> ## Documentation Index > Fetch the complete documentation index at: https://platform.stepfun.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Data paths Step Code stores configuration, credentials, sessions, and logs under `~/.stepcode/` by default. Understand the directory layout before backing up or cleaning data. ## Data root | System | Default path | | - | - | | macOS | `/Users//.stepcode` | | Linux | `/home//.stepcode` | | Windows | `C:\Users\\.stepcode` | `~` means your home directory. Agent configuration lives under `~/.stepcode/agent`. `.step-harness` is retired and no longer written; startup only reads old credentials for a one-time migration. ## Directory layout ```text theme={"theme":{"light":"light-plus","dark":"dark-plus"}} ~/.stepcode/ ├── config.toml ├── auth.json ├── models.json ├── .credentials.json ├── device-id ├── models-store.json ├── bin/ ├── logs/ ├── marketplaces/ ├── telemetry/ └── agent/ ├── AGENTS.md ├── prompts/ ├── skills/ ├── agents/ ├── themes/ ├── extensions/ ├── sessions/ ├── trust.json ├── bin/ ├── npm/ └── git/ ``` Some directories are created only when their feature is first used. `bin/` contains the main program and runtime resources; `agent/bin/` contains managed search tools. User directories add `~/.claude/skills` and `~/.stepcode/skills`; project directories add `.claude/skills` within the trusted scan scope. Claude directories are discovered automatically and do not need to be repeated in the `skills` array; non-default directories such as `~/.codex/skills` still require explicit configuration. ## Key files | File | Content | | - | - | | `config.toml` | Global settings and MCP server declarations | | `auth.json` | API keys and OAuth credentials; key values support `!command` and `$VAR` resolution | | `models.json` | Custom models and overrides, reloaded when `/model` opens | | `.credentials.json` | MCP OAuth tokens | | `models-store.json` | Model catalog cache | | `agent/trust.json` | Project trust records | Restrict credential files to the current user. POSIX systems use `0600`; check account-level file permissions on Windows. Do not commit or publicly upload the entire data directory. See [Configuration files](https://platform.stepfun.ai/docs/en/step-code/configuration/files.md) for setting details. ## Session data Sessions live in `agent/sessions//`, one JSONL file per session, containing messages, tool calls, outputs, and summaries. Use `/session` for the exact current path. Use `--session-dir` to select a directory; `sessionDir` and environment variables can also configure defaults. Check `/session` for the effective path. Records contain `id` / `parentId`, with the current position as the active leaf. Compaction summaries, branch summaries, calls, and output share one file. CLM maintains a working copy (`mirror-*/LIVE_CONTEXT.md`) and archive (`archive/`) under `live-context//` in the session directory. Without a session file it writes to a temporary directory. These are not the same files as the original session JSONL. Check related session data when backing up or cleaning, and do not treat the entire archive as short-term cache. See [Sessions and context](https://platform.stepfun.ai/docs/en/step-code/guides/sessions.md). Do not edit internal records directly. ## Built-in tool cache `rg` (ripgrep) and `fd` are downloaded on demand to `~/.stepcode/agent/bin/`, as `rg.exe` / `fd.exe` on Windows. Lookup order is an injected custom path > a downloaded local copy > system PATH. Content search falls back from ripgrep to `git grep` inside Git repositories, then POSIX `grep`. It reports an error when none are available. Deleting the cache may trigger another download. On restricted networks, check system PATH and download access first. ## Logs * `logs/`: runtime logs; start here for startup, connection, and tool errors. * `telemetry/`: telemetry buffers, separate from session records. Logs can include error details and environment information. Review them before sharing. Model calls, MCP, plugins, and deployment access external services as needed. See [Configuration files](https://platform.stepfun.ai/docs/en/step-code/configuration/files.md#telemetry) for telemetry, and [Environment variables](https://platform.stepfun.ai/docs/en/step-code/configuration/environment.md) for proxies and directory overrides. ## Project data | Location | Content | | - | - | | `.stepcode/config.toml` | Project settings; requires trust | | `.stepcode/cron/tasks.json` | Durable scheduled tasks | | `.stepcode/workflows/runs/` | Workflow run records | | `.stepcode/agents/`, `skills/`, `themes/`, `plugins/` | Project resources | | `.stepcode/plans/` | Plan files; `STEP_CODING_AGENT_PLAN_DIR` selects another directory, with relative paths resolved from the working directory; existing sessions keep their saved plan paths and are not migrated automatically | | `.stepcode/npm/` | Project-scoped npm packages | Share configuration and resources according to team conventions. Exclude runtime records, caches, private paths, and credentials; do not add the entire `.stepcode/` directory blindly. ## Cleaning up data > [!WARNING] > > Deleting a project's `.stepcode/` also deletes its configuration, tasks, and custom resources. Exit Step Code and back up required configuration and sessions first. | Goal | Action | | - | - | | Reset configuration | Back up and remove `config.toml` | | Clear sessions | Remove unneeded contents of `agent/sessions/` | | Clear logs | Delete old files in `logs/` | | Redownload search tools | Remove the corresponding tool from `agent/bin/` | | Sign out of a model platform | Use `/logout` | | Clear MCP authorization | `step mcp logout ` | | Clear telemetry buffers | Delete `telemetry/`; this does not disable telemetry | | Refresh the model cache | Back up and remove `models-store.json` | | Remove all data | Back up, delete Step Code's dedicated data directory, and clean up the installer's PATH entry | This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.