandHandler()
# Check if input is a command
if handler.is_command("/help"):
result = handler.execute("/help")
print(result)
# Get completions for auto-complete
completions = handler.get_completions("/he")
# Returns: ["/help"]
```
### Custom Commands
File-based commands in `.praisonai/commands/*.md` (and `.claude/commands/*.md` / `.agents/commands/*.md` when present) auto-register in interactive mode with `kind=CommandKind.CUSTOM`. Disable discovery with `SlashCommandHandler(discover_custom=False)`. See [Custom Agents & Commands](/docs/features/custom-agents-commands).
## Unified Command Registry
Type `/` at the interactive prompt to see every registered command in one menu — built-ins first, then your `.praisonai/commands/*.md` files, then installed skills (`SkillCommandSource`), then MCP prompts, then any `praisonai.commands` pack. A skill named `my-skill` shows up as `/my-skill` with the skill's own `description` from `SKILL.md` frontmatter, and pressing Enter runs it (the skill body renders as a prompt with any args appended).
Inside `praisonai code` (and the REPL / async TUI) a single `CommandRegistry` aggregates every command source into one `/name` namespace — built-ins, your `.praisonai/commands/*.md` files (plus `.claude/commands/*.md` and `.agents/commands/*.md` when present), skills, MCP prompts, and pip-installed command packs all appear together.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
B[⌨️ Built-ins] --> R[📇 CommandRegistry]
C[📄 .praisonai/commands/*.md
+ .claude / .agents] --> R
S[🧩 Skills] --> R
M[🔌 MCP prompts] --> R
P[📦 praisonai.commands packs] --> R
R --> NS[⚡ /name namespace]
classDef source fill:#189AB4,stroke:#7C90A0,color:#fff
classDef registry fill:#6366F1,stroke:#7C90A0,color:#fff
classDef out fill:#10B981,stroke:#7C90A0,color:#fff
class B,C,S,M,P source
class R registry
class NS out
```
| Source | Where commands come from |
| -------------------------------- | ------------------------------------------------------------------------- |
| `BuiltinCommandSource` | Built-in `/help`, `/undo`, `/sessions`, etc. |
| `CustomCommandSource` | `.praisonai/commands/*.md` files (same path as `praisonai run --command`) |
| `SkillCommandSource` | Skills exposed as `/name` (skips `user-invocable: false`) |
| `MCPPromptCommandSource` | MCP prompts exposed as `/name` |
| `praisonai.commands` entry point | Any pip-installed command pack |
**Not every installed skill appears in the `/` menu.** A skill whose `SKILL.md` frontmatter sets `user-invocable: false` is treated as model-only: the LLM can still auto-trigger it from the system-prompt listing, but it is absent from the completion menu and typing `/` falls through to "Unknown command". See [Skills → Invocation Policy](/docs/features/skills-invocation#invocation-policy) for the full visibility truth table.
### Custom commands work inside `praisonai code`
Create `.praisonai/commands/mydeploy.md`:
```markdown theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
Deploy to {{env}}: run tests, build the image, push to registry.
```
Then invoke it inside the interactive session:
```text theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> /mydeploy staging
```
This runs the exact interpolated template that `praisonai run --command mydeploy staging` would — full parity between interactive and CLI invocation.
### Skills work inside `praisonai code`
Type `/` at the prompt and your installed skills appear in the completion menu next to built-ins and custom commands:
```text theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> /
/help Show help
/clear Clear the screen
/mydeploy staging Deploy to staging: run tests, build...
/my-skill Does a useful thing ← installed skill
/pr-summary Summarise a PR
> /my-skill extra context
```
`/my-skill` renders `SKILL.md`'s body with the user's args appended, matching `praisonai "/my-skill extra context" --skills ./skills/my-skill`.
`/help` lists every discovered command and `command list --all` shows the same unified namespace. Later sources override earlier ones on a name collision, matching user/project override semantics.
Browse and run installed skills from the same menu — see [Skill Invocation → Discover skills in the interactive menu](/docs/features/skills-invocation#discover-skills-in-the-interactive-menu).
### Ship a command pack as a pip package
Register a command source in the `praisonai.commands` entry-point group in `pyproject.toml`:
```toml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
[project.entry-points."praisonai.commands"]
my_commands = "my_package.commands:make_source"
```
The registry discovers it on start — no user code needed. A broken pack is logged and skipped, never taking down the registry.
Register programmatic slash commands:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai.cli.features.slash_commands import (
SlashCommand, SlashCommandHandler, CommandKind
)
# Define custom command
def my_command(args, context):
return {"type": "custom", "message": f"Args: {args}"}
custom_cmd = SlashCommand(
name="mycommand",
description="My custom command",
handler=my_command,
kind=CommandKind.ACTION,
aliases=["mc"]
)
# Register it
handler = SlashCommandHandler()
handler.register(custom_cmd)
# Use it
result = handler.execute("/mycommand arg1 arg2")
```
### Command Context
Provide context for commands that need session data:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai.cli.features.slash_commands import CommandContext
# Create context with session data
context = CommandContext(
total_tokens=5000,
total_cost=0.015,
prompt_count=10,
current_model="gpt-4o",
session_start_time=time.time() - 300
)
# Set context on handler
handler.set_context(context)
# Now /cost will show real data
result = handler.execute("/cost")
```
## Integration with Interactive Mode
Slash commands are automatically available in interactive mode:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai chat
>>> Hello, help me with my code
[AI responds...]
>>> /cost
Session: abc12345
Tokens: 1,500
Cost: $0.0045
>>> /model gpt-4o-mini
Model changed to: gpt-4o-mini
>>> /exit
Goodbye!
```
## Command Reference
### /help
Show help information.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/help # Show all commands
/help # Show help for specific command
```
### /clear and /new
Reset the conversation. As of PR [#4943](https://github.com/MervinPraison/PraisonAI/pull/4943) both clear the **agent's conversation memory** as well as the screen — the old behaviour only wiped the display, leaving the model still holding the prior turns.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/clear # clear screen + agent memory
/new # start a fresh conversation (screen + agent memory)
```
### /import
Restore a conversation from a file into both the screen and the agent's state.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/import chat.json # load messages and rebuild the agent so it remembers them
```
Previously `/import` printed `Imported N messages` and then answered as though none of them existed — the transcript was restored on screen but never plumbed into the agent. It now goes through the same persist + rebuild path as `/continue`.
### /cost
Display session cost and token statistics.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/cost # Show full statistics
```
### /model
Manage the AI model.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/model # Show current model
/model # Change to specified model
```
### /plan
Toggle a persistent **read-only mode** — writes, edits, deletions, and shell commands are denied until you leave the mode.
| Usage | What it does |
| -------------- | ---------------------------------------------------------------------------------------------------------------- |
| `/plan` | Toggle on/off. First call enters read-only mode; second call exits and restores your launch-time policy. |
| `/plan off` | Explicit exit. Writes/edits/commands are allowed again. |
| `/plan ` | Enter read-only mode and produce a step-by-step plan for `` under enforcement. Run `/plan off` to execute. |
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> /plan
[PLAN] Plan mode enabled — read-only. Writes/edits/commands are denied until you /plan off.
> /plan refactor the auth module
[PLAN] Creating plan (read-only) for: refactor the auth module
...
> /plan off
Plan mode disabled. Writes/edits/commands are allowed again.
```
While plan mode is active, the status bar shows `[PLAN]`.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant TUI as praisonai chat
participant Backend as Approval Backend
User->>TUI: /plan
TUI->>Backend: set_permission_mode(PLAN)
Note over TUI: [PLAN] indicator on
User->>TUI: write file X
TUI->>Backend: request_approval(write, ...)
Backend-->>TUI: denied (PLAN)
TUI-->>User: blocked — /plan off to execute
User->>TUI: /plan off
TUI->>Backend: set_permission_mode(launch-time policy)
Note over TUI: [PLAN] indicator off
```
`/plan` flips the live approval backend into `PermissionMode.PLAN`, which unconditionally denies write / edit / delete / bash / shell tool calls. Exiting restores the **launch-time policy** (e.g. `accept-edits`, `bypass`) — not `default` — so a session that started with `--approval accept-edits` keeps that policy after `/plan off`.
Launch a session already in plan mode with `praisonai chat --approval plan` (or `praisonai code --plan`). See [Permission Modes](/docs/features/permission-modes) for the full mode reference.
**Real-world flow:**
Start `praisonai chat` with your default policy.
Type `/plan` — the status bar flips to `[PLAN]` and writes/edits are denied.
Ask `read src/auth/*.py and summarise the auth flow` — the agent uses read-only tools only.
Type `/plan design a fix for the token-refresh bug` — the agent produces a step-by-step plan with no accidental edits mid-plan.
Type `/plan off` — the status bar clears and your launch-time policy returns. Now `apply the plan` writes and edits normally.
### /diff
Show workspace file changes made this session, from the session-start baseline to the working directory.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/diff # all changes since session start
/diff --turn # only the last turn's changes (alias: -t)
/diff # changes to a single file since session start
```
`/diff` is backed by the checkpoint engine, so it requires auto-checkpointing: set `checkpoints.auto: true` in config **or** `PRAISONAI_CHECKPOINTS=on`. When disabled, `/diff` prints an enable hint and does nothing else.
See [Checkpoints](/docs/features/checkpoints) for the underlying engine and the "In-session `/diff`" deep-dive, including the `--turn` vs. session-scope decision guide.
### /commit
Commit changes with an AI-generated message.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/commit # Auto-generate commit message
/commit "message" # Use custom message
```
### /profile
Toggle profiling to see timing breakdown.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/profile # Toggle profiling on/off
```
When enabled, shows timing after each response:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
─── Profiling ───
Import: 0.1ms
Agent setup: 0.3ms
LLM call: 1,234.5ms
Display: 15.2ms
Total: 1,250.1ms
```
### /stats
Show session statistics.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/stats # Show token usage and cost
```
Output:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
Session Statistics
Model: gpt-4o-mini
Requests: 5
Input tokens: 1,234
Output tokens: 2,567
Total tokens: 3,801
Estimated cost: $0.0023
History turns: 10
```
`/stats` works on **every REPL surface** — the legacy REPL, the async TUI (`praisonai code`), and `praisonai chat`. In the async TUI it shares the same renderer as `/cost`, so both print the same panel and you don't need to remember which command works where.
### /compact
Compact the model's own `chat_history` to free context tokens.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/compact # compact chat_history now; reports what it freed
```
This command:
* Compacts the model's `chat_history`, not just the transcript pane.
* Reports what it freed (for example: 120 messages, 240,483 → 94,191 tokens).
* Runs **automatically at the turn boundary** when the session nears its context budget, instead of waiting for the provider to reject the request.
`/compact` used to be a display toggle. That behaviour now lives under `/compact-display` (alias `/dense`). See [Compaction](/docs/cli/compaction).
### /compact-display
Toggle compact output display mode — the old `/compact` behaviour.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/compact-display # toggle dense output
/dense # alias
```
### Git operator commands
Five git operator commands run directly, without the agent deciding to commit. They're **operator** commands, not agent tools.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/git-status # branch + staged/modified/untracked files
/git-diff [--staged] # uncommitted diff (or staged diff)
/git-log [n] # last n commits (default 10)
/git-commit [message] # stage + commit; message auto-generated when omitted
/git-undo # undo the last commit, keeping changes in the tree
```
See [Git Integration → Operator slash commands](/docs/cli/git-integration#operator-slash-commands).
### /map
Show the repository map — an operator overview of an unfamiliar repo, not an agent tool.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/map # map the workspace root
/map src/api # map a specific directory
```
See [Repository Map](/docs/cli/repo-map).
### /undo
Undo the last turn. What `/undo` restores depends on whether checkpointing and the session store are wired in.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/undo # roll back the last turn
```
| Checkpointing | Session store | `/undo` effect |
| ------------------------------------------------------------------------------------------ | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| Off (default) | n/a | Removes the last assistant + user message pair from history. Workspace files untouched. |
| On, no session store | n/a | Restores workspace files to the previous turn's checkpoint. Conversation history untouched (file-only fallback). |
| On, session store wired (**default in `praisonai` interactive mode and `praisonai code`**) | wired | Restores workspace files **and** rewinds `chat_history` to the message boundary captured at `checkpoint_turn()`. Diff preview shown first. |
The deep-dive lives in [Checkpoints → In-session `/undo` and `/revert`](/docs/features/checkpoints).
### /revert
Revert the last N turns — files **and** conversation together. Mirrors `/undo` but takes a turn count.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/revert # roll back the last 1 turn
/revert 3 # roll back the last 3 turns
/revert last # explicit alias for the last 1 turn
```
A diff preview is shown before restore, and `/revert` refuses to run beyond the recorded turn count (`Can only revert 1..N turn(s).`). Checkpointing is on by default in `praisonai` interactive mode and `praisonai code`, so `/revert` works out of the box.
The deep-dive lives in [Checkpoints → In-session `/undo` and `/revert`](/docs/features/checkpoints).
### /export
Export the current conversation to a file — available in the legacy REPL (the surface `praisonai code` runs by default).
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/export # write to a default file (conversation.md)
/export out.md # write to a caller-supplied path
/export out.json # a .json path exports JSON
```
`/export` picks one of two paths automatically:
| Path | When | Result |
| ------------------ | --------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- |
| Session-backed | A session id resolves | Routes through the canonical `session export` renderer — **byte-for-byte identical** to `praisonai session export ` on the CLI. |
| In-memory fallback | No session is persisted (e.g. `--no-session`) | Writes the in-memory chat history so `/export` still produces a transcript instead of failing. |
You don't need to `--session` first — the fallback means `/export` always produces something useful. See [`praisonai session export`](/docs/cli/session#export-a-session) for the same renderer on the CLI.
### /queue
Manage the message queue. Queue messages while the AI agent is processing and they'll be executed in order.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/queue # Show all queued messages
/queue clear # Clear the entire queue
/queue remove N # Remove message at index N
```
Output when messages are queued:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
❯ /queue
⏳ Processing...
Queued Messages (2):
0. ↳ Add docstrings to the function
1. ↳ Create unit tests
Use /queue clear to clear, /queue remove N to remove
```
Type new messages while the agent is processing. They'll be queued and executed automatically in FIFO order.
### /tasks
Inspect and cancel background tasks without leaving the conversation — parity with the CLI-only `praisonai background list`.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
/tasks # List background tasks (id, name, status, progress)
/tasks # Show detail for one task (incl. result/error)
/tasks cancel # Cancel a running task
```
`/tasks` reuses the same process-wide runner (`get_background_runner()`) as `praisonai background list`, so it shows the same tasks across the REPL, TUI, and bots.
When there are no tasks, it prints the empty state:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
❯ /tasks
No background tasks
```
`cancel` stops the **underlying future**, not just the task record — a running task is actually interrupted.
In **bot chats**, `/tasks` is per-user scoped: a caller only ever sees and cancels tasks whose `metadata["user_id"]` matches theirs (fail-closed). See [Bot Chat Commands → /tasks](/docs/features/bot-commands#tasks).
## Best Practices
1. **Use aliases** - `/h` is faster than `/help`
2. **Check costs regularly** - Use `/cost` to monitor spending
3. **Explore unfamiliar code with `/plan` first** - Read-only enforcement prevents accidental writes while you form a plan; run `/plan off` when you're ready to execute
4. **Commit frequently** - Use `/commit` after each logical change
## Related Features
* [Message Queue](/docs/cli/message-queue) - Full message queue documentation
* [Interactive TUI](/docs/cli/interactive-tui) - Full interactive terminal interface
* [Background Tasks](/docs/cli/background) - `/tasks` and `praisonai background list`
* [Cost Tracking](/docs/cli/cost-tracking) - Detailed cost monitoring
* [Git Integration](/docs/cli/git-integration) - Git operations